检索结果-内蒙古大学图书馆

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Singh, Amar Preet Gupta, Gaurav Soumya, K. Noida Institute Of Engineering And Technology Department Of Electrical & Electronics Engineering Uttar Pradesh Greater Noida India Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India

ISBN: (纸本)9798350366846

Although there has been a decrease in interpretability, significant progress has lately been achieved in developing state-of-the-art models. This assessment provides a thorough analysis of Explainable AI (XAI) within the framework of Natural Language Processing (NLP). This study examines the fundamental classification of descriptions in addition to the many techniques for producing and displaying explanations. The purpose of the survey is to provide a comprehensive study of the many approaches and strategies used to clarify the models' predictions, making it a helpful tool for people who develop NLP models. Additionally, we draw attention to the gaps in the current literature and urge further investigation into potential avenues for this crucial field of study. An experiment is also conducted and the results are discussed in this article. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Youtube Video Recommendation using user-based Collaborative Filtering and Graph Neural Networks Approaches to Improve users Personalized Experience 15

Youtube Video Recommendation using user-based Collaborative ...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Rock, Alvino C. Jebaseeli, T.Jemima Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore641114 India

ISBN: (纸本)9798331300579

YouTube's video recommendation method stands as a pinnacle in the realm of content discovery in enhancing user engagement on the *** User-Based Collaborative Filtering recommendation method relies on a robust foundation of data collection, encompassing user interactions, metadata, and content *** advanced deep learning techniques, videos and users are transformed into vectors within a high-dimensional space, forming the basis for understanding complex *** algorithm's training process involves the utilization of vast datasets, allowing the model to discern patterns in user behavior and content *** and rankings are determined in real-time, ensuring adaptability to evolving user *** feedback loop, fueled by user interactions, continuously refines the algorithm, striking a balance between user satisfaction and content ***'s commitment to preventing content bubbles is evident in the incorporation of diversity-enhancing strategies, introducing randomness and exploration to broaden user content *** remains a hallmark, tailoring recommendations based on individual user histories, preferences, and *** the recommendation method has significantly improved content discovery and user satisfaction, it is not without *** considerations, privacy concerns, and the need for algorithmic transparency remain focal points in ongoing *** forward, the future holds exciting possibilities, with emerging technologies poised to shape the evolution of YouTube's video recommendation method. © Grenze Scientific Society, 2024.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Image Recognition and Similarity Retrieval with Convolutional Neural Networks 2

Image Recognition and Similarity Retrieval with Convolutiona...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Dedeepya, P. Chiranjeevi, P. Narasimha, V. Shariff, Vahiduddin Ranjith, Jinugu Ramesh, Janjhyam Venkata Naga Computer Science & Engineering PVP Siddhartha Institute of Technology Vijayawada India Computer Science & Engineering Amrita Sai Institute of Science and Technology Bathinapadu India Computer Science & Engineering CMR College of Engineering & Technology Hyderabad India Computer Science & Engineering Sir C R Reddy College of Engineering Eluru India Computer Science & Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram India

ISBN: (纸本)9798350340235

Image is a form of representation of data that is presented with visual beauty and has many patterns in it, in a database of irregular image datasets it is enough to make us humans who like structured, neat, and high readability data sets Therefore, the role of machine learning in helping to search for the same image will greatly help humans both in implementing search engines, tidying up image data structures automatically, etc. This research will focus on creating the same 5-image search system based on input from the user using the CNN algorithm & pretrained models such as ResNet with the expected results of model accuracy ranging from 80-95%. This was carried out using the CIFAR-10 dataset as a source. The CIFAR-10 dataset is a medium-scale image data set with a total of 60000 images, there are 10 categories in it, meaning each category contains 6000 images with the size of each image being 32x32. In general, a dataset has different image sizes, so this research study will first do an overview about whether the data for each image is enough with a size of 32x32. © 2023 IEEE.

