检索结果-内蒙古大学图书馆

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

作者： Hazem Al-Najjar Nadia Al-Rousan Douaa Al-Rousan Department of Computer Science College of Information Technology University of Petra Amman Jordan Department of computer engineering College of Engineering AIBalqa Applied University Salt Jordan Department of Computer Engineering Faculty of Electrical Engineering and Information Systems German Jordanian University Amman Jordan School of Civil Engineering Universiti Sains Malaysia Nibong Tebal Pulau Pinang Malaysia

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This study is concerned with the comprehensive evaluation of machine learning models intended for the detection of hallucination in Large Language Model output. The preprocessing of the prompt and answers using TF-IDF vectorization has been done as a preliminary step before developing a hallucination prediction model. Afterwards, the generated dataset was then divided into training and testing, with percentages equal to 70% and 30%, respectively. The selected machine learning models were trained with the dataset created. In this research, eight various classifiers are implemented and compared. To evaluate the results of our approach, multiple metrics were taken into consideration: accuracy, precision, recall, and Fl-score. While the training results showed exceptional performance with accuracies exceeding 99% in several models, the test results indicated huge challenges in generalization. Random Forest had the highest testing accuracy of 94.77% at 65% precision but with a very low recall of 4.85%. Besides, cross validation is used with random forest and decision tree, the results showed that the cross-validation is better than the test and train splitting model. The study shows the significant trade-offs between precision and recall in hallucination detection, which is especially problematic while working with imbalanced datasets.

关键词： Training Measurement Accuracy Large language models Computational modeling Predictive models Decision trees Random forests Computational intelligence Testing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Patient Privacy and Data Security in Remote Healthcare Monitoring Using IoT and Wearable Technologies

Enhancing Patient Privacy and Data Security in Remote Health...

引用

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Singh, Navdeep Swetha, K. Al-Rubaye, Taqi Bahar, Tarannum Rajalakshmi, B. Anuradha, Kodali Lovely Professional University Phagwara India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India College of Medical Technologies The Islamic University Department of Medical Laboratory Technology Najaf Iraq Galgotias university Department of Electrical Electronics & Communication Engineering Uttar Pradesh Gerater Noida203201 India New Horizon College of Engineering Department of Computer Science Engineering Bangalore India Griet Department of Information Technology Bachupally Telangana Hyderabad India

ISBN: (纸本)9798331527495

'Enhancing Patient Privacy and Data Security in Remote Healthcare Monitoring Using IoT and Wearable Technologies' is a new approach to healthcare IT's major privacy and data security issues. Security must be updated as wearable gadgets and the Internet of Things (IoT) becomes increasingly widespread in remote healthcare tracking. Many people worry about online patient data security;thus, this study develops a thorough security solution that fits with current healthcare IT systems. A full security architecture with cutting-edge encryption techniques, real-time data transmission protocols, and flexible privacy safeguards is used. The recommended solution outperforms current security methods. A stronger 256-bit key protects patient data at a higher security level. Getting connection latency down to 20 ms speeds up remote healthcare systems. The proposed technique is resilient enough to withstand hostile attacks while maintaining healthcare services. The approach also allows real-world data analysis while preserving patients' identities 92% of the time. The strategy may be employed in complex healthcare IT since it balances data security and research. Overall, this study's findings are promising for safe medical technologies. The recommended method's superior encryption, quicker transmission, and reliable system have raised telehealth tracking privacy requirements. In healthcare IT, wearable technology and the Internet of Things are connecting swiftly. Better security procedures that prioritize patient privacy and data protection are outlined in this study. © 2025 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Educational data mining: a 10-year review

