检索结果-内蒙古大学图书馆

IEEE Students' Conference on Electrical, Electronics and computer science (SCEECS)

作者： Sivasanjith G Mohan Prabhu N Hemaswathi S Rajkumar P Rajeshkannan C R. Dhivya Dept. of Information Technology KARE Krishnankovil India Artificial Intelligence and Data Science Indra Ganesan College of Engineering Tiruchirappalli India Dept. of Computer Science and Engg. Mount Zion College of Engg. and Tech. Pudukottai India Dept. of Computer Science and Engg. Suguna College of Engineering Coimbatore India Dept. of Information Technology M.Kumarasamy College of Engineering Karur India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

All over the world, the population of elderly people is increasing a lot. There needs to be special attention to the welfare of the elderly person to make them confident in their independent quality of living. In recent years, researchers have shown much interest in smart home automation for people who live alone without any human assistance. However, the purchase of medical drugs, diapers, etc., outside the house has to be fulfilled by their family members or caretakers. In most cases, it is not feasible, as the family members may stay long away from the elders. Purchasing online is easy; however, analyzing the best product requires knowledge in each e-commerce application for better quality at a low cost. This paper proposes an integrated and intelligent e-commerce framework to avoid the drawback of purchasing items online in a single window using the NLP technique. The proposed framework provides offers, discounts, star ratings, and product reviews by analyzing other customers’ review data and purchase patterns. It provides interactive data analysis at a single window for the ease of elderly persons. The performance of the proposed framework was evaluated by 120 elderly persons using a simple questionnaire with a statistical analysis of a sample purchase.

关键词： Drugs Sentiment analysis Reviews Statistical analysis Urban areas Stars Smart homes Electronic commerce Older adults Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Integrating Spatial and Frequency Information for Under-Display Camera Image Restoration

arXiv

引用

arXiv 2025年

作者： Ahn, Kyusu Kim, Jinpyo Park, Chanwoo Kim, JiSoo Lee, Jaejin Dept. of Data Science Seoul National University Seoul Korea Republic of Dept. of Computer Science and Engineering Seoul National University Seoul Korea Republic of Research Center Samsung Display Co. Ltd. Yongin Korea Republic of

Under-Display Camera (UDC) houses a digital camera lens under a display panel. However, UDC introduces complex degradations such as noise, blur, decrease in transmittance, and flare. Despite the remarkable progress, previous research on UDC mainly focuses on eliminating diffraction in the spatial domain and rarely explores its potential in the frequency domain. It is essential to consider both the spatial and frequency domains effectively. For example, degradations, such as noise and blur, can be addressed by local information (e.g., CNN kernels in the spatial domain). At the same time, tackling flares may require leveraging global information (e.g., the frequency domain). In this paper, we revisit the UDC degradations in the Fourier space and figure out intrinsic frequency priors that imply the presence of the flares. Based on this observation, we propose a novel multi-level DNN architecture called SFIM. It efficiently restores UDC-distorted images by integrating local and global (the collective contribution of all points in the image) information. The architecture exploits CNNs to capture local information and FFT-based models to capture global information. SFIM comprises a spatial domain block (SDB), a Frequency Domain Block (FDB), and an Attention-based Multi-level Integration Block (AMIB). Specifically, SDB focuses more on detailed textures such as noise and blur, FDB emphasizes irregular texture loss in extensive areas such as flare, and AMIB enables effective cross-domain interaction. SFIM’s superior performance over state-of-the-art approaches is demonstrated through rigorous quantitative and qualitative assessments across three UDC benchmarks. © 2025, CC BY-NC-SA.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Comprehensive RAG-Driven Dashboard Within the ILO System for data Visualization and Query Support: A Case Study of the University of Petra

Design and Implementation of a Comprehensive RAG-Driven Dash...

引用

Computational Intelligence Approaches and applications (ICCIAA), International Conference on

作者： Mohammad Abu-Arqoub Abed Alkarim Banna Nuha El-Khalili Mohammad Al-Shaikh Hasan Department of Computer Science University of Petra Amman Jordan Data Science & Artificial Intelligence Dept. University of Petra Amman Jordan Software Engineering Department University of Petra Amman Jordan Computer Science Department Brunel University London London UK

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This article presents a comprehensive study on designing and implementing a dashboard for enhanced data visualization and query support at the University of Petra. The system leverages retrieval-augmented generation (RAG) and large language models (LLMs) to support diverse document types, including curricula, course descriptions, and program outcomes, alongside intended learning outcome (ILO)-related files. Our implementation demonstrates significant improvements in data accessibility and query response times while maintaining high accuracy in information retrieval and visualization. Through extensive evaluation, we show that this innovative approach transforms data management processes in higher education by enabling natural language interactions with educational data systems, building upon established business intelligence frameworks while introducing advanced AI capabilities.

