检索结果-内蒙古大学图书馆

Device Intelligence, Computing and Communication Technologies, (DICCT), International Conference on

作者： SM Faizanut Tauhid Safdar Tanweer Md. Tabrez Nafis Mohd Abdul Ahad Syed Mohd Faisal Malik Syed Sibtain Khalid Department of Computer Science and Engineering Jamia Hamdard Delhi India

ISBN: (数字)9798331543358

ISBN: (纸本)9798331543365

Heart disease is a leading global health challenge, emphasizing the need for effective diagnostic solutions. This study evaluated the accuracy of machine learning algorithms in heart disease diagnosis with the aim of finding the most reliable method. The algorithms examined contain Random Forest, Support Vector Classifier, Gradient Boosting, AdaBoost, Optimized Logistic Regression, SVM, Naive Bayes, K-Nearest Neighbors (KNN), Decision Trees, and SGD Classifier. Among them, optimized logistic regression and naive Bayes have the highest accuracy of up to 88.52%, demonstrating their predictive capabilities. The result of this work is optimized logistic regression and naive Bayes are capable of early detection of cardiovascular disease. Offering major perspective for integration into clinical practice. Future work will explore the refinement and real-world application of these models to further improve healthcare outcomes.

关键词： Heart Support vector machines Logistic regression Accuracy Machine learning algorithms Translation Nearest neighbor methods Vectors Bayes methods Random forests

来源：评论

学校读者我要写书评

暂无评论

Integrating humanoid robots with human musicians for synchronized musical performances

引用

PeerJ computer science 2025年 11卷 e2632-e2632页

作者： Lau, MengCheng Anderson, John Baltes, Jacky Bharti School of Engineering and Computer Science Laurentian University SudburyON Canada Department of Computer Science University of Manitoba WinnipegMB Canada Department of Electrical Engineering National Taiwan Normal University Taipei Taiwan

Entertainment robotics has garnered significant attention in recent years, with researchers focusing on developing robots capable of performing a variety of tasks, including magic, drawing, dancing, and music. This article presents our research on forming a musical band that includes both humanoid robots and human musicians, with the goal of achieving natural synchronization and collaboration during musical performances. We utilized two of our humanoid robots for this project: Polaris, a mid-sized humanoid robot, as the drummer, and Oscar, a Robotis-OP3 humanoid robot, as the keyboardist. The technical implementation incorporated essential components such as visual servoing, human-robot interaction, and Robot Operating System (ROS), enabling seamless communication and coordination between the humanoid robots and the human musicians. The success of this collaborative effort can be both seen and heard through the following YouTube link: https://***/pFOyt1KKCfY?feature=shared. Copyright 2025 Lau et al.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Application of adaptive guard channel reservation under hard handoff constraint in wireless cellular network

引用

International Journal of Wireless and Mobile Computing 2025年第2期28卷 170-185页

作者： Sahu, Promod Kumar Pati, Hemanta Kumar Pradha, Sateesh Kumar Department of Computer Science and Application Utkal University Vani Vihar Odisha Bhubaneswar India Department of Computer Science and Engineering International Institute of Information Technology Bhubaneswar Odisha Bhubaneswar India

Voice is the king of communication in wireless cellular network (WCN). Again, WCNs provide two types of calls, i.e., new call (NC) and handoff call (HC). Generally, HCs have higher priority than NCs because call dropping gives negative impact to users as compared to call blocking. So, to handle this problem some channels are reserved for HCs. If more channels are reserved for HCs, then handoff call dropping probability (HCDP) decreases at the same time as new call blocking probability (NCBP) increases;if fewer channels are reserved for HCs, HCDP increases and NCBP decreases. If channels are reserved for HCs by considering target HCDP then HCDP will be below the target and NCBP will be minimum for that target. So, keeping this in mind in this paper, we propose a mathematical model that estimates optimal number of guard channels (GCs) for HCs by considering target HCDP and keeping NCBP minimum. The mathematical model proposed assume static traffic parameters. However, in reality, the user traffic is dynamic and usually inherited through its testbed implementation. To obtain optimal performance we propose an adaptive GC reservation scheme by considering hard handoff constraint while implementing this model through testbed. Finally, we have verified testbed results with those of the model-based approach applying the parameters of different Global System for Mobile Communication (GSM) standards to evaluate its applicability to real systems. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

