检索结果-内蒙古大学图书馆

International Conference on Computer and Communications Technologies (ICCCT)

作者： N Shivaanivarsha J Swetha VL Ram Lashmi G S Yaswanth Rao Department of Electronics and Communication Engineering Sri Sairam Engineering College Chennai India

ISBN: (数字)9798331537579

ISBN: (纸本)9798331537586

Analysis of Detour Index in Graph Joins and Special Graph Structures Vehicular networks are crucial for modern transportation safety and efficiency. However, in adverse weather conditions such as fog, reduced visibility severely disrupts vehicle-to-vehicle (V2V) communication, increasing the risk of chain accidents. Traditional centralized approaches for managing vehicular communication suffer from high latency, limited scalability, and data privacy concerns, making them unsuitable for real-time decision-making in dynamic environments. To address these challenges, this project proposes a Federated learning Framework for Securing Vehicular Networks Using AI, enabling decentralized, privacy-preserving, and real-time threat detection in vehicular networks. The proposed system leverages Artificial Intelligence (AI) and Federated learning (FL) to enhance situational awareness and predict collision risks. A deep learning-based object detection model, utilizing the YOLO algorithm, identifies obstacles, vehicles, and hazardous conditions in low-visibility environments. Edge detection techniques further improve visual clarity and detection accuracy. Federated learning enables vehicles to collaboratively train AI models on local data without sharing raw information, ensuring data privacy and adaptability to real-world scenarios. Secure vehicle-to-vehicle (V2V) communication enhances decision-making speed, reducing latency in critical situations. By integrating AI-driven predictive analysis, federated learning, and decentralized data processing, this system significantly improves vehicular safety in challenging weather conditions. It ensures real-time hazard detection, reduces the likelihood of chain accidents, enhances data privacy, and scales effectively for large vehicular networks. This innovation marks a critical step toward intelligent, autonomous, and resilient transportation systems in smart cities.

关键词： YOLO Data privacy Federated learning image edge detection Decision making Vehicular ad hoc networks Transportation real-time systems Artificial intelligence Meteorology

来源：评论

学校读者我要写书评

暂无评论

ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation

引用

PATTERN RECOGNITION LETTERS 2021年 145卷 118-126页

作者： Liu, Yu Yang, Fan Ginhac, Dominique Univ Bourgogne Franche Comte ImViA EA7535 F-21078 Dijon France

Interpreting human actions requires understanding the spatial and temporal context of the scenes. Stateof-the-art action detectors based on Convolutional Neural Network (CNN) have demonstrated remarkable results by adopting two-stream or 3D CNN architectures. However, these methods typically operate in a non-real-time, ofline fashion due to system complexity to reason spatio-temporal information. Consequently, their high computational cost is not compliant with emerging real-world scenarios such as service robots or public surveillance where detection needs to take place at resource-limited edge devices. In this paper, we propose ACDnet, a compact action detection network targeting real-time edge computing which addresses both efficiency and accuracy. It intelligently exploits the temporal coherence between successive video frames to approximate their CNN features rather than naively extracting them. It also integrates memory feature aggregation from past video frames to enhance current detection stability, implicitly modeling long temporal cues over time. Experiments conducted on the public benchmark datasets UCF-24 and JHMDB-21 demonstrate that ACDnet, when integrated with the SSD detector, can robustly achieve detection well above real-time (75 FPS). At the same time, it retains reasonable accuracy (70.92 and 49.53 frame mAP) compared to other top-performing methods using far heavier configurations. Codes will be available at https://***/dginhac/ACDnet . (c) 2021 Elsevier B.V. All rights reserved.

关键词： Action detection real-time video processing Edge computing Motion-guided features deep learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised deep learning for 3D reconstruction with dual-frequency fringe projection profilometry

引用

OPTICS EXPRESS 2021年第20期29卷 32547-32567页

作者： Fan, Sizhe Liu, Shaoli Zhang, Xu Huang, Hao Liu, Wei Jin, Peng Beijing Inst Technol Sch Mech Engn Beijing 100081 Peoples R China

