Earticle

Due to the impact of wireless sensor networks (WSN) on dramatic reduction in computational and energy resources, research on the implications of this type of networks would be considered as a deliberate and update point. One of the main issues in these networks is the security. During transfer of data from source nodes to sink nodes or vice versa, many WSNs require applications to protect data privacy. Besides, computational and energy and memory limitations of WSNs and also defenseless environment that may be applied to them, make the possibility that these types of attacks occur more often. In this study, we provide a design using intelligent multi-agent systems that help us during the crime and after crime occurred to obtain more accurate forensics reports presentable to the court of law. A feature of the design of intelligent multi-agent system is to obtain evidence during crime, without the suspect realizing it; in fact, we can do live acquisitions. The proposed design was raised in WSN networks for first time. The investigation in firewall forensics consists of analyzing and interpreting information related to computer attacks which is contained in firewall log files. But the log files content is generally mysterious and difficult to decode. This paper proposes an intelligent system that automates the firewall forensics process and helps the security administrators to manage, exploit and interpret the firewall log file contents.

Clustering method is divided into hierarchical clustering, partitioning clustering, and more. K-Means algorithm is one of partitioning clustering methods and is adequate to cluster a lot of data rapidly and easily. The problem is it is too dependent on initial centers of clusters and needs the time of allocation and recalculation. We compare random method, max average distance method and triangle height method for selecting initial seeds in K-Means algorithm. It reduces total clustering time by minimizing the number of allocation and recalculation.

The KDD Cup 99 dataset has been the point of attraction for many researchers in the field of intrusion detection from the last decade. Many researchers have contributed their efforts to analyze the dataset by different techniques. Analysis can be used in any type of industry that produces and consumes data, of course that includes security. This paper is an analysis of 10% of KDD cup’99 training dataset based on intrusion detection. We have focused on establishing a relationship between the attack types and the protocol used by the hackers, using clustered data. Analysis of data is performed using k-means clustering; we have used the Oracle 10g data miner as a tool for the analysis of dataset and build 1000 clusters to segment the 494,020 records. The investigation revealed many interesting results about the protocols and attack types preferred by the hackers for intruding the networks.

Research and analyze the mobile terminal remote accessing to the database interfaces and methods. On this basis, proposed a middleware forms based on Object Relational mapping. The middleware achieves mobile terminals remote accessing the database and managements of mobile terminals to connect to the database and access mechanisms. This paper adopts the methods that mobile terminals remotely access to database based on ORM and it defines ORM rules that the mobile terminal remotely accesses to the database. It designs and proposes new approaches for mobile terminals and database transmission of information and management. The method achieves visualization of the database interface.

Noise data of web page is easy to cause the topic drift problem in web information extraction. To improve the accuracy of web information extraction effectively, a novel calculation method of mixing entropy is presented, which can more accurately reflect the topic information of web page. The information block is discussed under the multi-page site environment. The impacts of information within local page and the same information distribution between web pages generated by template are all considered so as to ensure the precision of calculating information entropy. The method is verified by calculating the entropy of information block in information extraction. Compared with other methods, the simulation results indicate that the novel method shows great superiority over other traditional methods in both the accuracy of information entropy calculation and discrimination between topic-related information blocks and topic-unrelated information blocks.

There are fewer techniques to group objects having similar characteristics deal with categorical data ,but some are of them be complicated in the clustering process while others have stability issues. In this paper we represent a new technique which it be more easier than the other techniques in computing the selecting clustering attribute process and at the same time having stability issues besides taking care of handling uncertainty and categorical data together, we called it (maximum significance of attributes) MSA. The proposed technique based on rough set theory by taking into account the concept of significance of attributes of the database. We analyzing and comparing the performance of MSA technique with (bi-clustering) BC, (total roughness) TR, (minimum-minimum roughness) MMR and (maximum dependency of attribute) MDA techniques.

Conceptual design is an early stage of the whole mechanical product development process, which is a problem-solving activity based on knowledge engineering. Designers often have difficulty in fulfilling complex product designs due to the lack of sufficient product design knowledge. This paper is devoted to presenting a systematic object-oriented knowledge modeling for conceptual design of mechanisms. After object-oriented knowledge representation strategy is introduced, the object-oriented inheritance relationship of mechanisms is discussed in detail, and then the design catalogue for conceptual design of mechanisms is also put forward. Knowledge modeling for conceptual design of mechanisms, including function knowledge modeling, mechanism unit knowledge modeling, mapping knowledge modeling, is discussed step by step. A computer aided mechanism conceptual design software system is developed, and the system implementation of above knowledge base is proposed. The pipe racking system for the oil drilling platform is given as an example, which demonstrates that the object-oriented knowledge modelling methodology is obviously helpful for mechanical product conceptual design of mechanisms.

