检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Johar, Sayyed Manjula, G.R. JNNCE-Shivamogga Visveswaraya Technological University Dept of AIML Belagavi India JNNCE-Shivamogga Visveswaraya Technological University Dept of Data Science Belagavi590018 India

ISBN: (纸本)9798331534950

The IoMT has dramatically empowered the process of remote patient monitoring (RPM) through much better real-time data collection and health analysis. The real struggle lies in categorizing and evaluating the patient's health-related datas due to its complexity and unbalanced nature. This study proposes an Intelligent W-DQN model based on a whale-optimized Deep-Q-Network (W-DQN) to identify and categorize pathological information, an LSTM-QDA model for recognizing temporal patterns and reducing dimensions, and a PathoDimClassifier for selecting features to address imbalanced data and noise issues effectively. Optimization techniques, including the Whale Optimization Algorithm and the Adam optimizer, are applied to improve accuracy rates while decreasing training duration and minimizing errors. The approach seeks to enhance health monitoring in time by providing accurate categorization and prompt medical interventions to ultimately enhance patient care results. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Unveiling Early Autism Spectrum Disorder Detection: A Comprehensive Study of Machine Learning and Deep Learning Approaches 6

Unveiling Early Autism Spectrum Disorder Detection: A Compre...

引用

6th IEEE Pune Section International Conference, PuneCon 2023

作者： Tarai, Trilochan Parhi, Manoranjan Mishra, Debahuti Shaw, Kailash University Department of Computer Science and Engineering Odisha Bhubaneswar India University Centre of Data Science Department of Computer Science and Engineering Odisha Bhubaneswar India Department of Aiml Pune India

ISBN: (纸本)9798350324204

According to research by the world health organization (WHO), approximately 0.63% of children are diagnosed with autism spectrum disorder (ASD). ASD commonly emerges during childhood and persists through adolescence and adulthood. Early detection of ASD is crucial as it can lead to effective interventions and improved outcomes. Machine learning and deep learning techniques have gained significant recognition for their efficacy in various fields including biomedicine and medicine. These models offer valuable tools for data interpretation in clinical diagnostics and decision-making processes. Consequently, researchers emphasize the utility of both machine learning and deep learning methods for disease screening. This study aims to leverage both machine learning and deep learning techniques to classify ASD cases using a dataset sourced from the UCI repository. The dataset encompasses pediatric cases. The classification task employed k-nearest neighbors' algorithm (k-NN), support vector machine (SVM), and convolutional neural network (CNN). Among these, CNN outperformed SVM and k-NN, achieving a remarkable accuracy of 99.71%. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Remaining Useful Life Prediction of Lithium-ion Batteries in Electric Vehicle Battery Management System 2

Machine Learning based Remaining Useful Life Prediction of L...

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Umayal, R.M. Darapaneni, Narayana Aditya, V. Paduri, Anwesh Reddy Ml and Data Science Pes University Bangalore India Aiml Great Learning Bangalore India Koneru Lakshmaiah Education Foundation Department of Commerce and Management Hyderabad India

ISBN: (纸本)9798350369960

The accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for the effective management and maintenance of electric vehicle (EV) battery systems. RUL prediction involves estimating the number of cycles or time until a battery's capacity degrades to a specified threshold, considering factors such as temperature, charging/discharging profiles, State-of-Charge(Q1), Voltage (C1, C2), and operational conditions. The RUL prediction of lithiumion batteries in EV battery management systems is a challenging task due to the complex interplay of degradation mechanisms and evolving battery technologies. data-driven approaches, leveraging machine learning algorithms and advanced data analytics techniques, have emerged as the primary method for RUL prediction. However, challenges remain in ensuring the scalability, reliability, and real -time applicability of prediction models. This paper aims to contribute to the field by developing state-of-the-art RUL prediction models that seamlessly integrate into existing EV battery management systems. This article first summarizes and classifies various methods for predicting the remaining service life of lithium-ion batteries that have been proposed in recent years. On this basis, by selecting specific criteria to evaluate and compare the accuracy of different models, find the most suitable method. Finally, summarize the development of various methods. According to the research in this article, the average accuracy of Random Forest regression and classification models is higher than the accuracy of the other methods, and the prediction cycle is shorter than the average of the other methods. © 2023 IEEE.

