Mid Sweden University

miun.sePublications
Change search
Refine search result
12 1 - 50 of 96
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Barac, Filip
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Caiola, Stefano
    Natl Instruments Italy, I-20090 Milan, Italy.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Sisinni, Emiliano
    Univ Brescia, Dept Informat Engn, I-25123 Brescia, Italy.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Channel Diagnostics for Wireless Sensor Networks in Harsh Industrial Environments2014In: IEEE Sensors Journal, ISSN 1530-437X, E-ISSN 1558-1748, Vol. 14, no 11, p. 3983-3995Article in journal (Refereed)
    Abstract [en]

    Wireless sensor network communication in industrial environments is compromised by interference, multipath fading, and signal attenuation. In that respect, accurate channel diagnostics is imperative to selecting the adequate countermeasures. This paper presents the lightweight packet error discriminator (LPED) that infers the wireless link condition by distinguishing between errors caused by multipath fading and attenuation, and those inflicted by interfering wideband single-channel communication systems (e.g., IEEE 802.11b/g), based on the differences in their error footprints. The LPED uses forward error correction in a novel context, namely, to determine the symbol error density, which is then fed to a discriminator for error source classification. The classification criteria are derived from an extensive set of error traces collected in three different types of industrial environments, and verified on a newly collected set of error traces. The proposed solution is evaluated both offline and online, in terms of classification accuracy, speed of channel diagnostics, and execution time. The results show that in ≥91% of cases, a single packet is sufficient for a correct channel diagnosis, accelerating link state inference by at least 270%, compared with the relevant state-of-the-art approaches. The execution time of LPED, for the worst case of packet corruption and maximum packet size, is below 30 ms with ≤3% of device memory consumption. Finally, live tests in an industrial environment show that LPED quickly recovers from link outage, by losing up to two packets on average, which is only one packet above the theoretical minimum.

  • 2.
    Barac, Filip
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Channel Coding and Interleaving in Industrial WSN: Abiding to Timing Constraints and Bit Error Nature2013In: Proceedings - M and N 2013: 2013 IEEE International Workshop on Measurements and Networking, 2013, p. 46-51Conference paper (Refereed)
    Abstract [en]

    Forward Error Correction is a preemptive manner of improving communication reliability. Albeit not a part of IEEE 802.15.4-2006 standard, its application in Industrial Wireless Sensor Networks has been widely considered. Nevertheless, this study is the first performance analysis on real error traces with sufficiently lightweight channel codes, with respect to IEEE 802.15.4-2006 and industrial wireless communication timing constraints. Based on these constraints and bit error properties from the collected traces, the use of Reed-Solomon (15,7) block code is suggested, which can be implemented in software. Experiments show that bit error nature on links affected by multipath fading and attenuation in industrial environments is such that RS(15,7) can correct ≥95% of erroneously received packets, without the necessity for interleaving. On links under IEEE 802.11 interference, typically up to 50% of corrupted packets can be recovered by combining RS(15,7) with symbol interleaving, which has proven to be more effective than its bit counterpart. The optimal interleaving depth is found empirically and it is shown that simple bit-interleaved 1/3 repetition code achieves at least 90% of correcting performance of RS(15,7) code on uninterfered links that operate ≥10 dB above the sensitivity threshold.

  • 3.
    Barac, Filip
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    CLAP: Chip-Level Augmentation of IEEE 802.15.4 PHY for Error-Intolerant WSN Communication2015In: IEEE Vehicular Technology Conference, Glasgow, Scotland: IEEE Vehicular Technology Society , 2015, p. 1-7Conference paper (Refereed)
    Abstract [en]

    Communication reliability is the ultimate priority in safety-critical wireless sensor network (WSN) communication. Surprisingly enough, the enormous potential of error control on direct sequence spread spectrum (DSSS) chips in IEEE 802.15.4 has been completely overlooked by the WSN community, possibly due to incorrect presumptions, such as the concerns about computational overhead. Current error-correction schemes in WSN counteract the error process once the errors have already propagated to bit- and packet-level. Motivated by the notion that errors should be confronted at the earliest stage, this work presents CLAP, a novel method that tremendously improves the error correction in WSN by fortifying the IEEE 802.15.4 Physical layer (PHY) with straightforward manipulations of DSSS chips. CLAP is implemented on a software-defined radio platform, and evaluated on real error traces from heavily WLAN-interfered IEEE 802.15.4 transmissions at 3 different environments. CLAP boosts the number of corrected packets by 1.78-6.88 times on severely interfered links, compared to two other state-of-the-art schemes. The overhead in terms of computational complexity is about 10% of execution time of the OQPSK demodulator in the legacy IEEE 802.15.4 receiver chain.

  • 4.
    Barac, Filip
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    LPED: Channel Diagnostics in WSN Through Channel Coding and Symbol Error Statistics2014In: IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings, Singapore: IEEE Sensors Council, 2014, p. 1-6Conference paper (Refereed)
    Abstract [en]

    Three major obstacles to wireless communication are electromagnetic interference, multipath fading and signal attenuation. The former stems mainly from collocated wireless systems operating in the same frequency band, while the latter two originate from physical properties of the environment. Identifying the source of packet corruption and loss is crucial, since the adequate countermeasures for different types of threats are essentially different. This problem is especially pronounced in industrial monitoring and control applications, where IEEE 802.15.4 communication is expected to deliver data within tight deadlines, with minimal packet loss. This work presents the Lightweight Packet Error Discriminator (LPED) that distinguishes between errors caused by multipath fading and attenuation, and those inflicted by IEEE 802.11 interference. LPED uses Forward Error Correction to determine the symbol error positions inside erroneously received packets and calculates the error density, which is then fed to a discriminator for error source classification. The statistical constituents of LPED are obtained from an extensive measurement campaign in two different types of industrial environments. The classifier incurs no overhead and in ≥90% of cases a single packet is sufficient for a correct channel diagnosis. Experiments show that LPED accelerates link diagnostics by at least 190%, compared to the relevant state-of-the-art approaches.

