检索结果-内蒙古大学图书馆

Coupling Mobile Brain Imaging and Virtual Reality Omnidirectional Treadmill to Explore Attenuated Situational Awareness during Distracted Walking

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年第3期16卷 1063-1076页

作者： Chuang, Chun-Hsiang Chiu, Tsai-Feng Hsu, Hao-Che Lin, Shih-Syun National Tsing Hua University Research Center for Education and Mind Sciences College of Education The Institute of Information Systems and Applications College of Electrical Engineering and Computer Science Hsinchu300 Taiwan National Tsing Hua University Research Center for Education and Mind Sciences Hsinchu300 Taiwan National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300193 Taiwan National Taiwan Ocean University Department of Computer Science and Engineering Keelung20224 Taiwan

Walking while engaging in distracting activities affects our perception of changes happening on the road, leading to exposure to hazardous conditions. This study aimed to evidence that pedestrians who become distracted when absorbed in their smartphones fail to maintain situational awareness. Thirty-six recruited participants performed a psychomotor vigilance task and a wayfinding task designed to simulate a multitasking scenario;meanwhile, an auditory oddball paradigm presented to participants tested their situational awareness of an external stimulus. The experiment was conducted in virtual reality (VR) environment with an omnidirectional treadmill. Participant's behavioral and electroencephalographic (EEG) responses were measured and analyzed using a newly proposed brain network measure, phase locking distance (PLD), to capture multitasking-associated couplings between brain regions. The current study supports the notion that multitasking can lead to diminished behavioral performance and changes in walking patterns. Despite the increased interregional brain connectivity, which may be an adaptive response to heightened cognitive demands, the associated reduction in event-related EEG activity suggests competition for neural resources during multitasking. Moreover, the observed EEG activities could indicate additional information processing capacity limitations and provide evidence of decreased situational awareness during multitasking, thereby increasing susceptibility to potentially hazardous situations. © 2016 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Advancing Human-computer Interaction: Real-Time Gesture Recognition and Language Generation Using CNN-LSTM Networks

Advancing Human-Computer Interaction: Real-Time Gesture Reco...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Kavitha, M. Brintha Rajakumari, S. Bharath Institute of Higher Education and Research Department of Computer Applications Tamil Nadu Chennai India Bharath Institute of Higher Education and Research Department of Computer Science Tamil Nadu Chennai India

ISBN: (纸本)9798331543617

Efficient human-computer interaction (HCI) has pushed forward hand gesture recognition (HGR), and natural language utterance generation (NLUG). Traditional systems are limited because these rely on static infrastructure and manual processing, accompanied by inaccuracies and latency. In comparison, the proposed system uses an advanced fusion of convolutional neural networks (CNNs) for gesture recognition and long short-term memory (LSTM) networks for language generation to achieve real-time processing with context-aware responses. The results of the experiments showed a 90.5% increase in precision for gesture recognition and BLEU score 0,715 NLUG were described as displaying superiority to existing systems on the tool performance The proposed approach also reduces the latency to 90 ms, while in traditional systems it is about 150 ms. These results suggest an opportunity to reimagine HCI systems as truly immersive and efficient, responsive experiences that can optimize not only user interactions with applications in specific domains, but also social computing at large. © 2024 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

An Automated Two-Stage Brain Tumour Diagnosis System Using SVM and Geodesic Distance-Based Colour Segmentation

An Automated Two-Stage Brain Tumour Diagnosis System Using S...

引用

International Conference on Power Engineering and Intelligent Systems, PEIS 2023

作者： Syedsafi, S. Sriramakrishnan, P. Kalaiselvi, T. Department of Computer Applications Kalasalingam Academy of Research and Education Tamil Nadu Krishnankoil626126 India Tamil Nadu Coimbatore641112 India Department of Computer Science and Applications The Gandhigram Rural Institute [Deemed to be University Tamil Nadu Dindigul624302 India