关键词： accuracy comparison data- driven approaches Lithium-ion Batteries Random Forest models RUL prediction

来源：评论

学校读者我要写书评

暂无评论

A DCNN with Jellyfish Questoptimization Algorithm in Order to Find Fetus Images 5

A DCNN with Jellyfish Questoptimization Algorithm in Order t...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Aravinda, K. Manjunatha, B. Kavin, Balasubramanian Prabhu Gangadevi, E. Balusamy, Balamurugan Gite, Shilpa New Horizon College of Engineering Ring Road Bellandur Post Bengaluru India Srm Institute of Science and Technology Department of Data Science and Business Systems Chengalpattu Kattankulathur India Loyola College Department of Computer Science Chennai India Delhi India Aiml Department Pune India

ISBN: (纸本)9798350383522

Incomplete closure around the spinal cord is the underlying cause of spina bifida, a birth condition. Multiple methods exist for identifying the presence of spina bifida. Ultrasound can be used to look for spinal axis deformities. However, due to the distortion inherent in prenatal ultrasound pictures, this method requires the expertise of a skilled physician in order to pinpoint the anomaly. Examining ultrasound pictures visually may be a subjective and error-prone process. The diagnosis procedure for spinal deformities may benefit from a computerised support system that can automatically locate the site of the abnormality. An algorithm for determining whether the entire spine in an ultrasound picture is healthy or diseased would be the first step in developing such software. In this study, we combine the power of the Jellyfish Search Optimisation Algorithm (JFSOA) with a deep convolution neural network to better identify SB. Improved classification accuracy is achieved by JFSOA's optimal selection of the SDL model's learning rate. Foetal ultrasound scans taken in the second trimester are widely regarded as a useful screening technique for identifying birth defects. The foetal spine picture from an ultrasound scan taken at the 18th week of pregnancy is used. Preprocessing pipelines, such as contrast improvement, intensity modification, and denoising, are used to improve the quality of ultrasound pictures and eliminate noise. Using this method, the suggested model can reliably recognise pictures of people with spina bifida. The suggested approach accurately identifies and labels ultrasound pictures as normal or defective based on the attributes retrieved © 2024 IEEE.

关键词： Fetus Abnormalities Jellyfish Search Optimization Algorithm Spina bifida Detection Synergic deep convolution neural network Ultrasound

来源：评论

学校读者我要写书评

暂无评论

Estimating the Association of Gene Disease using Knowledge Graph Embedding 15

Estimating the Association of Gene Disease using Knowledge G...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Lingan, Pooja Golden Nancy, R. Jebaseeli, T. Jemima Venkatesan, R. Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Division of AIML Karunya Institute of Technology and Sciences Coimbatore India Division of CSE Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9798331300579

Strategies for predicting gene-disease connections based on ontology cover a wide range of techniques, from conventional semantic similarity algorithms to more contemporary developments such as knowledge graph embeddings. While semantic similarity often delves within the hierarchical relations embedded in the ontology, knowledge graph embeddings take a broader view, considering a multitude of connections. Nevertheless, these embeddings are usually constructed across a single network, and additional ontologies would be necessary for more complicated tasks like gene-disease correlation prediction. The proposed research is delved into the impact of utilizing richer semantic representations derived from multiple ontologies. These representations aim to capture a comprehensive understanding of both genes and diseases, taking into account diverse types of relationships within the ontologies. The utility of using random walk-based knowledge graph embeddings, emphasizes the need for close integration of different ontologies to improve prediction performance. The multi-ontology approach contributes to a more nuanced and holistic interpretation of gene-disease associations, paving the way for improved biomedical insights. © Grenze Scientific Society, 2024.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Survey of Digital Twin for Industry 4.0: Benefits, Challenges and Opportunities

