检索结果-内蒙古大学图书馆

A systematic literature review of visual feature learning: deep learning techniques, applications, challenges and future directions

引用

Multimedia Tools and Applications 2024年 1-58页

作者： Abdullahi, Mohammed Oyelade, Olaide Nathaniel Kana, Armand Florentin Donfack Bagiwa, Mustapha Aminu Abdullahi, Fatimah Binta Junaidu, Sahalu Balarabe Iliyasu, Ibrahim Ore-ofe, Ajayi Chiroma, Haruna Department of Computer Science Ahmadu Bello University Zaria Zaria Nigeria Department of Mechanical Engineering Ahmadu Bello University Zaria Nigeria Department of Computer Engineering Ahmadu Bello University Zaria Nigeria College of Computer Science and Engineering University of Hafr Al Batin Hafar Al-Batin31991 Saudi Arabia School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Belfast United Kingdom

Visual Feature Learning (VFL) is a critical area of research in computer vision that involves the automatic extraction of features and patterns from images and videos. The applications of VFL are vast, including object detection and recognition, facial recognition, scene understanding, medical image analysis, and autonomous vehicles. In this paper, we propose to conduct extensive systematic literature review (SLR) on VFL based on deep learning algorithms. The paper conducted an SLR covering deep learning algorithms such as Convolutional Neural Networks (CNNs), Autoencoders, and Generative Adversarial Networks (GANs) including their variants. The review highlights the importance of VFL in computer vision and the limitations of traditional feature extraction techniques. Furthermore, it provides an in-depth analysis of the strengths and weaknesses of various deep learning algorithms for solving problems in VFL. The discussion of the applications of VFL provides an insight into the impact of VFL on various industries and domains. The review also analyzed the challenges faced by VFL, such as data scarcity and quality, overfitting, generalization, interpretability, and explainability. The discussion of future directions for VFL includes hybrid techniques, unsupervised feature learning, continual learning, attention-based models, and explainable AI. These techniques aim to address the challenges faced by VFL and improve the performance of the models. The systematic literature review concludes that VFL is a rapidly evolving field with the potential to transform many industries and domains. The review highlights the need for further research in VFL and emphasizes the importance of responsible use of VFL models in various applications. The review provides valuable insights for researchers and practitioners in the field of computer vision, who can use these insights to enhance their work and ensure the responsible use of VFL models. © The Author(s), under exclusive licence to

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A novel deep dual self-attention and Bi-LSTM fusion framework for Parkinson’s disease prediction using freezing of gait: a biometric application

引用

Multimedia Tools and Applications 2024年第33期83卷 80179-80200页

作者： Habib, Zeeshan Mughal, Muhammad Ali Khan, Muhammad Attique Hamza, Ameer Alturki, Nazik Jamel, Leila Department of Electrical Engineering HITEC University Taxila Pakistan Department of Computer Science HITEC University Taxila Pakistan Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia

Parkinson’s disease (PD) disorder is caused by the imbalance of inhibitory dopamine and excitatory acetylcholine neurotransmitters, which causes hindrance in locomotion. Freezing of gait (FOG), tremors, and bradykinesia are the most debilitating and disconcerting symptoms of Parkinson’s Disease (PD). FOG episodes occur due to neurological control disorder and motorized impairments, which sternly hinder voluntary movement and forward locomotion. The computational intelligence techniques can effectively predict PD from the sensor data. To detect the FOG episodes often experienced by PD patients, this paper utilizes a 5G spectrum that operates at 4.8 GHz. The main idea of the proposed system is to extract the wireless channel characteristics information (containing amplitude variances) that can be integrated into a 5G communication system. This system collects data through wireless devices such as dipole antennas, network interface cards, and RF signal generators. Five human activities were performed: fast walking, slow walking, sitting on a chair, FOG episodes, and voluntary stopping. We proposed a novel deep dual self-attention and Bi-LSTM fusion architecture for PD prediction to train the collected dataset. Two architectures have been proposed, namely Deep Dual Attention Neural Network (D2ANN) and BiLSTM Neural Network (BNN), for the classification of PD using Chanel State Information (CSI) data. After that, the most prominent information is extracted using self-attention activation. A newly informed weighted fusion approach is proposed, and tree growth optimization is employed for the best feature selection. Finally, the selected features are classified using a multilayer full SoftMax neural network. The experimental process was conducted on FOG wireless sensor network data and obtained the highest accuracy of 98.66%. Compared to the results with state-of-the-art techniques, the proposed framework shows improved accuracy, recall, and precision rates. © The Author(s

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Kinmen Wind Lion Face Generation Based on the Deep Convolutional Generative Adversarial Network 13

