检索结果-南通市图书馆

A Novel Action Transformer Network for Hybrid Multimodal Sign Language 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1期74卷 523-537页

作者： Sameena Javaid safdar Rizvi Department of Computer Sciences School of Engineering and Applied SciencesBahria UniversityKarachi CampusKarachiPakistan

Sign language fills the communication gap for people with hearing and speaking *** includes both visual modalities,manual gestures consisting of movements of hands,and non-manual gestures incorporating body movements including head,facial expressions,eyes,shoulder shrugging,*** both gestures have been detected;identifying separately may have better accuracy,butmuch communicational information is *** sign language mechanism is needed to detect manual and non-manual gestures to convey the appropriate detailed message to *** novel proposed system contributes as Sign LanguageAction Transformer Network(SLATN),localizing hand,body,and facial gestures in video *** we are expending a Transformer-style structural design as a“base network”to extract features from a spatiotemporal *** impulsively learns to track individual persons and their action context inmultiple ***,a“head network”emphasizes hand movement and facial expression simultaneously,which is often crucial to understanding sign language,using its attention mechanism for creating tight bounding boxes around classified *** model’s work is later compared with the traditional identification methods of activity *** not only works faster but achieves better accuracy as *** achieves overall 82.66%testing accuracy with a very considerable performance of computation with 94.13 Giga-Floating Point Operations per Second(G-FLOPS).Another contribution is a newly created dataset of Pakistan Sign Language forManual and Non-Manual(PkSLMNM)gestures.

关键词： Sign language gesture recognition manual signs non-manual signs action transformer network

Developing a Breast Cancer Resistance Protein Substrate Prediction System Using Deep Features and LDA

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8期76卷 1643-1663页

作者： Mehdi Hassan safdar Ali Jin young Kim Muhammad Sanaullah Hani Alquhayz Khushbakht safdar Department of Computer Science Air UniversitySector E-9PAF ComplexIslamabad44000Pakistan Department of ICT Convergence System Engineering Chonnam National UniversityGwangjuKorea Directorate of National Repository IslamabadPakistan Department of Computer Science Bahauddin Zakariya UniversityMultan60000Pakistan Department of Computer Science and Information College of Science in ZulfiMajmaah UniversityAl-Majmaah11952Saudi Arabia Pakistan Atomic Energy Commission General HospitalIslamabadPakistan

Breast cancer resistance protein(BCRP)is an important resistance protein that significantly impacts anticancer drug discovery,treatment,and *** identification of BCRP substrates is quite a challenging *** study aims to predict early substrate structure,which can help to optimize anticancer drug development and clinical *** this study,a novel intelligent approach-based methodology is developed by modifying the ResNet101 model using transfer learning(TL)for automatic deep feature(DF)extraction followed by classification with linear discriminant analysis algorithm(TLRNDF-LDA).This study utilized structural fingerprints,which are exploited by DF contrary to conventional molecular *** proposed in silico model achieved an outstanding accuracy performance of 98.56%on test data compared to other state-of-the-art approaches using standard quality ***,the model’s efficacy is validated via a statistical *** is demonstrated that the developedmodel can be used effectively for early prediction of the substrate *** pipeline of this study is flexible and can be extended for in vitro assessment efficacy of anticancer drug response,identification of BCRP functions in transport experiments,and prediction of prostate or lung cancer cell lines.

关键词： BCRP drug response deep learning transfer learning LDA In silico

Cyber Secure Framework for Smart Containers Based on Novel Hybrid DTLS Protocol

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 2022年第12期43卷 1297-1313页

作者： Waseem Ullah Khan safdar Nawaz Khan Marwat Salman Ahmed Department of Computer Systems Engineering University of Engineering and Technology PeshawarPeshawar25120Pakistan

