检索结果-内蒙古大学图书馆

9th International Conference on science, technology, engineering and Mathematics, ICONSTEM 2024

作者： Sathyaraj, P. Arulkumar, S. Ajina, A. Beshir, Kedir Umasankar, L. Arularasan, A.N. Rmk College of Engineering And Technology Department of Electronics And Communication Engineering Tamil Nadu Puduvoyal601206 India Wachemo University Department of Electrical And Computer Engineering Ethiopia M S Ramaiah Institute of Technology Department of Artificial Intelligence And Machine Learning Bangalore560054 India S.A. Engineering College Department of Electrical And Electronics Engineering Tamil Nadu Tiruvallur600077 India Panimalar Engineering College Department of Artificial Intelligence And Data Science Tamil Nadu Chennai600123 India

ISBN: (纸本)9798350365092

Rapid electronic device development requires more complicated and densely packed PCB designs. These systems need properly placed and connected electrical components for best performance and reliability. Complexity and time restrictions are rendering manual methods ineffective. Therefore, AI-based PCB insertion and routing automation methods have been developed. This research suggests using AI to optimize PCB component arrangement and routing. The system uses machine learning and optimization to improve design efficiency. The AI system creates layouts that match performance requirements, decrease signal interference, and meet manufacturing limits using previous design data and user preferences. A learning module that updates its knowledge base, an algorithm that chooses between design objectives, and real-time user input are examples. Signal integrity, thermal issues, and manufacturability are considered while modifying design requirements. Evaluation of the suggested methodology shows considerable gains in design efficiency, time-to-market, and electronic system performance. This research improves AI-automated PCB design, enabling more complex and effective electrical systems. AI in PCB design will revolutionize the industry by solving complicated design problems and speeding up the development of cutting-edge electronics. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of the Internet of Things (IOT) in the Context of 5G Wireless Systems 4

A Comprehensive Analysis of the Internet of Things (IOT) in ...

引用

4th International Conference on Innovative Practices in technology and Management, ICIPTM 2024

作者： Mohseni, Milad Kanwer, Budesh Singh, Navdeep Krishna, M Hari Rajalakshmi, B. Alkhafaji, Mohammed Ayad Islamic Azad University Department of Computer and Engineering Tabriz Iran Poornima Institute of Engineering & Technology Department of Artificial Intelligence & Data Science India Lovely Professional University Phagwara India Institute of Aeronautical Engineering Hyderabad India New Horizon College of Engineering Department of Computer Science Bangalore India National University of Science and Technology College of Technical Engineering Dhi Qar Iraq

ISBN: (纸本)9798350307757

The fast development of 5G wireless technologies (IoT) has been a major contributor to the rapid growth and expansion of the Internet of Things! This in-depth study investigates the mutually advantageous relationship between 5G and the Internet of Things (IoT), focusing on how the combination assists in the development of massive device networks, enhances connectivity, and enables the development of real-time applications. There are now new opportunities for innovative applications in smart cities, industrial automation, healthcare, and other industries owing to 5G, which enables Internet of Things devices to communicate with one another at a speed and efficiency that has never been seen before. In spite of the benefits, however, there are challenges to be faced, such as the construction of infrastructure to support the expansion of the Internet of Things and the assurance of robust security. This article provides an analysis of these components and a blueprint for leveraging the advantages of Internet of Things (IoT) with 5G while minimizing any potential downsides. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

SVM-Enhanced Dynamic Audiology Screening with IoT-Driven Monitoring for Personalized Hearing Health Management 2

SVM-Enhanced Dynamic Audiology Screening with IoT-Driven Mon...

引用

2nd International Conference on Self Sustainable artificial intelligence Systems, ICSSAS 2024

作者： Ronald, Bindu S. Raman, Ramakrishnan Vekariya, Daxa Baskar, V. Vijaya Rahul, J. Srinivasan, C. Symbiosis Law School Maharashtra Pune India Maharashtra Pune India Parul Institute of Engineering and Technology Parul University Faculty of Engineering and Technology Gujarat Vadodara India Sathyabama Institute of Science and Technology School of Electrical and Electronics Engineering Tamil Nadu Chennai India Agni College of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350368413

