检索结果-内蒙古大学图书馆

International Conference on ent Computing and Control Systems (ICICCS)

作者： Sahana Markande Rupa Shree S Minal Moharir Sarthak Lakhotia Computer Science Engineering RV College of Engineering Autonomous Institute Affiliated to VTU Belagavi Computer Science Engineering (Cyber Security) RV College of Engineering Autonomous Institute Affiliated to VTU Belagavi

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

Understanding customer sentiments is crucial for e-commerce platforms to enhance user experiences, improve product quality, and stay competitive. This study analyzes customer sentiments from product reviews across various categories using NLP techniques. Reviews are classified as positive, neutral, or negative through sentiment polarity and subjectivity analysis. Visual tools like heatmaps and word clouds can be used for simplification and better summarization of product reviews. In this approach, a new capability is proposed to the e-commerce platforms, where various product reviews are summarized with such visualizations. This helps the end customer to decide on buying the products much faster, improving the overall customer experience.

关键词： Sentiment analysis Visualization Accuracy Reviews Computational modeling Customer satisfaction Data visualization Tag clouds Electronic commerce Business

来源：评论

学校读者我要写书评

暂无评论

Privacy Data Management Mechanism Based on Blockchain and Federated Learning

引用

computers, Materials & Continua 2023年第1期74卷 37-53页

作者： Mingsen Mo Shan Ji Xiaowan Wang Ghulam Mohiuddin Yongjun Ren Engineering Research Center of Digital Forensics of Ministry of Education School of ComputerNanjing University of Information Science&TechnologyNanjing210044China Zhengde Polytechnic Nanjing211106China Xi’an University of Posts&Telecommunications Xi’an710061China Department of Cyber Security at VaporVM Abu Dhabi999041United Arab Emirates

Due to the extensive use of various intelligent terminals and the popularity of network social tools,a large amount of data in the field of medical *** to manage these massive data safely and reliably has become an important challenge for the medical network *** paper proposes a data management framework of medical network community based on Consortium Blockchain(CB)and Federated learning(FL),which realizes the data security sharing between medical institutions and research *** this framework,the data security sharing mechanism of medical network community based on smart contract and the data privacy protection mechanism based on FL and alliance chain are designed to ensure the security of data and the privacy of important data in medical network community,*** intelligent contract system based on Keyed-Homomorphic Public Key(KH-PKE)Encryption scheme is designed,so that medical data can be saved in the CB in the form of ciphertext,and the automatic sharing of data is *** knowledge mechanism is used to ensure the correctness of shared ***,the zero-knowledge mechanism introduces the dynamic group signature mechanism of chosen ciphertext attack(CCA)anonymity,which makes the scheme more efficient in computing and communication *** the end of this paper,the performance of the scheme is analyzed fromboth asymptotic and practical *** experimental comparative analysis,the scheme proposed in this paper is more effective and feasible.

关键词： Data management blockchain federated learning

来源：评论

学校读者我要写书评

暂无评论

Deep-Based Hybrid Model For Enhancing Land Region Prediction Outcomes 2

Deep-Based Hybrid Model For Enhancing Land Region Prediction...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Selvapandian, D. Raja, Laxmi Tharageswari, K. Vm, Senthilkumar Jc, Nikitha Hemalatha, M. Karpagam Academy of Higher Education Faculty of Engineering Department of Computer Science and Engineering Coimbatore India Karpagam Academy of Higher Education Faculty of Engineering Department of Cyber Security Coimbatore India Mahendra Institute of Technology Department of Information Technology Namakkal India Nandha Arts and Science College Department of Information Technology Erode India

ISBN: (纸本)9798331534950

Although satellite data is not a novel approach to mapping wetlands, its accuracy depends on data quality and categorization algorithms, making it a continuous challenge. The increasing accessibility of satellite data and the development of data modelling technologies, such as big data modelling using machine learning (ML) algorithms, have improved the accuracy of this type of mapping. Our work demonstrated a simple, scalable, and reliable wetland classification using linear Support Vector Machine (l-SVM) and unsupervised k-Nearest Neighbor (k-NN) machine learning approaches. Normalized difference vegetation index (NDVI) and normalized difference water index (NDWI), the two primary inputs were modelled using Landsat optical data. Subsequently, l-SVM was used to supervise k-NN data using training data collected from outside observations. The accuracy test results indicate that there is a considerable reduction in error for both optical indices, and all prediction models have an accuracy of about 99%. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Detection and Recognition using CNN and KERAS

Traffic Sign Detection and Recognition using CNN and KERAS

引用

Advances in Computation, Communication and Information Technology (ICAICCIT), International Conference on

作者： Digvijay Prabhat J. Pardhiv Sai S Vishnupriya S. S. Subashka Ramesh Computer Science and Engineering with Specialization in Cyber Security SRM IST Ramapuram Chennai India Department of Computer Science and Engineering SRM IST Ramapuram Chennai India

