检索结果-南通市图书馆

Sentiment Analysis of Roman Urdu on E-Commerce Reviews Using Machine Learning

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 Modeling in Engineering & Sciences 2022年第6期131卷 1263-1287页

作者： Bilal Chandio Asadullah Shaikh Maheen Bakhtyar Mesfer Alrizq Junaid Baber adel Sulaiman adel Rajab Waheed Noor Department of Computer Science and Information Technology University of BalochistanQuetta87300Pakistan College of Computer Science and Information Systems Najran UniversityNajran61441Saudi Arabia Department of Information Technology University of BalochistanQuetta87300Pakistan

Sentiment analysis task has widely been studied for various languages such as English and ***,Roman Urdu sentiment analysis yet requires more attention from peer-researchers due to the lack of Off-the-Shelf Natural Language Processing(NLP)*** primary objective of this study is to investigate the diverse machine learning methods for the sentiment analysis of Roman Urdu data which is very informal in nature and needs to be lexically *** mitigate this challenge,we propose a fine-tuned Support Vector Machine(SVM)powered by Roman Urdu *** our proposed scheme,the corpus data is initially cleaned to remove the anomalies from the *** initial pre-processing,each user review is being *** input text is transformed into a feature vector using the bag-of-word ***,the SVM is used to classify and detect user *** proposed scheme is based on a dictionary based Roman Urdu *** creation of the Roman Urdu stemmer is aimed at standardizing the text so as to minimize the level of *** efficacy of our proposed model is also empirically evaluated with diverse experimental configurations,so as to fine-tune the hyper-parameters and achieve superior ***,a series of experiments are conducted on diverse machine learning and deep learning models to compare the performance with our proposed *** also introduced the largest dataset on Roman Urdu,i.e.,Roman Urdu e-commerce dataset(RUECD),which contains 26K+user reviews annotated by the group of *** RUECD is challenging and the largest dataset available of Roman *** experiments show that the newly generated dataset is quite challenging and requires more attention from the peer researchers for Roman Urdu sentiment analysis.

关键词： Sentiment analysis Roman Urdu machine learning SVM

ON THE STABILITY OF A FUNCTIONALLY GRADED RECTANGULAR MICRO-PLATE SUBJECTED TO HYDROSTATIC AND NONLINEAR ELECTROSTATIC PRESSURES

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mechanica Solida Sinica 2013年第2期26卷 205-220页

作者： adel Nabian Ghader Rezazadeh Morteza Almassi Ali-Mohammad Borgheei Department of Agricultural Machinery Engineering Science and Research BranchIslamic Azad UniversityTehranIran Department of Mechanical Engineering Urmia UniversityUrmiaIran

This article studies the stability of a functionally graded clamped-clamped micro- plate subjected to hydrostatic and electrostatic pressures. Equilibrium positions of the micro-plate are determined and shown in the state control space. To study the stability of the equilibrium positions, the motion trajectories are given for different initial conditions in the phase plane. Effects of the electrostatic and hydrostatic pressure changes on the deflection and stability of the micro-plate for some sample value of k are studied and values of the applied voltage and hydrostatic pressure leading system to unstable conditions by undergoing a saddle node and homoclinic bifurcations are determined.

关键词： MEMS FGM stability micro-plate electrostatic hydrostatic pressure

Email Filtering Using Hybrid Feature Selection Model

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

Computer Modeling in Engineering & Sciences 2022年第8期132卷 435-450页

作者： adel Hamdan Mohammad Sami Smadi Tariq Alwada’n Computer Science Department The World Islamic Sciences and Education UniversityAmmanJordan Information System and Networks Department The World Islamic Sciences and Education UniversityAmmanJordan Network and Cybersecurity Department Teesside UniversityMiddlesbroughUK

Undoubtedly,spam is a serious problem,and the number of spam emails is increased ***,the massive number of spam emails prompts the need for spam detection *** methods and algorithms are used for spam ***,some emergent spam detection techniques use machine learning methods and feature *** methods and algorithms have been introduced for spam detecting and *** research proposes two models for spam detection and feature *** first model is evaluated with the email spam classification dataset,which is based on reducing the number of keywords to its *** results of this model are promising and highly *** second proposed model is based on creating features for spam detection as a first ***,the number of features is reduced using three well-known metaheuristic algorithms at the second *** algorithms used in the second model are Artificial Bee Colony(ABC),Ant Colony Optimization(ACO),and Particle Swarm Optimization(PSO),and these three algorithms are adapted to fit the proposed ***,the authors give it the names AABC,AACO,and APSO,*** dataset used for the evaluation of this model is ***,well-known criteria are used for the evaluation purposes of this model,such as true positive,false positive,false negative,precision,recall,and *** outcomes of the second proposed model are highly significant compared to the first one.

