检索结果-南通市图书馆

HybridHR-Net:Action Recognition in Video Sequences Using Optimal Deep Learning Fusion Assisted Framework

Computers, Materials & Continua 2023年第9期76卷 3275-3295页

作者： Muhammad Naeem Akbar Seemab Khan Muhammad umar farooq Majed Alhaisoni Usman Tariq Muhammad Usman Akram Department of Computer Engineering National University of Sciences and Technology(NUST)Islamabad46000Pakistan Department of Robotics SMME NUSTIslamabad45600Pakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Management Information System Department College of Business AdministrationPrince Sattam bin Abdulaziz UniversityAl-Kharj16278Saudi Arabia

The combination of spatiotemporal videos and essential features can improve the performance of human action recognition(HAR);however,the individual type of features usually degrades the performance due to similar actions and complex *** deep convolutional neural network has improved performance in recent years for several computer vision applications due to its spatial *** article proposes a new framework called for video surveillance human action recognition dubbed *** a few selected datasets,deep transfer learning is used to pre-trained the EfficientNet-b0 deep learning *** optimization is employed for the tuning of hyperparameters of the fine-tuned deep *** of fully connected layer features,we considered the average pooling layer features and performed two feature selection techniques-an improved artificial bee colony and an entropy-based *** a serial nature technique,the features that were selected are combined into a single vector,and then the results are categorized by machine learning *** publically accessible datasets have been utilized for the experimental approach and obtained notable accuracy of 97%,98.7%,100%,99.7%,and 96.8%,***,a comparison of the proposed framework with contemporarymethods is done to demonstrate the increase in accuracy.

关键词： Action recognition entropy deep learning transfer learning artificial bee colony feature fusion

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

Effectiveness of Deep Learning Models for Brain Tumor Classification and Segmentation

引用

Computers, Materials & Continua 2023年第7期76卷 711-729页

作者： Muhammad Irfan Ahmad Shaf Tariq Ali umar farooq Saifur Rahman Salim Nasar Faraj Mursal Mohammed Jalalah Samar M.Alqhtani Omar AlShorman Electrical Engineering Department College of EngineeringNajran UniversityNajran61441Saudi Arabia Department of Computer Science COMSATS University IslamabadSahiwal CampusSahiwal57000Pakistan Department of Information Systems College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia College of Engineering Najran UniversityNajran61441Saudi Arabia

A brain tumor is a mass or growth of abnormal cells in the *** children and adults,brain tumor is considered one of the leading causes of *** are several types of brain tumors,including benign(non-cancerous)and malignant(cancerous)*** brain tumors as early as possible is essential,as this can improve the chances of successful treatment and *** this problem,we bring forth a hybrid intelligent deep learning technique that uses several pre-trained models(Resnet50,Vgg16,Vgg19,U-Net)and their integration for computer-aided detection and localization systems in brain *** pre-trained and integrated deep learning models have been used on the publicly available dataset from The Cancer Genome *** dataset consists of 120 *** pre-trained models have been used to classify tumor or no tumor images,while integrated models are applied to segment the tumor region *** have evaluated their performance in terms of loss,accuracy,intersection over union,Jaccard distance,dice coefficient,and dice coefficient *** pre-trained models,the U-Net model achieves higher performance than other models by obtaining 95%*** contrast,U-Net with ResNet-50 out-performs all other models from integrated pre-trained models and correctly classified and segmented the tumor region.

关键词： Brain tumor deep learning ensemble detection healthcare

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

A Smart Wellness Service Platform and Its Practical Implementation

引用

Computers, Materials & Continua 2021年第1期66卷 45-57页

作者： umar farooq Intae Ryoo Gon Khang Department of Biomedical Engineering Kyung Hee University1732 Deogyeong-daeroGiheung-guYongin-siGyeonggi-do 17104Korea Department of Computer Engineering Kyung Hee University1732 Deogyeong-daeroGiheung-guYongin-siGyeonggi-do 17104Korea

Advances in the field of medical sciences and medical technology,and present-day challenges,such as an aging population,rising medical expenses,and lifestyle-related diseases,have collectively catalyzed a research ecosystem termed“smart wellness.”This article describes the establishment of a smart wellness service platform designed to empower individuals to create a sense of balance in their ***-by-step details include service model,design,and architectural *** a proof of concept,implementation details of a Health Improvement and Management Systems(HIMS)Hub,a Smart Wellness Service Platform deployed in six cities in South Korea,are *** on-site survey conducted in Busan Metropolitan City reveals the percentage of satisfied users to be 91.3%.Furthermore,data gathered from 27,236 physical evaluations of users from a Busan city center over the period of April 2013 to May 2018 reveal that males and females in their 50s and 60s account for the highest number of participants,while males in their 70s have a higher rate of participation than females in the same age group.

