检索结果-南通市图书馆

Combining Committee-Based Semi-Supervised Learning and Active 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

Journal of Computer Science & Technology 2010年第4期25卷 681-698页

作者： Mohamed farouk Abdel Hady Friedhelm Schwenker Institute of Neural Information Processing University of Ulm

Many data mining applications have a large amount of data but labeling data is usually difficult, expensive, or time consuming, as it requires human experts for annotation. Semi-supervised learning addresses this problem by using unlabeled data together with labeled data in the training process. Co-Training is a popular semi-supervised learning algorithm that has the assumptions that each example is represented by multiple sets of features （views） and these views are sufficient for learning and independent given the class. However, these assumptions axe strong and are not satisfied in many real-world domains. In this paper, a single-view variant of Co-Training, called Co-Training by Committee （CoBC） is proposed, in which an ensemble of diverse classifiers is used instead of redundant and independent views. We introduce a new labeling confidence measure for unlabeled examples based on estimating the local accuracy of the committee members on its neighborhood. Then we introduce two new learning algorithms, QBC-then-CoBC and QBC-with-CoBC, which combine the merits of committee-based semi-supervised learning and active learning. The random subspace method is applied on both C4.5 decision trees and 1-nearest neighbor classifiers to construct the diverse ensembles used for semi-supervised learning and active learning. Experiments show that these two combinations can outperform other non committee-based ones.

关键词： data mining classification active learning co-training semi-supervised learning ensemble learning randomsubspace method decision tree nearest neighbor classifier

New results for a Lasota-Wazewska model

在线全文

学校读者我要写书评

暂无评论

International Journal of Biomathematics 2019年第2期12卷 143-162页

作者： farouk Cherif Mohsen Miraoui MaPSFA LR11ES35ISSATUniversity of Sousse4002 SousseTunisia IPEIK University of Kairouan3100 KairouanTunisia LR11ES53Faculty of Sciences of Sfax University of SfaxTunisia

In nature there is no phenomenon that is purely periodic,and this gives the idea to consider the measure pseudo almost periodic *** this paper,by employing a suitable fixed point theorem,the proper ties of the measure pseudo almost periodic functions and differential inequality,we investigate the existence and uniqueness of the measure pseudo almost periodic solutions for some models of Lasota-Wazewska equation with measure pseudo almost periodic coefficients and mixed *** suppose that the linear part has almost periodic and the nonlinear part is assumed to be measure pseudo almost ***,the global attractivity and the exponential stability of the measure pseudo almost periodic solutions are also considered for the *** application,an illustrative numerical example is given to demonstrate the effectiveness of the obtained results.

关键词： Lasota Wazewska model measure pseudo almost periodic function fixed point theorem

The use of point load test for Dubai weak calcareous sandstones

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 Rock Mechanics and Geotechnical Engineering 2015年第4期7卷 452-457页

作者： Amr farouk Elhakim Department of Public Works Faculty of EngineeringCairo University

Intact rock is typically described according to its uniaxial compressive strength （UCS）. The UCS is needed in the design of geotechnical engineering problems including stability of rock slopes and design of shallow and deep foundations resting on and/or in rocks. Accordingly, a correct measure-ment/evaluation of the UCS is essential to a safe and economic design. Typically, the UCS is measured using the unconfined compression tests performed on cylindrical intact specimens with a minimum length to width ratio of 2. In several cases, especially for weak and very weak rocks, it is not possible to extract intact specimens with the needed minimum dimensions. Thus, alternative tests （e.g. point load test, Schmidt hammer） are used to measure rock strength. The UCS is computed based on the results of these tests through empirical correlations. The literature includes a plethora of these correlations that vary widely in estimating rock strength. Thus, it is paramount to validate these correlations to check their suitability for estimating rock strength for a specific location and geology. A review of the available correlations used to estimate the UCS from the point load test results is performed and summarized herein. Results of UCS, point load strength index and Young＇s modulus are gathered for calcareous sandstone specimens extracted from the Dubai area. A correlation for estimating the UCS from the point load strength index is proposed. Furthermore, the Young＇s modulus is correlated to the UCS.

关键词： Point load testUniaxial compressive strength (UCS)Rock characteristic elastic modulusDubai calcareous sandstoneCalcarenite

Multi-Attribute Selection Procedures Based on Regret and Rejoice for the Decision-Maker

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第2期70卷 2777-2795页

作者： Hanan Abdullah Mengash Manel farouk Ayadi Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia

Feelings influence human beings’decision-making;therefore,incorporation of feeling factors in decision-making is very *** and rejoice are very important emotional feelings that can have a great impact on decision-making if they are considered *** regret has received most of the attention in related research,rejoice has been less considered even though it can greatly influence people’s preferences in ***,systematically incorporating regret and rejoice in the multicriteria decision-making(MCDM)modeling frameworks for decision-making has received little research *** this paper,we introduce a new multiattribute selection procedure that incorporates both regret and rejoice to select the best *** utilize the positional advantage operator concept to develop regret and rejoice mathematical equations,and prove *** proposed MCDM procedure that incorporates these two emotional factors offers a decision-maker the flexibility to trade off some benefits in order to gain a state of psychological *** specifically,regret and rejoice are presentedmathematically to enable the decision-maker to determine the values of regret and rejoice,and then make the decision in which the rejoice value is higher than the regret *** test the performance of this new procedure,we apply it to three numerical examples proposed in previous *** results are matched with those obtained by other methods such as the regret model,VIKOR,PROMETHEE I,and PROMETHEE II,thereby proving the efficacy of the new procedure.

