检索结果-南通市图书馆

IDSSCNN-XgBoost:Improved Dual-Stream Shallow Convolutional Neural Network Based on Extreme Gradient Boosting Algorithm for Micro Expression 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 2025年第1期82卷 729-749页

作者： Adnan Ahmad Zhao Li Irfan tariq Zhengran He School of Information Science and Engineering Southeast UniversityNanjing210016China

Micro-expressions(ME)recognition is a complex task that requires advanced techniques to extract informative features fromfacial *** deep neural networks(DNNs)with convolutional structures have been ***,unlike DNNs,shallow convolutional neural networks often outperform deeper models in mitigating overfitting,particularly with small ***,many of these methods rely on a single feature for recognition,resulting in an insufficient ability to extract highly effective *** address this limitation,in this paper,an Improved Dual-stream Shallow Convolutional Neural Network based on an Extreme Gradient Boosting Algorithm(IDSSCNN-XgBoost)is introduced for ME *** proposed method utilizes a dual-stream architecture where motion vectors(temporal features)are extracted using Optical Flow TV-L1 and amplify subtle changes(spatial features)via EulerianVideoMagnification(EVM).These features are processed by IDSSCNN,with an attention mechanism applied to refine the extracted effective *** outputs are then fused,concatenated,and classified using the XgBoost *** comprehensive approach significantly improves recognition accuracy by leveraging the strengths of both temporal and spatial information,supported by the robust classification power of *** proposed method is evaluated on three publicly available ME databases named Chinese Academy of Sciences Micro-expression Database(CASMEII),Spontaneous Micro-Expression Database(SMICHS),and Spontaneous Actions and Micro-Movements(SAMM).Experimental results indicate that the proposed model can achieve outstanding results compared to recent *** accuracy results are 79.01%,69.22%,and 68.99%on CASMEII,SMIC-HS,and SAMM,and the F1-score are 75.47%,68.91%,and 63.84%,*** proposed method has the advantage of operational efficiency and less computational time.

关键词： ME recognition dual stream shallow convolutional neural network euler video magnification TV-L1 XgBoost

Image Authenticity Detection Using DWT and Circular Block-Based LTrP Features

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 2021年第11期69卷 1927-1944页

作者： Marriam Nawaz Zahid Mehmood Tahira Nazir Momina Masood Usman tariq Asmaa Mahdi munshi Awais Mehmood Muhammad Rashid Department of Computer Science University of Engineering and TechnologyTaxila47050Pakistan Department of Computer Engineering University of Engineering and TechnologyTaxila47050Pakistan College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia College of Computer Science and Engineering University of JeddahJeddah21577Saudi Arabia Department of Computer Engineering Umm Al-Qura UniversityMakkah21421Saudi Arabia

Copy-move forgery is the most common type of digital image manipulation,in which the content from the same image is used to forge *** manipulations are performed to hide the desired ***,forgery detection methods are required to identify forged *** have introduced a novel method for features computation by employing a circular block-based method through local tetra pattern(LTrP)features to detect the single and multiple copy-move attacks from the *** proposed method is applied over the circular blocks to efficiently and effectively deal with the post-processing *** also uses discrete wavelet transform(DWT)for dimension *** obtained approximate image is distributed into circular blocks on which the LTrP algorithm is employed to calculate the feature vector as the LTrP provides detailed information about the image content by utilizing the direction-based relation of central pixel to its ***,Jeffreys and Matusita distance is used for similarity *** the evaluation of the results,three datasets are used,namely MICC-F220,MICC-F2000,and *** the qualitative and quantitative analysis shows that the proposed method exhibits state-of-the-art performance under the presence of post-processing operations and can accurately locate single and multiple copy-move forgery attacks on the images.

关键词： Copy-move forgery discrete wavelet transform LTrP features image forensic circular blocks

Influence of site conditions on seismic design parameters for foundations as determined via nonlinear site response analysis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2021年第1期15卷 275-303页

作者： Muhammad tariq A.CHAUDHARY Civil Engineering Department Kuwait UniversityKhalidya 13060Kuwait

