Earticle

The text representation, “bag of words” or vector space model, is widely used by most of the classifiers in text categorization. All the documents fed into the classifier are represented as a vector in the vector space, which consists of all the terms extracted from training set. Due to the characteristics of high dimensionality, feature selection algorithm is usually used to reduce the dimensionality of the vector space. Through feature selection, each document is represented by some representative terms extracted from the training set. Although the classification results based on this document representation methodare better, it is inevitable that some documents may contain few even none representative terms, and these documents must be misclassified. In this paper, we proposed a new text representation method, KT-of-DOC, which represents one document using some key terms extracted from this document. We selected key terms of each document based on six feature selection algorithms, Improved Gini Index (GINI), Information Gain (IG), Mutual Information (MI), Odds Ratio (OR), Ambiguity Measure (AM) and DIA association factor (DIA), respectively, and evaluated the performance of two classifiers, Support Vector Machines (SVM) and K-Nearest Neighbors (KNN), on three benchmark collections, 20-Newsgroups, Reuters-21578 and WebKB. The results show that the proposed representation method can significantly improve the performance of classifier.

Regression testing is an activity during the maintenance phase to validate the changes made to the software and to ensure that these changes would not affect the previously verified code or functionality. Often, regression testing is performed with limited computing resources and time budget. So, fully comprehensive testing is not possible at this stage. Test-case prioritization techniques are applied to ensure the execution of test cases in some prioritized order and to achieve some specific goals in minimum possible time like, increasing the rate of fault detection, detecting the most critical faults as early as possible etc. The main objective of this paper is to achieve higher value of average percentage of faults detected, execute the higher priority test cases before lower priority test cases and also we target to decrease the execution time for achieving the maximum value of average percentage of faults detected. We proposed a new prioritization technique that uses a clustering approach and also considers various factors like, execution time of every test case, code coverage metric, fault detection ratio, test case failure rate and code complexity metric to reorder the execution of test cases. The results of this research work will show the importance of clustering technique and various factors taken into consideration, for achieving effective prioritization of test cases. The results of implementation will subsequently show that the proposed approach is more effective than the existing coverage and clustering based prioritization techniques. From the experimental results, we found that our proposed approach achieved higher value of average percentage of faults detected than other clustering based and coverage based techniques. Also, this approach reduces the execution time taken by the prioritized test cases.

For onboard single-station passive direction-finding and location, if there is any abnormal error in the observation data, the extended Kalman filter (EKF) algorithm adopted thereby will cause inaccurate location result. In order to improve algorithm robustness, the robust equivalent gain matrix is constructed according to the standardized prediction residual error and the robust EKF algorithm is applied to the onboard single-station passive direction-finding and location. In allusion to the low efficiency of the robust EKF algorithm, the single-station passive location algorithm based on the improved extended Kalman filter is proposed in this article on the basis of combining F distribution statistic, and meanwhile single abnormal error and continuous abnormal error are added in the observation value to test the algorithm resistance to different abnormal errors. The simulation shows that the algorithm proposed in this article can well weaken the influence of abnormal errors on position estimation and the algorithm based on F distribution discriminant can improve location efficiency.

In the present scenario most of the organization depends on the internet for their communication, storage and protection of their valuable data and other internal resources from the unauthorized access as the importance of internet is increasing rapidly the chances of attacks also increases in the ratio. Intrusion Detection System plays a very important role in network security. Its main role in the network is to help computer system to create and deal with network attacks. An IDS acts as a key component to ensuring the safety of any network or system on which it runs. IDS works on the concept of investigating all the incoming packets for the detection of any malicious activity. This is a survey paper on the various enhancements over the decades on IDS. Snort is a lightweight and open source software which used signature based IDS. In the survey, we used BASE for providing graphical interface for displaying the result. Its used world widely in Intrusion Detection and Prevention.

In cloud computing environments, the database is dynamic and real-time features, and in data access it has been a Gordian knot of cloud computing research; because in the ant colony algorithm that ants finding food shares similar correlation with cloud computing node finding the access to the database. Therefore, the introduction of ant colony algorithm into cloud computing database, the introduction of the chaos function in the pheromone update, both will make the improved pheromone avoid the possibility of getting into local convergence, and hence improve the efficiency of database access in the cloud computing, reduce the load in the cloud computing. The simulation results show that the algorithm in this paper has been significantly improved in terms of cloud computing network queries and database consumption, and greatly improved the efficiency of cloud computing.