关键词： Large language models Retrieval augmented generation Natural languages data visualization Transforms Educational technology Information retrieval data systems Business intelligence Time factors

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Machine Learning Approaches for Phishing Website Detection

Comprehensive Analysis of Machine Learning Approaches for Ph...

引用

Cognitive Computing in Engineering, Communications, sciences and Biomedical Health Informatics (IC3ECSBHI), International Conference on

作者： Pragna K P Suhani Shetty Ashwini Kodipalli Ushasree. A Shridhar B. Devamane Roshan Joy Martis Dept. of Electronics and Communication Engineering Global Academy Of Technology Bengaluru Karnataka India Dept. of Artificial Intelligence & Data Science Global Academy of Technology Bengaluru Karnataka India Dept. of Computer Science & Engineering Gokaraju Lailavathi Engineering College Hyderabad India Department of Computer Science School of Computing Amrita Vishwavidyapeetam Mysuru Dept. of Electronics & Communication Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

Website phishing, a notable cybercrime, involves deceiving individuals by impersonating legitimate websites. URL spoofing, a common technique in website phishing, involves creating website names. The primary objective of this paper is to accurately differentiate between legitimate and phishing sites using relevant URL attributes and different binary classification machine learning algorithms. This study compares simple, bagging, and boosting algorithms across performance analysis metrics. The best-performing models are selected for an ensemble approach. Additionally, various hyperparameter tuning techniques are assessed for the Random Forest Classifier, and Explainable AI methods like LIME and SHAP are used to interpret findings. The experiment yields optimal parameters, achieving 89. % accuracy with an ensemble model with K-Nearest Neighbors, Decision Tree, XG Boost, and Cat Boost. These findings highlight the significance of ensemble models and hyperparameter tuning in machine learning.

关键词： Uniform resource locators Machine learning algorithms Explainable AI Phishing Computational modeling Biological system modeling Nearest neighbor methods Performance analysis Tuning Random forests

来源：评论

学校读者我要写书评

暂无评论

Optimizing Production and Inventory Management for Defective Items in Manufacturing Systems 3

Optimizing Production and Inventory Management for Defective...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Ahmed, Khandakar Rabbi Hossain, Arafat Asif, MD Amaddus Bepary Mohammad, Mahathir Rahaman, Mustafizur Dewan, MD Arafat Miyan Research Institute International University of Business Agriculture and Technology Dhaka Bangladesh Central Michigan University Dept. of Business Data Analytics Mt Pleasant United States Southern California State University Dept. of Business Administration and Management Los Angeles CA United States Southern California State University Dept. of Business Administration and Management United States Westcliff University Dept. of Cloud Engineering Irvine CA United States Los Angeles City College Dept. of Computer Science Los Angeles United States

ISBN: (纸本)9798331523893

Manufacturing defective items is one of the challenges for production efficiency and inventory control. Conventional approaches like Economic Order Quantity (EOQ) and Just-in-Time (JIT) often fall short of the flexibility needed to respond to quality variations in real time. It promotes defect detection and control by employing machine learning (ML) for inventory management. Four classifiers were tested using the UCI SECOM dataset (Bagging, AdaBoost, Gradient Boosting, and Random Forest) to identify defective items. We used effective preprocessing techniques to boost model performance, such as SMOTE for class balancing and PCA for reducing dimensionality and standardization. The bagging and random forest classifiers produced 96.6% and 96.9% test accuracies, with good precision and recall scores. Within this context, we propose an Adaptive Inventory Management Framework comprising machine learning algorithms incorporating predictive analytics to reduce waste, optimize production scheduling(s), and improve resource allocation. These results are consistent with defining Industry 4.0 strategies and show that ML has the potential to transform defect management and inventory optimization in manufacturing systems. © 2025 IEEE.

