检索结果-内蒙古大学图书馆

Seven-level Cascade Multilevel Inverter based Minimum Switches for Photovoltaic applications

学校读者我要写书评

暂无评论

Seven-level Cascade Multilevel Inverter based Minimum Switch...

IEEE SSD International Multi-Conference on systems, Signals and Devices

作者： Ali Abedaljabar Al-Samawi Hafedh Trabelsi Department of Electronic and Communications Engineering College of Engineering Al-Muthanna University Al Muthanna Iraq Department of Electrical Engineering National Engineering School of Sfax (ENIS) Computer and Embedded Systems Laboratory (CES-Lab) Sfax University Sfax Tunisia

To enhance power quality and obtain high power from photovoltaic(PV), and mitigate the impact of the PV system's partial shading condition(PSC) and electrical mismatch power problems. This paper presents a single-phase, simple seven-level multilevel inverter architecture With a lower number of power components connected with four individual group PV systems integration converter DC/DC with independent Maximum Power Point Tracking(MPPT)in each group. The proposed inverter provides a reduced total harmonic distortion (THD) of voltage and unity active power. This reduction in the number of switches generates a decrease in the losses of switching and the number of drive circuits, which in turn causes a decrease in the control complication and decreases the cost and size of the control circuit. We compared this cascaded multilevel topology architecture to evaluate the performance of the suggested inverter, which needed modern cascade multilevel topologies with the same seven levels of voltage. The achievement of the comparison is dependent on several elements, including a set of parameters(diodes and capacitors), the overall harmonic distortion, and the number of switches included inside the inverter. The program(Simulink/Matlab) was used to verify the critical evaluation of the presented topology through simulation results.

关键词：

The Controllability, Observability, and Stability Analysis of a Class of Composite systems with Fractional Degree Generalized Frequency Variables

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2019年第3期6卷 859-864页

作者： Cuihong Wang Yafei Zhao YangQuan Chen IEEE the Department of Mathematics and Computer Science Shanxi Normal University the Mechatronics Embedded Systems and Automation(MESA) Lab

This paper is concerned with fundamental properties of a class of composite systems with fractional degree generalized frequency variables, including controllability, observability and stability. Firstly, some necessary and sufficient conditions are given to guarantee controllability and observability of such composite systems. Then we prove that the stability problem of such composite systems can be reduced to judging whether a fractional degree polynomial is stable. Finally, the stability analysis result is applied in the supervisory control of fractional-order multi-agent systems, and an example is provided to illustrate the effectiveness of the proposed methods.

关键词： Composite system controllability fractionalorder system observability stability

MEMORY-ENRICHED COMPUTATION AND LEARNING IN SPIKING NEURAL NETWORKS THROUGH HEBBIAN PLASTICITY

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Limbacher, Thomas Özdenizci, Ozan Legenstein, Robert Institute of Theoretical Computer Science Graz University of Technology Graz8010 Austria TU Graz SAL Dependable Embedded Systems Lab Silicon Austria Labs Graz8010 Austria

Memory is a key component of biological neural systems that enables the retention of information over a huge range of temporal scales, ranging from hundreds of milliseconds up to years. While Hebbian plasticity is believed to play a pivotal role in biological memory, it has so far been analyzed mostly in the context of pattern completion and unsupervised learning. Here, we propose that Hebbian plasticity is fundamental for computations in biological neural systems. We introduce a novel spiking neural network architecture that is enriched by Hebbian synaptic plasticity. We show that Hebbian enrichment renders spiking neural networks surprisingly versatile in terms of their computational as well as learning capabilities. It improves their abilities for out-of-distribution generalization, one-shot learning, cross-modal generative association, language processing, and reward-based learning. As spiking neural networks are the basis for energy-efficient neuromorphic hardware, this also suggests that powerful cognitive neuromorphic systems can be build based on this principle. © 2022, CC BY.

关键词： Neural networks

TS-MoCo: Time-Series Momentum Contrast for Self-Supervised Physiological Representation Learning

学校读者我要写书评

暂无评论

TS-MoCo: Time-Series Momentum Contrast for Self-Supervised P...

European Signal Processing Conference (EUSIPCO)

作者： Philipp Hallgarten David Bethge Ozan Özdcnizci Tobias Grosse-Puppendahl Enkelejda Kasneci Dr. Ing. h.c. F. Porsche AG Stuttgart Germany TU Munich Germany LMU Munich Germany Institute of Theoretical Computer Science TU Graz Austria TU Graz - SAL Dependable Embedded Systems Lab Silicon Austria Labs Graz Austria

Limited availability of labeled physiological data often prohibits the use of powerful supervised deep learning models in the biomedical machine intelligence domain. We approach this problem and propose a novel encoding framework that relies on self-supervised learning with momentum contrast to learn representations from multivariate time-series of various physiological domains without needing labels. Our model uses a transformer architecture that can be easily adapted to classification problems by optimizing a linear output classification layer. We experimentally evaluate our framework using two publicly available physiological datasets from different domains, i.e., human activity recognition from embedded inertial sensory and emotion recognition from electroencephalography. We show that our self-supervised learning approach can indeed learn discriminative features which can be exploited in downstream classification tasks. Our work enables the development of domain-agnostic intelligent systems that can effectively analyze multivariate time-series data from physiological domains.

关键词：

TS-MoCo: Time-Series Momentum Contrast for Self-Supervised Physiological Representation Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hallgarten, Philipp Bethge, David Özdenizci, Ozan Grosse-Puppendahl, Tobias Kasneci, Enkelejda Dr. Ing. h.c. F. Porsche AG Stuttgart Germany TU Munich Germany LMU Munich Germany Institute of Theoretical Computer Science TU Graz Austria TU Graz SAL Dependable Embedded Systems Lab Silicon Austria Labs Graz Austria

关键词： Emotion Recognition

A Multi-view Deep Convolutional Neural Network for Reduction of False Positive Findings in Breast Cancer Screening

学校读者我要写书评

暂无评论

A Multi-view Deep Convolutional Neural Network for Reduction...