ISBN: (纸本)9789819972159

In the medical profession, brain tumour is a very crucial illness. A brain tumour is an unwanted mass growing in the brain cells;if it’s not prevented, it will eventually cause death. Therefore, tumour diagnosis is essential. Magnetic resonance imaging (MRI) is used to identify the brain tumour quickly. The approach of detecting a brain tumour from human eyesight is quite difficult. The proposed work automatically diagnoses the brain tumour. This proposed technique has two stages: classification and segmentation. The classification stage is used to classify the T2W-MRI images into a tumour and normal using 8 x 8 blocks with gray-level co-occurrence matrix (GLCM) features using a support vector machine (SVM). The second stage segments the FAIR and T1C type MRI images using colour-based segmentation technique. This proposed method uses the BraTS2013 dataset. Classification and segmentation result is calculated by sensitivity, specificity and accuracy. In the segmentation, it additionally uses the dice similarity coefficient (DSC) to find the accuracy. The outcomes denote the proposed method's accuracy of classification as 96.66% and the DSC of segmentation accuracy as 80%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Iris Image Data Base Management Using Retinal Biometric Data for Security applications 1

Iris Image Data Base Management Using Retinal Biometric Data...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Sivasankari, K. Hanirex, D. Kerana Bharath Institute of Higher Education and Research Department of Computer Applications Tamil Nadu Chennai India Bharath Institute of Higher Education and Research Department of Computer Science Tamil Nadu Chennai India

ISBN: (纸本)9798350353648

IrisDB (Iris image Data Base) is an innovative database system presented in this work, designed to optimize the processes of retinal biometric data storage and retrieval. IrisDB effectively tackles the distinct obstacles presented by the substantial file size and high dimensionality of iris images through the incorporation of state-of-the-art indexing methodologies, optimal compression algorithms, and resilient encryption systems. To optimize storage utilization and facilitate retrieval operations, the system implements a hybrid compression method and a multi-tiered indexing mechanism. Critical data is further protected by AES-256 encryption. According to the testing outcomes, IrisDB is the optimal solution for large-scale biometric databases due to its substantial reduction in storage requirements and enhancement in retrieval times when compared to current systems. IrisDB competency in effectively managing enrollment and verification procedures is demonstrated through its thorough exposition of its architecture and workflow. Iris biometric data is utilized by numerous identification and security applications;the scalable and secure architecture of IrisDB has the capacity to fundamentally transform this procedure. © 2024 IEEE.

关键词： Indexing (of information)

来源：评论

学校读者我要写书评

暂无评论

Empowering Dynamic Scheduling in IoT Networks through Collaborative Policy Learning via Federated Reinforcement Techniques 2

Empowering Dynamic Scheduling in IoT Networks through Collab...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Thirunavukkarasu, M. Thaiyalnayaki, S. Jose, Naduvathezhath Nessariose Maheshwari, S. Pavithra, B. Malathi, G. Department of Computer Science & Applications S.A College of Arts & Science India Department of Computer Science Rabiammal Ahamed Maideen College for Women India Denken Solutions India Department of Information Technology Sri Sai Ranganathan Engineering College India Department of Computer science and Engineering Sri Sai Ranganathan Engineering College India Department of Computer Science and Engineering Sri Sai Ram Institute of Technology Chennai India

ISBN: (纸本)9798350383867

In the burgeoning landscape of Internet of Things (IoT) networks, efficient management of resources is paramount for ensuring optimal performance and resource utilization. Dynamic scheduling, particularly in the context of cloud-edge-terminal IoT networks, presents a significant challenge due to the diverse and dynamic nature of connected devices and their varying computational requirements. Traditional centralized approaches to scheduling may prove inadequate in such dynamic environments, necessitating the exploration of novel techniques. This project proposes a pioneering approach to address the dynamic scheduling challenges in IoT networks by leveraging collaborative policy learning through federated reinforcement techniques. The proposed framework harnesses the power of federated learning, a decentralized machine learning paradigm, to collectively train policies for dynamic scheduling tasks across distributed edge and terminal devices while preserving data privacy and security. Key components of the proposed framework include a collaborative learning architecture that orchestrates the exchange of policy updates among edge and terminal devices, enabling them to adaptively refine their scheduling policies based on local observations and feedback. Reinforcement learning serves as the underlying mechanism for policy optimization, allowing devices to learn and adapt to evolving network conditions and user demands over time. By decentralizing the learning process and leveraging the collective intelligence of edge and terminal devices, the proposed framework offers several advantages. These include improved scalability, reduced communication overhead, and enhanced resilience to network failures. Furthermore, the federated approach ensures data privacy and regulatory compliance by keeping sensitive information localized to individual devices. To evaluate the effectiveness of the proposed framework, comprehensive simulations and real-world experiments will be conducted u

