检索结果-内蒙古大学图书馆

NEAR: Non-Supervised Explainability Architecture for Accurate Review-Based Collaborative Filtering

IEEE Transactions on knowledge and Data engineering 2024年第2期36卷 750-765页

作者： Pugoy, Reinald Adrian Kao, Hung-Yu National Cheng Kung University Intelligent Knowledge Management Lab Department of Computer Science and Information Engineering Tainan City701 Taiwan University of the Philippines Open University Faculty of Information and Communication Studies Los Baños4031 Philippines

There is a critical issue in explainable recommender systems that compounds the challenges of explainability yet is rarely tackled: the lack of ground-truth explanation texts for training. It is unrealistic to expect every user-item pair in a dataset to have a corresponding target explanation. Hence, we pioneer the first non-supervised explainability architecture for review-based collaborative filtering (called NEAR) as our novel contribution to the theory of explanation construction in recommender systems. While maintaining excellent recommendation performance, our approach reformulates explainability as a non-supervised (i.e., unsupervised and self-supervised) explanation generation task. We formally define two explanation types, both of which NEAR can produce. An invariant explanation, fixed for all users, is based on the unsupervised extractive summary of an item's reviews via embedding clustering. Meanwhile, a variant explanation, personalized for a specific user, is a sentence-level text generated by our customized Transformer conditioned on every user-item-rating tuple and artificial ground-truth (self-supervised label) from one of the invariant explanation's sentences. Our empirical evaluation illustrates that NEAR's rating prediction accuracy is better than the other state-of-the-art baselines. Moreover, experiments and assessments show that NEAR-generated variant explanations are more personalized and distinct than those from other Transformer-based models, and our invariant explanations are preferred over those from other contemporary models in real life. © 1989-2012 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

AI Driven Psychological Pattern Analysis through Deep Learning-Enhanced Wearable Monitoring Systems 2

AI Driven Psychological Pattern Analysis through Deep Learni...

引用

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

作者： Abed Jawad, Mohammed Mohammed, Marwan Aziz Al-Hilali, Aqeel Taha Hussain, Faris Hassan Al-Nisour University College Baghdad Iraq Knowledge University College of Engineering Department of Computer Engineering Erbil Iraq Al-Farahidi University Department of Medical Instruments Engineering Techniques Baghdad10011 Iraq Al Kitab University Department of Medical Engineering Kirkuk Iraq

ISBN: (纸本)9798331534950

Quantitative research on tension environments has mostly used mobile assessment experiments in standardized settings. Recently, sensors and eye-tracking glasses have dedicated resources to future technologies, including multisensory monitoring systems that contain psychophysiological data in daily circumstances. This research proposes a Deep Learning aided wearable monitoring system (DLWMS) for psychological pattern analysis and mobile phone stress monitoring. Such systems must analyze stress states in mobile situations and look for tension parameter fluctuations. Using advanced quantitative monitoring system devices to collect physiological data on customers may help researchers study information systems (IS), which conventional treatments do not use. Participants demonstrate the possibility and acceptability of using m-Health technologies for psychophysiological health education. This approach helps prospective studies evaluate these technologies for optimizing safety in this sensitive population. © 2024 IEEE.

关键词： mHealth

来源：评论

学校读者我要写书评

暂无评论

Advanced deep learning approach for enhancing crop disease detection in agriculture using hyperspectral imaging

引用

Journal of Intelligent and Fuzzy Systems 2024年第2期46卷 3281-3294页

作者： Zekrifa, Djabeur Mohamed Seifeddine Lamani, Dharmanna Chaitanya, Gogineni Krishna Kanimozhi, K.V. Saraswat, Akash Sugumar, D. Vetrithangam, D. Koshariya, Ashok Kumar Manjunath, Manthur Sreeramulu Rajaram, A. Department of Bioinformatics Higher School of Food Science and Agri-Food Industry Ahmed Hamidouche Av Oued Smar Algiers Algeria Department of Computer Science & Information Technology School of Computing and Information Technology REVA University Rukmini Knowledge Park Kattigenahalli Karnataka Bengaluru India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India Department of Computer Science Engineering Dr. K. N. Modi University Jaipur Rajasthan Newai India Department of Electrical and Electronics Engineering Karunya Institute of Technology and Sciences Deemed to be University Coimbatore India Department of Computer Science and Engineering University Institute of Engineering Chandigarh University Punjab Mohali India Department of Plant Pathology School of Agriculture Lovely Professional University Punjab Phagwara India Department of Electronics and Communication Engineering E.G.S. Pillay Engineering College Tamilnadu Nagapattinam India

