检索结果-内蒙古大学图书馆

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Dharmateja, M. Rama, Prabha K.P. Asha, N. Nithya, P. Lalitha, S. Manojkumar, P. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Arunai Engineering College Department of Computer Science and Engineering Tamil Nadu Tiruvannamalai India Bannari Amman Institute of Technology Department of Electrical and Electronics Engineering Tamil Nadu Sathyamangalam India

ISBN: (纸本)9798350382952

Wireless Sensor Actuator Networks (WSANs) are sensitive to cyber threats due to present static encryption techniques. Adaptive security methods are required in WSAN settings to reduce evolving dangers and maintain data integrity. The paper introduces a novel method for encrypting WSAN data using AI and machine learning. Long Short-Term Memory (LSTM) networks process data, Genetic Algorithms (GAs) optimize encryption, and Isolation Forests detect threats in real-time. The proposed system achieved remarkable performance, with scores of 98% data integrity, 96% error repair, and 95% threat detection accuracy. Encryption rates reach their max at 200 Mbps, with optimal resource usage (30% CPU, 25% RAM) and a 5% false positive rate. The proposed AI-driven security architecture improves data integrity, encryption speed, and overall security efficacy in WSANs, surpassing existing methods. The paper overcomes the limitations of static encryption methods and proposes a proactive protection mechanism against developing cyber threats, making a substantial contribution to WSAN security improvement. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 697-711页

作者： Liu, Xin Yuan, Kaishen Niu, Xuesong Shi, Jingang Yu, Zitong Yue, Huanjing Yang, Jingyu Tianjin University School of Electrical and Information Engineering Tianjin300072 China Lappeenranta-Lahti University of Technology LUT Computer Vision and Pattern Recognition Laboratory School of Engineering Science Lappeenranta53850 Finland Beijing Institute for General Artificial Intelligence Beijing100080 China Xi'an Jiaotong University School of Software Engineering Xi'an710049 China Great Bay University Dongguan523000 China

Facial Action Unit (AU) detection is a crucial task in affective computing and social robotics as it helps to identify emotions expressed through facial expressions. Anatomically, there are innumerable correlations between AUs, which contain rich information and are vital for AU detection. Previous methods used fixed AU correlations based on expert experience or statistical rules on specific benchmarks, but it is challenging to comprehensively reflect complex correlations between AUs via hand-crafted settings. There are alternative methods that employ a fully connected graph to learn these dependencies exhaustively. However, these approaches can result in a computational explosion and high dependency with a large dataset. To address these challenges, this paper proposes a novel self-adjusting AU-correlation learning (SACL) method with less computation for AU detection. This method adaptively learns and updates AU correlation graphs by efficiently leveraging the characteristics of different levels of AU motion and emotion representation information extracted in different stages of the network. Moreover, this paper explores the role of multi-scale learning in correlation information extraction, and design a simple yet effective multi-scale feature learning (MSFL) method to promote better performance in AU detection. By integrating AU correlation information with multi-scale features, the proposed method obtains a more robust feature representation for the final AU detection. Extensive experiments show that the proposed method outperforms the state-of-the-art methods on widely used AU detection benchmark datasets, with only 28.7% and 12.0% of the parameters and FLOPs of the best method, respectively. The code for this method is available at https://***/linuxsino/Self-adjusting-AU. © 2010-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Parasitic Inductance of Surge Protective Devices for a Wide Frequency Range 37

Parasitic Inductance of Surge Protective Devices for a Wide ...

