Mid Sweden University

miun.sePublications
Change search
Link to record
Permanent link

Direct link
O'Nils, Mattias
Alternative names
Publications (10 of 181) Show all publications
Nie, Y., Sommella, P., Carratù, M., O'Nils, M. & Lundgren, J. (2023). A Deep CNN Transformer Hybrid Model for Skin Lesion Classification of Dermoscopic Images Using Focal Loss. Diagnostics, 13(1), Article ID 72.
Open this publication in new window or tab >>A Deep CNN Transformer Hybrid Model for Skin Lesion Classification of Dermoscopic Images Using Focal Loss
Show others...
2023 (English)In: Diagnostics, ISSN 2075-4418, Vol. 13, no 1, article id 72Article in journal (Refereed) Published
Abstract [en]

Skin cancers are the most cancers diagnosed worldwide, with an estimated > 1.5 million new cases in 2020. Use of computer-aided diagnosis (CAD) systems for early detection and classification of skin lesions helps reduce skin cancer mortality rates. Inspired by the success of the transformer network in natural language processing (NLP) and the deep convolutional neural network (DCNN) in computer vision, we propose an end-to-end CNN transformer hybrid model with a focal loss (FL) function to classify skin lesion images. First, the CNN extracts low-level, local feature maps from the dermoscopic images. In the second stage, the vision transformer (ViT) globally models these features, then extracts abstract and high-level semantic information, and finally sends this to the multi-layer perceptron (MLP) head for classification. Based on an evaluation of three different loss functions, the FL-based algorithm is aimed to improve the extreme class imbalance that exists in the International Skin Imaging Collaboration (ISIC) 2018 dataset. The experimental analysis demonstrates that impressive results of skin lesion classification are achieved by employing the hybrid model and FL strategy, which shows significantly high performance and outperforms the existing work. 

Keywords
deep learning, focal loss, hybrid model, skin lesion
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:miun:diva-46860 (URN)10.3390/diagnostics13010072 (DOI)000908965800001 ()2-s2.0-85145859869 (Scopus ID)
Available from: 2023-01-17 Created: 2023-01-17 Last updated: 2023-01-26Bibliographically approved
Hussain, M., O'Nils, M., Lundgren, J., Akbari-Saatlu, M., Hamrin, R. & Mattsson, C. (2023). A Deep Learning Approach for Classification and Measurement of Hazardous Gases Using Multi-Sensor Data Fusion. In: 2023 IEEE Sensors Applications Symposium (SAS): . Paper presented at 2023 IEEE Sensors Applications Symposium (SAS) Ottawa, ON, Canada. IEEE conference proceedings, Article ID 10254191.
Open this publication in new window or tab >>A Deep Learning Approach for Classification and Measurement of Hazardous Gases Using Multi-Sensor Data Fusion
Show others...
2023 (English)In: 2023 IEEE Sensors Applications Symposium (SAS), IEEE conference proceedings, 2023, article id 10254191Conference paper, Published paper (Refereed)
Abstract [en]

Significant risks to public health and the environment are posed by the release of hazardous gases from industries such as pulp and paper. In this study, the aim was to develop a multi-sensor system with a minimal number of sensors to detect and identify hazardous gases. Training and test data for two gases, hydrogen sulfide and methyl mercaptan, which are known to contribute significantly to odors, were generated in a controlled laboratory environment. The performance of two deep learning models, a 1d-CNN and a stacked LSTM, for data fusion with different sensor configurations was evaluated. The performance of these models was compared with a baseline machine learning model. It was observed that the baseline model was outperformed by the deep learning models and achieved good accuracy with a four-sensor configuration. The potential of a cost-effective multi-sensor system and deep learning models in detecting and identifying hazardous gases is demonstrated by this study, which can be used to collect data from multiple locations and help guide the development of in-situ measurement systems for real-time detection and identification of hazardous gases at industrial sites. The proposed system has important implications for reducing pollution and protecting public health.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2023
Keywords
Gas measurement, Pulp & Paper, Multi-sensor, Data fusion, Machine learning, Deep learning, CNN, 1D-CNN, SVM, LSTM, Gas classification
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-49384 (URN)10.1109/SAS58821.2023.10254191 (DOI)001086399500100 ()2-s2.0-85174035432 (Scopus ID)
Conference
2023 IEEE Sensors Applications Symposium (SAS) Ottawa, ON, Canada
Available from: 2023-09-26 Created: 2023-09-26 Last updated: 2023-11-10Bibliographically approved
Carratu, M., Gallo, V., Liguori, C., Pietrosanto, A., O'Nils, M. & Lundgren, J. (2023). An innovative method for log diameter measurements based on deep learning. In: 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC): . Paper presented at 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). IEEE
Open this publication in new window or tab >>An innovative method for log diameter measurements based on deep learning
Show others...
2023 (English)In: 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), IEEE, 2023Conference paper, Published paper (Refereed)
Abstract [en]

