检索结果-内蒙古大学图书馆

Wearable sensors and datasets for evaluating systems predicting falls and activities of daily living: recent advances and methodology

引用

Multimedia Tools and applications 2024年第29期83卷 73671-73701页

作者： Kaur, Rajbinder Sharma, Rohini Department of Computer Science and Applications Panjab University Chandigarh India

This paper provides a comprehensive survey of various aspects of the systems detecting falls and activities of daily living. Such systems are very useful for elderly people who live alone. The feature values pertaining to the movement can be acquired by the wearable sensors mounted on various parts of the body. Detecting activities of daily living and falls can help in alerting caretakers but predicting falls before occurrence can alert the subject and avoid injuries. The inertial measurements of body movements can help in detecting falls. However, the physiological features combined with inertial measurements of body movements can further improve the accuracy of detection and may lead to prediction. This paper provides a state-of-the art review of various sensors which can be used to capture inertial measures and physiological features. We also provide a comprehensive review of the existing forty-two datasets which comprises inertial measurements and can be extended with physiological features. A pilot study has been conducted using five machine learning techniques exhibiting the phases in detecting and predicting falls which concluded that original captured features are more characteristic than single representative feature computed using Sum Magnitude Vector. Further as we move towards developing a generalized system, accuracy gets affected. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Fake news detection on social media using Adaptive Optimization based Deep Learning Approach

引用

Multimedia Tools and applications 2025年第9期84卷 6091-6111页

作者： Steni Mol, T.S. Sreeja, P.S. Department of Computer Science Hindustan Institute of Technology and Science Chennai India Department of Computer Applications Vellore Institute of Technology Chennai India

Various content-sharing platforms and social media are developed in recent times so that it is highly possible to spread fake news and misinformation. This kind of news may cause chaos and panic among people. The automatic and accurate detection of fake news is a complex task. To consider this issue, an automatic and effective fake news detection approach is implemented. The proposed methodology is named Adaptive Adam Adadelta Optimizer-based Deep Bi-directional Long Short Term Memory (Bi-LSTM), in which Adaptive Adam AO is the merging of Adadelta Optimizer (AO), Adaptive concept, and Adam Optimization. The Bidirectional Encoder Representations from Transformers (BERT) is used for the tokenization and then, feature mining is done. Also, the dimensionality of the features is reduced by Singular Value Decomposition (SVD) and Moving Principal Component Analysis (MPCA). From them, the top-N feature selection is performed using Joint Quantum Entropy. Finally, for fake news detection, Adaptive Adam AO trained Deep Bi-LSTM is used, which obtained maximum specificity, sensitivity, and accuracy of 0.928, 0.945, and 0.938. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

PIF dataset: a comprehensive dataset of physiological and inertial features for recognition of human activities

引用

Multimedia Tools and applications 2024年第29期83卷 73607-73625页

作者： Dhaliwal, Manpreet Kaur Sharma, Rohini Kaur, Rajbinder Department of Computer Science and Applications Panjab University Chandigarh India

Activities and falls monitoring systems using wearable technology have a promising future. The publicly available datasets are based on a few inertial features only acquired with an accelerometer, gyroscope, smartphone or smart Watches. The activities and falls performed are also less. In this study, a dataset is created by collecting physiological features along with inertial features which will help in developing and validating systems studying the effect of physiological features on the detection and prediction of falls and activities. The dataset consists of 7 activities and 8 falls for inertial data;2 activities for ECG data;6 activities for EMG data and 6 activities for GSR data. Basic body parameters like height, weight, etc. along with beats per minute, SpO2 and blood pressure are also recorded for 12 subjects. The collected data is analyzed statistically using a boxplot, pair plot, correlation heatmap and p value. The activities are classified using SVM, KNN, RF and DT. For GSR, more than 90% accuracy is achieved and for EMG, the accuracy is less than 80%. For IMU data, more than 95% accuracy is achieved. The results encourage combining inertial, physiological and basic body parameters to detect and predict falls and activities. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Multiclassification of DDoS attacks using machine and deep learning techniques

