International Journal of Reasoning-based Intelligent Systems (42 papers in press)
Multi-objective design optimization of four-bar mechanisms using a hybrid ICA-GA algorithm
by Nejlaoui Mohamed
Abstract: This work presents a novel approach to the multi-objective optimal design of four-bar mechanisms. Three conflicting objective functions are considered simultaneously, i.e., the tracking error (TE), the transmission angle deviation from 90
Keywords: Design mechanism; ICA-GA; Hybrid algorithm; imperialist competitive algorithm; Genetic algorithm.
Community Detection Using Intelligent Water Drops Optimization Algorithm
by Iyad Abu Doush, Saba ElMustafa, Ameera Jaradat, Nahed Mansour
Abstract: Community structure means the existence of densely connected subgroups in the networks. It is a surprising property that appears in complex and naturally constructed networks. We are proposing a novel heuristic approach to the community detection problem. In this paper, the community detection problem is solved using the intelligent water drop heuristic on a group of real life networks. The proposed heuristic succeeded in grouping the nodes in the network into sets of densely connected subgroups. Our approach uses the modularity value as an optimization criterion. The quality of the resulting division in the network was proven using measures like modularity and NMI. The experimental results verify that our algorithm is highly efficient at discovering quality community structure.
Keywords: Complex network ; community detection ; intelligent water drop ; modularity Q ; social network ; community structure ; metaheuristic.
Special Issue on: CIIA'2015 Advances in Computational Intelligence for Big Data
An Improved HBA Metaheuristic
by Bekaddour Fatima, Chikh Amine
Abstract: As simple and effective optimization approach, HBA (Homogeneity Based Algorithm) is one of the recent metaheuristics, proposed to minimize the total misclassification cost of data mining approaches. However, one problem is that HBA does not adopt computational complexity of the used data mining technique. This is due to the way objective function is defined. So, in this paper, we have proposed an improved HBA (IHBA), which is utilizing a modified objective function that compute the computational complexity of the used classification method. We also test several clus-tering techniques as HBA parameters tuning, in order to enhance classifiers performance. We have tested IHBA on different benchmarks and the obtained results show the effectiveness of the pro-posed method.
Keywords: Metaheuristics; Performance; HBA; Optimization; Data Mining.
Rotation-invariant method for texture matching using model based histograms and GLCM.
by Izem Hamouchene
Abstract: Nowadays, the research is interested in informatics systems that process automatically the information without human intervention. Image is an interesting research area due to the growth of the technologies. Thus, very large data are generated. This represents industrial and economic problem. Texture is one of the important and complex field of image processing. As all surfaces of objects are textured in nature, we have proposed a new texture analysis method. One of the key problem in image processing is the rotation. Therefore, the proposed method is robust against rotation. The goal of this study is to construct a model from each texture. After that, the system classifies the query texture based on the extracted texture models. In this work, we applied a recent and efficient feature extraction method called Rotation Invariant Neighborhood-based Binary Pattern (RINBP). The RINBP method extract relative and invariant patterns from the textured image. The proposed system combines between two parts. First, extract the RINBP model from the texture to describe the local variation of the texture. Second, we apply the GLCM method in order to extract statistical measures from the texture. Thus, efficient combination between the model histogram and statistical measures represents an efficient and robust feature descriptor of the texture. In the experiments, we have used the Brodats album database, which is a reference texture database. Experimental parts illustrates the efficiency and the robustness of the proposed system against rotation.
Keywords: Rotation invariance; Model based histograms; Texture matching; Feature extraction; Neighborhood-based binary pattern.
A 0 -1 Bat Algorithm for Cellular Network Optimisation: A Systematic Study on Mapping Techniques
by Zakaria Abd El Moiz Dahi, Chaker Mezioud, Amer Draa
Abstract: Many research efforts are deployed today in order to design techniques that allow continuous metaheuristics to also solve binary problems. However, knowing that no work thoroughly studied these techniques, such a task is still difficult since these techniques are still ambiguous and misunderstood. The Bat Algorithm (BA) is a continuous algorithm that has been recently adapted using one of these techniques. However, that work suffered from several shortfalls. This paper conducts a systematic study in order to investigate the efficiency and usefulness of discretising continuous metaheuristics. This is done by proposing five Binary variants of the BA (BBAs) based on the principal mapping techniques existing in the literature. As problem benchmark, two optimisation problems in cellular networks, the Antenna Positioning Problem (APP) and the Reporting Cell Problem (RCP), are used. The proposed BBAs are evaluated using several types, sizes and complexities of data. Two of the top-ranked algorithms designed to solve the APP and the RCP, the Population-Based Incremental Learning (PBIL) and the Differential Evolution algorithm (DE), are taken as comparison basis. Several statistical tests are conducted as well. Experiments show that the angle modulation and the nearest-integer techniques are the best ones. In addition, results of the evaluation demonstrate that the BBAs based on these techniques still have some shortcomings, but they could outperform the PBIL in 5 out of 13 of the APP instances and achieve results as good as the ones obtained by the DE in 3 out of 12 of the RCP instances.
Keywords: Bat Algorithm; Binary Problems; Mapping Techniques; Antenna Positioning Problem; Reporting Cell Problem.
