检索结果-南通市图书馆

Learning Efficient residual networks through Dense Connecting

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Learning Efficient Residual Networks through Dense Connectin...

Real Time Thermal Image Based Machine Learning Approach for Early Collision Avoidance System of Snowplows

第37届中国控制会议

作者： Tianzhong Song Yan Song Yongxiong Wang Xuegang Huang Department of Control Science and Engineering University of Shanghai for Science and Technology Hypervelocity Aerodynamics Institute China Aerodynamics Research & Development Center

In this paper, a novel method is developed to study the efficient residual networks（Res Nets） through the dense connecting. More precisely, in order to enhance the feature mapping as well as reducing the computing resource requirements,the dense connecting is introduced into each residual block, which then gives rise to the resulting network structures dense residual networks（DRNs）. In the proposed DRNs, the feature maps of each block can be adequately used by the underlying Res Nets in virtue of the employed dense connecting. Moreover, the number of filters of each convolution is greatly reduced to the half, and this practically promotes the efficiency of the model. Under the application of dense connecting, the higher performance of Res Nets can be guaranteed as well as the reduction of the time-expense. Meanwhile, the addressed model is less prone to overfitting. In the end, a series of experiments on two benchmark datasets are utilized to illustrate the effectiveness of the proposed DRNs.

关键词： residual networks Dense connecting Convolution Feature mapping

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Intelligent Learning Systems and Applications 2024年第2期16卷 107-142页

作者： Fletcher Wadsworth Suresh S. Muknahallipatna Khaled Ksaibati Department of Electrical Engineering and Computer Science University of Wyoming Laramie WY USA Department of Civil and Architectural Engineering University of Wyoming Laramie WY USA

In an effort to reduce vehicle collisions with snowplows in poor weather conditions, this paper details the development of a real time thermal image based machine learning approach to an early collision avoidance system for snowplows, which intends to detect and estimate the distance of trailing vehicles. Due to the operational conditions of snowplows, which include heavy-blowing snow, traditional optical sensors like LiDAR and visible spectrum cameras have reduced effectiveness in detecting objects in such environments. Thus, we propose using a thermal infrared camera as the primary sensor along with machine learning algorithms. First, we curate a large dataset of thermal images of vehicles in heavy snow conditions. Using the curated dataset, two machine-learning models based on the modified ResNet architectures were trained to detect and estimate the trailing vehicle distance using real-time thermal images. The trained detection network was capable of detecting trailing vehicles 99.0% of the time at 1500.0 ft distance from the snowplow. The trained trailing distance network was capable of estimating distance with an average estimation error of 10.70 ft. The inference performance of the trained models is discussed, along with the interpretation of the performance.

关键词： Convolutional Neural networks residual networks Object Detection Image Processing Thermal Imaging

3-Dimensional Bag of Visual Words Framework on Action Recognition

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第6期63卷 1081-1091页

作者： Shiqi Wang Yimin Yang Ruizhong Wei Qingming Jonathan Wu Department of Computer Science Lakehead UniversityThunder BayCanada Department of Electrical and Computer Engineering University of WindsorWindsorCanada

Human motion recognition plays a crucial role in the video analysis ***,a given video may contain a variety of noises,such as an unstable background and redundant actions,that are completely different from the key *** noises pose a great challenge to human motion *** solve this problem,we propose a new method based on the 3-Dimensional(3D)Bag of Visual Words(BoVW)*** method includes two parts:The first part is the video action feature extractor,which can identify key actions by analyzing action *** the video action encoder,by analyzing the action characteristics of a given video,we use the deep 3D CNN pre-trained model to obtain expressive coding information.A classifier with subnetwork nodes is used for the final *** extensive experiments demonstrate that our method leads to an impressive effect on complex video *** approach achieves state-of-the-art performance on the datasets of UCF101(85.3%)and HMDB51(54.5%).

关键词： Action recognition 3D CNNs recurrent neural networks residual networks subnetwork nodes

An Optimized Deep residual Network with a Depth Concatenated Block for Handwritten Characters Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第7期68卷 1-28页

作者： Gibrael Abosamra Hadi Oqaibi Department of Information Systems King Abdulaziz UniversityJeddah21589SA

Even though much advancements have been achieved with regards to the recognition of handwritten characters,researchers still face difficulties with the handwritten character recognition problem,especially with the advent of new datasets like the Extended Modified National Institute of Standards and Technology dataset(EMNIST).The EMNIST dataset represents a challenge for both machine-learning and deep-learning techniques due to inter-class similarity and intra-class ***-class similarity exists because of the similarity between the shapes of certain characters in the *** presence of intra-class variability is mainly due to different shapes written by different writers for the same *** this research,we have optimized a deep residual network to achieve higher accuracy *** published state-of-the-art *** approach is mainly based on the prebuilt deep residual network model ResNet18,whose architecture has been enhanced by using the optimal number of residual blocks and the optimal size of the receptive field of the first convolutional filter,the replacement of the first max-pooling filter by an average pooling filter,and the addition of a drop-out layer before the fully connected layer.A distinctive modification has been introduced by replacing the final addition layer with a depth concatenation layer,which resulted in a novel deep architecture having higher accuracy *** pure residual ***,the dataset images’sizes have been adjusted to optimize their visibility in the ***,by tuning the training hyperparameters and using rotation and shear augmentations,the proposed model outperformed the state-of-the-art models by achieving average accuracies of 95.91%and 90.90%for the Letters and Balanced dataset sections,***,the average accuracies were improved to 95.9%and 91.06%for the Letters and Balanced sections,respectively,by using a group of 5 instances of the trained models and averagin

关键词： Handwritten character classification deep convolutional neural networks residual networks GoogLeNet ResNet18 DenseNet drop-out L2 regularization factor learning rate