Coffee plant is a plant whose seeds called coffee beans are grown in all over the world particularly in Ethiopia. The research focuses on three major type of coffee disease which occurs on the leave part of a coffee plant, these are Coffee Leaf Rust (CLR), Coffee Berry Disease (CBD), and Coffee Wilt Disease (CWD). The aim of this paper is recognition of the three types of coffee disease using imaging and machine learning techniques. The image of Coffee plant diseases were taken from the regions of Ethiopia where more coffee is produced i.e. Southern Nations, Nationalities, and Peoples, Jimma and Zegie. In this paper artificial neural network (ANN), k-Nearest Neighbours (KNN), Naïve and a hybrid of self organizing map (SOM) and Radial basis function (RBF) are used. We conduct experiment for each group of feature set in order to get a highly correlated and the more representing features. The total number of data sets is 9100. From the total of 9100, 70% were used for training and the remaining 30% were used for testing. . In general, the overall result showed that color features represents more than texture features regarding recognition of coffee plant diseases and the performance of combination of RBF (Radial basis function) and SOM (Self organizing map) is 90.07%.

Based on the operating status and growth level of the agriculture listed companies in China, this paper makes a study on the growth of the agricultural listed companies from their panel data of 2013 Annual Report. And the enterprises profitability is one of core elements to make the corporate financial analysis; corporate capital structure directly has an effect on the business performance and long-term development. This paper conducts 4 indicators which mainly affect the profitability of enterprise, uses the method of factor analysis to make the comprehensive evaluation score on the 18 representative agricultural listed companies in China. As the asset-liability ratio is a main indicator to reflect the capital the structure, the correlation analysis and regression analysis are carried on between the profitability and the asset-liability ratio of the enterprise. Finally the study analyzes the relationship between profitability and capital structure of the agriculture listed companies, and it shows that there is a slight negative correlation on them.

Kernel K-means clustering (KKC) is an effective nonlinear extension of K-means clustering, where all the samples in the initial space are mapped into the feature space and then K-means clustering is performed based on the mapped data. However, all the mapped data are expressed by the implicit form, which causes the initial cluster centers can’t be selected flexibly. Once the selected initial cluster centers aren’t suitable, it tends to fall into local optimal solutions and can’t guarantee stable result. Based on a standard orthogonal basis of the sub-space spanned by all the mapped data, a novel improving non-linear algorithm of KKC is presented in this paper. The novel algorithm can express the mapped data using the explicit form, which make it very flexible to select the initial cluster centers as the linear K-means clustering does. Moreover, the computational complexity of the presented algorithm is also significantly reduced compared to that of KKC. The results of simulation experiments illustrate the proposed method can eliminate the sensitivity to the initial cluster centers and simplify computational processing.

Cloud computing is a new generation of computing based on the layered model which provides different services to cloud customer. Conceptually, cloud computing offers a scalable platform for Big Data Analytic Applications (BDAAs) which can elastically provision resources based on data growth and complexity of analytic applications. This complexity of analysis increases with vast volumes of data in big enterprises which prefer effective and fast decision-making. Therefore, the importance of Service Level Agreement (SLA) is appeared which clarifies the roles between a customer (i.e., cloud user or Big Data analyst) and a provider for particular service provision comes. The main components of the SLAs are Quality of Service parameters which must be monitored to achieve a set of Service Level Objectives (SLOs) and detect violations. Indeed, many SLA management approaches have been developed as solutions for preventing SLA violations to avoid costly penalties. Consequently, many interesting solutions developed works of SLA violation management in cloud technology and cloud-hosted BDAAs. A survey about the existed works in terms of idea, strengths and weaknesses is introduced in this paper. Meanwhile, the challenges and new research directions in this area which require further investigation will be discussed to provide a comprehensive overview and big-picture.

