检索结果-内蒙古大学图书馆

Twin attention based multi-task convolutional bidirectional long short term memory for facial expression recognition

引用

Multimedia Tools and Applications 2025年第10期84卷 8037-8070页

作者： Sreenivas, Velagapudi Sivaneasan, B. Vani, K. Suvarna Chakrabarti, Prasun Singapore Institute of Technology Singapore138683 Singapore Engineering Cluster Singapore Institute of Technology Singapore138683 Singapore Department of Computer Science and Engineering AI/ML Research Group Head VR Siddhartha Engineering College Andhra Pradesh Vijayawada520007 India Department of Computer Science and Engineering Sir Padampat Singhania University Rajasthan Udaipur313601 India

Facial Expression Recognition (FER) aims to detect the emotional state of facial images. It is playing an increasingly important role in several application areas, including human–computer interaction (HCI), video transcriptions, and social communications. This article provides an adequate attention-based multi-task deep learning method for facial expression recognition. First, the input videos are collected from the RAVDESS and MELD datasets. Then, the input videos are converted using a threshold-based keyframe extraction algorithm. Next, the input data is pre-processed using the Adaptive Pixel Density Median Filtering (A-PDMF) method. Key features such as shape, color and texture are extracted from the pre-processed images. Finally, the facial expressions are recognized by proposing a novel twin attention-based multi-task convolutional bidirectional long-short-term memory method (TA-MC-BiLSTM). In addition, the classification parameters are optimally tuned using the EX-AHA method (Extended Artificial Hummingbird Algorithm). The proposed model reduces the size of facial features while accurately identifying the wide range of facial expressions. For simulation, the proposed method prefers python tool and results are analyzed using RAVDESS and MELD datasets. The simulation results show that the proposed model provides better results than other existing models in terms of accuracy of 99.6% for RAVEDESS and 99.4% for MELD. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

FQBDDA: fuzzy Q-learning based DDoS attack detection algorithm for cloud computing environment

引用

International Journal of Information technology (Singapore) 2024年第2期16卷 891-900页

作者： Kumar, Animesh Dutta, Sandip Pranav, Prashant Department of Computer Science and Engineering Birla Institute of Technology Mesra Ranchi 835215 India

With on-demand resources, flexibility, scalability, dynamic nature, and cheaper maintenance costs, cloud computing technology has revolutionized the Information technology sector, and almost everyone using the internet relies in some manner on the use of cloud services. Distributed denial of service (DDoS) attack blocks the services by flooding high or low volumes of malicious traffic to exhaust the servers, resources, etc. of the Cloud environment. In today’s era, they are challenging to detect because of low-rate traffic and its hidden approach in the cloud. Studying all DDoS attacks with their possible solution is essential to protect the cloud computing environment. In this paper, we have proposed a fuzzy Q learning algorithm and Chebyshev’s Inequality principle to counter the problem of DDoS attacks. The proposed framework follows the inclusion of Chebyshev’s inequality for workload prediction in the cloud in the analysis phase and fuzzy Q-learning in the planning phase. Experimental results prove that our proposed fuzzy Q-learning based DDoS attack detection algorithm for cloud computing environment (FQBDDA) model prevent DDoS attack. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Cloud computing DDoS attack Fuzzy logic Fuzzy Q-learning Optimization Q-learning Security

来源：评论

学校读者我要写书评

暂无评论

TSInc: Tie strength based incremental community detection using information cascades

引用

International Journal of Information technology (Singapore) 2024年第5期16卷 3243-3253页

作者： Das, Soumita Biswas, Anupam Department of Computer Science and Engineering National Institute of Technology Assam Silchar 788010 India