关键词： Canadian institute for Advanced Research (CIFAR) Dataset Convolutional Neural Networks (CNN) Deep Learning Deep Neural Network (DNN) Rectified Linear Units (ReLUs) Residual Neural Network (ResNet)

来源：评论

学校读者我要写书评

暂无评论

An Automated Methodology for Detecting Cercospora Infestations in Eggplant using YOLOv10N 4

An Automated Methodology for Detecting Cercospora Infestatio...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Deepan, S. Revathy, Ms. M. Kit - Kalaignarkarunanidhi Institute of Technology Department of Computer Science and Engineering Coimbatore India Cse Kit - Kalaignarkarunanidhi Institute of Technology Coimbatore India

ISBN: (纸本)9798331523923

Cercospora leaf spot, a damaging fungal disease in eggplants, threatens agricultural productivity and farmer livelihoods. This study introduces an automated system for early detection of Cercospora infestations and affected percentages using advanced image processing and the YOLOvlON algorithm. A diverse dataset of annotated eggplant leaf images highlights healthy and infected regions. Preprocessing steps, including noise reduction and feature enhancement, ensure accurate detection. Supervised data augmentation enhances the model's adaptability to real-world conditions. The proposed system achieves high precision with competitive metrics, such as mean Average Precision (mAP), precision, and recall. Its lightweight design ensures compatibility with various devices, promising accessible solutions for farmers. Future developments aim to integrate mobile platforms, advancing sustainable and scalable plant disease management in agriculture. © 2025 IEEE.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

A Quasi-Newton Neural Network Based Efficient Intrusion Detection System for Wireless Sensor Network

引用

computer Systems science & engineering 2023年第4期45卷 427-443页

作者： A.Gautami J.Shanthini S.Karthik Department of Electronics and Communication Engineering SNS College of TechnologyCoimbatoreTamilnaduIndia Department of Computer Science&Engineering Dr.N.G.P Institute of TechnologyCoimbatoreTamilnaduIndia Department of Computer Science&Engineering SNS College of TechnologyCoimbatoreTamilnaduIndia

In Wireless Sensor Networks(WSN),attacks mostly aim in limiting or eliminating the capability of the network to do its normal *** this misbehaviour is a demanding *** so far the prevailing research methods show poor ***3 centred efficient Intrusion Detection Systems(IDS)is proposed in WSN to ameliorate the *** proposed system encompasses Data Gathering(DG)in WSN as well as Intrusion Detection(ID)*** DG,the Sensor Nodes(SN)is formed as clusters in the WSN and the Distance-based Fruit Fly Fuzzy c-means(DFFF)algorithm chooses the Cluster Head(CH).Then,the data is amassed by the discovered ***,it is tested with the trained *** IDS encompasses‘3’steps:pre-processing,matrix reduction,and *** pre-processing,the data is organized in a clear ***,attributes are presented on the matrix format and the ELDA(entropybased linear discriminant analysis)lessens the matrix ***,the output as of the matrix reduction is inputted to the QN3 classifier,which classifies the denial-of-services(DoS),Remotes to Local(R2L),Users to Root(U2R),and probes into attacked or Normal *** an experimental estimation,the proposed algorithm’s performance is contrasted with the prevailing *** proposed work attains an enhanced outcome than the prevailing methods.

关键词： Distance fruit fly fuzzy c-means(DFFF) entropy-based linear discriminant analysis(ELDA) Quasi-Newton neural network(QN3) remote to local(R2L) denial of service(DoS) user to root(U2R)

来源：评论

学校读者我要写书评

暂无评论

Improved optimizer with deep learning model for emotion detection and classification

引用

Mathematical Biosciences and engineering 2024年第7期21卷 6631-6657页

作者： Joseph, Willson C. Kathrine, G. Jaspher Willsie Shanmuganathan, Vimal Sumathi, S. Pelusi, Danilo Valencia, Xiomara Patricia Blanco Verdú, Elena Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Computer Science and Engineering Adi Shankara Institute of Engineering and Technology Kerala India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore India Sri Eshwar College of Engineering Coimbatore India Communication Sciences University of Teramo Coste Sant’agostino Campus Teramo Italy Universidad Internacional de La Rioja La Rioja Logroño Spain

