检索结果-内蒙古大学图书馆

2024 International Conference on Computing and Intelligent reality Technologies, ICCIRT 2024

作者： Layek, Santanu Sharma, Gauransh Agarwal, Vihan Chandru Vignesh, C. School of Computer Science and Engineering Vellore Institute of Technology Tami Nadu Vellore India School of Computer Science and Engineering Tami Nadu Vellore India

ISBN: (纸本)9798331510299

The "Advanced Chat Application Integrating Machine learning for Sentimental Analysis" is a progressive interface that utilizes machine learning (ML) algorithm to analyze user's interaction and offer compatibility services with emotional intelligence in real-time. This platform offers the chat user an intelligent map of a comprehensive communication interface with the ability to also complete the human ability in the sense of the differentiation between emotions where it will show empathy based on the context of the user. By the implementation of sentiment analysis feature, the chat application is able to identify the emotions as happy, sad, angry or neutral that people portray when in a conversational mode of text. This is made possible by natural language processing (NLP) encoding using the artificial intelligence models that enjoy the capacity to determine the emotional content of the text messages by virtue of deep learning algorithms which were trained on large data. Therefore, the sentiment detection is able to increase the level of participation, improve on the services offered to patrons, and most importantly, the identification of symptoms of mental disorders in their early stages. © 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

Interpretation of Sign Language Using Machine learning 2

Interpretation of Sign Language Using Machine Learning

引用

2nd International Conference Computational and Characterization Techniques in Engineering and Sciences, IC3TES 2024

作者： Srivastava, Palak Hazela, Bramah Singh, Shikha Asthana, Pallavi Pandey, deependra Singh, Kamlesh Kumar Singh, Vineet Amity University Amity School of Engineering & Technology Department of Computer Science Engineering Uttar Pradesh India Amity University Amity School of Engineering & Technology Department of Electronics & Communication Engineering Uttar Pradesh India

ISBN: (纸本)9798350364699

Sign language detection using machine learning has emerged as a crucial area of research aimed at bridging communication barriers between individuals with hearing impairments and the broader community. This paper explores the application of machine learning techniques for the automatic recognition and interpretation of sign language gestures. A systematic review of existing methodologies, including traditional machine learning approaches and recent advancements in deep learning architectures, reveals key challenges such as variability in signing styles, regional dialects, and real-time processing requirements. To address these challenges, we propose a novel approach that leverages convolutional neural networks (CNNs) and long short-term memory (LSTM) models, which have demonstrated significant improvements in accuracy and generalization across diverse datasets. Our experimental results show the efficacy of these models on benchmark sign language datasets, achieving high levels of accuracy and robustness in real-world conditions. Furthermore, this study discusses the potential societal impacts of sign language detection systems in education, healthcare, and everyday communication, emphasizing the role of technological innovation in fostering inclusivity. By advancing machine learning methodologies, we contribute to the development of accessible communication solutions for individuals with hearing impairments. © 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

Optimized CNN Architecture based on Mutant Particle Swarm Optimization and Opposition Based learning for image Classification 1

Optimized CNN Architecture based on Mutant Particle Swarm Op...

引用

1st International Conference on Cyber Security and Computing, CyberComp 2024

作者： Saleem, Muhammad Asif Senan, Norhalina Aamir, Muhammad Universiti Tunn Hussein Onn Malaysia Faculty of Computer Science and Information Technology Batu Pahat Malaysia University of Oxford Department of Computer Science United Kingdom

ISBN: (纸本)9798350387728

Recent improvements in Convolution Neural Networks (CNN) have demonstrated extraordinary performance in solving real-world problems. However, the performance of CNN depends purely on its architectural parameters and their arrangements. Designing CNN architecture for a particular problem is time consuming and requires a deep understanding of Neural networks, which is not possible for each researcher. In this research, an automated CNN architecture based on the Particle Swarm Optimization algorithm empowered with an iterative mutation operator and Opposition-based learning strategy is proposed for image classification problems. The proposed technique significantly enhances performance in terms of accuracy, precision-recall, and convergence rate. The effectiveness of the proposed method is evaluated on benchmark datasets, including CIFAR-10, MNIST-Fashion, and Paddy Doctor Dataset. It demonstrates superior performance compared to traditional models which are Alex-Net, VGG19, GA-CNN, and PSO-CNN. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Supporting deep learning Based Autonomous Driving Applications on Resource-Constrained Devices 2

Supporting Deep Learning Based Autonomous Driving Applicatio...

