检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Systems, Advanced computing, and Communication, ISACC 2025

作者： Reddy, Kamalapuram Vigneswara Begum, Chimakurthy Mounika Neeraja, Adhi Jyotsna, C. Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering India

ISBN: (纸本)9798331523893

Air pollution poses serious health risks, including respiratory issues and hospitalization. This study focuses on predicting the Air Quality Index (AQI) in Delhi, leveraging data from monitoring stations and machine learning models like linear regression, support vector regression, and tree-based methods such as decision trees and random forests. Results show that the Decision Tree Regressor outperformed other models, achieving the lowest Root Mean Squared Error (RMSE) and highest R-squared (R2) values. Incorporating and advanced preprocessing enhanced accuracy, addressing seasonal variations in air quality data. The findings emphasize the value of machine learning in accurate AQI forecasting, supporting policy decisions, and improving urban air quality management. This research highlights the critical role of predictive models in mitigating air pollution's impact and protecting public health while suggesting pathways for future advancements in real-world applications. © 2025 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Deep-CNWO: a deep-chaotic nature whale optimization algorithm for early prediction of blood pressure disorder in smart healthcare settings

引用

Neural computing and Applications 2024年第24期36卷 15117-15136页

作者： Motwani, Anand Shukla, Piyush Kumar Pawar, Mahesh Arya, Monika Jain, Paras School of Computing Science and Engineering VIT Bhopal University Bhopal-Indore Highway Kothrikalan MP Sehore466114 India Department of Computer Science & amp Engineering University Institute of Technology RGPV MP Bhopal462033 India Department of Computer Science & amp Engineering CMR Engineering College Kandlakoya Medchal Telangana Hyderabad501401 India Department of Information Technology University Institute of Technology RGPV MP Bhopal462033 India

The integration of cloud and edge computing, along with machine learning, plays a vital role in the development of efficient healthcare systems in smart cities. However, machine and deep learning (DL) models are prone to delayed convergence and Type-I and Type-II errors due to data vastness and high degree imbalance. To overcome the shortcomings of previous frameworks, this work aims to propose an optimization method with DL, ‘Deep-Chaotic Nature Whale Optimization’ (Deep-CNWO) for early prediction of Blood Pressure disorders among patients under at-home supervision. A simplex search algorithm is integrated to improve the update mechanism of whale optimization algorithm (WOA), thereby creating a CNWO algorithm. The purpose of this hybrid optimization is to increase the accuracy and efficiency of DL models. Leveraging the power of DL and CNWO, this method (Deep-CNWO) provides an effective solution for early detection and proactive management of a chronic disease in at-home healthcare settings. We collected relevant data from clinical studies, including vital signs and patient contextual information, to train and evaluate the deep-CNWO model. The CNWO optimization approach has been used to improve the predictive performance and convergence of DL models. Experiments performed on imbalanced datasets using deep-CNWO have given 99.90% accuracy. The average F-score for emergency cases has improved by 22%, while the average accuracy has increased by 5.72% across all three classes, compared to the results reported in previous related work. Deep-CNWO improves the convergence of DL and reduces Type-I and Type-II errors. The experimental results demonstrate the efficacy of our proposed method for remote patient monitoring and highlight its potential for quick intervention during emergencies. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

EchoVision: RealTime Object Detection and Voice Assistance for the Visually Impaired 3

EchoVision: RealTime Object Detection and Voice Assistance f...

引用

3rd International Conference on Intelligent Systems, Advanced computing, and Communication, ISACC 2025

作者： Varshini, Penumarthi Hima Swati, V. Navya, D. Aiswariya Milan, K. Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering India

ISBN: (纸本)9798331523893

Visual impairment is one of the greatest challenges that individuals must overcome to access and navigate their environment. To address this crucial issue, the paper discusses an intelligent system that aims to improve the accessibility and independence of visually impaired people in their local communities. The proposed system uses an object detection model that interfaces with a text-to-speech system. It enables the user to express orally the names of objects which have been detected in their selected language and provides relevant information in the user's native language. Through a comprehensive evaluation, the efficiency of this system has been carefully examined. The results show important improvements on the object detection score which will enable users to interact with their environments with greater confidence and more independence. This paper takes an important step in narrowing the access gap and bringing independence to visually impaired individuals. © 2025 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Pioneering Pediatric Health - Machine Learning Ensembles for Appendicitis Detection 15

Pioneering Pediatric Health - Machine Learning Ensembles for...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Vimal, Tejasvin Ganesh, Amruth J.M. Kumar, S. Yougesh Abhishek, S. Anjali, T. Department of Electronics and Communication Engineering Amrita School of Engineering Amritapuri India Department of Computer Science and Engineering Amrita School of Computing Amritapuri India Rolls-Royce Inc Bangalore India

