检索结果-南通市图书馆

Comprehensive Review and Analysis on Facial Emotion Recognition:Performance Insights into Deep and Traditional Learning with Current Updates and Challenges

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 41-72页

作者： Amjad Rehman Muhammad Mujahid Alex Elyassih Bayan AlGhofaily Saeed Ali omer Bahaj Artificial Intelligence&Data Analytics Lab College of Computer&Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia MIS Department College of Business Administration Prince Sattam Bin Abdulaziz UniversityAlKharj11942Saudi Arabia

In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry *** demonstrations and applications in several fields,including computer games,smart homes,expression analysis,gesture recognition,surveillance films,depression therapy,patientmonitoring,anxiety,and others,have brought attention to its significant academic and commercial *** study emphasizes research that has only employed facial images for face expression recognition(FER),because facial expressions are a basic way that people communicate meaning to each *** immense achievement of deep learning has resulted in a growing use of its much architecture to enhance *** review is on machine learning,deep learning,and hybrid methods’use of preprocessing,augmentation techniques,and feature extraction for temporal properties of successive frames of *** following section gives a brief summary of assessment criteria that are accessible to the public and then compares them with benchmark results the most trustworthy way to assess FER-related research topics *** this review,a brief synopsis of the subject matter may be beneficial for novices in the field of FER as well as seasoned scholars seeking fruitful avenues for further *** information conveys fundamental knowledge and provides a comprehensive understanding of the most recent state-of-the-art research.

关键词： Face emotion recognition deep learning hybrid learning CK+ facial images machine learning technological development

Determination of ^(210)Po and ^(210)Pb depositions in lichen and soil samples collected from K?prüba??-Manisa,Turkey

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2018年第6期29卷 92-100页

作者： Sermin Cam kaynar Umit H. kaynar Umran Hicsonmez omer S. Sevinc Department of Physics Faculty of Sciences and Arts Manisa Celal Bayar University 45140 Manisa Turkey Science Education Faculty of Education Manisa Celal Bayar University 45900 Manisa Turkey Department of Chemistry Faculty of Sciences and ArtsManisa Celal Bayar University 45140 Manisa Turkey Primary School Science Teaching Duzce University81620 Manisa Turkey

üIn this study, we aimed to determine the accumulations of ^(210) Po and ^(210) Pb in soil and lichen samples in K? prü bas??. The K? prü bas?? district is home to the largest uranium deposits in Turkey. To date, there has been no study recorded in the literature related to ^(210) Po and ^(210) Pb depositions in lichens in K? prü bas??. Six different lichen species(Cladonia convoluta, Parmelina tiliacea, Physcia stellaris, Pleurosticta acetabulum, Xanthoparmelia conspersa, and Xanthoria parietina) as well as soil samples were collected from seven sampling locations around K? prü bas??. Lichens were used as biomonitors for ^(210) Po and ^(210) Pb deposition. The ^(210) Po and ^(210) Pb activity concentrations were measured in all the samples by alpha spectrometry. The activity concentrations in the lichen samples ranged from 64 to 577 Bq kg^(-1) with an average of 266 Bq kg^(-1) for ^(210) Po and from 78 to 565 Bq kg^(-1) with an average of 333 Bq kg^(-1) for ^(210) Pb. The activity ratios of ^(210) Po/ ^(210) Pb ranged from 0.80 to 1.99. In the lichen species,the mean ^(210) Po activity values varied from 154 Bq kg^(-1) in Pleurosticta acetabulum to 390 Bq kg^(-1) in Xanthoparmelia conspersa. The range of the mean ^(210) Pb activity was between 153 Bq kg^(-1) in Cladonia convoluta and 378 Bq kg^(-1) in Parmelina tiliacea. In the soil samples, ^(210) Po and ^(210) Pb activity concentrations were ranged from14 to 1268 Bq kg^(-1) and from 19 to 1113 Bq kg^(-1),respectively. While the values of ^(210) Po and ^(210) Pb measured in the lichen samples are comparable with those of the literature, the results of ^(210) Po and ^(210) Pb in the soil taken from the uranium mine are higher than the results of the literature studies.

关键词：土壤样品地衣种土耳其收集样品测量 alpha 平均数 Po

Using Metaheuristic OFA Algorithm for Service Placement in Fog Computing

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12期77卷 2881-2897页

作者： Riza Altunay omer faruk Bay Department of Information Systems Gazi UniversityAnkara06680Turkey Department of Computer Technologies Ondokuz Mayis UniversitySamsun55100Turkey Department of Electrical-Electronics Engineering Gazi UniversityAnkara06560Turkey