引用

2nd IEEE International Conference on Mobility, Operations, Services and Technologies, MOST 2024

作者： Uprety, Ishparsh Agnello, Griffen Zhao, Xinghui Washington State University Vancouver School of Engineering and Computer Science 14204 NE Samon Creek Ave. VancouverWA United States

ISBN: (纸本)9798350307733

With recent advances in computing and sensing technologies, autonomous driving has gained increasing interest and become a promising platform to support the next generation intelligent transportation systems. A critical requirement for autonomous driving systems is to be able to utilize AI and machine learning techniques to make reliable decisions on edge devices in a timely manner. Deploying reliable machine learning models on edge devices in a real-time environment is a challenging task. real-time applications such as traffic surveillance or traffic sign detection require consistently low latency in order for the device to keep up with its environment. Edge devices are able to compute machine learning tasks without needing to offload computation to a cloud server, however they often have a tight limit on the amount of available resources. Quantization is a model optimization technique used to increase inference speed at the cost of accuracy. In this paper, we carried out a comprehensive study on utilizing quantization to enable efficient and effective decision making for autonomous driving applications. Various quantization methods are analyzed, with a focus on the trade-offs between the learning performance and computational performance. Furthermore, we identify pre-processing techniques and types of data input that may improve the model's accuracy. The proposed approach will enhance the decision making process in resource-constrained environment, and provide more flexibility for deploying the autonomous driving applications. © 2024 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Advancing Alzheimer's Nodule Detection Through a Comprehensive Multi-Scene deep learning Framework 10

Advancing Alzheimer's Nodule Detection Through a Comprehensi...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Premkumar, C. Rajeshwari, R. Remya, R. Cholaathiraj, M.S. Reethika, A. Bharathidasan, S. Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Sathyamangalam India Cmr Institute of Technology Department of Computer Science and Engineering Bengaluru India Vel Tech Rangarajan Dr Sagunthala R&d institute of science and Technology Department of Electronics and Communication Engineering Chennai India Bannari Amman Institute of Technology Department of Artificial Intelligence and Machine Learning Sathyamangalam India Sri Ramakrishna Engineering College Department of Electronics and Communication Engineering Coimbatore India Erode Sengunthar Engineering College Department of Electronics and Communication Engineering Erode India

ISBN: (纸本)9798350384369

Determining the precise location of Alzheimer's nodules is essential for estimating the risk of brain cancer. Conventional CAD modules, including MRI, PET, and CT, struggle with feature extraction and segmentation due to time limits and complexity. This study proposes an efficient brain nodule detection technique based on the Multi-Scene deep learning Framework (MSDLF) that makes use of the vesselness filter. A four-channel CNN model is developed using information from two image sequences to enhance radiologists' ability to recognise four-stage nodules. This adaptable model may be used in two different classes. The outcomes demonstrate how well the MSDLF performs while processing substantial volumes of image data for brain nodule recognition, improving with accuracy 98.86% and 98.45% of sensitivity by using decreasing false positives. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Research on Group-level Pruning Algorithm Based on Progressive Sparsity Regularization 3

Research on Group-level Pruning Algorithm Based on Progressi...

引用

3rd International Conference on Electronics and Information Technology, EIT 2024

作者： Liu, Jianguo Zhou, Qi He, Yibo Chen, Wen Yin, Zhishuai Yan, Fuwu Zheng, Hao Wu, Youhua Foshan Xianhu Laboratory National Energy Key Laboratory for New Hydrogen-Ammonia Energy Technologies Foshan528200 China Wuhan University of Technology Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan China Wuhan University of Technology School of Automotive Engineering Hubei Wuhan430070 China SAIC-GM-Wuling Automobile Co. Ltd. Liuzhou545007 China