The increasing prevalence of hearing impairment across diverse age demographics, particularly in elderly populations, highlights the need for early diagnosis and ongoing therapy. Traditional audiology screening techniques often lack the necessary dynamic flexibility to meet personalized hearing health requirements over time. This system introduces an innovative method for dynamic audiology screening via IoT-based monitoring, using Support Vector Machine (SVM) algorithms for individualized hearing health management. The incorporation of IoT devices allows ongoing, real-time auditory data acquisition from the user's surroundings, recording essential metrics such as sound frequencies, noise levels, and auditory reactions. This data is analyzed using SVM to categorize and identify probable hearing impairments, providing great precision in differentiating between various degrees of hearing loss. The SVM model's strong classification skills render it especially effective in differentiating between varying levels of hearing loss, facilitating early identification and tailored therapy strategies. This tailored method of audiology screening boosts diagnostic precision and facilitates proactive management, perhaps improving long-term results for individuals with hearing impairments. © 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

Disaster Management Ecosystem Using Crowdsourced data, Deep Learning and NLP

Disaster Management Ecosystem Using Crowdsourced Data, Deep ...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： Vaishali Savale Siddhi Patil Atharva Raut Mrunmayee Phadke Rahul Sundkar Rajkumar Dongre Department of Artificial Intelligence and Data Science Engineering Vishwakarma Institute of Technology Pune Maharashtra India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

In recent years, the frequency and intensity of natural disasters have increased, necessitating more efficient and responsive disaster management systems. This paper presents a novel disaster management solution leveraging crowdsourced data to enhance disaster response and coordination. The system bridges the gap between citizens and emergency management officials by composing a mobile application for citizens to send real-time disaster alerts and a web application for administrators to monitor and manage these alerts. A customized DBSCAN algorithm, adapted to use haversine distance, is deployed to detect clusters of disaster alerts in real time, indicating potential disaster events. Upon cluster detection, administrators can delineate affected areas on a map, triggering notifications to users within these regions and enabling them to send help requests with images and messages. These help requests are processed using the BLIP model for image captioning and the ChatGPT API for categorization, assigning relevant tags to each request. The system provides administrators with real-time data analysis features, including map filtering and citizen help request category visualization, enabling more informed decision-making. Utilizing a cloud-based architecture ensures scalability, reliability, and efficient processing of large volumes of data. This research demonstrates the system's capability to provide timely alerts and comprehensive situational awareness, ultimately contributing to more efficient disaster management.

关键词： Cloud computing Disasters Scalability Decision making Disaster management Computer architecture Chatbots Real-time systems Reliability Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Detailed Analysis of Wavelet based Multi-Focus Image Fusion Techniques 5

A Detailed Analysis of Wavelet based Multi-Focus Image Fusio...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Mohamed Ali, E.A. Vinoth, M. Kalpanadevi, G. Subbulakshmi, M. Dharani, R. Jp College of Engineering Department of Electronics & Communication Engineering Tenkasi India K. Ramakrishnan College of Engineering Department of Electronics & Communication Engineering India Bannari Amman Institute of Technology Department of Artificial Intelligence & Data Science India J.J. College of Engineering and Technology Department of Electronics & Communication Engineering India

ISBN: (纸本)9798331504403

Image fusion combines multiple images of a single scene or object, captured by various sensors or from different angles, to create an enhanced composite image with greater informational content. This process has applications across diverse fields, including remote sensing, medical diagnostics, security systems, robotics, augmented reality, and stereovision. Its primary objectives include improving visual details, overall image quality, and offering novel perspectives. Among the various fusion methods, wavelet-based techniques have gained popularity due to their ability to preserve crucial details, minimize noise, and enhance visual quality. This study aims to compare the efficacy of eight distinct wavelet-based multi-focus image fusion approaches. To assess the spectral and spatial characteristics of the resulting fused images, the research employs eight performance metrics, providing a comprehensive analysis of these techniques. The findings of this comparative study are important for deciding which method is the simplest, most effective, and fastest to produce high-quality merged images. This will enable it to be used with a variety of imaging modalities, especially those that have limited hardware resources or produce images with a high level of quality. © 2024 IEEE.

