检索结果-南通市图书馆

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

Computers, Materials & Continua 2024年第5期79卷 2169-2186页

作者： Mahmood Ul Haq muhammad Athar Javed Sethi Najib Ben Aoun Ala saleh Alluhaidan Sadique Ahmad Zahid farid Department of Computer System Engineering University of Engineering&TechnologyPeshawar25000Pakistan College of Computer Science and Information Technology Al-Baha UniversityAlaqiq65779-7738Saudi Arabia REGIM-Lab:Research Groups in Intelligent Machines National School of Engineers of Sfax(ENIS)University of SfaxSfax3038Tunisia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia EIAS:Data Science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Sciences Bahria University Karachi CampusKarachi541004Pakistan Department of Electrical Engineering Abasyn UniversityPeshawar25000Pakistan

Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security,authentication, law enforcement, and surveillance. Deep learning (DL) models, notably convolutional neuralnetworks (CNNs), have shown promising results in the field of FR. However CNNs are easily fooled since theydo not encode position and orientation correlations between features. Hinton et al. envisioned Capsule Networksas a more robust design capable of retaining pose information and spatial correlations to recognize objects morelike the brain does. Lower-level capsules hold 8-dimensional vectors of attributes like position, hue, texture, andso on, which are routed to higher-level capsules via a new routing by agreement algorithm. This provides capsulenetworks with viewpoint invariance, which has previously evaded CNNs. This research presents a FR model basedon capsule networks that was tested using the LFW dataset, COMSATS face dataset, and own acquired photos usingcameras measuring 128 × 128 pixels, 40 × 40 pixels, and 30 × 30 pixels. The trained model outperforms state-ofthe-art algorithms, achieving 95.82% test accuracy and performing well on unseen faces that have been blurred orrotated. Additionally, the suggested model outperformed the recently released approaches on the COMSATS facedataset, achieving a high accuracy of 92.47%. Based on the results of this research as well as previous results, capsulenetworks perform better than deeper CNNs on unobserved altered data because of their special equivarianceproperties.

关键词： CapsNet face recognition artificial intelligence

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Gene Action Studies in the Inheritance of Economic Traits in Diallel Cross of Lentil (Lens culinaris Medik)

引用

American Journal of Plant Sciences 2016年第6期7卷 756-768页

作者： Fahim Abbas Asim Riaz Tanzeela Zafar muhammad Hassan Hafiz muhammad Imran Umar Javed Hassan Waseem Alam saleh muhammad Mudassir Mahmood Hamza Sohail Usman Ali Tiwana muhammad Tayyab Iqbal muhammad Bilal Nanjing Agriculture University Nanjing China Department of Pharmacy Health and Well-Being University of Sunderland Sunderland UK Centre of Agricultural Biochemistry and Biotechnology Faculty of Agriculture University of Agriculture Faisalabad Pakistan Department of Plant Breeding & Genetics Bahauddin Zakariya University Multan Pakistan Department of Entomology Bahauddin Zakariya University Multan Pakistan Department of Horticulture Bahauddin Zakariya University Multan Pakistan Arid Zone Research Institute Bahawalpur Pakistan Department of Plant Breeding & Genetics PMAS-UAA Rawalpindi Pakistan

The present study was conducted in 4 × 4 half diallel cross fashion using the genotypes named as NL-2002, NL-2006, Punjab Masoor-2009 and Markaz-2009 for the evaluation of gene action in the inheritance of economic traits of lentil by following the Griffing (1956) Method of analysis. Minirap 13.1 Copyright© 2000, Minitab inc. Method II, Model I was used for the analysis and gene action was computed by variance component analysis using Mixed Model with GLM (general linear model) procedure. The F1 direct crosses along with the parental genotypes were then evaluated by framing the experiment in RCBD in 3 replications. The data were recorded for the characters which are under the study are, plant height (cm), number of primary branches, number of secondary branches, number of pods per plant, number of seed per pod, seed yield per plant, biomass (gram), 100 seeds weight (gram), harvest index (%), yield per plant. The simple ANOVA for all the characters revealed that difference among genotypes was highly significant. As significant differences were present between the genotypes, it permitted subsequent analysis of the data. The Combining Ability (CA) results showed that value of variance for GCA (General Combining Ability) was significantly higher than that of those of the values of variance of SCA (Specific Combining Ability). Hence current results clearly depicted the role of additive type of gene action governing the characters under study.