Special Issue on: ICEST'2015 Information, Communication and Energy Systems and Technologies
Comparison of different methods for text skew estimation
by Darko Brodic, Ivo Draganov, Zoran Milivojevic, Visa Tasic
Abstract: This paper analyzes different methods for the evaluation of the text skew. The comparison is based on a dataset that consist of the printed text samples. These image samples are given in the resolution of 25, 50 and 300 dpi. Tested algorithms show different skew accuracy for different resolution of document images. The method with the smallest accuracy deviation demonstrates benefits over the other methods. Furthermore, this contributes to its robustness in applications.
Keywords: binarization; initial skew rate; moment based method; printed text documents; projection profiles methods; text skew.
Experimental determination of soil electrical parameters for creation of a computer model of a grounding system for lightning protection
by Rositsa Dimitrova, Marinela Yordanova, Margreta Vasileva, Milena Ivanova
Abstract: The paper presents multifactor experimental studies for determining the apparent soil resistivity and the dielectric permittivity depending on the frequency of the electromagnetic field, the multilayered structure, moisture content and density of the soil. The gravimetric method for considering the soil moisture during the experimental researches was chosen. The received experimental results were statistically processed and a mathematical modeling of the controlled parameters was performed considering the specifics of the examined soil. These analytically obtained results of the dependences would contribute to more precise sizing of the grounding systems and could be used for creation of accurate simulation models for study of wave processes in them.
Keywords: soil electrical parameters; soil resistivity; dielectric permittivity; multilayered soil; gravimetric method; mathematical modelling; grounding system; grounding rod; lightning protection.
An approach to Transformation of Data into Knowledge for Power Control in Smart Homes
by Ivaylo Atanasov, Anastas Nikolov, Evelina Pencheva
Abstract: Internet of Things (IoT) encompasses information and networking technologies which allow connected devices gathering data from their environment to exchange information with network applications. The increased number of diverse devices and the variety of multimodal data make interoperability a challenging task. Synthesis of semantic information from raw IoT data enables sharing of common data models between different applications. The paper presents an approach to modeling semantic annotation for power control in smart homes and then converting it to knowledge. The approach includes context aware models as well as a knowledge base describing behavior of an autonomous agent. The context aware models representing remote device management are formalized and verified using the concept of bisimulation. Temporal logic is used for specifying the agent behavior and reasoning about power control of home appliances.
Keywords: Internet of Things; Semantic annotation; Remote device management; Formal model verification; Weak bisimulation; Autonomous service model; Temporal logic.
Solving Medical Classification Problems with RBF Neural Network and Filter Methods
by Jasmina Novakovic
Abstract: This paper evaluates classification accuracy of radial basis function (RBF) neural network and filter methods for feature selection in medical data sets. To improve the diagnostic procedure in the daily routine and to avoid wrong diagnosis, machine learning methods can be used. Diagnosis of tumors, heart disease, hepatitis, liver and Parkinson's diseases are a few of the medical problems which we have used in artificial neural networks. The main objective of this paper is to show that it is possible to improve the performance of the system for inductive learning rules with RBF neural network for medical classification problems, using the filter methods for feature selections. The aim of this research is also to present and compare different algorithm approach for the construction system that learns from experience and makes decisions and predictions and reduce the expected number or percentage of errors.
Keywords: medical classification problems; classification accuracy; feature selection; filter methods; machine learning; RBF neural network.
Special Issue on: ICCMIT'16 Decision-support Systems Based on Intelligent Techniques
Social Network Analysis: Friendship inferred by chosen courses, Commuting time and Student Performance at University
by Lionel Khalil, Marie Khair
Abstract: Our Social Network Analysis (SNA) evaluates the performance of students taking courses with a group of friends versus students used to take courses alone. We evaluate the probability to be friend by comparing the number of courses shared by students with the probability to be assigned in the same classroom randomly based on curriculum constraints. A minimum of courses taken in common is used as a criterion to identify students belonging to a tribe of friends. The main findings are that students in tribes over perform other students by about half point of GPA, and are dropping and repeating fewer courses. Considering student without friends, we measured the impact of the commuting distance on GPA and drop off rate: students with very low GPA and high drop off are mostly students with significant higher commuting time.
Keywords: Social Network Analysis; Friendship; Student Performance; GPA; drop off; commuting time.
Special Issue on: Challenges in Smart Reasoning Intelligent Systems
Clustering Algorithm for Wireless Sensor Network to Improve the Efficiency of Acnode
by Youwei Shao
Abstract: In the vehicular ad hoc networks VANETs, the topological structure with high dynamic and frequent cracked link challenge the vehicle to vehicle communication. By taking VANETs city scene as the background, the Thesis proposes routing VAC-BNR (Vector-angle-cluster and bridge nodes-based routing) protocol based o clustering of direction vector angle and bridge nodes. The VAC - BNR protocol at first divides a road into the intersection area and straight line sections between or among intersections. In the straight line sections, according to the moving direction of vehicles, the vehicles are divided into different clusters, later on, utility value of the nodes in each cluster are calculated, and then priority of node forwarding data packages is arranged according to utility values of nodes; In the intersection area, the stability factor of the vehicles is calculated, which includes relative velocity and distance between the vehicle from surrounding vehicles, and the most stable vehicle in the intersection area is chosen as the forwarding node. The experimental data shows that the proposed VAC - BNR protocol can effectively improve data transmission in the urban scene environment.
Keywords: Topological structure; Clustering routing; Vector angle; Sensor network; Routing protocol.
