检索结果-内蒙古大学图书馆

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Kaswan, Suresh Yugal, Lisha Khirasaria, Vivek Amita Goyal, Parul Chandigarh University Department of Computer Science & Engineering Punjab Mohali India Sharda University Department of Computer Science & Engineering Greater Noida India Sharda University Faculty of Engineering and Technology Uzbekistan M. M. Engineering College Maharishi Markandeshwar Deemed to Be University Computer Science & Engineering Department Haryana Mullana India

ISBN: (纸本)9798350379945

Software testing is crucial for ensuring software quality, including security. This research presents a case study examining manual and open-source tool-based security testing of an e-commerce website. By applying various testing techniques, the study aims to identify potential vulnerabilities and assess security measures at different development stages. The findings will contribute to developing effective security testing strategies for web applications. © 2024 IEEE.

关键词： E-Commerce testing Security Testing Software Testing System testing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Road Extraction in Remote Sensing Imagery: A Lightweight Dilated Inception Deep Residual U-Net with Channel Attention (LDIDRU-CAN) Model and Pruning Strategies 15

Optimizing Road Extraction in Remote Sensing Imagery: A Ligh...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sharma, Palvi Kumar, Rakesh Gupta, Meenu Obaid, Ahmed J. Chandigarh University Dept. of Computer Science & Engineering Punjab India University of Kufa Faculty of Computer Science & Mathematics Najaf Iraq National University of Science and Technology College of Technical Engineering Dhi Qar Iraq

ISBN: (纸本)9798350370249

The major challenge in Road Extraction is to extract accurate and complete road network and to get high accuracy while minimizing computational power and ensuring faster prediction. It plays important role in urban planning, disaster management, automatic vehicle navigation and GPS navigation. Several earlier studies used complex deep networks that required large amounts of computational power and large storage. In order to address issues such as high storage requirements, computational load, access to memory delays, and low hardware deployment efficiency this research work presents a novel network model called LDIDRU-CAN. The proposed model is fast, compact, and efficient and requires less storage. The objective of this work, is to compress the original model using structured pruning strategy. This strategy simplified the original model and reduced their computation cost as well as storage requirements. For the reduction of the parameters, we focused on the Row Scale Regular Pruning (RSRP) and Low Learning Rate (LLR) retraining. After applying RSRP pruning approach it reduces storage requirements, parameters, and also contributes to a more than 50% reduction in hardware resource consumption and successfully enhances the parallelism of the model. Testing and validations are performed on the Massachusetts Road Dataset. With only 45 M parameters and 180 MB model size, the suggested network achieves remarkable performance with 87.91% precision, 85.51% recall, 86.69% F1-score and 98.91% accuracy. © 2024 IEEE.

关键词： Channel Attention LLR Pruning Road Extraction RSI RSRP

来源：评论

学校读者我要写书评

暂无评论

Cross-Scenario Device-Free Wireless Sensing with A Free-Energy View

引用

IEEE Internet of Things Journal 2025年第11期12卷 16610-16621页

作者： Chen, Bo Wang, Jie Liu, Xiaokai Gao, Qinghua Pan, Miao Fang, Yuguang Dalian Maritime University School of Information Science and Technology Dalian116026 China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian116023 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States City University of Hong Kong Department of Computer Science Hong Kong Hong Kong

Device-free wireless sensing (DFWS) has gained significant attention due to its high accuracy and privacy-preserving capabilities. DFWS systems work by analyzing the influence pattern of targets on the surrounding wireless signals. However, changes in the sensing scenario can alter signal propagation patterns, causing deep learning models to lose effectiveness in cross-scenario applications. To address this problem, we analyze the information content of different samples from a free-energy view, and provide a new idea to guide the alignment of target scenario samples with source scenario samples based on free-energy. We find that free-energy can measure the degree of scenario knowledge contribution of the samples. Based on this observation, we first perform unsupervised coarse alignment by minimizing the free-energy deviation between scenarios. Next, we iteratively select a few number of high free-energy samples near the decision boundary to fine-Tune the network, achieving scenario fine alignment with a small labeling effort. Extensive experiments on two public datasets and one self-collected dataset show that our proposed method achieves high accuracy in cross-scenario human activity and gesture recognition tasks. © 2014 IEEE.