关键词： Lentil Diallel Gene Action Studies

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Improving Growth Performance of Jatropha curcas by Inducing Polyploidy through Colchicine Treatment

引用

American Journal of Plant Sciences 2016年第6期7卷 769-772页

作者： Syed Amir Manzoor Asim Riaz Tanzeela Zafar muhammad Hassan Hafiz muhammad Imran Umar Javed Hassan Waseem Alam saleh muhammad Mudassir Mahmood Hamza Sohail Tanveer Aslam Feehan Hassan Fahim Abbas muhammad Faseeh Iqbal Department of Forestry Bahauddin Zakariya University Multan Pakistan Department of Pharmacy Health and Well-Being University of Sunderland Sunderland UK Centre of Agricultural Biochemistry and Biotechnology Faculty of Agriculture University of Agriculture Faisalabad Pakistan Department of Plant Breeding & Genetics Bahauddin Zakariya University Multan Pakistan Department of Entomology Bahauddin Zakariya University Multan Pakistan Department of Horticulture Bahauddin Zakariya University Multan Pakistan Nanjing Agriculture University Nanjing China Department of Soil Science Bahauddin Zakariya University Multan Pakistan

This study was planned to assess genetic variation in Jatropha curcas as affected by colchichine treatments. During the experiment, seeds of Jatropha curcas were collected from mature and healthy Jatropha plants and were soaked in different concentrations of colchicines. The second treatment was that of time of soaking (seeds were soaked in different concentrations for different time durations). The results clearly revealed that by increasing the concentration of colchicine treatment, parameters like stomatal density, and size of the guard cells were reduced.

关键词： Jatropha Polyploidy Colchicine Biofuel

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Active Learning Strategies for Textual Dataset-Automatic Labelling

引用

Computers, Materials & Continua 2023年第8期76卷 1409-1422页

作者： Sher muhammad Daudpota Saif Hassan Yazeed Alkhurayyif Abdullah saleh Alqahtani muhammad Haris Aziz Department of Computer Science Sukkur IBA UniversitySukkur65200Pakistan Al Quwayiyah College of Sciences and Humanities Shaqra UniversityShaqra15526Saudi Arabia Self-Development Skills Department Common First Year DeanshipKing Saud UniversityRiyadh12373Saudi Arabia STC’s Artificial Intelligence Chair Department of Information SystemsCollege of Computer and Information SciencesKing Saud UniversityRiyadh11451Saudi Arabia College of Engineering&Technology University of SargodhaSargodha40100Pakistan

The Internet revolution has resulted in abundant data from various sources,including social media,traditional media,*** the availability of data is no longer an issue,data labelling for exploiting it in supervised machine learning is still an expensive process and involves tedious human *** overall purpose of this study is to propose a strategy to automatically label the unlabeled textual data with the support of active learning in combination with deep *** specifically,this study assesses the performance of different active learning strategies in automatic labelling of the textual dataset at sentence and document *** achieve this objective,different experiments have been performed on the publicly available *** first set of experiments,we randomly choose a subset of instances from training dataset and train a deep neural network to assess performance on test *** the second set of experiments,we replace the random selection with different active learning strategies to choose a subset of the training dataset to train the same model and reassess its performance on test *** experimental results suggest that different active learning strategies yield performance improvement of 7% on document level datasets and 3%on sentence level datasets for auto labelling.