Facial emotion recognition (FER) is largely utilized to analyze human emotion in order to address the needs of many real-time applications such as computer-human interfaces, emotion detection, forensics, biometrics, and human-robot collaboration. Nonetheless, existing methods are mostly unable to offer correct predictions with a minimum error rate. In this paper, an innovative facial emotion recognition framework, termed extended walrus-based deep learning with Botox feature selection network (EWDL-BFSN), was designed to accurately detect facial emotions. The main goals of the EWDL-BFSN are to identify facial emotions automatically and effectively by choosing the optimal features and adjusting the hyperparameters of the classifier. The gradient wavelet anisotropic filter (GWAF) can be used for image pre-processing in the EWDL-BFSN model. Additionally, SqueezeNet is used to extract significant features. The improved Botox optimization algorithm (IBoA) is then used to choose the best features. Lastly, FER and classification are accomplished through the use of an enhanced optimization-based kernel residual 50 (EK-ResNet50) network. Meanwhile, a nature-inspired metaheuristic, walrus optimization algorithm (WOA) is utilized to pick the hyperparameters of EK-ResNet50 network model. The EWDL-BFSN model was trained and tested with publicly available CK+ and FER-2013 datasets. The Python platform was applied for implementation, and various performance metrics such as accuracy, sensitivity, specificity, and F1-score were analyzed with state-of-the-art methods. The proposed EWDL-BFSN model acquired an overall accuracy of 99.37 and 99.25% for both CK+ and FER-2013 datasets and proved its superiority in predicting facial emotions over state-of-the-art methods. ©2024 the Author(s), licensee AIMS Press.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A new electricity theft detection method using hybrid adaptive sampling and pipeline machine learning

引用

Multimedia Tools and Applications 2024年第18期83卷 54521-54544页

作者： Tripathi, Ashish Kumar Pandey, Avinash Chandra Sharma, Nikhil Department of Computer Science and Engineering Malaviya National Institute of Technology Rajasthan Jaipur302017 India Discipline of CSE PDPM Indian Institute of Information Technology Design and Manufacturing Madhya Pradesh Jabalpur482005 India

Electricity theft not only results in higher electricity costs for regular paying customers but is also a safety threat to the public due to illegal power connections made for cheating. Many governments and private companies have suffered substantial losses from electricity theft or fraud. Several approaches have been presented in the literature for electricity fraud detection. The existing methods for electricity fraud detection show poor performance as the electricity datasets are generally unbalanced or skewed. To handle skewness issues, SMOTE and ADASYN-based oversampling techniques are employed in some electricity fraud detection methods. However, existing oversampling methods typically increase the overlapping of classes and introduce additional noise. Therefore, in this paper, a new oversampling method named ADASYN-SGWO has been presented. The proposed ADASYN-SGWO employs ADASYN for oversampling and SSO-GWO for intelligent undersampling, which mitigates class imbalance issues in electricity datasets. After reducing the issue of class imbalance, random forest pipeline has been used to detect electricity fraud. To assess the efficiency of the proposed approach, precision, recall, F1 score, accuracy, Matthews correlation coefficient, and balance classification rate of the proposed and other state-of-the-art, including XG-boost classifier, Logistic regression, Gaussian naive Bayes, Random Forest classifier, Ada Boost classifier, LGBM classifier, and Quadrant discriminative analysis, have been computed and compared. Further, the proposed approach is also statistically validated using Friedman and post hoc analysis. The statistical analysis and experimental outcomes witnessed that the proposed ADASYN-SGWO-PRF method has outperformed all the other considered methods with 98.2% accuracy, which is significant for real-time applications of electricity theft detection problems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Spr

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Particle Swarm Optimization Algorithm Based U-Net Model for MRI Segmentation in Alzheimer's Disease

Particle Swarm Optimization Algorithm Based U-Net Model for ...