Kinmen Wind Lion Face Generation Based on the Deep Convoluti...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Wu, Chia-Huan Zhao, Yu-Xiang Chou, Cheng-Hou Hsieh, Yi-Zeng National Taiwan University of Science and Technology Department of Electrical and Computer Engineering Taiwan National Quemoy University Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798350355079

Under the advancements of science and technology at present, artificial intelligence has become widely applied in daily life. Hence, deep learning has attracted much attention in recent years and has been widely used in recognition, classification and generation. The results generated by generative adversarial networks have become increasingly realistic and are now being applied to human face generation and reconstruction. Among the various technologies, the deep convolutional generative adversarial network (DCGAN) is more widely used. Based on the trained DCGAN of human and cat faces, this paper collected Kinmen wind lion data by YOLOv3 and crawler technology and transferred the data to the DCGAN of wind lions through network-based transfer learning to generate complete wind lion faces. The experimental process consisted of four parts. The wind lion dataset was directly used to train the DCGAN in the first two parts, and the DCGAN of the human and cat faces was used for transfer learning in the second two parts. According to the results, the training effect of human face-based transfer learning was the best and was the closest to Kinmen's wind lions. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Secure information embedding in images with hybrid firefly algorithm

引用

Neural Computing and Applications 2024年 1-14页

作者： Nokhwal, Sahil Chandrasekharan, Manoj Chaudhary, Ankit Department of Computer Science University of Memphis MemphisTN United States Department of Electrical and Computer Engineering University of Memphis MemphisTN United States School of Engineering Jawaharlal Nehru University Delhi New Delhi India

Various methods have been proposed to secure access to sensitive information over time, such as many cryptographic methods in use to facilitate secure communications on the internet. But other methods like steganography have been overlooked which may be more suitable in cases where the act of transmission of sensitive information itself should remain a secret. Multiple techniques that are commonly discussed for such scenarios suffer from low capacity and high distortion in the output signal. This research introduces a novel steganographic approach for concealing a confidential portable document format (PDF) document within a host image by employing the hybrid firefly algorithm (HFA) proposed to select the pixel arrangement. This algorithm combines two widely used optimization algorithms to improve their performance. The suggested methodology utilizes the HFA algorithm to conduct a search for optimal pixel placements in the spatial domain. The purpose of this search is to accomplish two main goals: increasing the host image’s capacity and reducing distortion. Moreover, the proposed approach intends to reduce the time required for the embedding procedure. The findings indicate a decrease in image distortion and an accelerated rate of convergence in the search process. The resultant embeddings exhibit robustness against steganalytic assaults, hence rendering the identification of the embedded data, a formidable undertaking. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Seamless Graph Task Scheduling over Dynamic Vehicular Clouds: A Hybrid Methodology for Integrating Pilot and Instantaneous Decisions

引用

IEEE Transactions on Services Computing 2025年第03期18卷 1753-1768页

作者： Guo, Bingshuo Liwang, Minghui Xia, Xiaoyu Li, Li Jiao, Zhenzhen Hosseinalipour, Seyyedali Wang, Xianbin Xiamen University School of Informatics Fujian China Rmit University School of Computing Technologies MelbourneVIC Australia Tongji University Department of Control Science and Engineering Shanghai China Beijing Teleinfo Technology Co. Ltd. Caict IF-Labs China University at Buffalo-SUNY Department of Electrical Engineering NY United States Western University Department of Electrical and Computer Engineering ON Canada

Vehicular clouds (VCs) play a crucial role in the Internet-of-Vehicles (IoV) ecosystem by securing essential computing resources for a wide range of tasks. This paPertackles the intricacies of resource provisioning in dynamic VCs for computation-intensive tasks, represented by undirected graphs for parallel processing over multiple vehicles. We model the dynamics of VCs by considering multiple factors, including varying communication quality among vehicles, fluctuating computing capabilities of vehicles, uncertain contact duration among vehicles, and dynamic data exchange costs between vehicles. Our primary goal is to obtain feasible assignments between task components and nearby vehicles, called templates, in a timely manner with minimized task completion time and data exchange overhead. To achieve this, we propose a hybrid graph task scheduling (P-HTS) methodology that combines offline and online decision-making modes. For the offline mode, we introduce an approach called risk-aware pilot isomorphic subgraph searching (RA-PilotISS), which predicts feasible solutions for task scheduling in advance based on historical information. Then, for the online mode, we propose time-efficient instantaneous isomorphic subgraph searching (TE-InstaISS), serving as a backup approach for quickly identifying new optimal scheduling template when the one identified by RA-PilotISS becomes invalid due to changing conditions. Through comprehensive experiments, we demonstrate the superiority of our proposed hybrid mechanism compared to state-of-the-art methods in terms of various evaluative metrics, e.g., time efficiency such as the delay caused by seeking for possible templates and task completion time, as well as cost function, upon considering different VC scales and graph task topologies. © 2025 IEEE.