Fuzzy Neural Network Learning based on Hierarchical Agglomerative T-S Fuzzy Inference
by Tao Duan, Ang Wang
Abstract: It is well-known that the accuracy of classification prediction is relatively high, but the prediction result is obscure in concept since result is given in two-value form (0 or 1) which says that red tide exists or does not exist. On the other hand, the accuracy of numerical prediction is relatively low, but it can offer density value of plankton which influences red tide. In order to combine characteristics of the above mentioned two methods, a prediction method for red tide which is mixed with integration model of hierarchical agglomerative T-S fuzzy inference is proposed. In the Thesis, through using the proposed prediction method mixed with integration model of hierarchical agglomerative T-S fuzzy inference, taking respective advantages of classification prediction and numerical prediction in prediction process for reference, and through experiment and comparison, it is proved that this algorithm is better than LMBP algorithm in prediction accuracy which shows the validity of the proposed algorithm. In the next step, it is mainly to further study the practical application of the algorithm, and to apply this prediction model to red tide warning system, and also to conduct experimental verification for a certain period by using actual marine environment.
Keywords: Fuzzy inference; Neural network; Hierarchical agglomerative; Prediction.
Key Data for Cloud Computing based on Ensemble Clustering Approximate Analysis
by Zou Yu, Qin Zhong Ping
Abstract: To realize multi-label classification of text and meanwhile reduce calculation complexity and keep classification precision, dimensionality-reduction clustering method for fuzzy association of text multi-label based on cluster classification has been proposed. In text classification, it usually involves enormous feature numbers, which may cause curse of dimensionality. In addition, classification region can not always keep convex characteristics. It can be non-convex region composed of several overlapping or intersecting sub-regions. Above mentioned automatic classification system may require enormous memory requirement or has poor classification performance. Hence, new multi-label text classification method is proposed to overcome these problems in combination with fuzzy association technology. Fuzzy association evaluation is adopted to transform high-dimension text to low-dimension fuzzy association vector, thus avoiding curse of dimensionality. Experiment results show that the proposed method can more effectively classify text multi-label problem.
Keywords: Fuzzy transformation; Key data; Integration clustering; Cloud data; Data analysis.
Design of Unsupervised Facial Expression Animation Based on Geometric Grid Measurement
by Niu Chunzhou, Zhu Yukai
Abstract: Many actual application images in the real world are formed by high dimensional data in most cases, while the manifold learning algorithm can explore the nonlinear information hidden in these high dimensional data. As most of manifold learning algorithms can only be defined in training cluster, it is impossible to project the sample on the lower dimensional space. In the Thesis, we introduce a kind of double manifold algorithm based on LLE and Isomap. Different from the traditional LLE algorithm, our algorithm learns two kinds of manifold information in which one group of data relates to many types and it compares two kinds of single LLE algorithm and Isomap algorithm through the setting of the appropriate nearest neighbor number K. No matter for the recognition rate or running time, it is obviously superior to the other two kinds of algorithms and it can effectively achieve the estimation of facial expression and significantly reduce the computation complexity.
Keywords: Facial expression; Geometric grid; Unsupervised; Manifold learning algorithm; K-nearest neighbor.
Factor analysis model of the result of hospitalized patients with neurosis
by Sun Shanhui, Li Hong, Li Zhuangzhuang, Zhang Bingqiu
Abstract: To study the diagnosis of hospitalized patients with neurosis and its influencing factors, this article, on the basis of the data of treating hospitalized patients with neurosis hospitalization, empirically analyzes the relationship between the treating effect and personal basic situation, personal social relations, personal original condition, and makes the corresponding regression analysis and factor analysis. The results show that the patient's social relationship and personal character are obviously related to the diagnosis of neurosis. There are obvious correlations between the original condition in the early diagnosis and patients with neurosis, so it is important to strengthen the understanding and analysis of the original condition. We should strengthen publicity and education of mental health knowledge, encourage people from all walks of life to actively participate in it and improve their awareness of neurosis, and thus to effectively reduce the bias in patients with neurosis. Untimely separation and unharmonious relation with parents are one of socio-psychological factors which cause adults suffer neurological disorders.
Keywords: Neurosis; Diagnosis; Factor Analysis Model;.
Multi Criteria Decision Making Method based on Analytic Hierarchy Process with Intuitionistic Fuzzy Preference Information
by Cai Liang
Abstract: An extension method of multi criteria decision making (MCDM) is proposed in the Thesis for selection and assessment of parting line in mold design. First of all, linguistic variable is used to express grade of alternative parting line scheme and weight of criterion significance; and then, the membership function of final fuzzy assessed value is determined based on these linguistic values; in the end, a new ordering method of maximum and minimum sets will be adopted for normalization of weight grading and defuzzification to clear value and for strength and weakness ordering of alternative scheme. The verification and contrast experiment show effectiveness of the method in the Thesis and the comparison with traditional fuzzy multi criteria decision making method shows the method in the Thesis is more applicable.
Keywords: Fuzzy number; Multi criteria decision making; Selection of parting line; Mold design; Ordering of maximum and minimum sets.
MapReduce Optimization Information Query Method for File Management System
by XuGuang Zhu, Yuzhi Shen
Abstract: MJQO problem is very complicated, query speed influences execution efficiency of database application software. To solve deficiencies such as low rate of convergence, etc of PSO algorithm and improve optimization efficiency of database multi-connection query, this Thesis proposes a MJQO method adapting to escape momentum particle swarm optimization aiming at deficiencies of particle swarm optimization such as early-maturing, partial optimization, etc, and it verifies effectiveness of SAEV-MPSO via emulation contrasted test, and this algorithm can obtain optimal query scheme of MJQO in relatively short time. Crossover mechanism is first introduced by this algorithm of genetic algorithm to particle swarm algorithm to maintain diversity of it and prevent early-maturing phenomenon, and then this Thesis introduces search track of momentum algorithm smoothness particle to accelerate convergence rate of particle swarm; finally this Thesis applies this algorithm to database multi-connection query optimization solution to achieve optimal database query scheme. Emulation result indicates this algorithm improves database query efficiency and shortens query response time.