关键词： Medical robotics

来源：评论

学校读者我要写书评

暂无评论

Fault optimisation on IEEE 14-bus system with machine learning-based SPLIT TCSC

引用

International Journal of Power and Energy Conversion 2022年第3-4期13卷 319-347页

作者： Agrawal, Niharika Khan, Faheem Ahmed Gowda, Mamatha Department of Electrical and Electronics Engineering Ghousia College of Engineering Karnataka Ramanagaram District 562 159 India Department of Artificial Intelligence and Data Science BGS College of Engineering and Technology Mahalakshmi Puram Karnataka Bengaluru560 086 India

All the operations of the power system should be smooth, continuous, reliable, and efficient. An electric fault interrupts the normal flow of power, damages the electrical equipment, creates abnormal voltages and currents, and deteriorates the system’s power quality. In this manuscript, a novel device, the SPLIT TCSC, is implemented with the traditional proportional-integral (PI) controller and with controllers based on machine learning algorithms such as artificial neural network, and random forest for fault optimisation on IEEE 14-bus system. These controllers showed better results than the PI controller with respect to voltage during fault time and THD reduction. The voltage drop is around 30 kV, and the THD is around 1.95% with the system based on random forest. The results showed that power is utilised more effectively with the application of these algorithms in the system, along with improvements in the power quality, reliability, and efficiency of the system. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Advancements in Convolutional Neural Networks for Accurate and Efficient Skin Cancer Classification: A Comprehensive Survey 8th

Advancements in Convolutional Neural Networks for Accurate a...

引用

8th International Conference on Information and Communication technology for Intelligent Systems, ICTIS 2024

作者： Takale, Dattatray G. Kashid, Shraddha S. Deshmukh, Gopal B. Gawali, Piyush P. Mahalle, Parikshit N. Sule, Bipin Deshpande, Arati V. Ghule, Vijaykumar R. Department of Computer Engineering Vishwakarma Institute of Information Technology SPPU Pune India Department of Computer Engineering MIT ADT University Pune India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Information Technology SPPU Pune India and Humanities Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9789819766741

The cancer of the skin, particularly melanoma, is considered to be one of the most life-threatening types of cancer. The major cause of skin cancer is an unrepaired deoxyribonucleic acid (DNA) disruption in skin cells which results in heritable skin imperfections or mutations that result from the disruptions. It is very important to note that skin cancers are most curable at their earliest stages, but they tend to spread to multiple parts of the body and appear as lesions. Among the lesion parameters that doctors use to identify and distinguish between non-cancer skin cancer and melanoma skin cancer is similarity, structure, spread, color, etc. These parameters provide the doctors with a valuable tool to diagnose skin cancer early on. Due to the parameter study and significant increase in skin cancer incidence rates, many researchers decided to quickly identify and diagnose skin cancer. Early detection of skin cancer is essential to lowering the mortality rate. Using deep learning and transfer learning models, researchers have been able to detect skin cancer using various algorithms. A recent study demonstrates the capability of deep learning and deep transfer learning methods to classify and detect skin cancer early. The results of this study suggest that a comprehensive investigation into the methods of Deep Learning (DL) algorithms for locating skin cancer at several stages and types is required based on the analysis of the results of this study. An investigation into articles published in reputed journals was carried out with regard to the diagnosis of skin cancer based on the findings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Enhancing Customer Personality Prediction using Advanced Machine Learning Techniques and data Balancing Strategies: A Comprehensive Approach to Addressing Imbalanced datasets in Marketing Analytics 1

Enhancing Customer Personality Prediction using Advanced Mac...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Selvalakshmi, V. Sree, T. Manju Usha Saranya, S. Devi, A. Uma Basha, Md Shaik Amzad Velammal College of Engineering and Technology Department of Master of Business Administration Madurai India Department of Master of Business Administration Hyderabad India Rajalakshmi Institute of Technology Department of Artificial Intelligence and Data Science Chennai India Alpha College of Engineering Department of Management Studies Chennai India Hyderabad India

