检索结果-内蒙古大学图书馆

Secure deep learning-based energy efficient routing with intrusion detection system for wireless sensor networks

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 8587-8603页

作者： Sakthimohan, M. Deny, J. Elizabeth Rani, G. Department of Electronics and Communication Engineering Kalasalingam Academy of Research and Education Tamil Nadu India Department of Computer Science and Engineering Kalaignar Karunanidhi Institute of Technology Tamil Nadu Coimbatore India

In general, wireless sensor networks are used in various industries, including environmental monitoring, military applications, and queue tracking. To support vital applications, it is crucial to ensure effectiveness and security. To prolong the network lifetime, most current works either introduce energy-preserving and dynamic clustering strategies to maintain the optimal energy level or attempt to address intrusion detection to fix attacks. In addition, some strategies use routing algorithms to secure the network from one or two attacks to meet this requirement, but many fewer solutions can withstand multiple types of attacks. So, this paper proposes a secure deep learning-based energy-efficient routing (SDLEER) mechanism for WSNs that comes with an intrusion detection system for detecting attacks in the network. The proposed system overcomes the existing solutions’ drawbacks by including energy-efficient intrusion detection and prevention mechanisms in a single network. The system transfers the network’s data in an energy-aware manner and detects various kinds of network attacks in WSNs. The proposed system mainly comprises two phases, such as optimal cluster-based energy-aware routing and deep learning-based intrusion detection system. Initially, the cluster of sensor nodes is formed using the density peak k-mean clustering algorithm. After that, the proposed system applies an improved pelican optimization approach to select the cluster heads optimally. The data are transmitted to the base station via the chosen optimal cluster heads. Next, in the attack detection phase, the preprocessing operations, such as missing value imputation and normalization, are done on the gathered dataset. Next, the proposed system applies principal component analysis to reduce the dimensionality of the dataset. Finally, intrusion classification is performed by Smish activation included recurrent neural networks. The proposed system uses the NSL-KDD dataset to train and test it. The

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Surface functionalization of MnO2 NW embellished with metal nanoparticles for self-cleaning applications

引用

Applied Nanoscience (Switzerland) 2024年第3期14卷 519-529页

作者： Lynrah, Stacy A. Chinnamuthu, P. Rajkumari, Rajshree Lim, Ying Ying Walling, Lanusubo Vigneash, L. Department of Electronics and Communication Engineering NIT Nagaland Dimapur797103 India Department of Electronics and Communication Engineering Indian Institute of Information Technology Senapati Manipur795002 India Department of Electrical Electronic and Communication Engineering Tokyo City University Tokyo158‑8557 Japan Department of Electronics and Communication Engineering Arjun College of Technology Tamil Nadu Coimbatore642120 India

The present study investigates the synthesis of vertically aligned MnO2 nanowires (NW) decorated with gold (Au) and silver (Ag) nanoparticles (NP) via the glancing angle deposition (GLAD) technique without a need for a catalyst. The cross-sectional field emission scanning electron microscopy (FESEM) image and energy-dispersive X-ray spectroscopy (EDS) confirm the successful adornment of Ag NP and Au NP on the top surface of MnO2 NW. Elemental mapping has verified the presence of manganese (Mn), oxygen (O), silicon (Si), Ag, and Au within the sample. X-ray diffraction (XRD) patterns reveal the polycrystalline growth of the MnO2 film with the preferred orientation. AFM reveals that the surface roughness of Au NP/MnO2 NW is more than Ag NP/MnO2 NW. The measured water contact angles of Au NP/MnO2 NW, Ag NP/MnO2 NW, and MnO2 NW were 125° and 113°, respectively. Ag NP/MnO2 NW showed more hydrophilic properties under UV illumination than Au NP/MnO2 NW owing to the efficient separation of photogenerated electron–hole pairs. Ag NP/MnO2 NW’s higher photocatalytic activity than Au NP/MnO2 NW is attributed to the increased light absorption of the Ag NP in the UV region. The overall enhancement after decorating the noble metal NP on MnO2 NW could open new avenues for self-cleaning applications. © King Abdulaziz City for Science and Technology 2024.