关键词： Active learning automatic labelling textual datasets

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

X-ray Image-Based COVID-19 Patient Detection Using Machine Learning-Based Techniques

引用

Computer Systems Science & Engineering 2022年第11期43卷 671-682页

作者： Shabana Habib saleh Alyahya Aizaz Ahmed muhammad Islam Sheroz Khan Ishrat Khan muhammad Kamil Department of Information Technology College of ComputerQassim UniversityBuraidah52571Saudi Arabia Department of Electrical Engineering College of Engineering&Information TechnologyOnaizah CollegesOnaizah51911Saudi Arabia Digital Image Processing Lab Islamia CollegePeshawar25120KPKPakistan Department of Computer Science College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Electrical Engineering National University of Computer and Emerging SciencesPeshawarPakistan

In early December 2019,the city of Wuhan,China,reported an outbreak of coronavirus disease(COVID-19),caused by a novel severe acute respiratory syndrome coronavirus-2(SARS-CoV-2).On January 30,2020,the World Health Organization(WHO)declared the outbreak a global pandemic *** the face of the COVID-19 pandemic,the most important step has been the effective diagnosis and monitoring of infected *** COVID-19 using Machine Learning(ML)technologies can help the health care unit through assistive diagnostic suggestions,which can reduce the health unit's burden to a certain *** paper investigates the possibilities of ML techniques in identifying/detecting COVID-19 patients including both conventional and exploring from chest X-ray images the effect of viral *** approach includes preprocessing,feature extraction,and ***,the features are extracted using the Histogram of Oriented(HOG)and Local Binary Pattern(LBP)feature ***,for the extracted features classification,six ML models of Support Vector Machine(SVM)and K-Nearest Neighbor(KNN)is *** results show that the diagnostic accuracy of random forest classifier(RFC)on extracted HOG plusLBP features is as high as 94%followed by SVM at 93%.The sensitivity of the K-nearest neighbour model has reached an accuracy of 88%.Overall,the predicted approach has shown higher classification accuracy and effective diagnostic *** is a highly useful tool for clinical practitioners and radiologists to help them in diagnosing and tracking the cases of COVID-19.

关键词： Image pre-processing detection classification x-ray images filter

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

An Assessment of the Groundwater Potential of Bayero University Kano Permanent Site Using Induced Polarization and Self-potential Methods

引用

Journal of Earth Science and Engineering 2014年第10期4卷 587-596页

作者： Shehu Sani Jamaluddeen Abdulrahim Ali Bunawa muhammad saleh Department of Physics Usmanu Danfodiyo University Sokoto 840212 Nigeria Department of Physics Bayero University Kano 700231 Nigeria

This paper centers on the investigation of the subsurface condition of Bayero University Kano Permanent Site with the aim of understanding the lithology and also mapping out the groundwater patterns within the area. To achieve this, time domain IP (induced polarization) and SP (self-potential) methods were adopted using VES (vertical electrical sounding) technique with 49 stations sounded. The result of the interpreted and analyzed measured data shows that the area is underlain by two to five subsurface layers. These layers are top soil, laterite, weathered basement complex rocks, fractured basement complex rocks and fresh basement complex rocks. The aquiferous zone of the study area occurs in the weathered and fractured basements and its thickness ranges from 1.44 m to 70.157 m while the overburden thickness lies between 1.6 m and 72.104 m. SP values were plotted against depths of investigation in order to identify areas with greater depth of flow in the study area. From the analysis of the overburden thickness, aquifer thickness and SP values, the most favorable regions for groundwater exploitation were found around VES 6, 11, 13, 19, 26, 38, 44 and 48. The investigation also provides information about the subsurface condition with regards to engineering construction and safe place for refuse dumping in order to avoid groundwater contamination.

关键词：地下水潜力激发极化会址永久大学覆盖层厚度评估感应

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

R-IDPS: Real Time SDN-Based IDPS System for IoT Security

引用

Computers, Materials & Continua 2022年第11期73卷 3099-3118页

作者： Noman Mazhar Rosli saleh Reza Zaba muhammad Zeeshan M.Muzaffar Hameed Nauman Khan Faculty of Computer Science and Information Technology University of MalayaKuala Lumpur50603Malaysia Centre for Research in Industry 4.0 University of MalayaKuala Lumpur50603Malaysia MIMOS Berhad National Applied R&D CentreKuala Lumpur57000Malaysia School of Electrical Engineering and Computer Science National University of Sciences and TechnologyIslamabad44000Pakistan

