检索结果-内蒙古大学图书馆

A Social Distancing Framework Based on GPS and Bluetooth Empowered by Feature-based Machine Learning Algorithm

IEIE Transactions on Smart Processing and Computing 2025年第1期14卷 118-127页

作者： Khan, Muhammad Adnan Rehman, Abdur Abbas, Sagheer Ali, Muhammad Nadeem Kim, Byung-Seo Department of Software Faculty of Artificial Intelligence & Software Gachon University Seongnam13120 Korea Republic of School of Computer Science National College of Business Administration and Economics Lahore54000 Pakistan Department of Computer Science Prince Mohammad Bin Fahd University Al Khobar Saudi Arabia Department of Software and Communications Engineering Hongik University Sejong Campus Korea Republic of

The current COVID-19 epidemic is responsible for causing a catastrophe on a global scale due to its risky spread. The community’s insecurity is growing as a result of a lack of appropriate remedial measures and immunization against the disease. In this case, social distancing is thought to be an effective barrier against the spread of the contagion virus as the risk of virus transmission can be reduced by avoiding direct contact with people. Thus, the goal of this research is to develop and improve an AI (Artificial Intelligence) system architecture for social distance monitoring. The framework could also use the GPS (Global Positioning System) to recognize human separation through cell phones. The transition learning framework is also applied to improve the consistency of the existing system. In this manner, the detection system uses a pre-trained technique that takes a Bluetooth dataset and location-sharing dataset to link to an additional level. In an attempt to approximate social distancing breaches among people, we used Bluetooth technology along with GPS distance estimation and set a threshold. To predict if the distance value exceeds the required social distance standard, a violation threshold is calculated and then it sends an alarm to every individual who is not maintaining social distancing. In response, the individual who breaks the social distance limit is also monitored using a detection approach. © 2025 Institute of Electronics Engineers of Korea. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning

引用

Neural Computing and Applications 2025年第2期37卷 859-965页

作者： ŞAHiN, Emrullah Arslan, Naciye Nur Özdemir, Durmuş Department of Software Engineering Kütahya Dumlupınar University Kütahya43100 Turkey Department of Computer Engineering Kütahya Dumlupınar University Kütahya43100 Turkey

Deep learning models have revolutionized numerous fields, yet their decision-making processes often remain opaque, earning them the characterization of "black-box" models due to their lack of transparency and comprehensibility. This opacity presents significant challenges to understanding the rationale behind their decisions, thereby impeding their interpretability, explainability, and reliability. This review examines 718 studies published between 2015 and 2024 in high-impact journals indexed in SCI, SCI-E, SSCI, and ESCI, providing a crucial reference for researchers investigating methodologies and techniques in related domains. In this exploration, we evaluate a wide array of interpretability and explainability (XAI) strategies, including visual and feature-based explanations, local approach-based techniques, and Bayesian methods. These strategies are assessed for their effectiveness and applicability using a comprehensive set of evaluation metrics. Moving beyond traditional analyses, we propose a novel taxonomy of XAI methods, addressing gaps in the literature and offering a structured classification that elucidates the roles and interactions of these methods. Moreover, we explore the intricate relationship between interpretability and explainability, examining potential conflicts and highlighting the necessity for interpretability in practical applications. Through detailed comparative analysis, we underscore the strengths and limitations of various XAI methods across different data types, ensuring a thorough understanding of their practical performance and real-world utility. The review also examines model robustness against adversarial attacks, emphasizing the critical importance of transparency, reliability, and ethical considerations in model development. A significant emphasis is placed on identifying and mitigating biases in deep learning systems, providing insights into future research directions that aim to enhance fairness and reduce bias. By thoroughl

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning

DocTTT: Test-Time Training for Handwritten Document Recognit...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Gu, Wenhao Gu, Li Wang, Ziqiang Suen, Ching Yee Wang, Yang Concordia University Department of Computer Science and Software Engineering Canada