关键词： Labeling Sensors Wireless sensor networks Wireless communication Feature extraction Costs Internet of Things Gesture recognition Metalearning Training

来源：评论

学校读者我要写书评

暂无评论

Hybrid Grey Wolf and Dipper Throated Optimization in Network Intrusion Detection Systems

引用

computers, Materials & Continua 2023年第2期74卷 2695-2709页

作者： Reem Alkanhel Doaa Sami Khafaga El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Rashid Amin Mostafa Abotaleb B.M.El-den Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Science University of Engineering and TechnologyTaxilaPakistan Department of System Programming South Ural State UniversityChelyabinsk454080Russia

The Internet of Things(IoT)is a modern approach that enables connection with a wide variety of devices *** to the resource constraints and open nature of IoT nodes,the routing protocol for low power and lossy(RPL)networks may be vulnerable to several routing ***’s why a network intrusion detection system(NIDS)is needed to guard against routing assaults on RPL-based IoT *** imbalance between the false and valid attacks in the training set degrades the performance of machine learning employed to detect network ***,we propose in this paper a novel approach to balance the dataset classes based on metaheuristic optimization applied to locality-sensitive hashing and synthetic minority oversampling technique(LSH-SMOTE).The proposed optimization approach is based on a new hybrid between the grey wolf and dipper throated optimization *** prove the effectiveness of the proposed approach,a set of experiments were conducted to evaluate the performance of NIDS for three cases,namely,detection without dataset balancing,detection with SMOTE balancing,and detection with the proposed optimized LSHSOMTE *** results showed that the proposed approach outperforms the other approaches and could boost the detection *** addition,a statistical analysis is performed to study the significance and stability of the proposed *** conducted experiments include seven different types of attack cases in the RPL-NIDS17 *** on the 2696 CMC,2023,vol.74,no.2 proposed approach,the achieved accuracy is(98.1%),sensitivity is(97.8%),and specificity is(98.8%).

关键词： Metaheuristics grey wolf optimization dipper throated optimization dataset balancing locality sensitive hashing SMOTE

来源：评论

学校读者我要写书评

暂无评论

Economical Camera-based Measuring Scheme for Roundabout Traffic

引用

Periodica Polytechnica Transportation engineering 2025年第2期53卷 235-241页

作者： Kovács, Tamás Kovács, Lóránt Department of Information Technology GAMF Faculty of Engineering and Computer Science John von Neumann University Izsáki út 10. KecskemétH-6000 Hungary

Counting the turning movements in a four-leg roundabout is a challenging task and often executed by vehicle recognition and tracking on traffic videos. In order to obtain accurately all the 12 flow values of the origin-destination (O-D) matrix we need to measure arbitrary chosen 12 linearly independent flow values. However, the larger the area to be observed the more cameras are needed because the good pixel resolution of the vehicles and the proper camera inclination angles are essential. Here we propose a novel measuring scheme, which observes only two roundabout legs instead of observing all the four, as a result obtaining all the 12 flow values requires a reduced number of cameras. The directly measured flow values and the mathematical method of determining the O-D matrix are given in details. © 2025 Budapest University of Technology and Economics. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Telugu Language Analysis with XLM-RoBERTa: Enhancing Parts of Speech Tagging for Effective Natural Language Processing

引用

SN computer science 2025年第2期6卷 1-13页

作者： Bharathi Mohan, G. Prasanna Kumar, R. Krishna Jayanth, K. Doss, Srinath Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Faculty of Engineering and Technology Botho University Gaborone Botswana