引用

International Journal of Security and Networks 2024年第2期19卷 63-76页

作者： Bhatia, Rashmi Sharma, Rohini Department of Computer Science and Applications Panjab University Chandigarh India

There are very few studies to detect different classes of DDoS attacks. Multiclassification helps network administrators to study individual behaviour. In this study, 82 flow-based features are used to detect 13 types of DDoS attacks using seven machine learning techniques namely naive Bayes, decision tree, multinomial logistic regression, random forest, k-nearest neighbour, AdaBoost and one hidden layer multi-layer perceptron (MLP) and two deep learning techniques namely multiple hidden layers MLP and long short-term memory (LSTM). Different variants of deep learning techniques are compared while fine-tuning hyperparameters. Their performance is analysed using 5-fold cross-validation and compared with existing studies. The experimental results show that random forest performed best with the highest accuracy of 0.7677 followed by one hidden layer MLP with accuracy of 0.7485 and improvements in them can give better results. It is also concluded that appropriate selection of features is important to get higher accuracy with lesser classification time. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Video captioning – a survey

引用

Multimedia Tools and applications 2025年第2期84卷 947-978页

作者： Vaishnavi, J. Narmatha, V. Department of Computer Applications SRM Institute of Science and Technology Trichy India Department of Computer and Information Science Annamalai University Annamalai Nagar Tamilnadu 608002 India

The explosion of the novel phenomenon of the combination of computer vision and Natural language processing is playing a vital role in converting the ordinary world into a more technological pool. Natural language processing and computer vision are the vanguard of Artificial intelligence with the enormous potential currently ruling more fields. The trending Accelerated research of the NLP and CV combo are cancer screening, surgical simulation, visual properties description, visual retrieval, visual description, etc. Video captioning is a task of localizing the event and various features are extracted from the particular event and then the description of the entire event is performed with Natural languages using various techniques. The task of video captioning has some evolution of various techniques from Traditional methods to Deep learning. Currently, Deep learning techniques are ruling the field. Several models are being proposed for the better enhancement of the video captioning task with the default Encoder-Decoder framework and some models with the variance of Attention mechanism and Transfer learning etc., The Attainment of every technique and the accuracy of the generated results are highly dependent on the nature of the problem, diversity, performance of chosen dataset and construction of the technique with various layers, and the amount of data split for train, validate, and test. This survey discusses the captioning types, real-time applications of video captioning, evolution of various methods in video captioning, advanced techniques, different datasets, metrics that are used to evaluate the results, and analysis of the results of the existing models for video captioning. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Study on the Explainability of Thyroid Cancer Prediction:SHAP Values and Association-Rule Based Feature Integration Framework

引用

computers, Materials & Continua 2024年第5期79卷 3111-3138页

作者： Sujithra Sankar S.Sathyalakshmi Department of Computer Applications Hindustan Institute of Technology and ScienceChennaiTamil NaduIndia Department of Computer Engineering Hindustan Institute of Technology and ScienceChennaiTamil NaduIndia

In the era of advanced machine learning techniques,the development of accurate predictive models for complex medical conditions,such as thyroid cancer,has shown remarkable *** predictivemodels for thyroid cancer enhance early detection,improve resource allocation,and reduce ***,the widespread adoption of these models in clinical practice demands predictive performance along with interpretability and *** paper proposes a novel association-rule based feature-integratedmachine learning model which shows better classification and prediction accuracy than present *** study also focuses on the application of SHapley Additive exPlanations(SHAP)values as a powerful tool for explaining thyroid cancer prediction *** the proposed method,the association-rule based feature integration framework identifies frequently occurring attribute combinations in the *** original dataset is used in trainingmachine learning models,and further used in generating SHAP values *** the next phase,the dataset is integrated with the dominant feature sets identified through association-rule based *** new integrated dataset is used in re-training the machine learning *** new SHAP values generated from these models help in validating the contributions of feature sets in predicting *** conventional machine learning models lack interpretability,which can hinder their integration into clinical decision-making *** this study,the SHAP values are introduced along with association-rule based feature integration as a comprehensive framework for understanding the contributions of feature sets inmodelling the *** study discusses the importance of reliable predictive models for early diagnosis of thyroid cancer,and a validation framework of *** proposed model shows an accuracy of 93.48%.Performance metrics such as precision,recall,F1-score,and the area un