关键词： Undirected graphs

来源：评论

学校读者我要写书评

暂无评论

Social NSTransformers: Low-Quality Pedestrian Trajectory Prediction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5575-5588页

作者： Jiang, Zihan Ma, Yiqun Shi, Bingyu Lu, Xin Xing, Jian Goncalves, Nuno Jin, Bo Suzhou215000 China Northeast Forestry University College of Computer and Control Engineering Harbin150000 China University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Coimbra3030-290 Portugal

This article introduces a novel model for low-quality pedestrian trajectory prediction, the social nonstationary transformers (NSTransformers), that merges the strengths of NSTransformers and spatiotemporal graph transformer (STAR). The model can capture social interaction cues among pedestrians and integrate features across spatial and temporal dimensions to enhance the precision and resilience of trajectory predictions. We also propose an enhanced loss function that combines diversity loss with logarithmic root mean squared error (log-RMSE) to guarantee the reasonableness and diversity of the generated trajectories. This design adapts well to complex pedestrian interaction scenarios, thereby improving the reliability and accuracy of trajectory prediction. Furthermore, we integrate a generative adversarial network (GAN) to model the randomness inherent in pedestrian trajectories. Compared to the conventional standard Gaussian distribution, our GAN approach better simulates the intricate distribution found in pedestrian trajectories, enhancing the trajectory prediction's diversity and robustness. Experimental results reveal that our model outperforms several state-of-the-art methods. This research opens the avenue for future exploration in low-quality pedestrian trajectory prediction. © 2024 IEEE.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

ProTEA: Programmable Transformer Encoder Acceleration on FPGA

ProTEA: Programmable Transformer Encoder Acceleration on FPG...

引用

2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024

作者： Kabir, Ehsan Bakos, Jason D. Andrews, David Huang, Miaoqing University of Arkansas Department of Electrical Engineering and Computer Science Fayetteville United States University of South Carolina Department of Computer Science and Engineering United States

ISBN: (纸本)9798350355543

Transformer neural networks (TNN) have been widely utilized on a diverse range of applications, including natural language processing (NLP), machine translation, and computer vision (CV). Their widespread adoption has been primarily driven by the exceptional performance of their multi-head self-attention block used to extract key features from sequential data. The multi-head self-attention block is followed by feedforward neural networks, which play a crucial role in introducing non-linearity to assist the model in learning complex patterns. Despite the popularity of TNNs, there has been limited numbers of hardware accelerators targeting these two critical blocks. Most prior works have concentrated on sparse architectures that are not flexible for popular TNN variants. This paper introduces ProTEA, a runtime programmable accelerator tailored for the dense computations of most of state-of-the-art transformer encoders. ProTEA is designed to reduce latency by maximizing parallelism. We introduce an efficient tiling of large matrices that can distribute memory and computing resources across different hardware components within the FPGA. We provide run time evaluations of ProTEA on a Xilinx Alveo U55C high-performance data center accelerator card. Experimental results demonstrate that ProTEA can host a wide range of popular transformer networks and achieve near optimal performance with a tile size of 64 in the multi-head self-attention block and 6 in the feedforward networks block when configured with 8 parallel attention heads, 12 layers, and an embedding dimension of 768 on the U55C. Comparative results are provided showing ProTEA is 2.5× faster than an NVIDIA Titan XP GPU. Results also show that it achieves 1.3 - 2.8× speed up compared with current state-of-the-art custom designed FPGA accelerators. © 2024 IEEE.

关键词： Attention Encoder FPGA Hardware Accelerators High-Level Synthesis Natural Language Processing Neural Networks Transformer

来源：评论

学校读者我要写书评

暂无评论

Quality-Relevant Modeling and Monitoring of Industrial Cyber-Physical Systems: The Semi-Supervised Dynamic Latent Variable Models

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 39-47页

作者： Zhou, Le Wang, Yaoxin Wu, Yuanqing He, Shenghuang Song, Zhihuan Zhejiang University of Science and Technology Department of Automation and Electrical Engineering Hangzhou310023 China Guangdong University of Technology Department of Automation Guangzhou510006 China Dongguan University of Technology Department of Computer Science and Technology Dongguan523808 China Ningbo Industrial Internet Institute Ningbo315012 China Zhejiang University Department of Control Science and Engineering Hangzhou310027 China