  • 5.
    Barac, Filip
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    PREED: Packet Recovery by Exploiting the Determinism in Industrial WSN Communication2015In: Proceedings - IEEE International Conference on Distributed Computing in Sensor Systems, DCOSS 2015, Fortaleza, Brazil: IEEE Computer Society, 2015, p. 81-90Conference paper (Refereed)
    Abstract [en]

    The requirements of safety-critical wireless sensornetwork (WSN) applications, such as closed-loop control andtraffic safety, cannot be met by the IEEE 802.15.4-2006 standardnor its industrial WSN (IWSN) derivatives. The main problem inthat respect is the communication reliability, which is seriouslycompromised by 2.4-GHz interference, as well as multipathfading and attenuation (MFA) at industrial facilities. Meanwhile,communication blackouts in critical WSN applications maylead to devastating consequences, including production halts,damage to production assets and can pose a threat to safetyof human personnel. This work presents PREED, a method toimprove the reliability by exploiting the determinism in IWSNcommunication. The proposed solution is based on the analysisof bit error traces collected in real transmissions at four differentindustrial environments. A case study on WirelessHART packetformat shows that PREED recovers 42%-134% more packetsthan the competing approaches on links compromised by WLANinterference. In addition, PREED reduces one of the most trivialcauses of packet loss in IWSN, i.e. the corruption offrame lengthbyte, by 88% and 99%, for links exposed to WLAN interferenceand MFA, respectively.

  • 6.
    Barac, Filip
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems. ABB Corp Res, S-72178 Vasteras, Sweden.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Scrutinizing Bit- and Symbol-Errors of IEEE 802.15.4 Communication in Industrial Environments2014In: IEEE Transactions on Instrumentation and Measurement, ISSN 0018-9456, E-ISSN 1557-9662, Vol. 63, no 7, p. 1783-1794Article in journal (Refereed)
    Abstract [en]

    The knowledge of error nature in wireless channels is an essential constituent of efficient communication protocol design. To this end, this paper is the first comprehensive bit- and symbol-level analysis of IEEE 802.15.4 transmission errors in industrial environments. The intention with this paper is to extract the error properties relevant for future improvements of wireless communication reliability and coexistence of radio systems in these harsh conditions. An extensive set of bit-error traces was collected in a variety of scenarios and industrial environments, showing that error behavior is highly dependent on the cause of packet corruption. It is shown that errors inflicted by multipath fading and attenuation exhibit different properties than those imposed by IEEE 802.11 interference. The statistical behavior of these two patterns is concurrently investigated in terms of differences in bit-error distribution, error burst length, channel memory length, and the scale of packet corruption. With these conclusions at hand, abiding to the computational constraints of embedded sensors and the statistical properties of bit-errors, a Reed-Solomon $(15,k)$ block code is chosen to investigate the implications of bit-error nature on practical aspects of channel coding and interleaving. This paper is concluded by a number of findings of high practical relevance, concerning the optimal type, depth, and meaningfulness of interleaving.

  • 7.
    Barac, Filip
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Ubiquitous, yet Deceptive: Hardware-Based Channel Metrics on Interfered WSN Links2015In: IEEE Transactions on Vehicular Technology, ISSN 0018-9545, E-ISSN 1939-9359, Vol. 64, no 5, p. 1766-1778Article in journal (Refereed)
    Abstract [en]

    The ease of acquiring hardware-based link quality indicators is an alluring property for fast channel estimation in time- and safety-critical Wireless Sensor Network (WSN) applications, such as closed-loop control and interlocking. The two rudimentary hardware-based channel quality metrics, Received Signal Strength (RSS) and Link Quality Indicator (LQI), are the key constituents of channel estimation and a plethora of other WSN functionalities, from routing to transmit power control. Nevertheless, this study highlights three deficient aspects of these two indicators: 1) overall deceptiveness, i.e. the inability to reveal the presence of interference, falsely indicating excellent channel conditions in an unacceptably high fraction of cases; 2) the burstiness of missed detections, which compromises the attempts to eliminate the deceptiveness by averaging; 3) high mutual discrepancy of the two indicators, observed in 39-73% of packets, throughout different scenarios. The ability of RSS and LQI to indicate IEEE 802.11 interference is scrutinized in a variety of scenarios in typical industrial environments, using commercialoff- the-shelf hardware and realistic network topologies, giving the findings of this study a high general validity and practical relevance.

  • 8.
    Barac, Filip
    et al.
    Ericsson AB.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Sisinni, Emiliano
    University of Brescia.
    Error Manifestation in Industrial WSN Communication and Guidelines for Countermeasures2017In: Wireless Sensor Systems for Extreme Environments: Space, Underwater, Underground and Industrial / [ed] H. F. Rashvand and A. Abedi, John Wiley & Sons, 2017Chapter in book (Refereed)
  • 9.
    Dobslaw, Felix
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Zhang, Tinting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Challenges for the use of data aggregation in industrial Wireless Sensor Networks2015In: IEEE International Conference on Automation Science and Engineering, IEEE Computer Society, 2015, p. 138-144Conference paper (Refereed)
    Abstract [en]

    The provision of quality of service for Wireless Sensor Networks is more relevant than ever now where wireless solutions with their flexibility advantages are considered for the extension/substitution of wired networks for a multitude of industrial applications. Scheduling algorithms that give end-to-end guarantees for both reliability and latency exist, but according to recent investigations is the achieved quality of service insufficient for most control applications. Data aggregation is an effective tool to significantly improve on end-to-end contention and energy efficiency compared to single packet transmissions. In practice, though, it is not extensively used for process data processing on the MAC layer. In this paper, we outline the challenges for the use of data aggregation in Industrial Wireless Sensor Networks. We further extend SchedEx, a reliability-aware scheduling algorithm extension, for packet aggregation. Our simulations for scheduling algorithms from the literature show its great potential for industrial applications. Features for the inclusion of data aggregation into industrial standards such as WirelessHART are suggested, and remaining open issues for future work are presented and discussed.

  • 10.
    Dobslaw, Felix
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science.
    Tingting, Zhang
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Latency Improvement Strategies for Reliability-Aware Scheduling in Industrial Wireless Sensor Networks2015In: International Journal of Distributed Sensor Networks, ISSN 1550-1329, E-ISSN 1550-1477, Vol. 2015, p. 1-10, article id 178368Article in journal (Refereed)
    Abstract [en]

    We propose novel strategies for end-to-end reliability-aware scheduling in Industrial Wireless Sensor Networks (IWSNs). Becauseof stringent reliability requirements in industrial applications where missed packets may have disastrous or lethal consequences,all IWSN communication standards are based on Time Division Multiple Access (TDMA), allowing for deterministic channelaccess on the MAC layer. We therefore extend an existing generic and scalable reliability-aware scheduling approach by the name ofSchedEx. SchedEx has proven to quickly produce TDMA schedules that guarantee a user-defined end-to-end reliability level 𝜌 for allmultihop communication in a WSN. Moreover, SchedEx executes orders of magnitude faster than recent algorithms in the literaturewhile producing schedules with competitive latencies. We generalize the original problem formulation from single-channel tomultichannel scheduling and propose a scalable integration into the existing SchedEx approach. We further introduce a noveloptimal bound that produces TDMA schedules with latencies around 20% shorter than the original SchedEx algorithm. Combiningthe novel strategies with multiple sinks, multiple channels, and the introduced optimal bound, we could through simulations verifylatency improvements by almost an order of magnitude, reducing the TDMA superframe execution times from tens of seconds toseconds only, which allows for a utilization of SchedEx for many time-critical control applications.

