检索结果-南通市图书馆

Computer Decision Support System for Skin Cancer Localization and Classification

Computers, Materials & Continua 2021年第7期68卷 1041-1064页

作者： Muhammad Attique Khan tallha akram Muhammad Sharif Seifedine Kadry Yunyoung Nam Department of Computer Science COMSATS University IslamabadWah Campus47040Pakistan Department of Computer and Electrical Engineering COMSATS University IslamabadWah Campus47040Pakistan Department of Mathematics Beirut Arab UniversityBeirutLebanon Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea

In this work,we propose a new,fully automated system for multiclass skin lesion localization and classification using deep *** main challenge is to address the problem of imbalanced data classes,found in HAM10000,ISBI2018,and ISBI2019 ***,we consider a pretrained deep neural network model,DarkeNet19,and fine-tune the parameters of third convolutional layer to generate the image *** the visualized images are fused using a High-Frequency approach along with Multilayered Feed-Forward Neural Network(HFaFFNN).The resultant image is further enhanced by employing a log-opening based activation function to generate a localized binary ***,two pre-trained deep models,Darknet-53 and NasNet-mobile,are employed and fine-tuned according to the selected *** concept of transfer learning is later explored to train both models,where the input feed is the generated localized lesion *** the subsequent step,the extracted features are fused using parallel max entropy correlation(PMEC)*** avoid the problem of overfitting and to select the most discriminant feature information,we implement a hybrid optimization algorithm called entropy-kurtosis controlled whale optimization(EKWO)*** selected features are finally passed to the softmax classifier for the final *** datasets are used for the experimental process,such as HAM10000,ISBI2018,and ISBI2019 to achieve an accuracy of 95.8%,97.1%,and 85.35%,respectively.

关键词： Skin cancer convolutional neural network lesion localization transfer learning features fusion features 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

Salient Object Extraction Using Multilevel Gray Scale Quantization and Image Smoothing

引用

机床与液压 2013年第12期41卷 1-5页

作者： akram tallha HaiderAli Sajjad Department of Electrical Engineering COMSATS Institute of Information TechnologyWah CanttPakistan

A novel multi level image segmentation methodology is been proposed with the aim of extracting the salient object,keeping in view,only a small part of the visual scene undergoes attention and reaches the level of awareness while rest of details are *** advantage of multilevel gray scale quantization,image prominent object is separated from background,keeping in view the fact;salient object is having high contrast as compared to the *** inutile fragments were removed using morphological operations of opening and closing and making the image smoothened with Gaussian *** optimum threshold is selected for the binary conversion and final extrication of the salient object from the *** experimental data indicates that hybrid approach leads to improved segmentation with the apparent assertion of prime object extraction.

关键词：机床制造工艺金属压力加工设计

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

Video Analytics Framework for Human Action Recognition

引用

Computers, Materials & Continua 2021年第9期68卷 3841-3859页

作者： Muhammad Attique Khan Majed Alhaisoni Ammar Armghan Fayadh Alenezi Usman Tariq Yunyoung Nam tallha akram Department of Computer Science HITEC University TaxilaTaxila47080Pakistan College of Computer Science and Engineering University of Ha’ilHa’ilSaudi Arabia Department of Electrical Engineering College of EngineeringJouf UniversitySakakaSaudi Arabia College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-KhrajSaudi Arabia Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea Department of Computer Science COMSATS University IslamabadWah Campus47040Pakistan

Human action recognition(HAR)is an essential but challenging task for observing human *** problem encompasses the observations of variations in human movement and activity identification by machine learning *** article addresses the challenges in activity recognition by implementing and experimenting an intelligent segmentation,features reduction and selection framework.A novel approach has been introduced for the fusion of segmented frames and multi-level features of interests are *** entropy-skewness based features reduction technique has been implemented and the reduced features are converted into a codebook by serial based fusion.A custom made genetic algorithm is implemented on the constructed features codebook in order to select the strong and wellknown *** features are exploited by a multi-class SVM for action *** experimental results are undertaken on four action datasets,namely,Weizmann,KTH,Muhavi,and WVU *** achieved the recognition rate of 96.80%,100%,100%,and 100%*** reveals that the proposed action recognition approach is efficient and well accurate as compare to existing approaches.

关键词： Video analytics action recognition features classification entropy data analytic

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

Smart Devices Based Multisensory Approach for Complex Human Activity Recognition

引用

Computers, Materials & Continua 2022年第2期70卷 3221-3234页

作者： Muhammad Atif Hanif tallha akram Aamir Shahzad Muhammad Attique Khan Usman Tariq Jung-In Choi Yunyoung Nam Zanib Zulfiqar Department of Electrical and Computer Engineering COMSATS University IslamabadWah Campus47040Pakistan Department of Electrical and Computer Engineering COMSATS University IslamabadAbbottabad Campus22040Pakistan Department of Computer Science HITEC University TaxilaTaxilaPakistan College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-KhrajSaudi Arabia Department of Applied Artificial Intelligence Ajou UniversitySuwonKorea Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea Department of Electrical and Computer Engineering CUISahiwalPakistan

Sensors based Human Activity Recognition(HAR)have numerous applications in eHeath,sports,fitness assessments,ambient assisted living(AAL),human-computer interaction and many *** human physical activity can be monitored by using wearable sensors or external *** usage of external devices has disadvantages in terms of cost,hardware installation,storage,computational time and lighting conditions ***,most of the researchers used smart devices like smart phones,smart bands and watches which contain various sensors like accelerometer,gyroscope,GPS etc.,and adequate processing *** the task of recognition,human activities can be broadly categorized as basic and complex human *** of complex activities have received very less attention of researchers due to difficulty of problem by using either smart phones or smart *** reasons include lack of sensor-based labeled dataset having several complex human daily life *** of the researchers have worked on the smart phone’s inertial sensors to perform human activity recognition,whereas a few of them used both pocket and wrist *** this research,we have proposed a novel framework which is capable to recognize both basic and complex human activities using builtin-sensors of smart phone and smart *** have considered 25 physical activities,including 20 complex ones,using smart device’s built-in *** the best of our knowledge,the existing literature consider only up to 15 activities of daily life.

