| 1. |
- 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.
|
|
| 2. |
- O'Nils, Mattias, et al.
(författare)
-
Design of D-AMPS Channel Decoder with Codesign Methodologies
- 1996
-
Ingår i: BEC '96, the 5th Biennial Baltic Electronics Conference, October 7-11, 1996, Tallinn, Estonia : proceedings. - Tallinn, Estonia : Tallinn Technical University. - 9789985590263 ; , s. 491-
-
Konferensbidrag (refereegranskat)abstract
- This paper is a case study on tool based codesign methodology. The presented methods are observed by applying a D-AMPS channel decoder design to a codesign research tool-kit. The channel decoder functionality is described with five thousand lines of C code. The analysis (profiling, estimation, hardware-software partitioning and verification) of the C description are presented in the paper.
|
|
| 3. |
- O’Nils, Mattias, et al.
(författare)
-
Device driver and DMA controller synthesis from HW /SW communication protocol specifications
- 2001
-
Ingår i: Design automation for embedded systems. - : Kluwer Academic Publishers. - 0929-5585 .- 1572-8080. ; 6:2, s. 177-205
-
Tidskriftsartikel (refereegranskat)abstract
- We have separated the information required for HW /SW interface synthesis into three parts, the protocol specification, the operating system related information, and the processor related information. From these inputs a synthesis tool generates (a) device driver functions or (b) a combination of device driver functions and a DMA controller, depending on a designer’s decision. The clean separation of information facilitates (1) efficient design space exploration with combinations of different processors, operating systems and protocols, and (2) maintaining a large number of different versions and variants of HW /SW interfaces by synthesising them on demand. Protocols are specified as a grammar, which is fully independent of architecture and implementation. From this the synthesis tool generates device driver code in C and /or synthesizable RTL code in VHDL for DMA controllers. After the initial selection of implementation alternatives the presented methods are fully automated. Its computational complexity is quadratic in terms of the number of states. With real-life examples we show that the quality of the generated code is close to hand written quality in terms of performance, area and code size.
|
|
| 4. |
|
|
| 5. |
- O'Nils, Mattias, et al.
(författare)
-
Grammar Based Modelling and Synthesis of Device Drivers and Bus Interfaces
- 1998
-
Ingår i: Proceedings. 24th EUROMICRO Conference, 25-27 Aug. 1998, Västerås. - 0818686464 ; , s. 55-58
-
Konferensbidrag (refereegranskat)abstract
- ProGram, a grammar based communication protocol description language, is used for architectural independent modelling of device drivers and bus interfaces for mixed hardware/software systems. The specification of the protocol is separated from the description of processor bus interfaces and operating system device driver interfaces, which ensures a high efficiency in device driver development and maintenance. A synthesis method for device drivers is presented together with results on modelling and implementation efficiency for both device drivers and bus interfaces.
|
|
| 6. |
- Sánchez Leal, Isaac, et al.
(författare)
-
Impact of input data on intelligence partitioning decisions for IoT smart camera nodes
- 2021
-
Ingår i: Electronics. - : MDPI AG. - 2079-9292. ; 10:16
-
Tidskriftsartikel (refereegranskat)abstract
- Image processing systems exploit image information for a purpose determined by the application at hand. The implementation of image processing systems in an Internet of Things (IoT) context is a challenge due to the amount of data in an image processing system, which affects the three main node constraints: memory, latency and energy. One method to address these challenges is the partitioning of tasks between the IoT node and a server. In this work, we present an in-depth analysis of how the input image size and its content within the conventional image processing systems affect the decision on where tasks should be implemented, with respect to node energy and latency. We focus on explaining how the characteristics of the image are transferred through the system until finally influencing partition decisions. Our results show that the image size affects significantly the efficiency of the node offloading configurations. This is mainly due to the dominant cost of communication over processing as the image size increases. Furthermore, we observed that image content has limited effects in the node offloading analysis.
|
|
| 7. |
- Sánchez Leal, Isaac, et al.
(författare)
-
Waist Tightening of CNNs : A Case study on Tiny YOLOv3 for Distributed IoT Implementations
- 2023
-
Ingår i: ACM International Conference Proceeding Series. - : Association for Computing Machinery (ACM). - 9798400700491 ; , s. 241-246
-
Konferensbidrag (refereegranskat)abstract
- Computer vision systems in sensor nodes of the Internet of Things (IoT) based on Deep Learning (DL) are demanding because the DL models are memory and computation hungry while the nodes often come with tight constraints on energy, latency, and memory. Consequently, work has been done to reduce the model size or distribute part of the work to other nodes. However, then the question arises how these approaches impact the energy consumption at the node and the inference time of the system. In this work, we perform a case study to explore the impact of partitioning a Convolutional Neural Network (CNN) such that one part is implemented on the IoT node, while the rest is implemented on an edge device. The goal is to explore how the choice of partition point, quantization method and communication technology affects the IoT system. We identify possible partitioning points between layers, where we transform the feature maps passed between layers by applying quantization and compression to reduce the data sent over the communication channel between the two partitions in Tiny YOLOv3. The results show that a reduction of transmitted data by 99.8% reduces the network accuracy by 3 percentage points. Furthermore, the evaluation of various IoT communication protocols shows that the quantization of data facilitates CNN network partitioning with significant reduction of overall latency and node energy consumption.
|
|
| 8. |
- Saqib, Eiraj, et al.
(författare)
-
Optimizing the IoT Performance : A Case Study on Pruning a Distributed CNN
- 2023
-
Ingår i: 2023 IEEE Sensors Applications Symposium (SAS). - 9798350323078
-
Konferensbidrag (refereegranskat)abstract
- 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.
|
|
| 9. |
- Shallari, Irida, et al.
(författare)
-
Design space exploration for an IoT node : Trade-offs in processing and communication
- 2021
-
Ingår i: IEEE Access. - 2169-3536. ; 9, s. 65078-65090
-
Tidskriftsartikel (refereegranskat)abstract
- Optimising the energy consumption of IoT nodes can be tedious due to the due to complex trade-offs involved between processing and communication. In this article, we investigate the partitioning of processing between the sensor node and a server and study the energy trade-offs involved. We propose a method that provides a trade-off analysis for a given set of constraints and allows for exploring several intelligence partitioning configurations. Furthermore, we demonstrate how this method can be used for the analysis of four design examples with traditional and CNN-based image processing systems, and we also provide an implementation of it on Matlab. CCBY
|
|
| 10. |
- Tammemäe, Kalle, et al.
(författare)
-
AKKA: A Tool-kit for Cosynthesis and Prototyping
- 1996
-
Ingår i: Hardware-Software Cosynthesis for Reconfigurable Systems, IEE Colloquium, Bristol 22 Feb. 1996. - : IEE. ; , s. 8/1-8/8
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Shortened design and life time of embedded systems has motivated active research in HW/SW co-design area, together with evolution of relatively long-life of reconfigurable HW. In this paper we present Akka1[1][2] - a set of tools for design space exploration, co-simulation and co-synthesis with two industrial examples from the telecommunication field - Maintenance functionality of the ATM protocol and Channel decoder functionality of a D-AMPS base station. For fast prototyping we have selected Xilinx XC4013 FPGA based board from Virtual Computer Corporation. The board is connected to the system bus (SBus) of the host computer.
|
|