Keywords: Database query; Archive information management; Genetic algorithm; Mapreduce; Particle swarm.
Dynamic Path Planning of Mobile Robot based on Ant Colony Algorithm
by Long Zhuo-Qun
Abstract: The Thesis makes vehicle in cross-country environment as research object, and uses improved ant colony algorithm to research and analyze the cross-county path planning. First, improved ant colony algorithm is used to research cross-county path planning of vehicle, then Slope Table and Roughness Table are introduced to analyze topographic Slope and land surface propertys affect on path planning, and path optimization algorithm is designed considering restriction of slop and Roughness. Simulation result shows that this algorithm can realize cross-county path planning with speediness and efficiency. Experimental result demonstrates that the improved ant colony algorithm has stronger feasibility and better searching capability.
Keywords: Path planning of robot; Land surface property; Optimal method; Ant colony.
Construction of Evaluation System of Sports Talent Training Scheme based on Data Mining
by Gong Xun, Lin Suxia
Abstract: In order to improve the effectiveness of the evaluation system construction for sports talent training program, this paper puts forward a kind of evaluation system construction method for sports talent training program based on data mining. It provides the description target of sports talent training program, the problem that the upper bound of itemsets only used by the traditional mining algorithm has unsatisfactory effect on the high-expectation weight and downward closure property of mining algorithm in design hierarchy, and presents the proof process, and this property can effectively reduce the processing capacity of candidate set in the premise of ensuring the accuracy, to construct the two-stage data mining process. By comparing with the training program of 2007 version, the proposed method can eliminate the setting compulsory course equivalent to individual professional elective course, to promote the diverse development of students.rnrn
Keywords: Two-stage; Apriori algorithm; Sports talent; Training program.
Design of College Students' Physique Monitoring and Service Platform based on Computer and Network
by Haiyan Wang
Abstract: The problem of college students physique has become a serious problem which restricts the cultivation of high-competent talents in China. In view of the existing deficiencies in the monitoring platform of students physique, we fully utilize the advanced technology of computer and Internet development and follow the basic principles of economical practicality, scalability, user-friendliness and real-time information exchange to establish monitoring and service platform for college students physique. It will have far-reaching practical significance to fulfill the expected goals in different levels such as teaching management, campus sports, and students' individual physical intervention in all universities through the basic and extended functions of platform such as basic assessment, testing organization, data management, information release, fitness guidance, and printout. The main design idea of the platform, the function realization, and the design expansion and operation method of each module will provide reference for universities to establish their own physique monitoring and service platform in line with their own requirements.
Keywords: Computer; College students; Physique; Monitoring; Service.
Decision Making Model of energy Consumption based on Multi Uncertain Factors
by Cai Liang
Abstract: An Energy Consumption Decision Model Method based on multi-factor Agent Fuzzy Game Compromise is proposed in this Article, to promote availability of energy consumption decisions. First, give the Fuzzy Decision Model for Energy System based on multi-agent methods, in which fuzzy decision Agent is the core of whole alliance, able to get the energy demands information of users from user layer Agent, and the energy supply conditions and energy supply availability inside the alliance from energy consumption layer Agent; secondly, give a fuzzy game compromise weight decision method to build a relation matrix based on fuzzy evaluation, and propose an assessment methods for grey Euclid model; and at last, by simulation experiment, verify the availability of energy consumption decision model based on the proposed multi-factor Agent Fuzzy Game Compromise.
Keywords: Multi-factor; Agent model; Fuzzy compromise; Energy consumption; Decision model.
WSNs Heterogeneous Cluster Routing based on Distributed Fuzzy Logic Inference
by Tang JunYong, Chen Xiang
Abstract: Targeted at the wireless sensor network in heterogeneous distribution composed of solar energy supply nodes and zero energy supply nodes, the cluster routing algorithm based on node density and energy size is proposed. In this Thesis, the wireless sensor network of heterogeneous non-uniform distribution is studied, and sun energy harvesting model ISHE based on intensity of illumination is proposed. In IISHE model, at first, the light intensity sensor is used to read solar illuminance under the current environment, and then, energy size obtained by solar energy supply node at specified period can be estimated based on corresponding relation between illuminance and irradiance. The model is characteristic of strong timelines and high calculation accuracy. The second innovation point is to propose cluster routing algorithm of the wireless sensor network of heterogeneous non-uniform distribution based on node intensity and energy size in the Thesis. The experiment results show that invalidation round rate of the first node LEACH in the algorithm proposed in the Thesis is 86.2% higher than the average value and invalidation round rate of the last node is 65.9% higher than the average value; network coverage rate of the algorithm in 86% of lifetime is 38% higher than LEACH; network throughput of the algorithm proposed in the Thesis at round 2000 is 5 times as that of LEACH.
Keywords: Fuzzy inference; Distributed; Wireless sensor network; Cluster routing; Non-uniform distribution.