关键词： Wellness smart wellness smart wellness service platform u-Healthcare sports and exercise medicine

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

华南地块中三叠统巴东组红层磁倾角浅化效应

引用

北京大学学报（自然科学版） 2022年第3期58卷 469-480页

作者：韩露黄宝春赵千薛艺李能韬 umar farooq Jadoon 造山带与地壳演化教育部重点实验室北京大学地球与空间科学学院北京100871

对华南地块中三叠统巴东组红层样品进行系统的岩石磁学和古地磁学研究,采用高场等温剩磁各向异性(hf-AIR)方法,识别出巴东组红层的磁倾角浅化因子f=0.63。岩石磁学研究结果显示,巴东组红层的主要载磁矿物为赤铁矿和少量磁铁矿;磁化率和... 详细信息

对华南地块中三叠统巴东组红层样品进行系统的岩石磁学和古地磁学研究,采用高场等温剩磁各向异性(hf-AIR)方法,识别出巴东组红层的磁倾角浅化因子f=0.63。岩石磁学研究结果显示,巴东组红层的主要载磁矿物为赤铁矿和少量磁铁矿;磁化率和高场等温剩磁各向异性组构均指示其具有典型沉积组构特征,表明未遭受后期构造应力改造。高温特征剩磁分量为碎屑赤铁矿所携带,具有单一负极性,并在95%置信水平上通过褶皱检验,与前人在同一剖面不同位置获得的以正极性为主的古地磁方向一致。该特征剩磁方向在地层校正后的平均方向为Ds=222.1°,I_(s)=−27.2°(α95=8.7°),对应古地磁极为48.1°N,215.5°E(A_(95)=8.4°)。对包括本文数据在内的华南中三叠世红层高质量古地磁极数据(Q≥5)用f=0.63进行统一校正后,获得平均古地磁极为48.5°N,207.6°E(A_(95)=10.7°)。对比华北地块同样经hf-AIR方法浅化校正后的早三叠世古地磁极,两者在其东部参考点上的古纬度完全一致,验证了前人提出的华南华北中生代剪刀式旋转拼合模型。

关键词：华南地块巴东组红层磁倾角浅化校正高场等温剩磁各向异性古纬度

来源：

维普期刊数据库

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Spin-valley Hall phenomena driven by Van Hove singularities in blistered graphene

引用

npj Computational Materials 2020年第1期6卷 27-34页

作者： M.umar farooq Arqum Hashmi Tomoya Ono Li Huang Department of Physics Southern University of Science and TechnologyShenzhenGuangdong 518055China Center for Computational Sciences University of TsukubaTsukubaIbaraki 305-8577Japan Kansai Photon Science Institute National Institutes for Quantum and Radiological Science and Technology(QST)Kyoto 619-0215Japan Department of Electrical and Electronic Engineering Kobe UniversityKobe 657-8501Japan

Using first-principles calculations,we investigate the possibility of realizing valley Hall effects(VHE)in blistered graphene *** show that the Van Hove singularities(VHS)induced by structural deformations can give ri... 详细信息

关键词： graphene valley singularities

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

Greyscale based learning in BPNN for image restoration problem

引用

Journal of Beijing Institute of Technology 2013年第1期22卷 94-100页

作者： umar farooq 闫雪梅 SADIA Murawwat MUHAMMAD Imran School of Information and Electronics Beijing Institute of Technology

A new method of back propagation learning with respect to the problem of image restora- tion which is named as greyscale based learning in back propagation neural networks （BPNN） is in- vestigated. It is observed that by using this method the value of mean square error （MSE） decreases significantly. In addition, this method also gives good visual results when it is applied in image resto- ration problem. This method is also useful to tackle the inherited drawback of falling into local mini- ma by reducing its effect on overall system by bifurcating the learning locally different for different grey scale values. The performance of this algorithm has been studied in detail with different combi- nations of weights. In short, this algorithm provides much better results especially when compared with the simple back propagation algorithm with any further enhancements and without going for hy- brid solutions.

关键词： greyscale based learning back propagation neural network(BPNN) image restoration

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

A Composite State Convergence Scheme for Bilateral Teleoperation Systems

引用

IEEE/CAA Journal of Automatica Sinica 2019年第5期6卷 1166-1178页

作者： Muhammad Usman Asad umar farooq Jason Gu Ghulam Abbas Rong Liu Valentina E.Balas the Department of Electrical &Computer Engineering Dalhousie UniversityN.S.Canada the Department of Electrical & Computer Engineering Dalhousie UniversityN.S.Canada the Department of Electrical Engineering University of the Punjab LahorePakistan the Department of Electrical Engineering The University of LahorePakistan the Department of Biomedical Engineering Dalian University of TechnologyChina the Department of Automatics &Applied Software “Aurel Vlaicu” University of AradRomania

State convergence is a novel control algorithm for bilateral teleoperation of robotic systems. First, it models the teleoperation system on state space and considers all the possible interactions between the master and slave systems. Second, it presents an elegant design procedure which requires a set of equations to be solved in order to compute the control gains of the bilateral loop. These design conditions are obtained by turning the master-slave error into an autonomous system and imposing the desired dynamic behavior of the teleoperation system. Resultantly, the convergence of master and slave states is achieved in a well-defined manner. The present study aims at achieving a similar convergence behavior offered by state convergence controller while reducing the number of variables sent across the communication channel. The proposal suggests transmitting composite master and slave variables instead of full master and slave states while keeping the operator's force channel intact. We show that,with these composite and force variables;it is indeed possible to achieve the convergence of states in a desired way by strictly following the method of state convergence. The proposal leads to a reduced complexity state convergence algorithm which is termed as composite state convergence controller. In order to validate the proposed scheme in the absence and presence of communication time delays, MATLAB simulations and semi-real time experiments are performed on a single degree-of-freedom teleoperation system.

