Fuzzy trend models have been proposed to represent the trend in time-series.A model for multivariate time series is also provided. These models are based on fuzzification of the step function. Then a number of parameters may become large and the shape of trend becomes unnatural sometimes. In this study a generalized model is proposed for representing trend naturally by fewer parameters. An estimation method for the proposed fuzzy trend model is provided and its applicability is shown by simulation studies. A practical application to financial time series is also demonstrated.

View full abstract

In pattern recognition, feature selection is a quite important process for constructing practical systems. However, because there are many features as candidates to recognize object, it is difficult to select appropriate features for pattern recognition systematically. The previous research proposed a pattern recognition method using the ensemble system based on fuzzy classifier for multiple feature selection. However, this method can not apply for the problems with many input vectors because it takes a lot of time for learning when the number of the input vector increases. In this study, an attempt is made to overcome the problem by introducing ID3 (Iterative Dichotomizer 3) with classifiers consisting of many feature vectors. ID3 constructs the decision tree for multiple feature selection with the results obtained from classifiers based on each feature. Therefore, it is possible to select appropriate features applied many input vectors. Several benchmark problems are presented to demonstrate the efficiency and applicability of the proposed method.

View full abstract

In this paper, we discuss an approach of heuristic attribute reduction from large-scale data based on rough set theory and statistical methods. Attribute reduction is one of the most important research topics in the aspect of reasoning from data based on rough set. However, because of high computational complexity of attribute reduction, it is severe to directly apply attribute reduction methods to data with numerous samples and attributes. To solve this issue, in this paper, we introduce a hybrid method of a statistical approach of attribute reduction that was originally proposed by Bazan et al. and a heuristic attribute reduction from a decision tables with numerous attributes that was proposed by the authors.

View full abstract

Multivariate time series such as stock prices may be classified into some groups. The trend of group may have each tendency. A multivariate fuzzy trend model can decompose trends into a common trend and individual trends. However, the existing model does not take account of the trends of each group. Therefore, we propose a model which can decompose trends into the common trend, trend of each group and individual trends. The applicability of the model is shown by simulation studies. In addition the practical application is provided by using stock price data.

View full abstract

Neonatal cerebral disorders such as hypoxic-ischemic encephalopathy might deform brain shape, and reduce cerebral function. For cerebral disorders diagnosis, it is effective to measure cerebral volume and surface area using head magnetic resonance (MR) image. The measurement requires a brain segmentation process. However, an automated segmentation algorithm has not been established. This study proposes a new brain segmentation method in newborn head MR images. The proposed method uses a fuzzy object shape model, which is produced from some learning datasets. It segments the brain region by maximizing a fuzzy degree of a fuzzy deformable contour model based on the fuzzy object shape model and MR signal. The fuzzy degree is estimated by using expert knowledge of the brain MR images. In order to validate segmentation accuracy of the proposed method, we applied the proposed method to 12 newborn subjects. Subject's revised ages were between -1 month and 1 month. In 12 subjects, 9 subjects were used for creation of the fuzzy object shape model. And, the remained subjects were used for evaluation. The segmentation accuracy has been evaluated by using sensitivity and false-positive ratio, which were calculated by comparing with delineation result (ground truth).

View full abstract

Various approachs are done at the popular level in order to prevent global warming and reduce carbon dioxide emissions. A green curtain is one of them. It is important to continue the environmental practice that can be conducted at home like this. In this study, we do the consciousness analysis for growing the green curtain. We interviewed people who had growed the green curtain. Also, the obtained interview data was visualized by using the key graph, and relations to the continuousness of growing green curtain were extracted. Obtained knowledge were used to create questionnaire for consciousness analysis of green curtain.

View full abstract

Car racing game is a game of computer programs in IEEE 2007 Car racing Competition, where two car agents compete with each other for taking waypoints in a two-dimensional real-number plane. We have proposed a method that a car agent gradually learns its actions through several stages with fuzzy Q-learning from the initial state that it does not know how it acts. In the previous research, we introduced four stages where waypoints only appear forward, left and right, backward, and in a small range. We got a good result. However we could not analyze completely how four stages effect on the result. In this paper, we propose improved stages and their combinations based on our research result, and investigate the relation between scores and stages to get high scores. As a result, we get higher scores when we combine stages where a car agent learns actions such as turn quickly after it gets score and put on the brake after it turns. We design stages for a car agent to learn mainly these actions, and can get the best results.