ISBN: (纸本)9798331510831

Despite recent significant advancements in Handwritten Document Recognition (HDR), the efficient and accurate recognition of text against complex backgrounds, diverse handwriting styles, and varying document layouts remains a practical challenge. Moreover, this issue is seldom addressed in academic research, particularly in scenarios with minimal annotated data available. In this paper, we introduce the DocTTT framework to address these challenges. The key innovation of our approach is that it uses test-time training to adapt the model to each specific input during testing. We propose a novel Meta-Auxiliary learning approach that combines Meta-learning and self-supervised Masked Autoencoder (MAE). During testing, we adapt the visual representation parameters using a self-supervised MAE loss. During training, we learn the model parameters using a meta-learning framework, so that the model parameters are learned to adapt to a new input effectively. Experimental results show that our proposed method significantly outperforms existing state-of-the-art approaches on benchmark datasets. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Text Similarity in Human and AI-Generated Scientific Abstracts: A Comprehensive Analysis

引用

IEEE Access 2025年 13卷 74313-74334页

作者： Celikten, Tugba Onan, Aytug Izmir Katip Celebi University Department of Computer Engineering Izmir Turkey Manisa Celal Bayar University Department of Software Engineering Manisa Turkey

Text similarity is a crucial area of study that evaluates how similar texts are both semantically and syntactically. As data volumes increase, understanding the similarities and relationships between texts becomes essential, particularly in natural language processing (NLP) tasks such as text generation, summarization, and classification. This study examines the similarities between human-written scientific abstracts, AI-paraphrased abstracts, and AI-generated abstracts. Various methods, including cosine similarity, Word2Vec, and BERT, were evaluated based on mean, median, and standard deviation metrics. Among these, Word2Vec and FastText achieved the highest mean similarity scores (0.930), while BERT demonstrated superior performance with the highest median (0.841) and the lowest standard deviation (0.019) in the ’Human-Paraphrased’ category, showing consistent results across datasets. Additionally, the research investigates the implications of these similarities for text analysis and ethical standards, comparing various techniques for measuring text similarity and analysing their effectiveness. The findings offer valuable insights into the application areas of text similarity analysis. © 2013 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

Utility-Enhanced Personalized Privacy Preservation in Hierarchical Federated Learning

引用

IEEE Transactions on Mobile Computing 2025年第6期24卷 5264-5279页

作者： Chen, Jianan Jiang, Honglu Hu, Qin Purdue University Indianapolis Department of Computer Science IndianapolisIN46202 United States Miami University Department of Computer Science and Software Engineering OxfordOH45056 United States Georgia State University Department of Computer Science AtlantaGA30303 United States

Federated learning (FL) is a distributed learning framework that allows clients to jointly train a model by uploading parameter updates rather than sharing local data. FL deployed on a client-edge-cloud hierarchical architecture, named Hierarchical Federated Learning (HFL), can accelerate model training and accommodate more clients with reduced communication cost via edge aggregation. Unfortunately, HFL suffers from privacy risks since the submitted parameters from clients are vulnerable to privacy attacks. To address this issue, we propose a novel Differential Privacy (DP) definition tailored for HFL, i.e., Group Local Differential Privacy (GLDP). We design the Sampling-Randomizing-Shuffling (SRS) mechanism to implement GLDP in HFL, where the sampling process is employed to achieve a stronger level of privacy protection with less noise added. By combining the randomized response and the shuffling mechanism, our proposed SRS mechanism can achieve client-level personalization within ρk-GLDP for privacy preservation while balancing model performance and privacy protection in HFL. Privacy analysis and convergence analysis are conducted to provide theoretical performance guarantees. Experimental results based on real-world datasets verify the effectiveness of SRS. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Sentiment Analysis for Low-Resource Languages Using Fine-Tuned LLMs: A Case Study of Customer Reviews in Turkish Language

引用

IEEE Access 2025年 13卷 77382-77394页

作者： Kiziltepe, Rukiye Savran Ezin, Ercan Yentur, Omer Basbrain, Arwa Karakus, Murat Ankara University Department of Software Engineering Ankara Turkey Harran University Department of Computer Engineering Şanliurfa Turkey Kron Technology Software Solutions-Data Security & Data Management İstanbul Turkey Department of Computer Science King Abdulaziz University Jeddah Saudi Arabia