关键词： Composite variables linear control systems state convergence teleoperation time delay

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

Sedative and antinociceptive activities of two new sesquiterpenes isolated from Ricinus communis

引用

Chinese Journal of Natural Medicines 2018年第3期16卷 225-230页

作者： umar farooq Ajmal Khan Sadia Naz Abdur Rauf Haroon Khan Afsar Khan Irfan Ullah Syed Majid Bukhari Department of Chemistry COMSATS Institute of Information Technology UoN Chair of Oman's Medicinal Plants and Marine Natural Products University of Nizwa Department of Geology University of Swabi Anbar Department of Pharmacy Abdul Wali Khan University Department of Pharmacy Abasyn University

Two new sesquiterpenes, trivially named ricinusoids A(1) and ricinusoids B(2), were isolated from ethyl acetate fraction of Ricinus communis. The structures of new compounds were elucidated by detailed spectroscopic techniques, including 1 D-and 2 D-NMR, UV, IR spectroscopy, and mass spectrometry. The compounds(1-2) were also assessed for in-vivo sedative and analgesic like effects in open field and acetic acid induced writhing tests respectively at 5, 10, and 20 mg·kg^(–1) i.p. Pretreatment of both test compounds caused significant(P ≤ 0.05) reduction in locomotive activity like sedative agents and abdominal constrictions like analgesics. Both compounds(1-2) possessed marked sedative and antinociceptive effects in animal models.

关键词： Ricinus communis Sesquiterpenoids Euphorbiaceae 分光镜的技术 Antinociceptive 活动

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

Application of improved BPNN in image restoration-learning coefficient

引用

Journal of Beijing Institute of Technology 2012年第4期21卷 543-546页

作者： umar farooq 沈庭芝 Muhammad Imran 赵三元 Sadia Murawwat 王清云 School of Information and Electronics Beijing Institute of Technology School of Computer Science Beijing Institute of Technology

A new method of artificial intelligence based on a new improved back propagation neural network （BPNN） algorithm is partially applied in the problem of image restoration. In order to over- come the inherited issues in conventional back propagation algorithm i.e. slow convergence rate, longer training time, hard to achieve global minima etc. , different methods have been used including the introduction of dynamic learning rate and dynamic momentum coefficient etc. With the passage of time different techniques has been used to improve the dynamicity of these coefficients. The meth- od applied in this paper improves the effect of learning coefficient η by using a new way to modify the value dynamically during learning process. The experimental results show that this helps in im- proving the efficiency overall both in visual effect and quality analysis.

关键词： image restoration image processing intelligent back propagation neural network(BPNN) dynamic learning coefficient

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

Liver bioengineering:Current status and future perspectives

引用

World Journal of Gastroenterology 2012年第47期18卷 6926-6934页

作者： Christopher Booth Tom Soker Pedro Baptista Christina L Ross Shay Soker umar farooq Robert J Stratta Giuseppe Orlando Wake Forest Institute for Regenerative Medicine Wake Forest University School of MedicineWinston-SalemNC 27101United States Department of General Surgery Section of TransplantationWake Forest University School of MedicineWinston-SalemNC 27101United States

The present review aims to illustrate the strategies that are being implemented to regenerate or bioengineer livers for clinical *** are two general pathways to liver bioengineering and *** first consists of creating a supporting scaffold,either synthetically or by decellularization of human or animal organs,and seeding cells on the scaffold,where they will mature either in bioreactors or in *** strategy seems to offer the quickest route to clinical translation,as demonstrated by the development of liver organoids from rodent livers which were repopulated with organ specific cells of animal and/or human *** bioengineering has potential for transplantation and for toxicity testing during preclinical drug *** second possibility is to induce liver regeneration of dead or resected tissue by manipulating cell *** fact,it is well known that the liver has peculiar regenerative potential which allows hepatocyte hyperplasia after amputation of liver *** of autologous bone marrow cells,which aids in liver regeneration,into patients was shown to be safe and to improve their clinical condition,but the specific cells responsible for liver regeneration have not yet been determined and the underlying mechanisms remain largely unknown.A complete understanding of the cell pathways and dynamics and of the functioning of liver stem cell niche is necessary for the clinical translation of regenerative medicine *** well,it will be crucial to elucidate the mechanisms through which cells interact with the extracellular matrix,and how this latter supports and drives cell fate.

关键词：肝脏再生生物工程种子细胞器官特异性动物肝脏生物反应器细胞外基质人类起源

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

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：