检索结果-内蒙古大学图书馆

CCTG-NET: Contextualized Convolutional Transformer-GRU Network for speech emotion recognition

International Journal of Speech Technology 2023年第4期26卷 1099-1116页

作者： Tellai, Mohammed Mao, Qirong Department of Computer Science and Communication Engineering Jiangsu University Jiangsu Province Zhenjiang212013 China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Jiangsu Province Zhenjiang212013 China

Speech is a crucial aspect of human-to-human interactions and plays a fundamental role in the advancement of human–computer interaction (HCI) systems. Developing an accurate speech emotion recognition (SER) system for human conversations poses a critical yet challenging task. Existing state-of-the-art (SOTA) research in SER primarily focuses on modeling vocal information within individual conversational speech utterances, overlooking the significance of incorporating transactional information from the interaction context. In this paper, we present a novel Contextualized Convolutional Transformer-GRU Network (CCTG-Net) for recognizing speech emotions using Mel-spectrogram features, effectively integrating contextual information for emotion recognition. Our experiments are conducted on the widely-used emotional benchmark dataset, IEMOCAP. Compared to SOTA methods in four-class emotion recognition, our proposed model achieves a weighted accuracy of 88.4% and an unweighted accuracy (UA) of 89.1%. This marks a substantial 3.0% enhancement in UA while maintaining an optimal balance between performance and complexity. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Sleep Stage and Sleep Disorder Detection using Spatial and Temporal Attention based Capsule Network 1

Sleep Stage and Sleep Disorder Detection using Spatial and T...

引用

1st International Conference on Software, Systems and Information Technology, SSITCON 2024

作者： Devi, R. Renuga Elavarasi, S. Anitha Venkateswarlu, Chetti Anitha, R. Ali, Hassan Mohamed Srm Institute of Science and Technology Ramapuram Department of Computer Science and Applications Chennai India Sona College of Technology Department of Computer Science and Engineering Salem India Maisammaguda Department of Electronics and Communication Engineering Hyderabad India New Prince Shri Bhavani College of Engineering and Technology Department of Information Technology Chennai India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq

ISBN: (纸本)9798350352931

Sleep is referred as a cyclic process which is the most important part in human life. The sleep disorder and its stages are observed from time waveforms such as Electroencephalogram (EEG), Electrocardiograms (ECG), and Electromyograms (EMG) while diagnosing patients. However, the existing Deep Learning (DL) based neural network used for multi-modal sleep stage and sleep disorder detection has limitations in decision making that results in inaccurate detection of sleep stage. To overcome this limitation, a Spatial and Temporal Attention based Capsule Network (STA-CapsNet) is proposed for sleep stage and sleep disorder detecting for multimodal waveforms. The proposed CapsNet model with spatial and temporal attention mechanism focuses on informative regions that helps in making decision and classifies the sleep stages accurately. Firstly, the time waveforms are acquired and preprocessed to convert the signals into Red Green Blue (RGB) images for precise classification of sleep disorders. These RGB images are fed to proposed STA-CapsNet model for classifying the six stages of sleep correctly. Experimental results of the proposed STA-CapsNet method achieved accuracy of 9 6. 8 9 %which is higher than the existing approaches such as Convolutional Neural Network (CNN) and Visual Geometry Group-16 (VGG-16). © 2024 IEEE.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for Automated GUI Testing Using Quasi-Oppositional Genetic Sparrow Search Algorithm

A Hybrid Approach for Automated GUI Testing Using Quasi-Oppo...

引用

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

作者： Jayalakshmi, N. Sakthivel, K. Psna College of Engineering and Technology Department of Computer Applications Tamil Nadu Dindigul India K.S Rangasamy College of Technology Department of Computer Science and Business Systems Tamil Nadu Tiruchengode India

ISBN: (纸本)9798331543617

Testing of GUI is crucial for assessing software reliability, usability, and functionality;however, classical approaches are not sustainable in contemporary applications. It proposes the Quasi-Oppositional Genetic Sparrow Search Algorithm (OOGSSA) to auto-generate efficient GUI test cases. It combines genetic algorithms, sparrow search dynamics, and quasi-oppositional learning to optimize test suites, minimize redundant test cases, and improve the testing fault. The result obtained for the model OOGSSA is 95.8 % in test coverage, 85.3 % in redundancy, and 92.6 % in fault detection. Furthermore, test generation time was minimized to forty minutes and the overall testing time to seventy-five minutes, which is more efficient than conventional genetic or model-based testing. The outcomes presented above show that OOGSSA is highly efficient and effective in solving the issues of the current GUI testing and improving the overall quality and reliability of software. More enhancements to the algorithm will be done in future work as well as leveraging the algorithm to cover a wider GUI space including mobile and web. © 2024 IEEE.