引用

Discover Computing 2025年第1期28卷 1-25页

作者： Kalita, Emi Oyelere, Solomon Sunday Gaftandzhieva, Silvia Rajesh, Kandala N. V. P. S. Jagatheesaperumal, Senthil Kumar Mohamed, Asmaa Elbarawy, Yomna M. Desuky, Abeer S. Hussain, Sadiq Cifci, Mehmet Akif Theodorou, Paraskevi Hilčenko, Slavoljub Hazarika, Jiten Ali, Tazid Centre for Computer Science and Applications Dibrugarh University Dibrugarh 786004 India Department of Computer Science Electrical and Space Engineering Luleå University of Technology Skellefteå 931 87 Sweden Department of Computer Science Faculty of Environment Science and Economy University of Exeter Exeter United Kingdom Research Group On Data Artificial Intelligence and Innovations for Digital Transformation Johannesburg Business School (JBS) University of Johannesburg Johannesburg South Africa Faculty of Mathematics and Informatics University of Plovdiv “Paisii Hilendarski” Plovdiv Bulgaria School of Electronics Engineering VIT-AP University Vijayawada India Department of Electronics & Communication Engineering Mepco Schlenk Engineering College Sivakasi 626005 India Department of Mathematics Faculty of Science Al-Azhar University (Girls Branch) Cairo 11754 Egypt Department of Computer Engineering Bandirma Onyedi Eylul University Balikesir 10200 Turkey Engineering and Informatics Department Klaipėdos Valstybinė Kolegija/Higher Education Institution Klaipeda 92294 Lithuania Department of Digital Systems University of Piraeus Piraeus Greece College for Vocational Education of Preschool Teachers and Coaches Subotica Serbia Department of Statistics Dibrugarh University Dibrugarh 786004 India

This systematic review comprehensively examines the application and impacts of Educational Data Mining (EDM) over the past decade. It explores the use of various data mining tools and techniques, statistics, and machine learning algorithms in education. The review discusses how EDM helps understand and improve the learning experience, educational strategies, and institutional efficiency. It highlights the iterative process of EDM, its applications, and the benefits it offers to different stakeholders, including students, teachers, and educational institutions. The paper also discusses the challenges related to data ethics, privacy, and security in EDM. Key sections include a methodology for conducting the systematic review, exploring different data mining techniques and learning styles, and using Artificial Intelligence in EDM. The review concludes with a discussion of findings, future research directions, and a summary of the study’s contributions and limitations. © The Author(s) 2025.

关键词： Artificial intelligence in education Education data mining Explainability in education Multimodal learning analytics

来源：评论

学校读者我要写书评

暂无评论

Bounds on Box Codes

arXiv

引用

arXiv 2025年

作者： Langberg, Michael Schwartz, Moshe Tamo, Itzhak Department of Electrical Engineering University at Buffalo BuffaloNY14260 United States Department of Electrical and Computer Engineering McMaster University HamiltonONL8S 4K1 Canada School of Electrical and Computer Engineering Ben-Gurion University of the Negev Beer Sheva8410501 Israel Department of Electrical Engineering–Systems Tel Aviv University Tel Aviv6997801 Israel

Let nq(M, d) be the minimum length of a q-ary code of size M and minimum distance d. Bounding nq(M, d) is a fundamental problem that lies at the heart of coding theory. This work considers a generalization n‚q(M, d) of nq(M, d) corresponding to codes in which codewords have protected and unprotected entries;where (analogs of) distance and of length are measured with respect to protected entries only. Such codes, here referred to as box codes, have seen prior studies in the context of bipartite graph covering. Upper and lower bounds on n‚q(M, d) are presented. Copyright © 2025, The Authors. All rights reserved.

关键词： Programming theory

来源：评论

学校读者我要写书评

暂无评论

Sub-Module Capacitor Voltage Estimator for Modular Multilevel Converters Without Internal Measurements

引用

IEEE Transactions on Power Electronics 2025年

作者： Sanchez-Squella, Antonio Jimenez, Cristian Morales, Felipe Burgos, Rolando Federico Santa María University Department of Electrical Engineering Santiago8940897 Chile Virginia Tech Center of Power Electronics and Systems Bradley Department of Electrical and Computer Engineering BlacksburgVA24061 United States

In this article, a modular multilevel converter (MMC) sub-module (SM) capacitor voltage estimator which determine the state of the capacitors measuring the bus voltage, output voltage and current, is proven via simulation and experimentation. The estimator deals with the complete elimination of sensors for internal converter states in a MMC. This is achieved through a state observer based on an Extended Kalman Filter. Additionally, a dead-time compensator is included, which is not dimensioned within the state observer using converter equations. The steady-state behavior of the observer during startup with zero initial conditions and the dynamic behavior during a reference change are evaluated via experimentation, both cases are studied in open-loop configuration. To prove performance for various operating points, results are obtained for different modulation indexes. © 1986-2012 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Channel Knowledge Map for Cellular-Connected UAV via Binary Bayesian Filtering

