检索结果-南通市图书馆

Limits of Depth: Over-Smoothing and Over-Squashing in GNNs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2024年第1期7卷 205-216页

作者： Aafaq Mohi ud din Shaima Qureshi Department of Computer Science and Engineering National Institute of Technology SrinagarSrinagar 190006India

Graph Neural Networks(GNNs)have become a widely used tool for learning and analyzing data on graph structures,largely due to their ability to preserve graph structure and properties via graph representation ***,the effect of depth on the performance of GNNs,particularly isotropic and anisotropic models,remains an active area of *** study presents a comprehensive exploration of the impact of depth on GNNs,with a focus on the phenomena of over-smoothing and the bottleneck effect in deep graph neural *** research investigates the tradeoff between depth and performance,revealing that increasing depth can lead to over-smoothing and a decrease in performance due to the bottleneck *** also examine the impact of node degrees on classification accuracy,finding that nodes with low degrees can pose challenges for accurate *** experiments use several benchmark datasets and a range of evaluation metrics to compare isotropic and anisotropic GNNs of varying depths,also explore the scalability of these *** findings provide valuable insights into the design of deep GNNs and offer potential avenues for future research to improve their performance.

关键词： Graph Neural Networks(GNNs) learning on graphs over-smoothing over-squashing isotropic-GNNs anisotropic-GNNs

Assessment of seismic hazard of roller compacted concrete dam site in Gilgit-Baltistan of northern 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

Earthquake Engineering and Engineering Vibration 2021年第3期20卷 621-630页

作者： Shahzada Khurram Perveiz Khalid Jahanzeb Qureshi Zia ud Din Institute of Geology University of the PunjabLahore 54590Pakistan Department of Space Science University of the PunjabLahore 54590Pakistan

The proposed site of the Diamer Bhasha Dam in northern Pakistan is situated in an active tectonic zone with intensive seismicity,which makes it necessary for seismic hazard analysis(SHA).Deterministic and probabilistic approaches have been used for SHA of the dam *** Main Mantle Thrust(MMT),Main Karakaram Thrust(MKT),Raikot-Sassi Fault(RKSF)and Kohistan Fault(KF)have been considered as major seismic sources,all of which can create maximum ground shaking with maximum potential earthquake(MPE).Deterministically estimated MPE for magnitudes of 7.8,7.7,7.6,and 7.1 can be produced from MMT,MKT,RKSF and KF,*** corresponding peak ground accelerations(PGA)of 0.07,0.11,0.13 and 0.05 g can also be generated from these earthquakes,*** deterministic analysis predicts a so-called floating earthquake as a MPE of magnitude=7.1 as close as 10 km away from the *** corresponding PGA was computed as 0.38 g for a maximum design earthquake at the project ***,the probabilistic analysis revealed that the PGA with 50%probability of exceedance in 100 years is 0.18 ***,this PGA value related to the operational basis earthquake(OBE)is suggested for the design of this project with shear wave velocity(V_(s30))equal to 760 m/s under dense soil and soft rock conditions.

关键词： seismic hazard analysis peak ground acceleration Gilgat-Biltastan Diamer Bhasha Dam

Ex-Situ Cultivation of Medicinal Plant Species in High Altitudes at Swat,Pakistan

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

云南植物研究 2005年第6期27卷 676-684页

作者： Hassan Sher David Melick Zaheer-ud-ud-Khan Department of Botany Government Jahanzeb College Swat NWFP Pakistan Kunming Institute of Botany Chinese Academy of Sciences Kunming 650204 China Department of Botany G. C and University of Lahore Pakistan

An ex-situ experiment was conducted to evaluate the growth performance of six medicinal species (Bergenia ciliata,Valeriana jatamansi,Dioscorea deltoidea,Paeonia emodi,Polygonum amplexicaule and Viola serpense) from upper Swat,*** were conducted at four different locations in the upper Swat valley at altitudes ranging from 1200 to 1900 *** objectives were:1) to determine the suitability of ex-situ cultivation of different medicinal species,and;2) to assess the economic geasibility of growing medicinal plants in the area.A highest mean survival of 80.7% across all locations was observed for Viola serpense,followed by 58.7% for Valeriana *** remaining four species exhibited very poor survival rates,although Polygonum amplexicaule,did show encouraging signs of growth and flowered,before experiencing high mortality rates late in the *** generally seemed to enhance the degree of sprouting for all species except Viola ***,the productive yield of *** was certainly not reduced,but rather slightly enhanced in the higher altitude ***,cultivation of only two of the investigated species,Valeriana jatamansi and Viola serpense,appeared successful and potentially economically viable under farmland conditions at upper Swat.