关键词： Complex human activities human daily life activities features extraction data fusion multi-sensory smartwatch smartphone

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

Towards Prevention of Sportsmen Burnout:Formal Analysis of Sub-Optimal Tournament Scheduling

引用

Computers, Materials & Continua 2022年第1期70卷 1509-1526页

作者： Syed Rameez Naqvi Adnan Ahmad S.M.Riazul Islam tallha akram M.Abdullah-Al-Wadud Atif Alamri Department of Electrical and Computer Engineering COMSATS University IslamabadWah CampusWah47040Pakistan Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea Department of Software Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Research Chair of Pervasive and Mobile Computing King Saud UniversityRiyadh11543Saudi Arabia

Scheduling a sports tournament is a complex optimization problem,which requires a large number of hard constraints to *** the availability of several such constraints in the literature,there remains a gap sincemost of the new sports events pose their own unique set of requirements,and demand novel *** talking of the strictly time bound events,ensuring fairness between the different teams in terms of their rest days,traveling,and the number of successive games they play,becomes a difficult task to resolve,and demands *** this work,we present a similar situation with a recently played sports event,where a suboptimal schedule favored some of the sides more than the *** introduce various competitive parameters to draw a fairness comparison between the sides and propose a weighting criterion to point out the sides that enjoyed this schedule more than the ***,we use root mean squared error between an ideal schedule and the actual ones for each side to determine unfairness in the distribution of rest days across their entire *** latter is crucial,since successively playing a large number of games may lead to sportsmen burnout,which must be prevented.

关键词： Sports scheduling optimization constraint programming fatigue analysis

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

Brain Tumor Detection and Classification Using PSO and Convolutional Neural Network

引用

Computers, Materials & Continua 2022年第12期73卷 4501-4518页

作者： Muhammad Ali Jamal Hussain Shah Muhammad Attique Khan Majed Alhaisoni Usman Tariq tallha akram Ye Jin Kim Byoungchol Chang Department of Computer Science COMSATS University IslamabadWah CampusPakistan Departmnt of Computer Science HITEC University TaxilaPakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of EE COMSATS University IslamabadWah CampusPakistan Department of Computer Science Hanyang UniversitySeoul04763Korea Center for Computational Social Science Hanyang UniversitySeoul04763Korea

Tumor detection has been an active research topic in recent years due to the high mortality *** vision(CV)and image processing techniques have recently become popular for detecting tumors inMRI *** automated detection process is simpler and takes less time than manual *** addition,the difference in the expanding shape of brain tumor tissues complicates and complicates tumor detection for *** proposed a newframework for tumor detection aswell as tumor classification into relevant categories in this *** tumor segmentation,the proposed framework employs the Particle Swarm Optimization(PSO)algorithm,and for classification,the convolutional neural network(CNN)*** preprocessing techniques such as noise removal,image sharpening,and skull stripping are used at the start of the segmentation ***,PSO-based segmentation is *** the classification step,two pre-trained CNN models,alexnet and inception-V3,are used and trained using transfer *** a serial approach,features are extracted from both trained models and fused features for final *** classification,a variety of machine learning classifiers are *** dice values on datasets BRATS-2018 and BRATS-2017 are 98.11 percent and 98.25 percent,respectively,whereas average jaccard values are 96.30 percent and 96.57%(Segmentation Results).The results were extended on the same datasets for classification and achieved 99.0%accuracy,sensitivity of 0.99,specificity of 0.99,and precision of ***,the proposed method is compared to state-of-the-art existingmethods and outperforms them.

关键词： Magnetic resonance imaging(MRI) tumor segmentation deep learning features extraction classification

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

Classication of COVID-19 CT Scans via Extreme Learning Machin

引用

Computers, Materials & Continua 2021年第7期68卷 1003-1019页

作者： Muhammad Attique Khan Abdul Majid tallha akram Nazar Hussain Yunyoung Nam Seifedine Kadry Shui-Hua Wang Majed Alhaisoni Department of Computer Science HITEC UniversityTaxila47040Pakistan Department of Electrical Engineering COMSATS University IslamabadWah CampusWah CanttPakistan Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea Department of Mathematics and Computer Science Faculty of ScienceBeirut Arab UniversityLebanon Department of Mathematics University of LeicesterLeicesterUK College of Computer Science and Engineering University of Ha’ilHa’ilSaudi Arabia

Here,we use multi-type feature fusion and selection to predict COVID-19 infections on chest computed tomography(CT)*** scheme operates in four ***,we prepared a database containing COVID-19 pneumonia and normal CT *** images were retrieved from the Radiopaedia COVID-19 *** images were divided into training and test sets in a ratio of 70:***,multiple features were extracted from the training *** used canonical correlation analysis to fuse the features into single vectors;this enhanced the predictive *** next implemented a genetic algorithm(GA)in which an Extreme Learning Machine(ELM)served to assess GA *** on the ELM losses,the most discriminatory features were selected and saved as an ELM *** images were sent to the model,and the best-selected features compared to those of the trained model to allow nal *** employed the collected chest CT *** best predictive accuracy of the ELM classier was 93.9%;the scheme was effective.

关键词： Coronavirus classical features feature fusion feature optimization 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

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

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

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：