The fringe projection profilometry (FPP) technique has been widely applied in three-dimensional (3D) reconstruction in industry for its high speed and high accuracy. Recently, deep learning has been successfully applied in FPP to achieve high-accuracy and robust 3D reconstructions in an efficient way. However, the network training needs to generate and label numerous ground truth 3D data, which can be time-consuming and labor-intensive. In this paper, we propose to design an unsupervised convolutional neural network (CNN) model based on dual-frequency fringe images to fix the problem. The fringe reprojection model is created to transform the output height map to the corresponding fringe image to realize the unsupervised training of the CNN. Our network takes two fringe images with different frequencies and outputs the corresponding height map. Unlike most of the previous works, our proposed network avoids numerous data annotations and can be trained without ground truth 3D data for unsupervised learning. Experimental results verify that our proposed unsupervised model (1) can get competitive-accuracy reconstruction results compared with previous supervised methods, (2) has excellent anti-noise and generalization performance and (3) saves time for dataset generation and labeling (3.2 hours, one-sixth of the supervised method) and computer space for dataset storage (1.27 GB, one-tenth of the supervised method). (C) 2021 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： Fourier transforms Fringe analysis Fringe projection image processing Phase unwrapping Three dimensional reconstruction

来源：评论

学校读者我要写书评

暂无评论

Enhancement or Super-Resolution: learning-based Adaptive Video Streaming with Client-Side Video processing

Enhancement or Super-Resolution: Learning-based Adaptive Vid...

引用

IEEE International Conference on Communications (ICC)

作者： Yang, Junyan Jiang, Yang Wang, Shuoyao Shenzhen Univ Coll Elect & Informat Engn Shenzhen Peoples R China Inst High Performance Comp Singapore Singapore

ISBN: (数字)9781538683477

ISBN: (纸本)9781538683477

The rapid development of multimedia and communication technology has resulted in an urgent need for high-quality video streaming. However, robust video streaming under fluctuating network conditions and heterogeneous client computing capabilities remains a challenge. In this paper, we consider an enhancement-enabled video streaming network under a time-varying wireless network and limited computation capacity. "Enhancement" means that the client can improve the quality of the downloaded video segments via image processing modules. We aim to design a joint bitrate adaptation and client-side enhancement algorithm toward maximizing the quality of experience (QoE). We formulate the problem as a Markov decision process (MDP) and propose a deep reinforcement learning (DRL)-based framework, named ENAVS. As video streaming quality is mainly affected by video compression, we demonstrate that the video enhancement algorithm outperforms the super-resolution algorithm in terms of signal-to-noise ratio and frames per second, suggesting a better solution for client processing in video streaming. Ultimately, we implement ENAVS and demonstrate extensive testbed results under real-world bandwidth traces and videos. The simulation shows that ENAVS is capable of delivering 5% more QoE under the same bandwidth and computing power conditions as conventional ABR streaming.

关键词： Adaptive video streaming video enhancement reinforcement learning quality of experience(QoE)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Local Filters in Graph Convolutional Neural Networks 22nd

Dynamic Local Filters in Graph Convolutional Neural Networks

引用

22nd International Conference on image Analysis and processing (ICIAP)

作者： Apicella, Andrea Isgro, Francesco Pollastro, Andrea Prevete, Roberto Univ Naples Federico II Dept Elect Engn & Informat Technol Naples Italy Lab Augmented Real Hlth Monitoring ARHeMLab Naples Italy Privacy Applicat AIPA Lab Lab Artificial Intelligence Naples Italy Lawrence Berkeley Natl Lab Berkeley CA 94720 USA

ISBN: (纸本)9783031431524;9783031431531

Over the last few years, we have seen increasing data generated from non-Euclidean domains, usually represented as graphs with complex relationships. Graph Neural Networks (GNN) have gained a high interest because of their potential in processing graph-structured data. In particular, there is a strong interest in performing convolution on graphs using specific GNN architectures, generally called Graph Convolutional Neural Networks (GCNN). This paper presents a novel method to adapt the behaviour of a GCNN using an input-based dynamically generated filter. Notice that the idea of adapting the network behaviour to the inputs they process to maximize the total performances has aroused much interest in the neural networks literature over the years. The experimental assessment confirms the capabilities of the proposed approach, achieving promising results using simple architectures with a low number of filters.

关键词： Graph Convolutional Neural Networks deep learning Dynamic Neural Networks Programmable ANNs Graph Structure learning

来源：评论

学校读者我要写书评

暂无评论

Voice Command Recognition for Drone Control by deep Neural Networks on Embedded System 8

Voice Command Recognition for Drone Control by Deep Neural N...

