检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Wen, Ximing Tan, Wenjuan Weber, Rosina O. College of Computing and Informatics Drexel University Philadelphia United States Department of Computer Science Tsinghua University Beijing China

ISBN: (纸本)9798891761964

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on text classification tasks with their powerful word embeddings, but their black-box nature, which leads to a lack of interpretability, has been a major concern. In this work, we introduce GAProtoNet, a novel white-box Multi-head Graph Attention-based Prototypical Network designed to explain the decisions of text classification models built with LM encoders. In our approach, the input vector and prototypes are regarded as nodes within a graph, and we utilize multi-head graph attention to selectively construct edges between the input node and prototype nodes to learn an interpretable prototypical representation. During inference, the model makes decisions based on a linear combination of activated prototypes weighted by the attention score assigned for each prototype, allowing its choices to be transparently explained by the attention weights and the prototypes. Experiments on multiple public datasets show our approach achieves superior results without sacrificing the accuracy of the original black-box LMs. We also compare with four alternative prototypical network variations and our approach achieves the best accuracy and F1 among all. Our case study and visualization of prototype clusters also demonstrate the efficiency in explaining the decisions of black-box models built with LMs. Our codes are available at https://***/ximingwen/GAProtoNet. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Integration of data science with the intelligent IoT(IIoT): Current challenges and future perspectives

引用

Digital Communications and Networks 2025年第2期11卷 280-298页

作者： Inam Ullah Deepak Adhikari Xin Su Francesco Palmieri Celimuge Wu Chang Choi Department of Computer Engineering Gachon University University of Electronic Science and Technology of China College of Information Science and Engineering Hohai University Department of Computer Science University of Salerno Graduate School of Informatics and Engineering The University of Electro-Communications

The Intelligent Internet of Things(IIoT) involves real-world things that communicate or interact with each other through networking technologies by collecting data from these “things” and using intelligent approaches, such as Artificial Intelligence(AI) and machine learning, to make accurate decisions. Data science is the science of dealing with data and its relationships through intelligent approaches. Most state-of-the-art research focuses independently on either data science or IIoT, rather than exploring their integration. Therefore, to address the gap, this article provides a comprehensive survey on the advances and integration of data science with the Intelligent IoT(IIoT) system by classifying the existing IoT-based data science techniques and presenting a summary of various characteristics. The paper analyzes the data science or big data security and privacy features, including network architecture, data protection, and continuous monitoring of data, which face challenges in various IoT-based systems. Extensive insights into IoT data security, privacy, and challenges are visualized in the context of data science for IoT. In addition, this study reveals the current opportunities to enhance data science and IoT market development. The current gap and challenges faced in the integration of data science and IoT are comprehensively presented, followed by the future outlook and possible solutions.

关键词： Data science Internet of things (IoT) Big data Communication systems Networks Security Data science analytics

来源：评论

学校读者我要写书评

暂无评论

Aspect-based sentiment analysis in MOOCs: a systematic literature review introducing the MASC-MEF framework

引用

Journal of King Saud University - computer and Information sciences 2025年第1期37卷 1-33页

作者： Awadh, Wed Akeel Sulaiman, Rosnafisah Bte Mahmoud, Moamin A. Institute of Informatics and Computing in Energy University Tenaga Nasional Kajang Malaysia Department of Computer Information Systems University of Basrah Basrah Iraq Institute of Informatics and Computing in Energy Department of Informatics Universiti Tenaga Nasional Jalan IKRAM UNITEN Selangor Kajang Malaysia Institute of Informatics and Computing in Energy Department of Computing College of Computing and Informatics Universiti Tenaga Nasional Selangor Kajang Malaysia

Aspect-based sentiment analysis (ABSA) in massive open online courses (MOOCs) offers a powerful tool to understand student experiences and improve the quality of online education. As MOOCs grow in popularity, there is an increasing need to analyze student feedback at a granular level, focusing on specific course aspects rather than just overall sentiment. Despite ABSA’s potential in MOOCs, research in this specific domain remains limited. Thus, this review of the literature seeks to fill this gap by systematically examining ABSA within the realm of MOOCs. We utilized a PRISMA framework to guide the search process. Consequently, this review covered 57 studies conducted between 2019 and 2024, retrieved from eight electronic research databases. The studies included in this analysis were examined on the basis of their datasets, data preprocessing, ABSA tasks in MOOCs, evaluation aspects in online courses, fusion approach in ABSA, techniques of word representations, and evaluation criteria utilized to evaluate the proposed models. Additionally, this review introduces the multiaspect sentiment classification using multiembedding and fusion (MASC-MEF) framework, a novel approach that uniquely incorporates multiword embeddings and multifeature extraction along with advanced classification techniques. Results shed light on several critical issues and various limitations, pointing towards future directions for ABSA research within the realm of MOOCs. This review underscores significant contributions to improving ABSA in educational technology, with a focus on course effectiveness and advancements in online learning, guiding researchers towards innovative techniques to tackle this challenge in the future. © The Author(s) 2025.