Facial Feature Extraction based on Principal Component Analysis and Class Independent Kernel Sparse Representation
by Xin Xiong, Li Kefeng
Abstract: Robust Principal Component Analysis (RPCA) and kernel sparse representation technology which have been proposed in recent years provide a new idea for solving problems of the above three aspects. In this Thesis, classification algorithm of kernel sparse representation has been proposed based on robust principal component analysis by using RPCA technology to generate redundant dictionary and kernel sparse representation to structure classifier, and has been used for face recognition. Basic idea of this algorithm is to generate base dictionary and error dictionary by using RPCA technology, and to realize face recognition through classifier structured by kernel sparse representation. Firstly, each training sample matrix has been decomposed into a low rank matrix and a sparse error matrix by using RPCA technology, so as to structure base dictionary and error dictionary by using the low rank matrix and error matrix respectively, and generate redundancy dictionary of sparse representation of test samples. Then, Kernel regularized Orthogonal Matching Pursuit (KROMP) algorithm has been proposed to get sparse representation coefficient which has been used to complete classification and recognition of test samples. Compared with similar algorithms, algorithm in the Thesis is of a high recognition rate for face recognition, and has a strong ability to adapt to noise and error interference.rnrn
Keywords: Principal component analysis (PCA); Image recognition; Sparse representation; Face recognition; Facial feature; Feature extraction.
An Arabic Natural Language Interface for Querying Relational Databases Based on Natural Language Processing and Graph Theory Methods
by Bais Hanane, Mustapha Machkour, Lahcen Koutti
Abstract: Nowadays, databases represent a great source of information. To extract information from these databases, the user needs to write queries using database query languages, such as Structured Query Language(SQL). Generally, for using this type of language, this user must know the structure of the database. However, this task can be difficult for non-expert users. In that, the using of natural language to extract data from the database can be a very important and efficient method. The problems in using natural language query are that it doesn't give any specification about the path access correspond to the required data. For that, many previous works are deal with the problems of freeing users from knowing the detailed structure of the database. But, Almost of this works are designed to the English language. Whereas, for the Arabic language which is the subject of this paper, there is not any proposed system. For that, we present in this paper a model of a natural language interface for databases. This interface allows the user to access data stored in the database by using Arabic language and it obviates the need for users to know the internal structure of the underlying databases. Also, it can function independently of database domain, and it can to improve its knowledge base through experience.
Keywords: Arabic language processing; DataBase; Graph theory; Dijkstra Algorithm; Extended Context Free Grammar.
Special Issue on: Application of Multimedia Technology in Intelligent Manufacturing
A Effective System Layout Planning Method for Railway Logistics Center in the Background of Big Data
by Jie Li
Abstract: In the background of big data, railway logistics has become the inevitable trend of freight transportation. This paper puts forward a new method of logistics center function area layout. System layout planning (SLP) method is firstly used to analyze functional domains to construct a comprehensive correlation chart of the functional domains according to certain weights. Manhattan Distance and circuitous path are used to express the distances among the functional domains and to construct a double-object function with minimized total trucking expense and maximized total integrated relations. In the practical application of R.Muther line chart method, the proposed method can get the feasible scheme of layout of functional areas, and it has good application value.
Keywords: Big Data, Railway Logistics Center, Layout of Functional Domains, Manhattan Distance, Circuitous Path
Personalized ranking online reviews based on user individual preferences
by Wei Song, Shiwei Zhang, Lizhen Liu, Hanshi Wang
Abstract: With the development of e-commerce sites, online reviews have become important data resources for e-customers. However, the quality of review varies a lot, with positive reviews always intermingled with negative ones, seriously interfering with their accuracy and credibility and making it very difficult for consumers to make the right purchase decision. Nowadays, there have been many literatures on the category of reviews category or ranking for public. The thing is, they only satisfy common preferences, and ignore personalized preferences of individual users. In view of this phenomenon, this paper is trying to put forward a ranking method for individual preferences. It begins with collecting the rules of user preferences by showing reviews to them to let them mark the reviews they like. Then it combines the common rules with user personalized rules to get the range of features. Finally, after calculating the optimal solution of features, the paper strives to structure a ranking model to rank reviews with the set of optimal solution.
Keywords: attribute word; user preference rule; hill climbing algorithm; ranking
An Effective Foggy Image Acquisition Algorithm in Multimedia Big Data Era
by jinxing niu
Abstract: Outdoor images are often degraded by fog weather conditions in the era of multimedia big data , which affect computer vision applications severely. In this paper, an effective fog image acquisition algorithm based on big data analysis is proposed in the big data environment, and single image defogging algorithm based on histogram equalization and dark channel prior methods is proposed. The transmission and air light of the fog image need to be estimated by the dark channel prior theory methods, then clear images can be received after defogging and keep the original color. The experimental results show that the image by fog removal dark channel prior method can get clear images and keep the original color, the treatment effect is better than that of the histogram equalization method.
Keywords: Multimedia Big Data ,Foggy Image, Effective Foggy Image Acquisition Algorithm , Image Restoration, Big Data Analysis
Bi-level Optimization Model for Greener Transportation with Intelligent Transport System
by Kun Liu
Abstract: In this paper, we propose a bi-level optimization model (BLOM) with three algorithms. BLOM is intended for fuel saving and carbon dioxide emission reduction in both upper-level and lower-level model with Intelligent Transport System. Traffic signal schemes are optimized for minimizing total fuel consumption passing through a road intersection in unit time in the upper-level model. At the same time, traffic signal information data are sent to the lower-level model in which vehicle motion states are optimized for greener transportation. Three algorithms include hybrid genetic algorithm and particle swarm optimization in upper-level model with hybrid genetic algorithm and particle swarm optimization in lower-level model (GA-PSO/GA-PSO), GA in upper-level model with PSO in lower-level model (GA/PSO) and GA in both level model (GA/GA) are realized to compare and improve the performance of the model. The simulation results derive GA-PSO/GA-PSO hybrid algorithm converges faster with the best resolution and least calculation time than other GA/PSO and GA/GA algorithms.