    Download full text (pdf)
    fulltext
  • 11.
    Dobslaw, Felix
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    A Reliability-Aware Cross-layer Optimization Framework for Wireless Sensor Networks.Manuscript (preprint) (Other academic)
    Abstract [en]

    One of the biggest obstacles for a broad deploymentof Wireless Sensor Networks for industrial applications is the dif-ficulty to ensure end-to-end reliability guarantees while providingas tight latency guarantees as possible. In response, we proposea novel centralized optimization framework for Wireless SensorNetworks that identifies TDMA schedules and routing combi-nations in an integrated manner. The framework is shown toguarantee end-to-end reliability for all events send in a schedulingframe while minimizing the delay of all packet transmissions. Itcan further be applied using alternative Quality of Service ob-jectives and constraints including energy efficiency and fairness.We consider network settings with multiple channels, multiplesinks, and stringent reliability constraints for data collectingflows. We compare the results to those achieved by the onlyscalable reliability-aware TDMA scheduling algorithm to ourknowledge, SchedEx, which conducts scheduling only. By makingrouting part of the problem and by introducing the conceptof source-aware routing, we achieve latency improvements forall topologies, with a notable average improvement of up to31percent.

  • 12.
    Dobslaw, Felix
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    End-to-End Reliability-aware Scheduling for Wireless Sensor Networks2016In: IEEE Transactions on Industrial Informatics, ISSN 1551-3203, E-ISSN 1941-0050, Vol. 12, no 2, p. 758-767Article in journal (Refereed)
    Abstract [en]

    Wireless Sensor Networks (WSN) are gaining popularity as a flexible and economical alternative to field-bus installations for monitoring and control applications. For missioncritical applications, communication networks must provide endto- end reliability guarantees, posing substantial challenges for WSN. Reliability can be improved by redundancy, and is often addressed on the MAC layer by re-submission of lost packets, usually applying slotted scheduling. Recently, researchers have proposed a strategy to optimally improve the reliability of a given schedule by repeating the most rewarding slots in a schedule incrementally until a deadline. This Incrementer can be used with most scheduling algorithms but has scalability issues which narrows its usability to offline calculations of schedules, for networks that are rather static. In this paper, we introduce SchedEx, a generic heuristic scheduling algorithm extension which guarantees a user-defined end-to-end reliability. SchedEx produces competitive schedules to the existing approach, and it does that consistently more than an order of magnitude faster. The harsher the end-to-end reliability demand of the network, the better SchedEx performs compared to the Incrementer. We further show that SchedEx has a more evenly distributed improvement impact on the scheduling algorithms, whereas the Incrementer favors schedules created by certain scheduling algorithms.

  • 13.
    Dobslaw, Felix
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    QoS Assessment for Mission-critical Wireless Sensor Network Applications2013In: Proceedings - Conference on Local Computer Networks, LCN / [ed] Matthias Wählisch, IEEE Xplore , 2013, p. 663-666Conference paper (Refereed)
    Abstract [en]

    Wireless sensor networks (WSN) must ensure worst-case end-to-end delay and reliability guarantees for mission-critical applications.TDMA-based scheduling offers delay guarantees, thus it is used in industrial monitoring and automation. We propose to evolve pairs of TDMA schedule and routing-tree in a cross-layer in order to fulfill multiple conflicting QoS requirements,exemplified by latency and reliability.The genetic algorithm we utilize can be used as an analytical tool for both the feasibility and expected QoS in production. Near-optimal cross-layer solutions are found within seconds and can be directly enforced into the network.

  • 14.
    Dobslaw, Felix
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    QoS-Aware Cross-layer Configuration for Industrial Wireless Sensor Networks2016In: IEEE Transactions on Industrial Informatics, ISSN 1551-3203, E-ISSN 1941-0050, Vol. 12, no 5, p. 1679-1691, article id 7485858Article in journal (Refereed)
    Abstract [en]

    In many applications of Industrial Sensor Networks, stringentreliability and maximum delay constraints paired with priority demands ona sensor-basis are present. These QoS requirements pose tough challenges forIndustrial Wireless Sensor Networks that are deployed to an ever largerextent due to their flexibility and extendibility.In this paper, we introduce an integrated cross-layer framework, SchedEx-GA, spanning MAC layer and networklayer. SchedEx-GA attempts to identify a network configuration that fulfills all application-specific process requirements over a topology including the sensorpublish rates, maximum acceptable delay, service differentiation, and eventtransport reliabilities. The network configuration comprisesthe decision for routing, as well as scheduling.

    For many of the evaluatedtopologies it is not possible to find a valid configuration due to the physicalconditions of the environment. We therefore introduce a converging algorithm on top of the frameworkwhich configures a given topology by additional sink positioning in order tobuild a backbone with the gateway that guaranteesthe application specific constraints.The results show that, in order to guarantee a high end-to-end reliability of 99.999% for all flows in a network containing emergency, control loop, andmonitoring traffic, a backbone with multiple sinks is often required for thetested topologies. Additional features, such as multi-channel utilization andaggregation, though, can substantially reduce the demand for required sinks.In its present version, the framework is used for centralized control, butwith the potential to be extended for de-centralized control in future work.

  • 15.
    Forsström, Stefan
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Danielski, Itai
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Ecotechnology and Suistainable Building Engineering.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Jennehag, Ulf
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Collecting Indoor Environmental Sensor Values for Machine Learning Based Smart Building Control2021In: 2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS), IEEE, 2021, p. 37-43Conference paper (Refereed)
    Abstract [en]

    This research presents a solution for collecting indoor environmental sensor values and how the gathered sensor values then could be used for green building certification and in turn also machine learning based smart building control. We have created and implemented a proof of concept system consisting of a sensor collecting device using off the shelf hardware to complement the existing sensor information from buildings, as well as a cloud system for persistently storing this data for later usage. We have measured and evaluated our implemented system for our envisioned scenarios. In which we could observe that our proof-of-concept could scale to handle almost four sensor value updates per second at maximum stress, as well as having a latency for uploading a sensor value from our sensor of about 130 ms. Finally, we present our future and ongoing work based on these results which outlines our work for smart building control, green building certification, and the energy signature of buildings. 