引用

37th International Conference on Lightning Protection, ICLP 2024

作者： Hadjicostas, Alexandros Chrysochos, Andreas Tsovilis, Thomas High Voltage Laboratory School of Electrical and Computer Engineering Aristotle University of Thessaloniki Thessaloniki54124 Greece R&D Department Hellenic Cables Athens15125 Greece

ISBN: (纸本)9783800764174

This work investigates the efficacy of different experimental and simulation methodologies in determining the parasitic inductance of surge protective devices for a broad frequency spectrum. This is important since the inductive behavior of surge protective devices affects their maximum residual voltage, thus also the protection offered in the case of fast-front transients exhibiting high current derivatives. The parasitic inductance of a commercially available DIN rail surge protective device is determined by utilizing a dummy surge protective device with the voltage limiting component (varistor) replaced by a copper block. Parasitic inductance estimations are made by employing: i) dielectric spectroscopy measurements, ii) impulse current tests, and iii) finite element analysis simulations;results are discussed in terms of the accuracy of the proposed methods and associated challenges in determining the parasitic inductance. © 2024 IEEE, © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Surge protection

来源：评论

学校读者我要写书评

暂无评论

Detection of Lung and Colon Cancer Using Transfer and Ensemble Learning 24

Detection of Lung and Colon Cancer Using Transfer and Ensemb...

引用

7th International Conference on Networking, Intelligent systems and Security, NISS 2024

作者： Oubaalla, Abdelwahid Elmoubtahij Merras Elakkad, Nabil Engineering Systems and Applications Laboratory Ensa Sidi Mohamed Ben Abdellah University Fez Morocco Computer Engineering Higher School of Technology University of Ibn Zohr Agadir Morocco Image Laboratory High School of Technology Moulay Ismail University Meknes Morocco

ISBN: (纸本)9798400709296

Colon and lung cancers are responsible for the deaths of thousands of people worldwide every year. Early detection of these cancers can significantly increase the chances of recovery. This is achieved by analyzing histopathological images. This task has traditionally been performed by manual methods. As a result, the results of these analysis are highly dependent on the skills and professional experience of the pathologist, consuming time and manpower. Several studies have attempted to automate this task using deep learning techniques, in particular the convolutional neural network (CNN) models. In this paper, in order to enhance the classification performances on LC25000 histopathological images, we used transfer learning techniques to train three models based on the pre-trained models: VGG, ResNet and DenseNet. Next, we created a model based on the ensemble learning technique in order to enhance the classification performance of these images. This model successfully improved classification performances by achieving an accuracy of 97.4% on test data, 97% on training data and 97.5% on validation data. The aim of this paper is to demonstrate the effect of combining transfer learning and ensemble learning techniques in improving the performances of colon and lung cancer histopathological image classification. © 2024 ACM.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Enhancing precision livestock management with IoT: Insights from the WELLNESS project 11

Enhancing precision livestock management with IoT: Insights ...

引用

11th International Conference on Information and Communication Technologies in Agriculture, Food and Environment, HAICTA 2024

作者： Karampelia, Ioanna Banti, Konstantina Theodorou, Dimitrios Iliadis, Stylianos Chatzisavvas, Antonios Iatrou, Anna Maria Malamakis, Apostolos Banias, Georgios F. Louta, Malamati Kyriakidis, Thomas Dasygenis, Minas Department of Electrical and Computer Engineering University of Western Macedonia Kozani Greece Laboratory of Animal Husbandry School of Veterinary Medicine Aristotle University of Thessaloniki 54124 Greece Thessaloniki Greece

The utilization of Information and Communication Technologies (ICT) in livestock management has revolutionized traditional farming practices, enabling farmers to operate with precision and efficiency. ICT technologies facilitate real-time monitoring of animal health, behavior, and environmental conditions supporting productivity and sustainable farming practices. The objective of WELLNESS Project is to use ICT technologies in small ruminant systems located in Bourinos mountain region. GPS trackers were fitted on individual sheep and goats that were randomly selected from three flocks raised semi-intensively in order to monitor movement patterns and behaviour. In two farms portable meteorological stations were mounted in the outside walls of the barn to collect weather data. One station used LoRaWAN technology for efficient, long-range data transmission. This approach aims to allow for the correlation of environmental factors with livestock behavior, enabling the development of wellbeing indices and the assessment of milk quality specific to the Bourinos mountain region. © 2024 Copyright for this paper by its authors.