Crop diseases pose significant challenges to global food security and agricultural sustainability. Timely and accurate disease detection is crucial for effective disease management and minimizing crop losses. In recent years, hyperspectral imaging has emerged as a promising technology for non-destructive and early disease detection in crops. This research paper presents an advanced deep learning approach for enhancing crop disease detection using hyperspectral imaging. The primary objective is to propose a hybrid Autoencoder-Generative Adversarial Network (AE-GAN) model that effectively extracts meaningful features from hyperspectral images and addresses the limitations of existing techniques. The hybrid AE-GAN model combines the strengths of the Autoencoder for feature extraction and the Generative Adversarial Network for synthetic sample generation. Through extensive evaluation, the proposed model outperforms existing techniques, achieving exceptional accuracy in crop disease detection. The results demonstrate the superiority of the hybrid AE-GAN model, offering substantial advantages in terms of feature extraction, synthetic sample generation, and utilization of spatial and spectral information. The proposed model’s contributions to sustainable agriculture and global food security make it a valuable tool for advancing agricultural practices and enhancing crop health monitoring. With its promising implications, the hybrid AE-GAN model represents a significant advancement in crop disease detection, paving the way for a more resilient and food-secure future. © 2024 – IOS Press. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Application Layer IoT Protocols: MQTT and CoAP 4

Performance Evaluation of Application Layer IoT Protocols: M...

引用

4th International Conference on computer, Communication, Control and Information Technology, C3IT 2024

作者： Debnath, Manika Modak, Subrata Sarkar, Dhrubasish Supreme Knowledge Foundation Group of Institutions Department of Computer Science & Engineering West Bengal Mankundu India Supreme Institute of Management and Technology Computer Science & Information Technology West Bengal Mankundu India

ISBN: (纸本)9798350389128

The Internet of Things (IoT) is one of the most intriguing technological revolutions of the last few years due to its rapid expansion. The advancement of IoT applications is dependent on standard and real-time communication protocols. The IoT protocols are designed to enable reliable messaging. However, the selection of a standard and efficient messaging protocol is a difficult and intimidating task for any organization. One of the main challenging issues facing the loT is wireless sen-sor networks (WSNs). The devices that make up these networks have low levels of memory, processing power, and energy. Certain restricted protocols must be in place to function in WSNs due to their constrained nature. In the context of a business application for monitoring, this paper shows the experimental performance of two protocols: Message Queue Telemetry Transport (MQTT) and Constrained Application Protocol (CoAP). © 2024 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Improved Adaptive Fairness-Indexed Technique for Congestion Control in Underwater Networks 3

Improved Adaptive Fairness-Indexed Technique for Congestion ...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Balaji Vijayan, V. Manojee, K.S. Mohammed Ibrahim, M. Nivethitha, R. Thamaraimanalan, T. Ranjithkumar, M. Hkbk College of Engineering Department of Information Science and Engineering Karnataka Bengaluru India Kongunadu College of Engineering and Technology Department of Information Technology Tamilnadu Trichy India Sona College of Technology Department of Computer Science and Engineering Tamilnadu Salem India K.S.R. College of Engineering Department of Computer Science and Engineering Tamilnadu Thiruchengode India Sri Eshwar College of Engineering Department of Electronics and Communication Engineering Tamilnadu Coimbatore India Knowledge Institute of Technology Department of Computer Science and Business Systems Tamilnadu Salem India