View full abstract

In system design and development, abilities to combine related knowledge and to optimize are necessary. At the same time, it is important for developers to recognize problems and solve them logically. In College of Technology, not only classroom lecture but also many experiments and exercises have been introduced to cultivate practical engineers. Normally, that manufacture-type exercise is conducted in higher grades because it requires basic knowledge. However it is expected that such exercise for students in the lower grades enhances the logical mind for problem solving in the early stage of engineer education. Authors have conducted the exercise aimed at robot contest for lower grades in College of Technology. We have prepared the environment that students can concentrate on the manufacturing based on logical mind. For example, block-type robot provides easy setup has been adopted to reduce advance knowledge about mechanisms and electric circuits required in robot manufacturing. Moreover, we have used check sheets that make students aware of logical mind and effect verification of individual thought. In this paper, the validity of this educational method is proved by replies for assignments and the result of questionnaires.

View full abstract

Generative Topographic Mapping (GTM) is a nonlinear latent variable model introduced by Bishop et al. as a data visualization technique. The GTM uses the EM algorithm to obtain the maximum likelihood estimate. However, maximum likelihood estimation is prone to overfitting to training data. In this paper, we focus on a variational Bayesian approach to avoid overfitting, and we propose the GTM algorithm using the variational Bayesian approach.

View full abstract

We apply the action sequence search framework using tree search methods, that has already been realized in the simulated soccer domain, to the action game agent control task. In order to realize the online action sequence planning using the framework, we try to design a suitable action space and evaluation function for the action game agent.

View full abstract

Video Games are not only an important products but a good test bed for Realtime AI methods. In this paper, we modeled them as a imperfect information theoretical game.

View full abstract

In a process of cluster extraction by using Self-Organizing Map(SOM), information criterion such as AIC make it possible to improve the accuracy of cluster estimation. Furthermore, the number of clusters also can be estimated by using the information criterion. However, accurate estimation of the number of clusters is difficult when clusters have significantly different cluster-sizes and densities each other. In this paper, we examine the application of the information criterion to the cluster estimation process by which we try to resolve this problem.

View full abstract

In this paper, we propose an interactive fuzzy decision making method for fuzzy random multiobjective linear programming problems(FRMOLP), in which the criteria of probability maximization model and fractile optimization are considered simultaneously. In the proposed method, it is assumed that decision maker has fuzzy goals for not only permissible objective level of a probability maximization model but also permissible stochastic level of a fractile optimization model, and such fuzzy goals are quantified by eliciting the corresponding membership functions. Using the fuzzy decision, such two kinds of membership functions are integrated. In the integrated membership space, Pareto optimality concept is introduced, and the satisfactory solution of the decision maker for FRMOLP is obtained from among a Pareto Optimal solution set on the basis of linear programming technique.

View full abstract

RoboCup Soccer Game sets a goal that robots play soccer game with human player with human rules. The goal requires that robot players identify other player by sensors with equivalent abilities of human. We propose a system based USRASim that simulates soccer games by robot players with camera and present the result of games of 11 vs 11 robots used RoboCup Mixed Reality League.

View full abstract

Impressions of combinations of lighting patterns, lyrics and music are analyzed for designing the system which generates the theatrical effects using lighting patterns, lyrics and music based on adjectives representing producer's impressions of story scenes. Impression spaces of lighting patterns, lyrics and music are constructed by factor analysis using data obtained by pre-experiments. Lighting patterns, lyrics and music are generated according to the coordinates in the impression spaces of lyrics, music and lighting patterns, where the coordinates are estimated using the concept of co-occurrence of inputted adjectives. In this paper, subject experiments are performed to analyze the interaction of combinations of the lighting patterns, lyrics and music. The following four combinations are considered: (1) combinations based on same adjectives, (2) combinations based on counter adjectives, (3) combinations based on similar adjectives, (4) combinations based on dissimilar adjectives. Experimental results show that combinations (1),(3), and (4) are effective as theatrical effects of story scenes.

View full abstract

Generally it is accepted that a user interface is very important for any applications and environment (Parsaye, K., et al., 1992.). Especially, the pairwise-comparison data of AHP is the most important element in AHP, and it makes time and effort applied to a decision maker. Furthermore, whenever it replies to a long time question, it is easy to be patternized, and the value of CI(Consistency Index) often becomes high. In this paper,we identify that the pairwise-comparison interface of AHP affect to the value of CI and then developed the new interface which is more nearly intuitive and is hard to be patternized.

