| 1. |
- Bakowski, Mietek, et al.
(författare)
-
Theoretical Benchmarking of Vertical GaN Devices
- 2022
-
Ingår i: International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2022. - : Institute of Electrical and Electronics Engineers Inc.. - 9781665470957
-
Konferensbidrag (refereegranskat)abstract
- In this paper theoretical benchmarking of semi-vertical and vertical gallium nitride (GaN) MOSFETs with rated voltage of 1.2 kV to 3.3 kV is performed against corresponding silicon carbide (SiC) devices. Specific design features and technology requirements for realization of high voltage vertical GaN MOSFETs are discussed and implemented in simulated structures. The main findings are that a) specific on-resistance of vertical GaN devices is expected to be 75% and 40% of that for 1.2 kV and 3.3 kV SiC MOSFETs, respectively, b) semi-vertical GaN do not offer any advantage over SiC MOSFETs for medium and high voltage devices (>1.0 kV), and c) vertical GaN has largest potential advantage for high and ultra-high voltage devices (>2.0 kV).
|
|
| 2. |
- Duvignau, Romaric, 1989
(författare)
-
Metainformation Extraction from Encrypted Streaming Video Packet Traces
- 2022
-
Ingår i: International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2022. - 9781665470957 ; , s. 1-6
-
Konferensbidrag (refereegranskat)abstract
- In this study, we present a metainformation extraction pipeline and a Proof of Concept (PoC) implementation of a recognizer capable of classifying video titles, series titles as well as video genres from encrypted video streams. We show in a promising evaluation, using the Netflix and SVT Play catalogues as examples, that our PoC is capable of learning abstract data from the packet bursts visible in DASH encrypted streams (such as if a video fingerprint is rather a Drama or a Romance movie). This is, to the best of our knowledge, the first demonstration of successful extraction of video metainformation from coarse-grain encrypted network packet traces. While advocating updates in the DASH protocol in order to preserve viewers’ privacy, our results also pave the way to future computer forensics systems capable of successful content classification over encrypted channels.
|
|
| 3. |
- Kusetogullari, Anna, 1987-, et al.
(författare)
-
Genetic Algorithm-based Variable Selection Approach for High-Growth Firm Prediction
- 2022
-
Ingår i: International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2022. - : Institute of Electrical and Electronics Engineers (IEEE). - 9781665470957
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we propose a novel method for high-growth firm prediction by minimizing a cost function using a Genetic Algorithm (GA). To achieve it, the GA is used to search to find a set of important variables which provide the best fit for machine learning models so that accurate predictions can be made for high-growth firm prediction. The GA is employed to optimize the mean square error (MSE) between the accurate results and the predicted results of the machine learning methods by evolving the initially generated binary solutions through iterations. The proposed method obtains the best fitting set of variables for the machine learning methods for high-growth firm prediction. Four different machine learning methods which are Support Vector Machines (SVM), Logistic Regression, Random Forest (RF) and K-Nearest Neighbor (K-NN) have been employed with the GA and experimental results show that using RF with the GA achieves the best accuracy results with 94.93%. © 2022 IEEE.
|
|
| 4. |
- Lisova, Elena, et al.
(författare)
-
Communication Patterns for Evaluating Vehicular E/E Architectures
- 2022
-
Ingår i: International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2022. - : Institute of Electrical and Electronics Engineers Inc.. - 9781665470957
-
Konferensbidrag (refereegranskat)abstract
- The continuous innovation and advancement in vehicle software functionality has driven the evolution of its deployment platforms through several generations of vehicular Electrical and Electronic (E/E) architectures. It is a daunting task to evaluate pros and cons of allocating the new as well as legacy functionality to these architectures. In this paper, we propose a novel approach that uses communication patterns as a metric to evaluate different vehicular E/E architectures and propose a suitable allocation for the functionality. First, we present the characteristics of these patterns in vehicular systems that are derived from the state-of-the-art review, standardized vehicular software architectures, well-known onboard vehicular, communication protocols, industrial requirements and use cases. We leverage the derived communication patterns and their characteristics to propose an evaluation approach for different architectural solutions for the functionality. We utilize a use case from the vehicle industry to demonstrate the applicability and usability of the proposed approach.
|
|
