检索结果-内蒙古大学图书馆

Possibilities of using nano particles in human urine for transient biometrics

Materials Today: Proceedings 2023年 80卷 2765-2768页

作者： Ambiga, N. Nagarajan, A. Research Scholar Department of Computer Applications Alagappa University Tamilnadu Karaikudi India Assistant Professor Department of Computer Applications Alagappa University Tamilnadu Karaikudi India

The major aspect of this research paper is to investigate the data of Nano particles that exists in human urine The important aspect of this research paper is to study and investigate the Nano Particles present in the human urine to identify or recognise the human .The major use of nanoparticles is its presence in human biological fluid, urine and Blood. It is widely used in cosmetics, personal care, medicine, agriculture, food safety, and pharmacy. The level of the concentration of Nano particles present in human urine is analysed for defining Biometrics. It has raised a growing concern when excess or deficient may cause toxicity because of these Nano particles emerged due to the human beings and Environment. The assessment of Nano particles (size distribution and determination) is becoming a very big challenge to the human beings because of the need of the new and updated analytical instrumentation. The concentration of Nano particles is different to each and every individual. The results obtained from this investigation provides Biometric Authentication which is helpful in identifying a person and also it provides ancillary information to the primary biometrics as soft biometrics and even it can be considered for disease analysis. © 2021

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Transfer Learning Models for Brain Tumor Detection

引用

Procedia computer Science 2025年 258卷 2415-2424页

作者： Jyoti Anuj Kumar Silky Sachar Ph.D Scholar Computer Science and Applications Panjab University Chandigarh India Assistant Professor Computer Science and Applications Panjab University Chandigarh India

Brain tumors rank among the most dangerous and life-threatening conditions, requiring accurate and timely detection for efficient treatment. Conventional diagnosis techniques, which rely on radiologists’ manual interpretation of medical pictures, might be time-consuming and susceptible to inconsistencies. To address these issues, deep learning (DL) models have become effective instruments for automating tumor classification, improving both efficiency and accuracy. In this manuscript, we evaluate the efficiency of various DL models in classifying MRI images as either tumorous or non-tumorous using the BR35H dataset, which includes 2,100 training images and 600 validation images. We assess nine pre-trained transfer learning (TL) models: DenseNet121, MobileNetV2, Inception-V3, MobileNetV3Large, Xception, DenseNet201, VGG16, AlexNet, InceptionResNetV2, and VGG16. Each model is fine-tuned and evaluated using precision, accuracy, recall, and F1-score metrics. Among all the techniques, Xception achieved the greatest accuracy at 98.33%, while MobileNetV3Large exhibited the lowest accuracy at 75.16%. This outcome showed the efficiency of advanced DL models in binary tumor classification, highlighting the importance of model selection in developing accurate and reliable diagnostic tools. Overall, the Xception model stands out as the most promising for automating the detection of tumorous and non-tumorous conditions in MRI images, offering a significant improvement over the traditional diagnostic method.

关键词： MRI (Magnetic resonance images) Brain tumor Convolution Neural Network (CNN) Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in the detection and classification of dental caries

引用

Journal of Prosthetic Dentistry 2025年第5期133卷 1326-1332页

作者： Ahmed, Walaa Magdy Azhari, Amr Ahmed Fawaz, Khaled Ahmed Ahmed, Hani M. Alsadah, Zainab M. Majumdar, Aritra Carvalho, Ricardo Marins Assistant Professor Department of Restorative Dentistry Faculty of Dentistry King Abdulaziz University Jeddah Saudi Arabia Associate Professor Department of Orthopedic Surgery Faculty of Medicine Cairo University Cairo Egypt Assistant Professor Department of Civil Engineering Faculty of Engineering King Abdulaziz University Jeddah Saudi Arabia Consultant in Restorative Dentistry Dental Department East Jeddah General Hospital Ministry of Health Jeddah Saudi Arabia Graduate student Department of Computer Science Computer Science and Applications Virginia Polytechnic Institute and State University Blacksburg VA United States Professor Department of Oral Biological and Medical Sciences Faculty of Dentistry University of British Columbia Vancouver BC Canada

