检索结果-内蒙古大学图书馆

Multi-scale Vision Transformer toward improved non-invasive anaemia detection using palm video

Multimedia Tools and Applications 2024年第38期83卷 85825-85848页

作者： Kesarwani, Abhishek Das, Sunanda Kisku, Dakshina Ranjan Dalui, Mamata Department of Computer Science and Engineering National Institute of Technology Durgapur Durgapur India

Anaemia, a condition characterised by reduced haemoglobin levels, exerts a significant global impact, affecting billions of individuals worldwide. According to data from the World Health Organisation (WHO), India exhibits notably high anaemia prevalence in comparison to other developing nations. The urgency arises for the development of non-invasive, cost-effective, and accurate anaemia screening technologies, primarily due to the substantial costs and logistical complexities associated with invasive screening methods, which impede their broad adoption on a global scale. The current endeavor aims to establish a robust anaemia detection system through the integration of cutting-edge computational methodologies with the traditional yet less precise approach of assessing haemoglobin levels based on observation of palm pallor. The proposed method employs time-domain analysis to establish a correlation between blood haemoglobin concentration and the observed changes in palm colour resulting from the application and release of pressure. This involves employing a custom device to capture and record the complete sequence of palm colour changes using a smartphone camera sensor, followed by data processing and analysis. The Multi-scale Vision Transformer is then employed to extract features from dominant frames. The approach further incorporates the application of a multi-layer perceptron (MLP) network as a regression model based on the reduced feature outcomes. The proposed system accurately estimates blood haemoglobin levels with RMSE, sensitivity, specificity, and accuracy of 0.509, 96.88%, 86.39%, and 92.59%, respectively based on 531 video samples of palm evidence. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Conditional adversarial segmentation and deep learning approach for skin lesion sub-typing from dermoscopic images

引用

Neural Computing and Applications 2024年第26期36卷 16445-16463页

作者： Mirunalini, P. Desingu, Karthik Aswatha, S. Deepika, R. Deepika, V. Jaisakthi, S.M. Department of Computer Science Engineering Sri Sivasubramaniya Nadar College of Engineering Chennai603110 India School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Chennai600127 India

Automatic skin lesion subtyping is a crucial step for diagnosing and treating skin cancer and acts as a first level diagnostic aid for medical experts. Although, in general, deep learning is very effective in image processing tasks, there are notable areas of the processing pipeline in the dermoscopic image regime that can benefit from refinement. Our work identifies two such areas for improvement. First, most benchmark dermoscopic datasets for skin cancers and lesions are highly imbalanced due to the relative rarity and commonality in the occurrence of specific lesion types. Deep learning methods tend to exhibit biased performance in favor of the majority classes with such datasets, leading to poor generalization. Second, dermoscopic images can be associated with irrelevant information in the form of skin color, hair, veins, etc.;hence, limiting the information available to a neural network by retaining only relevant portions of an input image has been successful in prompting the network towards learning task-relevant features and thereby improving its performance. Hence, this research work augments the skin lesion characterization pipeline in the following ways. First, it balances the dataset to overcome sample size biases. Two balancing methods, synthetic minority oversampling TEchnique (SMOTE) and Reweighting, are applied, compared, and analyzed. Second, a lesion segmentation stage is introduced before classification, in addition to a preprocessing stage, to retain only the region of interest. A baseline segmentation approach based on Bi-Directional ConvLSTM U-Net is improved using conditional adversarial training for enhanced segmentation performance. Finally, the classification stage is implemented using EfficientNets, where the B2 variant is used to benchmark and choose between the balancing and segmentation techniques, and the architecture is then scaled through to B7 to analyze the performance boost in lesion classification. From these experiments, we find

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Routing Protocol in Flying Ad Hoc Networks: A Review

引用

computers, Materials & Continua 2025年第2期82卷 1615-1643页

作者： Priyanka Manjit Kaur Deepak Prashar Leo Mrsic Arfat Ahmad Khan Department of Computer Science and Engineering(CSE) Lovely Professional UniversityPhagwara144411India Department for Program Engineering Algebra UniversityGradiscanska 24Zagreb10000Croatia Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand

“Flying Ad Hoc Networks(FANETs)”,which use“Unmanned Aerial Vehicles(UAVs)”,are developing as a critical mechanism for numerous applications,such as military operations and civilian *** dynamic nature of FANETs,with high mobility,quick node migration,and frequent topology changes,presents substantial hurdles for routing protocol *** the preceding few years,researchers have found that machine learning gives productive solutions in routing while preserving the nature of FANET,which is topology change and high *** paper reviews current research on routing protocols and Machine Learning(ML)approaches applied to FANETs,emphasizing developments between 2021 and *** research uses the PRISMA approach to sift through the literature,filtering results from the SCOPUS database to find 82 relevant *** research study uses machine learning-based routing algorithms to beat the issues of high mobility,dynamic topologies,and intermittent connection in *** compared with conventional routing,it gives an energy-efficient and fast decision-making solution in a real-time environment,with greater fault tolerance *** protocols aim to increase routing efficiency,flexibility,and network stability using ML’s predictive and adaptive *** comprehensive review seeks to integrate existing information,offer novel integration approaches,and recommend future research topics for improving routing efficiency and flexibility in ***,the study highlights emerging trends in ML integration,discusses challenges faced during the review,and discusses overcoming these hurdles in future research.

关键词： FANET protocol machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing VANET communication using squid game optimization based energy aware clustering approach

引用

International Journal of Information Technology (Singapore) 2024年第8期16卷 5389-5394页

作者： Rajakumar, R. Suresh, T. Sekar, K. Department of Computer Science and Engineering Annamalai University Chidambaram India Department of Computer Science and Engineering Chadalawada Ramanamma Engineering College Tirupati India

Vehicular Ad-Hoc Networks (VANETs) are studied wireless networks that enable communication among vehicles and roadside infrastructure. The role a vital play in improving on-road safety, efficacy, and convenience by enabling real-time data interchange for controlling traffic, infotainment services, and collision avoidance. Energy efficiency in VANETs is vital because of the restricted power resources of vehicles. Methods like clustering, vehicles are categorized into groups to decrease communication overhead, and meta-heuristic approaches that optimize network performance by intelligent problem-solving approaches are deployed to exploit energy efficiency while preserving network reliability and responsiveness. These methodologies contribute to the effective implementation of VANETs, ensuring sustainable and dependable communication in dynamic vehicular environments. In this study, a new Squid Game Optimization based Energy Aware Clustering Approach (SGO-EACA) technique for VANET is introduced. The goal of the SGO-EACA technique is to optimally choose the cluster heads (CHs) and produce clusters in the VANET in such a way as to realize energy efficiency. In the SGO-EACA technique, the concept of typical Korean sport is used where the attackers try to achieve their goal, but players try to eliminate each other. Moreover, the SGO-EACA approach derives a fitness function (FF) containing multiple metrics such as Residual Energy (RE), Trust Level, Degree Difference, Total Energy consumption, Distance to Base Station (DBS), and Mobility. The simulation values exposed that the SGO-EACA approach surpassed earlier state-of-the-art approaches with respect to various aspects. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Cluster head Energy efficiency Fitness function Squid game optimization VANET Vehicle to vehicle

来源：评论

学校读者我要写书评

暂无评论

ALCTS—An Assistive Learning and Communicative Tool for Speech and Hearing Impaired Students

引用

computers, Materials & Continua 2025年第5期83卷 2599-2617页

作者： Shabana Ziyad Puthu Vedu Wafaa A.Ghonaim Naglaa M.Mostafa Pradeep Kumar Singh Computer Science Department College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl Kharj11942Saudi Arabia Faculty of Science Al-Azhar UniversityCairo12111Egypt Department of Mathematics Faculty of ScienceAl-Azhar University(Girl’s Branch)Cairo12111Egypt Department of Computer Science and Engineering Central University of JammuJammu and Kashmir181143India

Hearing and Speech impairment can be congenital or *** and speech-impaired students often hesitate to pursue higher education in reputable institutions due to their ***,the development of automated assistive learning tools within the educational field has empowered disabled students to pursue higher education in any field of *** learning devices enable students to access institutional resources and facilities *** proposed assistive learning and communication tool allows hearing and speech-impaired students to interact productively with their teachers and *** tool converts the audio signals into sign language videos for the speech and hearing-impaired to follow and converts the sign language to text format for the teachers to *** educational tool for the speech and hearing-impaired is implemented by customized deep learning models such as Convolution neural networks(CNN),Residual neural Networks(ResNet),and stacked Long short-term memory(LSTM)network *** assistive learning tool is a novel framework that interprets the static and dynamic gesture actions in American Sign Language(ASL).Such communicative tools empower the speech and hearing impaired to communicate effectively in a classroom environment and foster *** deep learning models were developed and experimentally evaluated with the standard performance *** model exhibits an accuracy of 99.7% for all static gesture classification and 99% for specific vocabulary of gesture action *** two-way communicative and educational tool encourages social inclusion and a promising career for disabled students.

