检索结果-内蒙古大学图书馆

3rd International Conference on Trends in Electrical, Electronics and Computer Engineering, TEECCON 2024

作者： Tembhurnikar, Atharv Sarvankar, Girish Yadav, Gitanjali Vaidya, Rohan Shelar, Aditya Bhage, Kartik Vishwakarma Institute of Information Technology Dept. of Artificial Intelligence and Data Science Pune India

ISBN: (纸本)9798331505714

Poor form is a primary contributor to exercise-related accidents, which can result in permanent physical handicap and deter people from maintaining a regular fitness regimen. This study suggests FitTip, an intelligent posture identification and correction device that uses computer vision and machine learning, as a means of preventing these kinds of injuries. Using a proprietary dataset of yoga and gym routines, we developed a convolutional neural network (CNN) integrated with the Mediapipe framework to accurately categorize and correct workout positions in real time. Position analysis is used in FitTip' s design to provide real-time feedback and change recommendations. The algorithm was evaluated on a dataset of five workout poses, and the results indicated that it could get 98.73% training and validation accuracy. These findings show how well algorithm works to improve overall fitness results and workout safety. The suggested algorithm offers a framework that is scalable for enhancing posture during activity, and it may eventually be integrated with wearables and fitness applications. It includes a real-time camera feed for pose detection, a key-point detection module, and a feedback algorithm that suggests corrections based on the angles between body joints. This paper also addresses challenges such as limited dataset size and variability in user movements, proposing solutions through enhanced preprocessing and pose analysis techniques. FitTip algorithm makes training safer and more accessible for people of all fitness levels, which adds to the expanding field of fitness technology. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Solving Multi-Objective Vehicle Routing Problems with Time Windows: A Decomposition-Based Multiform Optimization Approach

引用

Tsinghua science and technology 2024年第2期29卷 305-324页

作者： Yiqiao Cai Zifan Lin Meiqin Cheng Peizhong Liu Ying Zhou Xiamen Key Laboratory of Data Security and Blockchain Technology College of Computer Science and TechnologyHuaqiao UniversityXiamen361021China College of Engineering Huaqiao UniversityQuanzhou362000China School of Computer Sciences Shenzhen Institute of Information TechnologyShenzhen518000China

In solving multi-objective vehicle routing problems with time windows (MOVRPTW),most existing algorithms focus on the optimization of a single problem formulation. However,little effort has been devoted to exploiting valuable knowledge from the alternate formulations of MOVRPTW for better optimization performance. Aiming at this insufficiency,this study proposes a decomposition-based multi-objective multiform evolutionary algorithm (MMFEA/D),which performs the evolutionary search on multiple alternate formulations of MOVRPTW simultaneously to complement each other. In particular,the main characteristics of MMFEA/D are three folds. First,a multiform construction (MFC) strategy is adopted to construct multiple alternate formulations,each of which is formulated by grouping several adjacent subproblems based on the decomposition of MOVRPTW. Second,a transfer reproduction (TFR) mechanism is designed to generate offspring for each formulation via transferring promising solutions from other formulations,making that the useful traits captured from different formulations can be shared and leveraged to guide the evolutionary search. Third,an adaptive local search (ALS) strategy is developed to invest search effort on different alternate formulations as per their usefulness for MOVRPTW,thus facilitating the efficient allocation of computational resources. Experimental studies have demonstrated the superior performance of MMFEA/D on the classical Solomon instances and the real-world instances.

