检索结果-内蒙古大学图书馆

A Recurrent Neural Network for Multimodal Anomaly Detection by Using Spatio-Temporal Audio-Visual Data

computers, Materials & Continua 2024年第11期81卷 2493-2515页

作者： Sameema Tariq Ata-Ur-Rehman Maria Abubakar Waseem Iqbal Hatoon S.Alsagri Yousef A.Alduraywish Haya Abdullah AAlhakbani Department of Electrical Engineering University of Engineering and TechnologyLahore54890Pakistan Department of Electrical Engineering National University of Science and TechnologyNational University of Sciences and TechnologyIslamabad24090Pakistan Department of Business and Computing Ravensbourne University LondonRavensbourne UniversityLondonSE100EWEngland Electrical and Computer Engineering Department College of EngineeringSultan Qaboos UniversityMuscat123Oman College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11673Saudi Arabia

In video surveillance,anomaly detection requires training machine learning models on spatio-temporal video ***,sometimes the video-only data is not sufficient to accurately detect all the abnormal ***,we propose a novel audio-visual spatiotemporal autoencoder specifically designed to detect anomalies for video surveillance by utilizing audio data along with video *** paper presents a competitive approach to a multi-modal recurrent neural network for anomaly detection that combines separate spatial and temporal autoencoders to leverage both spatial and temporal features in audio-visual *** proposed model is trained to produce low reconstruction error for normal data and high error for abnormal data,effectively distinguishing between the two and assigning an anomaly *** is conducted on normal datasets,while testing is performed on both normal and anomalous *** anomaly scores from the models are combined using a late fusion technique,and a deep dense layer model is trained to produce decisive scores indicating whether a sequence is normal or *** model’s performance is evaluated on the University of California,San Diego Pedestrian 2(UCSD PED 2),University of Minnesota(UMN),and Tampere University of technology(TUT)Rare Sound Events datasets using six evaluation *** is compared with state-of-the-art methods depicting a high Area Under Curve(AUC)and a low Equal Error Rate(EER),achieving an(AUC)of 93.1 and an(EER)of 8.1 for the(UCSD)dataset,and an(AUC)of 94.9 and an(EER)of 5.9 for the UMN *** evaluations demonstrate that the joint results from the combined audio-visual model outperform those from separate models,highlighting the competitive advantage of the proposed multi-modal approach.

关键词： Acoustic-visual anomaly detection sequence-to-sequence autoencoder reconstruction error late fusion regularity score

来源：评论

学校读者我要写书评

暂无评论

Isolated Soft Switched Resonant Led Driver with Constant Output Current and Wide Input Voltage Range 16

Isolated Soft Switched Resonant Led Driver with Constant Out...

引用

16th Annual Power Electronics, Drive Systems, and Technologies Conference, PEDSTC 2025

作者： Askari, Shirin Farzanehfard, Hosein Maghsoudi, Mohammad Isfahan University of Technology Department of Electrical and Computer Engineering Isfahan Iran

ISBN: (纸本)9798331533946

This paper proposes an isolated LCC resonant converter (LCC-RC) designed to deliver a constant output current for LED drivers across a wide range of input voltages by integrating a boost front-end stage with an LCC resonant converter. This topology leverages an LCC network to deliver numerous advantages. It integrates the boost filter inductor and transformer magnetizing inductance, ensuring that the primary switches achieve full Zero Voltage Switching (ZVS) and the secondary rectifier diodes experience Zero Current Switching (ZCS) across a wide range of duty cycles. Notably, the output current remains load-independent, making this configuration well-suited for LED applications. In addition, efficiency is improved by functioning near the resonant frequency. The hybrid structure of the proposed converter facilitates the use of a straightforward constant-frequency asymmetrical pulsewidth modulation (APWM) scheme to control the output current. To confirm the theoretical analysis and validate the LED driver functionality, a 50 W experimental prototype of the proposed driver was successfully created in the laboratory. This prototype supports an extensive input voltage range spanning from 18 V to 40 V, enabling it to supply a 500 mA output current to a series of 1 to 30 LEDs. This corresponds to an extensive output voltage capability spanning 3.3-100 V. © 2025 IEEE.

