检索结果-南通市图书馆

Two-Stream Deep Learning Architecture-Based Human 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 2023年第3期74卷 5931-5949页

作者： Faheem Shehzad muhammad Attique Khan muhammad Asfand E.Yar muhammad Sharif Majed Alhaisoni usman Tariq Arnab Majumdar Orawit Thinnukool Department of Computer Science COMSATS University IslamabadWah CampusPakistan Department of Computer Science HITEC UniversityTaxilaPakistan Department of Computer Science Bahria UniversityIslamabadPakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia College of Computer Engineering and Science Prince Sattam Bin Abdulaziz UniversityAl-Kharaj11942Saudi Arabia Faculty of Engineering Imperial College LondonLondonSW72AZUK College of Arts Mediaand TechnologyChiang Mai UniversityChiang Mai50200Thailand

Human action recognition(HAR)based on Artificial intelligence reasoning is the most important research area in computer *** breakthroughs in this field have been observed in the last few years;additionally,the interest in research in this field is evolving,such as understanding of actions and scenes,studying human joints,and human posture *** HAR techniques are introduced in the ***,the challenge of redundant and irrelevant features reduces recognition *** also faced a few other challenges,such as differing perspectives,environmental conditions,and temporal variations,among *** this work,a deep learning and improved whale optimization algorithm based framework is proposed for *** proposed framework consists of a few core stages i.e.,frames initial preprocessing,fine-tuned pre-trained deep learning models through transfer learning(TL),features fusion using modified serial based approach,and improved whale optimization based best features selection for final *** pre-trained deep learning models such as InceptionV3 and Resnet101 are fine-tuned and TL is employed to train on action recognition *** fusion process increases the length of feature vectors;therefore,improved whale optimization algorithm is proposed and selects the best *** best selected features are finally classified usingmachine learning(ML)*** publicly accessible datasets such as Ut-interaction,Hollywood,Free Viewpoint Action Recognition usingMotion History Volumes(IXMAS),and centre of computer vision(UCF)Sports,are employed and achieved the testing accuracy of 100%,99.9%,99.1%,and 100%*** with state of the art techniques(SOTA),the proposed method showed the improved accuracy.

关键词： Human action recognition deep learning transfer learning fusion of multiple features features optimization

Security Requirement Management for Cloud-Assisted and Internet of Things—Enabled Smart City

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4期67卷 625-639页

作者： muhammad usman Tariq muhammad Babar Mian Ahmad Jan Akmal Saeed Khattak Mohammad Dahman Alshehri Abid Yahya Abu Dhabi School of Management Abu Dhabi6844United Arab Emirates Department of Computing and Technology Iqra UniversityIslamabad44000Pakistan Institute of Research and Development Duy Tan UniversityDa Nang550000Vietnam The Faculty of Information Technology Duy Tan UniversityDa Nang550000Vietnam Department of Computer Sciences Abdul Wali Khan UniversityMardan23200Pakistan Department of Computer Sciences Quaid-i-Azam UniversityIslamabad44000Pakistan Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Botswana International University of Science and Technology Palapye016Botswana

The world is rapidly changing with the advance of information *** expansion of the Internet of Things(IoT)is a huge step in the development of the smart *** IoT consists of connected devices that transfer *** IoT architecture permits on-demand services to a public pool of *** computing plays a vital role in developing IoT-enabled smart *** integration of cloud computing enhances the offering of distributed resources in the smart *** management of security requirements of cloud-assisted IoT systems can bring about risks to availability,security,performance,condentiality,and *** key reason for cloud-and IoT-enabled smart city application failure is improper security practices at the early stages of *** article proposes a framework to collect security requirements during the initial development phase of cloud-assisted IoT-enabled smart city *** three-layered architecture includes privacy preserved stakeholder analysis(PPSA),security requirement modeling and validation(SRMV),and secure cloud-assistance(SCA).A case study highlights the applicability and effectiveness of the proposed framework.A hybrid survey enables the identication and evaluation of signicant challenges.