关键词： Explainable AI machine learning clinical decision support systems thyroid cancer association-rule based framework SHAP values classification and prediction

来源：评论

学校读者我要写书评

暂无评论

Robust Image Forgery Localization Using Hybrid CNN-Transformer Synergy Based Framework

引用

computers, Materials & Continua 2025年第3期82卷 4691-4708页

作者： Sachin Sharma Brajesh Kumar Singh Hitendra Garg Department of Computer Science Abdul Kalam Technical UniversityLucknow226031India Department of Computer Engineering & Applications GLA UniversityMathura281406India Department of Computer Science Raja Balwant Singh Engineering Technical CampusAgra283105India

Image tampering detection and localization have emerged as a critical domain in combating the pervasive issue of image manipulation due to the advancement of the large-scale availability of sophisticated image editing *** manual forgery localization is often reliant on forensic *** recent times,machine learning(ML)and deep learning(DL)have shown promising results in automating image forgery ***,the ML-based method relies on hand-crafted ***,the DL method automatically extracts shallow spatial features to enhance the ***,DL-based methods lack the global co-relation of the features due to this performance degradation noticed in several *** the proposed study,we designed FLTNet(forgery localization transformer network)with a CNN(convolution neural network)encoder and transformer-based *** encoder extracts local high-dimensional features,and the transformer provides the global co-relation of the *** the decoder,we have exclusively utilized a CNN to upsample the features that generate tampered mask ***,we evaluated visual and quantitative performance on three standard datasets and comparison with six state-of-the-art *** IoU values of the proposed method on CASIA V1,CASIA V2,and CoMoFoD datasets are 0.77,0.82,and 0.84,*** addition,the F1-scores of these three datasets are 0.80,0.84,and 0.86,***,the visual results of the proposed method are clean and contain rich information,which can be used for real-time forgery *** code used in the study can be accessed through URL:https://***/ajit2k5/Forgery-Localization(accessed on 21 January 2025).

关键词： Image tampering convolution neural network(CNN) hybrid transformer localization

来源：评论

学校读者我要写书评

暂无评论

Eyeway: An Artificial Intelligence Of Things Pothole Detection System With Map Visualization 15

Eyeway: An Artificial Intelligence Of Things Pothole Detecti...

引用

15th International Conference on Emerging Ubiquitous Systems and Pervasive Networks / 14th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare, EUSPN/ICTH 2024

作者： Fortin, Leonhel V. Delos Santos, Arjean Rose V. Cagud, Pul Joven B. Castor, Paul Rodolf Llantos, Orven E. Department of Computer Applications Philippines Department of Computer Science Philippines

The critical role of road transport in the economic growth of the Philippines underscores the importance of maintaining an efficient infrastructure. Traditional methods for detecting potholes, primarily manual methods, have demonstrated significant limitations, revealing a technological gap in road maintenance. This study proposes a novel solution with the development of the EyeWay system, an AIoT prototype specifically designed for real-time pothole detection within the Philippine context. The primary focus of this study is the design, development, and evaluation of the effectiveness of the EyeWay system in revolutionizing road maintenance practices. By employing advanced computer vision algorithms, AI-on-edge technology, and map visualization techniques, the EyeWay system achieves real-time pothole detection. The system demonstrated a mAP of 91.8%, a testing accuracy of 82.95%, and an inference time of 1.76 milliseconds using the YOLOv5m model, highlighting substantial improvements in detection accuracy and efficiency. Despite these successes, challenges, such as GPS data inaccuracies and system overheating, have been identified, indicating areas for further enhancement. The EyeWay system offers significant advancement in proactive pothole identification and repair, contributing to road safety and reducing maintenance costs. This study provides valuable insights into the potential of AI-based systems for sustainable transportation infrastructure. © 2024 The Authors.