As more and more intelligent sensors and sensing applications are equipped with, smartphones are becoming smarter and play a greater role in people's lives. However, due to mobile platform diversity, the development and deployment of a context-aware application for different mobile devices are time-consuming and expensive, which in fact limits the large-scale application of context-aware technology in mobile heterogeneous environments. Unlike native applications, web applications are easy to develop, upgrade and deploy, and almost all smartphones today include a web browser for supporting running them. Another difference is that native applications can capture context information by accessing sensors available on the mobile device, but web applications running in the browser cannot. In this paper, we describe CaMWAF, a framework designed to support the rapid development of context-aware mobile web applications and simplify the exchange of context information in heterogeneous environments. With CaMWAF, developing a context-aware application is no longer a difficult and time-consuming task. In consideration of the resource limitation of mobile devices, the proposed framework delegates the computationally expensive tasks to the server, while enables the context-aware mobile applications to query and subscribe high-level context information in an easy and lightweight manner.

The value of offline data is continuously realized due to the rapid development of GPS, GSM and Wireless Sensor Technology. The Mobile Internet has become more common and with the advancement of technology, people have become more dependent on the mobile intelligent terminal. The Advertising model is influenced subtly by changes to the audiences’ lives and online patterns. Location Based Social Networking Services promote the precision advertising model into being, which is based on mobile internet. This paper used the methods of trajectory mining and POI clustering to create activity mapping table based on the users, location track data, then established user behavior feature model and built an advertising platform to implement precision advertising.

Inscriptions are the main source of historical study available throughout the world in constricted language. Epigraphy is the study of such inscriptions and the one who reads and understands (epigraphists or epigraphers) are in extinct condition, due to lack of knowledge transfer and interest. New inscriptions are found during excavation and finding expert epigraphers these days is a real challenge. Due to this, Researchers from the digital enhancement domain are actively involved in the decipherment of inscriptions all over the world. Automation Techniques uses Optical character recognition to convert the inscriptions into intelligible language. Currently works are witnessed in the literature survey on the global languages like Greek, Italian, Japanese, Russian, Latin, Iranian and Indian languages like Kannada, Tamil, Devanagari, Brahmi, Hoysala, and Pali. This paper reviews the techniques followed in automation of epigraphical scripts.

K-aggregate nearest neighbor query method of mobile objects in road networks is studied. Moving state model of object is introduced, and road network distance calculation formula is provided. Besides, this paper designs a kANN query algorithm that can find out the previous k target nodes with the smallest aggregate function value among multiple target nodes for various query points when query points and data points are under moving state in road networks. The candidate results are cut short via pruning method. Finally, performance of the algorithm is verified through simulation experiment, and results of the simulation experiment prove that this algorithm has high efficiency and accuracy.

The fast-developing Chinese higher education and research institutions are faced with more and more serious challenges in their financial regulation. Traditional accounting approaches may fail to distill useful decision-making suggestions confronted with the multi-species and huge-quantity financial “big data”. To reveal valuable information, this research focuses on the pattern recognition of the funding flows in 76 universities under Chinese Ministry of Education. Given the trend feature of the data series detected by the Mann-Kendall Non-Parameter Ranking Test, the low-frequency parts of the funding flows are distilled with wavelet transform to represent their basic features. Results show a clear hierarchy structure in the investments and expenses of universities according to their “titles” and advantage disciplines. Specifically, the comprehensive universities fall to different categories according to their “titles”, while the professional universities are classified according to their disciplines. The scientific and technical focused universities show larger variance among different categories than other specific discipline focused universities.

Multi-objective optimization (MOO) is the procedure of all the while streamlining two or all the more clashing objectives subject to specific requirements. Genuine building outlines regularly contain more than one clashing objective function, which requires a MOO approach. In a single objective optimization (SOO) issue, the ideal solution is clearly characterized, while a group of exchange offs that offers ascend to various groups exists in MOO issues. Every solution indiactes to a specific execution exchange off between the goals and can be viewed as ideal. In this paper introduces an overview on MOO and MOEA produces a solution of non-dominated (ND) solutions toward the end of run, which is called a Pareto set. An examination of Pareto strategies alongside their focal points and weaknesses and exploration take a shot at MOP utilizing distinctive systems.