International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)

作者： Nouha Derbel Hedi Tmar Adel Mahfoudhi Computer & Embedded Systems Lab University of Sfax Sfax Tunisia

ISBN: (数字)9781728175133

ISBN: (纸本)9781728175140

Screening mammography is commonly the only imaging exam allowing early-stage detection of breast cancer. The early detection is, in fact, associated with a decreased breast cancer mortality rate amongst women. However, false positive recall is one of the main limitations of screening practices and it is often associated with unnecessary workups and biopsies. To tackle this issue and improve the medical image classification performance in order to carry out a screening/diagnosis task, we propose to use a multi-view deep convolutional neural network - the proposed network can extract discriminative features from Cranial Caudal (CC) and Medio-Lateral Oblique (MLO) views for each breast of a patient (a set of four images). We experiment it on an augmented-data based subset selected from the open Digital Database for Screening Mammography (DDSM) using 5400 images. We show how the proposed method can lead to a better performance than the state-of-the-art ones, especially in terms of prediction accuracy and false positive rate reduction. In fact, The results show statistically significant reduction in false findings without increasing false negative cases. Our method achieves a specificity rate of 98% and an accuracy rate of 98.88%. Index Terms-Mammography, Breast cancer diagnosis, False positive findings, Deep learning, Multi-view deep convolutional neural network.

关键词： Breast cancer Training Mammography Task analysis Biomedical imaging Biopsy Linear programming

Vote and KNN outlier detection in Wireless Sensor Networks

学校读者我要写书评

暂无评论

Vote and KNN outlier detection in Wireless Sensor Networks

International Symposium on Networks, computers and Communications (ISNCC)

作者： Aymen Abid Salim El Khediri Tarek Moulahi Rym Cheour Abdennaceur Kachouri Computer and Embedded Systems Lab National Engineering School Sfax TUNISIA College of Computer Qassim University Qassim KSA Laboratoire HATEM Bettaher (IRESCOMATH) Gabes Tunisia Advanced Fluid Dynamics Energetics and Evironment Lab National Engineering School Sfax TUNISIA

The target of a Wireless Sensor Network (WSN) designer is to improve the robustness of the network while taking into account constraints such as verifying the detection of anomalies. Preventing anomalies can be assured by data analysis via outliers identification as it strongly affects decision-making in the case of smart-home, e-health and other high-risk applications. In this paper, we study some families of outliers and we propose to detect data anomalies using K Nearest Neighbours (KNN) and Voting techniques by a benchmark suitable to be a simulation for a smart-house. In order to evaluate the dependability, some performance metrics are analyzed such as data rate detection, precision, specificity and accuracy. Performance results are in the order of 100% detection rate with reduced false alarm and fast response time compared to some other existing ones.

关键词：

Stochastic mutual information gradient estimation for dimensionality reduction networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Özdenizci, Ozan Erdogmuş, Deniz Department of Electrical and Computer Engineering Northeastern University BostonMA United States Institute of Theoretical Computer Science Graz University of Technology Graz Austria TU Graz - SAL Dependable Embedded Systems Lab Silicon Austria Labs Graz Austria

Feature ranking and selection is a widely used approach in various applications of supervised dimensionality reduction in discriminative machine learning. Nevertheless there exists significant evidence on feature ranking and selection algorithms based on any criterion leading to potentially sub-optimal solutions for class separability. In that regard, we introduce emerging information theoretic feature transformation protocols as an end-to-end neural network training approach. We present a dimensionality reduction network (MMINet) training procedure based on the stochastic estimate of the mutual information gradient. The network projects high-dimensional features onto an output feature space where lower dimensional representations of features carry maximum mutual information with their associated class labels. Furthermore, we formulate the training objective to be estimated non-parametrically with no distributional assumptions. We experimentally evaluate our method with applications to high-dimensional biological data sets, and relate it to conventional feature selection algorithms to form a special case of our approach. © 2021, CC BY-NC-ND.

关键词： Neural networks

DOMAIN-INVARIANT REPRESENTATION LEARNING FROM EEG WITH PRIVATE ENCODERS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bethge, David Hallgarten, Philipp Grosse-Puppendahl, Tobias Kari, Mohamed Mikut, Ralf Schmidt, Albrecht Özdenizci, Ozan Dr. Ing. h.c. F. Porsche AG Stuttgart Germany Ludwig-Maximilians University Munich Germany Karlsruhe Institute of Technology Germany Institute of Theoretical Computer Science Graz University of Technology Austria TU Graz - SAL Dependable Embedded Systems Lab Silicon Austria Labs Austria

Deep learning based electroencephalography (EEG) signal processing methods are known to suffer from poor test-time generalization due to the changes in data distribution. This becomes a more challenging problem when privacy-preserving representation learning is of interest such as in clinical settings. To that end, we propose a multi-source learning architecture where we extract domain-invariant representations from dataset-specific private encoders. Our model utilizes a maximum-mean-discrepancy (MMD) based domain alignment approach to impose domain-invariance for encoded representations, which outperforms state-of-the-art approaches in EEG-based emotion classification. Furthermore, representations learned in our pipeline preserve domain privacy as dataset-specific private encoding alleviates the need for conventional, centralized EEG-based deep neural network training approaches with shared parameters. Copyright © 2022, The Authors. All rights reserved.

关键词： Electroencephalography