The widespread adoption of Deep Learning techniques for Computer Vision in recent years has brought major changes to the world of industry, contributing greatly to this sector's transition to Industry 4.0, also referred to as Smart Industry. This involves an increasingly predominant role of machines and automation within industrial processes. In this context, the Swedish forest industry is an excellent context for applying these techniques. In particular, this work will deal with automating the measurement of log diameters to date carried out manually by operators in the industry. The proposed methodology will use two object detection neural networks, one deputed to detect logs in the scene and the other for the calibrated target. The latter thus allows the camera calibration to be fully automated, enabling each diameter to be measured without any further operations by the operator. The results obtained are satisfactory and open the way for the industrial application of the proposed methodology. 

Place, publisher, year, edition, pages
IEEE, 2023
Keywords
automatic calibration, deep learning, measurement methodology
National Category
Computer Sciences
Identifiers
urn:nbn:se:miun:diva-49087 (URN)10.1109/I2MTC53148.2023.10176057 (DOI)001039259600175 ()2-s2.0-85166371036 (Scopus ID)978-1-6654-5383-7 (ISBN)
Conference
2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
Available from: 2023-08-17 Created: 2023-08-17 Last updated: 2023-09-01Bibliographically approved
Lundström, A., O'Nils, M. & Qureshi, F. (2023). An interactive threshold-setting procedure for improved multivariate anomaly detection in time series. IEEE Access, 11, 93898-93907
Open this publication in new window or tab >>An interactive threshold-setting procedure for improved multivariate anomaly detection in time series
2023 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 11, p. 93898-93907Article in journal (Refereed) Published
Abstract [en]

Anomaly detection in multivariate time series is valuable for many applications. In this context, unsupervised and semi-supervised deep learning methods that estimate how normal a new observation is have shown promising results on benchmark datasets. These methods are dependent on a threshold that determines which points should be regarded as anomalous and not be anomalous. However, finding the optimal threshold is not easy since no information about the ground truth is known in advance, which implies that there are limitations to automatic threshold-setting methods available today. An alternative is to utilize the expertise of users that can interact in a threshold-setting procedure, but for this to be practically feasible, the method needs to be both accurate and efficient in relation to the state-of-the-art automatic methods. Therefore, this study develops an interactive threshold-setting schema and examines to what extent it can outperform the current state-of-the-art automatic threshold-setting methods. The result of the study strongly indicates that the suggested method with little effort can provide higher accuracy than the automatic threshold-setting methods on a general basis. 

Place, publisher, year, edition, pages
IEEE, 2023
Keywords
Anomaly detection, Anomaly scoring, Data models, Deep learning, Electronic mail, Multivariate time series (MVTS), Time series analysis, Time-domain analysis, Training, Training data
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:miun:diva-49293 (URN)10.1109/ACCESS.2023.3310653 (DOI)001063183300001 ()2-s2.0-85169696562 (Scopus ID)
Available from: 2023-09-13 Created: 2023-09-13 Last updated: 2023-09-22Bibliographically approved
Lundström, A. & O'Nils, M. (2023). Factory-Based Vibration Data for Bearing-Fault Detection. DATA, 8(7), Article ID 115.
Open this publication in new window or tab >>Factory-Based Vibration Data for Bearing-Fault Detection
2023 (English)In: DATA, ISSN 2306-5729, Vol. 8, no 7, article id 115Article in journal (Refereed) Published
Abstract [en]