关键词： Nanowires

来源：评论

学校读者我要写书评

暂无评论

Beamforming Design for Dynamic Metasurface Antennas-Based Massive Multiuser MISO Downlink Systems

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the communications Society 2024年 5卷 1387-1398页

作者： Chen, Jung-Chieh Hsu, Chiu-Hsiang National Cheng Kung University Department of Electrical Engineering Tainan701401 Taiwan Institute of Computer and Communication Engineering National Cheng Kung University Tainan701401 Taiwan

This study addresses a massive multiuser multiple-input single-output downlink system with a base station equipped with dynamic metasurface antennas (DMAs) serving single-antenna users. Our goal is to jointly optimize the transmit precoder and configurable DMA coefficients to maximize system performance. This task is challenging due to the complex interdependencies between these parameters. The established solution, AO-RMO, employs alternating optimization (AO) to iteratively optimize the transmit precoder using the weighted minimum mean squared error algorithm and Riemannian manifold optimization (RMO) for the DMA coefficients. While AO-RMO performs reasonably well, it exhibits high time and computational complexity due to RMO. To address this issue, we propose a computationally efficient alternative: a projected gradient descent (PGD)-based algorithm for determining the DMA coefficients. Additionally, for practical reconfiguration of DMA coefficients with discrete values, we introduce the cross-entropy optimization (CEO)-based algorithm. Simulation results demonstrate that when continuous DMA coefficients are used, our proposed AO-PGD algorithm achieves nearly comparable weighted sum rate performance to the AO-RMO algorithm but with significantly reduced computational complexity and running time. When discrete DMA coefficients are applied, the proposed AO-CEO algorithm surpasses other benchmark algorithms in various system configurations. © 2020 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Federated Multitask Learning for Complaint Identification Using Graph Attention Network

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1277-1286页

作者： Singh, Apoorva Chandrasekar, Siddarth Sen, Tanmay Saha, Sriparna Department of Computer Science and Engineering Indian Institute of Technology Patna Patna801106 India Department of Electronics and Communication Engineering Iiitdm Kancheepuram600127 India Ericsson Kolkata700135 India

Prior study on automatically identifying complaints on social media has relied on extensive feature engineering in centralized settings, with no consideration for the decentralized, nonidentically independently distributed (Non-IID), and privacyconscious aspect of complaints, which can hinder data collection, distribution, and learning. In this work, we propose a graph attention network (GAT)-based multitask framework that intends to learn two closely related tasks, complaint detection (primary task) and sentiment classification (auxiliary task), simultaneously in federated learning scenarios. We propose the Federated Combination (FedComb) algorithm, a two-sided adaptive optimization technique that simultaneously optimizes global and local models. The proposed methodology outperforms several baselines for the intended task of recognizing complaints in decentralized settings, according to quantitative and qualitative studies on two benchmark datasets. Impact Statement-Automatic complaint identification is crucial to organizations as they provide insights to meet the customers' requirements, including handling and addressing the complaints. Unlike standard technologies developed using data stored in the cloud, a federated learning model allows businesses to learn complaint detection models without sharing their training data spread on their local databases with third-party cloud services. In this work, we propose a GAT-based sentiment-aided complaint identification in federated learning settings. The proposed FedComb algorithm integrates local and global model optimization, making it efficient compared to existing federated algorithms. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on NOMA-Based Backscatter communication for IoT Applications

引用

IEEE Internet of Things Journal 2025年第12期12卷 18929-18953页

作者： Mondal, Soumen Bepari, Dipen Chandra, Aniruddha Singh, Keshav Li, Chih-Peng Ding, Zhiguo National Sun Yat-sen University Institute of Communications Engineering Kaohsiung Taiwan Indian Institute of Information Technology Department of Electronics and Communication Engineering Maharashtra Pune India National Institute of Technology Durgapur Department of Electronics and Communication Engineering West Bengal 713209 India University of Manchester School of Electrical and Electronic Engineering ManchesterM13 9PL United Kingdom

Backscatter communication (BackCom) holds immense potential for enhancing the capabilities of energy-constrained Internet of Things (IoT) devices and supporting a wide range of applications. Non-orthogonal multiple-access (NOMA) schemes are advantageous for meeting the demands of massive connectivity in next-generation communication networks, and NOMA-aided BackCom can leverage the benefits of both BackCom and NOMA. This survey paper covers the basics of BackCom, explores different types of BackCom systems, and explains how NOMA can be integrated with BackCom, where various crucial issues, including design principles, channel state information (CSI) estimation, node pairing schemes, and reflection coefficient (RC) designs, are illustrated. Furthermore, this survey evaluates the effectiveness of different network architectures for NOMA-aided BackCom, especially in IoT networks, and identifies potential research directions and future trends in this area. The key considerations for designing and optimizing NOMA-aided BackCom systems in real-world scenarios are also highlighted in this survey. In addition, by reviewing the existing literature and research on NOMA-aided BackCom, this paper provides valuable insights for researchers and practitioners interested in this emerging wireless communication technique. © 2025 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Lightweight Certificateless Authenticated Key Agreement Protocol for V2V communications in IoV