引用

SN Computer science 2024年第1期5卷 1-9页

作者： Murgod, Tejaswini R. Sundaram, S. Meenakshi Mahanthesha, U. Murugesan, Pandiyanathan Department of AIML BNM Institute of Technology Banashankri Karnataka Bengaluru 560064 India Department of Artificial Intelligence & Data Science NITTE Meenakshi Institute of Technology Karnataka Bangalore 560064 India Department of CSE-Honours KL University Vijayawada India

Manufacturing processes are becoming increasingly digital. As this trend unfolds, many companies often struggle to determine what they should be doing to drive and deliver real value both operationally and strategically. The Digital Twin (DT) is a virtual representation of a physical object, which has been proposed as one of the key concepts for Industry 4.0. The DT provides a virtual representation of products along their lifecycle that enables the prediction and optimization of the behavior of a production system and its components. A digital twin can model as a composition of basic components that provide basic functionalities, such as identification, storage, communication, security, data management, Human Machine Interface (HMI) and simulation. Recently new advanced machine-learning algorithms, data visualization, and simulation techniques have created new opportunities for reducing costs and aggregating value to the production chain. Also Cyber Physical Systems (CPSs) have been proposed as a key concept of Industry 4.0 architectures. The CPS can be described as a set of physical devices, objects and equipment that interacts with virtual cyberspace through a communication network. The cyber model of each physical entity is seen as a digital representation of the real entity and as such, sometimes called the digital twin. The digital twin and CPS are gaining popularity due to their significant impacts on the realization of smart manufacturing within which data and information from different systems is used to increase self-awareness, self-predict, and self-configure functionalities. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Artificial Intelligence Digital Twin Industry 4.0 IoT

来源：评论

学校读者我要写书评

暂无评论

Opticurve: an optimized informer-curvelet framework for enhanced hyperspectral image segmentation and classification

引用

International Journal of Information Technology (Singapore) 2025年 1-16页

作者： Shaw, Kailash Wou Onn, Choo Li, Baihua Department of Computer Science and Engineering (AIML) Vishwakarma Institute of Technology Maharashtra Pune 411037 India Faculty of Data Science and Information Technology INTI International University Persiaran Perdana BBN Putra Nilai Negeri Sembilan Nilai 71800 Malaysia Department of Computer Science Loughborough University Loughborough LE11 3TU United Kingdom

Hyperspectral image (HSI) classification is crucial for applications in climate action, land use analysis, disaster risk reduction, and informed decision-making, given the complex spatial and spectral variations inherent in HSI data. Traditional methods struggle with accurately capturing these variations, necessitating more advanced techniques. This work introduces an Optimized Linformer-Curvelet (OptiCurve) Framework that integrates CNN-based feature extraction, Curvelet Transform for spatial detail capture, and Linformer for efficient feature representation. By combining these techniques, the model enhances HSI segmentation and classification, supporting improved outcomes in critical areas like environmental monitoring and disaster response. The framework is validated on four standard HSI datasets-Indian Pines, Pavia University, Kennedy Space Center, and Houston University-showing significant performance improvements over existing methods. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2025.

关键词： Climate action Disaster risk reduction Feature extraction Hyperspectral image classification Land use Linformer-Curvelet transform

来源：评论

学校读者我要写书评

暂无评论

Epilepsy Detection Using Supervised Learning Algorithms 2

Epilepsy Detection Using Supervised Learning Algorithms

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Krishnasamy, Lalitha Sriwastav, Yash Kumar Bharat, Suchak Pratik Ganachar, Sanjana R Nandha Engineering College Department of Artificial Intelligence and Data Science Erode India School of Engineering and Technology Christ University Department of CSE Bengaluru India School of Engineering and Technology Christ University Department of CSE AIML Bengaluru India