关键词：药用植物巴基斯坦种植技术宽叶甘松蓼属

Human Verification over Activity Analysis via Deep Data Mining

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 2023年第4期75卷 1391-1409页

作者： Kumar Abhishek Sheikh Badar ud din Tahir Senior Member IEEESeattle98103USA Department of Software Engineering Capital University of Science and Technology(CUST)Islamabad44000Pakistan

Human verification and activity analysis(HVAA)are primarily employed to observe,track,and monitor human motion patterns using redgreen-blue(RGB)images and *** human interaction using RGB images is one of the most complex machine learning tasks in recent *** models rely on various parameters,such as the detection rate,position,and direction of human body components in RGB *** paper presents robust human activity analysis for event recognition via the extraction of contextual intelligence-based *** use human interaction image sequences as input data,we first perform a few denoising ***,human-to-human analyses are employed to deliver more precise *** phase follows feature engineering techniques,including diverse feature ***,we used the graph mining method for feature optimization and AdaBoost for *** tested our proposed HVAA model on two benchmark *** testing of the proposed HVAA system exhibited a mean accuracy of 92.15%for the Sport Videos in theWild(SVW)*** second benchmark dataset,UT-interaction,had a mean accuracy of 92.83%.Therefore,these results demonstrated a better recognition rate and outperformed other novel techniques in body part tracking and event *** proposed HVAA system can be utilized in numerous real-world applications including,healthcare,surveillance,task monitoring,atomic actions,gesture and posture analysis.

关键词： AdaBoost classification deep features mining graph mining human detection human verification

PREPARATION OF THERMALLY EVAPORATED CdTe THIN FILMS

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics Letters 1990年第11期7卷 510-513页

作者： Shahzad Naseem Naseer-ud-Din Khadim Hussain Centre for Solid State Physics University of the PunjabQuaidCampusLahorePakistan

Thin films of cadmium telluride were prepared by evaporating cadmium telluride powder in a vacuum of less than 10^(-4) *** substrate temperature was varied systematically from room temperature to 300℃.The results of optical and structural characterizations have revealed that the films posses a high value of absorption coefficient with a bandgap value m the range 1.475-1.769eV,and that the films are of cubic structure with a preferred orientation along(111)*** probe measurements have shown that resistivity of these films is affected by the change in substrate temperature,with the lowest value(12.6 Ω·cm)being at 200℃.

关键词： films value cadmium

Energy-Efficient Scheduling Based on Task Migration Policy Using DPM for Homogeneous MPSoCs

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 965-981页

作者： Hamayun Khan Irfan ud din Arshad Ali Sami Alshmrany Department of Electrical Engineering Faculty of Engineering&Technology Superior University Lahore54000Pakistan Department of Computer Science Faculty of Computer Science&IT Superior University Lahore54000Pakistan Faculty of Computer and Information Systems Islamic University of MadinahAl Madinah Al Munawarah42351Saudi Arabia

Increasing the life span and efficiency of Multiprocessor System on Chip(MPSoC)by reducing power and energy utilization has become a critical chip design challenge for multiprocessor *** the advancement of technology,the performance management of central processing unit(CPU)is *** densities and thermal effects are quickly increasing in multi-core embedded technologies due to shrinking of chip *** energy consumption reaches a threshold that creates a delay in complementary metal oxide semiconductor(CMOS)circuits and reduces the speed by 10%–15%because excessive on-chip temperature shortens the chip’s life *** this paper,we address the scheduling&energy utilization problem by introducing and evaluating an optimal energy-aware earliest deadline first scheduling(EA-EDF)based technique formultiprocessor environments with task migration that enhances the performance and efficiency in multiprocessor systemon-chip while lowering energy and power *** selection of core andmigration of tasks prevents the system from reaching itsmaximumenergy utilization while effectively using the dynamic power management(DPM)*** in the execution of tasks the temperature and utilization factor(u_(i))on-chip increases that dissipate more *** proposed approach migrates such tasks to the core that produces less heat and consumes less power by distributing the load on other cores to lower the temperature and optimizes the duration of idle and sleep times across multiple *** performance of the EA-EDF algorithm was evaluated by an extensive set of experiments,where excellent results were reported when compared to other current techniques,the efficacy of the proposed methodology reduces the power and energy consumption by 4.3%–4.7%on a utilization of 6%,36%&46%at 520&624 MHz operating frequency when particularly in comparison to other energy-aware methods for *** are running and accurately scheduled to make an energy-efficient