The Internet of Things (IoTs) is apace growing, billions of IoT devicesare connected to the Internet which communicate and exchange data among eachother. Applications of IoT can be found in many fields of engineering and sciencessuch as healthcare, traffic, agriculture, oil and gas industries, and logistics. Inlogistics, the products which are to be transported may be sensitive and perishable, and require controlled environment. Most of the commercially availablelogistic containers are not integrated with IoT devices to provide controlled environment parameters inside the container and to transmit data to a remote *** necessitates the need for designing and fabricating IoT based smart containers. Due to constrained nature of IoT devices, these are prone to different cybersecurity attacks such as Denial of Service (DoS), Man in Middle (MITM) andReplay. Therefore, designing efficient cyber security framework are required forsmart container. The Datagram Transport Layer Security (DTLS) Protocol hasemerged as the de facto standard for securing communication in IoT ***, it is unable to minimize cyber security attacks such as Denial of Serviceand Distributed Denial of Service (DDoS) during the handshake process. Themain contribution of this paper is to design a cyber secure framework by implementing novel hybrid DTLS protocol in smart container which can efficientlyminimize the effects of cyber attacks during handshake process. The performanceof our proposed framework is evaluated in terms of energy efficiency, handshaketime, throughput and packet delivery ratio. Moreover, the proposed framework istested in IoT based smart containers. The proposed framework decreases handshake time more than 9% and saves 11% of energy efficiency for transmissionin compare of the standard DTLS, while increases packet delivery ratio andthroughput by 83% and 87% respectively.

关键词： Logistic container logistics security cyber security perishable products monitoring

End-to-End 2D Convolutional Neural Network Architecture for Lung Nodule Identification and Abnormal Detection in Cloud

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4期75卷 461-475页

作者： safdar Ali Saad Asad Zeeshan Asghar Atif Ali Dohyeun Kim Department of Software Engineering the University of LahoreDefence Road CampusLahore55150Pakistan Department of Computer Engineering Jeju National UniversityAra CampusJeju City63243Korea

The extent of the peril associated with cancer can be perceivedfrom the lack of treatment, ineffective early diagnosis techniques, and mostimportantly its fatality rate. Globally, cancer is the second leading cause ofdeath and among over a hundred types of cancer;lung cancer is the secondmost common type of cancer as well as the leading cause of cancer-relateddeaths. Anyhow, an accurate lung cancer diagnosis in a timely manner canelevate the likelihood of survival by a noticeable margin and medical imagingis a prevalent manner of cancer diagnosis since it is easily accessible to peoplearound the globe. Nonetheless, this is not eminently efficacious consideringhuman inspection of medical images can yield a high false positive rate. Ineffectiveand inefficient diagnosis is a crucial reason for such a high mortalityrate for this malady. However, the conspicuous advancements in deep learningand artificial intelligence have stimulated the development of exceedinglyprecise diagnosis systems. The development and performance of these systemsrely prominently on the data that is used to train these systems. A standardproblem witnessed in publicly available medical image datasets is the severeimbalance of data between different classes. This grave imbalance of data canmake a deep learning model biased towards the dominant class and unableto generalize. This study aims to present an end-to-end convolutional neuralnetwork that can accurately differentiate lung nodules from non-nodules andreduce the false positive rate to a bare minimum. To tackle the problem ofdata imbalance, we oversampled the data by transforming available images inthe minority class. The average false positive rate in the proposed method isa mere 1.5 percent. However, the average false negative rate is 31.76 *** proposed neural network has 68.66 percent sensitivity and 98.42 percentspecificity.

关键词： Convolutional neural networks medical image processing lung nodule identification data imbalance deep learning

Sickle cell nephropathy:A review of novel biomarkers and their potential roles in early detection of renal involvement

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Clinical Pediatrics 2022年第1期11卷 14-26页

作者： osam. y.safdar Rana M Baghdadi Sereen A Alahmadi Bana E Fakieh Amaal M Algaydi of Pediatric King Abdulaziz UniversityJEDDAH 21414Saudi Arabia College of Medicine King Abdulaziz UniversityJEDDAH 21422Saudi Arabia