Statement of problem: Automated detection of dental caries could enhance early detection, save clinician time, and enrich treatment decisions. However, a reliable system is lacking. Purpose: The purpose of this study was to train a deep learning model and to assess its ability to detect and classify dental caries. Material and methods: Bitewings radiographs with a 1876×1402-pixel resolution were collected, segmented, and anonymized with a radiographic image analysis software program and were identified and classified according to the modified King Abdulaziz University (KAU) classification for dental caries. The method was based on supervised learning algorithms trained on semantic segmentation tasks. Results: The mean score for the intersection-over-union of the model was 0.55 for proximal carious lesions on a 5-category segmentation assignment and a mean F1 score of 0.535 using 554 training samples. Conclusions: The study validated the high potential for developing an accurate caries detection model that will expedite caries identification, assess clinician decision-making, and improve the quality of patient care. © 2025 Editorial Council for The Journal of Prosthetic Dentistry

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Impact of the Blockchain on Academic Certificate Verification System-Review

EAI Endorsed Transactions on Energy Web

引用

EAI Endorsed Transactions on Energy Web 2021年第36期8卷 1-8页

作者： Kumutha, K. Jayalakshmi, S. Research Scholar VISTAS Assistant Professor Tagore College of Arts and Science Chennai India VISTAS Department of Computer Applications Chennai India

Blockchain innovation (BT) guarantees benefits in believe capacity, collaboration, organization, identifying proof, validity, and transparency. These solid suggestions for the long run of how to verify the authenticity of academic certificates because a paper-based certification is fallible to manipulation and susceptible to fraud. This literature review started by collecting a test of basically peer-reviewed sources, as well as an enlightening outline of articles from different other channels to analyse about approximately later approaches, techniques and later patterns on instruction which is being utilized in blockchain innovation on document verification from different sector such as banking, medical records and education system etc. This paper proposes a digital certificate verification blockchain based system employing anowner authentication scheme and time, space of the students are stored as blocks using blockchain technology. A distributed public record with tamper proof and immutable that preserves the state of the document, which creates security in the digital asset. This clearly stated that this technology is required to keep digital assets in secure and any one can access without loss of data and maintained it with minimum cost. © 2021 Kumutha.K et al., licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution license, which permits unlimited use, distribution and reproduction in any medium so long as the original work is properly cited.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Precaution Chatbot for Epilepsy Patients using Natural Language Processing and Deep Learning Sequential Model

引用

Procedia computer Science 2024年 233卷 537-546页

作者： E Kasthuri S. Subbulakshmi Rajasree Sreedharan Research Scholar Department of Computer Science and Engineering Assistant Professor Department of Computer Science and Applications Amrita School of Computing Amritapuri India Associate Professor Division of Nephrology Department of Pediatrics Medical College of Wisconsin Milwaukee Wisconsin USA

Epilepsy is a brain disorder that can affect people of all ages which is one of the most common neurological disorders affecting around 50 million individuals. Healthcare Chatbots schedule appointments, respond to patient inquiries, and offer relevant information, freeing medical staff to handle life crises. This paper implements a chatbot for epilepsy patients to increase awareness about epilepsy. Patients may easily access this AI-based healthcare chatbot whenever they have queries regarding precautions to be taken by epilepsy patients. Chatbot uses a rich set of epilepsy-related datasets collected from trusted websites which are preprocessed with NLP techniques to prepare the data for model ***, LSTM, and RNN models are created and evaluated to produce answers to user queries related to possible precautions to avoid seizures, safety measures to be taken by patients with seizure history, etc. Evaluation of models shows that the RNN model generates more accurate answers with 94% accuracy. Finally, the epilepsy question answering Chatbot for precaution is concluded with the RNN model.