关键词： MOVRPTW multiform optimization multiform construction knowledge transfer adaptive local search

来源：评论

学校读者我要写书评

暂无评论

Age-of-information-Aware Federated Learning

引用

Journal of Computer science & technology 2024年第3期39卷 637-653页

作者：徐殷肖明军吴晨吴杰周津锐孙贺 Student Member CCF 1.School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230026China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhou 215123China School of Data Science University of Science and Technology of ChinaHefei 230026China Department of Computer and Information Sciences Temple UniversityPhiladelphiaPA 19122U.S.A. CCF IEEE

Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private datasets to the central *** most existing research where the local datasets of clients are assumed to be unchanged over time throughout the whole FL process,our study addresses such scenarios in this paper where clients’datasets need to be updated periodically,and the server can incentivize clients to employ as fresh as possible datasets for local model *** primary objective is to design a client selection strategy to minimize the loss of the global model for FL loss within a constrained *** this end,we introduce the concept of“Age of information”(AoI)to quantitatively assess the freshness of local datasets and conduct a theoretical analysis of the convergence bound in our AoI-aware FL *** on the convergence bound,we further formulate our problem as a restless multi-armed bandit(RMAB)***,we relax the RMAB problem and apply the Lagrangian Dual approach to decouple it into multiple ***,we propose a Whittle’s Index Based Client Selection(WICS)algorithm to determine the set of selected *** addition,comprehensive simulations substantiate that the proposed algorithm can effectively reduce training loss and enhance the learning accuracy compared with some state-of-the-art methods.

关键词： federated learning Age of information restless multi-armed bandit Whittle’s index

来源：评论

学校读者我要写书评

暂无评论

Leveraging Blockchain for Development of Time Limit-Based Multi-authorized Secure Digital Signature Framework 5th

Leveraging Blockchain for Development of Time Limit-Based Mu...

引用

5th International Conference on Advances in information Communication technology and Computing, AICTC 2024

作者： Mallikharjuna Rao, K. Kumar, Ashutosh Agrawal, Deepesh Reyya, Shikhar Data Science and Artificial Intelligence International Institute of Information Technology Naya Raipur Naya Raipur India Computer Science and Engineering International Institute of Information Technology Naya Raipur Naya Raipur India

ISBN: (纸本)9789819761050

This article deeply dives into a shift in document security by introducing innovative authentication measures. Conventional digital signature methods are less secure and can easily be forged. Our research explores the integration of multiple signatures authentication and time-constrained signature features, which will boost the security of digital signatures across documents;by introducing a time-constrained signing approach, we are addressing potential issues and establishing robust defense against various threats. Also, multiple files can be uploaded using a single CID in interplanetary file system (IPFS). Besides introducing multiple signers and time-limit features, our research utilizes IPFS for secure and collaborative document management. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

CONSTRUCTING ERGODIC NETWORKS USING DISCRETE MARKOV CHAINS 51

CONSTRUCTING ERGODIC NETWORKS USING DISCRETE MARKOV CHAINS

引用

51st International Conference on Computers and Industrial Engineering, CIE 2024

作者： Ohba, H. Sadakuni, S. Matsuda, T. Mizuno, S. Faculty of Health Data Science Juntendo University Chiba Japan Faculty of Information Technology Kanagawa Institute of Technology Kanagawa Japan Department of Information Design Shizuoka Institute of Science and Technology Shizuoka Japan

In a region's tourism strategy, connecting famous locations to surrounding areas can stimulate activity throughout the region. Connections between locations can be established by identifying the central locations in the area and creating routes from them to other locations. This study proposes an algorithm to obtain ergodicity in discrete Markov chains by utilizing network centrality measures. The number of calculations to obtain ergodicity was compared using several definitions of network centrality, enabling the selection of an appropriate network centrality measure for the target network. The proposed method identifies the central locations within the network and determines the necessary adjustments to transition probabilities between locations to achieve ergodicity. If the location network holds ergodicity, a stationary distribution of the Markov chain exists and optimization applications are expected. Numerical calculations were used to demonstrate the method's applicability to various networks. Furthermore, using a Wi-Fi log, we observed that the proposed method can reconstruct a network with ergodicity for networks that use access points as locations, indicating the social applicability of the proposed method. The proposed method can be used to analyze various networks in modern society, such as facility operations and tourism stimulation. In facility operations, this method can be applied to manage human traffic and analyze stay duration. To promote tourism, by considering tourist sites as network locations, the method clarifies which routes should be prioritized to construct an uninterrupted tourist network, making the construction and operation of an extensive tourist network possible. © 2024 Computers and Industrial Engineering. All rights reserved.