This research investigates the efficacy of XLM-RoBERTa, a potent deep learning architecture rooted in transformer networks, for Part-of-Speech (POS) tagging—a foundational task in Natural Language Processing (NLP). The study narrows its focus to address the formidable UCD Telugu dataset, renowned for its intricate morphological characteristics that pose challenges to accurate tagging. Through meticulous fine-tuning of the pre-trained XLM-RoBERTa model. This study adeptly discerns and exploit intricate syntactic and semantic patterns underpinning the interplay between lexical elements and their respective POS tags. The rigorous evaluation regimen, complemented by a comprehensive statistical comparison with the Multilingual BERT model, conclusively establishes XLM-RoBERTa’s superiority. This advanced model attains a remarkable accuracy score of 91%, decisively surpassing the Multilingual BERT model, which achieves an accuracy of 88%. These findings not only underscore XLM-RoBERTa’s prowess in precise POS tagging, especially in the context of morphologically rich languages like Telugu, but also carry significant implications for the broader NLP community. This research unlocks valuable insights and positions XLM-RoBERTa as an exemplar of reliability and robustness in POS tagging. Furthermore, it extends an invitation for further exploration and innovation in deep learning architectures within the NLP domain. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bert Multilingual Bert NLP Parts-of-speech tagging Telugu XLM-RoBERTa

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Support Vector Machine (SVM) Model Through Parameter Optimization with Genetic Algorithm (GA) in Chronic Kidney Disease Classification 8

Performance Analysis of Support Vector Machine (SVM) Model T...

引用

8th International Conference on Electrical, Telecommunication and computer engineering, ELTICOM 2024

作者： Luaha, Lius Fahmi, Fahmi Zarlis, Muhammad Universitas Sumatera Utara Faculty of Computer Science Medan Indonesia Universitas Sumatera Utara Faculty of Engineering Medan Indonesia

ISBN: (纸本)9798331531249

This study uses hyperparameter optimization to improve accuracy in classifying CKD or chronic kidney disease with the use of a Support Vector Machine algorithm or SVM. SVM is combined with the Grid Search technique for hyperparameter optimization, and SVM is combined with GA or Genetic Algorithm for a more adaptive optimization method. The test results show that combining SVM with Grid Search produces an average accuracy of 80.00%. However, when SVM is optimized using the Genetic Algorithm, the classification accuracy increases significantly to an average of 98.75%. The model optimized with the Genetic Algorithm performs significantly in both target classes. For class 0 (non-CKD), this model achieves a precision of 98.00%, a recall of 100%, and an F1-score of 99.00%. Meanwhile, for class 1 (CKD), the precision is recorded at 100%, a recall of 96.00%, and an F1-score of 98.00%. Genetic Algorithm for SVM hyperparameter optimization substantially improves the classification ability in detecting CKD, providing more precise results than the SVM-Grid Search method. The combination approach of SVM and Genetic Algorithm offers a more effective solution in classifying chronic kidney disease, which can improve the accuracy of medical diagnosis and help in better clinical decision-making. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Improving Dynamic Behavior of Vehicular Ad Hoc Networks by Integrating Game Theory Technique 5th

Improving Dynamic Behavior of Vehicular Ad Hoc Networks by I...

引用

5th International Conference on Applied Technologies, ICAT 2023

作者： Tiwari, Shobhit Mani Baghel, Anurag Singh Department of Computer Science and Engineering Faculty of Engineering and Technology University of Lucknow Uttar Pradesh Lucknow India Department of Computer Science and Engineering School of ICT Gautam Buddha University Uttar Pradesh Greater Noida India