关键词： Dynamic power management dynamic voltage&frequency scaling dynamic thermal management multiprocessor system on chip complementary metal oxide semiconductor reliability

Applicability of deep neural networks for lithofacies classification from conventional well logs: An integrated approach

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Petroleum Research 2024年第3期9卷 393-408页

作者： Saud Qadir Khan Farzain ud Din Kirmani Mari Petroleum Company Limited IslamabadPakistan Department of Petroleum and Gas Enginering NFC.Institute of Engineering&Technology MultanPakistan

Parametric understanding for specifying formation characteristics can be perceived through conven-tional ***,attributes of reservoir lithology are practiced for hydrocarbon *** logging is conventional approach which is applicable to predict lithology efficiently as compared to geophysical modeling and petrophysical analysis due to cost effectiveness and suitable interpretation ***,manual interpretation of lithology identification through well logging data requires domain expertise with an extended length of time for ***,in this study,Deep Neural Network(DNN)has been deployed to automate the lithology identification process from well logging data which would provide support by increasing time-effective for monitoring *** model has been developed for predicting formation lithology leading to the optimization of the model through the thorough evaluation of the best parameters and hyperparameters including the number of neurons,number of layers,optimizer,learning rate,dropout values,and activation *** of the model is examined by utilizing different evaluation metrics through the division of the dataset into the subdomains of training,validation and ***,an attempt is contributed to remove interception for formation lithology prediction while addressing the imbalanced nature of the associated dataset as well in the training process using class *** is assessed that accuracy is not a true and only reliable metric to evaluate the lithology classification *** model with class weight recognizes all the classes but has low accuracy as well as a low F1-score while LSTM based model has high accuracyas well as a high F1-score.

关键词： Lithology identification Deep learning LSTM Imbalanced dataset Conventional well logs

Molecular Dynamics Simulation of Strontium Titanate

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics Letters 2010年第2期27卷 217-219页

作者： SEETAWAN Tosawat WONG-ud-DEE Gjindara THANACHAYANONT Chanchana AMORNKITBUMRUNG Vittaya Thermoelectrics Research Center and Department of Physics Faculty of Science and Technology Sakon Nakhon Rajabhat University 680 Nithayo Rd. Sakon Nakhon 47000 Thailand National Metal and Materials Technology Center 114 Thailand Science Park Paholyothin Rd. Klong 1 Klong Luang Pathumthani 12120 Thailand Integrated Nanotechnology Research Center and Department of Physics Faculty of Science Khon Kaen University 123 Mitrapab Rd. Khon Kaen 40002 Thailand

The molecular dynamics method is used to simulate the thermophysical properties of SrTiO3 thermoelectric material in the temperature range 300-2200 K. The Morse-type potential functions added to the Busing-Ida type potential for interatomic interaction are used in the simulation. The interatomic potential parameters are determined by fitting to the experimental data of lattice parameters with temperature and the data reported in literature. The linear thermal expansion coefficient, heat capacity and lattice contributions to the thermal conductivity are analyzed. The results agree with the data reported in the literature.

关键词： Condensed matter: electrical magnetic and optical Semiconductors Condensed matter: structural mechanical & thermal

Output Linearization of Single-Input Single-Output Fuzzy System to Improve Accuracy and Performance

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5期75卷 2413-2427页

作者： Salah-ud-din Khokhar QinKe Peng Muhammad Yasir Noor Department of Automation Science and Technology(System Engineering Institute) School of Electronics and Information EngineeringXi’an Jiaotong UniversityXi’anShaanxi710049China Department of Computer Science G.C.UniversityLahore54000PunjabPakistan Department of Physics(Electronics) G.C.UniversityLahore54000PunjabPakistan

For fuzzy systems to be implemented effectively,the fuzzy membership function(MF)is essential.A fuzzy system(FS)that implements precise input and output MFs is presented to enhance the performance and accuracy of single-input single-output(SISO)FSs and introduce the most applicable input and output MFs protocol to linearize the fuzzy system’s *** a variety of non-linear techniques,a SISO FS is *** results of FS experiments conducted in comparable conditions are then *** simulated results and the results of the experimental setup agree fairly *** findings of the suggested model demonstrate that the relative error is abated to a sufficient range(≤±10%)and that the mean absolute percentage error(MPAE)is reduced by around 66.2%.The proposed strategy to reduceMAPE using an FS improves the system’s performance and control *** using the best input and output MFs protocol,the energy and financial efficiency of every SISO FS can be improved with very little tuning of *** proposed fuzzy system performed far better than other modern days approaches available in the literature.

关键词： Mean absolute percentage error membership functions relative error fuzzy system