关键词： Multi-criteria decision-making positional advantage operator regret rejoice

Arithmetic Optimization with Deep Learning Enabled Anomaly Detection in Smart City

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 2022年第10期73卷 381-395页

作者： Mahmoud Ragab Maha farouk S.Sabir Information Technology Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Centre of Artificial Intelligence for Precision Medicines King Abdulaziz UniversityJeddah21589Saudi Arabia Mathematics Department Faculty of ScienceAl-Azhar UniversityNaser City11884CairoEgypt Information Systems Department Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia

In recent years,Smart City Infrastructures(SCI)have become familiar whereas intelligent models have been designed to improve the quality of living in smart ***,anomaly detection in SCI has become a hot research topic and is widely explored to enhance the safety of *** increasing popularity of video surveillance system and drastic increase in the amount of collected videos make the conventional physical investigation method to identify abnormal actions,a laborious *** this background,Deep Learning(DL)models can be used in the detection of anomalies found through video surveillance *** current research paper develops an Internet of Things Assisted Deep Learning Enabled Anomaly Detection Technique for Smart City Infrastructures,named(IoTAD-SCI)*** aim of the proposed IoTAD-SCI technique is to mainly identify the existence of anomalies in smart city ***,IoTAD-SCI technique involves Deep Consensus Network(DCN)model design to detect the anomalies in input video *** addition,Arithmetic Optimization Algorithm(AOA)is executed to tune the hyperparameters of the DCN ***,ID3 classifier is also utilized to classify the identified objects in different *** experimental analysis was conducted for the proposed IoTADSCI technique upon benchmark UCSD anomaly detection dataset and the results were inspected under different *** simulation results infer the superiority of the proposed IoTAD-SCI technique under different metrics.

关键词： Object detection anomaly detection smart city infrastructure deep learning parameter tuning

Stabilizing soft clay using geo-foam beads and cement bypass dust

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Underground Space 2020年第4期5卷 292-297页

作者： Essam farouk Badrawi Mahmoud Samir El-kady Structural Engineering Department Faculty of EngineeringZagazig UniversityEgypt Civil Engineering Department Jouf UniversitySaudi Arabia

Soft clays are usually classified according to their undrained shear strength,*** of Su less than 12.5 kPa are associated with very soft *** addition to their low shear strength,soft clays exhibit high compressibility upon ***,soft clays are considered to be problematic for foundation ***-foam is an industrial material that is characterized by a very low unit weight(20 kg/m^(3) on average)compared to that of the *** density of expanded polystyrene(EPS)ranges from 1.0%to 2.5%,which results in a compressive strength ranging between 70 kPa and 140 kPa and an elastic modulus ranging between 5 MPa and 12 *** geofoam blocks are used in a wide range of geotechnical applications as a lightweight fill *** main objective of this study was to investigate the geotechnical properties of soft clays containing geo-foam beads and cement bypass dust(CBPD).We also investigated the viability of preparing low-strength excavatable fill *** study the effect of(geofoam beads+CBPD)/soft clay on the fluid-state and hardened properties of new fill,we conducted experiments on two groups of mixtures(A&B).Each mixture contained different ratios of geo-foam beads and CBPD so that we could study the effect of the additive on the flow consistency,dry unit weight,unconfined compressive strength,and shear strength of the *** test results showed that the unconfined compressive strength of the studied mixtures without geo-foam ranged from 271.8 kPa to 1405.14 kPa at CBPD concentrations between 3.88%and 18.63%.The cohesion values for the group containing geo-foam ranged from 50 kPa to 20 kPa at geo-foam percentages between 0.32%and 1.35%.The friction angle of the group containing geo-foam ranged from 10 kPa to 22 kPa at CBPD percentages between 0.32%and 1.35%.Cement bypass dust can be successfully used to process self-compacting,self-leveling,excavatable and flowable fill material.

