| 111. |
- Lundström, Adam, et al.
(författare)
-
An interactive threshold-setting procedure for improved multivariate anomaly detection in time series
- 2023
-
Ingår i: IEEE Access. - : IEEE. - 2169-3536. ; 11, s. 93898-93907
-
Tidskriftsartikel (refereegranskat)abstract
- 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.
|
|
| 112. |
- Lundström, Adam, et al.
(författare)
-
Factory-Based Vibration Data for Bearing-Fault Detection
- 2023
-
Ingår i: DATA. - : MDPI. - 2306-5729. ; 8:7
-
Tidskriftsartikel (refereegranskat)abstract
- 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.
|
|
| 113. |
- Lundström, Adam, et al.
(författare)
-
Improving deep learning based anomaly detection on multivariate time series through separated anomaly scoring
- 2022
-
Ingår i: IEEE Access. - 2169-3536. ; 10, s. 108194-108204
-
Tidskriftsartikel (refereegranskat)abstract
- The importance of anomaly detection in multivariate time series has led to the development of several prominent deep learning solutions. As a part of the anomaly detection method, the scoring method has shown to be of significant importance when separating non-anomalous points from anomalous ones. At this time, most of the solutions utilize an aggregated score which means that relevant information created by the anomaly detection model might be lost. Therefore, this study has set out to examine to what extent anomaly detection in multivariate time series based on deep learning can be improved if all the residuals from each individual channel is considered in the anomaly score. To achieve this, an aggregated and separated scoring method has been applied with a simple denoising convulutional autoencoder (DCAE). In addition, the performance has been compared with other state-of-the-art methods. The result showed that the separated approach has the potential to generate a significantly higher performance than the aggregated one. At the same time, there were some indications suggesting that an aggregated scoring is better at generalizing when no labels to base the anomaly thresholds on, are available. Therefore, the result should serve as an encouragement to use a separated scoring approach together with a small sample of labeled anomalies to optimise the thresholds. Lastly, due to the impact of the anomaly score, the result suggests that future research within this field should consider applying the same anomaly scoring method when comparing the performance of deep learning algorithms.
|
|
| 114. |
- Mahmood, Aamir, 1980-, et al.
(författare)
-
Remote-Timber : An Outlook for Teleoperated Forestry With First 5G Measurements
- 2023
-
Ingår i: IEEE Industrial Electronics Magazine. - : IEEE. - 1932-4529 .- 1941-0115. ; 17:3, s. 42-53
-
Tidskriftsartikel (refereegranskat)abstract
- 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, Remote-Timber—demonstrating a 5G-connected teleoperation use-case within a workflow of timber terminal—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.
|
|
| 115. |
|
|
| 116. |
- Meng, Xiaozhou
(författare)
-
Maintenance Consideration for Long Life Cycle Embedded System
- 2012
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- In this thesis, the work presented is in relation to consideration to the maintenance of a long life cycle embedded system. Various issues can present problems for maintaining a long life cycle embedded system, such as component obsolescence and IP (intellectual property) portability. For products including automotive, avionics, military application etc., the desired life cycles for these systems are many times longer than the obsolescence cycle for the electronic components used in the systems. The maintainability is analyzed in relation to long life cycle embedded systems for different design technologies. FPGA platform solutions are proposed in order to ease the system maintenance. Different platform cases are evaluated by analyzing the essence of each case and the consequences of different risk scenarios during system maintenance. This has shown that an FPGA platform with a vendor and device independent soft IP has the highest maintainability.A mathematic model of obsolescence management for long life cycle embedded system maintenance is presented. This model can estimate the minimum management costs for the different system architecture and this consists of two parts. The first is to generate a graph in Matlab which is in the form of state transfer diagram. A segments table is then output from Matlab for further optimization. The second part is to find the lowest cost in the state transfer diagram, which can be viewed as a transshipment problem. Linear programming is used to calculate the minimized management cost and schedule, which is solved by Lingo. A simple Controller Area Network (CAN) controller system case study is shown in order to apply this model. The model is validated by a set of synthetic and experimentally selected values. The results provided by this are a minimized management cost and an optimized management time schedule. Test experiments of the maintenance cost responding to the interest rate and unit cost are implemented. The responses from the experiments meet our expectations. The reuse of predefined IP can shorten development times and assist the designer to meet time-to-market (TTM) requirements. System migration between devices is unavoidable, especially when it has a long life cycle expectation, so IP portability becomes an important issue for system maintenance. An M-JPEG decoder case study is presented in the thesis. The lack of any clear separation between computation and communication is shown to limit the IP’s portability with respect to different communication interfaces. A methodology is proposed to ease the interface modification and interface reuse, thus to increase the portability of an IP. Technology and tool dependent firmware IP components are also shown to limit the IP portability with respect to development tools and FPGA vendors.