ISBN: (数字)9798331541217

ISBN: (纸本)9798331541224

A traffic sign detection and recognition system based on CNN with high-accuracy and possibility of real-time implementation for autonomous driving applications has been presented. The Keras framework was used to develop the system, which overcomes limitations of traditional traffic sign recognition methods, commonly found to fail due to environmental variations such as changing light, object occlusions, or damaged traffic signs. It takes advantage of the comprehensive GTSRB dataset and performs data augmentations so as to generalize well to different driving environments. The optimized convolutional and pooling layers in the CNN architecture allow for efficient extraction of salient features, which is crucial as ASL often has similar sign classes that need to be differentiated across variations in scale, illumination, and orientation. The system ensures sign recognition instantaneously and with accurate classification performance, improving safety and efficiency of autonomous driving by providing a fast-accurate real-time recognition of a sign.

关键词： Accuracy Lighting Manuals Feature extraction Data augmentation Real-time systems Data models Safety Convolutional neural networks Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Smart Music Recommendation System Integrating NLP and Hybrid Algorithms

Smart Music Recommendation System Integrating NLP and Hybrid...

引用

Advances in Computation, Communication and Information Technology (ICAICCIT), International Conference on

作者： S. Roshan Kumar S. S. Subashka Ramesh Harsha Vardan V Adithya Yuvan Computer Science and Engineering with Specialization in Cyber Security SRM IST Ramapuram Chennai India Department of Computer Science and Engineering SRM IST Ramapuram Chennai India

ISBN: (数字)9798331541217

ISBN: (纸本)9798331541224

In an era where technological growth gives a massive amount of knowledge in music, intuitive and personalized music delivery forms the cornerstone for better user experience and satisfaction. The increasing reliance on voice-driven interfaces can be leveraged to create newer music recommendation systems. This paper explores the development of the Smart Music Recommendation System, which will use natural language processing (NLP), speech recognition, and hybrid algorithms to recommend music to the user based on his mood input through voice. The system leverages Google Speech Recognition API for real-time voice interaction ensuring a seamless interaction between the user and the system. The system additionally detects the user’s emotional state from voice commands, while search algorithms are employed to fetch and recommend songs. A hybrid recommendation approach combines content-based filtering for emotion-specific playlist generation for every mood for an enhanced listening experience. An exceptional feature in our system is offline download using Yt-dlp to any local device and playback processes using an automated threading mechanism. The system proposed here was tested and gave efficient performance in voice interaction, song suggestion according to mood, and coordination with external platforms for retrieving and playing songs.

关键词： Sentiment analysis Accuracy Mood Filtering Multimedia systems Speech recognition Real-time systems Internet Web sites Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Smart Agriculture-Based Food Quality Analysis with Healthcare security System Using Cloud Machine Learning Model

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 389-398页

作者： Vaithianathan, V. Rebecca, B. Begum, M. Fathima Sundarraj, Antony Allwyn Kumar, M. Prema Kiran, Ajmeera Department of Electronics and Communication Engineering Sri Sivasubramaniya Nadar College of Engineering Kalavakkam Chennai 603110 India Department of Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Hyderabad Telangana Dundigal 500043 India Assistant Professor Department of Computer Science and Engineering (Cyber Security) Madanapalle Institute of Technology and Science Andhra Pradesh-517325 Madanapalle India Department of Food Technology Sri Shakthi Institute of Engineering and Technology Coimbatore Tamilnadu Coimbatore India Dept. of ECE Shri Vishnu Engineering College for Women (A) Andhra Pradesh Bhimavaram 534202 India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

The primary sector of our Indian economy is agriculture. Today’s world’s most important and vital industries are agriculture and irrigation. Information and communication technology must be used in our agriculture sectors in order to support farmers and agriculturalists in improving their practices across the entire crop-growing and post-harvest processes. It is still challenging to define processed food, even in light of mounting research that suggests consuming more ultra-processed food has negative health effects. This research proposes novel technique in smart agriculture model based on cloud machine learning in cloud machine learning and healthcare system. By leveraging IoT and cloud-based data to create data-driven product decisions, cloud computing in agriculture can assist farmers with smart agriculture practices. Here, the input has been collected as food quality based on smart agriculture using a cloud model as well as processed for noise removal and normalisation. Then, based on this data, the healthcare security system has been analysed using reinforcement adversarial stacked encoder with Markov fuzzy algorithm. The experimental analysis has been carried out for various food quality datasets in terms of training accuracy, random precision, normalised correlation ratio, F-1 score, and AUC. The proposed technique achieved training accuracy of 96%, F-1 score of 94%, random precision of 97%, normalised correlation ratio of 93%, and AUC of 92%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Adversarial stacked encoder Cloud machine learning Cloud machine learning Healthcare system Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

S3A: State-Attention Inducing Adversarial Attacks on Black-box Proximal Policy Optimisation Models