View full abstract

Recently, There has been much work in the area of co-evolving morphology and control of autonomous robots. However, most work in this area remains acquiring simple motion like walking because of using primitive components such as cylinders and servo motors. We consider optimization method for combining and controlling "functional components" like wheels and joints with motors. Our method is based on Real valued Flexibly Connected Neural Network (RFCN). This paper describes the motion of autonomous robots acquired in a virtual three-dimensional space simulating physical law. We also show the motion of a real robot based on the result of simulation.

View full abstract

The mixed reality soccer system is interesting platform for education of embedded software and AI. But, the behavior is not stable. In this paper, we discussed recognition and communications of robots.

View full abstract

It could be unsafe for the visually impaired to train themselves to walk even with the help of assistant people. It could hardly be possible to eliminate the probability that they might fall down or bump into something. "Walk training simulator" is to be developed, which has a bipedal robot and utilizes haptic. The visually impaired are to be able to experience real walk training safely and repeatedly without any assistant people. It is certain that this simulator will help them to train themselves to walk in advance, safely, in a short time and effectively.

View full abstract

The parallel evolutionary P2P networking technique, which we previously proposed, divides all nodes composing a large-scale P2P network into multiple node groups, and then reconstructs the network topologies by an evolutionary algorithm in each node group. In this technique, a timing at which a set of network topologies (a population of the evolutionary algorithm) is evaluated and then reconstructed by evolutionary operators is the same for all of the node groups. However, this simultaneous evaluation and topology reconstruction has been shown to be not effective in terms of adaptation of the network topologies to users' (nodes') demands in our previous study. Therefore, in the present paper we propose a method that makes all the node groups evaluate and reconstruct a set of network topologies serially. Simulation results show that the proposed method indeed improves the performance of the parallel evolutionary P2P networking technique.

View full abstract

In this study, we are aimed for the construction of the Driver Preference Route search system for the individual driver. We used Fuzzy-AHP to correspond to the vagueness and diversity of the preference. The importance scale of AHP represents the judgment of human awareness by words. And the words are expressed quantitatively by numbers. In this paper, we introduced the Approximate Scale which properly reflect the judgment of human awareness, and showed the effectiveness by the route search results.

View full abstract

In this paper we first assume a peer-to-peer (P2P) network composing nodes with a variety of functions and then propose a method for each node to create new functions by combining others' functions in a P2P network. In the proposed method, a node (user) that desires a new function first creates a candidate of new function combining others' functions by using a source routing method that determines a next hop node based on numerical operations. Next, the node evaluates the created new function candidate and then genetic operators of a genetic algorithm adjusts parameter values used by the source routing method based on the user's evaluation value. Thus, new functions desired by a node are created by repeating the source routing for creating a candidate of new function, evaluation of the new function candidate by a node, and adjustment of the routing parameters by genetic operators. We show basic effectiveness of the proposed method through simulations.

View full abstract

In the field of self-organizing maps (SOMs), a distance measure is one of essential factors for developing the feature map. The Euclidean distance measure is the most popular one, but it is also known that alignment of any training patterns will be change depending on how to define the measure. In the preceding studies, whose primal objective is pattern generation by a trained SOM, a fragmentized distance measure is introduced to generate some distinct intermediate patterns. Even though only symmetrical patterns, i.e., emoticons, are used for training, some asymmetrical patterns are contained in the generated patterns. Then, as a next step, further considerations are carried out in this study. As a result, it is confirmed that i) a sub-map corresponding to each fragment is developed independently at first, ii) all sub-maps are integrated into one, and iii) it makes possible to contain a variety of patterns in the entire feature map.

View full abstract

In addition to fuzzy $c$-means clustering, possibilistic clustering is well-known as one of the useful techniques because it is robust against noise in data. Especially sparse possibilistic clustering is quite different from other possibilistic clustering methods in the point of membership function. We propose a way to induce the crispness in possibilistic clustering by using $L_1$-regularization and show classification function of sparse possibilistic clustering with crispness for understanding allocation rule. We, moreover, show the way of sequential extraction by proposed method. After that, we show the effectiveness of the proposed method through numerical examples.

View full abstract

We propose the Web retrieval supporting system which recommends the keyword used for the next.This system shows a user of what kind of subject search results contain the page using the word contained in a snippet.The keyword to recommend is determined when a user chooses the subject which he is searching for.SOM is used for extraction of subject and a decision tree is used for keyword selection.

View full abstract

The Takagi-Sugeno fuzzy system is widely used for nonlinear control systems design because it can represent a class of nonlinear systems. The Takagi-Sugeno fuzzy system representation is based on a set of local linear systems, and its control design employs linear control laws locally. In some cases, however, such control laws may not be perfect, and another control design may be desired.

View full abstract

In data mining approach, the quantitative attributes should be appropriately dealt with as well as the Boolean attributes. This paper presents an essential improvement for extracting fuzzy association rules from database. In this paper, we define equivalence of fuzzy itemsets and related theorems as a new concept for fuzzy data mining. Then, we propose a basic algorithm based on the Apriori algorithm for rule extraction utilizing equivalence of the fuzzy itemsets based on redundancy concepts of fuzzy association rules. The essential performance of the algorithm is evaluated through numerical experiments using benchmark data. From the results, the method is found to be promising in terms of computational time and redundant rule pruning.

View full abstract

In this paper, we propose a method used to code recipe data based on a recipe's cooking process and the quantity of its nutrients. A recipe coding method has been proposed in a preceding study; however, it has two problems. The first problem is that the recipe data do not contain information about the cooking process. The second problem is that the recipe data do not consider how the cooking process change the quantity of nutrients in the recipe. Therefore, to resolve these issues in this study, we propose using a tree structure as the method for coding recipe data. The recipe data can include the cooking process using the tree structure. In addition, the recipe data can reflect changes in the quantity of nutrients caused by the cooking process. In this study, we calculate the quantity of nutrients by using the conventional technique of previous studies and our proposed technique that uses a tree structure. As a result, the recipe data coded with the tree structure can calculate the quantity of nutrients for a recipe and achieve results that are closer to the values of the original recipe than those calculated using the conventional method of coding recipe data.

View full abstract

This paper proposes a similar image retrieval for the Kansei retrieval. The Kansei retrieval system is designed to search for user's clothing articles by considering their Kansei. The system adopts a Kansei retrieval agent. The agent identifies users's choice of clothing by imitating their Kansei. However, the agent's structure can become excessively complicated because considerable information is potentially available. Therefore, a Kansei retrieval system needs to utilizes similar image retrieval. Similar image retrieval searches for a clothing image on the basis of clothing images. Clothing design contains less information than clothing image. A design includes features intended to create a general impression of piece of clothing. In addition, the Kansei retrieval agent evaluates the design, and searches for the designs that a user likes on the basis of the evaluation. Therefore, the agent's structure does not become complicated. In this study, we created a similar image retrieval application and verified it effectiveness. The application searches for clothing images on the basis of the design that a user chooses. The results show that similar image retrieval can identify clothing images similar to the design. Thus, the effectiveness of the proposed similar image retrieval system was confirmed.

View full abstract

In recent years, many researches trying to make relation between multimedia and information of user's impression using the soft computing methods has been developed. But most of these researches aimed at developing multimedia search system, classify things into groups, and so on. So far we developed automatic pattern generation system based on user impression and suggest to the new application of the soft computing methods. In this research, we improve the evaluation methods.

View full abstract

This paper addresses properties of type-1 and type-2 fuzzy inference models. It first clarifies relationship between the Mamdani model and product-sum-gravity model from the point of view of equivalence. Second, the above relationship is applied to the type-2 fuzzy functional inference model. Finally, this paper shows that the inference results of the type-2 fuzzy functional inference model can be obtained by using the above relationship and property.

View full abstract

In this paper, we propose a move-action learning model for animal-like robots. A robot using the model learns to move to satisfy a desire. In our previous study, the model used a Recurrent Neural Network (RNN). The RNN learns movement by Back Propagation Through Time (BPTT) in our previous study. However, there is a problem that it is difficult to establish BPTT learning periods of learning for this model. Instead, we use a Genetic Algorithm (GA) to optimize connection weights for the RNN. We performed a simulation about a move-action learning model because we want to verify whether the robot can move from any location to satisfy its desire.

View full abstract

Tsallis entropy is a one parameter(q) extension of the Shannon entropy. The fuzzy c-means method regularized with the Tsallis entropy has been proposed by Yasuda et al. In this method,however,how to determine the q value is not clear. The q value can be determined by examining an extent of cluster distribution, because it strongly depends on the q value. Accordingly, in this research, we propose a method that makes a specific q value to correspond to each cluster. Each q value determines the extent of its cluster. Numerical experiments show that the proposed method is more effective than the Tsallis entropy regularization method.

View full abstract

Transform functions from the emotion in affinity arousal-pleasure space into the atmosphere in Atmosfield are proposed for the realization of casual communication among robots and humans. In the experiment of two persons conversations, proposed functions achieve 0.81 accuracy rate by comparing transform function outputs with their emotion and directly observed atmosphere. The results confirm the applicability of the proposed transform functions to human friendly application of household robots.

View full abstract

The authors propose a simple observation method of a micro climate in a suburban area based on the plant indicator. Yellow leaves of gingko as a plant indicator act as a measure of environmental conditions. The authors observed and analyzed the yellow leaves of gingko planted in the suburbs of Tokyo (Tama Newtown), in autumn. The processes of turn into yellow from green in ginkgo leaves are classified into simple patterns. From the results presented here, and we applied the logistic function as a mathematical model of the turn processes into yellow from green in ginkgo leaves. As a result, the expression was a well fit with the observed values.

View full abstract

A system of structuring images gathered by Google image search API and the neighbor texts using Formal Concept Analysis (FCA), is developed. Due to the variety of texts, it is difficult to do the clustering the images based on similarities. In order to solve the problem, we propose a method of adding adjectives to images based on classifiers. The classifiers are constructed through the learning process using training data which includes images and corresponding adjectives. We perform experiments using Google image retrieval system and confirm the effectiveness of the proposed method.

View full abstract

Finland, which topped in the world in a reading comprehension, mathematics, and scientific literacy in the Programme for International Student Assessment (PISA) by the Organisation for Economic Co-operation and Development (OECD), is also excellent in English language skills, and the sixth place in the world in the TOEFL iBT. The English language education starts formally from the third grade in the elementary school there. In this study, we investigated English textbooks for elementary school students in Finland, in terms of metrical linguistics.

View full abstract

This research is to clarify the relationship between the surrounding land use and the microclimate, in a suburb. The land use is visualized using a National Land Numerical Information (by GSI) has been provided for a GIS. A microclimate in a suburb is visualized by the Yellow leaves of gingko as a plant indicator. The correlation between the surrounding land use and the microclimate is analyzed and its relevance is discussed.

View full abstract

Estimation of modal choice is an essential problem for urban transport planning. Logit model is often applied as a discrete choice model based on random utility theory in the practical field. On the contrary, fuzzy logic approach has been proposed to describe the travel behaviour with human fuzziness. In the study, the hybrid model is introduced to create the advanced model with random utility and fuzzy logic. In particular, several formulations of hybrid model between logit model and fuzzy reasoning model are proposed. The application of the proposed model can be mentioned with the empirical database of person trip survey for urban area. Finally, the advantages of the hybrid model can be summarized in terms of description as well as estimation.

View full abstract

Car racing game is a game of computer programs in IEEE 2007 Car Racing Competition, where two car agents compete with each other for taking waypoints in a two-dimensional real-number plane. For a car agent's action selection, in this paper, we propose a Q-learning method in which a car agent can pass a present waypoint with the smaller number of steps. If the number of steps to pass the present waypoint is less than that of the similar past state, we give additional rewards (called step rewards) to all car agent's actions from the first step to the present waypoint except several last actions. As a result of the simulation, the number of steps of the car agent with the step rewards became a little less than that without it. Because the car agent runs so fast that it cannot efficiently pass the next waypoint.

View full abstract

Spatiotemporal localization of Brain Activities on Recalling Body Names Yoshinori Tanaka1) Takahiro Yamanoi1 )Mika Otsuki2) Hisashi Toyoshima3) Shin-ichi Ohnishi1) Toshimasa Yamazaki4) 1)Hokkai-Gakuen University 2)Hokkaido University 3)Japan Technical Software 4)Kyushu Institute of Technology abstruct The authors have measured electroencephaloglams (EEGs) from subjects observing an image of part of human body and recalling its name silently. The equivalent current dipole source localization (ECDL) method has been applied to those event related potentials (ERPs) : averaged EEGs. ECDs were localized to the primary visual area V1 around 100msec, to the interior temporal gyrus around 330msec, to the parahippocampal gyrus and hippocampus, the right angular gyrus, the corpus callosum, and then ECDs were localized to the Wernicke's area in the left hemisphere around 430msec. Then ECDs were localized to the left angular gyrus around 490msec, to the postcentral gyrus, and again to the parahippocampal gyrus (paraHip) around 600msec. Finally, ECDs were localized to the superior frontal gyrus around 630msec, to the frontal pole, and to the Broca's area around 725msec. From estimates of some activities on the paraHip and hippocampus, it is supposed to that searching and preservation in the memory have been done in the meantime.

View full abstract

Rough set theory was proposed by Z.Pawlak in 1982. This theory can mine knowledge granules through a decision rule from a database, a web base, a set and so on. The decision rule is used for data analysis as well. And we can apply the decision rule to reason, estimate, evaluate, or forecast an unknown object. In this paper, the rough set theory is used to analysis of time series data. Knowledge granules are minded from the data set of tick-wise price fluctuations. We inspect whether the knowledge varies according to the difference in stocks brand.

View full abstract

Recently, elderly people who live alone in a room is increased. But, it is hoped that the elderly people keep good health. To keep good health for elderly people, a human should act autonomously. Frankl's psychology insists to the meaning and value for a human life. Frankl's psychology discusses the importance of external value that is picked up by external stimuli. Therefore, it is expected that a person would act autonomously if a person find the meaning and value of human life from external stimuli by using a partner robot. In this research, we propose the robot interaction method based on frankl's psychology. Through human-robot interaction experiment, we verify that a human acts autonomously by the robot interaction based on frankl's psychology.

View full abstract

There are many efforts to code information related to drugs in order to ensure the safety of medicinal safety. In spite of this background, there is no coding system to express drug dosage forms. In this study, we utilize the fact that the same letters commonly appear in the names of the similar shape or the similar usage, and applied N-gram method to classify the dosage form names.

View full abstract

After 2011 Tohoku Earthquake, all enterprises in Japan must save energy continually. Especially, to save energy while keeping the production quality and the production volume is required in the manufacturing. This paper describes a visualization technique to analyze causalities among the productivity indices and energy for improving energy efficiency of factory equipment. As the result of the visualization in our factory, our proposed technique could successfully improve the energy efficiency on a molding machine, a press machine and compressors without a negative effect to the productivity that means production volume and supply pressure.

View full abstract

Using the relative relations among alternatives, the set function that shows the feature of an alternative is proposed. In the weighted sum model, such as the AHP models, the set function values are the average values of set function representation of the weights when the alternative has the top comprehensive value. In the Choquet integral models, the set function is consist of set function expression of singleton fuzzy measure and Mobius function of the fuzzy measure. To read the functions, we can understand the future of an alternative such as, "When both weights 1 and 2 put relatively importance, the alternative is selected".

View full abstract

Quiz, especially descriptive answer style, is one of effective method to grasp students' misunderstandings in a classroom. Teachers would improve their lectures by referring answers of a quiz. On the other hand, it is hard for teachers to read all answers in their classroom. In this paper, we discuss a method to extract keywords from live answers automatically.

View full abstract

A fuzzy regression model illustrates the potential possibilities inherent in the target system by including all data in the model. Tanaka and Guo employ exponential possibility distribution to build a model, while Inuiguchi et al. and Tajima are independently working on coinciding between the center of a possibility distribution and the center of a fuzzy regression model. Typically, samples influence and distort the shape of the model if they are far from the center of data. Yabuuchi and Watada have developed a model for describing the system possibility using the center of a fuzzy regression model and an approach that mends the distortion of the model. This model is a fuzzy regression model building through possibility maximization. The objective of this paper is to analyze the Japanese economy using our model, and to show the usefulness of our model by analyses.

View full abstract

In this paper, we develop a model that infers whether or not visitors in an online shopping site will purchase some product from their eye movements. Furthermore, we try to propose guidelines for purchase in online shopping sites.

View full abstract

Children who go to special education schools have many chances for exercise and physical activity. However, during vacation time, they generally experience weight increase and a worsening of their fitness levels. For example, the result of having compared the number of steps of a technical college student and a special need student, the daily physical activity of special needs students and regular high school students are similar while at school, but drops to half on holidays. So, our research builds the system which supports special need students with iPhone. In the system to propose, a student uses iPhone and a teacher uses the PC system. iPhone supports to count the number of steps, supports to exercise and management of a calorie. PC system is used by teacher. PC system can check the data sent from iPhone. By exchanging data between iPhone and a personal computer, a teacher can manage a student's movement time and consumption calorie also in vacation. Thereby, special need student lack of exercise will be relieved.

View full abstract