  • 16.
    Fält, Markus
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Forsström, Stefan
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    He, Qing
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Learning-Based Anomaly Detection Using Log Files with Sequential Relationships2022In: 6th International Conference on System Reliability and Science, Venice, Italy, 23-25 Nov. 2022, 2022, p. 337-342Conference paper (Refereed)
    Abstract [en]

    Modern IT systems have been transitioning from traditional on-premises solutions to a dynamic mixture of on-premises and off-premises solutions. This transition has also included a trend to run more systems on software-defined resources. The ease of setting up new software-defined servers and systems has led to an increase in IT system complexity as well as the amount of log data generated. Automatic log analysis has become a subject of interest because of the problems with manual log analysis in case of intrusion detection and root-cause analysis. Therefore, this paper proposes and tests a sequence based anomaly detection method. The work has been done in collaboration with the Swedish Social Insurance Agency's IT department. Real system log data with high privacy requirements and limited available information was generated for training and testing. The generated log data was produced with expected time regions of anomalous behavior. Our proposed anomaly detection model was then able to perform at a state-of-the-art level and could accurately detect certain error types. Showing the potential of the approach when applied directly to a real-world system.

  • 17.
    Fält, Markus
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology. Försäkringkassan, ITPBM Systems Management, Sundsvall, Sweden.
    Forsström, Stefan
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Machine Learning Based Anomaly Detection of Log Files Using Ensemble Learning and Self-Attention2021In: 5th International Conference on System Reliability and Science, Palermo, Italy, 24-26 Nov. 2021, 2021, p. 209-215Conference paper (Refereed)
    Abstract [en]

    Modern enterprise IT systems generate large amounts of log data to record system state, potential errors, and performance metrics. Manual analysis of log data is becoming more difficult as these systems become more complex. Therefore, machine learning based anomaly detection of system logs is a vital component for the future of system management. Existing log anomaly detection models commonly rely on learning the general normal behavior of the target systems to accurately detect anomalies. They are however limited by the often sparse existing system knowledge. Therefore, this paper proposes a general anomaly detection method which requires little or no knowledge of the target system. This is done by assuming there are semantic similarities in different systems’ log data. Labeled log data from other systems can then be used for training the anomaly detection model. The model uses self-attention transformers and ensemble learning techniques to learn the semantic representation of normal and abnormal log messages. The proposed method achieves a performance comparable to other log anomaly detection methods while requiring little knowledge of the target system.

    Download full text (pdf)
    fulltext
  • 18.
    Gidlund, Mikael
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Yang, Dong
    Beijing Jiatong University.
    Xu, Youzhi
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Shen, Wei
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Wireless communication method and system with collision avoidance protocol2015Patent (Other (popular science, discussion, etc.))
    Abstract [en]

    The invention concerns a method for providing wireless communication between a source node and a destination node in a wireless network wherein said wireless network uses a time division multiple access (TDMA) protocol. One or more dedicated TDMA transaction timeslots (60-71) are arranged in a superframe. The superframe comprises at least one dedicated transaction slot forming a hybrid protocol with two or more shared transaction slots 50 per superframe. The method is of particular advantage when practised with a WirelessHART protocol wireless sensor network and when used for monitoring and control equipment and processes in an industrial installation. A computer program, and a wireless node and a wireless network using the inventive method are also disclosed.

  • 19.
    Hassan, Ali
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Sjöström, Mårten
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Egiazarian, Karen
    Light-Weight EPINET Architecture for Fast Light Field Disparity Estimation2022In: Light-Weight EPINET Architecture for Fast Light Field Disparity Estimation: 26-28 Sept. 2022, Shanghai, China, Shanghai, China: IEEE Signal Processing Society, 2022, p. 1-5Conference paper (Refereed)
    Abstract [en]

    Recent deep learning-based light field disparity estimation algorithms require millions of parameters, which demand high computational cost and limit the model deployment. In this paper, an investigation is carried out to analyze the effect of depthwise separable convolution and ghost modules on state-of-the-art EPINET architecture for disparity estimation. Based on this investigation, four convolutional blocks are proposed to make the EPINET architecture a fast and light-weight network for disparity estimation. The experimental results exhibit that the proposed convolutional blocks have significantly reduced the computational cost of EPINET architecture by up to a factor of 3.89, while achieving comparable disparity maps on HCI Benchmark dataset.

    Download full text (pdf)
    fulltext
  • 20.
    Huang, X.
    et al.
    Department of Computer Science, University of Oxford, Oxford, United Kingdom.
    Fu, R.
    China Information Technology Security Evaluation Center, Beijing, China .
    Chen, B.
    Department of Computer Science, University of Oxford, Oxford, United Kingdom .
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Roscoe, A. W.
    Department of Computer Science, University of Oxford, Oxford, United Kingdom .
    User interactive Internet of things privacy preserved access control2012In: 2012 International Conference for Internet Technology and Secured Transactions, ICITST 2012, IEEE conference proceedings, 2012, p. 597-602Conference paper (Refereed)
    Abstract [en]

    The Internet of Things (IoT) is a network of objects; it is enabled by the Internet technologies. The IoT always collects sensitive data, but inadequate protection may lead to serious user privacy leakage. Thus, privacy protection functions are important to the IoT. Our research aims to provide better privacy protections to IoTs. Firstly, user controlled privacy preserved access control protocol is proposed. Secondly, context aware k-anonymity privacy policy and filter are designed. Thirdly, privacy protection mechanisms are investigated, and the privacy protection mechanisms are improved based on the investigation results. Therefore, users can control which of their personal data is being collected and accessed, who is collecting and accessing such data, and when these are happening. © 2012 Infonomics Society.

  • 21.
    Huang, Xin
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Jiang, Yang
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Gao, Xiong
    Gu, Rong
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Sensor Aided Authentication2010In: Communications in Computer and Information Science Volume 76 CCIS, 2010, Springer, 2010, p. 265-277Conference paper (Refereed)
    Abstract [en]

    The sharing of sensor data globally becomes possible by the development of wireless sensor network, cloud computing, and other related technologies. These new trends can also benefit information security. In this paper, the sensor data is involved in the authentication procedure which is one main component of security systems. Sensor aided password is proposed. In addition, the architecture for sensor aided authentication corresponding to the simple authentication scenario is also designed. Sensor data aided password generation and utilization bring convenience to users without weakening the password strength.

