检索结果-内蒙古大学图书馆

Deep Learning Technique Based State-Of-The-Art in Skin Cancer Detection: A Review

Journal of Mobile Multimedia 2023年第6期19卷 1583-1606页

作者： Srilakshmi, C.H. Lydia, E. Laxmi Ramakrishnaiah, N. Department of Information Technology Malla Reddy Engineering College for Women Telangana India Department of Computer Science and Engineering Vignan’s Institute of Information Technology Visakhapatnam India Department of CSE University College of Engineering JNTU Andhra Pradesh Kakinada India

Research of skin cancer images through visual survey and manual evaluation to investigate skin threatening development has always been abnormal. This manual evaluation of skin injuries to recognize melanoma is monotonous as well as somewhat long. With movement in advancement and fast development in computational resources, different AI techniques and significant learning methods have emerged for assessment of clinical pictures most especially the skin lesion images. In late years, AI arising as an innovation equipped for tackling issues connected with horticulture, medical services, business, and soon. To diminish the endanger to human existence we can embrace AI calculations in the medical care area and can foresee the deadliest skin illnesses like dangerous melanoma in beginning phases. The point of the research is to give bits of knowledge about various classifications of skin lesions and strategies executed to arrange and foresee skin diseases and the job of dermatologists while fostering the models, at last gives a general rundown of existing work. © 2023 River Publishers.

关键词： machine learning algorithms malignant melanoma skin cancers Skin lesion

来源：评论

学校读者我要写书评

暂无评论

AssignExpert - Host and Grade Programming Assignments in Educational Institutions 14

AssignExpert - Host and Grade Programming Assignments in Edu...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Chankhore, Neha Jatti, Ashwini Nathani, Vivek Desai, Varda Malkan, Ronak Tattikota, Nikhil Symbiosis Institute of Technology Computer Science and Engineering Department Pune India Symbiosis Institute of Technology Information Technology Department Pune India

ISBN: (纸本)9798350335095

AssignExpert is created using *** and runs Docker under the hood to sandbox the execution of user-submitted programs. The platform allows faculties and students to sign up with their employee or student roll numbers. Faculties can create a class and give assignments with a deadline. Students can join a class and see the assignments. The assignment page is bundled with a code editor, using which the assignment can be submitted. Faculties have the option to reveal the points scored or defer this action to a later period of time. This paper further describes the theoretical and practical motivations for all the design and implementation decisions. The code for the platform is open-source and is available on GitHub. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Vehicular Ad Hoc Network performance enhancement using VOA based Road Side Unit Deployment 3

Vehicular Ad Hoc Network performance enhancement using VOA b...

引用

3rd International Conference on Intelligent Computing, Instrumentation and Control Technologies, ICICICT 2022

作者： Sharma, Ayushi Pandey, Kavita Jaypee Institute of Information Technology Department of Computer Science & Engineering and Information Technology Noida India

ISBN: (数字)9781665410052

ISBN: (纸本)9781665410052

Road side unit (RSU) is the key element in VANET architecture. It is used to improve communication range, driving awareness, traffic safety, signal acknowledgement and violation. However, VANET faces major challenges in RSU deployment. To achieve the objectives of RSU deployment problem i.e. minimizing the cost of deployment and maximizing network coverage;swarm intelligence algorithm have been used in the literature. In our work, Virus optimization algorithm (VOA) has been applied on VANET to generate optimal solutions and is compared with swarm family algorithms such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). The outcome generated shows the expertise of the suggested algorithm i.e. VOA in terms of optimal RSU deployment and also on various performance metrics like overlapping rate, average transmission time and network connectivity. © 2022 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Sentimental Analysis of COVID-19 Twitter Data Using Machine Learning 8th

Sentimental Analysis of COVID-19 Twitter Data Using Machine ...

引用

8th International Conference on Emerging Research in Computing, information, Communication and Applications, ERCICA 2023

作者： Likhith, S.R. Pooja Ahuja, S. Prathibha, B.N. Uma Shankari, B. Department of School of Computer Science and Engineering and Information Science Bio-Intelligence Lab Presidency University Bengaluru India Nagarjuna College of Engineering and Technology Bengaluru India Nagarjuna College of Engineering and Technology Bengaluru India

ISBN: (纸本)9789819976218

Corona virus is considered as a scourge all over world by which most of the people got infected. Since the virus was spreading very quickly governments had to bring in very tough rules such as lock down. Lock down disrupted almost all sector like education, business etc.… During lock down and after the lock down people have used social media as their platform to express the opining regarding the pandemic. Tweeter is one such social media where people had shared their thoughts on the pandemic. In this study tweets which are made by the public is considered to analyses the sentiments. And in this research machine learning models are used to classify the data into five different classes namely positive, negative, neutral, extremely positive, and extremely negative. Decision Tree, Random Forest, Support Vector Machine, Logistic Regression, and Naïve Bayes are the ML models used to classify the sentiment and are achieving on accuracy of 99%, 99%, 97%, 94%, and 73%, respectively. Further precision, recall, F1-score, and world clod are calculated for each and every class. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： COVID-19 Decision tree Logistic regression ML Naïve Bayes Random forest Sentiment analysis SVM Tweets

