检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Das, Supantha Hazra, Arnab Pati, Soumen Kumar Ghosh, Soumadip Mallik, Saurav Banerjee, Suharta Mukherji, Ayan Li, Aimin Zhao, Zhongming Academy of Technology Hooghly Department of Information Technology West Bengal India Future Institute of Technology Kolkata Department of Computer Science and Engineering West Bengal India Maulana Abul Kalam Azad University of Technology West Bengal Haringhata Department of Bioinformatics West Bengal Nadia India Sister Nivedita University Department of Computer Science and Engineering West BengalNew Town Kolkata India Harvard T H Chan School of Public Health Department of Environmental Health BostonMA United States Meghnad Saha of Institute of Technology Department of Computer Science and Engineering West Bengal Kolkata India Pailan College of Management & Technology Department of Computer Science and Engineering West Bengal Kolkata India Xi'an University of Technology School of Computer Science & Engineering Shaanxi Xi'an710048 China The University of Texas Health Science Center Center for Precision Health School of Biomedical Informatics HoustonTX77030 United States

ISBN: (纸本)9781665468190

Chronic kidney disease (CKD) is as severe as cancer in today s world. It may even lead to the permanent failure of kidney. The initial detection of this disease is needed for timely cure. Our work presents a classifier (named ANFIS) in accordance with the notion of neuro-fuzzy in order to detect the existence of chronic kidney disease. We use blood test results of several patients for our research study. We compare our proposed classifier with some conventional classifiers such as Multi-layer Perceptron, Support Vector Machine, Logistic Regression and Decision Tree. Experimental results indicates that our proposed neuro-fuzzy rule-based classifier performs better than the other classifiers used here. ANFIS has given 3% to 4% better accuracy compared to the other classifiers. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Digital Health during COVID-19: informatics Dialogue with the World Health Organization

引用

Yearbook of Medical informatics 2021年第1期30卷 13-16页

作者： Koch, Sabine Hersh, William R. Bellazzi, Riccardo Leong, Tze Yun Yedaly, Moctar Al-Shorbaji, Najeeb Health Informatics Centre Department of Learning Informatics Management and Ethics Karolinska Institutet Stockholm Sweden Department of Medical Informatics & Clinical Epidemiology School of Medicine Oregon Health & Science University Portland OR United States Department of Electrical Computer and Biomedical Engineering University of Pavia Italy IRCCS ICS Maugeri Pavia Italy Department of Computer Science School of Computing National University of Singapore and AI Singapore Singapore Information Society Division African Union Commission Addis Ababa Ethiopia eHealth Development Association Amman Jordan

Background: On December 16, 2020 representatives of the International Medical informatics Association (IMIA), a Non-Governmental Organization in official relations with the World Health Organization (WHO), along with its International Academy for Health Sciences informatics (IAHSI), held an open dialogue with WHO Director General (WHO DG) Tedros Adhanom Ghebreyesus about the opportunities and challenges of digital health during the COVID-19 global pandemic. Objectives: The aim of this paper is to report the outcomes of the dialogue and discussions with more than 200 participants representing different civil society organizations (CSOs). Methods: The dialogue was held in form of a webinar. After an initial address of the WHO DG, short presentations by the panelists, and live discussions between panelists, the WHO DG and WHO representatives took place. The audience was able to post questions in written. These written discussions were saved with participants’ consent and summarized in this paper. Results: The main themes that were brought up by the audience for discussion were: (a) opportunities and challenges in general;(b) ethics and artificial intelligence;(c) digital divide;(d) education. Proposed actions included the development of a roadmap based on the lessons learned from the COVID-19 pandemic. Conclusions: Decision making by policy makers needs to be evidence-based and health informatics research should be used to support decisions surrounding digital health, and we further propose next steps in the collaboration between IMIA and WHO such as future engagement in the World Health Assembly. © 2021 Thieme Medical Publishers, Inc.. All rights reserved.