Intelligent Motion Control to Enhance the Swimming Performance of a Biomimetic Underwater Vehicle Using Reinforcement Learning Approach

引用

IEEE Access 2025年 13卷 37128-37146页

作者： Algarin-Pinto, Juan A. Garza-Castanon, Luis E. Vargas-Martinez, Adriana Minchala-Avila, Luis I. Payeur, Pierre Tecnológico de Monterrey School of Engineering and Sciences Nuevo Leon Monterrey64849 Mexico Universidad de Cuenca Department of Electrical Engineering Electronics and Telecommunications Azuay Cuenca010101 Ecuador University of Ottawa School of Electrical Engineering and Computer Science OttawaK1N 6N5 Canada

This article develops an intelligent motion control strategy using reinforcement learning to regulate a biomimetic autonomous underwater vehicle (BAUV) swimming performance. The BAUV is driven by the oscillatory motion of a lunate-shaped caudal fin. To navigate effectively, the vehicle must regulate its propeller’s motion to swim toward goals. The caudal fin’s oscillatory motion is defined by sine functions, where the amplitude, frequency, bias, and time shifting are the main flapping parameters that must be regulated. The developed algorithm, based on the n-step state-action-reward-state-action on-policy learning, fine-tunes these parameters. Further, deep Q learning network speed adjusters were designed to enhance BAUV guidance. By integrating waypoint guidance systems and intelligent path trackers, the vehicle reduces its heading deviation and distance to goals. The effectiveness of these methods was validated through simulations featuring various disturbances like longitudinal, lateral, and swirl currents. The proposed scheme allowed the vehicle to reach desired targets efficiently, even in the presence of strong currents. © 2025 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://***/licenses/by/4.0/

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Leakage Thresholds and Security Trade-offs in Finite Blocklength Wiretap Channels

Leakage Thresholds and Security Trade-offs in Finite Blockle...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Shabnam Sodagari Department of Computer Engineering Computer Science California State University Long Beach CA USA

ISBN: (数字)9798331520960

ISBN: (纸本)9798331520977

This work discusses the bounds for the wiretap channel (WTC) in the finite blocklength regime, characterizing the behavior of the performance trade-off between information delivery to the legitimate receiver and information leakage to the eavesdropper as a function of blocklength. Since the error probability at the legitimate receiver is the same as that of a conventional point-to-point channel, the characterization of the former builds on the finite blocklength analysis for that case. The information leakage bound relies on the analysis of the corresponding leakage density. This paper extends these concepts by incorporating the use of the Berry-Esseen theorem in assessing the convergence rates of leakage and secrecy metrics to their asymptotic values, which provides a refined analytical tool to evaluate the performance of secrecy systems under finite blocklength constraints. Furthermore, this approach facilitates a quantification of the trade-offs involved, integrating concepts such as the aggregate leakage rate and empirical average leakage, thus enabling a more comprehensive understanding of how system parameters affect the overall secrecy performance. This allows for a more detailed exploration of the dependencies between blocklength, secrecy, and reliability trade-offs required to balance effective communication against security imperatives. These analyses also highlight the critical balance necessary between ensuring low probability of error for the legitimate receiver while maintaining stringent secrecy requirements against an eavesdropper. Furthermore, the study introduces metrics such as aggregate leakage rate and empirical average leakage, providing new insights into how these factors interplay to influence the overall performance of secure communication systems.