  • 22.
    Huang, Xin
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Jiang, Yang
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Kanter, Theo
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Privacy for mHealth Presence2010In: International Journal of Next-Generation Networks, ISSN 0975-7252, E-ISSN 0975-7023, Vol. 2, no 4, p. 33-44Article in journal (Refereed)
    Abstract [en]

    mHealth data provision focuses on providing health services to patients via mobile devices and presence technologies. It has great influence to the healthcare business today, especially in the developing countries. However, the mHealth presence might be sensitive; and it brings potential privacy issues. For controlling what presence information can be given to which watcher, and when in mHealth presence service, XML Configuration Access Protocol (XCAP) is introduced. Nevertheless, it is not enough if only XCAP is applied. It just controls the direct privacy leakage; indirect flow might still leak the privacy information. Thus, presence authorization policy and privacy filter, which are components of XCAP, are improved based on k-anonymity for stopping indirect privacy leakage.

  • 23.
    Huang, Xin
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Natural Sciences, Engineering and Mathematics.
    Yin, He
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Natural Sciences, Engineering and Mathematics.
    Yifan, Hou
    Lisi, Li
    Lan, Sun
    Sina, Zhang
    Yang, Jiang
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Natural Sciences, Engineering and Mathematics.
    Privacy of Value-Added Context-Aware Service Cloud2009In: Lecture notes in computer science Volume 5931, Springer, 2009, Vol. 5931, p. 547-552Conference paper (Refereed)
    Abstract [en]

    In the cloud computing era, service provider cloud and context service cloud store all your personal context data. This is a positive aspect for value-added context-aware service cloud as it makes that context information collection are easier than was the case previously. However, this computing environment does add a series of threats in relation to privacy protection. Whoever receives the context information is able to deduce the status of the owners and, generally owners are not happy to share this information. In this paper, we propose a privacy preserved framework which can be utilized by value-added context-aware service cloud. Context data and related services access privileges are determined by context-aware role-based access control (CRAC) extended from role-based access control (RAC). Privacy preserved context service protocol (PPCS) is designed to protect user privacy from exposed context information. Additionally, user network and information diffusion is combined to evaluate the privacy protection effect.

  • 24.
    Huang, Xin
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Privacy and Security Aware Home Sensor System2010In: 2010 Cross-Strait Conference on Information Science and Technology, CSCIST 2010, Qinghuangdao, China, July, 2010, Scientific Research Publishing, 2010Conference paper (Refereed)
  • 25. Huang, Xin
    et al.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Natural Sciences, Engineering and Mathematics.
    Hou, Yifan
    ID management among clouds2009In: 2009 1st International Conference on Future Information Networks, ICFIN 2009, IEEE conference proceedings, 2009, p. 237-241Conference paper (Refereed)
    Abstract [en]

    In the following years, the desktop-based applications will be changed to cloud computing gradually. Since all users' profile and context data will be stored on the service supplier side based on their ID. ID is becoming a security bottleneck: attackers can trace all other information via user ID. Increasingly, a simple service may be involved in a chain of service clouds; each cloud is able to access data in its cloud without the control of any technology. With ID and password cross utilization in clear text, leakage of ID profile and password in one cloud may propagate to the whole cloud chain. Without proper protection, the success of cloud computing will be threatened by ID privacy leakage. In this paper, privacy preserved ID profile utilizing protocol (PPID) is proposed to prevent this privacy flaw. PPID together with its extension ID anonymity protocol (IDA) separate ID and services. With these two protocols, threaten from crash of whole cloud chain caused by ID privacy leakage is minimized.

  • 26.
    Huang, Xin
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Sun, Lan
    Outer System Flow Privacy Protection2010In: 2010 IEEE International Systems Conference Proceedings, SysCon 2010, IEEE conference proceedings, 2010, p. 117-120Conference paper (Refereed)
    Abstract [en]

    Nowadays, social networks, information networks and technological networks have already become main media of information publication and exchange. Meanwhile, the information diffusion in these networks is well studied. However, most privacy protection technologies, e.g., access control, have not considered the influence of these networks systematically. In this paper, a concept of outer system flow privacy control is proposed. In addition, system privacy requirements are reconsidered. Furthermore, in user case, role base access control (RBAC) is analyzed and improved based on the outer system flow control

  • 27.
    Jennehag, Ulf
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Increasing bandwidth utilization in next generation IPTV networks2004In: ICIP: 2004 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1- 5, IEEE conference proceedings, 2004, p. 2075-2078Conference paper (Refereed)
    Abstract [en]

    In this paper we present a novel idea regarding transmission of next generation IPTV content. Today IPTV systems utilize a COP structure tu provide stream synchronization points for the clients, these are used when a channel switch occur. Since channel switches made by TV audiences are quite rare it is redundant to send synchronization opportunities in a GOP manner. The proposed design, synchronization frames fur channel switching (SFCS), only requests synchronization frames when needed. We present a network traffic analysis model and compare it with simulations. SFCS increases bandwidth utilization compared to traditional COP system under the presented transmission environment.

  • 28.
    Jennehag, Ulf
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Pettersson, Stefan
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Improving transmission efficiency in H.264 based IPTV systems2007In: IEEE transactions on broadcasting, ISSN 0018-9316, E-ISSN 1557-9611, Vol. 53, no 1, p. 69-78Article in journal (Refereed)
    Abstract [en]

    In this paper, a novel proposal regarding the transmission of the next generation of live-TV content in an IPTV environment is presented. Today live-TV IP transmission systems utilizes a Group Of Pictures (GOP) structure in order to provide stream synchronization points for the clients. Synchronization points are used when a TV-channel switch occurs. The number of channel switches made by TV audiences have been shown to be rather rare. It is therefore redundant to send synchronization events in a GOP manner. Our proposal, Synchronization Frames for Channel Switching (SFCS), only requests synchronization points when required. Due to channel popularity distributions and the number of connected users, the total number of synchronization requests for a popular channel can increase to a level that makes SFCS less effective than GOP. Therefore, we introduce an SFCS-GOP hybrid. A complete network traffic analysis model, verified by a simple simulation environment, is also presented and the results show that the SFCS-GOP hybrid significantly increases the bandwidth utilization compared to a traditional GOP system

  • 29.
    Lavassani, Mehrzad
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Barac, Filip
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Handling Event-Triggered Traffic of Safety and Closed-Loop Control Systems in WSANs2016In: 14th IEEE International Conference on Industrial Informatics (INDIN'16), IEEE, 2016, p. 631-636, article id 7819237Conference paper (Refereed)
  • 30.
    Lavassani, Mehrzad
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Forsström, Stefan
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Jennehag, Ulf
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Combining Fog Computing with Sensor Mote Machine Learning for Industrial IoT2018In: Sensors, E-ISSN 1424-8220, Vol. 18, no 5, article id 1532Article in journal (Refereed)
    Abstract [en]