关键词： Zero voltage switching

来源：评论

学校读者我要写书评

暂无评论

Strategic Renewable Energy Resource Selection Using a Fuzzy Decision-Making Method

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 2117-2134页

作者： Anas Quteishat M.A.A.Younis Electrical Engineering Department Faculty of Engineering TechnologyAl-Balqa Applied UniversityAl-SaltJordan Department of Electrical and Computer Engineering Sohar UniversitySultanate of Oman

Renewable energy is created by renewable natural resources such as geothermal heat,sunlight,tides,rain,and *** resources are vital for all countries in terms of their economies and *** a result,selecting the optimal option for any country is critical in terms of energy *** country is nowadays planning to increase the share of renewable energy in their universal energy sources as a result of global *** the present work,the authors suggest fuzzy multi-characteristic decision-making approaches for renew-able energy source selection,and fuzzy set theory is a valuable methodology for dealing with uncertainty in the presence of incomplete or ambiguous *** study employed a hybrid method for order of preference by resemblance to an ideal solution based on fuzzy analytical network process-technique,which agrees with professional assessment scores to be linguistic phrases,fuzzy numbers,or crisp *** hybrid methodology is based on fuzzy set ideologies,which calculate alternatives in accordance with professional functional requirements using objective or subjective *** best-suited renewable energy alternative is discovered using the approach presented.

关键词： Multi characteristic decision making framework fuzzy sets fuzzy theory renewable energy energy resource selection

来源：评论

学校读者我要写书评

暂无评论

Fully Soft Switched Bridgeless Buck Power Factor Correction Converter 16

Fully Soft Switched Bridgeless Buck Power Factor Correction ...

引用

16th Annual Power Electronics, Drive Systems, and Technologies Conference, PEDSTC 2025

作者： Kaviani, Kosar Maghsoudi, Mohammad Farzanehfard, Hosein Isfahan University of Technology Department of Electrical and Computer Engineering Isfahan Iran

ISBN: (纸本)9798331533946

In this paper, a bridgeless buck PFC structure is presented. To Fulfill soft switching for the main switches an auxiliary circuitry is utilized. The main switches of the proposed structure operate under ZVS condition and the auxiliary switch operate under ZCS condition. The introduced topology operates at Discontinuous conduction mode (DCM) leading to intrinsic PFC capability. A 120 W, 100 kHz prototype is designed and simulated to validate theoretical analysis using PSIM software. The results show 97% efficiency and fully soft switching operation. © 2025 IEEE.

关键词： Buck converter

来源：评论

学校读者我要写书评

暂无评论

Outdoor navigation for visually impaired people using YOLOv5 and Transfer learning: an analytical study

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Shariatinezhad, Monir Molaeezadeh, Seyyedeh Fatemeh Gholami, Mohammad Department of Electrical and Computer Engineering Jundi-Shapur University of Technology Po.Box: 64615-334 Dezful Iran

This study introduces an obstacle detection system for visual impairment rehabilitation in visually impaired individuals, leveraging YOLOv5 and transfer learning. The methodology comprises four main phases. First phase is sidewalk dataset generation, involving creating our customized PESID dataset and a proprietary dataset. Second phase is image annotation into eight essential obstacle classes. We pay special attention to edges, slopes, and holes—often overlooked in existing sidewalk datasets. These aspects are crucial for ensuring the safety of visually impaired individuals. Third phase is model pretraining with the large-scale COCO dataset. Last phase is fine-tuning using transfer learning on specialized datasets. The evaluated models for obstacle detection include YOLOv3, YOLOv5s, YOLOv5l, YOLOv5x, YOLOv5n, MobilenetSSDv2, Detectron2, RetinaNet, and Faster RCNN. On the customized PESID dataset, YOLOv5s, YOLOv5x, YOLOv5m, and YOLOv5l outperform other models in terms of Mean Average Precision at an Intersection of Union (IOU) of 0.5 (MAP0.5) and detection speed. On our proprietary dataset, the YOLOv5l model achieves a MAP0.5 of 84.5% and 77 frames per second. Notably, the MAP0.5 scores for edges, slopes, and holes are 77%, 85%, and 84%, respectively. Additionally, improving image annotation quality significantly enhances model accuracy by more than 10% for two datasets. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Applications of Polymer Nanocomposites in High Voltage engineering: A Concise Review on Possible Applications and Questions Regarding Some Limitations