引用

8th International Conference on Electrical and Electronics Engineering (ICEEE)

作者： Yapicioglu, Cengizhan Dokur, Zumray Olmez, Tamer Istanbul Tech Univ Dept Elect & Commun Engn Istanbul Turkey

ISBN: (纸本)9781665440714

Speech recognition and its applications for controlling a system has been an important and attractive issue over the last few decades. Controlling electronic devices by speech commands allows us to manage systems quickly and easily since users would not need any additional information or remote controller. Being able to communicate a system by using speech commands also brings with the requirements of fast and accurate response. So, at the present, speech recognition algorithms are extensively performing on high performance computers. However, the improvements of system on a chip (SoC) board and deep neural network based algorithms, make it possible to execute such kind of programs on them. The proposed study defines a model for controlling a drone system by using Turkish speech directional commands in real time which is based on deep learning approaches using spectrogram images. At first, speech commands are detected in real time with the help of signal energy and zero crossing rate and these are converted to log spectrogram images. A CNN (three convolutional layers and a fully connected layer) structure is created and trained by feeding those images. Then, the trained model is moved to embedded board to achieve real time, low-cost performance. Speech commands are provided by the user instantaneously and transferred to the model as an input for decision. Then, algorithm decides which directional command is given by the user and desired operation is performed on the drone system. It is observed that, by using the proposed model, accuracies of 95.72% for offline dataset and 92,88% for real time classification are obtained.

关键词： speech recognition spectrogram convolutional neural networks deep learning speech processing image processing embedded systems

来源：评论

学校读者我要写书评

暂无评论

processing and Segmentation of Human Teeth from 2D images using Weakly Supervised learning

Processing and Segmentation of Human Teeth from 2D Images us...

引用

2023 World Symposium on Digital Intelligence for Systems and Machines, DISA 2023

作者： Kunzo, Tomáš Kocur, Viktor Gajdošech, Lukáš Madaras, Martin Department of Applied Informatics Comenius University Bratislava Slovakia

ISBN: (纸本)9798350343533

Teeth segmentation is an essential task in dental image analysis for accurate diagnosis and treatment planning. While supervised deep learning methods can be utilized for teeth segmentation, they often require extensive manual annotation of segmentation masks, which is time-consuming and costly. In this research, we propose a weakly supervised approach for teeth segmentation that reduces the need for manual annotation. Our method utilizes the output heatmaps and intermediate feature maps from a keypoint detection network to guide the segmentation process. We introduce the TriDental dataset, consisting of 3000 oral cavity images annotated with teeth keypoints, to train a teeth keypoint detection network. We combine feature maps from different layers of the keypoint detection network, enabling accurate teeth segmentation without explicit segmentation annotations. The detected keypoints are also used for further refinement of the segmentation masks. Experimental results on the TriDental dataset demonstrate the superiority of our approach in terms of accuracy and robustness compared to state-of-the-art segmentation methods. Our method offers a cost-effective and efficient solution for teeth segmentation in real-world dental applications, eliminating the need for extensive manual annotation efforts. © 2023 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

LSNet: IDENTIFICATION OF COPPER AND STAINLESS STEEL USING LASER SPECKLE IMAGING IN DISMAL SURROUNDINGS

引用

INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION 2021年第4期36卷 256-263页

作者： Lu, Yuri Hu, Menghan Zhai, Guangtao Yang, Simon X. East China Normal Univ Shanghai Key Lab Multidimens Informat Proc Shanghai 200241 Peoples R China Shanghai Jiao Tong Univ Inst Image Commun & Informat Proc Shanghai 200240 Peoples R China Univ Guelph Sch Engn Adv Robot & Intelligent Syst Lab Guelph ON N1G 2W1 Canada