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of Speech Emotion Recognition Through Advanced Ensemble Learning Techniques 9

Optimization of Speech Emotion Recognition Through Advanced ...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Prathyakshini Prathwini Keerthana Department of Information Science and Engineering Nitte Karkala India Department of Master of Computer Applications Nitte Karkala India Nitte Karkala India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377972

Recognition of emotion in speech (RES) is generating significant interest due to its promise to improve human-computer interaction through precise identification of emotions from speech signals. This work investigates how well deep learning methods advance RES accuracy. The study makes it possible to analyze a variety of speech patterns, emotional expressions, and demographic information all of which are crucial for developing trustworthy RES models. According to the study, CNNs demonstrated their ability to capture spatial characteristics from voice spectrogram representations with an amazing accuracy rate of 93%. RNNs performed exceptionally well at modeling temporal dependencies and capturing the sequential nature of speech, with an accuracy rate of 90%. Both models performed well, but some emotions such 'angry' and 'surprise' were more accurately detected than others, including 'disgust' and 'happy,' suggesting room for improvement. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An IoT-Based Approach to Measure the Effectiveness of Traditionally Prepared Compost in Indian Villages 1

An IoT-Based Approach to Measure the Effectiveness of Tradit...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Bhardwaj, Manish Singh, Shweta Tripathi, Arun Kumar Ujjawal Goel, Sparsh Kumar, Ankit KIET Group of Institutions Department of Computer Science and Information Technology Delhi-NCR region Ghaziabad India KIET Group of Institutions Department of Computer Applications Delhi-NCR region Ghaziabad India

ISBN: (纸本)9798350353648

The Smart Compost Monitoring system helps to monitor and check the compost made by the amateur or low knowledgeable farmers and enthusiasts and an ideal ratio achievement is the subject of the current invention, The innovation is built on using several sensors to monitor and track record for the required amount of nutrition as well as the compulsory elements for acquiring an ideal compost the invention is not only limited to the Rural Areas it can be deployed to the Urban areas as well. The suggested technology will use a special machine learning algorithm to take the readings from the compost and compare it with the previously fetched ideal ratios and provide the difference that is to be then fulfilled by the farmer. Every crop with different requirements will have selected predefined ratios to be reached and monitored and different prerequisites will be achieved before fully deploying the system. Furthermore, the paper can be a precise assessment of crucial parameters such as the carbon-tonitrogen (C/N) ratio and pH levels, ensuring accuracy in composting endeavours. The proposed architecture not only promises immediate assistance to those in need of natural compost but also eliminates the necessity for users to meticulously maintain nutritional levels during the composting process. By alerting users of any incompatible manure with their intended crops and confirming when optimal levels are achieved, the system offers comprehensive support throughout the composting journey. IoT enables us to have a Arduino unit directly installed in soil range of the crop land and by using the combined the range definitions of different sensors we are able to record the metrics of the sensors and then compare those with the predefined ones. © 2024 IEEE.

关键词： Patents and inventions

来源：评论

学校读者我要写书评

暂无评论

Parks-McClellan-Bandwidth Filtering Efficacy for Augmented Ailment Dissection in Bradykinesia 2

Parks-McClellan-Bandwidth Filtering Efficacy for Augmented A...