引用

IEEE Internet of Things Journal 2024年第16期11卷 27744-27759页

作者： Lin, Hui-Tang Jhuang, Wei-Li National Cheng Kung University Institute of Computer and Communication Engineering The Department of Electrical Engineering Tainan City701 Taiwan Silicon Motion Technology Corporation Zhubei Taiwan

With the emergence of the Internet of Things, traditional vehicular ad hoc networks have evolved into the more sophisticated Internet of Vehicles (IoV). IoV is expected to play a key role in the development of future smart cities and intelligent transportation systems. However, like most information technology systems, IoV is vulnerable to the cyberattack. A hacker may gain control over a vehicle, thereby posing serious danger to the vehicle occupants, surrounding vehicles and pedestrians. Consequently, improving the security of IoV is essential in ensuring its future success. Among the various security concerns surrounding IoV, secure communications and authentication are two of the most critical. Currently, most proposed works suffers the single-point-of-failure (SPOF) problem and the trusted third party (TTP) compromise issue. To address these issues, the present study proposes a secure key generation mechanism which leverages the advantages of blockchain technology and certificateless public-key cryptography. In the proposed method, the distributed architecture of blockchain is exploited to realize a decentralized TTP service to prevent the SPOF problem and the TTP compromise issue. In addition, an authenticated key agreement (AKA) protocol based on the legal key pairs is proposed to facilitate efficient mutual authentication and session key agreement between the vehicles. The security analysis results show that the proposed schemes have excellent resistance to the typical TTP issues. Moreover, the feasibility of the proposed AKA protocol is demonstrated through the extended Canetti-Krawczyk model. Finally, the performance analysis results show that the proposed scheme yields a significant reduction in the computational cost compared to the existing AKA protocols. © 2014 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

A geometric-approach based Combinatorial Transformative Scalogram analysis for multiclass identification of pathologies in a voice signal

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Khumukcham, Ranita Nongmeikapam, Kishorjit Department of Electronics and Communication Engineering Indian Institute of Information Technology Mantripukhri Manipur Imphal795002 India Department of Computer Science and Engineering Indian Institute of Information Technology Mantripukhri Manipur Imphal795002 India

Many researchers have preferred non-invasive techniques for recognizing the exact type of physiological abnormality in the vocal tract by training machine learning algorithms with feature descriptors extracted from the voice signal. However, until now, most techniques have been limited to classifying whether a voice is normal or abnormal. It is crucial that the trained Artificial Intelligence (AI) be able to identify the exact pathology associated with voice for implementation in a realistic environment. Another issue is the need to suppress the ambient noise that could be mixed up with the spectra of the voice. Current work proposes a robust, less time-consuming and non-invasive technique for the identification of pathology associated with a laryngeal voice signal. More specifically, a two-stage signal filtering approach that encompasses a score-based geometric approach and a glottal inverse filtering method is applied to the input voice signal. The aim here is to estimate the noise spectra, to regenerate a clean signal and finally to deliver a completely fundamental glottal flow-derived signal. For the next stage, clean glottal derivative signals are used in the formation of a novel fused-scalogram which is currently referred to as the "Combinatorial Transformative Scalogram (CTS)." The CTS is a time-frequency domain plot which is a combination of two time-frequency scalograms. There is a thorough investigation of the performance of the two individual scalograms as well as that of the CTS *** classification metrics are used to investigate performance, which are: sensitivity, mean accuracy, error, precision, false positive rate, specificity, Cohen’s kappa, Matthews Correlation Coefficient, and F1 score. Implementation of the VOice ICar fEDerico II (VOICED) standard database provided the highest mean accuracy of 94.12% with a sensitivity of 93.85% and a specificity of 97.96% against other existing techniques. The current method performed well despite the d

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

OCRBench: on the hidden mystery of OCR in large multimodal models

引用

Science China(Information Sciences) 2024年第12期67卷 23-35页

作者： Yuliang LIU Zhang LI Mingxin HUANG Biao YANG Wenwen YU Chunyuan LI Xu-Cheng YIN Cheng-Lin LIU Lianwen JIN Xiang BAI School of Artificial Intelligence and Automation Huazhong University of Science and Technology School of Electronic and Information Engineering South China University of Technology Microsoft Research School of Computer & Communication Engineering University of Science and Technology Beijing Institute of Automation Chinese Academy of Sciences School of Software Engineering Huazhong University of Science and Technology