Site conditions,including geotechnical properties and the geological setting,influence the near-surface response of strata subjected to seismic *** geotechnical parameters required for the design of foundations include mass density(ρ),damping ratio(β_(s)),shear wave velocity(V_(s)),and soil shear modulus(G_(s)).The values of the last three parameters are sensitive to the level of nonlinear strain induced in the strata due to seismic ground *** this study,the effect of variations in soil properties,such as plasticity index(PI),effective stress(σ′),over consolidation ratio(OCR),impedance contrast ratio(ICR)between the bedrock and the overlying strata,and depth of soil strata over bedrock(H),on seismic design parameters(β_(s),V_(s),and G_(s))was investigated for National Earthquake Hazards Reduction Program(NEHRP)site classes C and D,through 1D nonlinear seismic site response *** Morris one-at-a-time(OAT)sensitivity analysis indicated thatβ_(s),V_(s),and G_(s)were significantly influenced by variations in PI,while ICR affectedβ_(s)more than it affected V_(s)and G_(s).However,the influence of H on these parameters was less *** was also found that variations in soil properties influenced seismic design parameters in soil type D more significantly than in soil type *** relationships forβ_(s),V_(s),and G_(s)were derived based on the 1D seismic site response analysis and sensitivity analysis ***β_(s),V_(s),and G_(s)values obtained from the analysis were compared with the corresponding values in NEHRP to determine the similarities and differences between the two sets of *** need to incorporate PI and ICR in the metrics for determiningβ_(s),V_(s),and G_(s)for the seismic design of foundations was highlighted.

关键词： site effects 1D seismic site response analysis sensitivity analysis foundations shear wave velocity soil shear modulus

A comparison of IBC with 1997 UBC for modal response spectrum analysis in standard-occupancy buildings

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

Earthquake Engineering and Engineering Vibration 2011年第1期10卷 99-113页

作者： tariq M. Nahhas Umm Al-Qura University

This paper presents a comparison of the seismic forces generated from a Modal Response Spectrum Analysis （MRSA） by applying the provisions of two building codes, the 1997 Uniform Building Code （UBC） and the 2000-2009 International Building Code （IBC）, to the most common ordinary residential buildings of standard occupancy. Considering IBC as the state of the art benchmark code, the primary concern is the safety of buildings designed using the UBC as compared to those designed using the IBC. A sample of four buildings with different layouts and heights was used for this comparison. Each of these buildings was assumed to be located at four different geographical sample locations arbitrarily selected to represent various earthquake zones on a seismic map of the USA, and was subjected to code-compliant response spectrum analyses for all sample locations and for five different soil types at each location. Response spectrum analysis was performed using the ETABS software package. For all the cases investigated, the UBC was found to be significantly more conservative than the IBC. The UBC design response spectra have higher spectral accelerations, and as a result, the response spectrum analysis provided a much higher base shear and moment in the structural members as compared to the IBC. The conclusion is that ordinary office and residential buildings designed using UBC 1997 are considered to be overdesigned, and therefore they are quite safe even according to the IBC provisions.

关键词： response spectrum analysis seismic forces multi-story buildings seismic design building codes IBC UBC

Evaluation of line brattice length in an empty heading to improve air flow rate at the face using CFD

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

International Journal of Mining Science and Technology 2017年第2期27卷 253-259页

作者： Feroze tariq Genc Bekir School of Mining Engineering University of the WitwatersrandJohannesburg 2050South Africa

The effectiveness of line brattice(LB) ventilation system depends on the associated system ***, the effect of these variables on the air flow rates close to the face of the heading is not extensively studied. In this paper, the effect of the LB length in relation to the LB-wall distance on the air flow rate reaching the face is analysed. Scenarios were developed using four LB lengths, two LB-wall distances and two heading depths. These scenarios were simulated with a validated CFD model. The air flow rates and patterns at various locations inside the heading were analysed. This helped to find the minimum LB-face distance that should be maintained for each LB-wall distance to maximise the air flow rate at the face. The minimum length when used will improve ventilation and reduce energy cost.

关键词： Coal mine ventilation Auxiliary ventilation Line brattice ventilation system Computational fluid dynamics

Defocus Blur Segmentation Using Genetic Programming and Adaptive Threshold

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

Computers, Materials & Continua 2022年第3期70卷 4867-4882页

作者： Muhammad tariq Mahmood Future Convergence Engineering School of Computer Science and EngineeringKorea University of Technology and EducationCheonan31253Byeongcheon-myeonKorea

Detection and classification of the blurred and the non-blurred regions in images is a challenging task due to the limited available information about blur type,scenarios and level of *** this paper,we propose an effective method for blur detection and segmentation based on transfer learning *** proposed method consists of two separate *** the first step,genetic programming(GP)model is developed that quantify the amount of blur for each pixel in the *** GP model method uses the multiresolution features of the image and it provides an improved blur *** the second phase,the blur map is segmented into blurred and non-blurred regions by using an adaptive threshold.A model based on support vector machine(SVM)is developed to compute adaptive threshold for the input blur *** performance of the proposed method is evaluated using two different datasets and compared with various state-of-the-art *** comparative analysis reveals that the proposed method performs better against the state-of-the-art techniques.