This study investigates the application of advanced fine-tuned Large Language Models (LLMs) for Turkish Sentiment Analysis (SA), focusing on e-commerce product reviews. Our research utilizes four open-source Turkish SA datasets: Turkish Sentiment Analysis version 1 (TRSAv1), Vitamins and Supplements Customer Review (VSCR), Turkish Sentiment Analysis Dataset (TSAD), and TR Customer Review (TRCR). While these datasets were initially labeled based on star ratings, we implemented a comprehensive relabeling process using state-of-the-art LLMs to enhance data quality. To ensure reliable annotations, we first conducted a comparative analysis of different LLMs using the Cohen's Kappa agreement metric, which led to the selection of ChatGPT-4o-mini as the best-performing model for dataset annotation. Our methodology then focuses on evaluating the SA capabilities of leading instruction-tuned LLMs through a comparative analysis of zero-shot models and Low-Rank Adaptation (LoRA) fine-tuned LlaMA-3.2-1B-IT and Gemma- 2-2B-IT models. Evaluations were conducted on both in-domain and out-domain test sets derived from the original star-ratings-based labels and the newly generated GPT labels. The results demonstrate that our finetuned models outperformed leading commercial LLMs by 6% in both in-domain and out-domain evaluations. Notably, models fine-tuned on GPT-generated labels achieved superior performance, with in-domain and outdomain F1-scores reaching 0.912 and 0.9184, respectively. These findings underscore the transformative potential of combining LLM relabeling with LoRA fine-tuning for optimizing SA, demonstrating robust performance across diverse datasets and domains. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Integration of Federated Learning and Graph Convolutional Networks for Movie Recommendation Systems

引用

computers, Materials & Continua 2025年第5期83卷 2041-2057页

作者： Sony Peng Sophort Siet Ilkhomjon Sadriddinov Dae-Young Kim Kyuwon Park Doo-Soon Park Department of Software Convergence Soonchunhyang UniversityAsan31538Republic of Korea Department of Computer Software and Engineering Soonchunhyang UniversityAsan31538Republic of Korea AI⋅SW Education Institute Soonchunhyang UniversityAsan31538Republic of Korea

Recommendation systems(RSs)are crucial in personalizing user experiences in digital environments by suggesting relevant content or *** filtering(CF)is a widely used personalization technique that leverages user-item interactions to generate ***,it struggles with challenges like the cold-start problem,scalability issues,and data *** address these limitations,we develop a Graph Convolutional Networks(GCNs)model that captures the complex network of interactions between users and items,identifying subtle patterns that traditional methods may *** integrate this GCNs model into a federated learning(FL)framework,enabling themodel to learn fromdecentralized *** not only significantly enhances user privacy—a significant improvement over conventionalmodels but also reassures users about the safety of their ***,by securely incorporating demographic information,our approach further personalizes recommendations and mitigates the coldstart issue without compromising user *** validate our RSs model using the openMovieLens dataset and evaluate its performance across six key metrics:Precision,Recall,Area Under the Receiver Operating Characteristic Curve(ROC-AUC),F1 Score,Normalized Discounted Cumulative Gain(NDCG),and Mean Reciprocal Rank(MRR).The experimental results demonstrate significant enhancements in recommendation quality,underscoring that combining GCNs with CF in a federated setting provides a transformative solution for advanced recommendation systems.

关键词： Recommendation systems collaborative filtering graph convolutional networks federated learning framework

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Small-Sized Datasets Based on Eubank’s Optimal Spacing Theorem

引用

SN computer Science 2025年第1期6卷 1-19页

作者： Abedu, Samuel Mensah, Solomon Boafo, Frederick Department of Computer Science and Software Engineering Concordia University Montreal Canada Department of Computer Science University of Ghana Accra Ghana Department of Computer Science Lancaster University Ghana Accra Ghana

Conventional machine learning methods for software effort estimation (SEE) have seen an increase in research interest. Conversely, there are few research that try to evaluate how well deep learning techniques work in SEE. This can be attributed to the relatively small sizes of SEE datasets. The goal of the study is to establish a threshold for small-sized datasets in SEE. Additionally, it looks into how well certain deep learning and traditional machine learning models perform on small-sized datasets. From the body of existing literature, plausible SEE datasets are extracted and ranked along with their attributes and number of project cases. The ranking of the project instances is discretized into three classes (small, medium, and large) using Eubank’s optimal spacing theory. Using the leave-one-out cross-validation, each small-sized dataset is used to train two deep learning models and five conventional machine learning models. Each model’s ability to make predictions is evaluated using its mean absolute error. Results show that, on small-scale datasets, deep learning models outperform traditional machine learning models in terms of prediction accuracy, which contradicts what is previously known. Regularisation techniques can be used in conjunction with deep learning to address SEE. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning Eubank’s optimal spacing theory Small-sized software effort estimation Traditional Machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Bit-Plane Based Medical Image Cryptosystem Using Novel and Robust Sine-Cosine Chaotic Map