关键词： Feature selection artificial bee colony ant colony optimization particle swarm optimization spam detection emails filtering

Nucleotide Sequence Assessment of Four ORFs of Citrus Tristeza Virus: Evidence of Recombination

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Phyton-International Journal of Experimental Botany 2023年第3期92卷 691-705页

作者： adel A.Rezk Hala A.Amin Department of Agricultural Biotechnology College of Agricultural and Food ScienceKing Faisal UniversityAl-Ahsa31982Saudi Arabia Virus and Phytoplasma Research Department Plant Pathology Research InstituteAgricultural Research Center(ARC)Giza12619Egypt

Citrus Tristeza Virus(CTV),usually occurs in nature as a mixture of *** naturally infected citrus(Citrus sinensis)trees grafted on sour orange rootstock were collected from three citrus growing governorates in Egypt(Sharqia,Qalyubia and Garbia).In this study,RT-PCR,Single-Strand Conformation Polymorphism(SSCP)and nucleotide sequence analysis were used for four independent CTV genomic regions(p65,p18,p20,and p23)to detect and assess the sequence and genetic variabilities among CTV Egyptian *** products(650 bp)for the CTV p23 gene obtained from the selected isolates were used for the SSCP analysis and DNA *** patterns of p23 gene for individual isolates yielded different complex haplotype *** sequence analysis of p23 region amplified from six isolates under study revealed that p23 shared high nucleotide identity 98.7%with T36 isolate from USA,*** analysis of p23 gene indicated a close evolutionary relationship between all examined isolates and Qaha isolate(T36 isolate group),suggesting that they may have originated from closely related *** sequence analysis of the three genes located on CTV 3′-coterminal overhang,p18,p20 and p65,amplified from isolate A3,Sharqia governorate,revealed that the p18,p65,and p20 genes were related to the T3-KB isolate from South Africa with 99%–100%sequence *** relationship analysis for p65,p18 and p20 ORFs clustered the current A3 isolate with T3 genotype *** recombination analysis identified three of six isolates from Sharqia,and Garbia as potential recombinant for p23 *** isolates T36 and T3 were identified as major donors for recombination events in isolate *** results concluded that p23 ORF likely to be as a hotspot region for recombination and originated through recombination *** current study indicated that recombination is an important factor for the origin of CTV strains in Egypt.

关键词： Citrus Tristeza Virus hotspot region phylogenetic relationship analysis sequence comparison SSCP analysis

Review of application of artificial intelligence techniques in petroleum operations

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 2023年第2期8卷 167-182页

作者： Saeed Bahaloo Masoud Mehrizadeh adel Najafi-Marghmaleki Department of Petroleum Engineering Amirkabir University of TechnologyTehranIran Department of Petroleum Engineering School of Science and EngineeringKhazar UniversityBakuAzerbaijan Department of Petroleum Engineering Ahwaz Faculty of PetroleumPetroleum University of TechnologyAhwazIran

In the last few years,the use of artificial intelligence(AI)and machine learning(ML)techniques have received considerable notice as trending technologies in the petroleum *** utilization of new tools and modern technologies creates huge volumes of structured and un-structured *** and processing of these information at faster pace for the performance assessment and forecasting for field development and management is continuously growing as an important field of *** difficulties which were faced in predicting the operative features by utilizing the conventional methods have directed the academia and industry toward investigations focusing on the applications of ML and data driven approaches in exploration and production operations to achieve more accurate predictions which improves decision-making *** research provides a review to examine the use cases and application of AI and ML techniques in petroleum industry for optimization of the upstream processes such as reservoir studies,drilling and production *** challenges related to routine approaches for prognosis of operative parameters have been evaluated and the use cases of performance optimizations through employing data-driven approaches resulted in enhancement of decision-making workflows have been ***,possible scenarios of the way that artificial intelligence will develop and influence the oil and gas industry and how it may change it in the future was discussed.

关键词： Artificial intelligence Machine learning Upstream operation Oil and gas industry Petroleum systems Decision-making

Production and evaluation of novel functional extruded corn snacks fortified with ginger,bay leaves and turmeric powder

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Food Production, Processing and Nutrition 2022年第1期4卷 41-57页

作者： Sara adel Amer Ayat Ebrahim Rizk Special Food and Nutrition Research Department Food Technology Research Institute.Agricultural Research Center9 Gamaa StreetGizaEgypt