关键词： Aspect-based sentiment analysis Massive open online courses Multiaspect sentiment classification Online education technology Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Optimizing Image Retrieval in Cloud Servers with TN-AGW: A Secure and Efficient Approach

引用

Journal of The Institution of Engineers (India): Series B 2025年第2期106卷 459-473页

作者： Ponnuviji, N.P. Nirmala, G. Kokila, M. L. Sworna Priyadharshini, S. Indra Department of Computer Science and Engineering RMK College of Engineering and Technology Puduvoyal Thiruvallur India Department of Computer Science and Engineering RMD Engineering College Chennai India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nādu Kattankulathur Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

The increasing use of cloud-based image storage and retrieval systems has made ensuring security and efficiency crucial. The security enhancement of image retrieval and image archival in cloud computing has received considerable attention in transmitting data and ensuring data confidentiality among cloud servers and users. Various traditional image retrieval techniques regarding security have developed in recent years but they do not apply to large-scale environments. This paper introduces a new approach called Triple network-based adaptive grey wolf (TN-AGW) to address these challenges. The TN-AGW framework combines the adaptability of the Grey Wolf Optimization (GWO) algorithm with the resilience of Triple Network (TN) to enhance image retrieval in cloud servers while maintaining robust security measures. By using adaptive mechanisms, TN-AGW dynamically adjusts its parameters to improve the efficiency of image retrieval processes, reducing latency and utilization of resources. However, the image retrieval process is efficiently performed by a triple network and the parameters employed in the network are optimized by Adaptive Grey Wolf (AGW) optimization. Imputation of missing values, Min–Max normalization, and Z-score standardization processes are used to preprocess the images. The image extraction process is undertaken by a modified convolutional neural network (MCNN) approach. Moreover, input images are taken from datasets such as the Landsat 8 dataset and the Moderate Resolution Imaging Spectroradiometer (MODIS) dataset is employed for image retrieval. Further, the performance such as accuracy, precision, recall, specificity, F1-score, and false alarm rate (FAR) is evaluated, the value of accuracy reaches 98.1%, the precision of 97.2%, recall of 96.1%, and specificity of 917.2% respectively. Also, the convergence speed is enhanced in this TN-AGW approach. Therefore, the proposed TN-AGW approach achieves greater efficiency in image retrieving than other existing

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Enhanced sentiment analysis framework: Ensemble attention enhanced bidirectional long-short-term encoder for accurate classification of consumer reviews

引用

Alexandria Engineering Journal 2025年 127卷 265-283页

作者： Almalki, Ali Jaber Department of Computer Science and Artificial Intelligence College of Computing and Information Technology University of Bisha Bisha61922 Saudi Arabia

The fast growth of today's technology on social media, the web, etc caused the ongoing and fast creation of opinionated textual data. In this context, internet reviews by consumers determine upcoming consumers whether can buy a particular product or not. Because the thoughts regarding the products are expressed by commenting on reviews. The sentiment analysis is more supportive for comprehending feedback and the attitude of consumers regarding the product's characteristics. More sentiment classification tasks are carried out by the researchers but attained low level output due to difficulty in learning contextual words. To rectify this type of issue, current work focuses on developing a sentiment analysis framework by progressive techniques. The novel namely Ensemble Attention Enhanced Bidirectional Long-short-term Encoder (EAE-BiLE) is developed. The developed method analyzes online reviews and gains reviews from Amazon and the second task is to form high-quality input. The BERT model generates contextual word embeddings and Bi-directional Long-Short-Term Memory (Bi-LSTM) processes these embeddings in order to capture both backward and forward dependencies from the text. The novel method makes the accurate classification by focusing on important and relevant parts in the text using an attention mechanism that assigns different weights. Detailed experiments that expose the performance of the developed method are performed in this work. This requires a few evaluation metrics that can measure the effectiveness of the developed method, which is accomplished by F1-score, recall, accuracy, and precision. The developed EAE-BiLE framework yields higher rates of 97.2 %, 97.2 %, 99.1 %, and 98.4 % for precision, F1-score, accuracy, and recall. Its error performance is also low, which represents the developed method makes the precise classification. The developed EAE-BiLE excels with higher effectiveness than prior techniques for efficacious sentiment classification. © 2025 T