关键词： Epilepsy Seizure Chatbot Natutal Language Processing LSTM Long short-term memory Recurrent neural network Deep neural network

来源：评论

学校读者我要写书评

暂无评论

Insightful Clinical Assistance for Anemia Prediction with Data Analysis and Explainable AI

引用

Procedia computer Science 2024年 233卷 45-55页

Anemia among young people has positive correlation with susceptibility and impede cognitive development. As per WHO 2019 statistics global prevalence rate of anemia is 33 percent. This work aims to predict anemia with inferences to identify the root cause of anemia. Prediction is done with machine learning algorithms with proper pre-processing, data normalization, and class imbalance approaches. Explainable AI, a transparent model, is used to enhance the prediction which enables to draw inferences. LGM Boost learning model prediction has a 91% accuracy and explainable AI framework predictions of most contributing attribute is accurate when compared to other models. This approach helps healthcare professionals make informed decisions on the most optimal treatment for anemia.

关键词： Explainable Artificial Intelligence Machine learning Anemia Data preprocessing

来源：评论

学校读者我要写书评

暂无评论

GS-FFO Based Meta-Heuristic Clustering for Discovering Colossal Patterns in High-Dimensional Data 2nd

GS-FFO Based Meta-Heuristic Clustering for Discovering Colos...

引用

2nd Congress on Control, Robotics, and Mechatronics, CRM 2024

作者： Reddy, T. Sreenivasula Sathya, R. Nuka, Mallikharjuna Rao Research Scholar Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Annamalai Nagar Tamil Nadu Chidambaram608002 India Assistant Professor Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Annamalai Nagar Tamil Nadu Chidambaram608002 India Professor Department of Computer Applications Annamacharya Institute of Technology & Sciences YSR Kadapa Andhra Pradesh Rajampet516115 India

ISBN: (纸本)9789819768097

Colossal pattern mining, which involves deriving important relationships and insights from large and complex datasets, is an essential part of data analysis. Extracting association rules that satisfy preset minimum support and confidence criteria from a given database is the aim of association rule mining (ARM). Nevertheless, ARM often generates an unusually large number of association rules that are hard for end users to comprehend or validate, which lessens the significance of data mining discoveries. Based on the clustering methodology, this research study presents a new mining strategy. The process begins with a method called the Expressed Data Matrix (EDM), which transforms unstructured data into a structured format and enhances the quality and organisation of the information. Primary data cleaning processes are used to eliminate noise and inconsistencies from the data in order to further improve it. To address high-dimensionality issues and boost mining productivity, dimensionality reduction—which lowers the dataset to its most valuable features—is accomplished using Eigen-Principal Component Analysis (PCA). The core of this study is the hybridised clustering approach, or GS-FFO, which combines the Fruit Fly Optimisation technique (FOA) with Glow Swarm Optimisation (GSO). This technique improves the quality of clustering and reduces the probability of local optima convergence by integrating the benefits of both approaches. The suggested GS-FFO model outperforms with four datasets, including accident, pumbs*, retail, and yeast, with an accuracy of up to 98.5%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

The necessity of machine learning in clinical emergency medicine;a narrative review of the current literature

引用

Materials Today: Proceedings 2022年 56卷 2075-2081页

作者： Rajendran, Ratchana Singirikonda, Bhagyalaxmi Navpreet Jain, Neetu Naved, Mohd Khaja Mohiddin, Md. Assistant Professor - Finance International School of Management Excellence Bengaluru India Lecturer in Computer Science Computer Science and Applications Government Degree College for Women Mahatma Gandhi University India Bk Birla College of Arts Commerce and Science Kalyan India Institute of Management and Research India Department of Business Analytics Jagannath University Delhi-NCR India Senior Assistant Professor Bhilai Institute of Technology Chhattisgarh Raipur India