关键词： animal welfare Internet of Things (IoT) precision livestock smart collars sustainable agriculture

来源：评论

学校读者我要写书评

暂无评论

Exact Statistics and Tight Approximations for RIS-Assisted Communications in Generalized Fading Environments 100

Exact Statistics and Tight Approximations for RIS-Assisted C...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Luna Alvarado, Maria Cecilia Rafael Nogueira Da Silva, Carlos Simmons, Nidhi Sofotasios, Paschalis C. Cotton, Simon L. Yacoub, Michel Daoud University of Campinas Wireless Technology Laboratory School of Electrical and Computer Engineering Campinas Brazil Federal University of Triângulo Mineiro Department of Electrical Engineering Uberaba Brazil Belfast United Kingdom Khalifa University C2PS and 6G Center Department of Computer and Information Engineering Abu Dhabi United Arab Emirates

ISBN: (纸本)9798331517786

Reconfigurable Intelligent Surfaces (RISs) are considered a key candidate technology for next-generation 6G wireless systems, promising to extend network coverage, enhance spectral efficiency, and effectively mitigate interference. RISs will achieve this by controlling the propagation environment, enabled by carefully altering the reflective properties of their elements. In this context, this work presents a general framework for deriving the exact probability density function (PDF) and higher-order moments of the signal-to-ratio (SNR) in a RIS system, considering the direct transmission and RIS-assisted links from source to destination. Recognizing the analytical challenges associated with obtaining exact statistics for RIS-assisted systems, which persist in both common and more generalized fading models, the proposed contribution is realized with the aid of the suitable α-μ fading model. To that end, we derive accurate approximations for the κ-μ and the extended η-μ distributions, which constitute effective and versatile multipath fading models. Based on this, the achieved results are virtually indistinguishable from those obtained through simulations for various environmental settings. This renders the proposed framework a valuable tool for evaluating the performance of RIS systems, particularly in terms of the corresponding average symbol error rate (ASER). Tractable closed-form asymptotic expressions are also derived and utilized to provide a deeper understanding of the system's behavior. © 2024 IEEE.

关键词： Multipath fading

来源：评论

学校读者我要写书评

暂无评论

Enhancing Performance in Hybrid Satellite-Terrestrial Networks: A Novel Joint NOMA-NC Approach

Enhancing Performance in Hybrid Satellite-Terrestrial Networ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Karavolos, Michail Moraitis, Nektarios Tsipi, Lefteris Vouyioukas, Demosthenes University of the Aegean Dept. of Information and Communication Systems Engineering Samos83200 Greece National Technical University of Athens School of Electrical and Computer Engineering Zografou15773 Greece University of Piraeus Dept. of Digital Systems Piraeus18534 Greece

ISBN: (纸本)9798350351255

An appealing alternative towards dealing with mobility and coverage challenges in future wireless networks, are hybrid satellite-terrestrial networks (HSTNs). The combination of network coding (NC) and non-orthogonal multiple access (NOMA) techniques, have recently gained popularity due to their performance gains in improving the quality of a wireless transmission and exploiting the accessible spectrum. This paper introduces a joint NOMA-NC approach, integrated to an HSTN comprising a satellite, a terrestrial base station (BS), and multiple ground-based mobile terminals (MTs). The suggested method facilitates a cluster of end-users to be concurrently served through NOMA from a satellite using optimal power allocation, whereas the BS utilizes random linear NC to augment the MTs' reception in the event of errors. The simulation results confirm the effectiveness of the proposed methodology in improving system sum throughput, demonstrating substantial enhancements compared with both OMA with NC, and standalone NOMA and OMA approaches. The resilience of the suggested method is proved, improving the sum throughput even at low power transmissions and in the worst case channel conditions. © 2024 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Study of the Behavior of Water Droplets under the Influence of a Uniform Electric Field on Samples of Borosilicate Glass

引用

Journal of engineering Science and Technology Review 2022年第7期14卷 67-70页

作者： Baroutis, Ioannis Danikas, Michael G. Sarathi, Ramanujam Democritus University of Thrace School of Engineering Department of Electrical and Computer Engineering Xanthi67100 Greece Indian Institute of Technology Madras Department of Electrical Engineering High Voltage Laboratory Chennai600 036 India