关键词： Artificial Intelligence COVID-19 Global Health Medical informatics World Health Organization

来源：评论

学校读者我要写书评

暂无评论

Autonomous Multi-Objective Optimization Using Large Language Model

arXiv

引用

arXiv 2024年

作者： Huang, Yuxiao Wu, Shenghao Zhang, Wenjie Wu, Jibin Feng, Liang Tan, Kay Chen The Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Electrical and Elctronics Engineering The Hong Kong Polytechnic University Hong Kong The Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong College of Computer Science Chongqing University Chongqing400044 China

Multi-objective optimization problems (MOPs) are ubiquitous in real-world applications, presenting a complex challenge of balancing multiple conflicting objectives. Traditional evolutionary algorithms (EAs), though effective, often rely on domain-specific expertise and iterative fine-tuning, hindering adaptability to unseen MOPs. In recent years, the advent of Large Language Models (LLMs) has revolutionized software engineering by enabling the autonomous generation and refinement of programs. Leveraging this breakthrough, we propose a new LLM-based framework that autonomously designs EA operators for solving MOPs. The proposed framework includes a robust testing module to refine the generated EA operator through error-driven dialogue with LLMs, a dynamic selection strategy along with informative prompting-based crossover and mutation to fit textual optimization pipeline. Our approach facilitates the design of EA operators without the extensive demands for expert intervention, thereby speeding up the innovation of EA operators. Empirical studies across various MOP categories validate the robustness and superior performance of our proposed framework. © 2024, CC BY.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Image Based Feature Separation Using RBM Tech with ADBN Tech for Accurate Fruit Classification

Image Based Feature Separation Using RBM Tech with ADBN Tech...

引用

computing, Power and Communication Technologies (IC2PCT), IEEE International Conference on

作者： V Revathi Balasubramanian Prabhu Kavin Arunadevi Thirumalraj E. Gangadevi Balamurugan Balusamy Shilpa Gite Department of Applied Sciences - Physics New Horizon College of Engineering Ring Road Bellandur Post Bengaluru India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu Tamil Nadu India Department of Computer Science Engineering K.Ramakrishnan College of Technology Trichy Tamil Nadu Department of Computer Science Loyola College Chennai Delhi-National Capital Region (NCR) Shiv Nadar University AIML department Symbiosis Institute of Technology Pune Symbiosis International (Deemed University) Pune India

One of the fastest-growing subfields of computer vision and picture categorization is fruit identification. The fruit industry could start using a standardised categorization system so that shoppers can easily distinguish between different types and quality levels of fruit. From a health perspective, fruit quality is essential. The task of classifying fruits is crucial in many commercial contexts. A supermarket cashier may use a fruit categorization system to better recognise the varieties of fruit and their associated costs. It might also be used to determine whether or not a given kind of fruit is suitable for a person’s diet. The rising use of intelligent imaging equipment may be directly attributed to the proliferation and development of AI software. Deep learning methods, such as CNN, are now being used by researchers for picture categorization. CNN’s superior performance may be achieved without using any manually-crafted characteristics, in contrast to the older methods. For automated categorization, it employs a plethora of filters that strip relevant visual information. Classifying fruits accurately is a challenge in the horticulture sector and calls for the knowledge of an expert. For accurately and quantitatively analysing fruits, the currently mentioned categorization techniques fall short. Therefore, it is beneficial to review the latest suggestions for categorizing fruits. To solve this problem, we need a computerised system that can automatically sort fruits into their respective categories. Deep learning models, such as the Restricted Boltzmann Machine (RBM) and the Adam based Deep Belief Network (DBN), are used in this assignment to categorise fruits according to the attributes that have been determined to be optimum and generated. The proposed approach has been shown to have effective accuracy and quantitative analysis outcomes, and this is just the beginning of this realisation. In addition, the suggested scheme’s relatively strong computational mo

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Cardiovascular Disease Prediction with Data Mining and Machine Learning

Optimizing Cardiovascular Disease Prediction with Data Minin...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Garima Joshi Namita Joshi Himanshu Pant Preeti Malara Himanshu Rai Goyal Department of Zoology MBPG College Haldwani Nainital India College of Pharmacy y Graphic Era Hill University Bhimtal India School of Computing Graphic Era Hill University Bhimtal India College of Nursing Graphic Era Hill University Bhimtal India Computer Science & Engineering Graphic Era University Dehradun Uttarakhand