Whether the underlying mutations are homozygous,heterozygous,or coinherited with other hemoglobinopathies,sickle cell disease is known to afflict the kidneys,leading to the clinical entity known as sickle cell nephropathy(SCN).Although common,SCN remains diagnostically *** studies performed in the context of renal disorders often fail to detect early stage *** makes the quest for early diagnosis and treatment more challenging,and it increases the burden of chronic kidney disease-related morbidity among *** diagnostic tools have been employed to overcome this *** this study,we discuss various biomarkers of SCN,including those employed in clinical practice and others recently identified in experimental settings,such as markers of vascular injury,endothelial dysfunction,tubulo-glomerular damage,and oxidative *** include kidney injury molecule-1,monocyte chemoattractant protein-1,N-acetyl-B-D-glucosam.nidase,ceruloplasmin,orosomucoid,nephrin,and cation channels,among ***,we explore the potential of novel biomarkers for refining diagnostic and therapeutic approaches and describe some obstacles that still need to be *** highlight the importance of a collaborative approach to standardize the use of promising new ***,we outline the limitations of conventional markers of renal damage as extensions of the pathogenic process occurring at the level of the organ and its functional subunits,with a discussion of the expected pattern of clinical and biochemical progression among patients with SCN.

关键词： Sickle cell disease Sickle cell nephropathy Chronic kidney disease Kidney injury molecule-1 Monocyte chemoattractant protein-1 N-acetyl-B-D-glucosam.nidase

An Efficient Method for Underwater Video Summarization and Object Detection Using yoLoV3

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第2期35卷 1295-1310页

作者： Mubashir Javaid Muazzam Maqsood Farhan Aadil Jibran safdar yongsung Kim Department of Computer Science UETTaxilaPakistan Department of Computer Science COMSATS University IslamabadAttock CampusAttockPakistan Department of Technology Education Chungnam National UniversityDaejeon34134Korea

Currently,worldwide industries and communities are concerned with building,expanding,and exploring the assets and resources found in the oceans and *** precisely,to analyze a stock,archaeology,and surveillance,sev-eral cameras are installed underseas to collect ***,on the other hand,these large size videos require a lot of time and memory for their processing to extract relevant ***,to automate this manual procedure of video assessment,an accurate and efﬁcient automated system is a greater *** this perspective,we intend to present a complete framework solution for the task of video summarization and object detection in underwater *** employed a perceived motion energy(PME)method toﬁrst extract the keyframes followed by an object detection model approach namely yoloV3 to perform object detection in underwater *** issues of blurriness and low contrast in underwater images are also taken into account in the presented approach by applying the image enhancement ***,the suggested framework of underwater video summarization and object detection has been evaluated on a publicly available brackish *** is observed that the proposed framework shows good performance and hence ultimately assists several marine researchers or scientists related to theﬁeld of underwater archaeology,stock assessment,and surveillance.

关键词： Computer vision deep learning digital image processing underwater video analysis video summarization object detection yOLOV3

Status and Social Capital:A Cross-Sectional Quantitative Investigation of Flood Survivors in South Punjab,Pakistan

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Disaster Risk Science 2022年第4期13卷 549-560页

作者： Muhammad Siddique Akbar Muhammad Rizwan safdar Farhan Navid yousaf Daniel P.Aldrich Institute of Social and Cultural Studies University of the PunjabLahore 054590Pakistan Security and Resilience Studies Program Department of Political ScienceNortheastern UniversityBostonMA 02115USA

A growing body of evidence underscores that social capital mitigates the impact of natural hazards such as *** we know less about the distribution of social ties in developing countries regularly hit by *** study examined the differences between demographic groups in South Punjab,Pakistan affected by the 2010 floods,comparing respondents'levels of social capital measured through proxies such as received social support,perceived community cohesion,accessibility to leadership,and general level of *** carried out univariate and multivariate analyses of factors including gender,education,occupation,landholding,family size,annual income,number of livestock,and home *** data collected in face-to-face interviews with 450 flood survivors,our analysis showed no statistically significant difference in the flood victims'scores on all four scales based on gender and family ***,education,occupation,landholding,annual income,and home stability statistically correlated with levels of social *** with high levels of education,high levels of land,higher home stability,and a government job typically had higher scores in all four measurements of social *** results show strong inequality in the distribution of social capital,with better connections and assistance coming to those who already have better socioeconomic positions in society.

