检索结果-内蒙古大学图书馆

Streamlining plant disease diagnosis with convolutional neural networks and edge devices

Neural computing and Applications 2024年第29期36卷 18445-18477页

作者： Ahamed, Md. Faysal Salam, Abdus Nahiduzzaman, Md. Abdullah-Al-Wadud, M. Islam, S. M. Riazul Department of Computer Science and Engineering Rajshahi University of Engineering & ampTechnology Rajshahi6204 Bangladesh Department of Electrical and Computer Engineering Rajshahi University of Engineering & ampTechnology Rajshahi6204 Bangladesh Department of Electrical Engineering Qatar University Doha Qatar Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia School of Natural and Computing Sciences University of Aberdeen AberdeenAB24 3FX United Kingdom

In addressing labor-intensive process of manual plant disease detection, this article introduces an innovative solution—the lightweight parallel depthwise separable convolutional neural network (PDSCNN) coupled with a hybrid ridge regression extreme learning machine classifier. This combined approach automates plant disease classification, significantly expediting the learning process and reducing computational complexity. The PDSCNN model excels in feature capture, boasting a mere 9 layers and 0.053 million parameters, resulting in exceptional computational efficiency. On top of that, the classification performances of traditional ELM increased by introducing a hybrid ridge ELM model. Its accelerated operations, reduced memory usage, and optimized parallel processing render it lightweight and ideal for edge devices. The proposed framework exhibits remarkable efficacy, showcasing a precision of 95.76%, a recall of 89.29%, an F1-score of 91.25%, an accuracy of 94.22%, and an AUC of 99.72%. Moreover, training and testing times clock in at just 0.2314 and 0.0259 s, respectively. A comparative analysis against state-of-the-art transfer learning methods underscores its real-time analytical prowess. To demonstrate real-world applicability, we successfully validated our model on the Jetson Nano hardware, making it suitable for resource-constrained settings. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Intricacies of Cyber Harassment Intentions on Social Media Platforms 3

Unveiling the Intricacies of Cyber Harassment Intentions on ...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Shraya, Bejgum Reddy Dopathi, Hari Charan Anitha, G. Pattanaik, Balachandra Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Tamilnadu Chennai India Wallaga University Nekemte Department of Electrical and Computer Engineering Ethiopia

ISBN: (纸本)9798350381931

Cyberbullying is a severe issue that impacts teens and adults alike. Errors like hopelessness and suicide have resulted from it. The demand for material on social media platforms to be regulated is growing. In the work that follows, machine learning and natural language processing are used to construct a model to identify cyberbullying in text data. The program leverages data from two different types of cyberbullying: personal attacks on Wikipedia forums and tweets containing hate speech. To determine the optimal approach, three feature extraction techniques and four classifiers are examined. The method produces more than 80% accurate data from Wikipedia and more than 90% correct data from Twitter. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Diversified and compatible web APIs recommendation based on game theory in IoT

引用

Digital Communications and Networks 2024年第4期10卷 1198-1209页

作者： Wenwen Gong Huiping Wu Xiaokang Wang Xuyun Zhang Yawei Wang Yifei Chen Mohammad R.Khosravi College of Information and Electrical Engineering China Agricultural UniversityBeijing100000China Shandong Provincial University Laboratory for Protected Horticulture Weifang University of Science and TechnologyShouguang262700China Department of Computer Science St.Francis Xavier UniversityAntigonishNSCanada Department of Computing Macquarie UniversitySydneyNSW2122Australia Department of Computer Engineering Persian Gulf UniversityBushehr***Iran Department of Electrical and Electronic Engineering Shiraz University of TechnologyShiraz71557-13876Iran

With the ever-increasing popularity of Internet of Things(IoT),massive enterprises are attempting to encapsulate their developed outcomes into various lightweight Web Application Programming Interfaces(APIs)that can be accessible *** this context,finding and writing a list of existing Web APIs that can collectively meet the functional needs of software developers has become a promising approach to economically and easily develop successful mobile ***,the number and diversity of candidate IoT Web APIs places an additional burden on application developers’Web API selection decisions,as it is often a challenging task to simultaneously ensure the diversity and compatibility of the final set of Web APIs *** this challenge and latest successful applications of game theory in IoT,a Diversified and Compatible Web APIs Recommendation approach,namely DivCAR,is put forward in this *** of all,to achieve API diversity,DivCAR employs random walk sampling technique on a pre-built“API-API”correlation graph to generate diverse“API-API”correlation ***,with the diverse“API-API”correlation subgraphs,the compatible Web APIs recommendation problem is modeled as a minimum group Steiner tree search problem.A sorted set of multiple compatible and diverse Web APIs are returned to the application developer by solving the minimum group Steiner tree search *** last,a set of experiments are designed and implemented on a real dataset crawled from *** results validate the effectiveness and efficiency of our proposed DivCAR approach in balancing the Web APIs recommendation diversity and compatibility.