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

Heart-related diseases, or CVDs for short, are cardiovascular ailments that are now the most dangerous sickness in the world and the leading cause of mortality globally in recent decades, not just in India. Because of this, a dependable, precise, and efficient system is needed to recognize these disorders and provide prompt, appropriate treatment. Utilizing machine learning methods and algorithms on a range of medical datasets has automated large-scale and sophisticated data processing. Scientists have recently begun to use a range of machine learning methods to help doctors and other medical professionals identify heart-related conditions. Numerous machine learning and data mining approaches are utilized for the forecasting of cardiac disease, including Support Vector Machine (SVM), Random Forest, and Artificial Neural Network (ANN). Cardiovascular disease diagnosis and prognosis have become difficult issues for medical professionals. The enormous number of deaths from heart disease must be decreased, hence a rapid and effective diagnosis method must be found. In this field, data mining methods and machine learning algorithms are crucial. Researchers are working more quickly to create software that uses machine learning algorithms to assist physicians in identifying and predicting cardiac problems. In order to lower the death rate from cardiovascular disorders, this research creates a model that can accurately forecast these conditions.

关键词： Support vector machines Heart Machine learning algorithms Mortality Cardiac disease Machine learning Medical services Data mining Decision trees Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Convolutional Neural Networks (DCNNs) for Automated Classification of E-Waste Components: Focusing on Circuit Boards, Batteries, and Cables

Application of Deep Convolutional Neural Networks (DCNNs) fo...

引用

Innovations in High Speed Communication and Signal Processing (IHCSP), International Conference on

作者： Frederick Ruby Helen Sivaram Rajeyyagari Murugananth Gopal Raj Shamim Ahmad khan Varunadevi S I Infant raj Department of Humanities and Social Sciences Saveetha School of Law Saveetha Institute of Medical and Technical Sciences Chennai India Department of Computer Science College of Computing and Information Technology Shaqra University Shaqra Saudi Arabia Department of EEE Ahalia School of Engineering and Technology Palakkad Kerala India Glocal School of Science & Technology Glocal University U.P India Department of CSE CMS College of Engineering and Technology Coimbatore Tamilnadu Department of CSE K.Ramakrishnan College of Engineering Trichy Tamil Nadu India

ISBN: (数字)9798350368949

ISBN: (纸本)9798350368956

The proliferation of electronic waste (e-waste) has become a pressing environmental concern, necessitating efficient methods for its classification and management. Though there are traditional methods which are used when sorting and recyling e-waste, they are time-consuming, costly and most of the time, are not accurate and hence, a lot of resources are wasted in the process. This research aims at extending the use of Deep Convolutional Neural Networks (DCNNs) in the classification of critical e-waste components namely circuit boards, batteries, and cables. The proposed method fully utilizes the capacity of extracting features of DCNNs in order to accurately detect and sort these components by means of the receiving visual information. For training and testing the DCNN model a dataset was created and preprocessed and the target images included circuit boards of different orientations and sizes, batteries and cables. The architecture of a network was created considering aspect of depth and computational complexity guarantying high accuracy and feasible time for great data set processing. In the evaluation process of the model, a comparison was made with various standard performance measures, with checklists such as accuracy, precision and recall and F1-score to rate the prowess of the proposed model in taking part in the classifying process of e-waste components. From the analysis, the proposed DCNN model reached classification accuracy over 95.9% on all the categories suggesting the model can be used as a tool to sort e-waste automatically. The paper also considers the issues of implementing such technology in the current recycling systems and the overall advantages, which will be the increase of the sorting efficiency, decreased labor expenses, as well as elevated recovery rates of materials demanded in the market.

关键词： Accuracy Computational modeling Printed circuits Electronic waste Feature extraction Batteries Convolutional neural networks Integrated circuit modeling Cables Sorting

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Classification using Machine Learning Techniques

Skin Cancer Classification using Machine Learning Techniques

引用

BIT Conference (BITCON), International

作者： I. Sapthami Ch. Srilakshmi Batta Saranya N. Kumareshan Ramesh Kumar Ayyasamy P. Chinnasamy Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India Department of Information Technology VNR VJIET Bachupally Hyderabad India AIDS Department CBITGandipet Hyderabad India Department of ECE Professor/Centre for Advances in Signal Processing and Sensor Networks Sri Eshwar College of Engineering Coimbatore Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman (UTAR) Kampar Malaysia Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Srivilliputtur TamilNadu

