检索结果-内蒙古大学图书馆

Foveated Animations for Efficient Crowd Simulation

Proceedings of the ACM on computer Graphics and Interactive Techniques 2025年第1期8卷 1-14页

作者： Florin-Vladimir Stancu Tomer Weiss Rafael Kuffner dos Anjos School of Computer Science University of Leeds Leeds West Yorkshire United Kingdom Informatics New Jersey Institute of Technology Newark NJ USA

Foveated rendering techniques have seen recent development with the advent of commercial head-mounted displays with eye-tracking capabilities. The main drive is to exploit particular features of our peripheral vision that allow optimizing rendering pipelines, which allows using less computational effort where the human visual system may be unaware of differences. Most efforts have been focused on simplifying spatial visual detail on areas not being focused on by adjusting acuity of shading models, sharpness of images, and pixel density. However, other perception pipeline areas are also influential, particularly in certain purpose-specific applications. In this paper, we demonstrate it is possible to reduce animation rates in crowd simulations up to a complete stop for agents in our peripheral vision without users noticing the effect. We implemented a prototype Unity3D application with typical crowd simulation scenarios and carried out user experiments to study subjects’ perception to changes in animation rates. We find that in the best case we were able to reduce the number of operations by 99.3% compared to an unfoveated scenario, with opportunities for developments combined with other acceleration techniques. This paper also includes an in-depth discussion about human perception of movement in peripheral vision with novel ideas that will have applications beyond crowd simulation.

关键词： Perception Animation Foveated techniques Virtual Reality

来源：评论

学校读者我要写书评

暂无评论

Testbeds and Evaluation Frameworks for Anomaly Detection within Built Environments: A Systematic Review

引用

ACM Computing Surveys 2025年第9期57卷 1-36页

作者： Mohammed Alosaimi Omer Rana Charith Perera Computer Science and Informatics Cardiff University Cardiff United Kingdom of Great Britain and Northern Ireland and Computer Science and Information Technology King Abdulaziz University Jeddah Saudi Arabia School of Computer Science & Informatics Cardiff University Cardiff United Kingdom of Great Britain and Northern Ireland Cardiff University Cardiff United Kingdom of Great Britain and Northern Ireland

The Internet of Things (IoT) has revolutionized built environments by enabling seamless data exchange among devices such as sensors, actuators, and computers. However, IoT devices often lack robust security mechanisms, making them vulnerable to cyberattacks, privacy breaches, and operational anomalies caused by environmental factors or device faults. While anomaly detection techniques are critical for securing IoT systems, the role of testbeds in evaluating these techniques has been largely overlooked. This systematic review addresses this gap by treating testbeds as first-class entities essential for the standardized evaluation and validation of anomaly detection methods in built environments. We analyze testbed characteristics, including infrastructure configurations, device selection, user-interaction models, and methods for anomaly generation. We also examine evaluation frameworks, highlighting key metrics and integrating emerging technologies such as edge computing and 5G networks into testbed design. By providing a structured and comprehensive approach to testbed development and evaluation, this paper offers valuable guidance to researchers and practitioners in enhancing the reliability and effectiveness of anomaly detection systems. Our findings contribute to the development of more secure, adaptable, and scalable IoT systems, ultimately improving the security, resilience, and efficiency of built environments.

关键词： Smart home datasets evaluation metric network feature smart building

来源：评论

学校读者我要写书评

暂无评论

Teens Online Behavior and Support Interventions in Bangladesh

引用

ACM Journal on Computing and Sustainable Societies 2025年第1期3卷 1-22页

作者： Rahat Jahangir Rony Nova Ahmed School of Computer Science and Informatics Cardiff University Cardiff United Kingdom of Great Britain and Northern Ireland North South University Dhaka Bangladesh

Teens are vulnerable online, and their risk behaviors and possible support for safe online space are studied in the Western context but unexplored in developing countries. Considering the cultural context and research gaps, we interviewed n = 28 teens in urban Bangladesh to investigate their unique online activities, experiences, and strategies for protecting online accounts and knowledge. They are involved in several risk-taking behaviors, including communicating with strangers without being aware of possible vulnerabilities, uncovering their lack of online safety knowledge, and being unaware of online journeys from the beginning. These teens have negative online experiences; some coping techniques, such as hiding information, changing profile settings, and unfollowing the unknowns, help them without seeking additional support. We propose design interventions regarding knowledge and awareness increment, implementing co-learning and policy, which will help teens become aware and knowledgeable at the beginning of their online usage, reducing their negative experiences in the future.