关键词： Defective Items Industry 4.0 Inventory Management Machine Learning Manufacturing Systems SECOM dataset

来源：评论

学校读者我要写书评

暂无评论

Smoke Level Monitoring and Alerting in Automobiles using IoT

Smoke Level Monitoring and Alerting in Automobiles using IoT

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： M. Vani Pujitha Teja Aravind Kumar Rayalavarapu Lal Basha Shaik Sashank Madhabushi Department of Computer Science and Engineering Velagapudi Ramakrishna Siddhartha Engineering College Andhra Pradesh India Dept. of Artificial Intelligence and Data Science Velagapudi Ramakrishna Siddhartha Engineering College Andhra Pradesh India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Vehicle emissions significantly exacerbate air pollution, releasing harmful gases such as carbon monoxide (CO), nitrogen dioxide (NO 2 ), and hydrocarbons (HC) from poorly maintained engines and inefficient combustion processes. The study presents an Internet of Things (IoT)-based system to monitor the emissions, which mainly includes key pollutants like CO, NO 2 , and HC in real-time. Strategically positioned gas sensors near the vehicle's exhaust capture emission data, which an Arduino microcontroller processes with high accuracy. The system delivers continuous gas level updates via an LCD display and leverages an IoT framework to ensure seamless integration of sensors, microcontrollers, and mobile devices. This connectivity enables real-time data transmission and remote alerting, enhancing emission management. When pollutant levels surpass predefined safety thresholds, the system triggers immediate alerts through a Global System for Mobile Communications (GSM) module (SIM 900) via SMS to the vehicle owner's mobile, complemented by an audible buzzer. This alert notification encourages timely maintenance, reducing emissions and improving vehicle performance and contributing to cleaner air.

关键词： GSM Microcontrollers Real-time systems Sensor systems Mobile handsets Sensors Safety Nitrogen Gas detectors Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectives

arXiv

引用

arXiv 2025年

作者： Hossain, Delower Chen, Jake Y. Dept. of Computer Science The University of Alabama Birmingham United States Dept. of Genetic Biomedical Engineering Informatics and Data Science Heersink School of Medicine The University of Alabama Birmingham United States Systems Pharmacology AI Research Center The University of Alabama Birmingham United States

Over the last few decades, Artificial Intelligence (AI) scientists have been conducting investigations to attain human-level performance by a machine in accomplishing a cognitive task. Within machine learning, the ultimate aspiration is to attain Artificial General Intelligence (AGI) through a machine. This pursuit has led to the exploration of two distinct AI paradigms. Symbolic AI, also known as classical or GOFAI (Good Old-Fashioned AI) and Connectionist (Sub-symbolic) AI, represented by Neural Systems, are two mutually exclusive paradigms. Symbolic AI excels in reasoning, explainability, and knowledge representation but faces challenges in processing complex real-world data with noise. Conversely, deep learning (Black-Box systems) research breakthroughs in neural networks are notable, yet they lack reasoning and interpretability. Neuro-symbolic AI (NeSy), an emerging area of AI research, attempts to bridge this gap by integrating logical reasoning into neural networks, enabling them to learn and reason with symbolic representations. While a long path, this strategy has made significant progress towards achieving common sense reasoning by systems. This article conducts an extensive review of over 977 studies from prominent scientific databases (DBLP, ACL, IEEExplore, Scopus, PubMed, ICML, ICLR), thoroughly examining the multifaceted capabilities of Neuro-Symbolic AI, with a particular focus on its healthcare applications, particularly in drug discovery, and Protein engineering research. The survey addresses vital themes, including reasoning, explainability, integration strategies, 41 healthcare-related use cases, benchmarking, datasets, current approach limitations from both healthcare and broader perspectives, and proposed novel approaches for future experiments. Moreover, it identifies critical challenges in applying Neuro-Symbolic AI to medicine and represents a comprehensive exploration of its transformative potential in the biomedical field. © 2025, CC BY-NC

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

SkyNetPredictor: Network Performance Prediction in Avionic Communication using AI

arXiv

引用

arXiv 2025年

作者： Mukhtar, Hind Schaub, Raymond Erol-Kantarci, Melike Satcom Direct Inc. Melbourne Florida University of Ottawa OttawaON Canada Dept. of Data Science Satcom Direct Inc. MelbourneFL United States Dept. of Electrical & Computer Engineering University of Ottawa OttawaON Canada