引用

2023 International Conference on Advanced Computing and Communication Technologies, ICACCTech 2023

作者： Kingsly Stephen, R. Faritha Banu, J. College of Engineering and Technology Srm Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350380880

Alzheimer's disease is becoming more common over time. It is a long-term brain disease that gradually impairs people's memory, thinking skills, and finally their ability to perform even the most basic tasks. Early detection can help reduce the progression of this condition because it grows severe before any obvious symptoms show up and produces a brain problem that cannot be treated with drugs or other treatments. This paper proposes a Particle Swarm Optimization Algorithm based U-Net model for image segmentation in Alzheimer's disease classification. The proposed framework uses the Kaggle Alzheimer's image dataset database for training, testing, and validation and shows improved results of 88% Dice Coefficient, 83% Jaccard Index, and 90% F1 Score when compared with Threshold-based-segmentation, Region-Based-segmentation and Clustering-based-segmentation methodologies. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Reset-Free Reinforcement Learning via Multi-State Recovery and Failure Prevention for Autonomous Robots

引用

Tsinghua science and technology 2024年第5期29卷 1481-1494页

作者： Xu Zhou Benlian Xu Zhengqiang Jiang Jun Li Brett Nener School of Mechanical Engineering Changshu Institute of TechnologyChangshu 215500China School of Automation Nanjing University of Science and TechnologyNanjing 210094China School of Electronic and Information Engineering Suzhou University of Science and TechnologySuzhou 215009China Faculty of Medicine and Health The University of SydneySydney 2006Australia Department of Electrical Electronic and Computer EngineeringThe University of Western AustraliaPerth 6009Australia

Reinforcement learning holds promise in enabling robotic tasks as it can learn optimal policies via trial and ***,the practical deployment of reinforcement learning usually requires human intervention to provide episodic resets when a failure *** manual resets are generally unavailable in autonomous robots,we propose a reset-free reinforcement learning algorithm based on multi-state recovery and failure prevention to avoid failure-induced *** multi-state recovery provides robots with the capability of recovering from failures by self-correcting its behavior in the problematic state and,more importantly,deciding which previous state is the best to return to for efficient *** failure prevention reduces potential failures by predicting and excluding possible unsafe actions in specific *** simulations and real-world experiments are used to validate our algorithm with the results showing a significant reduction in the number of resets and failures during the learning.

关键词： reinforcement learning manual reset multi-state recovery failure prediction

来源：评论

学校读者我要写书评

暂无评论

Semantic Tree Based PPDP Technique for Multiple Sensitive Attributes in Inter Cloud

引用

SN computer science 2024年第6期5卷 722页

作者： Gadad, Veena Sowmyarani, C.N. Dayananda, P. Department of Computer Science and Engineering R V College of Engineering Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education

Digital devices and information systems have made data privacy essential. The collected data contains sensitive attributes such as salary, marital status and health history that need to be protected. Such data is exchanged or published to a third party using cloud infrastructure to perform various analyses, conduct research, and make critical decisions. Unauthorized users of the published data may violate privacy, notwithstanding the benefits. Data anonymization is one of the technique for achieving data privacy. Existing techniques consider single sensitive attribute and data is anonymized using generalization or suppression approaches. On observation, it is found that these techniques are less efficient since the collected data contains multiple sensitive attributes when anonymized using the same approaches leads to higher information loss and residue records. In this paper, multiple sensitive attributes are considered and the dataset is anonymized by constructing a semantic hierarchical tree it is further partitioned using the anatomy approach. Later, the partitions are stored in interclouds to achieve better privacy protection. Experiments are conducted to observe and analyze the computational performance, residue records and diversity percentage. The results obtained prove that the proposed technique is efficient when compared to the existing ones. © The Author(s) 2024.

关键词： Anonymization Data privacy Information loss Multiple sensitive attributes Privacy threats

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：