Community detection in dynamic networks is of great importance in social network analysis. For instance, online social networks such as Facebook, WhatsApp and LinkedIn are rapidly evolving with time. However, the majority of previous research have focused on community detection in static networks. It is computationally expensive to repeatedly use a static algorithm on snapshots of dynamic networks. In this paper, we propose a community detection algorithm namely, Tie Strength based Incremental Community detection (TSInc), aiming to find communities and track the dynamic events in each snapshot. TSInc determines communities using tie strength based information cascades. Following the initial snapshot, we construct a new subgraph based on the dynamic events in the subsequent snapshots and quickly assign communities. These communities in combination with the unchanged communities are merged to obtain the inherent community structure. These procedure is repeated for the remaining snapshots as well. Experimental results on several real-world dynamic networks and state-of-the-art approaches shows that TSInc algorithm outperforms the baseline algorithms in terms of effectiveness of the detected communities. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Cascades Community Dynamic networks Information Diffusion Tie Strength Tie strength

来源：评论

学校读者我要写书评

暂无评论

Innovative Video Classification Method based on Deep Learning Approach

引用

Recent Patents on engineering 2025年第2期19卷 95-107页

作者： Hemamalini, V. Jayasutha, D. Vinothini, V.R. Devi, R. Manjula Kumar, A. Anitha, E. Department of Networking and Communications School of Computing SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Arjun College of Technology Coimbatore Thamaraikulam India Department of Mathematics Bannari Amman Institute of Technology Sathyamangalam Erode638401 India Department of Computer Science and Design Kongu Engineering College Perundurai Erode638060 India Department of Civil Engineering University Institute of Engineering & Technology Maharshi Dayanand University Rohtak124001 India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore641202 India

Background: The automated classification of videos through artificial neural networks is addressed in this work. To explore the concepts and measure the results, the data set UCF101 is used, consisting of video clips taken from YouTube to recognize actions. The study is carried out with the authors' resources to determine the feasibility of independent research in the area. Methods: This work was developed in the Python programming language using the Keras library with Tensorflow as the back-end. The objective is to develop a network that presents performance compatible with the state of the art in terms of classifying videos according to the actions taken. Results: Given the hardware limitations, there is considerable distance between the implementation possibilities in this work and what is known as the state-of-the-art. Conclusion: Throughout the work, some aspects in which this limitation influenced the development are presented, but it is shown that this realization is feasible and that obtaining expressive results is possible 98.6% accuracy is obtained in the UCF101 data set, compared to the 98 percentage points of the best result ever reported, using, however, considerably fewer resources. In addition, the importance of transfer learning in achieving expressive results as well as the different performances of each architecture are reviewed. Thus, this work may open doors to carry patent-based outcomes. © 2025 Bentham Science Publishers.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing abnormality detection in fundus images with Triplet-OS and orchard search optimization model

引用

Neural Computing and Applications 2024年第36期36卷 23181-23194页

作者： Venkatraman, K. Hemalatha, R. Radhika, S. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha Nagar Thandalam Chennai India Department of Computer Science and Engineering St. Joseph’s College of Engineering Chennai India Department of EEE Sathyabama Institute of Science and Technology Chennai India

The accurate and early detection of abnormalities in fundus images is crucial for the timely diagnosis and treatment of various eye diseases, such as glaucoma and diabetic retinopathy. The detection of abnormalities in fundus images using traditional methods is often challenging due to high computational demands, scalability issues, and the requirement of large labeled datasets for effective training. To address these limitations, a new method called triplet-based orchard search (Triplet-OS) has been proposed in this paper. In this study, a GoogleNet (Inception) is utilized for feature extraction of fundus images. Also, the residual network is employed to detect abnormalities in fundus images. The Triplet-OS utilizes the medical imaging technique fundus photography dataset to capture detailed images of the interior surface of the eye, known as the fundus and the fundus includes the retina, optic disk, macula, and blood vessels. To enhance the performance of the Triplet-OS method, the orchard optimization algorithm has been implemented with an initial search strategy for hyperparameter optimization. The performance of the Triplet-OS method has been evaluated based on different metrics such as F1-score, specificity, AUC-ROC, recall, precision, and accuracy. Additionally, the performance of the proposed method has been compared with existing methods. Few-shot learning refers to a process where models can learn from just a small number of examples. This method has been applied to reduce the dependency on deep learning [1]. The goal is for machines to become as intelligent as humans. Today, numerous computing devices, extensive datasets, and advanced methods such as CNN and LSTM have been developed. AI has achieved human-like performance and, in many fields, surpasses human abilities. AI has become part of our daily lives, but it generally relies on large-scale data. In contrast, humans can often apply past knowledge to quickly learn new tasks [2]. For example, if given