引用

Journal of engineering Science and technology Review 2023年第5期16卷 156-163页

作者： Tsianakas, Vassilios Danikas, Michael G. Sarathi, Ramanujam Falekas, Georgios Democritus University of Thrace School of Engineering Department of Electrical and Computer Engineering Xanthi67100 Greece Indian Institute of Technology Madras Department of Electrical Engineering Chennai India

Polymer nanocomposites have been a topic of intensive research regarding High Voltage engineering since the nineties of the last century. They present an alternative to conventional polymers since the latter were diagnosed with certain drawbacks. In this paper, a short review is given as to the basic characteristics of the polymer nanocomposites and some comments are offered as to the possible applications of the said materials in High Voltage engineering. © 2023 School of Science, IHU. All rights reserved

关键词： Partial discharges

来源：评论

学校读者我要写书评

暂无评论

Artificial visual perception neural system using a solution-processable MoS_(2)-based in-memory light sensor

引用

Light(Science & Applications) 2023年第8期12卷 1583-1594页

作者： Dayanand Kumar Lana Joharji Hanrui Li Ayman Rezk Ammar Nayfeh Nazek El-Atab Smart Advanced Memory Devices and Applications(SAMA)LaboratoryElectrical and Computer Engineering ProgramComputer Electrical Mathematical Science and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955Kingdom of Saudi Arabia Department of Electrical Engineering and Computer Science Khalifa UniversityAbu Dhabi 127788United Arab Emirates

Optoelectronic devices are advantageous in in-memory light sensing for visual information processing,recognition,and storage in an energy-efficient ***,in-memory light sensors have been proposed to improve the energy,area,and time efficiencies of neuromorphic computing *** study is primarily focused on the development of a single sensing-storage-processing node based on a two-terminal solution-processable MoS2 metal-oxide-semiconductor(MOS)charge-trapping memory structure—the basic structure for charge-coupled devices(CCD)—and showing its suitability for in-memory light sensing and artificial visual *** memory window of the device increased from 2.8 V to more than 6V when the device was irradiated with optical lights of different wavelengths during the program ***,the charge retention capability of the device at a high temperature(100 ℃)was enhanced from 36 to 64%when exposed to a light wavelength of 400 *** larger shift in the threshold voltage with an increasing operating voltage confirmed that more charges were trapped at the Al_(2)O_(3)/MoS_(2) interface and in the MoS_(2) layer.A small convolutional neural network was proposed to measure the optical sensing and electrical programming abilities of the *** array simulation received optical images transmitted using a blue light wavelength and performed inference computation to process and recognize the images with 91%*** study is a significant step toward the development of optoelectronic MOS memory devices for neuromorphic visual perception,adaptive parallel processing networks for in-memory light sensing,and smart CCD cameras with artificial visual perception capabilities.

关键词： visual neural process

来源：评论

学校读者我要写书评

暂无评论

A Generic, High-Performance, Compression-Aware Framework for Data Parallel DNN Training

引用

IEEE Transactions on Parallel and Distributed Systems 2023年 1-20页

作者： Wu, Hao Wang, Shiyi Bai, Youhui Li, Cheng Zhou, Quan Yi, Jun Yan, Feng Chen, Ruichuan Xu, Yinlong Department of Computer Science and Technology University of Science and Technology of China Hefei China Computer Science Department and Electrical and Computer Engineering Department University of Houston USA Nokia Bell Labs

Gradient compression is a promising approach to alleviating the communication bottleneck in data parallel deep neural network (DNN) training by significantly reducing the data volume of gradients for synchronization. While gradient compression is being actively adopted by the industry (e.g., Facebook and AWS), our study reveals that there are two critical but often overlooked challenges: 1) inefficient coordination between compression and communication during gradient synchronization incurs substantial overheads, and 2) developing, optimizing, and integrating gradient compression algorithms into DNN systems imposes heavy burdens on DNN practitioners, and ad-hoc compression implementations often yield surprisingly poor system performance. In this paper, we propose a compression-aware gradient synchronization architecture, CaSync, which relies on flexible composition of basic computing and communication primitives. It is general and compatible with any gradient compression algorithms and gradient synchronization strategies and enables high-performance computation-communication pipelining. We further introduce a gradient compression toolkit, CompLL, to enable efficient development and automated integration of on-GPU compression algorithms into DNN systems with little programming burden. Lastly, we build a compression-aware DNN training framework HiPress with CaSync and CompLL. HiPress is open-sourced and runs on mainstream DNN systems such as MXNet, TensorFlow, and PyTorch. Evaluation via a 16-node cluster with 128 NVIDIA V100 GPUs and a 100 Gbps network shows that HiPress improves the training speed over current compression-enabled systems (e.g., BytePS-onebit, Ring-DGC and PyTorch-PowerSGD) by 9.8%-69.5% across six popular DNN models. IEEE