关键词： Security privacy smart city Internet of Things cloud computing

Cache in fog computing design,concepts,contributions,and security issues in machine learning prospective

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Digital Communications and Networks 2023年第5期9卷 1033-1052页

作者： muhammad Ali Naeem Yousaf Bin Zikria Rashid Ali usman Tariq Yahui Meng Ali Kashif Bashir School of Science Guangdong University of Petrochemical TechnologyMaoming525000China Department of Information and Communication Engineering Yeungnam UniversityGyeongsan38541Republic of Korea Department of Information and Communication Technologies Universitat Pompeu FabraBarcelonaSpain College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Computing and Mathematics Manchester Metropolitan UniversityManchesterUnited Kingdom Woxsen School of Business Woxsen UniversityHyderabadIndia Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon

The massive growth of diversified smart devices and continuous data generation poses a challenge to communication *** deal with this problem,communication networks consider fog computing as one of promising technologies that can improve overall communication *** brings on-demand services proximate to the end devices and delivers the requested data in a short *** computing faces several issues such as latency,bandwidth,and link utilization due to limited resources and the high processing demands of end *** this end,fog caching plays an imperative role in addressing data dissemination *** study provides a comprehensive discussion of fog computing,Internet of Things(IoTs)and the critical issues related to data security and dissemination in fog ***,we determine the fog-based caching schemes and contribute to deal with the existing issues of fog ***,this paper presents a number of caching schemes with their contributions,benefits,and challenges to overcome the problems and limitations of fog *** also identify machine learning-based approaches for cache security and management in fog computing,as well as several prospective future research directions in caching,fog computing,and machine learning.

关键词： Internet of things Cloud computing Fog computing Caching Latency

Impact of Tillage and Herbicides on Weed Density, Yield and Quality of Cotton in Wheat Based Cropping System

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Integrative Agriculture 2013年第9期12卷 1568-1579页

作者： Khalid usman Niamatullah Khan muhammad Umar Khan Aziz ur Rehman Said Ghulam Department of Agronomy Faculty of AgricultureGomal University Department of Agriculture Chemistry Faculty of AgricultureGomal University Department of Soil & Environmental Sciences Faculty of AgricultureGomal University

Conservation tillage may improve yield of cotton in addition to improvement in soil quality if practiced for longer period. However, the practice may not be productive in short-term particularly when severe weeds are infesting the crops such as Cynodon dactylon, Conyza canadensis, Tribulus terrestris, and Cyperus rotundus, etc. Recent studies indicate that conventional tillage （CT） is more productive than zero tillage （ZT）/reduced tillage （RT）. Performance of cotton under three tillage systems, viz., ZT, RT and CT; and five herbicides, i.e., haloxyfop-R-methyl 10.8 EC （108 g a.i. ha^-1）, lactofen 24 EC （168 g a.i. ha^-1）, haloxyfop 10.8 EC ＋ lactofen 24 EC, hand weeding, and weedy check were evaluated during 2010-2011 at Gomal University, ***, Pakistan, to explore the best management option for effective weed control, enhanced yield and quality of cotton grown after wheat. The results revealed that hand weeding and Haloxyfop as post emergence alone or in combination with Lactofen reduced weed density to the minimum irrespective of the tillage systems. Excessive rainfall and cooler temperature limited cotton growth and yield in 2010. The adverse weather conditions had more adverse effect on boll weight under ZT and RT than CT. Haloxyfop ＋ lactofen produced higher seed cotton yield in RT than ZT, however, it could not exceed CT. Broad-spectrum herbicides x CT produced the highest number of bolls/plant, boll weight and seed cotton yield. Fiber quality and net returns were also the highest in broad-spectrum herbicides x CT. In conclusion, broad-spectrum herbicides under CT were more productive in wheat based cropping system on silty clay soil of ***.

关键词： tillage herbicide cotton seed cotton yield weed density net return

Intelligent Sound-Based Early Fault Detection System for Vehicles

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

Computer Systems Science & Engineering 2023年第9期46卷 3175-3190页

作者： Fawad Nasim Sohail Masood Arfan Jaffar usman Ahmad muhammad Rashid Superior University LahorePakistan Intelligent Data Visual Computing Research(IDVCR) LahorePakistan National University of Technology IslamabadPakistan