引用

IEEE Transactions on Communications 2025年

作者： Yang, Yuhang Xu, Xiaoli Zeng, Yong Sun, Haijian Hu, Rose Qingyang Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Purple Mountain Laboratories Nanjing211111 China University of Georgia School of Electrical and Computer Engineering AthensGA United States Utah State University Department of Electrical and Computer Engineering LoganUT United States

Channel knowledge map (CKM) is a promising technology to enable environment-aware wireless communications and sensing. Link state map (LSM) is one particular type of CKM that aims to learn the location-specific line-of-sight (LoS) link probability between the transmitter and the receiver at all possible locations, which provides the prior information to enhance the communication quality of dynamic networks. This paper investigates the LSM construction for cellular-connected unmanned aerial vehicles (UAVs) by utilizing both the expert empirical mathematical model and the measurement data. Specifically, we first model the LSM as a binary spatial random field and its initial distribution is obtained by the empirical model. Then we propose an effective binary Bayesian filter to sequentially update the LSM by using the channel measurement. To efficiently update the LSM, we establish the spatial correlation models of LoS probability on the location pairs in both the distance and angular domains, which are adopted in the Bayesian filter for updating the probabilities at locations without measurements. Simulation results demonstrate the effectiveness of the proposed algorithm for LSM construction, which significantly outperforms the benchmark scheme, especially when the measurements are sparse. © 1972-2012 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Analysis of Channel Uncertainty in Trusted Wireless Services via Repeated Interactions

引用

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 2248-2265页

作者： Chen, Bingwen Ling, Xintong Cao, Weihang Wang, Jiaheng Ding, Zhi Southeast University National Mobile Communications Research Laboratory Nanjing211189 China Purple Mountain Laboratories Nanjing210023 China University of Maryland Department of Electrical and Computer Engineering College ParkMD20742 United States University of California at Davis Department of Electrical and Computer Engineering DavisCA95616 United States

The coexistence of heterogeneous sub-networks in 6G poses new security and trust concerns and thus calls for a perimeterless-security model. Blockchain radio access network (B-RAN) provides a trust-building approach via repeated interactions rather than relying on pre-established trust or central authentication. Such a trust-building process naturally supports dynamic trusted services across various service providers (SP) without the need for perimeter-based authentications;however, it remains vulnerable to environmental and system unreliability such as wireless channel uncertainty. In this study, we investigate channel unreliability in the trust-building framework based on repeated interactions for secure wireless services. We derive specific requirements for achieving cooperation between SPs and clients via a repeated game model and illustrate the implications of channel unreliability on sustaining trusted wireless services. We consider the framework design and optimization to guarantee SP-client cooperation, given the worst channel condition and/or the least cooperation willingness. Furthermore, we explore the maximum cooperation area to enhance service resilience and reveal the trade-off relationship between transmission efficiency, security integrity, and cooperative margin. Finally, we present simulations to demonstrate the system performance over fading channels and verify our results. © 1983-2012 IEEE.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

Enhanced Breast Cancer Molecular Biomarker Classification: A Novel Two-Stage Machine Learning Pipeline for Accurate Histological Analysis of Whole Slide Images

Enhanced Breast Cancer Molecular Biomarker Classification: A...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Aboudessouki, A. Ali, Kh.M. Alksas, A. Elsharkawy, M. Rahma, M. Abo Ghazal, M. Mekky, N. El-Daydamony, E. Gondim, D. El-Baz, A. BioImaging Laboratory Bioengineering Department University of Louisville United States Pathology Department Faculty of Medicine Mansoura University Egypt Mansoura University Hospital Mansoura University Egypt Electrical Computer and Biomedical Engineering Department Abu Dhabi University United Arab Emirates Department of Information Technology Faculty of Computers and Information Mansoura University Egypt Department of Pathology and Laboratory Medicine University of Louisville LouisvilleKY United States