Keywords: Bi-level optimization; greener transportation; Intelligent Transport System
The Development and Popularization of Network Platform of College Sports Venues in Intelligent Manufacturing
by Han Kaiyan, Wang Qin
Abstract: With the promotion of the national fitness campaign, the number of physical exercise shows explosive growth in China.The question that blocks the development of sports exposed which is a lack of public sports venues. This paper focuses on building a network platform of all college sports venues resources which can reach the goal to serve national fitness, and proposes an Improved Parallel Heuristic Map Reduce Algorithm (IPHMRA). The experimental results show the stability, concurrency and feasibility of the network platform of college sports venues in big data era.
Keywords: Intelligent manufacturing, college sports venues, national fitness, Improved Parallel Heuristic Map Reduce Algorithm (IPHMRA), stability and concurrency.
Special Issue on: Artificial Intelligent Techniques Applied to the Study of Engineering Applications
Exploiting Ontology to map requirements derived from informal descriptions
by Murugesh Sundaram, Jayal A
Abstract: Requirements are narration of the services which a software system should make available along with the constraints that should be satisfied when the system operates. Software requirements have to be arrived from descriptions that are often incomplete, inconsistent, informal and ambiguous . Such informal descriptions have to be preprocessed and information constructs have to be extracted. This article deals with use of an ontology specific to Automatic Teller Machine(ATM) operations domain that contains the concepts, the relationships that exists among the concepts and the focus is to decide on the feasibility of the requirement by mapping the extracted requirement with the requirement defined in the background ontology. The developed ontology is queried using Simple Protocol and RDF Query Language (SPARQL), if the derived requirement is present in the ontology it is said to be feasible; else decision may be taken to eliminate the requirements that are invalid and infeasible. Ontology is a formal specification of concepts with their attributes and relationship in a particular domain. As standard description formalism, the Web Ontology Language (OWL) that is based on Resource Description Framework (RDF) is to be used.
Keywords: Ontology, Requirements elicitation, Simple Protocol And RDF Query Language (SPARQL), Web Ontology Language (OWL), Resource Description Framework (RDF), Unstructured documents, Natural Language Processing (NLP).
Application of mutation inspired Constrained Factor PSO considering voltage stability and losses by locating and rating TCSC during N-1 Contingency
by Jayachitra S, Baskar G, Feridinand T
Abstract: This paper describes, a strategy for optimal placement and setting of series FACTS controller- Thyristor Controlled Series Capacitor (TCSC) under single line contingency (N -1) using Particle Swarm Optimization(PSO), Constriction Factor PSO(CFPSO), Cauchy mutation- CFPSO(CM-CFPSO) & Gaussian Mutation – CFPSO(GM-CFPSO) algorithm in order to reduce over loading and power loss in transmission lines and to improve voltage stability of a power system. In this proposed CM-CFPSO & GM-CFPSO methods, a new-fangled position equation is framed and the features of the Constriction Factor Approach (CF) is incorporated with the proposed approach. To detect the most severe transmission line, Composite Severity Index (COSI) is calculated under N-1 contingency and top three severe lines are taken for this research work. To validate the consequence of proposed approach, simulation studies are carried out on a standard IEEE 30-bus network. Appraisals are made in provisions of eminence solution, execution time and stable convergence behaviour
Keywords: Particle Swarm Optimization; Composite Severity Index; Mutation; Contingency; Optimal placement; Constraint Factor; Thyristor Controlled Series Capacitor;
Special Issue on: Recent Trends in Reasoning-based Intelligence Systems
Cloud Computing Resource Scheduling and Leasing Algorithm based on Extreme Price Filter
by Liu Xiaoming, Li Zonghui, Wang Junjie, Xu Xujiang
Abstract: VRS problem provides virtual resource of different types and different prices. CSP should select the most profitable leasing strategy during confirmation of virtual resource in VRS. However, there is no algorithm at present that considers about virtual resources selection of price and type. Because the price fluctuations of different types of resource are inconsistent, resource with the biggest profit can vary among different price intervals. A cloud computing virtual resource leasing algorithm considering about extreme price filtering has been proposed in this paper, which realizes optimal selection for handling leasing price for task virtual machine. First, three-function module cloud composed of virtual resource provider, cloud service provider and final user has been adopted to calculate environment and list calculation target for virtual resource leasing profit; second, distribution and task urgency of price has been fully considered. For weakly stationary price sequence, outlier detection method has been adopted to make extreme price filtering. At the same time, weak equilibrium operator has been designed, exponential function has been used to control the overall shape of curve, non-uniform mutation operator has been used to make local operating adjusting, realize effective prediction for price in the future and optimal selection and make optimal selection for handling leasing price of task virtual machine.
Keywords: extreme price; maximization; filtering algorithm; cloud computing; resource scheduling.