The importance of preventing failures in bearings has led to a large amount of research being conducted to find methods for fault diagnostics and prognostics. Many of these solutions, such as deep learning methods, require a significant amount of data to perform well. This is a reason why publicly available data are important, and there currently exist several open datasets that contain different conditions and faults. However, one challenge is that almost all of these data come from a laboratory setting, where conditions might differ from those found in an industrial environment where the methods are intended to be used. This also means that there may be characteristics of the industrial data that are important to take into account. Therefore, this study describes a completely new dataset for bearing faults from a pulp mill. The analysis of the data shows that the faults vary significantly in terms of fault development, rotation speed, and the amplitude of the vibration signal. It also suggests that methods built for this environment need to consider that no historical examples of faults in the target domain exist and that external events can occur that are not related to any condition of the bearing.

Place, publisher, year, edition, pages
MDPI, 2023
Keywords
bearing, diagnostics, fault detection, dataset, fault diagnosis
National Category
Control Engineering
Identifiers
urn:nbn:se:miun:diva-49074 (URN)10.3390/data8070115 (DOI)001035081000001 ()2-s2.0-85166415713 (Scopus ID)
Available from: 2023-08-16 Created: 2023-08-16 Last updated: 2023-08-16Bibliographically approved
Gallo, V., Shallari, I., Carratu, M. & O'Nils, M. (2023). Metrological Characterization of a Clip Fastener assembly fault detection system based on Deep Learning. In: 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC): . Paper presented at 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). IEEE
Open this publication in new window or tab >>Metrological Characterization of a Clip Fastener assembly fault detection system based on Deep Learning
2023 (English)In: 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), IEEE, 2023Conference paper, Published paper (Refereed)
Abstract [en]

In a time when Artificial Intelligence (AI) technologies are nearly ubiquitous, railway construction and maintenance systems have not fully grasped the capabilities of such technologies. Traditional railway inspection methods rely on inspection from experienced workers, making such tasks costly from both, the monetary and the time perspective. From an overview of the state-of-the-art research in this area regarding AI-based systems, we observed that their main focus was solely on detection accuracy of different railway components. However, if we consider the critical importance of railway fastening in the overall safety of the railway, there is a need for a thorough analysis of these AI-based methodologies, to define their uncertainty also from a metrological perspective. In this article we address this issue, proposing an image-based system that detects the rotational displacement of the fastened railway clips. Furthermore, we provide an uncertainty analysis of the measurement system, where the resulting uncertainty is of 0.42°, within the 3° error margin defined by the clip manufacturer. 

Place, publisher, year, edition, pages
IEEE, 2023
Keywords
angle measurement, Oriented object detection, railway fastener clip
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-49092 (URN)10.1109/I2MTC53148.2023.10176099 (DOI)001039259600216 ()2-s2.0-85166376311 (Scopus ID)9781665453837 (ISBN)
Conference
2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
Available from: 2023-08-17 Created: 2023-08-17 Last updated: 2023-09-01Bibliographically approved
Saqib, E., Sánchez Leal, I., Shallari, I., Jantsch, A., Krug, S. & O'Nils, M. (2023). Optimizing the IoT Performance: A Case Study on Pruning a Distributed CNN. In: 2023 IEEE Sensors Applications Symposium (SAS): . Paper presented at 2023 IEEE Sensors Applications Symposium, SAS 2023.
Open this publication in new window or tab >>Optimizing the IoT Performance: A Case Study on Pruning a Distributed CNN
Show others...
2023 (English)In: 2023 IEEE Sensors Applications Symposium (SAS), 2023Conference paper, Published paper (Refereed)
Abstract [en]