关键词： Sign language recognition system ASL dynamic gestures facial key points CNN LSTM ResNet

来源：评论

学校读者我要写书评

暂无评论

A Transfer Function Design for Medical Volume Data Using a Knowledge Database Based on Deep Image and Primitive Intensity Profile Features Retrieval

引用

Journal of computer science & Technology 2024年第2期39卷 320-335页

作者： Younhyun Jung Jim Kong 盛斌 Jinman Kim School of Computing Gachon UniversitySeongnam 13120Korea School of Computer Science The University of SydneySydney 2006Australia Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China

Direct volume rendering(DVR)is a technique that emphasizes structures of interest(SOIs)within a volume visually,while simultaneously depicting adjacent regional information,e.g.,the spatial location of a structure concerning its *** DVR,transfer function(TF)plays a key role by enabling accurate identification of SOIs interactively as well as ensuring appropriate visibility of *** generation typically involves non-intuitive trial-and-error optimization of rendering parameters,which is time-consuming and *** at mitigating this manual process have led to approaches that make use of a knowledge database consisting of pre-designed TFs by domain *** these approaches,a user navigates the knowledge database to find the most suitable pre-designed TF for their input volume to visualize the *** these approaches potentially reduce the workload to generate the TFs,they,however,require manual TF navigation of the knowledge database,as well as the likely fine tuning of the selected TF to suit the *** this work,we propose a TF design approach,CBR-TF,where we introduce a new content-based retrieval(CBR)method to automatically navigate the knowledge *** of pre-designed TFs,our knowledge database contains volumes with SOI *** an input volume,our CBR-TF approach retrieves relevant volumes(with SOI labels)from the knowledge database;the retrieved labels are then used to generate and optimize TFs of the *** approach largely reduces manual TF navigation and fine *** our CBR-TF approach,we introduce a novel volumetric image feature which includes both a local primitive intensity profile along the SOIs and regional spatial semantics available from the co-planar images to the *** the regional spatial semantics,we adopt a convolutional neural network to obtain high-level image feature *** the intensity profile,we extend the dynamic time warping technique to address subtle alignment

关键词： data retrieval direct volume rendering ray analysis transfer function

来源：评论

学校读者我要写书评

暂无评论

A Voice Assistive Mobile Application Tool to Detect Cardiovascular Disease Using Machine Learning Approach

引用

Biomedical Materials and Devices 2024年第2期2卷 1246-1257页

作者： Uddin, Khandaker Mohammad Mohi Dey, Samrat Kumar Babu, Hafiz Md. Hasan Department of Computer Science and Engineering Southeast University School of Science and Technology Bangladesh Open University Department of Computer Science and Engineering University of Dhaka

Many people all around the world suffer from heart disease, which is regarded as a severe illness. In healthcare, especially cardiology, it is crucial to accurately and quickly diagnose cardiac problems. In this research, we proposed an accurate and efficient mobile application-based system for diagnosing cardiac disease based on machine learning approaches. The developed mobile application is voice assistive, which makes the proposed application more user-friendly. Numerous machine learning methods have been examined in this study to predict and diagnose cardiovascular disease (CVD). A detailed comparative study was also drawn using eighteen (18) classification algorithms such as Support Vector Machines, Logistic Regression, Linear SVC, K-Nearest Neighbors, Naive Bayes, Stochastic Gradient Descent, Gradient Boosting, Ridge, Bagging, Random Forest, Decision Tree, XGB, LGBM, Extra Trees Perceptron, and Voting Classifier (hard or soft voting). Sixty-eight thousand nine hundred seventy-five (68,975) samples from various patients were used to test the performance of each approach. According to the study, Random Forest and Decision Trees have the best accuracy levels at 99.9%. However, the Support Vector Machine classifier had the lowest performance, barely achieving 60% accuracy. © The Author(s), under exclusive licence to Springer science+Business Media, LLC 2024.