关键词： Internet of things Web APIs recommendation Game theory Diversity and compatibility

来源：评论

学校读者我要写书评

暂无评论

Enhancing waste sorting and recycling efficiency: robust deep learning-based approach for classification and detection

引用

Neural computing and Applications 2025年第6期37卷 4567-4583页

作者： Sayem, Faizul Rakib Islam, Md. Sakib Bin Naznine, Mansura Nashbat, Mohammad Hasan-Zia, Mazhar Kunju, Ali K Ansaruddin Khandakar, Amith Ashraf, Azad Majid, Molla Ehsanul Kashem, Saad Bin Abul Chowdhury, Muhammad E. H. Department of Electrical and Electronic Engineering University of Dhaka Dhaka Bangladesh Department of Biomedical Engineering Military Institute of Science and Technology Dhaka Bangladesh Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi6204 Bangladesh Chemical Engineering Department University of Doha for Science and Technology Doha Qatar Department of Electrical Engineering Qatar University Doha2713 Qatar Computer Applications Department Academic Bridge Program Qatar Foundation Doha Qatar Department of Computing Science AFG College With the University of Aberdeen Doha Qatar

Given the severity of waste pollution as a major environmental concern, intelligent and sustainable waste management is becoming increasingly crucial in both developed and developing countries. The material composition and volume of urban solid waste are key considerations in processing, managing, and utilizing city waste. Deep learning technologies have emerged as viable solutions to address waste management issues by reducing labor costs and automating complex tasks. However, the limited number of trash image categories and the inadequacy of existing datasets have constrained the proper evaluation of machine learning model performance across a large number of waste classes. In this paper, we present robust waste image classification and object detection studies using deep learning models, utilizing 28 distinct recyclable categories of waste images comprising a total of 10,406 images. For the waste classification task, we proposed a novel dual-stream network that outperformed several state-of-the-art models, achieving an overall classification accuracy of 83.11%. Additionally, we introduced the GELAN-E (generalized efficient layer aggregation network) model for waste object detection tasks, obtaining a mean average precision (mAP50) of 63%, surpassing other state-of-the-art detection models. These advancements demonstrate significant progress in the field of intelligent waste management, paving the way for more efficient and effective solutions. © The Author(s) 2024.

关键词： Deep learning for waste management Intelligent waste management Object detection in waste management Sustainable waste processing Urban solid waste Waste image classification

来源：评论

学校读者我要写书评

暂无评论

Inductive Lottery Ticket Learning for Graph Neural Networks

引用

Journal of computer Science & Technology 2024年第6期39卷 1223-1237页

作者： Yong-Duo Sui Xiang Wang Tianlong Chen Meng Wang Xiang-Nan He Tat-Seng Chua School of Data Science University of Science and Technology of ChinaHefei 230027China Department of Electrical and Computer Engineering The University of Texas at AustinAustin 78712U.S.A School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China School of Computing National University of SingaporeSingapore

Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplored. The recent work Unified GNN Sparsification (UGS) studies lottery ticket learning for GNNs, aiming to find a subset of model parameters and graph structures that can best maintain the GNN performance. However, it is tailed for the transductive setting, failing to generalize to unseen graphs, which are common in inductive tasks like graph classification. In this work, we propose a simple and effective learning paradigm, Inductive Co-Pruning of GNNs (ICPG), to endow graph lottery tickets with inductive pruning capacity. To prune the input graphs, we design a predictive model to generate importance scores for each edge based on the input. To prune the model parameters, it views the weight’s magnitude as their importance scores. Then we design an iterative co-pruning strategy to trim the graph edges and GNN weights based on their importance scores. Although it might be strikingly simple, ICPG surpasses the existing pruning method and can be universally applicable in both inductive and transductive learning settings. On 10 graph-classification and two node-classification benchmarks, ICPG achieves the same performance level with 14.26%–43.12% sparsity for graphs and 48.80%–91.41% sparsity for the GNN model.