关键词： Software reliability

来源：评论

学校读者我要写书评

暂无评论

Contrastive Loss Function Siamese Network for Change Detection on Remote Sensing Images 2

Contrastive Loss Function Siamese Network for Change Detecti...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Saranya, N. Naga Alkhayyat, Ahmad Shreyas, A.V. Raviprakash, M.L. Jayachandran, T. Saveetha College of Liberal Arts & Science Simats Department of Computer Applications Chennai India College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Civil Engineering Bengaluru India Kalpataru Institute of Technology Department of Computer Science and Engineering Tiptur India Nandha Engineering College Department of Ece Erode India

ISBN: (纸本)9798350373110

To observe the changes in the earth surface is increasing due to development of navigation software applications and also mainly prediction purposes for agriculture purpose and environmental hazards. To overcome the problem one of the most crucial technological choices for effectively identifying changes in observations in remote sensing photos is Change Detection (CD). applications for CD are numerous and include mapping disasters, environmental monitoring, urban planning and land use study. On the other hand, the CD applications face significant hurdles due to the often-occurring class imbalance issue. In order to tackle this problem, a new type of Contrastive loss function Siamese network (CLFS-Net) that integrates the links between scenes and foregrounds to yield global-aware features for effective change detection. The CLFS-Net improve symbiotic connection learning between scene and foreground while simultaneously learning contextual relationships. The proposed CLFS-Network gained in terms of accuracy as 90%, precision as 95% and recall as 91% and f1 score as 95% respectively. © 2024 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Smart Health Management Application Using IoT and Smart Sensors 2

Smart Health Management Application Using IoT and Smart Sens...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Arnika Shaikh, Asmat Ara Kumar, Mukesh Sharma, Bhasker Yadav, Dinesh Kumar Aeri, Manisha Sharda School of Engineering and Technology Sharda University Department of Computer Science and Applications Up Greater Noida India Parle Tilak Vidyalaya Association's Institute of Management Department of Marketing Management Maharashtra Mumbai India Graphic Era Hill University Department of Computer Science & Engineering Uttarakhand Dehradun India Hitech Institute of Engineering and Technology Department of Computer Science UP Ghaziabad India Lloyd Institute of Engineering & Technology Department of Mechanical Engineering UP Greater Noida India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350371055

Clever fitness management software using the Internet of Factors (IoT) and smart sensors are a modern answer for powerful and personalized health care. This technology integrates innovative sensors with IoT, creating a community of connected gadgets that can music and screen a character's health and well-being. The utility collects facts in actual time, which are then analyzed and processed to provide valuable insights and recommendations for stepped-forward fitness management. The software uses diverse clever sensors, including health trackers, blood strain monitors, and glucose video display units, to constantly display the consumer's vital signs, symptoms, and physical activities. This record is then transmitted to the cloud for garage and analysis. © 2024 IEEE.

关键词： Garage Health care Management Sumptoms Transmitted

来源：评论

学校读者我要写书评

暂无评论

Product Recommendation System using Deep Learning based Recurrent Neural Network

Product Recommendation System using Deep Learning based Recu...

引用

2023 International Conference on computer Communication and Informatics, ICCCI 2023

作者： Shanthi, S. Nirmaladevi, K. Mathiarasi, N. Tharani, As. Krithika Monisha, A. Kuppuchamy, R. Krishnamoorthy, N. Kongu Engineering College Department of Computer Science & Engineering Perundurai India PSNA College of Engineering and Technology Department of Computer Applications Tamilnadu Dindigul India Vellore Institute of Technology Department of Software Systems and Engineering Vellore Campus India

ISBN: (纸本)9798350348217

Today's marketing strategies place a high priority on comprehending customer sentiments. It will not only give businesses a better understanding of how their clients view their goods and/or services, but it will also give them suggestions on how to enhance their offerings. We make an effort to comprehend the relationship between various factors in customer reviews on an online store for women's clothing. The proposed system also classifies each review, according to, whether it recommends the product in question or not, and whether it has a positive, negative, or neutral sentiment. With the exception of review titles and review texts, we used univariate and multivariate analyses on datasets features to accomplish these goals. Additionally, we have implemented a bidirectional recurrent neural network (RNN) with a long-short term memory unit (LSTM) for sentiment and recommendation. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Novel Machine Learning-Enhanced Swarm Intelligence Algorithm for Cost-Effective Cloud Load Balancing

A Novel Machine Learning-Enhanced Swarm Intelligence Algorit...