In unconstrained environments, identification of materials in a non-contact manner is of great necessity. However, most of the current material recognition technologies and their algorithms are contact measurement technologies under restricted conditions. In the current work, we attempt to propose a material recognition solution in the application scenario under harsh conditions. We first set up a specific application scenario to identify the copper and the stainless steel in the dark environment, where the existing material identification technologies are insufficient to carry out material recognition. To accomplish this task, we utilized a laser speckle imaging technique to acquire the speckle images of copper and stainless steel. As we used a laser in the near-infrared band, the whole process of image acquisition was silent. The hardware setup as described above can meet the requirements of multiple special application scenarios such as military reconnaissance. Afterwards, the obtained speckle image was combined with the proposed end-to-end model, i.e., Laser Speckle Network (LSNet). As a result, the classification accuracy of LSNet is 0.963, which is better than other deep learning networks. Also, LSNet is suitable for real-time detection due to the relatively less test time of 4 ms. The experimental results show that the combination of the laser speckle imaging and the proposed LSNet framework can achieve the recognition of the copper and the stainless steel in dismal surroundings. Experimental results show that the combination of the two techniques is feasible. Its unique advantages for dark environments are expected to lead to applications in the military reconnaissance, autonomous driving and other fields.

关键词： Laser speckle material recognition deep learning image processing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wearable based real-time Glucose Monitoring via Phasic image Representation learning based deep learning

arXiv

引用

arXiv 2024年

作者： Zhu, Yidong Aimandi, Nadia B. Arif Ul Alam, Mohammad University of Massachusetts Lowell United States University of Massachusetts Chan Medical School United States National Institute on Aging National Institute of Health

In the U.S., over a third of adults are pre-diabetic, with 80% unaware of their status. This underlines the need for better glucose monitoring to prevent type 2 diabetes and related heart diseases. Existing wearable glucose monitors are limited by the lack of models trained on small datasets, as collecting extensive glucose data is often costly and impractical. Our study introduces a novel machine learning method using modified recurrence plots in the frequency domain to improve glucose level prediction accuracy from wearable device data, even with limited datasets. This technique combines advanced signal processing with machine learning to extract more meaningful features. We tested our method against existing models using historical data, showing that our approach surpasses the current 87% accuracy benchmark in predicting real-time interstitial glucose levels. Copyright © 2024, The Authors. All rights reserved.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

RhinoGuardNet: An Integrated deep learning System for Monitoring, Movement Prediction, and Threat Detection in Javan Rhino Conservation

RhinoGuardNet: An Integrated Deep Learning System for Monito...

引用

Machine learning and Autonomous Systems (ICMLAS), International Conference on

作者： P. Ebby Darney A. Vegi Fernando R. Santhana Krishnan J. Relin Francis Raj V. Lavanya V. Vinoth Kumar Department of Electrical and Electronics Engineering Rajarajeswari College of Engineering Bangalore India Department of AIML (CS Cluster) Dayananda Sagar University Bangalore India Department of Electronics and Communication Engineering SCAD College of Engineering and Technology Cheranmhadevi India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Computer Science and Engineering Velammal College of Engineering and Technology Madurai India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Avadi Chennai India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

The Javan rhinoceros (Rhinoceros sondaicus), one of the most critically endangered species, faces numerous threats such as poaching, habitat destruction, and limited monitoring capabilities. Traditional conservation methods are often ineffective due to the vast and difficult-to-access nature of rhino habitats. This paper proposes a Hybrid deep learning (HDL) framework, combining CNNs, RNNs, and GNNs, to address these challenges and enhance conservation efforts. The proposed system offers a comprehensive solution for real-time rhino monitoring, poacher detection, and habitat preservation. The framework integrates CNNs for image-based monitoring, enabling the detection of rhinos, poachers, and habitat changes using camera trap images, drone footage, and satellite images. RNNs, specifically LSTM networks, are employed to analyze bioacoustic recordings from forest microphones, capturing long-term dependencies in sound data to detect rhino vocalizations and poaching sounds like gunshots or chainsaws. In addition, GNNs are utilized to process GPS tracking data to model spatial-temporal relationships and predict rhino movement, optimizing anti-poaching patrol routes and identifying high-risk zones for poaching. The proposed framework has been assessed using various evaluation metrics such as mAP for object detection, F1-Score for audio classification, and RMSE for movement prediction. The system is designed to be deployed in the field on a cloud-based platform, enabling real-time monitoring and decision-making. Edge computing on drones and sensor devices ensures low-latency processing and immediate action in response to detected threats. This model is expected to significantly enhance Javan rhino conservation by providing accurate, real-time data and actionable insights.

关键词： deep learning Tracking Habitats real-time systems Data models Threat assessment Satellite images Recording Monitoring Drones

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：