来源：评论

学校读者我要写书评

暂无评论

Administration of Digital Identities Using Blockchain 5

Administration of Digital Identities Using Blockchain

引用

5th International Conference on Contemporary Computing and Informatics, IC3I 2022

作者： Kumar, Shipra Ravi Goyal, Mukta Jaypee Institute of Information Technology Department of Computer Science Engineering and Information Technology Noida India

ISBN: (纸本)9798350398267

Since the last two decades, the problem of check theft and the data breaches from centralized systems has gotten worse. In this study, we looked at how blockchain technology is employed in identification systems and how it may be applied to verify an identity's veracity and legitimacy. The drawbacks of the conventional identification systems were examined in depth, and the advantages of using a Blockchain-based identity system were discussed, including the removal of the middleman and the need for long wait times for verification, authorization, and attestation. Nobody can alter their identification data because the nodes in a blockchain are supposed to be immutable, and because asymmetric cryptography is utilized while sharing data, personal information is kept secure. We were able to effectively establish an identity wallet-a node in a chain on the Ethereum platform-and test a self-sovereign identification system for a single person. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

UPMatch: Enhancing Semi-Supervised Medical Image Classification through Contrastive Learning with Unreliable Pseudo Labels 46

UPMatch: Enhancing Semi-Supervised Medical Image Classificat...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Hu, Jihong Li, Yinhao Lin, Lanfen Chen, Yen-Wei Ritsumeikan University The Graduate School of Information Science and Engineering Osaka Japan Ritsumeikan University The College of Information Science and Engineering Osaka Japan Zhejiang University The College of Computer Science and Technology Hangzhou China

ISBN: (纸本)9798350371499

Pseudo-labeling based semi-supervised learning (SSL) framework has proven highly successful in medical image analysis (MIA) by addressing the problem of a shortage of labeled samples. However, the existing SSL methods use a fixed or flexible confidence threshold to filter reliable samples, leaving large number of unlabeled samples unused. This is a more serious issue in MIA because of the low inter-class distance and imbalanced categories. We argue that effectively mining useful information hidden in ambiguous unlabeled sample is the key to improve model performance, so we propose UPmatch, a new pseudo labeling-based SSL framework. Our framework introduces a contrastive unreliable pseudo label learning module (CUPM) that incorporates unreliable pseudo label samples into the training process. Additionally, we propose an informative sample selection strategy (ISSS) that selects samples used in contrastive learning iteratively in each mini-batch. Our experiments on TissueMNIST and ISIC2019 dataset with various training settings demonstrate the effectiveness of our proposed strategy. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimized Feature Selection and Machine Learning for Accurate Celiac Disease Diagnosis with Model Interpretability

Biomedical Materials and Devices

引用

Biomedical Materials and Devices 2025年 1-22页

作者： Chowdhury, Abir Druvo, Md Mahbubur Rahman Uddin, Khandaker Mohammad Mohi Islam, Md.Shariful Uddin, Md Ashraf Department of Computer Science and Engineering Dhaka International University Dhaka 1205 Bangladesh Department of Computer Science and Engineering Southeast University Dhaka International University Dhaka 1208 Bangladesh School of Information and Technology Deakin University Geelong Warun Ponds Australia

Celiac disease is a chronic autoimmune illness caused by gluten consumption that affects millions worldwide. Accurate diagnosis is critical for optimal care but traditional approaches frequently lack precision. The proposed work uses machine learning approaches to improve diagnostic accuracy on a dataset that includes clinical and laboratory variables. Preprocessing the data involved firstly scaling and encoding the categorical values. Then, selecting the important features using the recursive feature elimination (RFE) with an extra tree classifier (ETC) (RFE + ETC) and assessing the five machine learning models KNN, GNB, MNB, BNB, and QDA were important procedures. KNN outperformed the others, achieving 99.49% accuracy, 99.36% precision, 100% recall, and an AUC of 99.98% on the selected feature. Furthermore, the study integrated the findings into a web application to aid in real-time diagnostic decision-making, assuring clinical applicability. This study emphasizes the necessity of strong feature selection and advanced machine learning approaches in improving celiac disease diagnosis and therapy. Shapley additive explanations (SHAP) were finally incorporated for interpretability, providing details on different variables affect model predictions. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Celiac disease Interpretability KNN Machine learning RFE + ETC SHAP Web application

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Probabilistic Elastic Net Regression Model (EPERM) for Heart Disease Prediction

An Enhanced Probabilistic Elastic Net Regression Model (EPER...