ISBN: (纸本)9798331529246

This study tackles imbalanced customer response prediction by integrating advanced resampling methods with diverse machine learning and ensemble techniques. Novel resampling approaches (SMOTE, Borderline-SMOTE, ADASYN, and SMOTEENN) were systematically applied alongside Logistic Regression, Random Forest, Gradient Boosting, LightGBM, SVM, and Neural Networks. Stacking and voting ensembles further consolidated individual model strengths. Results show that coupling resampling with ensembles significantly boosts minority class metrics. For example, ADASYN combined with LightGBM achieved a 95% accuracy and substantially improved minority class recall and precision, while SMOTEENN with a voting ensemble reached a 99% recall, albeit with a slight precision trade-off. These findings underscore that employing sophisticated data rebalancing techniques in conjunction with hybrid ensembles can surpass traditional models, offering a balanced improvement in metrics such as accuracy, precision, recall, and F1 score. The practical significance lies in enabling more reliable predictions in highly imbalanced scenarios, ultimately enhancing decision-making processes. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Medical Image Analysis Using Deep Learning Technnique 5

Medical Image Analysis Using Deep Learning Technnique

引用

5th International Conference on Information Management and Machine intelligence, ICIMMI 2023

作者： Saxena, Surabhi Parveen, Nikhat Agarwal, Devendra Department of Artificial Intelligence and Data Science Poornima Institute of Engineering & Technology Rajasthan Jaipur India Department of Computer Science and Engineering Konneru Lakshmaiah Education Foundation Vijayawada Guntur India Goel Institute of Technology and Management Uttar Pradesh Lucknow India

ISBN: (纸本)9798400709418

Clinical picture classification, pattern recognition, and quantification have seen significant advancements with the help of artificial intelligence, particularly through deep learning techniques. Deep learning has rapidly emerged as the most rapidly evolving field within AI, and its applications have been successfully demonstrated across various domains, including medicine. This review briefly examines recent applied research in several medical fields, such as neurology, brain imaging, retinal analysis, pneumonias, computerized pathology, breast imaging, cardiovascular studies, musculoskeletal imaging, and gastrointestinal imaging. Deep learning networks prove to be highly effective when dealing with large scale medical datasets, enabling information discovery, knowledge dissemination, and knowledge-based prediction. This research aims to present both foundational knowledge and state-of-the-art deep learning techniques to facilitate the interpretation and analysis of medical images. The primary objectives of this work are to explore advancements in medical image processing research and implement the identified and addressed key criteria in practical applications. © 2023 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Aerodynamic system instability identification with sample entropy algorithm based on feature extraction

引用

Propulsion and Power Research 2023年第1期12卷 138-152页

作者： Mingming Zhang Jia Zhang Anping Hou Aiguo Xia Wei Tuo Yongzhao Lv Faculty of Science Beijing University of TechnologyBeijing 100124China School of Energy and Power Engineering Beihang UniversityBeijing 100191China Beijing Aeronautical Technology Research Center Beijing 100076China Zhengzhou Aerotropolis Institute of Artificial Intelligence ZhengzhouHenan 451162China

Based on the sample entropy algorithm in nonlinear dynamics,an improved sample entropy method is proposed in the aerodynamic system instability identification for the stall precursor detection based on the nonlinear feature extraction algorithm in an axial *** sample entropy algorithm is an improved algorithm based on the approximate entropy algorithm,which quantifies the regularity and the predictability of data in time *** with the spatial modes representing for the rotating stall in the circumferential direction,the recognition capacity of the sample entropy is displayed well on the detection of stall *** indications of rotating waves are extracted by the circumferential analysis from modal wave *** significant ascendant in the amplitude of the spatial mode is a pronounced feature well before the imminence of *** processing with the spatial mode effectively avoids the problems of inaccurate identification of a single measuring point only depending on *** to the different selections of similarity tolerance,two kinds of sample entropy are *** properties of the development process of the identification model show obvious mutation phenomena at the boundary of instability,which reveal the inherent characteristic in aerodynamic *** the dynamic difference quotient is computed according to the difference quotient criterion,after the smooth management by discrete *** rapid increase of difference quotient can be regarded as a significant feature of the system approaching the flow *** is proven that based on the principle of sample entropy algorithm,the nonlinear characteristic of rotating stall can be well *** inception can be suggested by about 12-68 revolutions before the stall *** prediction method presenting is accounted for the nonlinearity of the complex flow in stall,which is in a view of data fusion system of pressure for the spatial mode tracking.

关键词： Sample entropy algorithm Spatial mode data fusion Inception identification Nonlinear dynamics

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：