引用

computers, Materials & Continua 2025年第4期83卷 917-933页

作者： Zeric Tabekoueng Njitacke Louai A.Maghrabi Musheer Ahmad Turki Althaqafi Department of Electrical and Electronic Engineering College of Technology(COT)University of BueaBueaP.O.Box 63Cameroon Department of Software Engineering College of EngineeringUniversity of Business and TechnologyJeddah22246Saudi Arabia Department of Computer Engineering Jamia Millia IslamiaNew Delhi110025India Department of Computer Science School of EngineeringComputing and DesignDar Al-Hekma UniversityJeddah22246Saudi Arabia

This paper presents a high-security medical image encryption method that leverages a novel and robust sine-cosine *** map demonstrates remarkable chaotic dynamics over a wide range of *** employ nonlinear analytical tools to thoroughly investigate the dynamics of the chaotic map,which allows us to select optimal parameter configurations for the encryption *** findings indicate that the proposed sine-cosine map is capable of generating a rich variety of chaotic attractors,an essential characteristic for effective *** encryption technique is based on bit-plane decomposition,wherein a plain image is divided into distinct bit *** planes are organized into two matrices:one containing the most significant bit planes and the other housing the least significant *** subsequent phases of chaotic confusion and diffusion utilize these matrices to enhance *** auxiliary matrix is then generated,comprising the combined bit planes that yield the final encrypted *** results demonstrate that our proposed technique achieves a commendable level of security for safeguarding sensitive patient information in medical *** a result,image quality is evaluated using the Structural Similarity Index(SSIM),yielding values close to zero for encrypted images and approaching one for decrypted ***,the entropy values of the encrypted images are near 8,with a Number of Pixel Change Rate(NPCR)and Unified Average Change Intensity(UACI)exceeding 99.50%and 33%,***,quantitative assessments of occlusion attacks,along with comparisons to leading algorithms,validate the integrity and efficacy of our medical image encryption approach.

关键词： Image cryptosystem robust chaos sine-cosine map nonlinear analysis tools medical images

来源：评论

学校读者我要写书评

暂无评论

A Trustworthy Analysis Approach for Chatbots on Health Data: ChatGPT-4 Example 29

A Trustworthy Analysis Approach for Chatbots on Health Data:...

引用

29th International Conference on Information Technology, IT 2025

作者： Arslanoǧlu, Kübra Karaköse, Mehmet The University of Firat The Faculty of Engineering The Department of Software Engineering Elazig Turkey The University of Firat The Faculty of Engineering The Department of Computer Engineering Elazig Turkey

ISBN: (纸本)9798331517649

Considering the increasing and widespread use of chatbots, it is of great importance to provide methods and tools to address ethical concerns and to make users aware of various aspects of a chatbot, including non-functional features. The Generative Pre-Trained Transformer (GPT) is a state-of-the-art Natural Language Generation (NLG) model, enhanced by the latest version of GPT-4. This study evaluates the trustworthiness of the responses of three different chatbot models, BlenderBot with Hugging Face, ChatGPT-3.5 and ChatGPT-4, to 100 randomly selected medical questions. The accuracy and semantic similarity of the answers were measured by BLEU, ROUGE-1 and Cosine Similarity metrics, and response times were also recorded as an important performance factor. The results showed that GPT-4 exhibited superior performance, thus being able to produce more accurate and contextually reliable responses. However, the significantly longer response time of GPT-4 emerged as a disadvantage that may affect real-time utilisation. These findings provide an important reference for the effective use of GPT-4 in the context of health chatbots. The study contributes to the literature on improving the effectiveness of chatbots in healthcare by drawing attention to the importance of balancing speed, accuracy and trustworthiness, as well as the fact that the answers obtained are drawn with Application Programming Interface (API). © 2025 IEEE.

关键词： Electronic health record

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：