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

End-to-end optimized ensemble model for Alzheimer’s disease detection 19

End-to-end optimized ensemble model for Alzheimer’s disease...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Hassan, Abdelrahman Abuhmed, Tamer El-Sappagh, Shaker Faculty of Computer Science and Engineering Galala University Egypt College of Computing and Informatics Sungkyunkwan University Korea Republic of

ISBN: (纸本)9798331507817

Alzheimer's disease (AD) is a progressive neurodegenerative disorder with an increasing prevalence among the elderly, making early and accurate diagnosis critical for effective intervention and management. This paper introduces an end-to-end machine learning pipeline optimized for detecting AD using multimodal data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The study proposes an ensemble model that integrates key modalities—demographics, cognitive scores, neuropsychological assessments, and MRI data—via early fusion to enhance AD detection. Various machine learning models, including Logistic Regression, Gradient Boosting, AdaBoost, XGBoost, Support Vector Machine, and Neural Networks, are compared, and feature selection is optimized through Recursive Feature Elimination, ANOVA F-value, and mutual information methods, with mutual information showing the most efficacy. With further hyperparameter tuning, the highest accuracy is achieved at 95.85%, with Gradient Boosting as the top-performing model. Additional experiments assess and evaluate individual modality contributions, underscoring the predictive value of cognitive scores and neuropsychological features. To enhance clinical interpretability, we incorporate model explainability using LIME and SHAP, which identify key features influencing model predictions across different AD stages. Explainable AI (XAI) is essential in healthcare for providing transparency and supporting clinician confidence by highlighting which biomarkers, such as MMSE, CDRSB, and PTAU, contribute most to diagnostic outcomes. This study demonstrates classical machine learning's potential in AD diagnostics, offering a pathway to cost-effective and clinically viable models for neurodegenerative disease management. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Smart Pharmacy Systems: Enhancing Drug Safety and Operational Efficiency 19

Leveraging Large Language Models for Smart Pharmacy Systems:...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Osheba, Abdelrahman Abou-El-Ela, Ahmed Adel, Osama Maaod, Youssef Abuhmed, Tamer El-Sappagh, Shaker Faculty of Computer Science and Engineering Galala University Egypt College of Computing and Informatics Sungkyunkwan University Korea Republic of

ISBN: (纸本)9798331507817

Adverse drug reactions (ADRs) remain a crucial challenge in healthcare systems, highly contributing to patient mortality. We present an innovative smart pharmacy system that utilizes advanced large language models (LLMs) to enhance drug safety and pharmacy operational efficiency. Our system integrates real-time data from patient's prescriptions, medication databases, and electronic health records (EHR) to automate the detection of potential drug interactions, optimizing clinical decision-making and reducing ADR-related risks. The system's architecture is designed to easily manage prescription processing for patients, inventory management and control, and Pharmacist consultations through an intelligent chatbot interface. Key features include real-time tracking of medication expiration and inventory levels, an interaction checker API for identifying and mitigating risky drug combinations, and an LLM-powered chatbot for accurate data analysis and visualization. By combining advanced computational techniques with AI-driven insights, our smart pharmacy system not only improves medication safety but also eases pharmacy operations. This transformative approach holds the potential to significantly reduce ADR-related hospital admissions and enhance overall healthcare delivery. Our research underscores the vital role of AI and LLMs in modern pharmacy practice, offering an inclusive solution that integrates easily into existing healthcare infrastructures. The proposed smart pharmacy system can be plugged into hospital EHR systems to automatically track patient medications. © 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

RT-PPS: Real-time privacy-preserving scheme for cloud-hosted IoT data

引用

Journal of High Speed Networks 2025年第1期31卷 71-89页

作者： Elhoseny, Mohamed Riad, Khaled College of Computing and Informatics University of Sharjah Sharjah27272 United Arab Emirates Faculty of Computers and Information Mansoura University Mansoura35516 Egypt Computer Science Department College of Computer Sciences & Information Technology King Faisal University Al-Ahsa 31982 Saudi Arabia Mathematics Department Faculty of Science Zagazig University Zagazig44519 Egypt