ISBN: (纸本)9783031589553

In this paper, we give the focus on the continuous advancement in the domain of Vehicular ad hoc networks (VANET’s) and that is developed as a tool for developing the base for platform intelligent mode in the communication (inter vehicle communications) and needful for enhanced improvement under the performance effect and traffic safety. Here, we have deployed the game theory method in the VANET domain and thereafter categorizes between the hop vehicle and the source vehicle. The New approach to the VANET analysis we have identified and used the social parameters and hence made it look more novel approach. "Researching vehicle ad hoc networks poses challenges due to their dynamic nature, the movement of large vehicles, unlimited energy resources, and the evolution of wireless networks. Game theory is commonly employed in wireless networks to explore the interplay between competition and cooperation. In this study, we present a system for ad hoc networks in cars, utilizing game theory to automate car groups and board elections. This approach eliminates the necessity for regular bulk updates. Furthermore, the social behavior of each car is leveraged to create clusters in the car environment. The K-means algorithm in machine learning is applied to develop social cars. The proposed system underwent testing for various characteristics, including CH lifetime, average group lifetime, average number of joins, throughput, and packet loss rate. The results demonstrate that VANET performs exceptionally well, achieving an overall performance ranging from 0.95 to 0.989". © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Big Data Healthcare Monitoring System: Improved Recurrent Neural Network for Disease Classification with Apache Spark

引用

Sensing and Imaging 2025年第1期26卷 1-52页

作者： Prabhugouda, Amruta Asra, Syeda Sharnbasva University Karnataka Kalaburagi585102 India Department of Computer Science and Engineering Faculty of Engineering and Technology Sharnbasva University Karnataka Kalaburagi585102 India

Big data analytics has increasingly penetrated the medical industry due to the swift growth of Internet technology along with medical data digitalization, hospital information systems, a huge count of Electronic Health Records (EHR) and other emerging data. The big data’s potential in healthcare is mainly based on its capability of detecting patterns and turning the high volume of data into actionable knowledge for decision-makers. Considering the applications of big data analytics in the medical industry, we have introduced an improved RNN-based big data healthcare monitoring system including the following working stages. Firstly, acquired data gets pre-processed by an outlier detection process. Afterwards, Improved SMOTE (Synthetic Minority Oversampling Technique) based class imbalance processing is performed to get the balanced data. This balanced data is handled using the Spark framework, with the master node carrying out an improved Deep Fuzzy Clustering (DFC) based clustering process and the slave node handling feature extraction and an enhanced Support Vector Machine Recursive Feature Elimination (SVM-RFE) based feature selection process. To divide the data according to the patient’s condition, an enhanced Deep Autoencoder-based Fuzzy C Means Clustering (DAE-FCM) is suggested in the improved DFC. Features including statistics, enhanced entropy, and mutual information are extracted throughout the feature extraction process. Ultimately, an Improved Recurrent Neural Network (RNN) is used to classify diseases using the chosen feature from the slave node. The implementation outcomes proved that the proposed big data healthcare monitoring system can provide effective and accurate disease classification. The Improved RNN method demonstrated the highest accuracy, achieving an impressive rate of 0.945 for dataset 1 and 0.947 for dataset 2 at training data 80%, while the conventional methods acquired the least accuracy ratings. By integrating advanced techniques, the s

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

AggreMark: Efficient Watermarking in Federated Learning via Weighted Averaging 17

AggreMark: Efficient Watermarking in Federated Learning via ...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Lian, Zhuotao Wang, Weiyu Su, Chunhua Sakurai, Kouichi Kyushu University Faculty of Information Science and Electrical Engineering Fukuoka Japan University of Aizu School of Computer Science and Engineering Aizuwakamatsu Japan

ISBN: (纸本)9798350351637

Federated learning has rapidly advanced as a privacy-preserving, distributed machine learning methodology. Protecting the intellectual property rights of federated models, however, poses significant challenges. Existing backdoor-based watermarking techniques suffer from complexity, inefficiency, and implementation challenges. In this paper, we present AggreMark, a novel watermarking approach that incorporates parallel server-side training and watermark embedding during the weighted averaging phase of federated learning. This method does not alter the original model structure or parameters related to the original learning task and adds no additional time overhead, ensuring its practicality for real-world applications. AggreMark is easy to implement and maintain, and it robustly preserves the model's high performance. We validate the method's effectiveness and robustness against pruning-based watermark removal attacks through experiments on CIFAR-10. © 2024 IEEE.

关键词： Federated learning

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：