ISBN: (纸本)9798350369151

With the rapid development of autonomous driving systems, deep learning models play a crucial role in their implementation. However, these models typically have high computational complexity and storage demands, posing challenges to the real-time processing capabilities of embedded devices. To address this issue, this paper proposes a group-level pruning algorithm based on progressive sparsity regularization. The algorithm groups model parameters and progressively increases the sparsity regularization strength, effectively reducing computational load and storage requirements while maintaining model performance. Additionally, the algorithm introduces group-level weight importance calculation based on the L2-norm, combined with weight gradient direction information to achieve a more refined pruning strategy. Experimental results demonstrate that the proposed algorithm achieves a 2.58× speedup on the ResNet-56 model on the CIFAR dataset, significantly compressing the model's parameter size while maintaining accuracy. This research provides an effective solution for real-time applications such as autonomous driving, where efficient model deployment is essential. © 2024 IEEE.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Convergence of deep learning and Forensic Methodologies Using Self-attention Integrated EfficientNet Model for deep Fake Detection

引用

SN Computer Science 2024年第8期5卷 1-12页

作者： Singh, Rimjhim Padam Sree, Nichenametla Hima Reddy, Koti Leela Sai Praneeth Jashwanth, Kandukuri Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

The immensely increasing number of deepfake technologies poses significant challenges to digital media integrity, leading to the immediate need for effective deepfake detection methods. In light of the growing threat posed by sophisticated synthetic media, this paper tackles the urgent need for accurate deepfake detection in real-time by proposing a novel classification model employing a fine-tuned EfficientNet-B0 model with an optimally integrated Self-attention mechanism. The study also analyzes various deepfake generation techniques by utilizing a suite of Convolutional Neural Networks namely, XceptionNet, NasNetLarge, InceptionV3, ConNextv1, ConvNext2 and EfficientB0 model on the Celeb-DF dataset for baseline model selection and performance comparison purposes. The results prove that the proposed fine-tuned EfficientNet-B0 model with integrated self-attention mechanism is the most superior at identifying complex long-range dependencies and relations in various unconnected image regions, highlighting the importance of attention mechanisms in improving deep learning models for multimedia forensics with a remarkable F-score of 97.67%. In an era marked by the proliferation of sophisticated artificial intelligence (AI)-driven synthetic media, these findings establish the foundation for strengthening digital media platform security and protecting information authenticity. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Celeb-DF dataset EfficientNetB0 Multimedia forensics NasNetLarge Self-attention mechanism Xception deepfake detection

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Data Aggregation in Vehicular Ad Hoc Networks Using deep learning Techniques

Privacy-Preserving Data Aggregation in Vehicular Ad Hoc Netw...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Balaji, T.S. Hariharan, R. Glaret Subin, P. Balaji, S. Bharathi, S. Prasanna SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Electronics and Communication Engineering Tamilnadu Chennai India Saveetha Sch. of Eng. Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Electrical and Electronics Engineering Tamilnadu Chennai India SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Electronics and Communication Engineering Tamilnadu Chennai600026 India School of Electronics Engineering Vellore Institute of Technology Tamil Nadu Chennai600127 India

ISBN: (纸本)9798331542344

Vehicular Ad Hoc Networks (VANETs) are a significant breakthrough in intelligent transportation systems which allow vehicles to exchange information and with other vehicles and the surrounding infrastructure in realtime. But the utilization of vehicular data collection and aggregation poses problem areas in the issues of privacy, security and performance. This research presents a new conceptual model to employ deep learning algorithms for privacy preservation of data aggregated in V ANETs. We adopt differential privacy for providing privacy-preserving capabilities, federated learning and the usage of the blockchain make it more scalable and secure and edge computing to retain efficiency for solving these challenges. It's about adding controlled noise in order to prevent data points from being reverse engineered, differential privacy is used. Federated learning is used to decentralize the data processing, where participation of the central location is opted out and raw data transmission is kept to the barest minimum as a means of ensuring data privacy. Blockchain technology adds another layer of more secure and reliable aggregation of data improving the overall security of transactions and the prevention of alteration or sabotage. Edge computing is incorporated to ensure the real-time response of the system hence minimizing the latency of the system besides enhancing the performance of the system. In this regard, the study demonstrates that the proposed system ideally implements all the three objectives concerning privacy, data usefulness and real-time capability. Although using differential privacy slightly affects the accuracy of a model it greatly enhances the privacy of data. Together with edge computing, federated learning avoids performance degradation in privacy-preserving computations by decentralizing computations and minimizing transmission costs. The combination of block-chains with the existing networks helps to eliminate cases of data manipulation while