    Digitalization is a global trend becoming ever more important to our connected and sustainable society. This trend also affects industry where the Industrial Internet of Things is an important part, and there is a need to conserve spectrum as well as energy when communicating data to a fog or cloud back-end system. In this paper we investigate the benefits of fog computing by proposing a novel distributed learning model on the sensor device and simulating the data stream in the fog, instead of transmitting all raw sensor values to the cloud back-end. To save energy and to communicate as few packets as possible, the updated parameters of the learned model at the sensor device are communicated in longer time intervals to a fog computing system. The proposed framework is implemented and tested in a real world testbed in order to make quantitative measurements and evaluate the system. Our results show that the proposed model can achieve a 98% decrease in the number of packets sent over the wireless link, and the fog node can still simulate the data stream with an acceptable accuracy of 97%. We also observe an end-to-end delay of 180 ms in our proposed three-layer framework. Hence, the framework shows that a combination of fog and cloud computing with a distributed data modeling at the sensor device for wireless sensor networks can be beneficial for Industrial Internet of Things applications.

    Download full text (pdf)
    fulltext
  • 31.
    Li, Jiyun
    et al.
    Donghua University, Shanghai, China.
    Mei, Zhijie
    Donghua University, Shanghai, China.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    A method for document image enhancement to improve template-based classification2020In: ACM International Conference Proceeding Series, ACM Digital Library, 2020, p. 87-91Conference paper (Refereed)
    Abstract [en]

    Document classification is one of the significant procedure in paper document recognition. This article proposed a method for document image enhancement to improve the performance of classification in the convolutional neural network. An enhanced document image was generated by extracting the table frame, text region, and shape of the raw document. The template-based classification experiment on 414 customs documents and more than one thousand generated images showed the enhanced image could help CNN model achieve higher accuracies compared to the original images. It could also diminish the interference of noise and unrelated features in document classification optimizing the robustness of networks. The proposed method also demonstrated the channels of the image could provide more information except for color in deep neural networks. As the similarity in the whole image classification tasks, the conclusion might provide ideas for the training of the neural networks in other fields such as street view recognition, medical image recognition, etc. 

  • 32.
    Lin, Yeqiang
    et al.
    Donghua Univ, Dept Comp Sci & Technol, Shanghai, Peoples R China.
    Lavassani, Mehrzad
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Li, Jiyun
    Donghua Univ, Dept Comp Sci & Technol, Shanghai, Peoples R China.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    PixVid: Capturing Temporal Correlated Changes in Time Series2017In: Proceedings - 5th International Conference on Advanced Cloud and Big Data, CBD 2017, 2017, p. 337-342, article id 8026960Conference paper (Refereed)
    Abstract [en]

    Time series is one of the main research domains in variety of disciplines. Visualization is an important mechanism to present the raw data as well as the processed time series for further analysis. Many successful visualization techniques have been reported recently. However, most of these techniques display data statically, intending to show as much information as possible by one image or plot. We propose PixVid, a visualization technique which orders the dimensions by constructing a hierarchal dimension cluster tree, and then uses a pixel-oriented technique to form images and displays the data in video format.

  • 33.
    Lindén, Johannes
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Forsström, Stefan
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Evaluating Combinations of Classification Algorithms and Paragraph Vectors for News Article Classification2018In: Proceedings of the 2018 Federated Conference on Computer Science and Information Systems / [ed] Maria Ganzha, Leszek Maciaszek, Marcin Paprzycki, Warzaw: Polskie Towarzystwo Informatyczne , 2018, p. 489-495, article id 8511213Conference paper (Refereed)
    Abstract [en]

    News companies have a need to automate and make the process of writing about popular and new events more effective. Current technologies involve robotic programs that fill in values in templates and website listeners that notify editors when changes are made so that the editor can read up on the source change on the actual website. Editors can provide news faster and better if directly provided with abstracts of the external sources and categorical meta-data that supports what the text is about. In this article, the focus is on the importance of evaluating critical parameter modifications of the four classification algorithms Decisiontree, Randomforest, Multi Layer perceptron and Long-Short-Term-Memory in a combination with the paragraph vector algorithms Distributed Memory and Distributed Bag of Words, with an aim to categorise news articles. The result shows that Decisiontree and Multi Layer perceptron are stable within a short interval, while Randomforest is more dependent on the parameters best split and number of trees. The most accurate model is Long-Short-Term-Memory model that achieves an accuracy of 71%.

  • 34.
    Lindén, Johannes
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Wang, Xutao
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Forsström, Stefan
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Bilingual Auto-Categorization Comparison of two LSTM Text Classifiers2019In: 2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI), 2019Conference paper (Refereed)
    Abstract [en]

    Multi linguistic problems such as auto-categorization is not an easy task. It is possible to train different models for each language, another way to do auto-categorization is to build the model in one base language and use automatic translation from other languages to that base language. Different languages have a bias to a language specific grammar and syntax and will therefore pose problems to be expressed in other languages. Translating from one language into a non-verbal language could potentially have a positive impact of the categorization results. A non-verbal language could for example be pure information in form of a knowledge graph relation extraction from the text. In this article a comparison is conducted between Chinese and Swedish languages. Two categorization models are developed and validated on each dataset. The purpose is to make an auto-categorization model that works for n'importe quel langage. One model is built upon LSTM and optimized for Swedish and the other is an improved Bidirectional-LSTM Convolution model optimized for Chinese. The improved algorithm is trained on both languages and compared with the LSTM algorithm. The Bidirectional-LSTM algorithm performs approximately 20% units better than the LSTM algorithm, which is significant.

  • 35.
    Lindén, Johannes
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Wang, Xutao
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Forsström, Stefan
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Productify news article classification model with Sagemaker2020In: Advances in Science, Technology and Engineering Systems, ISSN 2415-6698, Vol. 5, no 2, p. 13-18Article in journal (Refereed)
    Abstract [en]

     News companies have a need to automate and make the process of writing about popular and new events more effective. Current technologies involve robotic programs that fill in values in templates and website listeners that notify editors when changes are made so that the editor can read up on the source change on the actual website. Editors can provide news faster and better if directly provided with abstracts of the external sources and categorical meta-data that supports what the text is about. To make categorical meta-data a reality an auto-categorization model was created and optimized for Swedish articles written by local news journalists. The problem was that it was not scale-able enough to use out of the box. Instead of having this local model that could make good predictions of the text documents, the model is to be deployed in the cloud and an API interface is created. The API can be accessed from the tools where the articles is being written and therefore these services can automatically assign categories to the articles once the journalist is done writing it. To allow scale-ability to several thousands of simultaneously categorized articles and at the same time improving the workflow of deploying new models easier the API is uploaded to Sagemaker where several models are trained and once an improved model is found that model will be used in production in such a way that the system organically adapts to new written articles. An evaluation of Sagemaker API was done and it was concluded that the complexity of this solution was polynomial. 