Extruded corn snacks are accepted by all human ages especially children, but they have low functional value. Therefore, corn extruded snacks contain rich nutraceuticals dried herbs including Laurus nobilis (T1), Curcuma longa (T2), Zingiber officinale Roscoe (T3), and the mixture of these herbs (T4) were manufactured and analyzed. The results declared that all the herbal extruded corn snacks had significantly higher ash, fibers, minerals, and vitamins A and B6. For minerals, the highest percent of increase compared to control was achieved by Fe, K, Ca, Zn content in order, being the highest in T4. The contents of Vitamin A and B6 were ranged from 283 to 445 IU/100 g and from 0.01 to 0.08 mg/100 g for the herbal extrudates, respectively. The increased percent in herbal corn snacks relative to control ranged from 743 to 452%, 188 to 17.6%, and from 313 to 99% for total phenolics, flavonoids, and antioxidant activity. Besides, the highest number of phenolic compounds was recorded in T4. Despite the fact that approximately all herbal extruded products had good texture and color characteristics, the best formulation was T2 and T4 corn snacks. Furthermore, the extruded products were microbiologically safe for up to 9 months. The formulation of herbal-corn snacks could fulfill consumers’ requirement for ready-to-eat-healthy foods with acceptable sensory attributes and also economically suitable for the food industry.

关键词： Ginger Laurel Turmeric Extrusion Corn snacks functional foods

Effect of axial load and transverse reinforcements on the seismic performance of reinforced concrete columns

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

作者： azar Nafisi

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2019年第4期13卷 831-851页

作者： Mounir Ait BELKACEM Hakim BECHTOULA Nouredine BOURAHLA adel Ait BELKACEM Department of Earthquake Engineering National Earthquake Engineering Research Centre (C.G.S) Algiers 16005 Algeria Department of Civil Engineering LGGC Laboratory Blida 1-University Blida 09000 Algeria Department of Civil Engineering Science & Technology University (USTHB) Algiers 16111 Algeria

The aim of this research is to assess the seismic performance of reinforced concrete columns under different axial load and transverse reinforcement ratios. These two parameters are very important as for the ductility, strength, stiffness, and energy dissipation capacity for a given reinforced concrete column. Effects of variable axial load ratio and transverse reinforcement ratio on the seismic performance of reinforced concrete columns are thoroughly analyzed. The finite element computer program Seismo-Structure was used to perform the analysis of series of reinforced concrete columns tested by the second author and other researchers. In order to reflect the reality and grasp the actual behavior of the specimens, special attention was paid to select the models for concrete, confined concrete, and steel components. Good agreements were obtained between the experimental and the analytical results either for the lateral force-drift relationships or for the damage progress prediction at different stages of the loading.

关键词： reinforced concrete columns axial load transverse reinforcement ductility

Hybridization of Fuzzy and Hard Semi-Supervised Clustering Algorithms Tuned with Ant Lion Optimizer Applied to Higgs Boson Search

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 Modeling in Engineering & Sciences 2020年第11期125卷 459-494页

作者： Soukaina Mjahed Khadija Bouzaachane Ahmad Taher azar Salah El Hadaj Said Raghay Faculty of Sciences and Technology Department of Applied Mathematics and Computer SciencesCadi Ayyad UniversityMarrakech40000Morocco Robotics and Internet-of-Things Lab(RIOTU) Prince Sultan UniversityRiyadh12435Saudi Arabia Faculty of Computers and Artificial Intelligence Benha UniversityBenha13511Egypt

This paper focuses on the unsupervised detection of the Higgs boson particle using the most informative features and variables which characterize the“Higgs machine learning challenge 2014”data *** unsupervised detection goes in this paper analysis through 4 steps:(1)selection of the most informative features from the considered data;(2)definition of the number of clusters based on the elbow *** experimental results showed that the optimal number of clusters that group the considered data in an unsupervised manner corresponds to 2 clusters;(3)proposition of a new approach for hybridization of both hard and fuzzy clustering tuned with Ant Lion Optimization(ALO);(4)comparison with some existing metaheuristic optimizations such as Genetic Algorithm(GA)and Particle Swarm Optimization(PSO).By employing a multi-angle analysis based on the cluster validation indices,the confusion matrix,the efficiencies and purities rates,the average cost variation,the computational time and the Sammon mapping visualization,the results highlight the effectiveness of the improved Gustafson-Kessel algorithm optimized withALO(ALOGK)to validate the proposed *** if the paper gives a complete clustering analysis,its novel contribution concerns only the Steps(1)and(3)considered *** first contribution lies in the method used for Step(1)to select the most informative features and *** used the t-Statistic technique to rank ***,a feature mapping is applied using Self-Organizing Map(SOM)to identify the level of correlation between ***,Particle Swarm Optimization(PSO),a metaheuristic optimization technique,is used to reduce the data set *** second contribution of thiswork concern the third step,where each one of the clustering algorithms as K-means(KM),Global K-means(GlobalKM),Partitioning AroundMedoids(PAM),Fuzzy C-means(FCM),Gustafson-Kessel(GK)and Gath-Geva(GG)is optimized and tuned with ALO.

关键词： Ant lion optimization binary clustering clustering algorithms Higgs boson feature extraction dimensionality reduction elbow criterion genetic algorithm particle swarm optimization