The advent of the latest technologies like the Internet of things(IoT)transforms the world from a manual to an automated way of ***,IoT sector open numerous security *** traditional networks,intrusion detection and prevention systems(IDPS)have been the key player in the market to ensure *** challenges to the conventional IDPS are implementation cost,computing power,processing delay,and ***,online machine learning model training has been an *** these challenges still question the IoT network *** has been a lot of research for IoT based detection systems to secure the IoT devices such as centralized and distributed architecture-based detection *** centralized system has issues like a single point of failure and load balancing while distributed system design has scalability and heterogeneity *** this study,we design and develop an agent-based hybrid prevention system based on software-defined networking(SDN)*** system uses lite weight agents with the ability to scaleup for bigger networks and is feasible for heterogeneous IoT *** baseline profile for the IoT devices has been developed by analyzing network flows from all the IoT *** profile helps in extracting IoT device *** features help in the development of our dataset that we use for anomaly *** anomaly detection,support vector machine has been used to detect internet control message protocol(ICMP)flood and transmission control protocol synchronize(TCP SYN)flood *** proposed system based on machine learning model is fully capable of online and offline *** than detection accuracy,the system can fully mitigate the attacks using the software-defined technology SDN *** major goal of the research is to analyze the accuracy of the hybrid agent-based intrusion detection systems as compared to conventional centralized only solutions,especially under the flood attac

关键词： Machine learning Internet of things software defined networking distributed denial of service attacks

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Optimizing Steering Angle Predictive Convolutional Neural Network for Autonomous Car

引用

Computers, Materials & Continua 2022年第5期71卷 2285-2302页

作者： Hajira Saleem Faisal Riaz Asadullah Shaikh Khairan Rajab Adel Rajab muhammad Akram Mana saleh Al Reshan Control Automotive and Robotics Lab Affiliated lab of National Center of Robotics and Automation(NCRA HEC Pakistan)and with the Department of Computer Science and Information TechnologyMirpur University of Science and Technology(MUST)Mirpur Azad Kashmir10250Pakistan College of Computer Science and Information System Najran UniversityNajran61441Saudi Arabia College of Computer Science and Engineering University of South FloridaTampa33620United States

Deep learning techniques,particularly convolutional neural networks(CNNs),have exhibited remarkable performance in solving visionrelated problems,especially in unpredictable,dynamic,and challenging *** autonomous vehicles,imitation-learning-based steering angle prediction is viable due to the visual imagery comprehension of *** this regard,globally,researchers are currently focusing on the architectural design and optimization of the hyperparameters of CNNs to achieve the best *** has proven the superiority of metaheuristic algorithms over the manual-tuning of ***,to the best of our knowledge,these techniques are yet to be applied to address the problem of imitationlearning-based steering angle ***,in this study,we examine the application of the bat algorithm and particle swarm optimization algorithm for the optimization of the CNN model and its hyperparameters,which are employed to solve the steering angle prediction *** validate the performance of each hyperparameters’set and architectural parameters’set,we utilized the Udacity steering angle dataset and obtained the best results at the following hyperparameter set:optimizer,Adagrad;learning rate,0.0052;and nonlinear activation function,exponential linear *** per our findings,we determined that the deep learning models show better results but require more training epochs and time as compared to shallower *** show the superiority of our approach in optimizing CNNs through metaheuristic algorithms as compared with the manual-tuning *** testing was also performed using the model trained with the optimal architecture,which we developed using our approach.

关键词： Bat algorithm convolutional neural network hyperparameters metaheuristic optimization algorithm steering angle prediction

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Optimal Deep Reinforcement Learning for Intrusion Detection in UAVs

引用

Computers, Materials & Continua 2022年第2期70卷 2639-2653页

作者： V.Praveena A.Vijayaraj P.Chinnasamy Ihsan Ali Roobaea Alroobaea saleh Yahya Alyahyan muhammad Ahsan Raza Department of Computer Science and Engineering Dr.N.G.P Institute of TechnologyCoimbatore641048India Department of Information Technology Vignan’s Foundation for ScienceTechnology&ResearchGuntur522213India Department of Information Technology Sri Shakthi Institute of Engineering and TechnologyCoimbatore641062India Department of Computer System and Technology Faculty of Computer Science and Information TechnologyUniversity of MalayaKuala Lumpur50603Malaysia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Science Community College in DwadmiShaqra University11961Saudi Arabia Department of Information Technology Bahauddin Zakariya UniversityMultan60000Pakistan