关键词： Equivalence classes

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Classification using Machine Learning Algorithm

Breast Cancer Classification using Machine Learning Algorith...

引用

2024 International Conference on Knowledge Engineering and Communication Systems, ICKECS 2024

作者： Anu, D. Vidhya, K. Nitte Meenakshi Institute of Technology Artificial Intelligence & Data Science Bangalore India East West Institute of Technology Information Science & Engg Bangalore India

ISBN: (纸本)9798350359688

Around the globe in this era breast cancer is the most common disease among women, previously detection of breast cancer was a long and tedious process. In the proposed system the patient's data set will be collected. The collected data set will be manipulated and cleaned using feature extraction process [1]. The data set attributes consist of the nuclei measurements information. Nuclei measurements include radius, texture, perimeter etc. Also, the data set has the information whether the women breast does have the cancer or not by means of already calculated data which is indicated as benign or malignant. Benign are the non-cancerous tumor cell and that does not invade the neighboring cell, but malignant are the cancercausing tumor and it invades the neighbor cell after the manipulation and feature extraction of the data, it is further processed by machine learning algorithms under neural network. The dataset will be split into dependent and independent data. Dependent data are the data expect id and diagnosis, where the independent are diagnosis data [2]. The split data is 75% of training data and 25 % is testing data. Then scale the data (feature scaling) to bring the training data to a particular range of 0 to 1. The logistic regression is a part of machine learning algorithm which is a subset of random forest classifier, confusion matrix, SVM classifier, KNN classifiers are made used for both training and testing the data set. With the result the accuracy will be calculated [3]. The highest accuracy method will be chosen and the result data and original data will be compare to find the accurate result that whether the women does have the cancer or not. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Fine extraction of multi-crop planting area based on deep learning with Sentinel- 2 time-series data

引用

Environmental science and Pollution Research 2025年第19期32卷 11931-11949页

作者： Jiang, Jingmin Zhang, Jiahua Wang, Xue Zhang, Shichao Kong, Delong Wang, Xiaopeng Ali, Shawkat Ullah, Hidayat Space Information and Big Earth Data Research Center School of Computer Science and Technology Qingdao University Qingdao266071 China Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China

Accurate and timely access to the spatial distribution of crops is crucial for sustainable agricultural development and food security. However, extracting multi-crop areas based on high-resolution time-series data and deep learning still faces challenges. Therefore, this study aims to provide an effective model for multi-crop classification using high-resolution remote sensing time-series data. We designed two deep learning models based on convolutional neural network-long short-term memory (CNN-LSTM) and bidirectional long short-term memory (Bi-LSTM). The monthly synthetic time series of the normalized difference vegetation index (NDVI) from Sentinel-2 data will be used as input features to extract the multi-crop planting area in Shandong province’s northwestern, southwestern, and eastern regions. The results showed that deep learning models achieved higher accuracy compared to the random forest (RF) and extreme gradient boosting (XGBoost) models, with CNN-LSTM achieving the highest overall accuracy of 96.48%. At the county level, the coefficients of determination (R2) for the CNN-LSTM model were 0.91 for wheat, 0.88 for maize, and 0.73 for spring cotton. This study demonstrates that the CNN-LSTM model combined with monthly synthetic time-series NDVI provides a feasible approach for accurately mapping high-resolution multi-crop planting areas and also contributes significantly to decision support and resource management in agricultural production. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Deep learning High-resolution Monthly synthetic time-series NDVI Multi-crop classification Remote sensing Sentinel- 2

来源：评论

学校读者我要写书评

暂无评论

Advanced Driving Assistance System: Real-Time Traffic Sign Detection and Driver Drowsiness Monitoring 15

Advanced Driving Assistance System: Real-Time Traffic Sign D...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Bailke, Preeti Khedkar, Sanskruti Kumbhar, Sanket Mohod, Khushi Mandalpure, Shantanu Vishwakarma Institute of Technology Department of Information Technology Pune India Vishwakarma Institute of Technology Department of Artificial Intelligence and Data Science Pune India