In modern industrial cyber-physical systems, a mass of process variables has been obtained by the high-sampling online sensors. Meanwhile, the key quality indexes are usually obtained infrequently from the laboratory. Hence, these quality variables are with low sampling rate. To avail of the complete process and quality variables with various sampling rates in the dynamic processes, a set of semi-supervised dynamic latent variable models are proposed for dynamic modeling and quality-relevant monitoring. The proposed models have built a unified structure to consider both the auto-correlations and cross-correlations between the process and quality variables with unbalanced sampling sizes. Hence, the feature extraction of the time series data is dynamically adjusted under the guidance of the quality variables. Then, the quality-relevant monitoring schemes are proposed, which is validated by a numerical case and an actual wastewater treatment process. © 2024 IEEE. All rights reserved.

关键词： Indexes Probabilistic logic Kalman filters Noise Cyber-physical systems Analytical models Parameter estimation Time series analysis Process monitoring Numerical models

来源：评论

学校读者我要写书评

暂无评论

Understanding Consumer Perceptions of Green Software: A Study in the Online Social Media Marketing Context

Understanding Consumer Perceptions of Green Software: A Stud...

引用

2023 International Conference on Industry sciences and computer science Innovation, iSCSi 2023

作者： Irtisamul, Shadat Hassan, Marzan Binte Sadia, Farzana Hasan, Mahady Rokonuzzaman, Mohammad Department of Computer Science and Engineering Independent University Bangladesh Dhaka Bangladesh Department of Electrical Engineering and Computer Science North South University Dhaka Bangladesh

This study explores the influence of social media marketing on consumers' decisions to purchase green software and identifies key factors affecting those decisions. The findings contribute to effective marketing strategies for promoting environmentally friendly technologies and increasing the adoption of green software. Social media marketing is highlighted as a crucial platform for communication and collaboration, shaping consumers' subjective norms and influencing decision-making. By utilizing persuasive techniques and emphasizing eco-friendly choices, social media marketing can significantly impact consumers' behavior, attitudes, and decision-making processes, promoting sustainable practices and increasing the adoption of eco-friendly software. © 2024 The Authors. Published by ELSEVIER B.V.

关键词： Consumer behavior

来源：评论

学校读者我要写书评

暂无评论

Enhancing sound pressure output in graphene-based hybrid bone conduction hearing aids through electromagnetic and electrostatic integration

引用

Nano Research 2025年第4期18卷 425-434页

作者： Dong-Kwan Lee Hyunwoo Baek Byung-Ho Kang § Jongchan Yoo Kun-Woo Nam Sang Hyun Lee Illsoo Sohn Eunjung Han June Choi Sung-Hoon Park Department of Mechanical Engineering Soongsil UniversitySeoul 06978Republic of Korea Department of Otorhinolaryngology-Head and Neck Surgery Korea University College of MedicineAnsan HospitalAnsan 15355Republic of Korea School of Electrical Engineering Korea UniversitySeoul 02841Republic of Korea Department of Computer Science and Engineering Seoul National University of Science and TechnologySeoul 01811Republic of Korea

Bone conduction hearing aids(BCHA)actively serve patients with conductive hearing loss or external auditory canal problems,including auditory canal atresia,ossicular dislocation,*** are typically categorized into surgically implanted devices,embedded directly into the skull,and adhesive devices,which transmit sound through the *** latter are advantageous for being noninvasive and suitable for children under ***,adhesive devices,due to their sound transmission method,require enhanced sound output performance compared to implanted ***,known for its low mass density yet excellent mechanical and electrical properties,finds application in various electronic ***,it serves as a diaphragm in electroacoustic transducers,enabling stable vibrations across broad frequency *** electroacoustic transducers of BCHA are typically driven by electromagnetic methods,which may be effective in low-frequency ranges but not in high-frequency *** study successfully introduced a hybrid approach that combines the complementary advantages of both electromagnetic and electrostatic modes by utilizing a graphene sheet as the diaphragm for a hybrid graphene *** electrostatic mode,which performs better in highfrequency ranges compared to the electromagnetic mode,was implemented in this hybrid *** to the measured frequency response data,the hybrid mode showed up to an 11 dB improvement compared to the electromagnetic mode and up to a 21 dB improvement compared to the electrostatic mode,exhibiting a relatively flat shape over a wide frequency ***,the device’s effectiveness as a BCHA is confirmed through experiments on rabbits,showcasing its potential in auditory aid advancement.

关键词： graphene bone conduction hearing aid loudspeaker frequency response

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：