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a comprehensive evaluation of large multimodal models, such as GPT4V and Gemini, in various text-related visual tasks including text recognition, scene text-centric visual question answering(VQA), document-oriented VQA, key information extraction(KIE), and handwritten mathematical expression recognition(HMER). To facilitate the assessment of optical character recognition(OCR) capabilities in large multimodal models, we propose OCRBench, a comprehensive evaluation benchmark. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available. Furthermore, our study reveals both the strengths and weaknesses of these models, particularly in handling multilingual text, handwritten text, non-semantic text, and mathematical expression *** importantly, the baseline results presented in this study could provide a foundational framework for the conception and assessment of innovative strategies targeted at enhancing zero-shot multimodal *** evaluation pipeline and benchmark are available at https://***/Yuliang-Liu/Multimodal OCR.

关键词： large multimodal model OCR text recognition scene text-centric VQA document-oriented VQA key information extraction handwritten mathematical expression recognition

来源：评论

学校读者我要写书评

暂无评论

Classification of Crop Across Heterogeneous Landscape Through Experienced Artificial Bee Colony

引用

SN computer Science 2024年第4期5卷 428页

作者： Ravikiran, H.K. Jayanth, J. Sathisha, M.S. Yogeesh, G.H. Dileep, R. Department of Electronics and Communication Engineering Navkis College of Engineering Karnataka Hassan India Department of Electronics and Communication Engineering GSSS Institute of Engineering and Technology for Women Karnataka Mysore India Department of Computer Science and Engineering Navkis College of Engineering Karnataka Hassan India

This study aims to develop an experienced artificial bee colony algorithm which is proposed for classification of crops using remote sensed data. The study was conducted in Devnur village located in Nanajangudu taluk of Mysore district, where a highly differed irrigated agriculture system is present. The study is designed to overcome the issues of misclassification in crop patterns due to similar crop Phenology. In Artificial Bee Colony algorithm a single parameter like waggle dance is used for training and validating the classes particularly in high resolution images, this may lead to misclassification of classes like crops which has a same spectral features. In order to avoid this misclassification, a group of experienced employed bee is been trained and updated by each employed bee through a waggle dance where each employed bee depends on its own experience and the current terrain in each space. Here these features help in identifying the classes and updating of the weights in order to map the agents and identifying the classes and robust the spatial and spectral features. This resultant algorithm is called Experienced Artificial bee colony (EABC). The proposed strategy gives a structure within which a pixel based EABC gives commonly integral data to one another, so characterization process is refined through waggle dance. The findings of the experiment indicate that the suggested approach exhibits a 7% and 6% enhancement in Level 2, and an 8% and 5% improvement in Level 3 categories, respectively, compared to the Artificial Bee Colony (ABC) algorithm and Support Vector Machine (SVM). © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： ABC Cropped area EABC LISS IV data SVM

来源：评论

学校读者我要写书评

暂无评论

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 868-881页

作者： He, Ziqiang Wan, Shaohua Zappatore, Marco Lu, Hu School of Computer Science and Communication Engineering Jiangsu University Zhenjiang212013 China Shenzhen Institute forAdvanced Study University of Electronic Science and Technology of China Shenzhen518110 China Department of Engineering for Innovation University of Salento Lecce73100 Italy

In recent years, multiview clustering algorithms have achieved promising performance by exploiting the complementarity and consistency of different views. However, many multiview spectral clustering methods only focus on the consistent information of views, and the time cost of feature decomposition is expensive. Moreover, these methods also require postprocessing (e.g., k-means) to obtain the final clustering results. To overcome these limitations simultaneously, we propose a novel multiview clustering algorithm. First, the method removes the inconsistent information of the views through cross-view measurement to maintain consistent information. These inconsistencies may be caused by noise, corruptions, or view-specific properties and will affect the quality of the similarity matrix. Then, we learn a consensus embedding matrix with nonnegative constraints by performing a low-rank decomposition of the consistency information. In this way, we can replace the eigendecomposition of the n bm × n Laplacian matrix in spectral clustering with the singular value decomposition of a n bm ×c low-rank matrix to reduce the computational burden, where c bm ll n. Furthermore, due to the nonnegative constraint, we can directly obtain the clustering results. Also, to consider the diversity of views, adaptive weighting is applied to different view data. Compared to state-of-the-art multiview clustering methods on five benchmark multiview datasets, we demonstrate the superiority and effectiveness of our approach. We release the source code at https://***/hulu88/FAMvC. © 2023 IEEE.

关键词： Embeddings

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：