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Detecting Communities Using Network Embedding and Graph Clustering Approach 6th

Detecting Communities Using Network Embedding and Graph Clus...

引用

6th International Conference on Soft Computing and Signal Processing, ICSCSP 2023

作者： Bhattacharya, Riju Nagwani, Naresh Kumar Tripathi, Sarsij Department of Computer Science and Engineering National Institute of Technology Raipur Raipur India Department of Computer Science and Engineering Motilal Nehru National Institute of Technology Allahabad Allahabad India

ISBN: (纸本)9789819984503

Complex network community structure has been shown effective in many fields, including biology, social media, health, and more. Researchers have explored many different techniques for studying complex networks and discovering communities within them. Most of them, however, lack the expressiveness necessary to learn the node and edge representations of complicated networks. This study has aimed to improve the performance of the Hierarchical Clustering algorithm by analyzing a framework for learning continuous feature representations using node embedding methods for nodes in networks. The proposed method improves upon previous methods by training a map from nodes to a feature space with fewer dimensions. The proposed approach employs the Hierarchical Clustering method to accomplish community identification in the benchmark networks by determining the level of similarity between any pair of node embeddings. Substantial exploratory research on a variety of real-world social networks has shown the efficacy of the proposed approach compared to existing state-of-the-art community discovery techniques. The proposed method has provided high-accuracy results when applied to graph datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Classification of Autism Spectrum Disorder using CNN & Transfer Learning 2

Classification of Autism Spectrum Disorder using CNN & Trans...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Das, Shyamali Chaudhury, Pamela Tripathy, Hrudaya Kumar Sillicon Institute of Technology Department of Computer Science and Engineering Odisha Bhubaneswar India School of Computer Engineering Kalinga Institute of Industrial Technology Odisha Bhubaneswar India

ISBN: (纸本)9798350370188

Autism spectrum disorder (ASD) is a neurodevelopment condition that impacts a person's ability to communicate and interact socially. Diagnosing autism spectrum disorder (ASD) early and correctly is critical for providing appropriate help to those who need it. Transferring information or learned representations from one task or domain to another is possible using a computerized learning technique known as transfer learning. In this study, we proposed a method for classifying ASD using an Enhanced Layerwise Sequential Convolutional Neural Network (ELS-CNN) with transfer learning. Transfer learning involves leveraging pre-trained models on large-scale datasets used for the Kaggle platform and fine-tuning them for specific tasks. A dataset that tested these models was collected and consisted of 2,928 face images. These images are preprocessed using Adaptive Median Filtering to remove noise from an image and Histogram Equalization to improve image contrast. Otsu's Binary Threshold can be used for image segmentation. Extracting the features can be Principal Component Analysis (PCA) for image compression. We suggested the ELS-CNN algorithm, which has demonstrated good performance in a number of image identification applications. The output of the deep learning neural network models was assessed using common assessment measures like accuracy, precision, recall, and fl-score. The Enhanced Layerwise Sequential CNN algorithm achieved the highest accuracy. © 2024 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of free space optical system incorporating circular polarization shift keying and mode division multiplexing

引用

Journal of Optical Communications 2024年第2期45卷 347-354页

作者： Meenu Sharma, Anshu Malhotra, Rahul Department of Electronics and Communication Engineering CT Institute of Engineering Research and Technology Greater Kailash Maqsudan Punjab Jalandhar144008 India Computer Science and Engineering CT Institute of Technology & Research Greater Kailash Maqsudan Punjab Jalandhar144008 India Computer Science and Engineering CT Institute of Technology and Management Shahpur Near Lambra Punjab Jalandhar144020 India