Satellite-based communication systems are integral to delivering high-speed data services in aviation, particularly for business aviation operations requiring global connectivity. These systems, however, are challenged by a multitude of interdependent factors such as satellite handovers, congestion, flight maneuvers and seasonal trends, making network performance prediction a complex task. No established methodologies currently exist for network performance prediction in avionic communication systems. This paper addresses the gap by proposing machine learning (ML)-based approaches for pre-flight network performance predictions. The proposed models predict performance along a given flight path, taking as input positional and network-related information and outputting the predicted performance for each position. In business aviation, flight crews typically have multiple flight plans to choose from for each city pair, allowing them to select the most optimal option. This approach enables proactive decision-making, such as selecting optimal flight paths prior to departure. © 2025, CC BY-NC-ND.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Psi-zeta Approach for Assessing Network Efficiency in Log-Normal Fading and Spectrum Sharing Interference Environments

Psi-zeta Approach for Assessing Network Efficiency in Log-No...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： Preeti Narooka Shekhar Verma Abhishek Dwivedi Keshav Kaushik Vineeta Singh Priyanka Gaur Artificial Intelligence and Machine Learning School of Computer and Engineering Manipal University Jaipur Rajasthan India Department of Computer Applications School of Engineering and Technology Chhatrapati Shahu ji Maharaj University Kanpur India Sharda School of Computer Science & Engineering Sharda University Greater Noida India Department of Computer Science and Engineering School of Engineering and Technology Chhatrapati Shahu ji Maharaj University Kanpur India Dept. of Computer Applications Chandigarh Group of Colleges Jhanjheri Mohali India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

The paper introduced the Psi-zeta computation of network efficiency under a scenario of log-normal fading and spectrum sharing interferences. This model is aimed to improve different performance metrics such as throughput, Signal-to-Interference-plus-Noise-Ratio (SINR), energy efficiency and finally outage probability also reducing. Simulations demonstrate that when evaluating the overall performance, Psi-zeta is superior to traditional methods by managing interference and resource allocation agilely. The results, especially under high load and heavy interference conditions, exhibit remarkable enhancements in network performance. The strong modifiability and expandability of psi-zeta show that it can be a good candidate for improving network efficiency in future wireless networks like 6G, where parameters like performance, reliability and energy efficiency are the key factors. This work has significant potential to enable the next-generation communication systems.

关键词： Fading channels Wireless networks Interference Probability Throughput Energy efficiency Power system reliability Reliability Next generation networking Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning for Smart Healthcare Using SDN-Driven Edge Computing

Personalized Federated Learning for Smart Healthcare Using S...

引用

IEEE Southeastcon

作者： Deborsi Basu Ritu Chaudhary Uttam Ghosh Raja Datta G. S. Sanyal School of Telecommunications Indian Institute of Technology Kharagpur India Dept. of Electronics and Electrical Communication Engineering Indian Institute of Technology Kharagpur India Dept. of Computer Science and Data Science School of Applied Computational Sciences MMC TN USA

ISBN: (数字)9798331504847

ISBN: (纸本)9798331504854

The advancement in distributed Federated Learning (FL) techniques is transforming next-generation edge computing, especially in e-Helathcare systems where data integrity and security are critical concerns. Collecting, processing and analyzing such substantial medical data is highly challenging due to their non-identical and versatile nature. Conventional FL approaches often show unsatisfactory and inaccurate results while operating on those data. Traditional FL methods also lack optimal dynamic management mechanisms for edge devices in ehealthcare, which is crucial to ensure that only authorized devices participate in handling any system failures and new registrations. To tackle such important aspects, in this work, we propose a personalized FL technique to handle abrupt label shifts among clients' data. The proposed approach further targets to achieve personalized models for local edge clients. A statistical batch normalization is proposed on customized edge servers, keeping the data specificity intact. To make the proposed system more secure and robust, a Software Defined Network-based (SDN-based) centralized server is used that allows only authorized and efficient edge clients to participate. The proposed comprehensive experiments on two healthcare datasets demonstrate better accuracy than traditional FL methods with enhanced security and privacy.

关键词： data privacy Federated learning data integrity Medical services Servers Security Software defined networking Next generation networking Batch normalization Edge computing

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：