引用

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Syed Jamalullah, R. Gladence, L. Mary Bharanidharan, G. Rasheedh, J Abdul Sathyabama Institute of Science and Technology Department of Cse Chennai India Department of Computer Applications Chennai India

ISBN: (纸本)9798350325799

Advancements in electroencephalogram (EEG) data processing have enabled the consistent monitoring of the human brain, playing a crucial role in the early detection and prevention of potential health issues. This study analyzes EEG data to identify abnormal signals, particularly those related to Bradykinesia, a neurological disorder associated with an increased risk of Parkinson's disease. Previous research has utilized neural networks, clinical features, and computational methodologies for signal classification. This research proposes using the Parks McClellan best approach and filter order estimation across various frequency bands to extract meaningful characteristics from EEG data. Additionally, the Power Spectral Density (PSD) approach, Fast Fourier Transform (FFT) method, and periodogram are employed to differentiate amplitude bandwidths. The non-linear vector technique enhances classification accuracy through the Peak Signal-to-Noise Ratio (PSNR). The study also explores the evaluation of consistency quotient using mean-square and mean-absolute error methodologies. By calculating the cross-correlation average of bandwidths, the classification accuracy of the Bradykinesia assessment is improved. The research findings, supported by simulated computations and MATLAB algorithmic implementations, validate the effectiveness of the proposed methods. This research contributes to the ongoing efforts in EEG data analysis, enhancing the early detection and intervention of brain health issues. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approaches for Stocks Price Prediction: A New Institutive Way of Neural Architecture Design

Hybrid Approaches for Stocks Price Prediction: A New Institu...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Sharma, Vikram Rakhra, Manik Sharma, Vikrant Sarkar, Tiyas Singh, Amanpreet Jairath, Kapil Lovely Professional University Department of Computer Science and Engineering Phagwara India Graphic Era Deemed to be University Department of Computer Science and Engineering Graphic Era Hill University Phagwara India Lovely Professional University School of Computer Science and Engineering Phagwara India Lovely Professional University Department of Computer Scienceand Applications Phagwara India Trinity College Department of Sciences Jalandhar India

ISBN: (纸本)9798350378092

Stock price prediction is a critical aspect of financial decision-making for both individual investors and institutions. Traditional methods such as ARIMA and deep learning techniques like ANNs, LSTM, and GRU have demonstrated effectiveness in forecasting stock prices but suffer from inherent limitations. In recent years, hybrid models have emerged as a promising approach to address these shortcomings. This research paper introduces and evaluates three novel hybrid models for stock price prediction. First model integrates GRU, LSTM, and attention mechanisms to leverage the strengths of each component. By employing attention mechanisms, the model can focus on relevant information, thereby enhancing prediction accuracy. The second model combines GRU and LSTM networks with attention mechanisms, incorporating additional architectural elements to further refine predictive capabilities. The third proposed model is a fusion of the first two, augmented with additional features and enhancements to achieve superior performance in stock price prediction tasks. Evaluation of these proposed models utilizes commonly used metrics to assess predictive accuracy and generalizability. The results demonstrate the effectiveness of the proposed hybrid approaches in improving stock price prediction performance. This research contributes to the advancement of stock price prediction methodologies by proposing innovative hybrid models, offering valuable tools for researchers and practitioners in the finance industry seeking enhanced forecasting accuracy and decision-making capabilities. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Lexicon and Attention Based Handwritten Text Recognition System

引用

Machine Graphics and Vision 2022年第1-4期31卷 75-92页

作者： Kumari, Lalita Singh, Sukhdeep Rathore, Vaibhav Varish Singh Sharma, Anuj Department of Computer Science and Applications Panjab University Chandigarh India Punjab Moga India Computer Networking and Information Technology PRL Gujarat Ahmedabad India

The handwritten text recognition problem is widely studied by the researchers of computer vision community due to its scope of improvement and applicability to daily lives. It is a sub-domain of pattern recognition. Due to advancement of computational power of computers since last few decades neural networks based systems heavily contributed towards providing the state-of-the-art handwritten text recognizers. In the same direction, we have taken two state-of-the art neural networks systems and merged the attention mechanism with it. The attention technique has been widely used in the domain of neural machine translations and automatic speech recognition and now is being implemented in text recognition domain. In this study, we are able to achieve 4.15% character error rate and 9.72% word error rate on IAM dataset, 7.07% character error rate and 16.14% word error rate on GW dataset after merging the attention and word beam search decoder with existing Flor et al. architecture. To analyse further, we have also used system similar to Shi et al. neural network system with greedy decoder and observed 23.27% improvement in character error rate from the base model. © 2022 Faculty of Applied Informatics and Mathematics - WZIM, Warsaw University of Life sciences - SGGW. All rights reserved.

关键词： Decoding

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：