ISBN: (纸本)9798350370249

Children’s appendicitis is often diagnosed using outdated techniques that may not be as quick or accurate as they need to be. The present investigation employs sophisticated machine learning (ML) methodologies to mitigate these constraints and enhance the diagnostic results. We investigated the effectiveness of many ensemble machine learning (ML) models, such as Gradient Boosting Machine (GBM), CatBoost, LightGBM, AdaBoost, and Decision Trees, using a proprietary dataset that contains a diverse range of pediatric appendicitis cases. After extensive training and validation, these models showed amazing accuracy and precision rates—the best models reaching up to 99% accuracy. In addition to outlining each model’s effectiveness, our comparison study clarifies which models are applicable in clinical contexts. This research work addresses how these models might improve clinical processes, lower diagnostic mistake rates, and speed up and improve the accuracy of clinical decision-making. The findings of this study demonstrate the revolutionary potential of machine learning to improve pediatric healthcare by offering reliable instruments for intricate medical diagnosis. ©2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Unveiling Mental Health Insights: Twitter Text Analysis Using NMF and Clustering 5th

Unveiling Mental Health Insights: Twitter Text Analysis Usin...

引用

5th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2024

作者： Jahanve, Poluru Reddy Karna, Siwani Reddy, T. Anisha Dinesh Kumar, K. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bangalore India

ISBN: (纸本)9789819788644

Recently, social media has taken over the majority of the day. This is mostly because everyone expresses emotions or responds to tweets or posts with comments. As the individual expresses their thoughts, a large amount of data can be generated. This data is utilized to analyze people’s sentiments and emotions and predict their mental health. The fundamental aim of this research is to create a prediction model that utilizes available data to predict an individual’s mental health. The data set utilized includes Twitter data. To convert the text-based data into numerical values, Term Frequency-Inverse Document Frequency (TF-IDF) is utilized. Then, MNon-negative Matrix Factorization (NMF) and Clustering are performed in these numerical values to decompose large data into non-negative matrices and group similar data respectively. This study has significant implications for mental health professionals, as it offers a scalable and non-invasive tool for early detection and intervention in mental health issues. Different machine learning algorithms such as Random Forest (RF), Decision Tree (DT), Support Vector Classifier (SVC), Multinominal Naive Bayes (MNB), and XGBoost have been used. The result of the study shows promising predictive capabilities for identifying mental health conditions based on tweets. Among these, RF and DT achieved the highest accuracy of 97.4% in classifying individuals with mental health challenges. In conclusion, this study presents a novel approach to predicting mental health outcomes using Twitter data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Improving energy efficiency in scalable WSNs through IoT-driven approach

引用

International Journal of Information Technology (Singapore) 2025年 1-11页

作者： Singh, Omkar Kushwaha, Ajay Shriram Sharma, Col. Rahul Kumar, Lalit National Institute of Fashion Technology Bihar Patna India Department of Computer Science & Application Sharda School of Computing Sciences & Engineering Sharda University UP Greater Noida India School of Computer Science & Engineering ILM University Greater Noida India

A novel QoS-Driven Optimization for Energy-Efficient Clustering Routing (QDOEECR) protocol tailored for IoT-based Wireless Sensor Networks (WSNs), addressing the critical challenge of energy efficiency in sensor nodes with limited battery life. The protocol’s innovative approach lies in its advanced techniques for optimizing the selection of sub-sink nodes and identifying the optimal path to the sink node, ensuring improved adherence to Quality of Service (QoS) standards. Performance evaluations, conducted through MATLAB simulations, demonstrate the QDOEECR protocol's superior performance, achieving significant advancements over existing routing protocols. These include 30–35% reduction in end-to-end delay, 25–30% improvement in throughput, 35–40% decrease in energy consumption, 28–32% reduction in packet loss, and 32–38% extension in network lifetime. These results establish QDOEECR as a groundbreaking solution that not only enhances energy efficiency but also elevates network performance metrics beyond the capabilities of current state-of-the-art protocols like CBCCP, HCSM, and ZEAL. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： CBCCP HCSM IoT QDOEECR WSN ZEAL

来源：评论

学校读者我要写书评

暂无评论

Loan Approval Prediction Using Credit Card Score Analysis 5th

Loan Approval Prediction Using Credit Card Score Analysis

引用

5th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2024

作者： Sri Sai Samhitha, J. Sagar, K. Adarsh Haritha, Kundula Dinesh Kumar, K. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9789819788644