关键词： Blur measure blur segmentation sharpness measure genetic programming support vector machine

Linear Wavefield Optimization Using a Modified Source

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Communications in Computational Physics 2020年第6期28卷 276-296页

作者： tariq Alkhalifah Physical Sciences and Engineering King Abdullah University of Science and TechnologyMail box#1280Thuwal 23955-6900Saudi Arabia

Recorded seismic data are sensitive to the Earth’s elastic properties,and thus,they carry information of such properties in their *** sensitivity of such waveforms to the properties is nonlinear causing all kinds of difficulties to the inversion of such *** directly for the components forming the wave equation,which includes the wave equation operator(or its perturbation),and the wavefield,as independent parameters enhances the convexity of the inverse *** optimization in this case is provided by an objective function that maximizes the data fitting and the wave equation fidelity,*** enhance the practicality and efficiency of the optimization,I recast the velocity perturbations as secondary sources in a modified source function,and invert for the wavefield and the modified source function,as independent *** optimization in this case corresponds to a linear *** inverted functions can be used directly to extract the velocity *** gradient methods,this optimization problem is free of the Born approximation limitations in the update,including single scattering and cross talk that may arise for example in the case of multi *** specific features are shown for a simple synthetic example,as well as the Marmousi model.

关键词： Inversion optimization scattering theory

Big Data Analytics with Optimal Deep Learning Model for Medical Image Classification

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 2023年第2期44卷 1433-1449页

作者： tariq Mohammed Alqahtani Department of Medical Equipment Technology College of Applied Medical SciencesMajmaah UniversityAl Majmaah11952Saudi Arabia

In recent years,huge volumes of healthcare data are getting generated in various *** advancements made in medical imaging are tremendous owing to which biomedical image acquisition has become easier and *** to such massive generation of big data,the utilization of new methods based on Big Data Analytics(BDA),Machine Learning(ML),and Artiﬁcial Intelligence(AI)have become *** this aspect,the current research work develops a new Big Data Analytics with Cat Swarm Optimization based deep Learning(BDA-CSODL)technique for medical image classiﬁcation on Apache Spark *** aim of the proposed BDA-CSODL technique is to classify the medical images and diagnose the disease ***-CSODL technique involves different stages of operations such as preprocessing,segmentation,fea-ture extraction,and classiﬁ*** addition,BDA-CSODL technique also fol-lows multi-level thresholding-based image segmentation approach for the detection of infected regions in medical ***,a deep convolutional neural network-based Inception v3 method is utilized in this study as feature *** Gradient Descent(SGD)model is used for parameter tuning ***,CSO with Long Short-Term Memory(CSO-LSTM)model is employed as a classiﬁcation model to determine the appropriate class labels to *** SGD and CSO design approaches help in improving the overall image classiﬁcation performance of the proposed BDA-CSODL technique.A wide range of simulations was conducted on benchmark medical image datasets and the com-prehensive comparative results demonstrate the supremacy of the proposed BDA-CSODL technique under different measures.

关键词： Big data analytics healthcare deep learning image classiﬁcation biomedical imaging machine learning

Hybridizing Artificial Bee Colony with Bat Algorithm for Web Service Composition

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 2023年第8期46卷 2429-2445页

作者： tariq Ahamed Ahanger Fadl Dahan Usman tariq Department of Management Information Systems College of Business AdministrationPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Management Information Systems College of Business Administration-Hawtat Bani TamimPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Computer Sciences Faculty of Computing and Information Technology Al-TurbahTaiz UniversityTaiz9674Yemen

In the Internet of Things(IoT),the users have complex needs,and the Web Service Composition(WSC)was introduced to address these *** WSC’s main objective is to search for the optimal combination of web services in response to the user needs and the level of Quality of Services(QoS)*** challenge of this problem is the huge number of web services that achieve similar functionality with different levels of QoS *** this paper,we introduce an extension of our previous works on the Artificial Bee Colony(ABC)and Bat Algorithm(BA).A new hybrid algorithm was proposed between the ABC and BA to achieve a better tradeoff between local exploitation and global *** bat agent is used to improve the solution of exhausted bees after a threshold(limits),and also an Elitist Strategy(ES)is added to BA to increase the convergence *** performance and convergence behavior of the proposed hybrid algorithm was tested using extensive comparative experiments with current state-ofthe-art nature-inspired algorithms on 12 benchmark datasets using three evaluation criteria(average fitness values,best fitness values,and execution time)that were measured for 30 different *** datasets are created from real-world datasets and artificially to form different scale sizes of WSC *** results show that the proposed algorithm enhances the search performance and convergence rate on finding the near-optimal web services combination compared to *** signed-rank significant test is usedwhere the proposed algorithm results significantly differ fromother algorithms on 100%of datasets.

关键词： Internet of things artificial bee colony bat algorithm elitist strategy web service composition