Data mining is a complex systematic engineering. For complex systems that is influenced by multi indexes, the relevance, hierarchy and fuzziness among indexes pose great challenges to data mining of complex system. Therefore, the paper proposes a multi-index grey relational data mining model of complex system based on grey system theory. First, the paper constructs index sets and grey categories for data mining objectives, and, under the different grey categories, builds up grey classic domain and grey partial domain for the aforementioned index sets. Next, normalized processing is undertaken to unify scales of different kinds of insets, whose weight generating algorithm is also provided herein. The paper then establishes a grey relational coefficient model and a grey relational degree model whose value is used to obtain the grey categories of the data mining objectives. Finally, the paper verifies and expounds multi-index grey relational data mining model by applying it to real-life practice. The results show the effectiveness and feasibility of this model.

Mining association rules is an important research direction in the field of data mining. Related studies have proposed many used to efficiently find large-scale database association rules algorithm, but the research on maintenance problem of association rules is less. Especially many transaction database is always in constant updates. Increase or decrease occurs when the database or dataset minimum support after the change, how to maintain the association rules have been, it got the attention of many researchers. Based on IFP-Growth increment of association rules mining model and to modify the FP-tree, put forward the suitable for transaction data and support the tree model of change, at the same time under different conditions is given incremental association rules mining algorithm, and reduce the frequency of the original dataset range query and query, and in a case of massive dataset multi-level tree structure decomposition, dynamic allocation rule tree branches, ensure load balancing, improve operation efficiency.

With the development of foreign tourist trade, market requirements for professional tour guides is getting higher, and bilingual talent is getting more and more attention. In this paper, the author constructs a three-dimensional teaching system of tourism management major, and analyzes the teaching effect of tourism management practice by using online survey. The results show that the most expected achievement of students in the internship process is practical experience; the second is the management ability and interact ability. In the practice teaching of tourism management, it shows that the course set up rate of tour guide simulation is 68.8%, service skills training is 36.3%, most students are satisfied with the tourism practice curriculum. Therefore, in carrying out the practice teaching process, college should pay attention to the integration of the practice teaching system of Tourism Management.

Aiming at the low accuracy of stereo matching algorithm caused by the larger gray change, an improved algorithm is proposed. Sobel operator is used to compute the gradient of pixels. Based on the gradient histogram, the adaptive thresholds are derived and the support window is determined automatically. The neighbor pixels are compared with the average of all pixels in the window instead of the center pixel to complete the census transform. The disparity image is abtained through searching the best match point in the left and right images. The hardware implementation with parallel procssing is elaborately designed to improve the capability of the large data processing and computational efficiency based on FPGA. The experimental results show that the improved scheme and hardware structure can obtain disparity map with higher accuracy and stronger robustness.

Android is an Operating System that is more powerful supporting a large number of smartphones. Android applications are developed using Java, and so it can be easily ported to the new platform. The primary aim of introducing PHP Android application is that the extension of data storage from SQLite to the MySQL. Here the PHP is used to fetch the data from the MySQL database at the web server. The PHP page will use JSON parsing for reading the data from the database. Here there will be communication between PHP and Android application. The PHP page will contact MySQL database and will fetch the data and returns the result. Our e-municipal is designed to automate the activities of Municipal Corporation that deal with different day to day general public amenities. The primary aim of this application is to ease the user to communicate with Municipal Corporation via a handheld Android application. The general user can easily register themselves and quickly send a petition to the municipal corporation regarding the problems they face in Metro water connection, sanitation and electricity maintenance. They can quickly record the birth and death and also can check their complaint status. The user can also view the tender which is applied by the municipality and can apply for it. Corporation officers and employees can see all the complaints from different users on different problems. Only the admin have the power to change all the data from the user. Here the tender allocation was based on spatial data mining algorithm rather than traditional clustering algorithm.

In recent years, with the development of the information industry, we ushered in the age of big data, more and more Internet and mobile products are popping up. According to the mobile device is portable, real-time etc, the development of mobile phone system become the focus of scientific and technological development, but the research on its local database is relatively small. This paper introduced a query optimization method based on improved Particle Swarm Optimization algorithm (PSO) for SQLite database on Android platform. This method improves the original PSO, and put the database transaction into the Particle Swarm Optimization algorithm, and should be used to join query. It improves the speed of complex query, and optimizes the query on SQLite database. Experimental results show that this method is an effective way to optimize the SQLite database query, and also can be used in the Android platform.