Training Project Arrangement for Tennis Athletes based on BP Neural Network Model
by Wang Hao, Yuan Hong
Abstract: In order to improve the prediction accuracy of athletes tennis training effect, a kind of prediction method for athletes tennis training effect of RBF (Boundary Value Constraints Radial Basis Function, BVC-RBF) neural network with boundary value constraints is proposed. Firstly, the internal and external factors that influence the athletes tennis training effect is analyzed, and the influence models of 12 indexes including quantitative load heart rate and body fat percentage are predicted and analyzed emphatically; secondly, the RBF neural network algorithm with boundary value constraints is built to solve the boundary value constraint equation, so as to obtain the compensation function, and the least square method is used to train traditional RBF neural network, which achieves the improvement of prediction algorithm performance; finally, the simulation experiment shows that the proposed method provides higher prediction accuracy, which has a certain guiding value for tennis training.
Keywords: tennis training; boundary value constraint; rbf neural network; least squares; prediction accuracy.
Algorithm of Key Data Ensemble Clustering and Approximate Analysis in Cloud Computing
by Zhang Haijun, Xia Wendong, Liu Yuanfeng
Abstract: One collaborative data fusion recommendation algorithm (SFS-TOPSIS) based on customer satisfaction degree and characteristic approximation has been designed to improve recommended execution efficiency of data fusion algorithm as well as the reliability of recommendation result, so as to recommend service that meets more personalized demands to user. First, it starts from calculation efficiency and recommended precision angle that improves service recommendation algorithm, makes improvement for similarity evaluation by combining user attribute and satisfaction degree for service, makes real-time updating and algorithm improvement for it by combining time-varying weight method TOPSIS fusion algorithm and designs a collaborative data fusion recommendation algorithm based on customer satisfaction degree and characteristic approximation. Second, for the problem of inadequate definition of traditional similarity for resolution, improvements have been made based on user evaluation confidence, interest preference and characteristic similarity evaluation; make it more suitable for the real experience of user by combining the similarity substitution of user attribute for user. Last, time-varying weight method has been adopted to improve standard TOPSIS fusion, improve time-varying attribute of TOPSIS decision fusion and realize effective attribute fusion of user similarity data; through making simulation comparison on two standard testing sets of and , it indicates that the service recommendation performance of SFS-TOPSIS is more superior. The proposed SFS-TOPSIS algorithm can improve service recommendation accuracy effectively and it is with certain application value.
Keywords: big data; similarity; approximate analysis; clustering; cloud computing; decision recommendation.
Parallel Cluster Analysis of Multi City Congestion based on Spatial Temporal Potential Correction in Mobile Phone APP
by Shi Jin
Abstract: To improve urban road congestion detection and governance efficiency of city, this paper puts forward spatial-temporal analysis method for urban road congestion of multiprocessor parallel clustering based on potential field correction, establishes spatial-temporal model of urban road congestion based on temporal data of GIS four-dimensional space and constructs multiprocessor parallel clustering method by utilizing potential field correction method and designs parallel multiprocessing detection method of urban road congestion of distance matrix, neighborhood radius and density function. Experimental result verifies effectiveness of method mentioned and it shows that method mentioned can realize fast and effective detection analysis of urban road congestion and provides data support for urban road congestion management.
Keywords: spatial-temporal analysis; parallel clustering; urban road congestion; GIS four-dimensional space; spatial-temporal model.
Design of Public Bicycle Scheduling Model based on Data Mining Algorithm
by Zhang Haijun, Xia Wendong, Liu Yuanfeng
Abstract: Guangzhou Public Bicycle System has been the largest bike-sharing program in the world. Software of the system was developed by our research team. To meet the fluctuating demand for bicycles and for vacant lockers at each station, employees need to actively shift bicycles between stations by a fleet of vehicles. Hybrid GRA-SP metaheuristic which incorporate a path-relinking procedure have been successfully applied for different combinatorial problems. Data mining is a process that uses a variety of data analysis tools to discover patterns and relationships in data. In this paper, a new hybrid data mining metaheuristic combines GRA-SP which incorporate path-relinking procedure with data mining process is proposed and some improvement are made.
Keywords: public resource; scheduling; mining algorithm; model.
Parallel K-Means Algorithm based on Two Stage Clustering of Large Data
by Xia Wendong, Liu Yuanfeng, Chen Deli
Abstract: Aiming at the fact that the algorithm communication time occupation ratio is too high and the practical application value is limited under the Mapreduce mechanism, a Hadoop-based two stage parallel c-Means clustering algorithm is proposed to solve the classification problem of super large data. First, the Hadoop-based two stage parallel fuzzy c-Means clustering algorithm is proposed to process the clustering of large data; and a protocol-based group typical individual reduction strategy is used to improve the time complexity of the MPI communication model of Mapreduce, so as to improve the overall efficiency of the algorithm; secondly, the interference of bad data items can be effectively eliminated by the selective group reduction algorithm, so that the algorithm in this paper has higher operating efficiency and clustering success rate. In terms of parallel rate and speedup ratio, the parallel rate and speedup ratio of the proposed algorithm in this paper on the large data set is better than the performance of the small data set, which means that the algorithm in this paper can adjust itself according to the amount of data in real time. The simulation results show that the performance of PGR-PFCM algorithm is better in the processing of large data.
Keywords: parallel algorithm; fuzzy clustering; K-Means; big data; two stages.