Implementing Convolutional Neural Networks (CNN) based computer vision algorithms in Internet of Things (IoT) sensor nodes can be difficult due to strict computational, memory, and latency constraints. To address these challenges, researchers have utilized techniques such as quantization, pruning, and model partitioning. Partitioning the CNN reduces the computational burden on an individual node, but the overall system computational load remains constant. Additionally, communication energy is also incurred. To understand the effect of partitioning and pruning on energy and latency, we conducted a case study using a feet detection application realized with Tiny Yolo-v3 on a 12th Gen Intel CPU with NVIDIA GeForce RTX 3090 GPU. After partitioning the CNN between the sequential layers, we apply quantization, pruning, and compression and study the effects on energy and latency. We analyze the extent to which computational tasks, data, and latency can be reduced while maintaining a high level of accuracy. After achieving this reduction, we offloaded the remaining partitioned model to the edge node. We found that over 90% computation reduction and over 99% data transmission reduction are possible while maintaining mean average precision above 95%. This results in up to 17x energy savings and up to 5.2x performance speed-up. 

Keywords
CNN, IoT, Partitioning, Pruning, Quantization, Tiny YOLO-v3
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:miun:diva-49648 (URN)10.1109/SAS58821.2023.10254054 (DOI)2-s2.0-85174060733 (Scopus ID)9798350323078 (ISBN)
Conference
2023 IEEE Sensors Applications Symposium, SAS 2023
Available from: 2023-10-24 Created: 2023-10-24 Last updated: 2023-10-24Bibliographically approved
Mahmood, A., Abedin, S. F., O'Nils, M., Bergman, M. & Gidlund, M. (2023). Remote-Timber: An Outlook for Teleoperated Forestry With First 5G Measurements. IEEE Industrial Electronics Magazine, 17(3), 42-53
Open this publication in new window or tab >>Remote-Timber: An Outlook for Teleoperated Forestry With First 5G Measurements
Show others...
2023 (English)In: IEEE Industrial Electronics Magazine, ISSN 1932-4529, E-ISSN 1941-0115, Vol. 17, no 3, p. 42-53Article in journal (Refereed) Published
Abstract [en]

Across all industries, digitalization and automation are on the rise under the Industry 4.0 vision, and the forest industry is no exception. The forest industry depends on distributed flows of raw materials to the industry through various phases, wherein the typical workflow of timber loading and offloading is finding traction in using automation and 5G wireless networking technologies to enhance efficiency and reduce cost. This article presents one such ongoing effort in Sweden, <italic>Remote-Timber</italic>&#x2014;demonstrating a 5G-connected teleoperation use-case within a workflow of timber terminal&#x2014;and disseminates its business attractiveness as well as first measurement results on network performance. Also, it outlines the future needs of the 5G network design/optimization from teleoperation perspective. Overall, the motivation of this article is to disseminate our early-stage findings and reflections to the industrial and academic communities for furthering the research and development activities in enhancing 5G networks for verticals. 

Place, publisher, year, edition, pages
IEEE, 2023
Keywords
5G mobile communication, Automation, Forestry, Industries, Loading, Safety, Wheels
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-49023 (URN)10.1109/MIE.2023.3284202 (DOI)001025606800001 ()2-s2.0-85163446104 (Scopus ID)
Available from: 2023-08-15 Created: 2023-08-15 Last updated: 2023-09-21Bibliographically approved
Forsström, S., Forsberg, M., O'Nils, M., Sidén, J., Österberg, P. & Engberg, B. A. (2023). Specialanpassade kurser för yrkesverksamma ingenjörer: Erfarenheter och upplevelser. In: Bidrag från den 9:e utvecklingskonferensen för Sveriges ingenjörsutbildningar: . Paper presented at 9:e utvecklingskonferensen för Sveriges ingenjörsutbildningar (pp. 348-353). Mälardalens universitet
Open this publication in new window or tab >>Specialanpassade kurser för yrkesverksamma ingenjörer: Erfarenheter och upplevelser
Show others...
2023 (Swedish)In: Bidrag från den 9:e utvecklingskonferensen för Sveriges ingenjörsutbildningar, Mälardalens universitet, 2023, p. 348-353Conference paper, Published paper (Other academic)
Abstract [sv]