    Download full text (pdf)
    fulltext
  • 36.
    Lindén, Johannes
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Forsström, Stefan
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Österberg, Patrik
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Multi-language Information Extraction with Text Pattern Recognition2021In: Computer Science & Information Technology (CS & IT): Natural Language Computing7th International Conference on Natural Language Computing (NATL 2021), November 27~28, 2021, London, United Kingdom / [ed] David C. Wyld, Dhinaharan Nagamalai, 2021, Vol. 11, p. 1-17Conference paper (Refereed)
    Abstract [en]

    Information extraction is a task that can extract meta-data information from text. The research in this article proposes a new information extraction algorithm called GenerateIE. The proposed algorithm identifies pairs of entities and relations described in a piece of text. The extracted meta-data is useful in many areas, but within this research the focus is to use them in news-media contexts to provide the gist of the written articles for analytics and paraphrasing of news information. GenerateIE algorithm is compared with existing state of the art algorithms with two benefits. Firstly, the GenerateIE provides the co-referenced word as the entity instead of using he, she, it, etc. which is more beneficial for knowledge graphs. Secondly GenerateIE can be applied on multiple languages without changing the algorithm itself apart from the underlying natural language text-parsing. Furthermore, the performance of GenerateIE compared with state-of-the-art algorithms is not significantly better, but it offers competitive results. 

  • 37.
    Lu, Xuchen
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Tang, Hongling
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Cheng, Wenli
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Heterogeneous Data Source Middleware for Android E-Health Application2012In: 2012 EIGHTH INTERNATIONAL CONFERENCE ON MOBILE AD HOC AND SENSOR NETWORKS (MSN 2012), 2012, p. 92-99Conference paper (Other academic)
    Abstract [en]

    Heterogeneous data sources management is a big challenge for complex projects, especially in the situation of sensor net work. The incompatibility of different data sources makes it complicated for a project to modify databases in use or adapt to new sensors. In this paper, we propose a middleware solution to address the problem. The middleware uses an abstract class to shield the differences among heterogeneous data sources and creates a data source service wrapper for each. Both permanent data info and real-time data flows should pass through the middleware during communication of data sources and application. And by implementing a corresponding data source service wrapper, it's very convenient to add a new data source. At the same time, the middleware uses XML to accomplish data mapping and transmission, so as to solve the incompatibility of data sources schema and ensure platform independence. We deployed the middleware to our E-Health project. Our experience has proved the flexibility and extensibility of the middleware.

  • 38.
    Malmberg, Åke
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Intelligent agents for information retreival in internet1997In: Artificial intelligence and soft computing : proceedings of the IASTED international conference, Banff, Canada, July 27 to August 1, 1997, Anaheim, Calif.: IASTED/ACTA Press , 1997, p. 327-330Conference paper (Refereed)
    Abstract [en]

    Building intelligent software agents using traditional knowledge acquisition methods is difficult because of the dynamic properties of Internet. Knowledge about Internet can be divided in two levels. The first level is knowledge about tools and methods for searching information in Internet. The second level is knowledge about information in Internet (meta level). We focus on the meta level. Our approach is to identify knowledge sources in Internet. The knowledge may be implemented in a software agent and the planning can be improved by combining the knowledge from several intelligent software agents.

  • 39.
    Marx, B.
    et al.
    Fachhochschule Osnabrueck.
    Kollecker, J.
    Fachhochschule Osnabrueck.
    Lammen, B.
    Fachhochschule Osnabrueck.
    Nordin, J.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Sjöström, Mårten
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Distributed Vehicle Simulation - A Student Project in Mechatronics and Distributed Systems2008In: 9th International Workshop on Research and Education in Mechatronics, Bergamo, Italy, 18-19 September 2008., 2008Conference paper (Other academic)
  • 40.
    Naskar, Sujash
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    Hancke Jr, Gerhard P.
    City University of Hong Kong.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
    OTP-Based Symmetric Group Key Establishment Scheme for IoT Networks2021In: IECON Proceedings (Industrial Electronics Conference), 2021Conference paper (Refereed)
    Abstract [en]

    One of the major challenges in implementing agroup key establishment and management scheme to providesecurity solutions for group communication in the Internet of Things (IoT) is the limited resource availability of the nodes suchas memory, computation, and energy. To ensure security such as confidentiality, integrity of the transmitting messages in a certain IoT group, a feasible group key establishment and management scheme is necessary which uses minimum resources but provides high scalability and strong security. In this paper, we propose asymmetric group key establishment scheme that uses the secrecy guarantee provided by One Time Pad (OTP) and performs computations like bitwise Exclusive OR (XOR) and bit shifting of randomly generated binary vectors to produce random different keys for different sessions of message transmission. We show that our scheme is lightweight to support the resource-constrained nature of IoT nodes by using only primitive operations and scalable to support the dynamic constellation of IoT network groups where nodes can join and exit frequently. We prove that our scheme is secure under a designed threat model where a similar existing scheme fails by a detailed analysis

  • 41. Olsson, K
    et al.
    Andersson, Roger
    Zhang, TingTing
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Xu, Youshi
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    A Fast Implementation Scheme for 2-D Discrete Cosine Transform1997Patent (Other (popular science, discussion, etc.))
  • 42. Olsson, K
    et al.
    Andersson, Roger
    Zhang, TingTing
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Xu, Youshi
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Digital Video Temporal Noise Reduction1997Patent (Other (popular science, discussion, etc.))
  • 43.
    Padghalm, Lin
    et al.
    IDA, Linköping University.
    Zhang, Tingting
    IDA, Linköping University.
    Building the Ontology for a Medical Diagnosis System Using Standard Text1995In: In the IJCAI’95 Workshop ”Basic Ontological Issues in Knowledge Sharing, Canada, 1995Conference paper (Refereed)
  • 44.
    Padghalm, Lin
    et al.
    IDA, Linköping University.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Terminological Logic with Defaults: A definition and an Application1993In: Proceedings of IJCAI'93, France, 1993Conference paper (Other academic)
  • 45.
    Peng, Yingli
    et al.
    Donghua University, Shanghai, China.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems. STC.
    Sun, Li
    Donghua University, Shanghai, China.
    Chen, Jie
    Donghua University, Shanghai, China.
    A Novel Data Mining Method on Falling Detection and Daily Activities Recognition2015In: Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI, IEEE Computer Society, 2015, p. 675-681, article id 7372198Conference paper (Refereed)
    Abstract [en]

    With the intensification of aging population, a growing number of elderly people have to live alone due to domestic and social reasons. Falling becomes one of the most crucial factors in threatening the elderly's lives, which is always difficult to be detected as it is instantaneous and easy to be confused with other motions, such as lying down. In this paper, a new method is proposed for accurate falling detection and activities recognition. It applies hierarchical classifiers to the time series data set including eleven activities of daily living (ADLs), collected by four wearable sensors. The new method combines two machine learning algorithms, performs concrete analysis on the original outcome and then obtains several scarcely-confused groups separately. The experiment indicates that the new method improves the accuracy of classification to a larger extent, reached to more than 90%. Furthermore, the matched algorithm for applying these classifiers, called Hierarchical Classifier Algorithm (HCA), is proposed as well.