In this work, a free-space optical (FSO) communication system with the integration of mode division multiplexing and circular polarization shift keying (CpolSK) is proposed at 2 × 40 Gbps using LG00 and LG01 modes. Effects of diverse weather conditions such as clear weather, light rain, moderate rain, heavy rain, thin fog, thick fog, and heavy fog are studied on system performance. Further, a detailed comparison of CpolSK and polarization shift keying (PolSK) is performed at different FSO lengths in terms of log bit error rate. For implementation, analysis, and comparison, Optiwave Optisystem software is used and results show that CpolSK covers 100 km link distance and PolSK limits to 90 km only. Also, LG00 mode performs better than LG01 mode under all weather instabilities in the proposed system. © 2024 Walter de Gruyter GmbH. All rights reserved.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Analysis on Third Party Application 2

Vulnerability Analysis on Third Party Application

引用

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

作者： Supreetha, H.H. Rajani Suma, H.C. Divya, K.P. Suhasini Computer Science Engineering Department Acharya Institute of Technology bangalore India Electronics Engineering Department BGSIT Institute of Technology BG Nagar India Computer Science Engineering Department Maharaja Institute of Technology Mysore India Electronics Engineering Department Bangalore Institute of Technology Bangalore India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383867

Road traffic has been an open challenge in a highly-populated area in the world. India is one of them where traffic management is a crucial problem to solve. Road traffic congestion, traffic rule violation, road accidents are the outcome of limitless traffic. The paper attempts to highlight the Real-Time Traffic Control System (RTTCS) monitoring vehicles, passengers, detecting objects on the road, and license plate detection. This paper proposes an RTTCS based on Machine Learning (ML) model, which takes traffic streaming as an input, monitors the traffic by detecting objects, finds the count of the objects per class, detects license plates and recognizes license plate characters using Easy-OCR. For depth analysis, the RTTCS analysis is performed for a particular location at various timestamps for easy traffic monitoring. The proposed system uses the you Only Look once version-4 (YOLOv4) for object detection (e.g., bicycle, motorbike, cars). The transfer learning concept uses pre-trained convolutional weights to optimize the model. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Smart Monitoring and Irrigation Regulation via IoT and Cloud 8

Smart Monitoring and Irrigation Regulation via IoT and Cloud

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Sumalatha, Konatham Harshdeep, Kumar Vellore Institute of Technology School of Computer Science & Engineering Department of Database Systems Vellore India Vellore Institute of Technology Computer Science and Engineering Vellore India

ISBN: (纸本)9798350376425

The increasing demand for agricultural produce and the strain on global water resources highlight the need for innovative solutions to improve water efficiency in farming. This work introduces an IoT-powered Smart Irrigation System designed to optimize water usage, ensuring sustainable crop cultivation. Traditional irrigation methods often lead to inefficiencies, wasting water and increasing costs, as they fail to consider varying soil moisture and environmental conditions across fields. This can result in suboptimal crop growth and resource depletion. To overcome these challenges, the proposed system integrates IoT technology with smart irrigation practices. Sensors deployed in the field collect real-time data on soil moisture, temperature, humidity, and light intensity, which a central controller then processes. Using cloud-based analytics, the controller adjusts irrigation schedules and water distribution to match current conditions precisely. The system's primary goal is to create an eco-friendly, cost-effective solution that reduces water waste, lowers operational costs, and minimizes environmental impact. Scalable and adaptable to various crops and environments, this smart irrigation system promises to improve crop yields, promote sustainable agriculture, and address water scarcity challenges globally. © 2024 IEEE.

关键词： Cloud Computing Real-Time Data Analytics Smart Irrigation Soil Moisture Sensors

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：