ISBN: (纸本)9798350383652

In the current scenario, people are suffering and isolated by themselves by seizure detection and prediction in epilepsy. Also, it is highly essential that it needs to be identified through wearable devices. Researchers discussed this issue and outlined future developments in this field, suggesting that Machine Learning (ML) techniques could radically change how we diagnose and manage patients with epilepsy. However, as data availability has increased, Deep Learning (DL) techniques have become the most cutting-edge approach to adopt and use with wearable devices. On the other hand, large amounts of data are needed to train DL models, making overfitting problematic. DL models are created with open-source toolboxes and Python, allowing researchers to create automated systems and broaden computational accessibility. This work thoroughly overviews deep learning (DL) methods and neuroimaging modalities for automated epileptic seizure identification. It covers several MRI and EEG techniques for epileptic seizure diagnosis and treatment programmes designed to treat these seizures. The study also covers the difficulties in precise detection, the benefits and drawbacks of DL-based strategies, potential DL models and upcoming research in this area. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

'Challenges and Solution for Security & Living in High Altitude Area Siachen'

'Challenges and Solution for Security & Living in High Altit...

引用

2023 International Conference on Sustainable Emerging Innovations in Engineering and Technology, ICSEIET 2023

作者： Singh, Anirudh Pratap Rajput, Anushree Kumar, Anil Jain, Dhyanendra Verma, Pranshi Iit Madras Data Science & Application Chennai India Abes Ec CSE-AIML Ghaziabad India Gurukula Kangari University Department of Mathematics & Statistics Haridwar India Mjp Rohilkhand University CGC-MJPRU Department of Mathematics & Statistics Bareilly India ABES Engineering College Department of CSE-AIML Ghaziabad India

ISBN: (纸本)9798350329186

This abstract discusses the challenges faced by soldiers at high-altitude border fronts and proposes a solution to address these issues. The soldiers endure extreme weather conditions, including strong winds of 300 KM/Hour and bone-chilling temperatures of -60 degrees Celsius, along with blizzards and avalanches. Food scarcity is common, necessitating snow boiling for drinking water, and limited time for eating due to freezing conditions. Communication with loved ones is challenging due to the lack of mobile networks in such remote locations. To tackle these problems, the author introduces a Multipurpose cable system that provides electrical power, telecommunication lines for base camp connectivity, and optical fiber for data sharing. The cable is designed to withstand extreme weather conditions and is spread within the snow using specific alloys to ensure stability at temperatures ranging from -75°C to -100°C. The cable includes self-security features to prevent tampering and provides GPS navigation capabilities. The proposed solution enables the supply of frozen food to soldiers, which can be cooked on electric heaters, making the process environmentally friendly. Additionally, an Indestructible Secure Communication Network is suggested, utilizing optical and telecommunication cables covered with metal repair paste for added security. This network establishes an unhackable serverless system at critical locations, facilitating secure communication for defense forces, research labs, and ministries. The proposed system utilizes two specially designed cables for different terrains and risk levels, effectively connecting high-altitude posts to bases without disturbing the environment. By implementing this solution, the aim is to improve the living conditions and security of armed forces stationed at challenging high-altitude border fronts. © 2023 IEEE.

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

ML Powered Analytics for Sensing Demand in Consumer Industry 6

ML Powered Analytics for Sensing Demand in Consumer Industry

引用

6th IEEE Pune Section International Conference, PuneCon 2023

作者： Shanbhogue, Rahul Yashwanth, N.D. Paduri, Anwesh Reddy Ramakrishna, Panish Prabhu, Srikanth Dhulipati, Muralidhara Sarma Darapaneni, Narayana Pes University Data Science & Machine Learning Bangalore India Koneru Lakshmaiah Eduaction Foundation Department of Commerce and Management Hyderabad India Great Learning/Northwestern University Aiml IL United States

ISBN: (纸本)9798350324204

The consumer goods industry is facing significant challenges in meeting the consumer's everevolving demands and preferences. The e-commerce and online delivery brought in the ease of access to purchase products, while the popularity of social media brought the social sentiment angle which are impacting customer purchases patterns. These factors are leading to a rise in influencer marketing campaigns and have enabled businesses or brands to reach consumers faster. The goal of the study is to address these challenges and to explore the use of Machine learning and big data analytic techniques to provide insights by understanding consumer purchase patterns, sales data, market and social media trends, news feed and stock levels to predict future demand for products in advance which will better enable inventory planning. © 2023 IEEE.

关键词： Big data

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：