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Integrating the Internet of Things to Protect Electric Vehicle Control Systems from Cyber Attacks

引用

IAENG International Journal of Applied Mathematics 2024年第3期54卷 433-440页

作者： Bhukya, Baddu Naik Venkataiah, V. Kuchibhatla, S. Mani Koteswari, S. Kumari, R.V.S. Lakshmi Raju, Yallapragada Ravi Department of Electrical and Electronics Engineering Prasad V. Potluri Siddhartha Institute of Technology Andhra Pradesh Vijayawada India Department of Computer Science Engineering CMR College of Engineering & Technology Telangana Hyderabad India Department of Electrical and Electronics Engineering ACE Engineering College Telangana Hyderabad India Department of Electronics and Communication Engineering Pragati Engineering College Kakinada India Andhra Pradesh Surampalem India Department of Electrical and Electronics Engineering Gayatri Vidya Parishad College of Engineering for Women Andhra Pradesh Visakhapatnam India Department of Computer Science and Technology Madanapalle Institute of Technology and Science Andhra Pradesh India

The Internet of Things (IoT) facilitates the delivery of intelligent services by sensing, gathering, processing, and exchanging data from millions of linked smart devices. The Internet of Things (IoT), which is based on communication infrastructure, provides real-time cyber-physical device monitoring, control, and sensing, such as electric autos. Traditional communication infrastructure's vulnerability to cyberattacks hampered IoT's capacity to investigate these potential applications. This study proposes an algorithm for monitoring and controlling electric vehicles through the Internet of Things communication network to prevent fake data injection attacks. A state-space model depicts a fully autonomous electric car equipped with a vision system. Intelligent sensors and actuators from the Internet of Things are utilized to monitor and change system conditions, compensating for the large distance between the electric car and the control center. Sensing data is delivered from the vehicle to the central command center via an insecure, attack-prone communication path. The mean square error approach is used to derive states in the most effective state estimation system for comprehending and showing autos. A semi-definite programming approach is used to create an optimal control algorithm to manage the vehicle states. The simulation results show how precisely and successfully the proposed algorithms can foresee and regulate a vehicle's state. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Highly transparent anti-reflection coating enhances the underwater efficiency and stability of perovskite solar modules

引用

Nano Research 2024年第9期17卷 8126-8133页

作者： Feng Qian Shihao Yuan Ting Zhang Lei Wang Xiaobo Li Hualin Zheng Qien Xu Zhi David Chen Shibin Li School of Optoelectronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu 610054China Department of Electrical and Computer Engineering and Center for Nanoscale Science and Engineering University of KentuckyLexingtonKentucky 40506USA

Perovskite solar cells have shown great potential in the field of underwater solar cells due to their excellent optoelectronic properties;however,their underwater performance and stability still hinder their practical *** this research,a 1H,1H,2H,2H-heptadecafluorodecyl acrylate(HFDA)anti-reflection coating(ARC)was introduced as a high-transparent material for encapsulating perovskite solar modules(PSMs).Optical characterization results revealed that HFDA can effectively reduce reflection of light below 800 nm,aiding in the absorption of light within this wavelength range by underwater solar ***,a remarkable efficiency of 14.65%was achieved even at a water depth of 50 ***,the concentration of Pb^(2+)for HFDA-encapsulated film is significantly reduced from 186 to 16.5 ppb after being immersed in water for 347 ***,the encapsulated PSMs still remained above 80%of their initial efficiency after continuous underwater illumination for 400 ***,being exposed to air,the encapsulated PSMs maintained 94%of their original efficiency after 1000 h light *** highly transparent ARC shows great potentials in enhancing the stability of perovskite devices,applicable not only to underwater cells but also extendable to land-based photovoltaic devices.

关键词： underwater photovoltaics perovskite solar modules anti-reflection coating underwater stability

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：