检索结果-南通市图书馆

An efficient deep learning-assisted person re-identification solution for intelligent video surveillance in smart cities

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第4期17卷 83-96页

作者： Muazzam MAQSOOD Sadaf YASMIN Saira GILLANI Maryam BUKHARI seungmin rho Sang-Soo YEO Department of Computer Science COMSATS University IslamabadAttock CampusAttock 43600Pakistan Department of Computer Science Bahria UniversityLahore 54600Pakistan Department of Industrial Security Chung-Ang UniversitySeoul 06974Republic of Korea Department of Computer Engineering Mokwon UniversityDaejeon 35349Republic of Korea

Innovations on the Internet of Everything(IoE)enabled systems are driving a change in the settings where we interact in smart units,recognized globally as smart city ***,intelligent video-surveillance systems are critical to increasing the security of these smart *** precisely,in today’s world of smart video surveillance,person re-identification(Re-ID)has gained increased consideration by *** researchers have designed deep learningbased algorithms for person Re-ID because they have achieved substantial breakthroughs in computer vision *** this line of research,we designed an adaptive feature refinementbased deep learning architecture to conduct person *** the proposed architecture,the inter-channel and inter-spatial relationship of features between the images of the same individual taken from nonidentical camera viewpoints are focused on learning spatial and channel *** addition,the spatial pyramid pooling layer is inserted to extract the multiscale and fixed-dimension feature vectors irrespective of the size of the feature ***,the model’s effectiveness is validated on the CUHK01 and CUHK02 *** compared with existing approaches,the approach presented in this paper achieves encouraging Rank 1 and 5 scores of 24.6% and 54.8%,respectively.

关键词： Internet of Everything(IoE) visual surveillance systems big data security systems person re-identification(Re-ID) deep learning

Long Short Term Memory Networks Based Anomaly Detection for KPIs

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2019年第8期61卷 829-847页

作者： Haiqi Zhu Fanzhi Meng seungmin rho Mohan Li Jianyu Wang Shaohui Liu Feng Jiang School of Computer Science and Technology Harbin Institute of TechnologyHarbin150000China Institute of Computer Application China Academy of Engineer PhysicsMianyang621900China Department of Software Sejong UniversitySeoulKorea Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510006China

In real-world many internet-based service companies need to closely monitor large amounts of data in order to ensure stable operation of their ***,anomaly detection for these data with various patterns and data quality has been a great challenge,especially without *** this paper,we adopt an anomaly detection algorithm based on Long Short-Term Memory(LSTM)Network in terms of reconstructing KPIs and predicting *** use the reconstruction error and prediction error respectively as the criteria for judging anomalies,and we test our method with real data from a company in the insurance industry and achieved good performance.

关键词： LSTM anomaly detection KPIs

A Smart Heart Disease Diagnostic System Using Deep Vanilla LSTM

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10期77卷 1251-1279页

作者： Maryam Bukhari Sadaf Yasmin Sheneela Naz Mehr Yahya Durrani Mubashir Javaid Jihoon Moon seungmin rho Department of Computer Science COMSATS University IslamabadAttock CampusAttockPakistan Department of Computer Science COMSATS University IslamabadIslamabadPakistan Department of Computer Science UET TaxilaTaxilaPakistan Department of AI and Big Data Soonchunhyang UniversityAsanKorea Department of Industrial Security Chung-Ang UniversitySeoul06974Korea

Effective smart healthcare frameworks contain novel and emerging solutions for remote disease diagnostics,which aid in the prevention of several diseases including heart-related *** this context,regular monitoring of cardiac patients through smart healthcare systems based on Electrocardiogram(ECG)signals has the potential to save many *** existing studies,several heart disease diagnostic systems are proposed by employing different state-of-the-art methods,however,improving such methods is always an intriguing area of ***,in this research,a smart healthcare system is proposed for the diagnosis of heart disease using ECG *** proposed framework extracts both linear and time-series information on the ECG signals and fuses them into a single framework *** linear characteristics of ECG signals are extracted by convolution layers followed by Gaussian Error Linear Units(GeLu)and time series characteristics of ECG beats are extracted by Vanilla Long Short-Term Memory Networks(LSTM).Following on,the feature reduction of linear information is done with the help of ID Generalized Gated Pooling(GGP).In addition,data misbalancing issues are also addressed with the help of the Synthetic Minority Oversampling Technique(SMOTE).The performance assessment of the proposed model is done over the two publicly available datasets named MIT-BIH arrhythmia database(MITDB)and PTB Diagnostic ECG database(PTBDB).The proposed framework achieves an average accuracy performance of 99.14%along with a 95%recall value.