In this paper, a novel solution and application of the red Y2O3:Eu3+ dopant phosphor for enhancing color rendering index to more 86 for multi-chip white LED lamps (MCW-LEDs), which have correlated color temperature (CCT) of 7700 K, 6600 K, 5600 K, are presented. Then the effect of the concentration of Y2O3:Eu3+ phosphor on the color rendering index (CRI) is simulated, analyzed and demonstrated. After that the lumen output of MCW-LEDs depended on concentration Y2O3:Eu3+ phosphor is discovered. The lumen output has a decrease tendency at large weight range due to the enhancement extinction coefficient, according to Mie-scattering theory. Simulation results provided important conclusions for selecting and developing the phosphor materials in MCW-LEDs manufacturing.

With the development of social economy, the life cycle of the product is becoming shorter and shorter. Online shopping provides more convenient channels, but also produces the problem such as the return, when the returned products in the reverse logistics chain flow, how to calculate the logistics cost and improve customer satisfaction is very important. In this paper, the author analyzes the operation mode and the characteristics of the reverse logistics network, and makes an evaluation of the performance of the reverse logistics network in 24 provinces of China by using DEA model. The results show that the technical efficiency and scale efficiency in 8 provinces is equals as 1, and that means reverse logistics network is DEA effective. At the same time, we put forward the corresponding improvement measures for the situation of reverse logistics network in Sichuan province.

This paper introduces three core modules of query reformulation engine, mapping document, query reformulation module, and statement conversion module. Mapping document is an XML document that keeps the mapping information between local data source and related data sources; using mapping document, applications could find data sources that have mapping relationship with its local data source. The query reformulation module reformulates the query statements submitted by users to local data resource to query statements to all data sources that have mapping relationship with local data resource. The statement conversion module converts XPath statements to OQL statements that are supported by OGSA-DQP; through OGSA-EDAI in the bottom layer, the access result to the data sources could be obtained. When a user submits an XPath statement to OGSA-DQP, it calls the query reformulation module, which first checks the mapping document to find information of other data sources, then expands and reformulates this XPath statement into query statements that are suitable for the mapped data sources. Afterward, the statement conversion module converts the reformulated XPath statements into OQL statements and returns to OGSA-DQP, which then performs the query operation.

In the past few years, microblogging websites have evolved to become a source of varied kind of information. Twitter is a popular microblogging website where users create short status messages called ‘tweets’. In this paper, we present a state-of-the art model trained using a support vector machine with Bag-Of-Words and TF-IDF features for each tweet. The proposed model provides a visual and an auditory representation of the sentiments that the tweets have been classified into. The results show a state-of-the art performance achieved by the model with a F1 measure of 77.47 and an accuracy of 77.93% which is better than the existing models.

Mining association rules for data is not only an essential part of data mining but also a hot issue in knowledge engineering and researches on data mining technology. Since multi-data mining is characterized as being multi-type, multi-level, multi-implicational and complicated, the efficiency of multi- data association rule mining usually cannot be high, precision and accuracy are of a relatively low degree, and the targets of mining cannot be obtained quickly. Therefore, on the basis of improving traditional association rule mining algorithm, this paper researched on multi-data association rule mining algorithm and based on grey relational analysis, proposed a multi-data association rule mining algorithm. Firstly, the associate objects most relevant to the target objects are obtained through the grey relational analysis, which helps to form single- or multi-target data associates; after that, the multi-data association rule mining model which sets data associates as the new mining objects is established. Under the conditions that the level of support and confidence are met, the frequent patterns of corresponding data associates and further, the multi-data association rule, are obtained. Simulation experiments implied that the model have the advantages of simplicity, practicality, operability, decent precision and accuracy.

In recent years, research in data provenance has attracted a lot of attention, since it helps to judge the relevance and trustworthiness of the information enclosed in the data. However, many webpages still lack provenance annotation, and this is a main obstacle of tracing the content. In this paper, we propose a model for on-line Web paper variation, based on the W3C PROV Data Model. A semantic similarity clustering method is adopted to determine the relationship within the documents derivation, and feature words variation and the responsible person can be found with the aid of PROV-O. To verify this model, a detailed case study is shown in this paper.