Cloud computing technology is changing the mode of the spatial information industry which is applied and provides new ideas for it. Since Hadoop platform provides easy expansion, high performance, high fault tolerance and other advantages, we propose a novel vector spatial data storage schema based on it to solve the problems on how to use cloud computing technology to directly manage spatial data and present data topological relations. Firstly, vector spatial data storage schema is designed based on column-oriented storage structures and key/value mapping to express spatial topological relations. Secondly, we design middleware and merge with vector spatial data storage schema in order to directly store spatial data and present geospatial data access refinement schemes based on GeoTools toolkit. Thirdly, we verify the middleware and the data storage schema through Hadoop cluster experiments. Comprehensive experiments demonstrate that our proposal is efficient and applicable to directly storing large-scale vector spatial data and timely express spatial topological relations.

The traditional k-prototypes algorithm is well versed in clustering data with mixed numeric and categorical attributes, while it is limited to complete data. In order to handle incomplete data set with missing values, an improved k-prototypes algorithm is proposed in this paper, which employs a new dissimilarity measure for incomplete data set with mixed numeric and categorical attributes and a new approach to select k objects as the initial prototypes based on the nearest neighbors. The improved k-prototypes algorithm can not only cluster incomplete data with no need to impute the missing values, but also avoid randomness in choosing initial prototypes. To illustrate the accuracy of the established algorithm, traditional k-prototypes algorithm and k-prototypes employing the new dissimilarity measure are compared to the improved k-prototypes algorithm by using data from UCI machine learning repository. The experimental results show that the improved k-prototypes algorithm is superior to the other two algorithms with higher clustering accuracy.

The core of service product innovation is to understand the demands of users. Self-service technology has changed the contact mode between users and the service, thus the traditional way to acquire information of users’ demands could no longer meet the requirement of self-service product innovation. The advantages of data mining technology on analyzing and forecasting information can help reveal implication relations between users and products. It can also obtain the potential and valuable information of users’ needs and increase the success rate of product innovation. This study proposed a new self-service product innovation model, and it analyzed and explored the approaches using data mining technology in the process of self-service product innovation to effectively import users’ needs and organize product function design.

This paper concentrates on the issue of weather data mining. We propose a ARIMA algorithm based on Hadoop framework, and implement an effective weather data analyzing and forecasting system. We present the procedure to parallelize the ARIMA algorithm in the Hadoop environment, and construct a scalable, easy-to maintain, and effective weather forecasting system. Several experiments are conducted and results show that the proposed system is highly effective in terms of data storage, management, as well as query.

As correspondence analysis based on structured data ignores the important information contained in the text field of patent documents easily, this article combines text mining algorithms and corresponding analysis methods, and then uses the method to analyze enterprise technology competent advantage. This article describes the procedure of analyzing enterprise competitive advantage in detail. It takes the State Intellectual Property Office patent database as data source, analyses 210 authorized patents in optical communication and the top twenty applicants, gets the correspondence analysis figure.

With the development of the cloud computing, more and more enterprises migrate their application systems to the cloud computing environment, these systems need multiple data resource collaborative work, and integrate existing heterogeneous data storage system. This paper aiming at the massive data processing, proposes a kind of heterogeneous data resource management model. This model implement massive resources storage, massive storage network’ generation, update and balance of workload, proposes the security management and monitoring methods. The model proposed by this paper gives a novel solution to the heterogeneous data resource management and application in the cloud.

Accurate forecasting of electric load has always been the most important issues in the electricity industry, particularly for developing countries. Due to the various influences, electric load forecasting reveals highly nonlinear characteristics. The SVR model with Particle Swarm Optimization and Cross Validation is proposed according to the characteristics of the nonlinear electricity consumption data which are new Data Mining Techniques (DMT). In this model, PSO-CV method is used to the parameter determination. Then PSO-CV-SVR model is applied to the electricity consumption prediction of Jiangsu province. The result shows better than the ANNs method and improves the accuracy of the prediction.

In today’s communication system computer and information security is a major concern as these are vulnerable to potential attackers. Because to increase the potential of advanced computer communication and distributed systems leads to attack on the data flow over the network which affects integrity and availability of information greatly. Therefore, the security of Web applications is a key topic in computer security. This paper presents two hybrid approaches for modeling IDS. C5.0 and HMM are combined as a hierarchical hybrid intelligent system model (C5.0-HMM). Empirical results with KDD Cup 99 Intrusion data illustrate that the proposed hybrid systems provide more accurate intrusion detection systems.

In recent years, the Pareto/NBD model has gotten the favor of many scholars because of its accurate ability of predicting the future customer purchase frequency. Firstly, the paper analyzed the disadvantages of Pareto/NBD model; Secondly, the paper put forward an improved Pareto/NBD model which integrated the customer personalized information in order to resolve the problem in the Pareto/NBD model and improve the accuracy of prediction; Thirdly, the paper used the real sales data of a Dalian Mall as the sample, empirically tested the superiority of the improved Pareto/NBD model to the original Pareto/NBD model. Finally, this paper combined with the improved Pareto/NBD model and the Gamma-Gamma model to predict each customer lifetime value, and put forward the segmentation method based on CLV and management strategy, help the enterprises implement differentiated marketing and enhance the level of customer relationship management (CRM).