引用

2024 International Conference on Future Technologies for Smart Society, ICFTSS 2024

作者： Selvi, Vennira Kumar, T.Ganesh Shajilin Loret, J.B. Kumar, K.Sampath Julian, Anitha Rishi, Priti Presidency University School of Cse and Information Science Bangalore India Galgotias University School of Computer Science and Engineering Greater Noida India Francis Xavier Engineering College Department of Information Technology Tirunelveli India Amet University Department of Computer Science and Engineering Chennai India Saveetha Engineering College Department of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Department of Electronics and Communication Engineering Vadaplani Campus India

ISBN: (纸本)9798350373844

Heart attack prediction is a significant contributor to worldwide morbidity. Cardiovascular illness is a critical component of clinical data analysis prediction. A precise diagnosis of cardiac disease can save lives, yet an inaccurate diagnosis can lead to death. To predict heart disease prior, an Enhanced Probabilistic Elastic Net Regression model (EPERM) is presented, which is utilized to classify cardiac disease, and every feature selection is based on correlation with the goal value. The Attribute Ranking Method was used to select and organize highly positive associated attributes based on their weight. Finally, conditional probability is utilized to estimate the likelihood of cardiac disease in advance. This study makes use of one of the largest disease-related databases. Regarding projected illness progression, the suggested algorithm outperforms the most recent techniques. The findings also demonstrate how a patient's disease sequence may alter their risk management in the future. Our prediction model, based on Elastic Net Regression and data analysis, discovered several traits that clinical knowledge had previously overlooked. This article investigates clinical diagnostic records from the past decade to identify probable heart cancer symptoms and comorbidities. It also provides early disease prediction, allowing a greater number of patients to receive an early diagnosis. The suggested model accurately predicts evidence of a person's heart illness using Probability-based Elastic Net Regression. The results show that the technique is a reliable and consistent prediction model. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Evidential Open Set Recognition for Imbalanced Medical Images via Multi-level Data Augmentation

Evidential Open Set Recognition for Imbalanced Medical Image...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhao, Rui-Wei Xu, Yiqian Zhang, Ying Feng, Rui Shanghai Maritime University College of Information Engineering China Fudan University Academy for Engineering and Technology China Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)9798350386226

Due to the exstence of common and rare diseases, the complex clinical scenario often poses the challenging class imbalanced open set recognition problem. Unfortunately, most existing approaches are ill-suited for such situations with limited and imbalanced data during training and the possibility of encountering unseen classes during test. In this work, we propose a novel Multi-level mixup-based Evidential Open Set Recognition (ME-OSR) approach to more explicitly and effectively address the open set recognition for class-imbalanced medical images. Briefly, we first extract disentangled discriminative and background image features. Then, based on the original images and extracted features, we propose to sample and conduct Multi-level Open Mixup (MOM) for a more balanced open set data augmentation. It includes extensive intra- and interclass mixup operations in both image and feature spaces, which can augment rare classes with different feature combinations and generate potential pseudo-unknown class examples in the open set to boost the model training. Based on the augmented data and their extracted discriminative features, we propose a Regularized Evidential Deep Learning (REDL) classifier to work with the augmented data to achieve open set recognition with prediction uncertainty estimation and unknown example rejection. Through comparative experiments and ablation studies on several representative medical datasets, we showed that our proposed method outperforms other state-of-the-arts on four popular medical OSR datasets. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Spatio–Temporal Constrained Geomagnetic Indoor Localization With Arbitrary Walking Speed

引用

IEEE Internet of Things Journal 2025年第12期12卷 21740-21756页

作者： Liu, Ning Peng, Gezhi Ling, Hua-Bao Niu, Qun He, Tao Sun Yat-sen University School of Computer Science and Engineering Guangdong Key Laboratory of Information Security Technology Guangzhou510006 China Sun Yat-sen University School of Artificial Intelligence Zhuhai519000 China

This article focuses on the accuracy and practicality of geomagnetic-based indoor localization in large-scale real-world sites. Previous studies often use continuous geomagnetic sequences for better discriminability but ignore that longer sequences, while more accurate, increase response times. Shorter sequences enhance practicality but sacrifice accuracy. Additionally, varying walking speeds can cause sequence variations along the same path, leading to ambiguity. To address these challenges, we propose a spatial–temporal constrained indoor localization model (STC-loc) that enables both accurate and practical localization using geomagnetic sequences collected at arbitrary walking speeds. Specifically, we first design a speedoriented adaptive normalization module to tackle the walking speed heterogeneity problem. Then, to balance accuracy and practicality, we initially employ shorter sequences as input and a self-attention hierarchical structure to efficiently extract the temporal features for initial location estimation. Subsequently, we further apply an encoder–decoder-based refinement strategy, leveraging spatial contextual for continuous localization to ensure accuracy and robustness. Additionally, a slide-window-based twophase system architecture optimizes processing efficiency and scalability. Experiments on three large-scale real-world sites have demonstrated the superiority of the proposed STC-loc, reducing the localization error by more than 43% with shorter geomagnetic sequences. © 2014 IEEE.

关键词： Geomagnetism

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：