检索结果-南通市图书馆

Neural Machine Translation Models with Attention-Based Dropout Layer

Computers, Materials & Continua 2023年第5期75卷 2981-3009页

作者： Huma Israr safdar abbas khan Muhammad Ali Tahir Muhammad Khuram Shahzad Muneer Ahmad Jasni Mohamad Zain School of Electrical Engineering and Computer Science(SEECS) National University of Science and TechnologyIslamabadPakistan Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Kompleks Al-KhawarizmiUniversiti Teknologi MARA40450Shah AlamSelangorMalaysia

In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of *** model has obtained state-of-the-art performance for several language ***,there has been little work exploring useful architectures for Urdu-to-English machine *** conducted extensive Urdu-to-English translation experiments using Long short-term memory(LSTM)/Bidirectional recurrent neural networks(Bi-RNN)/Statistical recurrent unit(SRU)/Gated recurrent unit(GRU)/Convolutional neural network(CNN)and *** results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen *** trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,*** a qualitative perspective,the translation of the test sets was examined manually,and it was observed that trained models tend to produce repetitive output more *** attention score produced by Bi-RNN and LSTM produced clear alignment,while GRU showed incorrect translation for words,poor alignment and lack of a clear ***,we considered refining the attention-based models by defining an additional attention-based dropout *** dropout fixes alignment errors and minimizes translation errors at the word *** empirical demonstration and comparison with their counterparts,we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation *** ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as *** empirically concluded that adding an attention-based dropout layer helps improve GRU,SRU,and Transformer translation and is considerably more efficient in translation quality and speed.

关键词： Natural language processing neural machine translation word embedding attention perplexity selective dropout regularization Urdu Persian Arabic BLEU

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

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

引用

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

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

Text Augmentation-Based Model for Emotion Recognition Using Transformers

引用

Computers, Materials & Continua 2023年第9期76卷 3523-3547页

作者： Fida Mohammad Mukhtaj khan safdar Nawaz khan Marwat Naveed Jan Neelam Gohar Muhammad Bilal Amal Al-Rasheed Department of Computer Science The University of HaripurHaripur22620Pakistan Department of Computer Systems Engineering Faculty of Electrical and Computer EngineeringUniversity of Engineering and Technology PeshawarPeshawar25120Pakistan Department of Electronics Engineering Technology University of TechnologyNowshera24100Pakistan Department of Computer Science Shaheed Benazir BhuttoWomen UniversityPeshawar25000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia

Emotion Recognition in Conversations(ERC)is fundamental in creating emotionally ***-BasedNetwork(GBN)models have gained popularity in detecting conversational contexts for ERC ***,their limited ability to collect and acquire contextual information hinders their *** propose a Text Augmentation-based computational model for recognizing emotions using transformers(TA-MERT)to address *** proposed model uses the Multimodal Emotion Lines Dataset(MELD),which ensures a balanced representation for recognizing human *** used text augmentation techniques to producemore training data,improving the proposed model’s *** encoders train the deep neural network(DNN)model,especially Bidirectional Encoder(BE)representations that capture both forward and backward contextual *** integration improves the accuracy and robustness of the proposed ***,we present a method for balancing the training dataset by creating enhanced samples from the original *** balancing the dataset across all emotion categories,we can lessen the adverse effects of data imbalance on the accuracy of the proposed *** results on the MELD dataset show that TA-MERT outperforms earlier methods,achieving a weighted F1 score of 62.60%and an accuracy of 64.36%.Overall,the proposed TA-MERT model solves the GBN models’weaknesses in obtaining contextual data for ***-MERT model recognizes human emotions more accurately by employing text augmentation and transformer-based *** balanced dataset and the additional training samples also enhance its *** findings highlight the significance of transformer-based approaches for special emotion recognition in conversations.

关键词： Emotion recognition in conversation graph-based network text augmentation-basedmodel multimodal emotion lines dataset bidirectional encoder representation for transformer

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

Reconfigurable Compact Wideband Circularly Polarised Dielectric Resonator Antenna for Wireless Applications

引用

Computers, Materials & Continua 2021年第8期68卷 2095-2109页

作者： Shahid khan Xin Cheng Ren Haider Ali Camel Tanougast Abdul Rauf safdar Nawaz khan Marwat Muhammad Rizwan Anjum LCOMS ASECUniversity de LorraineMetz57070France School of Physics and Electronic Information Yanan UniveristyYanan761000China Department of Electronics Technology University of TechnologyNowshera24100Pakistan Department of Electrical Engineering National University of Sciences and TechnologyIslamabad44000Pakistan Department of Computer Systems Engineering University of Engineering and TechnologyPeshawar25120Pakistan Department of Electronic Engineering The Islamia University of BahawalpurBahawalpur63100Pakistan

In this work,a novel compact wideband reconfigurable circularly polarised(CP)dielectric resonator antenna(DRA)is *** L-shaped Dielectric resonator antenna is excited by an inverted question mark shaped *** arrangement of feed-line helps to generate two orthogonal modes inside the DR,which makes the design circularly polarised.A thin micro-strip line placed on the defected ground plane not only helps to generate a wideband response but also assist in the positioning of the two diode *** switches located at the left and right of the micro-strip line helps in performing two switching *** novel compact design offers the reconfigurability between 2.9–3.8 GHz which can be used for different important wireless *** the switching operation I,the achieved impedance bandwidth is 24%while axial ratio bandwidth(ARBW)is 42%.For this switching state,the design has 100%CP ***,the switching operation II achieves 60%impedance bandwidth and 58.88%ARBW with 76.36%CP *** proposed design has a maximum measured gain of 3.4 dBi and 93%radiation *** proposed design is novel in terms of compactness and performance *** prototype is fabricated for the performance analysis which shows that the simulated and measured results are in close agreement.