An intelligent sound-based early fault detection system has been proposed for vehicles using machine *** system is designed to detect faults in vehicles at an early stage by analyzing the sound emitted by the *** detection and correction of defects can improve the efficiency and life of the engine and other mechanical *** system uses a microphone to capture the sound emitted by the vehicle and a machine-learning algorithm to analyze the sound and detect faults.A possible fault is determined in the vehicle based on this processed *** classification is done at the first stage to differentiate between faulty and healthy *** collected noisy and normal sound samples of the car engine under normal and different abnormal conditions from multiple workshops and verified the data from *** used the time domain,frequency domain,and time-frequency domain features to detect the normal and abnormal conditions of the vehicle *** used abnormal car data to classify it into fifteen other classical vehicle *** experimented with various signal processing techniques and presented the comparison *** the detection and further problem classification,random forest showed the highest results of 97%and 92%with time-frequency features.

关键词： Sound classification signal processing random forest random tree time-frequency domain J48

Cotton Leaf Diseases Recognition Using Deep Learning and Genetic Algorithm

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12期69卷 2917-2932页

作者： muhammad Rizwan Latif Muhamamd Attique Khan muhammad Younus Javed Haris Masood usman Tariq Yunyoung Nam Seifedine Kadry Department of Computer Science HITEC University TaxilaTaxilaPakistan Wah Engineering College University of WahWah Cantt47080Pakistan College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-KhrajSaudi Arabia Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea Faculty of Applied Computing and Technology Noroff University CollegeKristiansandNorway

Globally,Pakistan ranks 4th in cotton production,6th as an importer of raw cotton,and 3rd in cotton *** 10%of GDP and 55%of the country’s foreign exchange earnings depend on cotton *** 1.5 million people in Pakistan are engaged in the cotton value ***,several diseases such as Mildew,Leaf Spot,and Soreshine affect cotton *** diagnosis is not a good solution due to several factors such as high cost and unavailability of an ***,it is essential to develop an automated technique that can accurately detect and recognize these diseases at their early *** this study,a new technique is proposed using deep learning architecture with serially fused features and the best feature *** proposed architecture consists of the following steps:(a)a self-collected dataset of cotton diseases is prepared and labeled by an expert;(b)data augmentation is performed on the collected dataset to increase the number of images for better training at the earlier step;(c)a pre-trained deep learning model named ResNet101 is employed and trained through a transfer learning approach;(d)features are computed from the third and fourth last layers and serially combined into one matrix;(e)a genetic algorithm is applied to the combined matrix to select the best points for further *** final recognition,a Cubic SVM approach was utilized and validated on a prepared *** the newly prepared dataset,the highest achieved accuracy was 98.8%using Cubic SVM,which shows the perfection of the proposed framework..

关键词： Plants diseases data augmentation deep learning features fusion features selection

A Framework of Deep Learning and Selection-Based Breast Cancer Detection from Histopathology 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

Computer Systems Science & Engineering 2023年第5期45卷 1001-1016页

作者： muhammad Junaid Umer muhammad Sharif Majed Alhaisoni usman Tariq Ye Jin Kim Byoungchol Chang Department of Computer Science COMSATS University IslamabadWah CampusWah CanttPakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman University(PNU)P.O.BOX 84428Riyadh11671Saudi Arabia College of Computer Engineering and Science Prince Sattam Bin Abdulaziz UniversityAl-Kharaj11942Saudi Arabia Department of Computer Science Hanyang UniversitySeoul04763Korea Center for Computational Social Science Hanyang UniversitySeoul04763Korea

Breast cancer(BC)is a most spreading and deadly cancerous malady which is mostly diagnosed in middle-aged women worldwide and effecting beyond a half-million people every *** BC positive newly diagnosed cases in 2018 reached 2.1 million around the world with a death rate of 11.6%of total *** diagnosis and detection of breast cancer disease with proper treatment may reduce the number of *** gold standard for BC detection is biopsy analysis which needs an expert for correct *** diagnosis of BC is a complex and challenging *** work proposed a deep learning-based(DL)solution for the early detection of this deadly disease from histopathology *** evaluate the robustness of the proposed method a large publically available breast histopathology image database containing a total of 277524 histopathology images is *** proposed automatic diagnosis of BC detection and classification mainly involves three ***,a DL model is proposed for feature ***,the extracted feature vector(FV)is passed to the proposed novel feature selection(FS)framework for the best ***,for the classification of BC into invasive ductal carcinoma(IDC)and normal class different machine learning(ML)algorithms are *** outcomes of the proposed methodology achieved the highest accuracy of 92.7%which shows that the proposed technique can successfully be implemented for BC detection to aid the pathologists in the early and accurate diagnosis of BC.

