检索结果-内蒙古大学图书馆

3rd International Conference for Innovation in technology, INOCON 2024

作者： Mahale, Pragati Prashant Deshmukh, Rakesh K. Pise, Priya Gardi, Manish Subhash Kalinga University Raipur India AISSMS's Institute of Information Technology Department of Information Technology Pune India Artificial Intelligence and Data Science Indira College of Engineering and Management Pune India JSPM'S Jayawantrao Sawant College of Engineering Computer Engineering Department Pune411028 India

ISBN: (纸本)9798350381931

Methods based on deep learning are widely used nowadays for data analysis. These procedures involve low time investment and simple tools. In this research, WBC classification was suggested using module weighted optimized CNN. Two transfer learning modules and deformable convolutional (DC) layers characterize our technique, which we use to improve resilience. For WBC classification on low-resolution and noisy data sets, the suggested Optimized CNN (OCNN) demonstrated the best results because to its precise feature extraction and improved network weights. It has the potential to be employed in clinical settings as an alternate technique. White blood cells (WBCs) are immune system cells that may be found throughout the body in the blood, lymph, and other tissues. There is a current upward trend in the prevalence of WBC-related blood disorders such leukemia and lymphoma. The process of analyzing leukocytes in microscopic blood images is the major concern of this research. In this paper, we work on WBCs segmentation from microscopic blood images. © 2024 IEEE.

关键词： Blood

来源：评论

学校读者我要写书评

暂无评论

AI-Optimized Placement and Routing for PCB Design 9

AI-Optimized Placement and Routing for PCB Design

引用

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

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

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

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

Diabetic Foot Ulcer Detection and Classification using ConvMixer Model 5

Diabetic Foot Ulcer Detection and Classification using ConvM...

引用

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

作者： Anusha, N. Vidhya, R. Jani Anbarasi, L. Dhanya, D. Pushparani, S. Mohan, Geetha Vellore Institute of Technology School of Computer Science and Engineering Department of IoT Vellore Campus Vellore India Agni College of Technology Department of Information Technology Chennai India Vellore Institute of Technology School of Computer Science and Engineering Chennai India Mar Ephraem College of Engineering and Technology Department of Artificial Intelligence and Data Science Elavuvilai India Meenakshi College of Engineering Department of Cse Chennai India Institute of Applied Technology Computer Science Abu Dhabi United Arab Emirates

ISBN: (纸本)9798331504403

Diabetic foot ulcer (DFUs) are a common and significant consequence of diabetes, frequently resulting in severe illness and amputations if not promptly identified and treated. The growing occurrence of DFUs is a substantial obstacle to healthcare globally. Precise and prompt categorization of DFUs is essential for efficient treatment and avoidance of consequences. This research analyzed ConvMixer model for comprehensive classification designed to accurately evaluate DFU. The DFU images are preprocessed using the watershed algorithm that helps in separating different regions of an image, such as the ulcer and surrounding tissues, to improve the neural network's ability to extract high-quality information. The framework utilizes depthwise and pointwise convolutions to mix spatial and channel-wise information in an efficient manner to effectively extract pertinent information from various clinical DFU dataset. The proposed work features a multi-layered depthwise and pointwise convolutional architecture, created especially to manage the complex patterns and variances found in various diabetic foot ulcer stages and variants (DFUs). By integrating these convolutions and skip associations, the network facilitates hierarchical extraction of features and robust representation of features. Experimental results on a substantial and varied DFU dataset demonstrate that the ConvMixer model achieves an impressive accuracy rate of 97.16%, with a precision, F1-score and a sensitivity of 97%, 97% and 99.08% respectively. © 2024 IEEE.

关键词： Diseases

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

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

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

Machine Learning in Healthcare: A Review of Applications, Opportunities and Challenges 2

Machine Learning in Healthcare: A Review of Applications, Op...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Thute, Trupti Saratkar, Saniya Chaudhari, Aarti Raut, Rohini Thakare, Gayatri Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

This article explores the potential of machine learning (ML) in transforming healthcare. It provides an overview of ML and its various categories, highlighting how supervised and unsupervised learning algorithms can be utilized for tasks like disease diagnosis, treatment personalization, and resource allocation. The article delves into specific applications of ML in healthcare, including image analysis for early disease detection, visualization of complex medical data, and personalized medicine approaches. It further explores the exciting opportunities presented by ML, such as improved diagnostics and treatment, increased efficiency and cost reduction, and advancements in research and development. However, the article also acknowledges the challenges associated with implementing ML in healthcare, including data privacy concerns, real-time data requirements, and the complexity of certain models. Overall, the article emphasizes the multifaceted landscape of ML in healthcare, showcasing its potential to revolutionize the industry while acknowledging the hurdles that need to be addressed for successful integration. © 2025 IEEE.

关键词： Theranostics

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：