ISBN: (纸本)9798331300579

The Advanced Driver Assistance System (ADAS) has emerged as a critical technology for enhancing road safety and preventing *** research paper aims to provide a comprehensive study on the development and implementation of an ADAS through the utilization of a traffic sign detection Android *** of the key functionalities of the ADAS is real-time updates on the current speed of the *** constantly monitoring the speed, the system can provide timely warnings to the driver in case they exceed the speed limit, thereby reducing the likelihood of ac-accidents caused by *** integrates driver drowsiness detection using smart spectacles equipped with eye activity *** spectacles can monitor the driver's eye movements and identify signs of drowsiness or *** such cases, the system can issue alerts or recommendations to the driver, encouraging them to take a break or refocus their attention on the *** integrating these functionalities, the ADAS aims to enhance road safety, assist drivers with timely information and warnings, and ultimately reduce the risk of accidents on the roads. © Grenze Scientific Society, 2024.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Hate Speech Detection Approach Using Neutrosophic Neural Networks for Social Media Forensics

引用

Computers, Materials & Continua 2024年第4期79卷 243-262页

作者： Yasmine M.Ibrahim Reem Essameldin Saad M.Darwish Department of Information Technology Institute of Graduate Studies and ResearchAlexandria UniversityAlexandria21526Egypt Faculty of Computers and Information Technology Egyptian E-Learning University(EELU)Giza12611Egypt Faculty of Computers and Data Science Alexandria UniversityAlexandria21554Egypt

Detecting hate speech automatically in social media forensics has emerged as a highly challenging task due tothe complex nature of language used in such platforms. Currently, several methods exist for classifying hatespeech, but they still suffer from ambiguity when differentiating between hateful and offensive content and theyalso lack accuracy. The work suggested in this paper uses a combination of the Whale Optimization Algorithm(WOA) and Particle Swarm Optimization (PSO) to adjust the weights of two Multi-Layer Perceptron (MLPs)for neutrosophic sets classification. During the training process of the MLP, the WOA is employed to exploreand determine the optimal set of weights. The PSO algorithm adjusts the weights to optimize the performanceof the MLP as fine-tuning. Additionally, in this approach, two separate MLP models are employed. One MLPis dedicated to predicting degrees of truth membership, while the other MLP focuses on predicting degrees offalse membership. The difference between these memberships quantifies uncertainty, indicating the degree ofindeterminacy in predictions. The experimental results indicate the superior performance of our model comparedto previous work when evaluated on the Davidson dataset.

关键词： Hate speech detection whale optimization neutrosophic sets social media forensics

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Cerebral Stroke Prediction: Mastery Unveiled Through Stratified K-Fold and K-Fold Cross Validation Techniques for Imbalanced datasets 15

Revolutionizing Cerebral Stroke Prediction: Mastery Unveiled...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Mundargi, Zarinabegam Khedkar, Sanskruti Kumbhar, Sanket Mohod, Khushi Meshram, Yashashri Vishwakarma Institute of Technology Department of Information Technology Pune India Vishwakarma Institute of Technology Department of Artificial Intelligence and Data Science Pune India

ISBN: (纸本)9798331300579

In the realm of healthcare data analysis, stroke prediction stands as a critical task necessitating accurate and reliable machine learning models. Cross-validation techniques play a pivotal role in ensuring the robustness of these models. Among various methods, K-Fold and Stratified K-Fold have emerged as key contenders. The challenge of handling imbalanced datasets is particularly pertinent in stroke prediction, where the occurrence of strokes is often a rare event. This study meticulously explores the significance of cross-validation techniques in stroke prediction, with a focus on addressing class imbalances. Our research focuses on comparing the effectiveness of K-Fold and Stratified K-Fold techniques in managing the stroke dataset. Our findings shed light on the superiority of Stratified K-Fold in effectively managing imbalanced data, providing crucial insights for the advancement of stroke prediction models and healthcare applications. © Grenze Scientific Society, 2024.

关键词： Prediction models

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：