引用

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

作者： Satheesh, Nimmati Sakthivel, K. Psna College of Engineering and Technology Department of Computer Applications Tamil Nadu Dindigul India K.S Rangasamy College of Technology Department of Computer Science and Business Systems Tamil Nadu Tiruchengode India

ISBN: (纸本)9798331543617

Cloud computing refers to the instant accessibility of shared computer resources over the internet on-demand, thereby revolutionizing the way organizations deploy and manage their IT infrastructure. Efficient load balancing in a cloud environment scales up, utilizing resources with optimized cost-effectiveness. This paper introduces a new Machine Learning-guided Improved Swarm Intelligence Algorithm for reliable load balancing in cloud computing. Methodology It spans on three main elements. The first is the data center controller for the management of tasks. VM allocation uses an Improved Beetle Swarm Optimization Algorithm and one-dimensional convolutional probabilistic neural network is used for host load prediction. To propose an approach that looks to optimize the key metrics such as make span, average cost of VM, resource utilization, and value response time through iterative optimization process. The results of the experiments reflect the success of the proposed algorithm, because an improved performance of load balancing is obtained in comparison with those achieved using PSO, Grey Wolf Optimization, and Genetic Algorithm. The convergence diagram displays the iterative optimization process achieved by the proposed algorithm in obtaining a balance among various performance metrics. Overall, the methodology proposed in this work will provide promising facilitation in the increased efficiency, scalability, and cost-effectiveness of environments based on cloud computing with a reliable load balancing. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Pneumothorax Diagnosis and Segmentation Using Deep Convolution Neural Network

A Novel Method for Pneumothorax Diagnosis and Segmentation U...

引用

2023 International Conference on computer Communication and Informatics, ICCCI 2023

ISBN: (纸本)9798350348217

A pneumothorax is the accumulation of air in the pleural space between the chest and lungs. Air that is in the lungs during breathing can leak out of the lungs and become trapped between the chest and lungs in the thoracic cavity, causing chest pain, difficulty breathing, and ultimately the complete collapse of the taut lungs. pneumothorax. Therefore, early diagnosis and treatment should be started. Neural networks have proven effective in image classification tasks, and many researchers believe that training neural network models can detect radiologist-diagnosed chest abnormalities such as pneumonia and pneumothorax. is proving. Moreover, we utilize various techniques, including Stochastic Weight Averaging (SWA), aggressive data augmentation, and learning rate schedule. We use the chest x-ray dataset provided by the 2019 SIIM-ACR In this study, a ResNet-34 neural network is trained on a data set of chest x-rays containing over 10,675 images to create a model that predicts the presence of pneumothorax from chest *** suggested system receives a Dice Similarity Coefficient (DSC) of 0.8410 © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Detection Using SSD Mobilenet & Faster RCNN 2

Traffic Sign Detection Using SSD Mobilenet & Faster RCNN

引用

2nd IEEE International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies, ViTECoN 2023

作者： Asif, Shaik Mohammad Anil, T. Tangudu, Satwik Keertan, G.H. Sai Don, S. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Applications Amritapuri India

ISBN: (纸本)9798350347982

This paper presents a deep learning-based approach to traffic sign detection. The proposed approach utilizes state- of-the-art object detection models, such as SSD and RCNN, to detect traffic signs in real time. Tensorflow is used as a platform for training deep learning models and the models are being implemented on Google Colab and Kaggle cloud due to the GPU availability on the respective platforms. The models are evaluated on a traffic sign dataset from Kaggle, and it achieves high detection accuracy. Moreover, the proposed approach is robust to different lighting and weather conditions and is capable of detecting traffic signs from various distances and angles. The findings of this study show that by effectively detecting and recognizing traffic signs, deep learning-based techniques can potentially increase the safety and effectiveness of transportation networks. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Potential Impacts of Online-Based Learning 2.0 and Certification on Employability 1

引用

3rd International Conference on Universal Threats in Expert applications and Solutions, UNI-TEAS 2024

作者： Saini, Dilip Kumar Jang Bahadur Singh, Sumeshwar Negi, Neerja Bhandari, Sonam Kumar, Raj Joshi, Kapil Department of Computer Science and Engineering Himalayan School of Science and Technology Swami Rama Himalayan University Dehradun India Department of Computer Science and Engineering Graphic Era Hill University Uttarakhand Dehradun India School of Computer Applications Manav Rachna International Institute of Research and Studies Faridabad India Department of CSE Uttaranchal Institute of Technology Uttaranchal University Dehradun India Department of School of Computer Science and Engineering Dev Bhoomi Uttarakhand University Dehradun Dehradun India

ISBN: (数字)9789819738106

ISBN: (纸本)9789819738090

Rapid advancement in technology innovation has seen an expansion in online-based learning programs as a major aspect of numerous organizations’ course offerings around the globe. Online learning in colleges has gotten more interactive, adaptable, collaborative, and participative. It has gained a fundamental part to play later on as a classroom teaching tool and a self-study platform for skill improvement. The reason for this examination is to consider the likely effects of online-based learning and accreditation regarding employability. The term employability implies a set of abilities, understanding, and individual qualities that make a graduate bound to pick up work and prevail in their chosen occupation. This paper has especially investigated the issues of online certification real availability, their impacts on employability, and their overall points of interest and weaknesses. Recommendations for further work and refinements of the pedagogical implementation that builds on these findings are presented in the final stages of this research paper. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： E-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：