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Yichuan Zhao, Chen Liu, Zhiquan Hei, Xinhong Ma, Jianfeng Xi’an University of Technology College of Computer Science and Engineering Xi’an710048 China Jinan University College of Cyber Security Guangzhou510632 China Xidian University School of Cyber Engineering Xi’an710071 China

In the current era when the Internet of Things (IoT) is booming and various smart devices are closely interconnected to build a complex network system, the demand for efficient control and resource management strategies is extremely urgent. Proximal Policy Optimization (PPO), as a highly representative algorithm in deep reinforcement learning, has great potential in aspects such as precise control of IoT devices, rational resource allocation, and intelligent interaction. However, in the practical applications of the IoT, PPO mostly exists as a black-box model, which is vulnerable to adversarial attacks. Moreover, the continuous action space scenarios applicable to PPO further increase the difficulty of analysis and protection. Therefore, this paper innovatively proposes a State-Attention Adversarial Attack (S3A) for black-box PPO models in continuous action space scenarios. This method is based on the model’s attention to states, has a low cost, integrates the parts of model extraction, action clustering, and decision-making interference of the model under specific states, and has a clear interference purpose. By constructing an IoT-related victim model in the MuJoCo environment provided by the Gym library and implementing adversarial attacks, experiments have found that under four repetitions in five simulation environments, S3A reduces the final reward of the victim model by an average of 48.5%, which strongly verifies the effectiveness and influence of this attack method. © 2014 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Unified Channel Modeling of WiFi and LiFi Using Conditional GAN 5

Data-Driven Unified Channel Modeling of WiFi and LiFi Using ...

引用

5th International Conference on Intelligent Computing, Communication, Networking and Services, ICCNS 2024

作者： Saif, Amal Ibrahim, Rahmeh Almajali, Sufyan Salameh, Haythem Bany Princess Sumaya University for Technology Computer Science Department Amman11941 Jordan Princess Sumaya University for Technology Cyber Security Department Amman11941 Jordan College of Engineering Al Ain University Al Ain United Arab Emirates

ISBN: (纸本)9798350354690

Wireless communication systems, rooted in the propagation of electromagnetic waves, have traditionally operated within the framework of digital modules such as source coding, encryption, and modulation. However, the conventional 'modular' approach faces challenges in achieving 'global optimization,' relying on simulated environments that diverge from real-world channel conditions. This paper proposes a solution to integrate deep learning into wireless communication systems, envisioning intelligent communication systems that learn and adapt. Recent strides in wireless channel modeling have embraced Generative Adversarial Networks (GANs) to generate realistic communication channel models. GANs applied to optical and Radio Frequency (RF) channels bridge gaps where actual measurements are unavailable, providing synthetic models that mirror real-world statistics. This paper's contribution involves innovating channel modeling by replacing autoencoder latent spaces with a GAN model, generalizing the model for diverse channel types, implementing a data-driven approach using Conditional GANs for realistic channel effects, and constructing a unified model adept at simultaneously handling WiFi and LiFi channels. The envisioned outcome is a groundbreaking approach that transcends the limitations of traditional wireless communication, propelling intelligent communication networks into an era of adaptability and optimized performance. © 2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Optimizing Patient Outcomes with AI and Predictive Analytics in Healthcare 65

Optimizing Patient Outcomes with AI and Predictive Analytics...

引用

65th IEEE Annual International Scientific Conference on Power and Electrical engineering of Riga Technical University, RTUCON 2024

作者： Janjua, Jamshaid Iqbal Ghazal, Taher M. Abushiba, Walid Abbas, Sagheer Lahore Pakistan College of Arts & Science Applied Science University P.O.Box 5055 Manama Bahrain Center for Cyber Security Faculty of Information Science and Technology Selangor Bangi43600 Malaysia College of Engineering Applied Science University Bahrain PMU Department of Computer Science Al Khobar Saudi Arabia

ISBN: (纸本)9798350365771

Healthcare's integration with the emerging artificial intelligence, predictive analytics and health information exchange (HIE) system is currently undergoing a revolution. These emerging technologies are offering better diagnostic accuracies, more personalized treatments, and better patients' outcomes. Artificial Intelligence supported by data from either Electronic Health Records or other big data sources are increasing the accuracy of forecasting critical patient conditions such as disease developments, hospital readmission rates, and mortality risks in patients. These AI-empowered models ensure seamless data sharing between the care providers and promote operational interoperability. Challenges to overcome include issues of privacy of the data, the biases of the prediction algorithms, and the proper integration of the model into the currently established operational environments of healthcare providers. With these technologies combined, it will become possible to optimize patient's outcomes with the provision of data to empower real-time medical interventions. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models 41

Intersecting-Boundary-Sensitive Fingerprinting for Tampering...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Bai, Xiaofan He, Chaoxiang Ma, Xiaojing Zhu, Bin Benjamin Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Microsoft United States School of Computer Science and Technology Huazhong University of Science and Technology China Cluster and Grid Computing Lab China

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF. Copyright 2024 by the author(s)

关键词： HTTP

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：