Shimpei Matsumoto

A study on postural optimization for bicycle exercise based on electromyography

At present, commercially available bicycles have various sizes of frame to suit the user’s physical size, and the positions of both the saddle and the handlebars can be altered, but there is a lack of interest in the importance of the rider’s position when riding the bicycle in relation to their physical properties. Adjusting the rider’s position on the cycle on the basis of their physical properties before the exercise makes it possible to improve its efficiency. In this article, we develop an automatic saddle height-control system for cycle exercise, and present a useful method of determining cycling posture with the use of physical information. This system is composed of a computer, an electromyographic measurement device, and a fixed cycle trainer. In particular, in order to give the fixed cycle trainer a degree of freedom depending on the direction of the seat tube, we designed and built a device to control the height of the saddle. This article explains the structure of the system, introduces our data processing method, and discusses the results of our experiments. We then give an evaluation of the standard cycling posture for different settings of saddle height based on a quantitative evaluation method, principal component analysis.

Monte-Carlo Tree Search for a reentrant scheduling problem

This paper reports application results of Monte-Carlo Tree Search (MCTS) for a practical problem. In this paper, a reentrant scheduling problem is considered as a practical problem which has been addressed by our previous works. MCTS introduced by Coulom is a best-first search where the pseudorandom simulations guide the solution of problem. Recent improvements on MCTS have produced strong computer Go program, which has a large search space, and the success is a hot topic for selecting the best move. So far, most of reports about MCTS have been on two-player game, and MCTS has been applied rarely in one-player perfect-information games. MCTS does not need an admissible heuristic, so the application of MCTS for one-player games might be an interesting alternative. Additionally, one-player games like puzzles are determinately operated only by one players decision, so sequences of changes in state are describable as a network diagram of interdependence of operations. Therefore if MCTS for one-player games is considered as a meta-heuristic algorithm, we can use this algorithm for not only many practical problems, but also combinatorial optimization problems. Especially as MCTS does not fully depend on evaluation function, so the solutions based on MCTS remain effective if objective function of problem is modified. This paper firstly investigated on the application of Single Player MCTS (SP-MCTS) introduced by Schadd et al. Next this paper showed the effectiveness of new simulation strategies on SP-MCTS by numerical experiments. Based on the results, this paper discussed the application potentiality of SP-MCTS for a practical reentrant scheduling problem.

Effects of sharing farmers' information using content management system

In recent years, new business models for agricultural markets have appeared. Under this perspective, we develop a new information system for urban markets to facilitate the transactions. Both sides, consumers and farmers, require certain information from markets about agricultural products. For example, consumers may make requests about the exact information of agricultural products or their safety, while farmers may want to make requests about the information on how to boast their produce. Under the considerations of such requirements at the markets, which may be conflicting, we propose a new information system to assist in the negotiation between parties.

Development of Web‐Based Menu Planning Support System and its Solution Using Genetic Algorithm

Recently lifestyle‐related diseases have become an object of public concern, while at the same time people are being more health conscious. As an essential factor for causing the lifestyle‐related diseases, we assume that the knowledge circulation on dietary habits is still insufficient. This paper focuses on everyday meals close to our life and proposes a well‐balanced menu planning system as a preventive measure of lifestyle‐related diseases. The system is developed by using a Web‐based frontend and it provides multi‐user services and menu information sharing capabilities like social networking services (SNS). The system is implemented on a Web server running Apache (HTTP server software), MySQL (database management system), and PHP (scripting language for dynamic Web pages). For the menu planning, a genetic algorithm is applied by understanding this problem as multidimensional 0–1 integer programming.

Predicting the individual best saddle height of bicycle based on electromyography and Fuzzy Inference

Recently, various social issues, such as global warming problem, economical abrupt move, and diseases associated with adult lifestyle habits, are reported. Against them, the role of bicycle has been reviewed as one of effective solutions. In fact, many types of bicycles have been developed and have been widely used in our daily life. Though commercially available bicycles have various size of frame for users physical size, and the positions both of a saddle and a handle can be modified, but there is a lack of interests in the importance of bicycle position as a shared awareness. Provision of proper riding posture for riders based on their physical properties would enable to improve the efficiency of cycling exercise, and to prevent some chronic pains occurred in places of body. To establish an optimization method of bicycle position based on individual biomedical information, this study focuses on the importance of bicycle position, especially we address to search a suitable saddle height corresponding to users physical features and properties. This paper firstly develops an automatic saddle height control system, and secondly supposes an evaluation standard of cycling exercise based on electromyographic signals of riders leg during cycling exercise, and an optimization method of saddle height by using Fast Fourier Transformation (FFT), Principle Component Analysis (PCA), and Fuzzy Inference. This paper shows firstly the concepts of the evaluation standard we have defined for riders pedaling performance with some experimental results, and introduces a fuzzy control system for automatic saddle height control.