Clinical databases may be categorized by medical experts as massive records that consist of massive portions of facts. These facts can include medical health sufferers and their scientific conditions. Analyzing the quantitative and qualitative medical records further to produce relationships amongst a massive variety of samples requires the use of machine learning strategies. These strategies will unveil hidden scientific know-how in phrases of correlation and affiliation of reputedly impartial variables. This review intends to focus on the use of a predictive set of rules for the prediction of trauma sufferers on admission to the health center if the medical industry wants to are expecting the vital remedy for sufferers and furnished the vital measures for the trauma sufferers who are earlier than getting into the crucial situation. Managing large data sets is a challenge for most medical systems that involve Artificial Intelligence. This study offers an overview of machine learning applications in medical medication, and specifically the ability to respond to emergencies. The relevant, recently posted research on machine learning and scientific records with a focal went through various investigation procedures. The goal of this process was to address professionals and the challenge of such approaches in clinical medicine. The effects of this look may be utilized in the prediction of trauma patient's reputations six hours after admission to the health center. © 2021

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Improving Intrusion Detection Systems using Reinforcement Learning: Responding to New Cyber Attacks and Threats

Improving Intrusion Detection Systems using Reinforcement Le...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Manoj Sethi Vishal Verma Applications Analyst Avaya LLC Irving TX United States Assistant Professor of Computer Science Government College Chhachhrauli Haryana India

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

Cyber threats are evolving quickly, making traditional intrusion detection systems (IDS) less efficient at detecting and responding to new attack vectors. Cyber attackers constantly change their tactics, making rule-based systems unable to identify new threats. Intelligent solutions are needed. This study proposes using Reinforcement Learning (RL) to improve intrusion detection systems (IDS) to detect existing attacks and dynamically adapt to new cyber threats. Our method trains RL models to identify, classify, and respond to possible intrusions in real time, learning from previous attack data and simulated scenarios. The suggested system uses RL to learn from an environment with diverse security risks, allowing the IDS to continuously adapt its threat detection tactics without manual rule generation or regular updates. RL's capacity to evaluate and respond to new attack patterns makes it more flexible and sensitive to zero-day attacks and complex persistent threats, which traditional systems miss. The research describes the RL-based IDS architecture, including reward functions to improve detection accuracy and response efficiency. A case study using the model in real-world network environments shows improved detection rates and fewer false positives than standard IDS approaches. The study also examines Q-learning and Deep Q Networks (DQN) RL algorithms to determine the best way to train the system on labelled and unlabelled network traffic. To prove the system works, detection accuracy, false positive rates, and real-time response times are examined. The results imply that RL-based intrusion detection systems can improve network security, giving a potential alternative for organisations that must adapt to new and complex cyber threats. As cyber threats evolve, this approach can be used to build proactive, adaptive IDS that can handle new attack patterns.

关键词： Training Accuracy Q-learning Computational modeling Intrusion detection Manuals Network security Real-time systems Vectors Threat assessment

来源：评论

学校读者我要写书评

暂无评论

Intelligent Agents for Crowdsourced Software Engineering : A Survey 22

Intelligent Agents for Crowdsourced Software Engineering : A...

引用

Proceedings of the 4th International Conference on Information Management & Machine Intelligence

作者： Arokiaraj S Amudha T Swamynathan R Dept. of Computer Applications Bharathiar University India Professor Dept. of Computer Applications Bharathiar University India Assistant Professor Amity Business School Amity University United Arab Emirates

ISBN: (纸本)9781450399937

Intelligent agent is software that gathers information from the dynamic environment, act autonomously and achieve the expected goals. Agents enable software components as processes that are autonomous, proactive, adaptive and heterogeneous. applications of intelligent agents are spanned across the domains and industries. This research provides a study of intelligent agent characteristics, types and applications to different fields, especially in a disrupting working model ‘Crowdsourcing’ to which organizations are moving to realize the benefit of commodification of expertise. This paper also summarizes the significance of crowdsourcing in software engineering, and outlines the objective of research aiming to address the key challenges in the quality assurance and planning in the crowdsourced software development, by defining an intelligent agent based framework.

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：