关键词： Wireless networks Surveillance Forensics Aggregates Oral communication Receivers Ultra reliable low latency communication Information leakage Safety Eavesdropping

来源：评论

学校读者我要写书评

暂无评论

Comparing Deep Reinforcement Learning Methods for HVAC System Optimization with Forecast Parameters Over Various Time Periods

Comparing Deep Reinforcement Learning Methods for HVAC Syste...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Prema Arokia Mary G Hema M S S Bama Nageswara Guptha Dept. of Computer Science and Engineering Sri Venkateshwara College of Engineering Bengaluru India Dept. of Computer Science and Engineering RV Institute of Technology and Management Bengaluru India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

Buildings are significant contributors to global energy consumption. Maintaining comfortable indoor temperatures while reducing energy consumption are conflicting objectives. Deep Reinforcement Learning (DRL) is a promising area of research for building Heating, Ventilation and Air Conditioning (HVAC) system optimization. In this study an open-source framework Building Optimization Testing Framework (BOPTEST), which is a virtual testbed that help comparison different control strategies for evaluation of DRL control methods is used. A Proportional-Integral (PI) controller is used to benchmark the DRL methods. A single zone residential building of 192 m 2 with a radial heating system and a heat pump in a climate zone with high heating requirement with dynamic electricity prices with prices varying every 15 min based on demand is chosen for implementing different control strategies. On comparing Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO) and Twin Delay DDPG (TD3) based DRL controllers and the baseline controller, the DDPG based controller reduced energy consumption by 97.3 % and operating cost by 17.7 % during the peak heating period with reference to baseline method. Then on analyzing the impact of inclusion of forecast parameters occupancy, solar irradiance, and electricity prices over the period 3, 6 and 12 hours in DDPG based controller. The prediction for 3 hours gave the greatest reduction in thermal discomfort of 99.7 % and prediction for 12 hours gave maximum reduction in cost by 30.4 % but resulted in only 82% reduction in thermal comfort when compared with baseline method indicating that longer prediction horizon is not necessarily results in better performance.

关键词： Energy consumption HVAC Costs PI control Heat pumps Electricity Buildings Deep reinforcement learning Optimization Resistance heating

来源：评论

学校读者我要写书评

暂无评论

Harnessing AI Algorithms for Accurate Medical Diagnosis from Electronic Health Record

Harnessing AI Algorithms for Accurate Medical Diagnosis from...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Jyoti Nishant Tanisha Aggarwal Sumit Department of Computer Science and Engineering Chandigarh University Mohali India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

The integration of Artificial Intelligence into health care systems has really transformed the analyses and interpretations that medical professionals conduct with regards to Electronic Health Records. EHRs are full of patient data, which, when effectively used, may help enhance diagnostic accuracy and treatment outcomes. The current paper discusses the role of AI algorithms in processing and analyzing EHR data to enable accurate and timely medical diagnosis. Specifically, we look into various techniques and methods in machine learning and deep learning, including natural language processing for unstructured clinical notes and predictive modeling for disease detection. Our approach ultimately develops towards improving the accuracy of diagnosis by finding patterns or correlations within complex datasets, reducing rates of misdiagnosis, and most importantly ensuring that clinicians’ decision-making abilities would be bettered. We also discuss some challenges surrounding data quality, privacy issues, and the requirement for explainable AI to be operated in clinical environments where transparency is the key. We are going to be able to demonstrate how this system can help revolutionize diagnostics because of its automated nature, really improving patient care and healthcare workflows in the process.

关键词： Deep learning Data privacy Accuracy Decision making Predictive models Natural language processing Medical diagnosis Artificial intelligence Electronic medical records Diseases

来源：评论

学校读者我要写书评

暂无评论

deCIFer: Crystal Structure Prediction from Powder Diffraction Data using Autoregressive Language Models

arXiv

引用

arXiv 2025年

作者： Johansen, Frederik Lizak Friis-Jensen, Ulrik Dam, Erik Bjørnager Jensen, Kirsten Marie Ørnsbjerg Mercado, Rocío Selvan, Raghavendra Department of Computer Science University of Copenhagen Denmark Department of Chemistry University of Copenhagen Denmark Department of Computer Science & Engineering Chalmers University of Technology Sweden