  • 46.
    Reiman, Ulf
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Pettersson, Stefan
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    A secure multicast downstream authentication protocol in sensor network2007Conference paper (Refereed)
    Abstract [en]

    A secure multicast downstream authentication protocol in sensor network: we develop a authentication protocol for sensor networks where the transmitted data is protected by algorithms� for privacy and authentication

  • 47.
    Shen, Wei
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science.
    Barac, Filip
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science. ABB Corporate Research, SE-72178 Vasteras, Sweden.
    PriorityMAC: A Priority-Enhanced MAC Protocol for Critical Traffic in Industrial Wireless Sensor and Actuator Networks2014In: IEEE Transactions on Industrial Informatics, ISSN 1551-3203, E-ISSN 1941-0050, Vol. 10, no 1, p. 824-835Article in journal (Refereed)
    Abstract [en]

    This paper proposes PriorityMAC, a priority-enhanced medium access control protocol, designed for critical traffic in industrial wireless sensor and actuator networks (IWSAN). A notable trend in industrial automation in recent years has been the replacement of wired communication by IWSANs. Exceeding the required delay bound for unpredictable and emergency traffic could lead to system instability, economic and material losses, system failure, and, ultimately, a threat to human safety. Guaranteeing the timely delivery of the IWSAN critical traffic and its prioritization over regular traffic (e.g., noncritical monitoring traffic) is a significant challenge. Therefore, we present the design, implementation, performance analysis, and evaluation of PriorityMAC. A series of novel mechanisms (e.g., high priority indication space) are proposed to enable high-priority traffic to hijack the transmission bandwidth of the low-priority traffic. To the best of our knowledge, this is the first priority-enhanced MAC protocol compatible with industrial standards for IWSAN. PriorityMAC is implemented in TinyOS and evaluated on a testbed of Telosb motes. The experimental results indicate that PriorityMAC efficiently handles different traffic categories with different latency requirements, thereby achieving a significant improvement in the delivery latency compared with the current industrial standards. © 2005-2012 IEEE.

  • 48.
    Shen, Wei
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Technology and Media.
    Gidlund, Mikael
    ABB Corporate Research.
    Distributed Data Gathering Scheduling Protocol for Wireless Sensor Actor and Actuator Networks2012In: Communications (ICC), 2012 IEEE International Conference on, IEEE Communications Society, 2012, p. 7120-7125Conference paper (Refereed)
    Abstract [en]

    This paper presents a cross-layer distributed scheduling protocol for sensor data gathering transmission inwireless sensor actor and actuator networks. We propose the parent-dominant decision scheduling with collision free (PDDS-CF) algorithm to adapt the dynamics of links in a realistic low-power wireless network. In addition, the protocol has a light-weight mechanism to maintain the conflict links. We have evaluated the protocol andimplementation in TinyOS and Telosb hardware. The experiment shows that our protocol has robustness to the topology changes and it has significant improvements to reduce the traffic load in realistic wireless networks.

    Download full text (pdf)
    fulltext
  • 49.
    Shen, Wei
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Joint Routing and MAC for Critical Traffic in Industrial Wireless Sensor and Actuator Networks2013In: IEEE International Symposium on Industrial Electronics, 2013, p. Art. no. 6563730-Conference paper (Refereed)
    Abstract [en]

    This paper proposes Delay Bounded Routing (DBR) and a Priority-based Medium Access Control method (PriorityMAC), designed for routing critical traffic in Industrial Wireless Sensor and Actuator Networks (IWSAN). A notable trend in industrial automation in recent years is the replacement of wired communication with IWSAN. Exceeding the required delay bound for unpredictable and emergency traffic could lead to system instability, economic and material losses, system failure and, ultimately, a threat to human safety. Guaranteeing the timely delivery of the critical traffic and its prioritization over regular traffic (e. g. non-critical monitoring traffic) is a significant challenge. Therefore, we present the design, implementation and evaluation of DBR and PriorityMAC. DBR and PriorityMAC are implemented in TinyOS and evaluated on a testbed of Telosb motes. The experimental results indicate that our protocol achieves a significant improvement of the end-to-end delivery latency compared to the current industrial standards.

  • 50.
    Shen, Wei
    et al.
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Zhang, Tingting
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems.
    Gidlund, Mikael
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems. ABB Corp Res, Vasterås, Sweden.
    Dobslaw, Felix
    Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System science.
    SAS-TDMA: A Source Aware Scheduling Algorithm for Real-Time Communication in Industrial Wireless Sensor Networks2013In: Wireless networks, ISSN 1022-0038, E-ISSN 1572-8196, Vol. 19, no 6, p. 1155-1170Article in journal (Refereed)
    Abstract [en]

    Scheduling algorithms play an importantrole for TDMA-based wireless sensor networks. ExistingTDMA scheduling algorithms address a multitude of objectives.However, their adaptation to the dynamics of a realistic wirelesssensor network has not been investigated in a satisfactorymanner. This is a key issue considering the challenges withinindustrial applications for wireless sensor networks, given thetime-constraints and harsh environments.In response to those challenges, we present SAS-TDMA, asource-aware scheduling algorithm. It is a cross-layer solutionwhich adapts itself to network dynamics. It realizes a tradeoffbetween scheduling length and its configurational overheadincurred by rapid responses to routes changes. We implementeda TDMA stack instead of the default CSMA stack and introduceda cross-layer for scheduling in TOSSIM, the TinyOS simulator.Numerical results show that SAS-TDMA improves the qualityof service for the entire network. It achieves significant improvementsfor realistic dynamic wireless sensor networks whencompared to existing scheduling algorithms with the aim tominimize latency for real-time communication.

12 1 - 50 of 96
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf