Earticle

The travel pattern is changing to provision of personal customized information through the mobile based tourism service due to distribution of Smart devices. Easy acquisition of the tourism information through mobile devices changes the existing tourism based on looking around to approaching the in-depth tourism information and the type of information also changes to various types such as game or mission carry-out from the simple information. This paper studied the methods to experience and acquire the educational tourism information through not only the provision of the simple information through the location based service of the tourist sites but also carrying out the mission using the location based sensors, Question typed game, joint solution and competing solution and designed and implemented a mobile game system to vitalize the culture tourism.

In this paper, a new road surface crack detection algorithm is proposed; it is based on the ridge edge detection on fractional calculus and the dual-thresholds on a binary image. First, the multi-scale reduction of image data is used to shrink an original image to eliminate noise, which can not only smooth an image but also enhance cracks. Then, the main cracks are extracted by using the ridge edge detection on fractional calculus in a grey scale image. Subsequently, the resulted binary image is further processed by applying both short and long line thresholds to eliminate short curves and noise for getting rough crack segments. Finally the gaps in cracks are connected with a curve connection function which is an artificial intelligence routine. The experiments show that the algorithm for pavement crack images has the good performance of noise immunity, accurate positioning, and high accuracy. It can accurately locate and detect small and thin cracks that are difficult to identify by other traditional algorithms.

The same activity under different user situations in the elderly care system may lead to different intelligent system response, since user needs vary with the changing situations. Activity awareness (AA) emphasizes that systems intelligently respond to user needs by aware the user-performed activities which is denoted and comprehended according to various user situations. But most current AA technics use similar patterns retrieved from the growing historical data, neglecting the situation change, called dataset driven. Thus, an aptly approach is needed in support of AA systems to handle various activity denotations in different user situations. Responding to the problem, this paper proposes an Ontology-based Problem-logic driven approach (OPL) to enhance the AA system by denoting user activities with the problem logic according to user-oriented denoted problem domains, where the AA system can seamlessly integrate with inferring for intelligent system response. Specifically, denoted problem domain and logic are proposed to support the OPL concepts, while activity graph is formed to support the intelligent system response based on the annotated problem logic. With the OPL, systems can directly target at the changing situations by rule-based inferring. A case study is performed upon the scenario retrieved from a European elderly care project, where a proof-of-concept prototype is established to confirm the validity of the OPL approach.

Nowadays, increasing number of people prefer to shop online which has become a central part in their daily life. However, this precipitates a need to get knowledge about how people show their interests in the product which may contribute to recommend the right product for them. In this paper, an experiment was conducted in a clothing website which aimed to find out how and when people were interested in certain product in terms of eye movement and browsing behaviour. The results show that for eye movement, there is no direct relationship between pupil diameter and interests, and user’s interests have direct correlativity with blink frequency for some users. Moreover, eye movement can predict the user’s interests, and the accuracy is about 62%; for browsing behaviour, scroll times and display time also has something to do with the user’s interest; as for the relationship between eye movement and interactive behaviour, when scroll times increases, then saccade will increases too, but fixation time will reduce. Therefore, the conclusion can be drawn that when users shop online, they always need to interact with online store, and eye movement and interactive behaviour occurs in a particular pattern. This result could contribute to choose the corresponding parameters for recommendation and avoid using the parameters which can reflect users’ interests in the same degree or choose the one which can reflect users’ interest effectively to greatest extent.

Discovery of investment focuses for ensuing handling is one of the fundamental parts of machine vision. Object order of pictures vigorously depends on investment point identification from which nearby picture descriptors are registered for picture matching. Since investment focuses are focused around luminance, past methodologies generally overlooked the color viewpoint. Later an approach that uses saliency-based peculiarity determination improved by a primary part dissection based scale choice strategy is created. It is utilized to lessen the affectability to changing imaging conditions, and hence it is a light-invariant investment point's location framework. Utilization of color expands the uniqueness of investment focuses. In the setting of item distinguishment, the human observation framework is regularly pulled in by contrasts between parts of pictures and by movement or moving articles. In this manner, in the feature indexing system, investment focuses give more helpful data when contrasted with static pictures. So we propose to amplify the above methodology for element feature streams utilizing Space-Time Interest Points (Stips) that uses a calculation for scale adaption of spatio-worldly investment focuses. STIP distinguishes moving questions in features and describes some particular changes in the development of these articles. A handy execution of the proposed framework accepts our case to help element streams and further it could be utilized as a part of uses, for example, Motion Tracking, Entity Detection and Naming applications.

Recommendation algorithm is a kind of method in information filtering and has been widely applied on Internet. Collaborative filtering is widely used in the recommendation systems and has turned out to be successful. With the growth of the resources, it is difficult for users to find learning resources that suit for themselves. The recommendation algorithm is required to analyze the behavior of the users and then recommend object of learning. Online judge is a kind of the online learning. People can evaluate their programming ability through online judge. The performance of the different recommendation algorithms is analyzed in this paper and it is proposed that the item-based collaborative filtering recommendation algorithms should be applied into the online learning system. Based on the algorithm, we propose that by pre-processing the data and using user data that have solve large number of problems, we can get a better recommendation result.

As cloud computing has emerged as a promising technique in mainstream application domains, significant attention has been paid to distributed video encoding, in which resource-intensive encoding tasks are distributed across unlimited computational resources available in the cloud environment. For distributed video encoding, the input video must be partitioned into several segments. This approach decreases the total encoding time but may suffer from quality degradation associated with a lack of information, such as the coding complexity of the previous video segment. In this paper, two well-known video partitioning methods are explored from different performance perspectives, including encoding time, bitrates, and peak signal-to-noise ratio (PSNR).

In this paper, we design and implement a three-tier salary management system for higher vocational colleges. At the beginning, we conduct an overview of the entire present situation of the salary management mechanism for the higher vocational colleges, and propose to improve the financial work efficiency of the higher vocational colleges by using ASP.NET based information management system. Then, we analyze the primary system requirements and divide the system into four functional modules, which are the salary management module, the system management module, the login module, and the query as well as report module. Next, for the system design, we present details about the use case design, the data process design, the business process design, the database design, and the design of architecture as well as modules. Last, we implement the system based on a three-tier architecture, which are the user presentation tier, the business logic tier and the data access tier.

Support vector machine (SVM) is biased towards the majority class, in some case dataset is class-imbalanced and the bias is even larger for high-dimensional. In order to improve the classification accuracy of SVM on high-dimensional imbalanced data, we combine signal-noise ratio (SNR) and under-sampling technique based on K-means. In this article firstly we apply SNR into feature selection to reducing the feature amount then solve the problem of data imbalance using under-sampling technique based on K-means. To verify the feasibility of the proposed strategy, we utilize some metrics such as receiver operating characteristic curve (ROC curve) and area under the receiver operating characteristic curve (AUC value).As a result, the AUC value increased by 4%~16% before and after the process. The experimental results show that our strategy is feasible and effective exactly.

In recent years, the global film market scale has been growing up year by year. As an important pillar industry of the digital content, visual effects boost the local economy greatly. Therefore, many countries and regions attach great importance to them and take them as the key supported industry. This paper, based on Porter’s Diamond Model, selects such industrial clusters of the most internationally-competitive effects - Hollywood, London and Wellington as the research objects, investigates the status quo of the world visual effects industry and comparatively analyses the factors of limiting industrial development, looking for long-term sustainable development strategy which can break the bottleneck of regional visual effects industry, and exploring branding strategies to strengthen regional effects industries in global competition.

The localization accuracy of the wireless sensor network node is improved by introducing the virtual anchor node, so the virtual anchor node is constructed and applied by many researchers to optimize the localization algorithm further. This paper presents the broad definition of the virtual anchor node and indicates its significance in the wireless sensor network node localization; the wireless sensor network node localization algorithm based on the virtual anchor node is introduced mainly in two aspects of constructing the virtual anchor node and its application in localization. The scheme for constructing the virtual anchor node includes the random construction method, the geometric constraint method, the node upgrade method, the network training method, etc. And the scheme for its application in localization includes the model reconstruction method, the rank sequence method, etc. By making a concrete analysis of the localization scheme based on the virtual anchor node, its future research prospect and its application development trend are put forward.

A portable navigation device is a portable electronic product, which has an important function in terms of positioning capability. In order to improve the positioning performance, an efficient portable navigation device is proposed in this paper. The proposed portable navigation device integrates the GPS receiver module and BDS receiver module, and then owns the GPS and BDS positioning capabilities simultaneously. In order to improve the performance of displaying the electronic maps, an efficient strategy based on the levels of detail is designed to display the electronic maps. A series of experiments are conducted and the experimental results show that the proposed portable navigation device can receive and analyze both the BDS and GPS data correctly, as well as the proposed strategy for displaying the electronic maps is better than the traditional strategy that displays all the map files at the same time.

Software effort estimation is the key task for the effective project management. It is widely used for planning and monitoring software project development as a means to deliver the product on time and within budget. So far, no model has been proved to be successful at effectively and accurately estimating software development effort. So it is useful to research a particular model for a particular type of project. This paper present an approach for small organic project, based on our previous work. Besides using Gauss-Newton model to calibrate the parameters of the COCOMO, using Fuzzy logic algorithm to optimize it, we also imply Deming Regression, Expert judgment, and Machine learning to improve this model. This model is based on historical project data. Experimental results show that the model is effective for software estimation. The accuracy comparison of each model is presented.

2D vector maps are very important data in geographical information systems (GISs). It is considered to be content for which verification of integrity and authentication are urgently required. Using a marking technique and a rotation, scaling and translation (RST) invariant watermark generation method, we propose a scheme that detects and locates malicious attacks with high accuracy while providing the RST invariance property. In particular, we propose setting a unique mark on each feature, calculating the authentication watermark for each spatial feature group by folding the hash results of the differences of the log-radiuses, and embedding the watermark using a RST invariant watermarking method. While the watermark ensures both the sensitivity to malicious manipulations and the RST invariance property, the mark of each feature provides superior accuracy of tamper localization. Moreover, this algorithm is immune to feature rearrangement and vertex reversing operations. Theoretical analysis and experimental results are provided to demonstrate the effectiveness of our method.

In this paper, we propose the caching technique to minimize the streaming for multimedia item and the service latency. As mobile ad-hoc network (MANET) has no fixed communication infrastructure, the route maintenance and the transmission management are important issues. Caching technique is used to improve the performance of data access. In the proposed caching scheme, mobile node stores the multimedia item passing through itself and the popular items delivered by the routing nodes located in 1 hop away from itself. We adopt caching policy based on LRU and the popularity and the block distance of multimedia items. In evaluation, we examined our proposed scheme in the view of the caching probability and the cache hit ratio as the function of the network size and the node density under the random waypoint mobility model. From simulation results, we confirm that the proposed scheme offers better performance substantially.

To perform missions assigned by people, the mobile robot needs to learn both itself and the world it is in, to use the learned knowledge to reason and make decisions to resolve problems, and to guide further learning, and to establish its knowledge base which contains huge amounts of common sense. During the process of executing missions by reasoning and learning, it is critical to enable domain-specific robots be more tolerant rather than puzzled when encountering perturbations. In this paper, active logic is improved to deal with contradicted beliefs, metacognitive loop is incorporated to supervise and guide the whole reasoning process. Finally, route crack experiments state that this metacognitive loop and improved active logic based method can handle robot commonsense reasoning in an efficient way and be comparatively robust with perturbations.