关键词： Teens Online Behavior Online Vulnerabilities Risky Behaviors Teens in Bangladesh Design Interventions for Teens Developing Country Context

来源：评论

学校读者我要写书评

暂无评论

Explainable Hybrid Model for Presaging Tumor Stage Classification with Survival Survey

引用

SN computer science 2025年第4期6卷 1-24页

作者： Manna, Sweta Mistry, Sujoy Zhao, Zhongming Dahal, Keshav Department of Computer Science and Engineering Maulana Abul Kalam Azad University of Technology Nadia W.B Kolkata 741249 India Center for Precision Health School of Biomedical Informatics The University of Texas Health Science Center at Houston Houston TX United States School of Engineering and Computing University of the West of Scotland Paisley PA1 2BE United Kingdom

Tumor stage classification with a survival survey during detection time is the most crucial part of cancer treatment. The survivability period is directly associated with the early detection of the stage. This study developed a hybrid model to accurately classify the tumor (T) stages with the survivability analysis. The study aims to provide an explainable Artificial Intelligence framework (such as SHAP, and SHAPASH), through which the trustability and interpretability of the proposed model can increase. Along with the XAI, this hybrid approach uses two statistical models, ANOVA and LASSO with the standard TNM (tumor, node, metastasis) method for the T-stage classification. Afterward, the survivability analysis for each T stage is shown by the Kaplan–Meier (KM) method, proportion hazard ratio (Cox). Where KM is used to represent the survivability of individual tumor stages in months and the Cox regression shows the risk factors of the events. Initially, the proposed model was examined on a full dataset that contained malignant and benign data for evaluating the performance of the model, therefore stage classification for T1, T2, and T3 performs for malignant data. The K-fold and repeated-stratified K-fold cross-validation are used to measure the accuracy of the whole dataset for lung and breast cancer. For lung cancer, maximum accuracy was attained by MLP–97.64 in K-fold cross-validation. In breast cancer maximum accuracy achieved by GPC-99.57 in repeated-stratified K-fold cross validation. The results of both datasets are compared with the state-of-the-art models. The study contributed by representing the significance of individual features for tumor staging using the advanced approach of XAI, the SHAPASH interface. The accuracy of the T1, T2, and T3 stages based on malignant data was demonstrated with various classifier models with cross-validation. Finally, it is expected that executing that approach will improve patient outcomes. By using, advanced artificial in

关键词： ANOVA Breast cancer Deep learning Explainable artificial intelligence F-score Gaussian process classification LASSO Lung cancer Machine learning Random-Forest Shapely additive explanation XGBoost

来源：评论

学校读者我要写书评

暂无评论

Fetal Health Risk Classification Using Important Feature Selection and Cart Model on Cardiotocography Data

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第1期49卷 193-206页

作者： Ilham, Ahmad Nagara, Thahta Ardhika Prabu Kamaruddin, Mudyawati Khikmah, Laelatul Mantoro, Teddy Department of Informatics Universitas Muhammadiyah Semarang Semarang Indonesia Intelligent Data Science Research Group Universitas Muhammadiyah Semarang Semarang Indonesia Postgraduate Program of Medical Laboratory Science Universitas Muhammadiyah Semarang Semarang Indonesia Interdisciplinary Research Laboratory for Experimental Plasma Medicine Universitas Muhammadiyah Semarang Semarang Indonesia Department of Statistics Institut Teknologi Statistika dan Bisnis Muhammadiyah Semarang Semarang Indonesia School of Computer Science Nusa Putra University West Java Indonesia