This paper investigates the behavior of water droplets on the surface of borosilicate glass samples. Borosilicate glass is used in MEMS and this is due to its special properties, such as its excellent insulating property, its inertness to most chemical substances, its easy connection to silicon and its optical permeability. In this paper, water droplet conductivities and wet etched borosilicate glass samples– are investigated. It seems that droplet conductivity plays a dominant role in determining the flashover voltage of the aforementioned samples. © 2021

关键词： Surface discharges

来源：评论

学校读者我要写书评

暂无评论

Coverage analysis and handover strategy in RF/VLC heterogeneous networks

引用

Applied Optics 2025年第15期64卷 4160-4173页

作者： Feng, Renhai Guo, Yatong Yousaf, Muhammad Zain Khan, Baseem Luo, Liping School of Electrical and Information Engineering Tianjin University Tianjin300072 China School of Physics and Electronic Engineering Xinjiang Normal University Ürümqi830054 China Center for Renewable Energy and Microgrids Huanjiang Laboratory Zhejiang University Zhejiang Zhuji311816 China School of Electrical and Information Engineering Hubei University of Automotive Technology Shiyan China School of Aeronautics and Astronautics Zhejiang University Hangzhou310027 China Department of Electrical and Computer Engineering Hawassa University Hawassa Ethiopia School of Electronics and Information Guangxi Minzu University Nanning530006 China Guangxi Colleges Universities Engineering Research Center for Multi-modal Information Intelligent Sensing Processing and Application Nanning530006 China

Coverage analysis in heterogeneous networks (HetNets) remains insufficient, especially under user mobility and diverse association strategies. To address this, this paper proposes a contact probability and coverage approximation based on association strategy (CPCA-AS) to analyze the coverage probability (CPr) in visible light communication (VLC) and radio frequency (RF) HetNets. Based on the proposed stochastic geometry framework, CPCA-AS evaluates coverage performance under various configurations, including RF-only, VLC-only, and hybrid RF/VLC scenarios. The model incorporates a contact probability mechanism and considers two strategies: opportunistic VLC and maximum received signal power (MRSP). For VLC networks, CPCA-AS utilizes the Gil-Pelaez inversion theorem, and Laplace transforms to efficiently approximate CPr. For RF networks, Markov and Gamma inequalities form conservative accurate approximations and lower bounds. CPCA-AS effectively captures the influence of the photodetector’s field-of-view (FoV) on interference and association behavior. Monte Carlo simulations validate the accuracy of the CPCA-AS. Results demonstrate that CPCA-AS improves CPr. The opportunistic VLC strategy performs better in high-interference and large FoV scenarios. In contrast, the MRSP strategy is more effective in low-interference and low-rate environments. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Work-in-Progress: A Hybrid Collaborative Multi Agent Decision Making Algorithm With Factored-Value Max-Plus

Work-in-Progress: A Hybrid Collaborative Multi Agent Decisio...

引用

2023 IEEE International Black Sea Conference on Communications and Networking, BlackSeaCom 2023

作者： Cotae, Paul Reindorf, Nii Emil Alexander Kang, Myong Velazquez, Alexander The University of the District of Columbia Department of Electrical and Computer Engineering WashingtonDC United States Center for High Assurance Computer Systems U. S. Naval Research Laboratory WashingtonDC United States

ISBN: (纸本)9798350337822

We focus on a real-time multi agent decision-making algorithm that combines a centralized algorithm and a distributed algorithm. A network segmentation is unavoidable in a dynamic environment. In such cases, it is necessary for each agent to continually make the most urgent real-time decisions in both centralized and decentralized ways. In this paper, we present a Hybrid Factored-Value Max-Plus algorithm with cost which has online, anytime, and scalable properties despite network segmentation. We also study the performance of centralized and distributed algorithms to understand the performance characteristics of a hybrid algorithm. © 2023 IEEE.

关键词： Decision making

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：