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Fast image Super-Resolution Based on Limit Gradient Embedding Cascaded Forest

引用

CIRCUITS SYSTEMS AND SIGNAL processing 2022年第4期41卷 2007-2026页

作者： Yang, Xin Wu, Chenhuan Zhou, Dake Li, Tao Nanjing Univ Aeronaut & Astronaut Sch Automat Engn Nanjing 211106 Peoples R China

At present, the deep learning super-resolution (SR) method has achieved excellent results, but it also faces problems such as large models, high computational cost, a large amounts of training data, and poor interpretability. However, traditional machine learning-based methods still have room for improvement in feature extraction and model structure. This paper constructs a gradient embedding cascade forest structure on the basis of random forest and proposes a limit gradient embedding cascaded forest SR (LGECFSR) model. In feature construction, we not only adopt the first-order gradient, the second-order gradient, and other features of the image but also fuse the information of the original LR image. In addition, image blocks of different sizes are used for training, which increases the model's generalization ability. Compared with the state-of-the-art machine learning-based methods, our method achieves the best performance and the second-best computational speed. In addition, compared with some deep learning-based methods, our model has a similar reconstruction effect and the best computational speed. In detail, for some reconstruction tasks, the Multi-Adds of LGECFSR is one-tenth to one-4000th of that of some current models. However, the SR performance of LGECFSR is the same or slightly better than that of some current classical algorithms.

关键词： Super resolution Cascade forest Machine learning Limit gradient embedding real time

来源：评论

学校读者我要写书评

暂无评论

Ultrareliable Low-Latency Slicing in Space-Air-Ground Multiaccess Edge Computing Networks for Next-Generation Internet of Things and Mobile Applications

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第3期11卷 3956-3978页

作者： Asheralieva, Alia Niyato, Dusit Wei, Xuetao Southern Univ Sci & Technol Dept Comp Sci & Engn Shenzhen 518055 Guangdong Peoples R China Loughborough Univ Dept Comp Sci Loughborough LE11 3TU England Nanyang Technol Univ Sch Comp Sci & Engn Jurong West 639798 Singapore Southern Univ Sci & Technol Res Inst Trustworthy Autonomous Syst Shenzhen 518055 Guangdong Peoples R China

We study the problem of ultrareliable and low-latency slicing in multiaccess edge computing (MEC) systems for the next-generation Internet of Things (IoT) and mobile applications operating in the space-air-ground integrated network. The network has a dynamic topology formed by multiple nonstationary nodes with unstable communication links and unreliable processing/transmission resources. Each node can be in one of two hidden states: 1) reliable-in which the node generates no data errors and no losses and 2) unreliable-when the node can generate/propagate random data errors/losses. Solving this problem is difficult, as it represents the nondeterministic polynomial-time (NP) hard nonconcave nonsmooth stochastic maximization problem which depends on the unknown hidden nodes' states and private information about local, dynamic parameters of each node, which is known only to this node, and not to other nodes. To address these challenges, we develop a new deep learning (DL) model based on the message passing graph neural network (MPNN) to estimate hidden nodes' states. We then propose a novel algorithm based on the online alternating direction method of multipliers (ADMMs)-an extension of the well-known classical "static" ADMM to dynamic settings, where our slicing problem can be solved distributedly, in real time, without revealing local (private) information of the nodes. We show that our algorithm converges to a global optimum of the slicing problem and has a good consistent performance even in highly dynamic, unreliable scenarios.

关键词： Heuristic algorithms Space-air-ground integrated networks Reliability Network topology Dynamic scheduling Vehicle dynamics Optimization deep learning (DL) dynamic optimization edge computing graph neural networks (GNNs) graphs Internet of Things (IoT) mathematical decomposition network slicing next-generation wireless networks nonconvex optimization space-air-ground integrated networks (SAGINs) ultrareliable and low-latency communications

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：