ISBN: (数字)9798331518394

ISBN: (纸本)9798331518400

The death rate from skin cancer has radically grown due to a lack of understanding about the indications and prevention measures. It is one of the most lethal types of cancers, and the mortality rate due to skin cancer has risen sharply. Cancer must be diagnosed as early as possible to halt its growth and prevent metastasis. Even though there are numerous varieties of skin cancer, melanoma, basal cell carcinoma, and squamous cell carcinoma are considered the three most dangerous types of skin cancer. This research, using the CNN image-processing technology and machine learning, tries to detect and classify into the many kinds of skin cancer. Artificial intelligence (AI) based algorithms for automated skin cancer classification have consistently outperformed human professionals in several clinical studies, laying the groundwork for a future in which AI will be widely used.

关键词： Squamous cell carcinoma Prevention and mitigation Mortality Melanoma Machine learning Data augmentation Skin Classification algorithms Convolutional neural networks Skin cancer

来源：评论

学校读者我要写书评

暂无评论

Unmasking Digital Deceptions: A Comprehensive Survey of Synthetic Reality Analysis Across Multimedia Domains

Unmasking Digital Deceptions: A Comprehensive Survey of Synt...

引用

Electronic Systems and Intelligent computing (ICESIC), International Conference on

作者： Sneha Chaudhary Komal Chaurasiya Suthir Sriram Ravikumar S Nivethitha V Thangavel M Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology College of Information and Technology United Arab Emirates University

ISBN: (数字)9798331522988

ISBN: (纸本)9798331522995

The general accessibility of social networking sites like Facebook, Myspace and TikTok has transformed the way information is communicated, but it has also made it simpler to spread misleading information, thanks to cutting-edge technologies like deepfakes. The use of artificial intelligence in deepfake technology produces material that is remarkably life- like but fake, making it difficult to identify and remove fraudulent content. The evolution of deepfake technology is reviewed in this study, starting with early breakthroughs like the Video Rewrite Program and continuing with more current developments like the Synthesizing Obama and Face2Face projects. We provide a comprehensive analysis of the state-of-the-art detection strategies, namely Region-based CNNs (RCNNs), Conventional Neural Networks (CNNs), and hybrid approaches that combine various deep learning techniques. Though these methods have advanced, there are still issues with accuracy, integration complexity, and adaptability to new deepfake techniques. This paper suggests a novel approach that integrates image, video, and audio analysis into a single detection framework in order to overcome these difficulties. The new approach is directed towards improvement of detection accuracy and the lowering of the false alarm using advanced and deep learning engines along with the real time processing requirements. Early results indicate that the detection capabilities have significantly improved compared to existing solutions operating in real time environment while having less latency and higher recall and precision rates. This method is more effective for deepfake detection and at the same time helps in augmenting the comprehensiveness and efficiency of the system there by making it suitable for wider uses. The study emphasizes the presence of the need for the evolution of static approaches towards the effective defection of sophisticated false information and the justification of new possibilities in the fight a

关键词： Deep learning Surveys Deepfakes Technological innovation Accuracy Video on demand Social networking (online) Real-time systems Web sites Protection

来源：评论

学校读者我要写书评

暂无评论

Oral cavity carcinoma detection using BAT algorithm-optimized machine learning models with transfer learning and random sampling

引用

computers in Biology and Medicine 2025年第Pt B期192卷 110250-110250页

作者： Folorunso, Sakinat O. Abdulwarith, Akinshipo Adeniyi, Abidemi Emmanuel Aworinde, Halleluyah Oluwatobi Awotunde, Joseph Bamidele Artificial Intelligence Systems Research Group Department of Computer Science Olabisi Onabanjo University Ago-Iwoye Nigeria Department of Oral and Maxillofacial Pathology and Biology Faculty of Dentistry University of Lagos Lagos Nigeria Department of Computer Science College of Computing and Communication Studies Bowen University Iwo Nigeria Chitkara University Institute of Engineering and Technology Chitkara University Punjab India MIVA Open University Abuja Nigeria Department of Information Technology Durban University of Technology KZ Durban South Africa Department of Computer Science Faculty of Communication and Information Sciences University of Ilorin Nigeria