Fetal mortality and newborn health issues require urgent attention because of high maternal and infant mortality rates during labor, highlighting the critical need for accurate fetal condition monitoring to reduce complications. This study proposes the development of a fetal health risk classification model based on Important Feature Selection (IFS) and a Classification and Regression Tree (CART) using cardiotocography (CTG) data from the UCI Machine Learning Repository. The IFS method was used to select the most relevant features, reduce model complexity, and increase generalization to prevent overfitting. The IFS-CART model was tested with 10-fold cross-validation and showed an accuracy of 94.50%, superior to the conventional CART, which only reached 93.83%. In addition, the average values of the True Positive Rate (TPR) and True Negative Rate (TNR) also increased, indicating that this model is effective in distinguishing normal, suspected, and pathological fetal conditions. Evaluation using the area under the curve receiver operating characteristic (AUC-ROC) showed that the model had high performance in detecting at-risk conditions, with an AUC of 0.981 for the"suspect" class. This finding confirmed that IFS-CART is not only accurate but also has high interpretability, making it easy for medical personnel to use for clinical decision support. The results of this study show that IFS-CART can serve as a reliable decision support system for real-time fetal health monitoring. Further implementation is expected to improve diagnostic accuracy and prevent complications during pregnancy and labor © 2025 Slovene Society Informatika. All rights reserved.

关键词： Fetal monitoring

来源：评论

学校读者我要写书评

暂无评论

Joint Content Caching and Request Routing for User-Centric Many-Objective Metaverse Services

引用

IEEE Transactions on Network science and Engineering 2025年第3期12卷 1911-1925页

作者： Hu, Zhaoming Fang, Chao Wang, Zhuwei Chen, Jining Tseng, Shu-Ming Dong, Mianxiong Beijing University of Technology College of Computer Science Beijing100021 China Beijing University of Technology School of Information Science and Technology Beijing100021 China Guangxi Information Center Guangxi Key Laboratory of Digital Infrastructure Nanning530000 China National Taipei University of Technology Department of Electronic Engineering Taipei106 Taiwan Muroran Institute of Technology Department of Sciences and Informatics Muroran050-0071 Japan

Metaverse, as a revolutionary technology that changes the way of human interaction, brings new challenges to content delivery services due to the extensive data transmission and personalized service requirements. To ensure a personalized user experiences while improving the utilization of heterogeneous network resources, a user-centric many-objective metaverse content delivery framework is proposed to optimize content delivery through user attention awareness. This framework addresses two key subproblems in metaverse content delivery by investigating user-centric many-objective cooperative content caching and deep reinforcement learning (DRL)-based request routing. The user-centric many-objective cooperative content caching is proposed to dynamically combine three basic preference prediction results to predict user preferences and control network resource allocation, which can simultaneously optimize prediction precision, delay, offloaded traffic, and load balancing. In DRL-based request routing, the reward function is designed to enable the optimization of multiple objectives. The multi-objective DRL routing algorithm is employed to continuously observe network states and make adaptive routing decisions in response to user requests. In the simulation, a movie dataset is employed to simulate user requests and support user attention awareness. The results show that the proposed content delivery framework outperforms existing basic prediction algorithms and other content delivery algorithms on four evaluation indicators. © 2013 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Detection of Yoga Poses Using CNN and LSTM Models 3rd

Detection of Yoga Poses Using CNN and LSTM Models

引用

3rd International Conference on Computing, Communication and Learning, CoCoLe 2024

作者： Rukmini, Bheemanapalli Sushmini, Chaganti Sai Biswal, Saubhagya Ranjan Computer Science Engineering School of Computing and Informatics Vignan’s Foundation for Science Technology and Research Andhra Pradesh Guntur India