关键词： Geo-foam beads Cement bypass dust Flowable fill Shear strength

DYNAMICS OF NEW CLASS OF HOPFIELD NEURAL NETWORKS WITH TIME-VARYING AND DISTRIBUTED DELAYS

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 Mathematica Scientia 2016年第3期36卷 891-912页

作者： Adnene ARBI farouk CHERIF Chaouki AOUITI Abderrahmen TOUATI Department of Mathematics Facultd des Sciences de BizerteUniversity of CarthageJarzouna 7021BizerteTunisia Department of Computer Science ISSATSLaboratory of Math PhysicsUniversity of SousseSpecials Functions and Applications LR11ES35ecole suprieure des sciences et de technologieSousse 4002Tunisia

In this paper, we investigate the dynamics and the global exponential stability of a new class of Hopfield neural network with time-varying and distributed delays. In fact, the properties of norms and the contraction principle are adjusted to ensure the existence as well as the uniqueness of the pseudo almost periodic solution, which is also its derivative pseudo almost periodic. This results are without resorting to the theory of exponential dichotomy. Furthermore, by employing the suitable Lyapunov function, some delayindependent sufficient conditions are derived for exponential convergence. The main originality lies in the fact that spaces considered in this paper generalize the notion of periodicity and almost periodicity. Lastly, two examples are given to demonstrate the validity of the proposed theoretical results.

关键词： delayed functional differential equations neural networks pseudo-almost peri- odic solution global exponential stability time-varying and distributed delays fixed point theorem

A Nonlinear Optimal Control Approach for Bacterial Infections Under Antibiotics Resistance

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第6期37卷 2293-2317页

作者： RIGATOS Gerasimos ABBASZADEH Masoud SIANO Pierluigi AL-NUMAY Mohammed ZOUARI farouk Unit of Industrial Automation Industrial Systems Institute26504Rion PatrasGreece Dept.of ECS Engineering Rensselaer Polytechnic Institute12065TroyNYUSA Dept.of Management and Innovation Systems University of Salerno84084FiscianoItaly Dept.of Electrical Eng. King Saud UniversityRiyadh 11421Saudi Arabia Laboratoire d'Automatique ENIT Tunisie1002 Tunis

The overuse and misuse of antibiotics has become a major problem for public *** become resistant to antibiotics and because of this the anticipated therapeutic effect is never ***-hospital infections are often aggravated and large amounts of money are spent for treating complications in the patients'*** this paper a nonlinear optimal(H-infinity)control method is developed for the dynamic model of bacterial infections exhibiting resistance to ***,differential flatness properties are proven for the associated state-space ***,the state-space description undergoes approximate linearization with the use of first-order Taylor series expansion and through the computation of the associated Jacobian *** linearization process takes place at each sampling instance around a time-varying operating point which is defined by the present value of the system's state vector and by the last sampled value of the control inputs *** the approximately linearized model of the system a stabilizing H-infinity feedback controller is *** compute the controller's gains an algebraic Riccati equation has to be repetitively solved at each time-step of the control *** global stability properties of the control scheme are proven through Lyapunov *** proposed method achieves stabilization and remedy for the bacterial infection under moderate use of antibiotics.

关键词： Bacterial infection differential flatness properties global stability Jacobian matrices nonlinear H-infinity control resistance to antibiotics Riccati equation Taylor series expansion

New model for standpipe pressure prediction while drilling using Group Method of Data Handling

在线全文

学校读者我要写书评

暂无评论

Petroleum 2022年第2期8卷 210-218页

作者： Mohamed Riad Youcefi Ahmed Hadjadj farouk Said Boukredera Laboratory of Petroleum Equipment’s Reliability and Materials Faculty of Hydrocarbons and ChemistryUniversity M’hamed Bougara of BoumerdesAvenue de l’Independance35000BoumerdesAlgeria

The continuous evaluation of the measured Stand Pipe Pressure(SPP)against a modeled SPP value in real-time involves the automatic detection of undesirable drilling events such as drill string washouts and mud pump *** theoretical and experimental studies have been established to calculate the friction pressure losses using different rheological models and based on an extension of pipe flow correlations to an annular ***,it would not be feasible to employ these models for real-time applications since they are limited to some conditions and intervals of application and require input parameters that might not be available in real-time on each *** this study,The Group Method of Data Handling(GMDH)is applied to develop a trustworthy model that can predict the SPP in real-time as a function of mud flow,well depth,RPM and the Fan VG viscometer reading at 600 and 300 *** order to accomplish the modeling task,3351 data points were collected from two wells from Algerian *** and statistical assessment criteria disclosed that the model predictions are in excellent agreement with the experimental data with a coefficient of determination of 0.9666 and an average percent relative error less than 2.401%.Furthermore,another dataset(1594 data points)from well-3 was employed to validate the developed correlation for *** obtained results confirmed that the proposed GMDH-SPP model can be applied in real-time to estimate the SPP with high ***,it was found that the proposed GMDH correlation follows the physically expected trends with respect to the employed input ***,the findings of this study can help for the early detection of downhole problems such as drill string washout,pump failure,and bit balling.

关键词： Stand pipe pressure GMDH Drilling Mud flow Real-time monitoring Drill string washouts