Cluster Analysis Algorithm based on Key Data Integration for Cloud Computing
by Li Dong-rui
Abstract: In order to improve scheduling efficiency and resource utilization ratio of cloud computing platform, a kind of cloud task scheduling algorithm of improved fuzzy cluster has been proposed. Firstly, cloud task scheduling algorithm of improved fuzzy cluster has been introduced, which mainly uses fuzzy FCM algorithm to complete resource cluster to three resource sets including computing type, storage type and bandwidth type in the context of using parallel processing to ensure the efficiency. On this basis, Min-min algorithm has been improved towards Qos so that the resource of cluster set with the shortest time in completion of task allocation will not be idle and the resource of cluster set with the longest time in completion will be liberated from the busy schedule to improve the utilization ratio of resources, ensure load balance, reduce execution costs and enhance customer satisfaction; secondly, tasks have been allocated to each cluster through heuristic algorithm and the results have been adjusted according to set threshold to obtain the better scheduling results. The experimental results show that the proposed algorithm is superior to the traditional algorithm without cluster in terms of execution time. Compared with the algorithm without adjustment of the threshold, the algorithm is better in performance and load balance which is a more efficient cloud task scheduling algorithm.
Keywords: big data; cloud computing; approximate data; fuzzy cluster; resource scheduling; intelligent algorithm.
Two Echelon Supply Chain Model of Agricultural Products based on Stochastic Fuzzy Process of Cost Demand
by Gao Jie
Abstract: Stochastic fuzziness existed in supply chain process has important influence on inventory maintenance and decision processing of normal system operation, especially under the situation of coupling existed in two echelon supply chain, this influence will be amplified to some extent. To process this potential influencing factor effectively, one two echelon supply chain model based on stochastic fuzzy process of cost demand has been designed, which can improve the rationality of supply arrangement. First, for the studied two echelon supply chain objects, joint cost has been taken as target to make optimal model design; Second, considering about the stochastic fuzziness existed in two echelon supply chain, the demand rate of market for products as well as supply and distribution time have been selected as main research parameters, two echelon supply stochastic demand model based on triangular fuzzy number has been constructed and then model solving process has been deduced according to the characteristics of design model; Last, verification for the performance of proposed model has been made based on parameter influence experiment and horizontal contrast. This paper has made full use of research results of above literature in single echelon supply chain and focused on study the IPP inventory management integration system, which is composed of single manufacturer and single demand customer. For real application scenario, two echelon supply chain meets the distribution demand and it the most common.
Keywords: joint cost; fuzzy demand; demand rate; two echelon supply chain; distribution; logistics.
Parameter Tuning of Boiler Thermal Process based on SVM Neural Net Optimization
by He Peng
Abstract: Because of complex characteristics, such as multivariable coupling in boiler thermal process of circulating fluid bed, parameter turning, there is relatively large difficulty in automatic accurate control so that a kind of Self-adaptive Controller Algorithm is put forward. Fuse fuzzy control and equivalent method of BP neural net usage structure to fuzzy BP neural net and bring in weight of Genetic Algorithm optimization BP neural net by aiming at defects, such long convergence time of neutral net and realize self-adaptive accuracy control to boiler thermal process of circulating fluid bed by feed-forward compensation decoupling device. It is showed from experiment results that the Algorithm can adapt to working condition of variable parameter boiler thermal process of circulating fluid bed and it has realized uncoupling of bed temperature and main steam pressure.
Keywords: boiler thermal process of circulating fluid bed; thermal self-adaptive control; fuzzy control; bp neural net; genetic algorithm.
Design of Human-Computer Interaction Interface Considering User Friendliness
by Chen Hong
Abstract: Analysis and modeling for interactions on self-service terminal interface have been made in this paper based on distributed cognition theory, which is to confirm the relationship between interactions and information presentation in human-computer interaction and propose interface interaction design method of self-service terminal based on user cognitive ability. With adoption of this method, designers need to make research on users and identify the user group that needs to be taken care of firstly, and then make analysis of cognitive ability, set up user cognitive load model, describe the interactive behavior of users, confirm basic interaction frame, and then establish interaction design matrix with universal usability design model and propose interactive design program. We take hotel self-service terminal as example, adopt this method to make design program and then verify the effectiveness of the proposed design method through making comparisons with design program formed by traditional method. This interactive design method can help designers develop self-service terminal interface that is suitable for people to understand and use, decrease the cognitive load of users and meet the diversified demands of self-service terminal users for cognition.
Keywords: universal usability; cognition theory; user friendliness; interactive design; interface system.
Complex Electromechanical System Condition Monitoring based on Improved Particle Swarm Optimization RBF for Audio Visual Fusion
by Xu Jiangwei, Li Tiejun, Zhang Liang
Abstract: To improve transient stability of multi-generator power system, continuous high-order sliding mode excitation control strategy is put forward. Power angle deviation of each generator is variable of sliding mode. Nonlinear and uncertain high-order sliding mode control of multi-generator power system is transferred into limited time stability problem of uncertain integral chain system. Realize limited time convergence of system condition and overcome uncertainty, such as unmodeled dynamics of system, measuring error and external disturbance etc. through combination of controller and geometric homogeneous continuous control law and second-order sliding mode super-twisting algorithm. Observe power angle differential with precise robust differentiator. Analyze and verify limited time stability of closed-loop system theoretically. High-order sliding mode excitation controller designed can keep voltage stability at generator terminal and improves transient stability of power system effectively. Simulation result aimed at 3-generator system verifies effectiveness of control method mentioned.
Keywords: multi-generator power system; transient stability; continuous high-order sliding mode; excitation control; condition monitoring.