关键词： Breast cancer deep learning FS IDC ML SVM

Optimized Evaluation of Mobile Base Station by Modern Topological Invariants

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 363-378页

作者： Khalid Hamid muhammad Waseem Iqbal muhammad usman Ashraf Ahmed Mohammed Alghamdi Adel A.Bahaddad Khalid Ali Almarhabi Department of Computer Science Superior UniversityLahore54000Pakistan Department of Software Engineering Superior UniversityLahore54000Pakistan Department of Computer Science GC Women UniversitySialkot53310Pakistan Department of Software Engineering College of Computer Science and EngineeringUniversity of Jeddah21493Saudi Arabia Department of Information System Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science College of Computing in Al-QunfudahUmm Al-Qura UniversityMakkah24381Saudi Arabia

Due to a tremendous increase in mobile traffic,mobile operators have started to restructure their networks to offload their *** directions will lead to fundamental changes in the design of future Fifthgeneration(5G)cellular *** the formal reason,the study solves the physical network of the mobile base station for the prediction of the best characteristics to develop an enhanced network with the help of graph *** number that can be uniquely calculated by a graph is known as a graph *** the last two decades,innumerable numerical graph invariants have been portrayed and used for correlation *** any case,no efficient assessment has been embraced to choose,how much these invariants are connected with a network *** paper will talk about two unique variations of the hexagonal graph with great capability of forecasting in the field of optimized mobile base station topology in setting with physical *** K-banhatti sombor invariants(KBSO)and Contrharmonic-quadratic invariants(CQIs)are newly introduced and have various expectation characteristics for various variations of hexagonal graphs or *** the hexagonal networks are used in mobile base stations in layered,forms called *** review settled the topology of a hexagon of two distinct sorts with two invariants KBSO and CQIs and their reduced *** deduced outcomes can be utilized for the modeling of mobile cellular networks,multiprocessors interconnections,microchips,chemical compound synthesis and memory interconnection *** results find sharp upper bounds and lower bounds of the honeycomb network to utilize the Mobile base station network(MBSN)for the high load of traffic and minimal traffic also.

关键词： Hexagonal networks k-banhatti sombor invariants maple network graph artificial intelligence contraharmonic-quadratic invariants honeycomb

Want to make me emotional？ The influence of emotional advertisements on women＇s consumption behavior

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 Business Research in China 2017年第3期11卷 341-373页

作者： Salman Majeed Changbao Lu muhammad usman School of Economics and Management Fuzhou UniversityFuzhou Fujian 350002 People's Republic of China School of Economics and Management Fuzhou University Fuzhou Fujian 350002 People's Republic of China Institute of Business Administration (IBA) Quaid-e-Azamcampus University of the Punjab Lahore 54000 Pakistan Nippon Paint Pakistan (Private) Limited Lahore 54000 Pakistan

A wide difference of opinion exists about the content and composition of emotions. Advertising may influence an audience and their buying decisions about products and services. The objective of this study is to better conceptualize how women emotionally respond to emotional advertisements （EAs）. The variant views are integrated into an ACE model, composed of subordinate levels of emotions （E）, celebrity endorsements （C）, and appeal drivers （A）. This empirical study examines women＇s emotional response using data from 240 Chinese women respondents. The study participants were invited to develop ACE mix based advertisements and fill out questionnaires. PLS-SEM analysis, a novel approach in ACE advertisement development and its applicability to consumer behavior, was used. The results show that showbiz celebrities expressing the emotion of happiness with music and color make the most effective ACE mix to influence the consumption behavior of women. The results are significantly mediated by attention levels and are widely applicable in the burgeoning advertising industry. The study also calls for further research with different ACE mixes in different contexts and on different audiences. It also opens doors for policy making and an appropriate understanding of women＇s consumption behavior in the Chinese context.

关键词： Emotions Celebrity endorsement Appeal drivers Advertisement Consumer behavior