关键词： lottery ticket hypothesis graph neural networks neural network pruning

来源：评论

学校读者我要写书评

暂无评论

Ultrasensitive textile strain sensors redefine wearable silent speech interfaces with high machine learning efficiency

引用

npj Flexible Electronics 2024年第1期8卷 664-674页

作者： Chenyu Tang Muzi Xu Wentian Yi Zibo Zhang Edoardo Occhipinti Chaoqun Dong Dafydd Ravenscroft Sung-Min Jung Sanghyo Lee Shuo Gao Jong Min Kim Luigi Giuseppe Occhipinti Electrical Engineering Division Department of EngineeringUniversity of CambridgeCambridgeUK Department of Electronic and Electrical Engineering University College LondonLondonUK UKRI Centre for Doctoral Training in AI for Healthcare Department of ComputingImperial College LondonLondonUK School of Materials Science and Engineering Kumoh National Institute of Technology(KIT)GumiSouth Korea School of Instrumentation Science and Optoelectronic Engineering Beihang UniversityBeijingChina

This work introduces a silent speech interface(SSI),proposing a few-layer graphene(FLG)strain sensing mechanism based on thorough cracks and AI-based self-adaptation capabilities that overcome the limitations of state-of-the-art technologies by simultaneously achieving high accuracy,high computational efficiency,and fast decoding speed while maintaining excellent user *** demonstrate its application in a biocompatible textile-integrated ultrasensitive strain sensor embedded into a smart choker,which conforms to the user’s *** to the structure of ordered through cracks in the graphene-coated textile,the proposed strain gauge achieves a gauge factor of 317 with<5%strain,corresponding to a 420%improvement over existing textile strain sensors fabricated by printing and coating technologies reported to *** high sensitivity allows it to capture subtle throat movements,simplifying signal processing and enabling the use of a computationally efficient neural *** resulting neural network,based on a one-dimensional convolutional model,reduces computational load by 90%while maintaining a remarkable 95.25%accuracy in speech *** synergy in sensor design and neural network optimization offers a promising solution for practical,wearable SSI systems,paving the way for seamless,natural silent communication in diverse settings.

关键词： strain wear neural

来源：评论

学校读者我要写书评

暂无评论

Leveraging Industry 4.0 in Education for Remote Implementation in a Team-Based computer engineering Capstone Project 54

Leveraging Industry 4.0 in Education for Remote Implementati...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Sasidhar, Sangit Vachery, Jithin National University of Singapore Department of Electrical and Computer Engineering Singapore School of Computing National University of Singapore Singapore

ISBN: (纸本)9798350351507

This Innovative Practice Category Full Paper presents the remote implementation of an embedded systems capstone project for computer engineering students. A capstone project is a feature of most undergraduate programs in computer engineering. Such a project is usually meant to expose students to the development of a large system from conceptualization to its final implementation, involving substantial design and development of hardware and software components. In our university, students were given the opportunity to work on a cutting-edge problem focused on healthcare - 'Designing a wearable device that automatically detects human activities'. It is an area where a large amount of research is ongoing, and hundreds of scientific papers are published every year. In addition, students had to evaluate and adopt techniques from existing literature and adapt them to meet the problem requirements. Students equipped themselves with state-of-the-art hardware, Bio-signal processing, machine learning, power optimization and secure communications to design the wearable. Thus, the project reinforced their knowledge of fundamentals, while exposing them to a problem with no obvious solution. Through the capstone project, students are able to better appreciate the relevance of the various components in the computer engineering curriculum to large-scale computer engineering projects. Students are organized into teams of six to execute the project. The COVID-19 pandemic resulted in the university migrating the teaching online for all courses. This was particularly challenging to implement for the capstone project as one of the key requirements is for the members to work together and subsystems to interact with each other. A course refresh resulted in a credits update and this provided a unique opportunity for the teaching team to re-design the project with core Industry 4.0 technologies such as hardware acceleration, remote processing, networking, remote analytics, and secure protoc

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

FUG: Feature-Universal Graph Contrastive Pre-training for Graphs with Diverse Node Features 38

FUG: Feature-Universal Graph Contrastive Pre-training for Gr...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Jitao Jin, Di Ge, Meng Shan, Lianze Wang, Xin He, Dongxiao Feng, Zhiyong College of Intelligence and Computing Tianjin University China Department of Electrical and Computer Engineering National University of Singapore Singapore

Graph Neural Networks (GNNs), known for their effective graph encoding, are extensively used across various fields. Graph self-supervised pre-training, which trains GNN encoders without manual labels to generate high-quality graph representations, has garnered widespread attention. However, due to the inherent complex characteristics in graphs, GNNs encoders pre-trained on one dataset struggle to directly adapt to others that have different node feature shapes. This typically necessitates either model rebuilding or data alignment. The former results in non-transferability as each dataset need to rebuild a new model, while the latter brings serious knowledge loss since it forces features into a uniform shape by preprocessing such as Principal Component Analysis (PCA). To address this challenge, we propose a new Feature-Universal Graph contrastive pre-training strategy (FUG) that naturally avoids the need for model rebuilding and data reshaping. Specifically, inspired by discussions in existing work on the relationship between contrastive Learning and PCA, we conducted a theoretical analysis and discovered that PCA's optimization objective is a special case of that in contrastive Learning. We designed an encoder with contrastive constraints to emulate PCA's generation of basis transformation matrix, which is utilized to losslessly adapt features in different datasets. Furthermore, we introduced a global uniformity constraint to replace negative sampling, reducing the time complexity from O(n2) to O(n), and by explicitly defining positive samples, FUG avoids the substantial memory requirements of data augmentation. In cross domain experiments, FUG has a performance close to the re-trained new models. The source code is available at: https://***/hedongxiao-tju/FUG. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Approach for Condition Monitoring and Improving Power Output of Photovoltaic Systems