The use of fog computing in the Internet of Things(IoT)has emerged as a crucial solution,bringing cloud services closer to end users to process large amounts of data generated within the *** its advantages,the increasing task demands from IoT objects often overload fog devices with limited resources,resulting in system delays,high network usage,and increased energy *** of the major challenges in fog computing for IoT applications is the efficient deployment of services between fog *** address this challenge,we propose a novel Optimal Foraging Algorithm(OFA)for task placement on appropriate fog devices,taking into account the limited resources of each fog *** OFA algorithm optimizes task sharing between fog devices by evaluating incoming task requests based on their types and allocating the services to the most suitable fog *** our study,we compare the performance of the OFA algorithm with two other popular algorithms:Genetic Algorithm(GA)and Randomized Search Algorithm(RA).Through extensive simulation experiments,our findings demonstrate significant improvements achieved by the OFA ***,it leads to up to 39.06%reduction in energy consumption for the Elektroensefalografi(EEG)application,up to 25.86%decrease in CPU utilization for the Intelligent surveillance through distributed camera networks(DCNS)application,up to 57.94%reduction in network utilization,and up to 23.83%improvement in runtime,outperforming other *** a result,the proposed OFA algorithm enhances the system’s efficiency by effectively allocating incoming task requests to the appropriate fog devices,mitigating the challenges posed by resource limitations and contributing to a more optimized IoT ecosystem.

关键词： Internet of Things cloud computing fog computing

Optimization of drill bit replacement time in open-cast coal mines

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 Coal Science & Technology 2019年第3期6卷 399-407页

作者： omer faruk Ugurlu Mustafa Kumral Department of Mining and Materials Engineering McGill University 3450 University Street Montreal QC H3A 0E8 Canada

To gain a competitive edge within the international and compet让ive setting of coal markets, coal producers must find new ways of reducing costs. Increasing bench drilling efficiency and performance in open-cast coal mines has the potential to generate savings. Specifically, monitoring, analyzing, and optimizing the drilling operation can reduce drilling costs. For example, determining the optimal drill bit replacement time will help to achieve the desirable penetration rate. This paper presents a life data analysis of drill bits to fit a statistical distribution using failure records. These results are then used to formulate a cost minimization problem to estimate the drill bit replacement time using the evolutionary algorithm. The effect of cost on the uncertainty associated with replacement time is assessed through Monte-Carlo simulation. The relationship between the total expected replacement cost and replacement time is also presented. A case study shows that the proposed approach can be used to assist with designing a drill bit replacement schedule and minimize costs in open-cast coal mines.

关键词： Cost minimization Drilling operation Optimum replacement time Evolutionary algorithm Sensitivity analysis Monte Carlo simulation

Performance investigation of LAMBDA and bootstrapping methods for PPP narrow-lane ambiguity resolution

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Geo-Spatial Information Science 2021年第4期24卷 604-614页

作者： omer faruk Atiz Sermet Ogutcu Salih Alcay Pan Li Ilkay Bugdayci Department of Geomatics Engineering Necmettin Erbakan UniversityKonyaTurkey Department of Geodesy and Remote Sensing German Research Centre for GeosciencesPotsdamGermany

Precise point positioning with ambiguity resolution(PPP-AR)is a powerful tool for geodetic and time-constrained applications that require high *** performance of PPP-AR highly depends on the reliability of the correct integer carrier-phase ambiguity *** this study,the performance of narrow-lane ambiguity resolution of PPP using the Least-squares AMBiguity Decorrelation(LAMBDA)and bootstrapping methods is extensively investigated using real data from 55 IGS stations over one-month in *** PPP with 24-,12-,8-,4-,2-,1-and½-h sessions using two different cutoff angles(7°and 30°)was conducted with three PPP modes:***-float and two kinds of ambiguity-fixed PPP using the LAMBDA and bootstrapping methods for narrow-lane AR,*** results show that the LAMBDA method can produce more reliable results for 2 hour and shorter observation sessions com-pared with the bootstrapping method using a 7°cutoff *** a 30°cutoff angle,the LAMBDA method outperforms the bootstrapping method for observation sessions of 4 h and *** long observation times,the bootstrapping method produced much more accurate coordinates compared with the LAMBDA method without considering the wrong fixes *** results also show that occurrences of fixing the wrong integer ambiguities using the bootstrapping method are higher than that of the LAMBDA method.

关键词： Ambiguity resolution narrow-lane Precise point positioning(PPP) LAMBDA bootstrapping

Ensemble and optimized hybrid algorithms through Runge Kutta optimizer for sewer sediment transport modeling using a data pre-processing 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

International Journal of Sediment Research 2023年第6期38卷 847-858页

作者： Enes Gul Mir Jafar Sadegh Safari omer faruk Dursun Gokmen Tayfur Department of Civil Engineering Inonu University Department of Civil Engineering Yasar University Department of Civil Engineering Izmir Institute of Technology

Uncontrolled sediment deposition in drainage and sewer systems raises unexpected maintenance *** this end,implementation of an accurate model relying on effective parameters involved is a reliable *** this study,three machine learning techniques,namely extreme learning machine(ELM),multilayer perceptron neural network(MLPNN),and M5P model tree(M5PMT);and three optimization approaches of Runge Kutta(RUN),genetic algorithm(GA),and particle swarm optimization(PSO) are applied for *** optimization and ensemble hybridization approaches are applied in the modeling *** the case of hybrid optimized models,the ELM and MLPNN models are hybridized with RUN,GA,and PSO algorithms to develop six hybrid models of ELM-RUN,ELM-GA,ELMPSO,MLPNN-RUN,MLPNN-GA,and *** hybrid models are developed through coupling the ELM and MLPNN models with the M5PMT *** data pre-processing approach is applied to find the best randomness characteristic of the utilized *** illustrate that the RUNbased hybrid models outperform the GA-and PSO-based *** the MLPNN-RUN and MLPNN-M5PMT hybrid models generate better results than their alternatives,MLPNN-M5PMT slightly outperforms MLPNN-RUN model with a coefficient of determination of 0.84 and a root mean square error of *** current study shows the superiority of the ensemble-based approach to the optimization *** investigation is needed by considering alternative optimization techniques to enhance sediment transport modeling.