关键词： Motor transportation

来源：评论

学校读者我要写书评

暂无评论

Predictive VM placement algorithm for resource optimization: leveraging deep learning forecasting and resource relationship modeling

引用

International Journal of computers and applications 2025年第4期47卷 398-411页

作者： Garg, Rajni Arora, Indu Gupta, Anu Department of Computer Science Lala Lajpat Rai Govt. College Moga India Department of Computer Science Mehr Chand Mahajan DAV College for Women Chandigarh India Department of Computer Science and Applications Panjab University Chandigarh India

The growing demand for cloud computing has made it imperative to optimize the utilization of cloud resources. Resource optimization can be improved through Virtual Machine (VM) Placement. In order to effectively optimize placement of VMs, it becomes necessary to anticipate future resource demand. However, accurate resource forecasting is a major challenge due to the dynamic nature of cloud applications. Furthermore, if VMs are placed on the same server, it can lead to resource contention, especially when they compete for the same resources. This contention can adversely affect VMs performance and potentially increase cost for users, as well as energy consumption by the infrastructure. This work proposes a model named Predictive Disparity-based Virtual Machine Placement (PDVMP) which aims to enhance VM placement decision. The model integrates forecasting techniques grounded in Deep Learning for estimating the future resource needs of VMs. This estimation is incorporated in VM placement decision in order to ensure long-term sustainability of the VM on the destination server. Moreover, the model used in the current research work balances resource optimization and execution performance by packing multiple VMs that exhibit complementary resource demand on a same physical server. The performance of PDVMP model is tested against benchmark placement policies using real workload traces of bitBrains datacenter. The results show that the proposed approach improves resource utilization while reducing both performance bottlenecks and energy consumption. The experimentation shows an improvement in Energy Performance Metric ranging from 49.3% to 62.97%. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Bismuth alloys

来源：评论

学校读者我要写书评

暂无评论

Adaptive E-Learning Environments: A Methodological Approach to Identifying and Integrating Multi-layered Learning Styles

引用

SN computer science 2024年第6期5卷 772页

作者： Ramesh, M. Jayashree, R. Department of Computer Science and Applications Faculty of Science and Humanities SRM Institute of Science and Technology Department of Computer Applications Faculty of Science and Humanities SRM Institute of Science and Technology

E-learning environments represent digital platforms designed to facilitate online learning experiences. Recognizing the diverse learning preferences of individuals, the need for identifying and integrating multi-layered learning styles within these environments is paramount. Existing approaches often face limitations in accurately capturing and accommodating these intricate learning styles. To address these challenges, this study proposes a novel approach. Firstly, the integration of word embedding-based feature extraction transforms textual data into continuous vector representations, enhancing feature robustness and meaningfulness. Secondly, leveraging deep belief networks (DBNs) allows for the automatic learning of hierarchical data representations, improving model performance by capturing complex patterns. Thirdly, the DBN-based model accommodates multi-layered learning styles, including visual, auditory, kinaesthetic, and read/write preferences, offering personalized recommendations to learners. Lastly, the proposed approach is scalable and generalizable, capable of handling large datasets and diverse educational contexts, thus enhancing the efficacy of e-learning platforms. This innovative approach demonstrates promising advancements in learning style identification within e-learning environments, providing personalized guidance to learners and improving the overall effectiveness of online education. The proposed Deep Belief Network (DBN) model exhibits a significant average increase in accuracy compared to other methods implemented in Python. With an accuracy of 99.5%, the DBN model surpasses the accuracy of the K-Nearest Neighbours (KNN) and Random Forest (RF) models by 25.4 and 3.3%, respectively. This substantial improvement underscores the superiority of the proposed DBN model in learning style identification. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep belief networks E-learning environments Learning style identification Multi-layered learning styles Word embedding

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：