引用

computers, Materials & Continua 2023年第3期74卷 5757-5776页

作者： Nebras M.Sobahi Ahteshamul Haque V S Bharath Kurukuru Md.Mottahir Alam Asif Irshad Khan Department of Electrical and Computer Engineering(ECE) King Abdulaziz UniversityJeddah 21589Saudi Arabia Advance Power Electronics Research Lab Department of Electrical EngineeringJamia Millia IslamiaNew DelhiIndia Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah 21589Saudi Arabia

Increasing renewable energy targets globally has raised the requirement for the efficient and profitable operation of solar photovoltaic(PV)*** light of this requirement,this paper provides a path for evaluating the operating condition and improving the power output of the PV system in a grid integrated *** achieve this,different types of faults in grid-connected PV systems(GCPVs)and their impact on the energy loss associated with the electrical network are analyzed.A data-driven approach using neural networks(NNs)is proposed to achieve root cause analysis and localize the fault to the component level in the *** localized fault condition is combined with a parallel operation of adaptive neurofuzzy inference units(ANFIUs)to develop a power mismatch-based control unit(PMCU)for improving the power output of the *** develop the proposed framework,a 10-kW single-phase GCPV is simulated for training the NN-based anomaly detection approach with 14 deviation ***,the developed algorithm is combined with the PMCU implemented with the experimental setup of *** results identified 98.2%training accuracy and 43000 observations/sec prediction speed for the trained classifier,and improved power output with reduced voltage and current harmonics for the grid-connected PV operation.

关键词： Condition monitoring anomaly detection performance evaluation fault classification optimization

来源：评论

学校读者我要写书评

暂无评论

Reliability-aware swarm based multi-objective optimization for controller placement in distributed SDN architecture

引用

Digital Communications and Networks 2024年第5期10卷 1245-1257页

作者： Abeer A.Z.Ibrahim Fazirulhisyam Hashim Aduwati Sali Nor K.Noordin Keivan Navaie Saber M.E.Fadul Department of Computer and Communication Systems Engineering Faculty of EngineeringUniversiti Putra MalaysiaSerdang43400Malaysia Wireless and Photonics Networks Research Centre(WiPNET) Faculty of EngineeringUniversiti Putra MalaysiaSerdang43400Malaysia Department of Communication and Computer Engineering College of Engineering and Medical SciencesKhartoum11111Sudan School of Computing and Communications Lancaster UniversityLancasterLA14YWUnited Kingdom Department of Electrical and Electronics Engineering Faculty of EngineeringUniversiti Putra MalaysiaSerdang43400Malaysia

The deployment of distributed multi-controllers for Software-Defined Networking(SDN)architecture is an emerging solution to improve network scalability and ***,the network control failure affects the dynamic resource allocation in distributed networks resulting in network disruption and low ***,we consider the control plane fault tolerance for cost-effective and accurate controller location models during control plane *** fault-tolerance strategy has been applied to distributed SDN control architecture,which allows each switch to migrate to next controller to enhance network *** this paper,the Reliable and Dynamic Mapping-based Controller Placement(RDMCP)problem in distributed architecture is framed as an optimization problem to improve the system reliability,quality,and *** considering the bound constraints,a heuristic state-of-the-art Controller Placement Problem(CPP)algorithm is used to address the optimal assignment and reassignment of switches to nearby controllers other than their regular *** algorithm identifies the optimal controller location,minimum number of controllers,and the expected assignment costs after failure at the lowest effective cost.A metaheuristic Particle Swarm Optimization(PSO)algorithm was combined with RDMCP to form a hybrid approach that improves objective function optimization in terms of reliability and *** effectiveness of our hybrid RDMCP-PSO was then evaluated using extensive experiments and compared with other baseline *** findings demonstrate that the proposed hybrid technique significantly increases the network performance regarding the controller number and load balancing of the standalone heuristic CPP algorithm.

关键词： Software defined networking Dynamic mapping Particle swarm optimization Reliability Multi-objective optimization Evolutionary

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：