ISBN: (纸本)9798331528201

In underwater acoustic sensor networks (UASNs), effective congestion control is essential for ensuring reliable data transmission and resource efficiency, especially in the face of challenging environmental factors such as water velocity, pressure, temperature, and salinity. This paper introduces a novel Adaptive Fairness-Indexed Congestion Control (AFICC) mechanism that employs Q-learning to dynamically adjust transmission rates among nodes, ensuring equitable resource distribution and minimizing congestion. Our simulations, conducted with 100 nodes at depths of up to 1000 meters, reveal that AFICC significantly outperforms two existing algorithms: Rate-Based Congestion Control (RBCC) and Energy-Aware Congestion Control (EACC). Specifically, AFICC achieved a Packet Delivery Ratio (PDR) of 93%, compared to 85% for RBCC and 80% for EACC. Additionally, the End-to-End Delay was reduced to an average of 150 milliseconds with AFICC, while RBCC and EACC recorded delays of 220 milliseconds and 210 milliseconds, respectively. AFICC also demonstrated a 25% improvement in Energy Efficiency over EACC and maintained a Jain's Fairness Index of 0.92, surpassing the 0.82 and 0.78 indices achieved by RBCC and EACC, respectively. These results confirm that AFICC offers a robust framework for congestion control in UASNs, effectively adapting to fluctuating underwater conditions while ensuring reliable communication and equitable resource allocation. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Solar Radiation Prediction Using the Random Forest Regression Algorithm 4th

Solar Radiation Prediction Using the Random Forest Regressio...

引用

4th EAI International Conference on Big Data Innovation for Sustainable Cognitive Computing, BDCC 2021

作者： Thota, Sandeep Kumar Reddy Mala, C. Chandamuri, Praneetha Nooka, Chandana Department of Computer Science and Engineering Rajiv Gandhi University of Knowledge Technologies- RK Valley Campus Andhra Pradesh Kadapa India Department of Computer Science and Engineering National Institute of Technology Tamil Nadu Tiruchirappalli India

ISBN: (纸本)9783031076534

Solar radiation data is critical for solar energy research and development. It is extremely valuable for design and simulation of solar thermal technologies and solar photovoltaic applications because it offers essential data about the energy that impacts the earth. Because conventional energy sources are rapidly decreasing, sustainable energy sources such as solar, biomass, and wind are growing more prominent. Solar energy is the most generally acknowledged renewable energy source since it is abundant all around the planet. As a result, this project examines the model and methodologies utilized to forecast solar radiation. Random forest algorithm is used in solar radiation prediction;this algorithm combines the benefits of both techniques utilized, resulting in faster calculation and convergence to optimal results. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Aerial Reliable Collaborative Communications for Terrestrial Mobile Users via Evolutionary Multi-Objective Deep Reinforcement Learning

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5731-5748页

作者： Sun, Geng Xiao, Jian Li, Jiahui Wang, Jiacheng Kang, Jiawen Niyato, Dusit Mao, Shiwen the College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China the College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore the School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore the School of Automation Guangdong University of Technology Guangzhou510641 China the Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States

—Unmanned aerial vehicles (UAVs) have emerged as the potential aerial base stations (BSs) to improve terrestrial communications. However, the limited onboard energy and antenna power of a UAV restrict its communication range and transmission capability. To address these limitations, this work employs collaborative beamforming through a UAV-enabled virtual antenna array to improve transmission performance from the UAV to terrestrial mobile users, under interference from non-associated BSs and dynamic channel conditions. Specifically, we introduce a memory-based random walk model to more accurately depict the mobility patterns of terrestrial mobile users. Following this, we formulate a multi-objective optimization problem (MOP) focused on maximizing the transmission rate while minimizing the flight energy consumption of the UAV swarm. Given the NP-hard nature of the formulated MOP and the highly dynamic environment, we transform this problem into a multi-objective Markov decision process and propose an improved evolutionary multi-objective reinforcement learning algorithm. Specifically, this algorithm introduces an evolutionary learning approach to obtain the approximate Pareto set for the formulated MOP. Moreover, the algorithm incorporates a long short-term memory network and hyper-sphere-based task selection method to discern the movement patterns of terrestrial mobile users and improve the diversity of the obtained Pareto set. Simulation results demonstrate that the proposed method effectively generates a diverse range of non-dominated policies and outperforms existing methods. Additional simulations demonstrate the scalability and robustness of the proposed CB-based method under different system parameters and various unexpected circumstances. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection and Security Enhancement Through Machine Learning in Administrative Information Systems 7

Anomaly Detection and Security Enhancement Through Machine L...