关键词： Flood survivors Pakistan Social capital South Punjab

Genetics of congenital and infantile nephrotic syndrome

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

World Journal of Pediatrics 2019年第2期15卷 198-203页

作者： Sara Nawfal Sharief Nada Abdullatif Hefni Walaa Ali Alzahrani Iman Ibrahim Nazer Marwa Abdullah Bayazeed Khalid A.Alhasan osam. y.safdar Sherif M.El-Desoky Jameela Abdulaziz Kari King Abdulaziz University JeddahKingdom of Saudi Arabia College of Medicine Pediatric DepartmentKing Saud UniversityRiyadhKingdom of Saudi Arabia Department of Pediatrics Faculty of MedicinePediatric Nephrology Center of ExcellenceKing Abdulaziz UniversityPO Box 80215Jeddah 21589Kingdom of Saudi Arabia

Background Congenital and infantile nephrotic syndrome (CNS and INS) are rare inherited defects in glomerular filtration involving a variety of gene *** study aimed to analyze all genetic mutations associated with congenital and infantile nephrotic syndrome treated at our *** also discussed our different approach secondary to culture and *** A retrospective single-center study of all children diagnosed as NS before the age of l year over a duration of over one *** Twenty-nine children (12 boys) were included in the *** median age (range) was 2.4 (0.1-12) months (20 CNS and 9 INS).Consanguinity was present in 90% of *** genetic analysis' results were only available for 20 *** underlying causative homozygous mutation was detected in 18 children (90%):NPHS1 (9),NPHS2(2),LAMB2(3),PLCE1(1),WT1(1),and ITSN1 novel mutation (2).One child had heterozygous mutation of NPHS2 and another child had heterozygous mutation of NPHS1 which could not explain the *** CNS cases were all managed with intermittent intravenous albumin infusion,ACEi,diuretics,and *** of the children were managed by nephrectomy followed by peritoneal dialysis (PD) because of limited *** one child achieved partial remission,while 15 children died at a median (range) age of 5.8 (1.25-29) *** remaining 14 children were followed up for an average of 36 (3.9-120) *** children progressed to end-stage kidney disease and PD was performed in only two *** NPHS1 is the main underlying cause of CNS and INS in our study *** and INS were associated with high morbidity and mortality.

关键词： Congenital nephrotic Infantile nephrotic Genetics Outcome

Sign Language to Sentence Formation:A Real Time Solution for Deaf People

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8期72卷 2501-2519页

作者： Muhammad Sanaullah Muhammad Kashif Babar Ahmad Tauqeer safdar Mehdi Hassan Mohd Hilmi Hasan Amir Haider Bahauddin Zakariya University Department of Computer ScienceMultan60000Pakistan Air University Department of Computer ScienceMultan60000Pakistan Air University Department of Computer ScienceIslamabad44000Pakistan Centre for Research in Data Science Department of Computer and Information SciencesUniversiti Teknologi PETRONASSeri Iskandar32610PerakMalaysia Department of Intelligent Mechatronics Engineering Sejong UniversitySeoul05006Korea

Communication is a basic need of every human being to exchange thoughts and interact with the *** peoples usually confab through different spoken languages,whereas deaf people cannot do ***,the Sign Language(SL)is the communication medium of such people for their conversation and interaction with the *** SL is expressed in terms of specific gesture for every word and a gesture is consisted in a sequence of performed *** acute people normally observe these signs to understand the difference between single and multiple gestures for singular and plural words *** signs for singular words such as I,eat,drink,home are unalike the plural words as school,cars,players.A special training is required to gain the sufficient knowledge and practice so that people can differentiate and understand every gesture/sign *** researches have been performed to articulate the computer-based solution to understand the single gesture with the help of a single hand *** complete understanding of such communications are possible only with the help of this differentiation of gestures in computer-based solution of SL to cope with the real world ***,there is still a demand for specific environment to automate such a communication solution to interact with such type of special *** research focuses on facilitating the deaf community by capturing the gestures in video format and then mapping and differentiating as single or multiple gestures used in ***,these are converted into the respective words/sentences within a reasonable *** provide a real time solution for the deaf people to communicate and interact with the society.

关键词： Sign language machine learning conventional neural network image processing deaf community