Novel materials drive progress across applications from energy storage to electronics. Automated characterization of material structures with machine learning methods offers a promising strategy for accelerating this key step in material design. In this work, we introduce an autoregressive language model that performs crystal structure prediction (CSP) from powder diffraction data. The presented model, deCIFer, generates crystal structures in the widely used Crystallographic Information File (CIF) format and can be conditioned on powder X-ray diffraction (PXRD) data. Unlike earlier works that primarily rely on high-level descriptors like composition, deCIFer performs CSP from diffraction data. We train deCIFer on nearly 2.3M unique crystal structures and validate on diverse sets of PXRD patterns for characterizing challenging inorganic crystal systems. Qualitative and quantitative assessments using the residual weighted profile and Wasserstein distance show that deCIFer produces structures that more accurately match the target diffraction data when conditioned, compared to the unconditioned case. Notably, deCIFer can achieve a 94% match rate on unseen data. deCIFer bridges experimental diffraction data with computational CSP, lending itself as a powerful tool for crystal structure characterization and accelerating materials discovery. 1 © 2025, CC BY.

关键词： Crystal structure

来源：评论

学校读者我要写书评

暂无评论

An Innovative Method to Detect Cyberbullying on Social Media

An Innovative Method to Detect Cyberbullying on Social Media

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： P. Pandiaraja K. Muthumanickam M. Geetha P.C. Senthil Mahesh Vedhashree S K C. Selvarathi Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of Information Technology Kongunadu College of Engineering and Technology Tholurpatti Trichy Tamil Nadu India Department of Computer Science and Engineering M.Kumarasamy College of Engineering Karur India Department of Computer Science and Engineering Excel Engineering College Komarapalayam Tamilnadu India Department of Electronics and Communication Engineering Karpagam Institute of Technology Coimbatore India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Today social media has fundamentally altered global communication and information exchange. However, as these platforms have become more widely used, so has cyber-hatred which is a significant problem that has caught academics' attention. This article has been addressed by a variety of methods from deep learning and machine learning, including recurrent neural networks, convolutional neural networks, logistic regression, and Naive Bayes. These techniques distinguish between various classes using mathematical concepts. However, sentiment-oriented data offers an accurate picture of how the public reads communications online, accurate classification necessitates a more "critical thinking" perspective. Two machine learning classifiers were employed in this study, one of which was built on a review of the literature to look at efficient classification techniques. Four online hatred datasets using logistic regression and multinomial naive Bayes. To better grasp the text in the datasets, the classifier results were enhanced by using XG-Boost algorithm.

关键词： Uniform resource locators Support vector machines Logistic regression Accuracy Cyberbullying Feature extraction Boosting Bayes methods Classification algorithms Random forests

来源：评论

学校读者我要写书评

暂无评论

Enhancing Product Review Understanding: Text Summarization with BART Large XSum 1st

Enhancing Product Review Understanding: Text Summarization w...

引用

1st International Research Conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Gopika, S. Balaji, Mayuri Mahimaa Vishwanath, M. Karthikayani, K. Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai Vadapalani India

ISBN: (纸本)9783031823824

Online shopping has revolutionized the way consumers make purchasing decisions. Customer reviews play a crucial role in this process, providing valuable insights into product quality and satisfaction. However, sifting through numerous reviews can be time-consuming for customers. This research aims to address this issue by proposing a novel method to generate a single summary for the overall reviews of each product across different years. The proposed approach utilizes the BART large xsum model to streamline the summarization process. Initially, the dataset is preprocessed to remove irrelevant reviews, such as those lacking product IDs or years. Subsequently, the dataset is divided into batches, each containing 1024 tokens, to facilitate efficient processing. Summaries are generated for each batch, and the output is then used as input for the next stage. Finally, a concise summary is produced for each product across different years. Experimental evaluations are conducted using the Amazon baby product reviews dataset, with the performance of the BART large xsum model assessed using confidence scores. The results demonstrate that the proposed method effectively generates concise summaries for the overall reviews of each product across different years, saving customers valuable time in decision-making. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Sales

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：