ISBN: (纸本)9783031790409

Yoga is a holistic practice that encompasses physical, mental, and spiritual well-being. Central to yoga are its postures, or "asanas," which are designed to promote flexibility, strength, and balance in the body. Each yoga posture holds its own significance, targeting specific muscle groups and energy centers. Proper alignment in these postures is crucial not only for reaping physical benefits but also for cultivating mindfulness and concentration. In this work, we presented an approach to detect the yoga poses using CNN and LSTM methods. For each model, the data loading process involves reading images, resizing them, and organizing them into appropriate formats for training and testing. The CNN model comprises several convolutional and pooling layers, while the LSTM model includes LSTM layers for temporal sequence processing. The combined CNN-LSTM model emerged as a robust solution, leveraging the strengths of both architectures to achieve a comprehensive understanding of yoga poses. Its performance was evaluated on a test dataset, revealing insights into its accuracy and loss metrics. Notably, the CNN model exhibited an accuracy of 85.53%, surpassing other models studied in the research. This highlights the efficacy of the CNN approach in recognizing spatial features inherent in yoga postures, contributing significantly to the overall success of the model in identifying and categorizing yoga stances from input images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Digitization of Medical Data: LLM-Based Data Entry, Cleansing, and Visualization Solutions

Digitization of Medical Data: LLM-Based Data Entry, Cleansin...

引用

Learning and Technology Conference (L&T)

作者： Mahmoud Amgad Bahaa Shamoon Hagar Mekhemar Rodeen Mostafa Toqa Tamer Habiba Mohamed Sahar Fawzi Center for Informatics Science (CIS) School of Information Technology and Computer Science Nile University Sheikh Zayed City Giza Egypt

ISBN: (数字)9798331532215

ISBN: (纸本)9798331532222

Healthcare data management faces several challenges, including errors from manual data entry, variations in data quality, and an increasing need for advanced tools to efficiently handle large datasets. This paper introduces Data-Care, an innovative application designed to automate medical record digitization by leveraging advanced technologies such as Large Language Models (LLMs), Optical Character Recognition (OCR), and NoSQL databases. Together, these technologies significantly reduce the need for manual input, minimizing errors and enhancing data accuracy. A key feature of Data-Care is its data cleansing module, which resolves issues like data inconsistencies and missing values, ensuring the integrity and accuracy of the dataset. Additionally, the application provides a powerful offline visualization tool, enabling healthcare professionals to generate comprehensive reports that support informed decision-making and streamline workflows across various healthcare processes. Extensive performance tests demonstrated that the integration of LLMs and OCR in Data-Care achieved accuracy rates between 76% and 93%, depending on the quality of the input data. These results underscore Data-Care's capacity to improve both the speed and accuracy of data entry, offering a robust solution for the digitization and management of healthcare data.

关键词： Accuracy Data integrity NoSQL databases Large language models Optical character recognition Decision making Data visualization Medical services Manuals Usability

来源：评论

学校读者我要写书评

暂无评论

Recent Trends and Challenges in Assistive Applications for Sinhala-Speaking Adults with Dyslexia: A Decade in Review

Recent Trends and Challenges in Assistive Applications for S...

引用

Advanced Research in Computing (ICARC), International Conference on

作者： Peshala Perera Deshan Sumanathilaka School of Computing Informatics Institute of Technology Colombo Sri Lanka School of Mathematics and Computer Science Swansea University United Kingdom

ISBN: (数字)9798331530983

ISBN: (纸本)9798331530990

This paper discusses assistive technologies developed for Sinhala-speaking dyslexics, focusing on the challenges they face and how existing tools attempt to address them. Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, this review analyzed research publications from 2015 to 2024, highlighting topics such as phonetic processing, text normalization, and error detection. Of the 85 initially reviewed, 32 were included in the meta-analysis to represent major challenges posed by the lack of annotated datasets and Natural Language Processing (NLP) resources tailored to the cognitive and linguistic needs of the adult patient population. This review points out the need for the extension of low-resource language toolkits and proper integration of assistive NLP applications. The study concludes that while significant progress has been made, a collaborative, interdisciplinary approach is crucial to improving literacy, independence, and social participation for Sinhala-speaking adults with dyslexia.

关键词： Training Adaptation models Collaboration Phonetics Assistive technologies Dyslexia Natural language processing Complexity theory Text to speech Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Boss is aWare—Are you? Employee Comprehension and Legal Awareness of Workplace Monitoring 25

Boss is aWare—Are you? Employee Comprehension and Legal Awa...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Teshan S. Bunwaree Katarzyna Stawarz Philippa Collins Sandy J. J. Gould School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Law School University of Bristol Bristol United Kingdom

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：