Banking sector offers a large variety of financial services out of which the significant amenities include payment services, custodial and safety support, loan application assistance and credit card options. Machine Learning and Data science has a vast application in the field of Banking sector. These domains play significant role in the field of loan prediction which helps in fraud detection, risk management system, maintaining efficiency, transparency and helping in continuous improvement. Due to the increasing rate of loan defaults, it’s a difficult task for the banking authorities to assess the loan requests and deal with the risks of customers defaulting the loan. An automatic loan prediction system is developed using machine learning models where the machine learns and predicts whether to approve the loan or not based on the eligibility criteria. Six prediction models including Logistic Regression Model, Decision tree, Random Forest, Support Vector Machine, K-Nearest Neighbor Classifier and XG-Boost algorithm have been performed. A comparative analysis is carried out between the models where the performance metrics for each model is calculated and compared based on which the best suitable model for predicting the loan approval status is concluded. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Ultimately Bounded Output Feedback Control for Networked Nonlinear Systems With Unreliable Communication Channel: A Buffer-Aided Strategy

引用

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1566-1578页

作者： Yuhan Zhang Zidong Wang Lei Zou Yun Chen Guoping Lu the College of Electrical Engineering and Automation Shandong University of Science and TechnologyQingdao 266590China IEEE the Department of Computer Science Brunel UniversityUB83PHUnited Kingdom the College of Information Science and Technology Donghua UniversityShanghai 201620 the Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of EducationShanghai 201620China the School of Automation Hangzhou Dianzi UniversityHangzhou 310018China the School of Electrical Engineering Nantong UniversityNantong 226019China

This paper concerns ultimately bounded output-feedback control problems for networked systems with unknown nonlinear dynamics. Sensor-to-observer signal transmission is facilitated over networks that has communication *** transmissions are carried out over an unreliable communication channel. In order to enhance the utilization rate of measurement data, a buffer-aided strategy is novelly employed to store historical measurements when communication networks are inaccessible. Using the neural network technique, a novel observer-based controller is introduced to address effects of signal transmission behaviors and unknown nonlinear *** the application of stochastic analysis and Lyapunov stability, a joint framework is constructed for analyzing resultant system performance under the introduced controller. Subsequently, existence conditions for the desired output-feedback controller are delineated. The required parameters for the observerbased controller are then determined by resolving some specific matrix inequalities. Finally, a simulation example is showcased to confirm method efficacy.

关键词： Buffer-aided strategy neural networks nonlinear control output-feedback control unreliable communication channel

来源：评论

学校读者我要写书评

暂无评论

NL2Code: A Hybrid NLP and Model-Driven Framework for Automated Code Generation from Natural Language and UML

NL2Code: A Hybrid NLP and Model-Driven Framework for Automat...

引用

2025 IEEE International Students' Conference on electrical, Electronics and computer science, SCEECS 2025

作者： Nair, Reshma P Thushara, M.G. Amrita School of Computing Amrita Department of Computer Science & Engineering Kerala Vishwa Vidyapeetham Amritapuri Kollam India Amrita School of Computing Amrita Department of Computer Science & Applications Kerala Vishwa Vidyapeetham Amritapuri Kollam India

ISBN: (纸本)9798331529833

The process of converting natural language requirements and visual models into executable software code remains an ongoing challenge in software engineering. We developed an intelligent system that adopts Natural Language Processing (NLP) and Model-Driven engineering (MDE) to generate code from natural language requirements and UML diagrams. It then applies advanced NLP techniques for natural language specification, such as tokenization, POS tagging, semantic analysis, and information extraction. This information can be transformed into computer language construct and design patterns with the help of MDE concepts. It generates code templates, skeleton code, and real code and incorporates key principles of software engineering and technological specializations. Case studies explain how the system can improve the software development lifecycle for a development company by automatically translating the natural language and the visual models into code. The system synthesized code with 92-95 % accuracy and 92-93 % completeness in three particular cases of use, proving the efficiency of the translation process of natural language requirements and UML diagrams into executable code. The present work enriches software engineering, NLP, as well as the integration of MDE, and code generation, reducing time consumption, manual efforts, and fast communication in the Software Development Process. © 2025 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Continuous Query-based Data Trading

引用

Performance Evaluation Review 2024年第1期52卷 73-74页

作者： Cheng, Jin Ding, Ningning Lui, John C.S. Huang, Jianwei School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society The Chinese University of Hong Kong Shenzhen Shenzhen China Department of Electrical and Computer Engineering Northwestern University Evanston United States Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Hong Kong

In the era of big data, traditional data trading methods designed for one-time queries on static databases fail to meet the demands of continuous query-based trading on streaming data, often resulting in repeated and inaccurate charges due to neglecting computation sharing in continuous query execution. To address this, we introduce CQTrade, the first trading framework tailored for continuous queries, which incorporates computation sharing across different time windows and queries, enhancing integration with existing trading systems. Our contributions include a theoretical analysis of computation-sharing techniques, the development of a general optimization problem to maximize seller revenue adaptable to various techniques, and the proposal of a branch-and-price algorithm to handle the problem's complexity. Our evaluation shows that the proposed framework improves the success rate of data trading by 12.8% and boosts the seller's revenue by an average of 28.7%, compared to the one-time query-based data trading methods used in the current data market. © 2024 Owner/Author.

关键词： Integer programming

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：