I dagens samhälle blir det allt viktigare att fortbilda sig under hela sitt yrkesverksamma liv. För att möta efterfrågan på det livslånga lärandet har Mittuniversitetet utvecklat och genomfört ett antal kurser som riktar sig mot yrkesverksamma ingenjörer. Detta arbete presenterar våra erfarenheter av att ge dessa kurser, med en tyngdpunkt på studenternas upplevelser. Syftet med detta är att bygga upp en vetenskaplig bas för vad vi gör som är bra, men även vad som kan förbättras och förändras. Målsättningen är att göra dessa specialanpassade kurser riktade mot yrkesverksamma ingenjörer så givande och flexibla som möjligt. Våra initiala resultat visar bland annat att studenternas negativa upplevelser ofta var kopplade till antagningsförfarandet och det praktiska genomförandet av kurserna. Man hade svårigheter med att hitta hur man skulle registrera sig på kursen och att tidsramen för registrering kunde vara ett problem. Läroplattformen uppfattades som svår att överblicka och det förekom även viss otydlighet gällande var undervisningen skulle äga rum. Den positiva responsen i utvärderingarna gällde främst det faktiska kursinnehållet, då man ansåg att uppgifter och kursmaterial var givande. Vidare uppskattades kursupplägget, att man kunde kombinera studierna med arbete. Framledes kommer vi att fortsätta med dessa utvärderingar i takt med att kurserna ges, och därefter anpassa vårt mottagande och kommunikationen med studenterna. Även kursupplägget ses över kontinuerligt via den återkoppling vi mottar. 

Place, publisher, year, edition, pages
Mälardalens universitet, 2023
Keywords
Livslångt lärande, Expertkompetens, Ingenjörer, Microlearning, Yrkesverksamma.
National Category
Learning
Identifiers
urn:nbn:se:miun:diva-49951 (URN)978-91-7485-620-0 (ISBN)
Conference
9:e utvecklingskonferensen för Sveriges ingenjörsutbildningar
Available from: 2023-11-26 Created: 2023-11-26 Last updated: 2024-03-05Bibliographically approved
Carratù, M., Gallo, V., Liguori, C., Lundgren, J., O'Nils, M. & Pietrosanto, A. (2023). Vision-Based System for Measuring the Diameter of Wood Logs. IEEE Open Journal of Instrumentation and Measurement, 2, 1-12
Open this publication in new window or tab >>Vision-Based System for Measuring the Diameter of Wood Logs
Show others...
2023 (English)In: IEEE Open Journal of Instrumentation and Measurement, ISSN 2768-7236, Vol. 2, p. 1-12Article in journal (Refereed) Published
Abstract [en]

Detecting and measuring objects with vision-based systems in uncontrolled environments is a difficult task that today, thanks to the development of increasingly advanced artificial intelligence-based techniques, can be solved with greater ease. In this context, this article proposes a novel approach for the vision-based measurement of objects in uncontrolled environments using a specific type of convolutional neural network (CNN) named you only look once (YOLO) and a direct linear transformation (DLT) process. The case study concerned designing a novel vision-based system for measuring the diameter of wood logs cut and loaded onto trucks. This problem has been occurring in the Swedish forestry industry. In fact, this operation is not carried out with computer vision algorithms because of the high variability of environmental conditions caused by the changing position of the sun, weather conditions, and the variability of truck positioning. To solve this problem, the YOLO network is proposed to locate logs while attempting to maintain a high Intersection over Union (IoU) value for the correct estimation of log size. Furthermore, in order to obtain accurate measurements, the DLT is used to convert into world coordinates the dimensions of the logs themselves. The proposed CNN-based solution is described after briefly introducing today’s methodologies adopted for wood bundle analysis. Particular attention is paid to both the training and the calibration steps. Results report that for 80% of cases, the error reported has been smaller than 4 cm, representing only 8% of the measurement, considering a mean log diameter for the application of 50 cm.

Place, publisher, year, edition, pages
IEEE, 2023
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:miun:diva-50167 (URN)10.1109/OJIM.2023.3264042 (DOI)
Available from: 2023-12-21 Created: 2023-12-21 Last updated: 2023-12-21Bibliographically approved
Organisations

Search in DiVA

Show all publications