关键词： Ensemble learning Hybrid model Machine learning Open channels Sediment transport Sewer pipes

Predicting cash holdings using supervised machine learning algorithms

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Financial Innovation 2022年第1期8卷 1459-1477页

作者： ŞirinÖzlem omer faruk Tan Department of Industrial Engineering Faculty of EngineeringMEF UniversityIstanbulTurkey Department of Accounting and Finance Faculty of Business AdministrationMarmara UniversityIstanbulTurkey

This study predicts the cash holdings policy of Turkish firms,given the 20 selected features with machine learning algorithm methods.211 listed firms in the Borsa Istanbul are analyzed over the period between 2006 and *** linear regression(MLR),k-nearest neighbors(KNN),support vector regression(SVR),decision trees(DT),extreme gradient boosting algorithm(XGBoost)and multi-layer neural networks(MLNN)are used for *** reveal that MLR,KNN,and SVR provide high root mean square error(RMSE)and low R2 ***,more complex algorithms,such as DT and especially XGBoost,derive higher accuracy with a 0.73 R 2 ***,using advanced machine learning algorithms,we may predict cash holdings considerably.

关键词： boosting policy networks

Cellulolytic characterization of the rumen-isolated Acinetobacter pittii ROBY and design of a potential controlled-release drug delivery system

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Engineering Microbiology 2024年第3期4卷 22-28页

作者： Ruken Sariboga omer faruk Sarioglu Istanbul Medeniyet University Department of Molecular Biology and GeneticsIstanbul 34730Turkey Istanbul Medeniyet University Science and Advanced Technologies Research Center(BILTAM)Istanbul 34730Turkey

A novel cellulolytic bacterial strain,ROBY,was isolated from a bovine rumen sample using the enrichment cul-ture *** isolate was found to be Acinetobacter pittii,with>99%similarity according to 16S rRNA gene sequence *** potential use of this strain in combination with doxorubicin(Dox)-integrated cellulose nanoparticles(Dox-CNPs)was evaluated as a proof-of-concept study for the further development of this approach as a novel controlled-release drug delivery *** isolate can utilize CNPs as the sole carbon source for growth and degrade both Dox-CNPs and empty CNPs with high *** cellulases isolated from bacteria may also be used to trigger Dox *** results also demonstrated that the release of Dox into the environment due to nanoparticle degradation in the samples incubated with Dox-CNPs significantly affected bac-terial cell viability(∼75%decrease),proving the release of Dox due to bacterial cellulase activity and suggesting the great potential of this approach for further development.

关键词： Acinetobacter pittii Microcrystalline cellulose Cellulose nanoparticle Controlled-release drug delivery system Doxorubicin

An integrated spatial planning of the mountainous landscapes for ski sports in a case area at the eastern Türkiye

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Mountain Science 2024年第3期21卷 754-767页

作者： SATIR Onur TOSUN Busra COSKUN OZYOL Funda OZDEMIR omer faruk BERBEROGLU Suha Dept.of Landscape Architecture Van Yuzuncu Yil UniversityVan 65090Türkiye School of Physical Education&Sports Van Yuzuncu Yil UniversityVan 65090Türkiye Van Yuzuncu Yil University Dept.of Architecture&Urban Planning Van 65090Türkiye Dept.of Remote Sensing&GIS Cukurova UniversityAdana 01330Türkiye

Mountainous regions have disadvantages in economic development because of harsh physical and climatic ***,winter tourism activities are one of the key components for supporting economic development in the *** a ski resort area supports direct and indirect employment in a region,and it stops immigration from mountainous regions to other *** research aimed to assess the potential ski areas using a multi criteria evaluation technique in the Van region which is located in the eastern part of Tü*** this context,snow cover duration,sun effect,slope,slope length,elevation,population density,distance from main roads and lake visibility were used as input factors in the decision making *** factor was standardized using a fuzzy technique based on existing well-known ski centers in Tü*** weight of inputs was defined by applying a survey to the professional *** most important factors were detected as transportation opportunities and snow covers whereas,the least important factors were elevation and population ***,lake visibility was very important to make a difference from other existing facilities in the ***,it was included as constraints and lake visible areas were extracted at the final stage of the *** ski areas were mapped in three levels as professional,intermediate and beginner *** of the suitable areas was selected as a sample projection and for the 3D simulation of the ski investment *** costs and benefits were *** was found that a ski tourism area investment can be amortized in 3 years in the region.

关键词： Winter sports and tourism Decision making 3D simulation and modelling Landscape planning GIS