Image completion is aim to fill the missing regions in images. A robust completion technique using similarity analysis and transformation is proposed to address this problem. Firstly, in order to decrease the search space of patches, random mapping method is used to analyze texture regions which have similar structure and texture with damaged regions. Secondly, geometric and photometric transformations of image are adopted to find the best patches. Thirdly, increasing the accuracy of the structure propagation, a priority calculation method is optimized based on confidence factor and edge information. Finally, a number of examples on real and synthetic images show the effectiveness of our algorithm for image completion.

Disease conditions in the human brain can be detected by using medical image analysis. Content Based Image Retrieval of medical images can be used as an alternative to recognize the medical images of the human brain. In CBIR, feature extraction and recognition methods was an important feature because of medical image was different from the general image. In this study medical images that contain clinical information will be used as feature extraction using a canny edge detection and recognition features using non-negative matrix Factorization (NNMF). The purpose of this paper was to describe the use of canny edge detection and NNMF in CBIR. So CBIR could provide information on brain diseases and abnormalities. The results showed that the detection of disease in the human brain can be done by using both methods with good results if done preprocessing using histogram equalization.

We explore the idea of creating a classifier that can be used to detect presence of hate speech in web discourses such as web forums and blogs. In this work, hate speech problem is abstracted into three main thematic areas of race, nationality and religion. The goal of our research is to create a model classifier that uses sentiment analysis techniques and in particular subjectivity detection to not only detect that a given sentence is subjective but also to identify and rate the polarity of sentiment expressions. We begin by whittling down the document size by removing objective sentences. Then, using subjectivity and semantic features related to hate speech, we create a lexicon that is employed to build a classifier for hate speech detection. Experiments with a hate corpus show significant practical application for a real-world web discourse.

Chaotic diagonal recurrent neural network is optimized and proposed to predict ship rolling motion. Aiming at the traditional arithmetic deductions of each weight value mediate do not give the specific sample time, it makes some lacks in this kind of deduction, the paper tries to optimize sampling time, carried out the derivation of the weight training and a convergence theorem of each weight learn algorithm based on Lyapunov function is given and proofed. Simulation results demonstrate the use of optimal sampling times increases the accuracy of all of the weight and algorithm convergence, to advance predicted precision so that forecast time of ten seconds efficiently. obviously better than using feed-forward BP neural network to predict.

Recent studies on married immigrant women's cultural adaptation putting emphasis upon identity were concentrated upon the women's personal characteristics not to cognize values of environment surrounding the women. This study investigated cultural variety of the women's cultural variety depending upon country to find out entry into foreign countries such as international trade by participation in the society including corporate activities that differed from point of view of consumers. This study cognized the women's adaptation to lives in Korea from point of view of culture and adaptation by using viewpoints of adaptation between men and organizations that differed from precedent studies depending upon the women's adaptation to lives in Korea: And, the study selected factors of conjugation of characteristics of each country at personal level of the women so that the women's affirmative roles would help strategic marketers of the other country at global corporate environment in Korea.

As to the high request of low power consumption for hardware/software partitioning algorithm in multi-core processor structure, based on reducing the system power consumption, the relevant formal model was defined, and the problem was decomposed into two periods: the task division of heterogeneous multi-core platform and low power scheduling. The quantum genetic algorithm was proposed in the paper by taking the advantage of quantum computing combined with the traditional genetic algorithm, and the scheduling method based on critical tasks was used to solve scheduling problems of task after division. Experimental results show that the quantum genetic algorithm increases the diversity of population in the process of task partitioning and the task scheduling algorithm based on the key tasks determines the optimal execution order. The whole algorithm achieves the design goals of reducing the power consumption of the system and lessening the time complexity.