Background: Oral cavity carcinoma remains a major public health concern, where early and accurate detection is vital for improving patient outcomes and survival rates. Current diagnostic systems often face challenges such as limited feature selection capabilities, imbalanced datasets, and computational inefficiencies. Methods: This study proposes a novel diagnostic framework TR-ROS-BAT-ML that integrates transfer learning, random sampling, and a BAT algorithm-based optimization strategy with ensemble machine learning classifiers. A dataset comprising 1224 hematoxylin and eosin (H&E)-stained histological images (at 100x and 400x magnifications) of normal oral epithelium and Oral Squamous Cell Carcinoma (OSCC) was collected from 230 patients using a Leica ICC50 HD microscopy camera. Pre-trained deep learning models (NANSNetLarge, EfficientNetB7, EfficientNetV2L, EfficientNetV2S, EfficientNetV2M) were employed for feature extraction. To address class imbalance, random oversampling techniques were applied. The BAT algorithm, inspired by bat echolocation behavior, was used for feature selection and hyperparameter tuning. Optimized features were classified using ensemble methods, including XGBoost, AdaBoost, Extra Trees (ET), Histogram-Based Gradient Boosting (HBGC), and MultiLayer Perceptron (MLP). Results: The proposed approach achieved high diagnostic performance across multiple model combinations. The best performance was recorded with the optimized ET model using random oversampling, achieving a recall of 0.992, demonstrating its efficacy in detecting oral lesions. In contrast, the combination of EfficientNetV2S + ROS + MLP yielded the lowest accuracy at 50.8 %. These results confirm the robustness of the TR-ROS-BAT-ML framework in handling imbalanced datasets and optimizing classification performance. Conclusions: This study demonstrates the effectiveness of combining nature-inspired optimization, transfer learning, and ensemble machine learning for enhanced detecti

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

E-Commerce Supply Chains with Considerations of Cyber-Security

E-Commerce Supply Chains with Considerations of Cyber-Securi...

引用

computer Science and Emerging Technologies (CSET), International Conference on

作者： Firas H. Zawaideh Waheeb Abu-ulbeh Yousef I. Majdalawi Muhammad D. Zakaria Julaily Aida Jusoh Sunanda Das Department of Cyber Security Faculty of Science and Informaiton Technology Irbid National University Irbid Jordan Cybersecurity Department Faculty of Administrative sciences and Informatics Al-Istiqlal University Palestine Business & E-commerce Department Faculty of Management and Financial Sciences Petra University Amman Faculty of Informatics and Computing UniSZA Malaysia School of Computer Science and Engineering Jain University Bangalore India

As the global e-commerce landscape continues to expand rapidly, the efficiency and security of supply chains have become critical areas of concern. With the increasing reliance on digital platforms and the interconnected nature of supply chains, the vulnerability to cyber threats has escalated significantly. This research paper delves into the multifaceted domain of e-commerce supply chains with a primary focus on cyber-security considerations. The objective of this study is to assess the existing cyber-security measures and vulnerabilities within e-commerce supply chains while proposing effective strategies to mitigate potential risks. Through an extensive literature review, the paper highlights various cyber-security challenges faced by e-commerce enterprises, including data breaches, ransomware attacks, and supply chain disruptions caused by cyber-attacks on logistics partners. By analyzing real-world case studies and industry reports, the research provides valuable insights into the consequences of cyber-security lapses and their impact on supply chain resilience and consumer trust. The research also explores the technological advancements and best practices that can fortify e-commerce supply chains against cyber threats. It examines the role of encryption, multi-factor authentication, secure payment gateways, and cloud-based security solutions in safeguarding sensitive data and maintaining the integrity of supply chain operations. Additionally, the study investigates the importance of employee training and awareness programs to cultivate a cyber-security-oriented organizational culture. Furthermore, this paper considers the legal and regulatory aspects of cyber-security in the context of e-commerce supply chains. By examining international laws, industry standards, and compliance requirements, it highlights the responsibilities and obligations of e-commerce businesses to protect customer data and secure the flow of goods throughout the supply chain. The efficie

关键词：

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：