关键词： Smart systems deep learning ECG signals heart disease concurrent learning LSTM generalized gated pooling

Anomaly Based Camera Prioritization in Large Scale Surveillance Networks

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 2022年第2期70卷 2171-2190页

作者： Altaf Hussain Khan Muhammad Hayat Ullah Amin Ullah Ali Shariq Imran Mi Young Lee seungmin rho Muhammad Sajjad Department of Software Sejong University143-747SeoulKorea Digital Image Processing Lab Islamia College Peshawar25000Pakistan Color Lab Department of Computer ScienceNorwegian University of Science and Technology(NTNU)2815GjovikNorway CORIS Institute Oregon State University97331OregonUSA

Digital surveillance systems are ubiquitous and continuously generate massive amounts of data,and manual monitoring is required in order to recognise human activities in public *** surveillance systems that can automatically identify normal and abnormal activities are highly desirable,as these would allow for efficient monitoring by selecting only those camera feeds in which abnormal activities are *** paper proposes an energy-efficient camera prioritisation framework that intelligently adjusts the priority of cameras in a vast surveillance network using feedback from the activity recognition *** proposed system addresses the limitations of existing manual monitoring surveillance systems using a three-step *** the first step,the salient frames are selected from the online video stream using a frame differencing method.A lightweight 3D convolutional neural network(3DCNN)architecture is applied to extract spatio-temporal features from the salient frames in the second ***,the probabilities predicted by the 3DCNN network and the metadata of the cameras are processed using a linear threshold gate sigmoid mechanism to control the priority of the *** proposed system performs well compared to state-of-theart violent activity recognition methods in terms of efficient camera prioritisation in large-scale surveillance *** experiments and an evaluation of activity recognition and camera prioritisation showed that our approach achieved an accuracy of 98%with an F1-score of 0.97 on the Hockey Fight dataset,and an accuracy of 99%with an F1-score of 0.98 on the Violent Crowd dataset.

关键词： Camera prioritisation surveillance networks convolutional neural network computer vision deep learning resource-constrained device violent activity recognition

Intelligent Prediction Approach for Diabetic Retinopathy Using Deep Learning Based Convolutional Neural Networks Algorithm by Means of Retina Photographs

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2期66卷 1613-1629页

作者： G.Arun Sampaul Thomas Y.Harold Robinson E.Golden Julie Vimal Shanmuganathan seungmin rho Yunyoung Nam CSE Department J.B.Institute of Engineering and TechnologyHyderabad500075India School of Information Technology and Engineering Vellore Institute of TechnologyVellore632014India Department of Computer Science and Engineering Anna University Regional CampusTirunelveli627007India Department of Information Technology National Engineering CollegeKovilpatti628503India Department of Software Sejong University209 Neungdong-roGwangjin-guSeoul05006Korea Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea

Retinopathy is a human eye disease that causes changes in retinal blood vessels that leads to bleed,leak fluid and vision *** of retinopathy are blurred vision,changes in color perception,red spots,and eye pain and it cannot be detected with a naked *** this paper,a new methodology based on Convolutional Neural Networks(CNN)is developed and proposed to intelligent retinopathy prediction and give a decision about the presence of retinopathy with automatic diabetic retinopathy screening with accurate *** CNN model is trained by different images of eyes that have retinopathy and those which do not have *** fully connected layers perform the classification process of the images from the dataset with the pooling layers minimize the coherence among the adjacent *** feature loss factor increases the label value to identify the patterns with the kernel-based *** performance of the proposed model is compared with the related methods of DREAM,KNN,GD-CNN and *** results show that the proposed CNN performs better.