In recent years,progressive developments have been observed in recent technologies and the production cost has been continuously *** such scenario,Internet of Things(IoT)network which is comprised of a set of Unmanned Aerial Vehicles(UAV),has received more attention from civilian tomilitary *** network security poses a serious challenge to UAV networks whereas the intrusion detection system(IDS)is found to be an effective process to secure the UAV *** IDSs are not adequate to handle the latest computer networks that possess maximumbandwidth and data *** order to improve the detection performance and reduce the false alarms generated by IDS,several researchers have employed Machine Learning(ML)and Deep Learning(DL)algorithms to address the intrusion detection *** this view,the current research article presents a deep reinforcement learning technique,optimized by BlackWidow Optimization(DRL-BWO)algorithm,for UAV *** addition,DRL involves an improved reinforcement learning-based Deep Belief Network(DBN)for intrusion *** parameter optimization of DRL technique,BWO algorithm is *** helps in improving the intrusion detection performance of UAV *** extensive set of experimental analysis was performed to highlight the supremacy of the proposed *** the simulation values,it is evident that the proposed method is appropriate as it attained high precision,recall,F-measure,and accuracy values such as 0.985,0.993,0.988,and 0.989 respectively.

关键词： Intrusion detection UAV networks reinforcement learning deep learning parameter optimization

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Origin of Quartz Cement in the Paleogene Sandstone Reservoir of Shahejie Formation,Bohai Bay Basin,China

引用

Acta Geologica Sinica(English Edition) 2022年第1期96卷 248-260页

作者： muhammad KASHIF CAO Yingchang Nizam Ud DIN Uzair SIDDIQUE XI Kelai Faisal REHMAN Noor AHMED GU Xihao Mohammad saleh GAGHMAN Department of Earth sciences University of SargodhaSargodha 40100Pakistan School of Geosciences China University of PetroleumQingdaoShandong 266580China College of Earth sciences and Engineering Hohai UniversityNanjing 210098China Institute of Marine Geology and Resources Ocean CollegeZhejiang UniversityZhoushanZhejiang 316021China Department of Earth sciences Quaid-I-Azam UniversityIslamabad 45320Pakistan

The precipitation of authigenic quartz plays a significant role to reduce the reservoir characteristics and enhance the stiffness of the *** Es_(1) sandstone of Shahejie Formation is acting as a significant hydrocarbon producing rock in the Nanpu *** methods like thin section petrography,cathodoluminescence(CL),scanning electron microscope(SEM,with EDS),and electron microprobe analysis has been used to reveal the origin of quartz cement as well as to evaluate the effect of quartz cement on reservoir *** studied sandstone is classified as immature to mature feldspathic litharenite and lithic arkose and consists of quartz,feldspar,rock fragments and *** studies and SEM analysis shows that the authigenic quartz is acting a significant cement that reduces the reservoir *** clay minerals(kaolinite and mixed layer illite to smectite)are dominant in the Es_(1) sandstone,that can reduce the reservoir ***,CL and thin section analysis reveal that there are two stages of quartz cement in the studied samples;that are pore filling authigenic cement and quartz overgrowth *** inclusion homogenization temperatures shows that stages of quartz cement were developed with continuous process from 70℃ to 130℃.Quartz cements were generally originated from I/S reaction,feldspar dissolution,conversion of rock fragments and pressure *** dissolution(K-feldspar)and kaolinite to illite reaction is an insignificant silica source for the silica cement which is internally precipitated in a close system with diffusion transporting ***,quartz cement significantly enhance the rock strengthen and brittleness effectively as well as it reduce the overall reservoir quality.

关键词： origin authigenic quartz silica sources diffusion Shahejie Formation

来源：

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

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：