引用

7th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2023

作者： Awad, Omer Fawzi Sulaiman, Sazan Kamal Ali Alshmeel, Ghassan Hamada College of Medicine Tikrit University Department of Surgery Salahalden Iraq College of Computer Engineering Knowledge University Department of Computer Engineering Erbil Iraq Scientific Research Center Al-Ayen University Thi-Qar Iraq

ISBN: (纸本)9798350342154

The task of identifying anomalies in cybersecurity presents notable difficulties, frequently marked by substantial computational intricacy or dependence on heuristic approaches. This study presents a novel two-tier classification model that incorporates many machine learning approaches, such as Naïve Bayes, Random Forest, Decision Tree, Certainty Factor Voting version of KNN classifiers, and Linear Discriminant Analysis for dimension reduction. The experimental data reveal a considerable and promising improvement in detection rates and false alarms compared to previous models. The model is trained by utilizing two balanced training sets that are constructed using the SMOTE method. The evaluation of the chosen similarity measure is conducted to effectively handle imbalanced network anomaly datasets. The suggested model demonstrates a notable characteristic of having a low calculation time, which may be attributed to its effective dimension reduction and feature selection techniques. The system demonstrates exceptional proficiency in identifying uncommon and intricate forms of attacks, including those that closely resemble typical patterns of activity, such as User to Root and Remote to Local, which present elevated levels of risk. The evaluation procedures are carried out utilizing the Numenta Anomaly Benchmark (NAB) dataset, which offers a thorough evaluation of the effectiveness of the model in real-world situations. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Preserving Visual Authenticity: Block chain-Augmented AI Frameworks for Advanced Digital Deception Recognition and Mitigation 5

Preserving Visual Authenticity: Block chain-Augmented AI Fra...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Priya, M. Murugesan, J. Bhuvaneswari, P. Rubigha, M. Lalithambikai, S. Mohanraj, B. Knowledge Institute of Technology Department of Information Technology Salem India Sona College of Technology Department of Computer Science and Engineering Salem India Sona College of Technology Department of Information Technology Salem India

ISBN: (纸本)9798331504403

The rapid advancements in deep learning have given rise to sophisticated DeepFake technologies, posing significant threats to visual integrity and authenticity in digital media. This paper presents an innovative approach to DeepFake detection and mitigation by integrating blockchain technology with artificial intelligence frameworks. The proposed Blockchain-Augmented AI (BAAI) framework utilizes the immutability and decentralized nature of block chain to enhance the security and reliability of the detection process. Our method involves the development of advanced AI models for detecting DeepFakes, which are then integrated with a blockchain-based ledger to ensure the verifiability and traceability of detection results. In this proposed work, a novel integration of blockchain technology and AI designed to enhance DeepFake detection capabilities. The framework achieves a 97% accuracy rate, ensuring reliable identification of manipulated media, while maintaining a low false positive rate of 3%. These results highlight the BAAI framework's effectiveness in minimizing erroneous detections and its robustness in safeguarding digital visual content. In the face of increasingly sophisticated DeepFake technologies, this framework offers a crucial advancement in combating digital deception. © 2024 IEEE.

关键词： Blockchain-Augmented AI (BAAI) DeepFake Detection Detection Accuracy Detection Precision False Positives Media Authenticity Visual Integrity

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Reinforcement Learning Strategies for Enhanced Autonomous Vehicle Navigation Systems 2

Advanced Deep Reinforcement Learning Strategies for Enhanced...

引用

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Dhinakaran, M. Rajasekaran, R.Thalapathi Balaji, V. Aarthi, V. Ambika, S. Galgotias College of Engineering & Technology Knowledge Park Ii Department of Electronics and Communication Engineering Uttar Pradesh Greater Noida India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Easwari Engineering College Department of Computer Science and Engineering Chennai India Grt Institute of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Tiruttani India E.G.S. Pillay Engineering College Department of Information Technology Tamil Nadu Nagapattinam India

ISBN: (纸本)9798350387933

The objective of this research is to investigate more sophisticated techniques in Deep Reinforcement Learning (DRL) for the purpose of improving navigation systems for autonomous vehicles. The results of our research indicate that the success rates of DRL algorithms are encouraging: DQN (75.2%), PPO (82.6%), and TRPO (78.1%). The success of navigation is highly influenced by optimisation factors such as parameter tuning (87.4%), exploration-exploitation balance (85.1%), and reward shaping (88.9%). The generalisation score for transfer learning is rather good (92.3%), while the safety modules are designed to make the system safer. These findings highlight the significance of algorithm selection, parameter optimisation, and advanced techniques in the process of optimising navigation for autonomous vehicles, hence establishing essential benchmarks for future developments. © 2024 IEEE.

关键词： Navigation systems

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：