关键词： Convolutional neural networks dental diagnosis image recognition diabetic retinopathy detection

A Triplet-Branch Convolutional Neural Network for Part-Based Gait 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

Computer Systems Science & Engineering 2023年第11期47卷 2027-2047页

作者： Sang-Soo Yeo seungmin rho Hyungjoon Kim Jibran Safdar Umar Zia Mehr Yahya Durrani Department of Computer Engineering Mokwon UniversityDaejeonKorea Department of Industrial Security Chung-Ang UniversitySeoul06974Korea Department of Computer Engineering Semyung UniversityJechun-siKorea Department of Computer Science UET TaxilaTaxilaPakistan Department of Computer Science COMSATS University IslamabadAttock CampusAttockPakistan

Intelligent vision-based surveillance systems are designed to deal with the gigantic volume of videos captured in a particular environment to perform the interpretation of scenes in form of detection,tracking,monitoring,behavioral analysis,and *** addition to that,another evolving way of surveillance systems in a particular environment is human gait-based *** the existing research,several methodological frameworks are designed to use deep learning and traditional methods,nevertheless,the accuracies of these methods drop substantially when they are subjected to covariate *** covariate variables disrupt the gait features and hence the recognition of subjects becomes *** handle these issues,a region-based triplet-branch Convolutional Neural Network(CNN)is proposed in this research that is focused on different parts of the human Gait Energy Image(GEI)including the head,legs,and body separately to classify the subjects,and later on,the final identification of subjects is decided by probability-based majority voting ***,to enhance the feature extraction and draw the discriminative features,we have added soft attention layers on each branch to generate the soft attention *** proposed model is validated on the CASIA-B database and findings indicate that part-based learning through triplet-branch CNN shows good performance of 72.98%under covariate conditions as well as also outperforms single-branch CNN models.

关键词： Vision-based surveillance systems deep learning triplet-branch CNN gait recognition covariate conditions

Call for Papers Special Issue on Deep Learning and Evolutionary Computation for Satellite Imagery

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2022年第1期5卷 79-79页

作者： Krishna Kant Singh Soumyabrata Dev Akansha Singh seungmin rho Jain(Deemed to be University) BangaloreIndia University College Dublin Ireland Bennett University Greater NoidaIndia Sejong University Korea

Satellite images are humungous sources of data that require efficient methods for knowledge *** increased availability of earth data from satellite images has immense opportunities in various ***,the volume and heterogeneity of data poses serious computational *** development of efficient techniques has the potential of discovering hidden information from these *** knowledge can be used in various activities related to planning,monitoring,and managing the earth *** learning are being widely used for image analysis and *** learning based models can be effectively used for mining and knowledge discovery from satellite images.

关键词： has Deep knowledge

Recent progress on dense nuclear matter in skyrmion approaches

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2017年第3期60卷 1-24页

作者： Yong Liang Ma Mannque rho Center of Theoretical Physics and College of Physics Jilin University Institut de Physique Th'eorique CEA Saclay

The Skyrme model provides a novel unified approach to nuclear physics. In this approach, single baryon, baryonic matter and medium-modified hadron properties are treated on the same footing. Intrinsic density dependence(IDD) reflecting the change of vacuum by compressed baryonic matter figures naturally in the approach. In this article, we review the recent progress on accessing dense nuclear matter by putting baryons treated as solitons, namely, skyrmions, on crystal lattice with accents on the implications in compact stars.

关键词： Skyrme model hidden symmetries skyrmion crystal holographic nucleon BPS nuclei compact stars

Recent advances in 2D,3D and higher-order topological photonics

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Light(Science & Applications) 2020年第1期9卷 763-792页

作者： Minkyung Kim Zubin Jacob Junsuk rho Department of Mechanical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea School of Electrical and Computer Engineering Birck Nanotechnology CenterPurdue UniversityWest LafayetteIN 47906USA Department of Chemical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea

Over the past decade,topology has emerged as a major branch in broad areas of physics,from atomic lattices to condensed *** particular,topology has received significant attention in photonics because light waves can serve as a platform to investigate nontrivial bulk and edge physics with the aid of carefully engineered photonic crystals and ***,photonics provides enriched physics that arises from spin-1 vectorial electromagnetic ***,we review recent progress in the growing field of topological photonics in three *** first part is dedicated to the basics of topological band theory and introduces various two-dimensional topological *** second part reviews three-dimensional topological phases and numerous approaches to achieve them in ***,we present recently emerging fields in topological photonics that have not yet been *** part includes topological degeneracies in nonzero dimensions,unidirectional Maxwellian spin waves,higher-order photonic topological phases,and stacking of photonic crystals to attain layer *** addition to the various approaches for realizing photonic topological phases,we also discuss the interaction between light and topological matter and the efforts towards practical applications of topological photonics.

关键词： topological topology dimensions