关键词： Cardiovascular heart disease Detection Healthcare informatics Machine learning Mobile application

来源：评论

学校读者我要写书评

暂无评论

Community detection of trajectory data for location-based facility recommendation system

引用

International Journal of Information and Communication Technology 2024年第2期25卷 101-117页

作者： Sabarish, B.A. Karthi, R. Kumar, T. Gireesh Department of Computer Science and Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India

Trajectory contains spatial-data generated from traces of moving objects like people, animals, etc. Community generated from trajectories portrays common behaviour. Trajectory clustering based on community-detection involves region-graph generation and community-detection. In region-graph generation, trajectories are projected to spatial grid to transform GPS representation into string representation. Sequential graph is generated from string representation. Edge-based similarity is calculated between trajectories to create an adjacency matrix representing relationship and represent entire region. In community-detection phase, region-graph is divided into communities using various algorithms and validated using modularity values. Based on analysis, Louvain, fast-greedy, leading-eigenvector, and edge-betweenness algorithms provide the optimum modularity value for better community detection. Analysing the community can be used as a pre-processing step in identifying location for location-based services (LBS), including hotspots, delay-tolerant-networks, and mobile antenna placements for better coverage. Design and capacity planning of the network based on the size and pattern of the community improves quality of LBS. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Language Translator Using Python 1

Language Translator Using Python

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Raj, Mayank Devang, Ashish Chanchal, Satya Saini, Kavita Galgotias University School of Computer Science and Engineering Department of Computer Science and Engineering India

ISBN: (纸本)9798350356816

The most well-known type of correspondence between people is Discourse and correspondence assumes a vital part for conveying data. The truth of the matter is that each specific person on the planet won't discuss the same language, numerous people will be communicating in various dialects. Summing up the required content is particularly vital to conveying the right message. On the off chance that the data required isn't conveyed appropriately then numerous entanglements might happen. If either side of the imparting people is uninformed about the language, then the pattern of discourse will be deficient. Thus, we want a framework that will settle our language obstruction issue. So, we concocted a framework for example "Language Convertor utilizing Python"which will change over discourse of one language into another dialect utilizing Python. project intends to foster a flexible and easy-to-use instrument that can consistently interpret text between different dialects. This undertaking uses the force of Python, alongside famous libraries like Google Decipher Programming interface or DeepL API, to make a proficient language change device. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

An Improved Gannet Optimization Algorithm Based on Opposition-Based Schemes for Feature Selection Problems in High-Dimensional Datasets

引用

SN computer science 2024年第1期5卷 183页

作者： Avinash, N. Sinha, Sitesh Kumar Shivamurthaiah, M. Department of computer science and engineering Rabindranath tagore university Bhopal India Department of Computer Science and Engineering APS College of Engineering Bangalore India

In the ever-evolving landscape of optimization algorithms for healthcare datasets, this study introduces an innovative fusion of the gannet optimization algorithm (GOA) with advanced opposition-based learning (OBL) techniques, including quasi-OBL, generalized OBL, and partial OBL. The primary novelty of our approach lies in the hybridization of GOA with OBL schemes. While GOA itself draws inspiration from the hunting behavior of gannets, OBL techniques introduce a layer of opposition-based learning that mimics the dialectical nature of opposing forces. By integrating these two distinct paradigms, we create a symbiotic relationship between exploration and exploitation. This synergy empowers our optimization framework to dynamically adapt to the complex landscape of high-dimensional healthcare datasets, underlining its prowess in classification tasks, particularly when employed with support vector machine (SVM) and k-nearest neighbor (KNN) classifiers. Statistical validation further underscores the significance of our results. The p value analysis reveals that our GOBL–GOA approach stands as a statistically superior alternative, making substantial strides in feature selection and classification accuracy. Beyond statistics, our approach excels in practicality, effectively identifying and selecting relevant features to provide accurate insights from complex healthcare data, as demonstrated by precision, recall, and F1-score metrics. In conclusion, our study not only introduces a paradigm shift in feature selection and optimization but also advances the cause of precise disease detection and prognosis, holding immense potential to enhance healthcare outcomes globally. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Feature selection Gannet optimization algorithm High-dimensional dataset Opposition-based learning

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：