|
|
| 117. |
- Meng, Xiaozhou
(författare)
-
Technology Driven Obsolescence Management for Embedded Systems
- 2014
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- In this thesis, the work presented is in relation to technology driven obsolescence management for embedded systems.Component obsolescence problems may occur in systems with a life cycle longer than that of one or more of their components when there is a demand without enough existing stock, such as automotive, avionics, military applications, etc. This thesis analyzes the component obsolescence problem from both the design technology selection and management perspectives.Design technologies selection is associated with hardware and software. Several hardware platforms such as COTS and field-programmable gate array (FPGA) are discussed. FPGA intellectual property (IP) portability is emphasized which will affect the obsolescence management cost. Embedded software is also a crucial part for system sustainment. A risk analysis is performed in relation to long life cycle systems for different design technologies. Different platform cases are evaluated by analyzing the essence of each case and the consequences of different risk scenarios during system maintenance. This has shown that an FPGA platform with the vendor and device independent soft IPs has the highest maintainability and the minimum redesign cost.The reuse of a predefined IP can shorten the development times and assist the designer to meet time-to-market (TTM) requirements. System migration between devices is unavoidable, especially when it has a long life cycle expectation, so IP portability becomes an important issue for system maintenance. If an IP for FPGAs is truly portable, it must be easily adaptable to different communication interfaces, being portable between different FPGA vendors and devices, having no dependencies on the tool set and library used for the system design and no restriction on the communication interface. An M-JPEG decoder and a soft microprocessor portability analysis case study are presented in the thesis. A methodology is proposed to ease the interface modification and interface reuse, thus to increase the portability of an IP.A strategic proactive obsolescence management model is proposed from a management perspective. This model can estimate the minimum management costs for a system with different architectures. It consists of two parts. The first is to generate a graph, which is in the form of an obsolescence management diagram. A segments table containing the data of this diagram is calculated and prepared for optimization at a second step. This second part is to find the minimum cost for system obsolescence management. Mixed integer linear programming (MILP) is used to calculate the minimum management cost and schedule. The model is open sourced thus allowing other research groups to freely download and modify it.Both the design technology selection and the strategic proactive obsolescence management are demonstrated by an industrial display computer system case study. The results show significant cost avoidance as compared to the original method used by the company.Finally, the research results are encapsulated into an obsolescence management cost avoidance methodology.
|
|
| 118. |
- Nie, Yali, et al.
(författare)
-
A Deep CNN Transformer Hybrid Model for Skin Lesion Classification of Dermoscopic Images Using Focal Loss
- 2023
-
Ingår i: Diagnostics. - : MDPI AG. - 2075-4418. ; 13:1
-
Tidskriftsartikel (refereegranskat)abstract
- 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.
|
|
| 119. |
- Nie, Yali, et al.
(författare)
-
Automatic Detection of Melanoma with Yolo Deep Convolutional Neural Networks
- 2019
-
Ingår i: 2019 E-Health and Bioengineering Conference (EHB). - : IEEE. - 9781728126036
-
Konferensbidrag (refereegranskat)abstract
- In the past three years, deep convolutional neural networks (DCNNs) have achieved promising performance in detecting skin cancer. However, improving the accuracy and efficiency of the automatic detection of melanoma is still urgent due to the visual similarity of benign and malignant dermoscopy. There is also a need for fast and computationally effective systems for mobile applications targeting caregivers and homes. This paper presents the You Only Look Once (Yolo) algorithms, which are based on DCNNs applied to the detection of melanoma. The Yolo algorithms comprise YoloV1, YoloV2, and YoloV3, whose methodology first resets the input image size and then divides the image into several cells. According to the position of the detected object in the cell, the network will try to predict the bounding box of the object and the class confidence score. Our test results indicate that the mean average precision (mAP) of Yolo can exceed 0.82 with a training set of only 200 images, proving that this method has great advantages for detecting melanoma in lightweight system applications.
|
|
| 120. |
- Nie, Yali
(författare)
-
Automatic Melanoma Diagnosis in Dermoscopic Imaging Base on Deep Learning System
- 2021
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Melanoma is one of the deadliest forms of cancer. Unfortunately, its incidence rates have been increasing all over the world. One of the techniques used by dermatologists to diagnose melanomas is an imaging modality called dermoscopy. The skin lesion is inspected using a magnification device and a light source. This technique makes it possible for the dermatologist to observe subcutaneous structures that would be invisible otherwise. However, the use of dermoscopy is not straightforward, requiring years of practice. Moreover, the diagnosis is many times subjective and challenging to reproduce. Therefore, it is necessary to develop automatic methods that will help dermatologists provide more reliable diagnoses. Since this cancer is visible on the skin, it is potentially detectable at a very early stage when it is curable. Recent developments have converged to make fully automatic early melanoma detection a real possibility. First, the advent of dermoscopy has enabled a dramatic boost in the clinical diagnostic ability to the point that it can detect melanoma in the clinic at the earliest stages. This technology’s global adoption has allowed the accumulation of extensive collections of dermoscopy images. The development of advanced technologies in image processing and machine learning has given us the ability to distinguish malignant melanoma from the many benign mimics that require no biopsy. These new technologies should allow earlier detection of melanoma and reduce a large number of unnecessary and costly biopsy procedures. Although some of the new systems reported for these technologies have shown promise in preliminary trials, a widespread implementation must await further technical progress in accuracy and reproducibility. This thesis provides an overview of our deep learning (DL) based methods used in the diagnosis of melanoma in dermoscopy images. First, we introduce the background. Then, this paper gives a brief overview of the state-of-art article on melanoma interpret. After that, a review is provided on the deep learning models for melanoma image analysis and the main popular techniques to improve the diagnose performance. We also made a summary of our research results. Finally, we discuss the challenges and opportunities for automating melanocytic skin lesions’ diagnostic procedures. We end with an overview of a conclusion and directions for the following research plan.
|
|