Deep Attention Network for Pneumonia Detection Using Chest X-Ray Images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第1期74卷 1673-1691页

作者： Sukhendra Singh Sur Singh Rawat Manoj Gupta B.K.Tripathi Faisal Alanzi Arnab Majumdar Pattaraporn Khuwuthyakorn Orawit Thinnukool Department of Information Technology JSS Academy of Technical EducationNoidaIndia JSS Academy of Technical Education NoidaIndia Department of Electronics and Communication Engineering JECRC University JaipurRajasthanIndia Harcourt Butler Technological University Kanpur India Department of Electrical Engineering Prince Sattam Bin Abdulaziz UniversityCollege of EngineeringAl Kharj16278Saudi Arabia Faculty of Engineering Imperial College LondonLondonSW72AZUK College of Arts Media and TechnologyChiang Mai UniversityChiang Mai50200Thailand

In computer vision,object recognition and image categorization have proven to be difficult *** have,nevertheless,generated responses to a wide range of difficult issues from a variety of *** Neural networks(CNNs)have recently been identified as the most widely proposed deep learning(DL)algorithms in the *** have unquestionably delivered cutting-edge achievements,particularly in the areas of image classification,speech recognition,and video ***,it has been noticed that the CNN-training assignment demands a large amount of data,which is in low supply,especially in the medical industry,and as a result,the training process takes *** this paper,we describe an attentionaware CNN architecture for classifying chest X-ray images to diagnose Pneumonia in order to address the aforementioned *** provide attention-aware properties to the Attention *** attentionaware features of various modules alter as the layers become *** a bottom-up top-down feedforward structure,the feedforward and feedback attention processes are integrated into a single feedforward process inside each attention *** the present work,a deep neural network(DNN)is combined with an attention mechanism to test the prediction of Pneumonia disease using chest X-ray *** produce attention-aware features,the suggested networkwas built by merging channel and spatial attentionmodules in DNN *** this network,we worked on a publicly available Kaggle chest X-ray *** testing was carried out to validate the suggested *** the experimental results,we attained an accuracy of 95.47%and an F-score of 0.92,indicating that the suggested model outperformed against the baseline models.

关键词： Attention network image classification object detection residual networks deep neural network

Microphone Array Speech Separation Algorithm Based on TC-ResNet

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第11期69卷 2705-2716页

作者： Lin Zhou Yue Xu Tianyi Wang Kun Feng Jingang Shi School of Information Science and Engineering Southeast UniversityNanjing210096China Center for Machine Vision and Signal Analysis University of OuluOuluFI-90014Finland

Traditional separation methods have limited ability to handle the speech separation problem in high reverberant and low signal-to-noise ratio(SNR)environments,and thus achieve unsatisfactory *** this study,a convolutional neural network with temporal convolution and residual network(TC-ResNet)is proposed to realize speech separation in a complex acoustic environment.A simplified steered-response power phase transform,denoted as GSRP-PHAT,is employed to reduce the computational *** extracted features are reshaped to a special tensor as the system inputs and implements temporal convolution,which not only enlarges the receptive field of the convolution layer but also significantly reduces the network computational *** blocks are used to combine multiresolution features and accelerate the training procedure.A modified ideal ratio mask is applied as the training *** results demonstrate that the proposed microphone array speech separation algorithm based on TC-ResNet achieves a better performance in terms of distortion ratio,source-to-interference ratio,and short-time objective intelligibility in low SNR and high reverberant environments,particularly in untrained *** indicates that the proposed method has generalization to untrained conditions.

关键词： residual networks temporal convolution neural networks speech separation

An Automatic Deep Neural Network Model for Fingerprint Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第5期36卷 2007-2023页

作者： Amira Tarek Mahmoud Wael AAwad Gamal Behery Mohamed Abouhawwash Mehedi Masud Hanan Aljuaid Ahmed Ismail Ebada Department of Computer Science Faculty of SciencePort Said UniversityPort SaidEgypt Department of Computer Science Faculty of Computers and Artificial IntelligenceDamietta UniversityNew DamiettaEgypt Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)College of EngineeringMichigan State UniversityEast LansingMI 48824USA Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Computer Sciences Department College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman University(PNU)P.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems Faculty of Computers and Artificial IntelligenceDamietta UniversityNew DamiettaEgypt

The accuracy ofﬁngerprint recognition model is extremely important due to its usage in forensic and securityﬁ***ﬁngerprint recognition system has particular network architecture whereas many other networks achieve higher *** solve this problem in a uniﬁed model,this paper proposes a model that can automatically specify ***,it is called an automatic deep neural net-work(ADNN).Our algorithm can specify the appropriate architecture of the neur-al network used and some signiﬁcant parameters of this *** parameters are the number ofﬁlters,epochs,and *** guarantees the high-est accuracy by updating itself until achieving 99%accuracy then it stops and out-puts the ***,this paper proposes an end-to-end methodology for recognizing a person’s identity from the inputﬁngerprint image based on a resi-dual convolutional neural *** is a complete system and is fully automated whether in the features extraction stage or the classiﬁcation *** goal is to automate thisﬁngerprint recognition system because the more automatic the sys-tem is,the more time and effort it *** model also allows users to react by inputting the initial values of these ***,the model updates itself until itﬁnds the optimal values for the parameters and achieves the best *** advantage of our algorithm is that it can recognize people from their thumb and otherﬁngers and its ability to recognize distorted *** algo-rithm achieved 99.75%accuracy on the publicﬁngerprint dataset(SOCOFing).This is the best accuracy compared with other models.

关键词： Automatic system ﬁngerprint classiﬁcation residual networks deep learning

Dual-scale residual network for spectral CT image super-resolution

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Dual-scale residual network for spectral CT image super-reso...