The Internet of Things (IoT) is a rapidly growing network of devices that can communicate with each other and with cloud-based services. These devices generate vast amounts of data that can be used to provide valuable insights into user behavior, environmental conditions, and other important factors. However, as this data is collected and processed by cloud-hosted services, there is a growing concern about privacy and security. Without adequate protection, sensitive information could be exposed to hackers or other malicious actors, putting both individuals and organizations at risk. To address this challenge, real-time privacy-preserving techniques can be used to protect IoT data without compromising its value. This paper introduces an efficient Real-time privacy-preserving scheme (RT-PPS) for cloud-hosted IoT data. RT-PPS employs multi-authority attribute-based encryption on a hybrid cloud environment to keep data secure and private, while still allowing it to be processed and analyzed by cloud-hosted services. RT-PPS has efficient response time and resource consumption, which gives it the ability to handle a huge number of concurrent users at the same time without notable delay. The proposed RT-PPS has been validated through extensive experimental evaluation on a variety of configurations. Moreover, the proposed scheme has been computationally compared with the state-of-the-artwork. RT-PPS has shown excellent performance, effectiveness, and efficiency. The RT-PPS encryption time for a 1 GB dataset while considering 1024 slices is approximately 1000 ms. Also, the RT-PPS decryption time for a 1 GB ciphertext while considering 1024 slices are approximately 235 ms. Finally, RT-PPS is proven secure against any polynomial-time attacks and their variations that have at most a negligible advantage in the introduced security model. Moreover compared to most of the state-of-the-artwork, RT-PPS reduced the ciphertext size and lowered the computations in the encryption, key g

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

Toward AI-Augmented Formal Verification: A Preliminary Investigation of ENGRU and Its Challenges

引用

IEEE Access 2025年 13卷 84357-84379页

作者： Dechsupa, Chanon Panboonyuen, Teerapong Vatanawood, Wiwat Padungweang, Praisan So-In, Chakchai Khon Kaen University College of Computing Department of Computer Science Khon Kaen400002 Thailand Chulalongkorn University Faculty of Engineering Department of Computer Engineering Bangkok10300 Thailand

State-space graphs and automata serve as fundamental tools for modeling and analyzing the behavior of computational systems. Recurrent neural networks (RNNs) and language models are deeply intertwined, as RNNS provide the foundational architecture that enables language models to process sequential data, capture contextual dependencies, and improve natural language processing tasks. Both RNNs and state-space graphs help evaluate discrete-time systems within this formal framework. However, the basic question of their equivalence remains an open challenge regarding the models governing sentence structure in natural language and the formal model in automata theory. In this paper, we present ENGRU (Enhanced Gated Recurrent Units), a novel deep learning-based approach for formal verification. ENGRU integrates concepts of model checking techniques, Colored Petri Nets (CPNs), and sequential learning to analyze systems at a high level of abstraction. CPN models undergo state-space enumeration via a model-checking tool, generating a state-space graph and an automaton from inherent state transition patterns. These graphs are transformed into sequential representations as sub-paths, enabling ENGRU to learn the execution paths and predict system behaviors. ENGRU effectively predicts goal states within discrete-time models by the competency of gated recurrent mechanisms, encouraging early bug detection and allowing predictive state-space exploration. Experimental results demonstrate that ENGRU’s ability achieves high accuracy and efficiency in goal state predictions. © 2013 IEEE.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Edge computing Techniques for Advanced Video Surveillance in Autonomous Vehicles

引用

computers, Materials & Continua 2025年第4期83卷 1239-1255页

作者： Mohammad Tabrez Quasim Khair Ul Nisa Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBishaP.O.Box 551Saudi Arabia

The blockchain-based audiovisual transmission systems were built to create a distributed and flexible smart transport system(STS).This system lets customers,video creators,and service providers directly connect with each ***-based STS devices need a lot of computer power to change different video feed quality and forms into different versions and structures that meet the needs of different *** the other hand,existing blockchains can’t support live streaming because they take too long to process and don’t have enough computer *** amounts of video data being sent and analyzed put too much stress on networks for vehicles.A video surveillance method is suggested in this paper to improve the performance of the blockchain system’s data and lower the latency across the multiple access edge computing(MEC)*** integration of MEC and blockchain for video surveillance in autonomous vehicles(IMEC-BVS)framework has been *** deal with this problem,the joint optimization problem is shown using the actor-critical asynchronous advantage(ACAA)method and deep reinforcement training as a Markov Choice Progression(MCP).Simulation results show that the suggested method quickly converges and improves the performance of MEC and blockchain when used together for video surveillance in self-driving cars compared to other methods.

关键词： Blockchain multiple access edge computing video surveillance autonomous vehicles

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：