Worker's knowledge evaluation with single-player Monte Carlo tree search for a practical reentrant scheduling problem

This paper shows the application results of single-player Monte Carlo tree search (SP-MCTS), an alternative of MCTS, for a practical reentrant scheduling problem addressed by our previous works. Especially in this paper, worker’s IF-THEN knowledge evaluation method with SP-MCTS is proposed. SP-MCTS is thought to be a meta-heuristic algorithm for NP-completeness problems, because SP-MCTS is applicable for any types of problems, where the problem’s state changes determinately in each discrete time. Therefore, SP-MCTS might be useful for not only perfect-information one-player games, but also other problems, as long as search spaces are describable as a tree structure, and the solution is stoppable with the termination determinably. The authors have considered that SP-MCTS is useful for obtaining/evaluating knowledge. This paper first describes the basic idea of SP-MCTS, and second shows the detail of the scheduling problem, including formulation. After, this paper examines the availability of SP-MCTS for a practical problem. Especially, the potentiality of SP-MCTS for knowledge evaluation is discussed from the experimental results.

Extraction of Physical Motion Dictating the Difference between Skilled Cyclist and Beginner

In the field of cycling competition, cyclists commonly utilize binding pedals to maximize their competitive performance. The feature of binding pedals is to hold the sole of cycling shoe on the upper body of pedal, which enables a cyclist to not only push down the pedals but also pull up the pedals in one revolution of pedaling motion. Pedaling motion is implemented by the combination of muscle activities of lower extremity. The conversion efficiency from the physical strength of a cyclist to the propulsion power of a bicycle has been considered as the skill of pedaling exercise. By the way, neither effective instruments nor methods to accurately evaluate the pedaling skill have been established. Then, this study aims to extract the difference of physical motions between a skilled cyclist and a beginner by using the mechanical data of a bicycle and the electrophysiological data of a subject while pedaling exercise. This paper firstly introduces the experimental device and describes the protocol of measurement experiment. The measured data are statistically processed by using principal component analysis to extract the physical motions dictating the difference of pedaling skill between a skilled cyclist and a beginner.

Development of automatic positioning system for bicycle saddle based on lower limb's EMG signals during pedaling motion

This paper proposes an automation system for cyclists, which provides the optimum setting of bicycle components such as saddle and handle against the physical properties of a cyclist. In order to complete our purpose, the evaluation criteria for saddle setting by using bio-signals of a cyclist who pedals a bicycle have to be established firstly. We focus on patterns of muscle activity of the leg muscles that activate in pedaling exercise, and assume that undesirable pattern of muscle activity would appear in the pedaling motion of inexperienced cyclists. We use principal component analysis (PCA) to extract the features of muscle activity from the leg muscles. Our previous work has already clarified that the PCA scores come close to zero in the pedaling motion performed by a skilled cyclist at the saddle height which is subjectively evaluated good. In this paper, we add other degrees of freedoms of saddle setting such as fore-and-back position and angle adjustment to the experimental device. Surface electromyogram (SEMG) of the leg muscles has also been used to measure bio-signals of a cyclist during pedaling exercise. With the use of the aforementioned experimental environment, the effects of setting height and fore-and-back position to the pattern of muscle activity of the leg muscles are investigated in this paper.

Feasibility of Integrated Menu Recommendation and Self‐Order System for Small‐Scale Restaurants

In recent years, point of sales (POS) systems with order function have been developed for restaurants. Since expensive apparatus and system are required for installing POS systems, usually only large‐scale restaurant chains can afford to introduce them. In this research, we consider the POS management in a restaurant, which cooperates with an automatic order function by using a personal digital device aiming at the safety of the food, pursuit of service, and further operational efficiency improvements, such as foods management, accounting treatment, and ordering work. In traditional POS systems, information recommendation technology is not taken into consideration. We realize the recommendation of a menu according to the user’s preference using rough sets and menu planning based on stock status by applying information recommendation technology. Therefore, we believe that this system can be used in comfort with regard to freshness of foods, allergy, diabetes, etc. Furthermore, due to the reduction of the p...

Business process analysis to obtain empirical lot sizing rule in printing process

We have addressed the improvement of production efficiency in an automobile parts supplier, and have revised the business processes to develop the knowledge-based production scheduling software as final goal. This paper focuses on the printing process from the whole of production processes, and describes the result of business process analysis to obtain the workerpsilas implicit knowledge. Until now the whole of business processes in the parts supplier have been examined by our previous researches, and we have mainly discussed the operation in printing process as a lot sizing scheduling problem only by theoretical aspect. However the previous approaches cannot flexibly respond to the change of production conditions such as the dispersion of order, the interrupt of urgent task, and the change of inventory quantity in spite of the actual field can handle these. Therefore this paper regards that the expertpsilas technical know-how of tacit knowledge in the actual printing field is mostly important factor in response to the change of production conditions, and the realities of lot sizing is grasped by the production performance records.