关键词： Circularly polarized DRA ARBW bandwidth gain radiation efficiency

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 Novel Action Transformer Network for Hybrid Multimodal Sign Language Recognition

引用

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

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

Suspicious Activities Recognition in Video Sequences Using DarkNet-NasNet Optimal Deep Features

引用

Computer Systems Science & Engineering 2023年第11期47卷 2337-2360页

作者： safdar khan Muhammad Attique khan Jamal Hussain Shah Faheem Shehzad Taerang Kim Jae-Hyuk Cha Department of Computer Science COMSATS University IslamabadWah CampusWah Cantt47040Pakistan Department of Computer Science HITEC UniversityTaxila47080Pakistan Department of Computer Science Hanyang UniversitySeoul04763Korea

Human Suspicious Activity Recognition(HSAR)is a critical and active research area in computer vision that relies on artificial intelligence *** advances have been made in this field recently due to important applications such as video *** video surveillance,humans are monitored through video cameras when doing suspicious activities such as kidnapping,fighting,snatching,and a few *** numerous techniques have been introduced in the literature for routine human actions(HAR),very few studies are available for *** study proposes a deep convolutional neural network(CNN)and optimal featuresbased framework for HSAR in video *** framework consists of various stages,including preprocessing video frames,fine-tuning deep models(Darknet 19 and Nasnet mobile)using transfer learning,serial-based feature fusion,feature selection via equilibrium feature optimizer,and neural network classifiers for ***-tuning two models using some hit and trial methods is the first challenge of this work that was later employed for feature ***,features are fused in a serial approach,and then an improved optimization method is proposed to select the best *** proposed technique was evaluated on two action datasets,Hybrid-KTH01 and HybridKTH02,and achieved an accuracy of 99.8%and 99.7%,*** proposed method exhibited higher precision compared to existing state-ofthe-art approaches.

关键词： Suspicious activity deep learning weights surveillance 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

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

引用

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

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

Adipose-brain crosstalk: do adipokines have a role in neuroprotection?

引用

Neural Regeneration Research 2015年第9期10卷 1381-1382页

作者： Jonathan P.Little Adeel safdar School of Health and Exercise Sciences University of British Columbia Okanagan Departments of Pediatrics and Medicine Mc Master University

Accumulating evidence from epidemiological and experi- mental studies indicate that obesity, and its related metabolic consequences of insulin resistance and type 2 diabetes, are associated with accelerated cognitive decline （Yates et al., 2012）. The etiology of neurodegeneration in obesity is undoubtedly complex, with vascular, metabolic, inflammatory, and structural changes all likely to play a role （Yates et al., 2012）. The discovery of leptin in 1994 and the subsequent advancement in our understanding that adipose tissue is an endocrine organ that can communicate with the brain to regulate appetite （Zhang et al., 1994） brings about the in- triguing possibility that adipose-brain crosstalk can regulate aspects of neuronal physiology and pathology （Aguilar-Valles et al., 2015）. Indeed neurons have been shown to express receptors for various adipokines, indicating that factors released from adipose tissue have the potential to communi- cate directly with the brain. Research in this area is relatively new, and while epidemiological data points towards the negative consequences of adipose-brain crosstalk （Whitmer et al., 2005）, some intriguing new studies highlight that the secretory profile of adipose tissue might be involved in reduction in neurodegeneration via maintenance of neuronal viability （Tezapsidis et al., 2009; Wan et al., 2015）.

关键词： cell Adipose-brain crosstalk

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

Analysis of socio-environmental impacts of the loss of urban trees and vegetation in Lahore,Pakistan:a review of public perception

引用

Ecological Processes 2016年第1期5卷 48-59页

作者： safdar Ali Shirazi Jamil H.Kazmi Department of Geography University of the PunjabQuaid-i-Azam CampusLahorePakistan Department of Geography University of KarachiKarachiPakistan

Introduction:This paper focused on the process of urbanization in Lahore and its correlation with the loss of urban vegetation and perceived environmental impacts based on local population’s perception through administration of a questionnaire *** is known as a city of gardens and green spaces in Pakistan and always possessed rich green character in its long *** the past few decades due to rapid urbanization,the city has lost its aesthetically important urban vegetation,tress,and *** field studies and remote sensing data revealed that the loss of vegetation has been experienced at an astonishing rate in many union councils of the ***:This study was conceived to probe importance and value of the urban tress and vegetation of Lahore in an environmental context and its general importance for the residents of the *** objectives were to analyze the role of vegetation in the life of citizens;the specific objective was to reveal the attitudes and responses of city dwellers about loss of urban trees/vegetation and its role in the overall environment,process of urbanization,and maintenance *** the present paper,perception of local people(n=2080)regarding the socio-environmental impacts due to the ongoing process of urbanization and detriments of vegetation loss has been probed through administration of a household *** collected data has been tested with respondent’s age,gender,marital status,education,monthly income,and ***:This study was an attempt to document and explore the change in historical transformation in vegetation and perception of the sample population of *** perception survey has revealed that urbanization is the major cause of loss of vegetation and has caused a number of perceived environmental problems in the ***:The study underlined an analysis of people’s perceptions regarding the loss of trees and *** perceived socio-environmental findings revea

关键词： Anthropogenic Union council Socio-environmental Perception Vegetation Urban trees

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

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

引用

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

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：