ISBN: (纸本)9798350368741

Breast cancer, a prevalent and diverse form of cancer, is characterized by unique clinicopathologic features. Accurate classification of its molecular subtype, essential for targeted treatment and improved survival rates, relies on testing molecular biomarkers such as estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and Ki67 antigen. This study introduces an innovative two-stage machine learning pipeline for breast cancer PR molecular biomarker classification using whole slide immunohistochemistry images. Our approach consists of two specialized stages. In the first stage, a watershed algorithm segments the Cells from the input image. Morphological and statistical features extracted from these segments are then used by machine learning classifiers to distinguish between tumor and nontumor tissues [1]-[3]. The second stage focuses on the tumor tissues that were identified in the first stage, extracting texture and appearance features to classify them into positive or negative biomarker responses, again using machine learning classifiers [4], [5]. This method not only automates the classification of PR biomarkers in tumor regions but also generates a detailed image map for each cell in the Whole Slide Image (WSI). By doing so, it can determine whether the tissue represents tumor cells and whether the tumor tissue exhibits positive or negative PR status. The results show the ability of our machine learning-based approach to augment pathologists' diagnostic capabilities, offering significant advancements in the automated classification of histopathological images. © 2025 IEEE.

关键词： Breast cancer Histopathology Immunohistochemistry Machine Learning Marker-based Watershed Segmentation Molecular biomarker Status Molecular biomarkers Tissue classification Tumor Detection Watershed Segmentation

来源：评论

学校读者我要写书评

暂无评论

Safe Multi-Robotic Arm Interaction via 3D Convex Shapes

arXiv

引用

arXiv 2025年

作者： Kaypak, Ali Umut Wei, Shiqing Krishnamurthy, Prashanth Khorrami, Farshad Control/Robotics Research Laboratory Electrical and Computer Engineering Department Tandon School of Engineering New York University BrooklynNY11201 United States

Inter-robot collisions pose a significant safety risk when multiple robotic arms operate in close proximity. We present an online collision avoidance methodology leveraging 3D convex shape-based High-Order Control Barrier Functions (HOCBFs) to address this issue. While prior works focused on using Control Barrier Functions (CBFs) for human–robotic arm and single-arm collision avoidance, we explore the problem of collision avoidance between multiple robotic arms operating in a shared space. In our methodology, we utilize the proposed HOCBFs as centralized and decentralized safety filters. These safety filters are compatible with any nominal controller and ensure safety without significantly restricting the robots’ workspace. A key challenge in implementing these filters is the computational overhead caused by the large number of safety constraints and the computation of a Hessian matrix per constraint. We address this challenge by employing numerical differentiation methods to approximate computationally intensive terms. The effectiveness of our method is demonstrated through extensive simulation studies and real-world experiments with Franka Research 3 robotic arms. © 2025, CC BY.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

IMPACT: an interactive multi-disease prevention and counterfactual treatment system using explainable AI and a multimodal LLM

引用

PeerJ computer Science 2025年 11卷

作者： Mohanty, Prasant Kumar Francis, Sharmila Anand John Barik, Rabindra Kumar Reddy, K. Hemant Kumar Roy, Diptendu Sinha Saikia, Manob Jyoti Department of Computer Science and Engineering National Institute of Technology Meghalaya Shillong India Department of Computer Science Rijal Alma’a King Khalid University Abha Saudi Arabia School of Computer Applications KIIT Deemed to be University Odisha Bhubaneswar India Department of Computer Science and Engineering VIT-AP University Beside AP Secretariat Amaravati Andhra Pradesh India Biomedical Sensors & Systems Lab The University of Memphis MemphisTN United States Electrical and Computer Engineering Department The University of Memphis MemphisTN United States

Multi-disease conditions strain the body’s defenses, complicating recovery and increasing mortality risk. Therefore, effective concurrent prevention of multiple diseases is essential for mitigating complications and improving overall well-being. Explainable artificial intelligence (XAI) with an advanced multimodal large language model (LLM) can create an interactive system enabling the general public to engage in natural language without any specialized knowledge prerequisites. Counterfactual explanation, an XAI method, offers valuable insights by suggesting adjustments to patient features to minimize disease risks. However, addressing multiple diseases simultaneously poses challenging barriers. This article proposes an interactive multi-disease prevention system that uses Google Gemini Pro, a multimodal LLM, and a non-dominated sorting genetic algorithm, namely NSGA-II, to overcome such problems. This system recommends changes in feature values to concurrently minimize the risk of diseases such as heart attacks and diabetes. The system facilitates personalized feature value selection, significantly reducing disease attack probabilities to as low as possible. Such an approach holds the potential to simultaneously address the unresolved issue of preventing and managing multiple diseases for the general public. © 2025 Mohanty et al.

关键词： Diseases

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：