Nowadays, heritage is eventually inexistence, inaccessible and design decision due to the constructions of new buildings and sites. Various techniques in virtual reality have been proposed in producing virtual heritage. Improper management of virtual heritages in their virtual environments in terms of location and link may cause delivering information unsystematically. This paper is purposed to model virtual heritage environments for one case study of sheltered pavilion using Hierarchy-Embedded Virtual Objects technique. This technique is a hierarchical, tree-structured approach that emulates a tree structure with a set of linked nodes. Three different virtual heritage environments have been published through the tree structure in HEVO Editor. Organizing Editor has enables virtual heritages to be managed in terms of location and link. The resulted virtual heritage environments can be visualized, interacted and navigated through Viewing Editor. These virtual heritage environments are believed to be significant for learning the VH and presenting the values inculcated inside them. Challenges of the modelling technique, research quantification, modelling goals and VH attractions also have been discussed for advanced consideration to model VH.

The splicing and three-dimensional measurement of the hydraulic turbine blade is achieved in this paper. The large size of hydraulic turbine blades makes it impossible to take a complete picture of the entire blade. Multiple images of various segments must be obtained and then spliced together at later stages. Landmarks are installed in public area of the adjacent segments of hydraulic turbine blades, which are used when splicing segmental images together using least squares method, to obtain three-dimensional surface information ofthe entire blade. Based on the principles of the structure light measurement, a three-dimensional measurement system is designed, its parameters are also defined, and mathematical models of the three-dimensional measurement are established. The hydraulic turbine blade is simulated by using software package “3ds max” to build a hydraulic turbine blade model. Simulation of splicing and three-dimensional measurement of the hydraulic turbine blade shape is achieved. The reconstruction of the three-dimensional Hydraulic turbine blade is then obtained based on the measured data.

This paper mainly explores the use of Support Vector Machines (SVMs) for Uyghur text classification, presents the process of text categorization: Text preprocessing, feature dimensionality reduction, representation method and classification of text features etc., discusses the SVMs classification algorithm in the application of Uyghur text classification. Focus on the construction of text categorization model and its procedures. Experiment results show that training by using the selected training data with the guarantee of the performance of the classifier, has higher efficiency than other nearest neighbor classifier (KNN), Naive Bayes (NB) classifier with increased accuracy.

Elements of globalization in the world of education has expanded and developed, and made an Higher Education institutions market has been developed as a global phenomenon, so that Higher Education institutions aware to show their existence in global and high competition. The objective of this study was to apply data warehouse and data mining techniques that can be used by universities to obtain relevant information about their current condition, and to track the institution's development, which is required by the management to monitor organization performance in marketing area, and to support information in decision making process. The research method began with the collection of data and information, analyzes the current condition in marketing area, design the data warehouse model and mining the data. The obtained results were the data warehouse model and evaluation model using data mining technique to support the management in marketing decision-making process.

Welding sequence is the important influence factor of the temperature field and residual stress and deformation in welding structure, At present, determining the welding sequence is usually based on experience and test method. For complex structure it is very difficult to get the optimum welding sequence. This study is aiming to settle the problem of solving the optimum welding sequence of complex box welding structure. In our study, we take the welding deformation as objective function, and then, associate glowworm swarm optimization algorithm with thermal-mechanical coupling and nonlinear thermal elastoplastic finite element model to optimize numerical simulation, eventually the optimum welding sequence is determined. Optimization results demonstrate that the optimum welding sequence obtained by our method has small welding deformation and little change rate. At the same time, our method is faster, more accurate, more effective than the traditional experience or test method.

Bezier curve are very strong for variety of application. Specifically in image processing it applies to object recognition, face recognition, and human gait recognition. It also works on fingerprint and other biometric system recognition. This paper presents a work to recognize digital images of human frontal faces using the approximated Bezier curve and an intelligent process of learning using neural network. The main structural features of faces like eye, eyebrows, nose, lips, and Face boundaries are extracted and using minimum of these features face is recognized efficiently.