Tomohito Wada

The relationship between court surface and tactics in tennis using a computerized scorebook.

The purpose of this study was to use a newly developed computerised scorebook for tennis in order to clarify the characteristics of tennis tactics used on specific court surfaces. The authors developed a computerised scorebook for tennis that calculates the time duration of shots, points, and the time between points. Data were collected from matches played by male Japanese intercollegiate players. A total of 97 points were observed. Two observers (A, B) were recruited for recording matches using the scorebook. The mean error of observer A was 0.003±0.05 s, while the mean error of observer B was 0.02±0.10 s. The computerised scorebook for tennis was used to collect data for clarifying the characteristics of tennis tactics used on specific court surfaces. Forty-one matches from the Grand Slam tournaments held in 2003 and 2004 were analyzed. The scorebook recorded the final shot of each point, the result of each point, and the time duration of each shot. The final shots were categorised into the following 5 groups: service, return of serve, ground strokes, attacking strokes, and defending strokes. The time between the impact of the serve and the impact of the return of serve determined the duration of service. The time duration of ground strokes was calculated as the time between the impact of one player and the impact of the other player. A chi-square test was used to compare the distribution of the final shots on each surface. An ANOVA test was conducted in order to compare the time duration on each surface and a Tukey’s HSD test was used for multiple comparisons. For the last shot of each point, significant differences were observed between the court surface and the distribution of the type of stroke. The percentage of ground strokes was high on clay while the percentages for attacking and defending strokes were high on grass. Furthermore, the rate of service strokes was high on hard courts. The shot time duration of the 1st service was 0.91 s on clay, 0.71 s on grass, and 0.73 s on hard courts. The time duration of service on clay was significantly longer than the time durations observed on other surfaces. The time duration of ground strokes was 1.36 s on clay, 1.34 s on grass, and 1.35 s on hard courts. The time duration of ground strokes on clay was significantly longer than time durations observed on grass; however, the difference was only 2/100 of a second. Service and return of service strokes were important to the tactics used on grass and hard courts as players must react more quickly than on clay. Ground strokes were important on clay and hard courts, and the average time duration of ground strokes was equal on these surfaces.

A Predictive Model for Gait Recognition

Gait Recognition has been paid an attention to as non-contact and unobtrusive biometric method. Magnitude and phase spectra of horizontal and vertical movement of ankles in a normal walk are effective and efficient signatures in gait recognition. However, gait recognition rate degrades significantly due to variance caused by covariates of clothing, surface or time lapse. In this paper, to improve gait recognition rate on a variety of footwear, a predictive model is proposed. The predictive model is able to estimate slipper gait from shoes gait. By using predictive slipper gait, much higher recognition rate is achieved for slipper gait over time lapse than ones without predictive model. The predictive model designed in this paper succeeds in separation of the variance due to a footwear covariate from the variance due to a time covariate.

An analysis of time factors in elite male tennis players using the computerised scorebook for tennis

The authors developed the computerized scorebook for tennis to analyze the time duration of shots. The purpose of this study was to analyze the time factors in Grand Slam singles matches using the computerized scorebook for tennis. Eighty-two players’ performances from forty-one matches in Grand Slam tournaments held in 2003 and 2004 were analyzed. The French Open, Wimbledon and the U.S. Open were selected to compare the effect of court surface on timing factors. The time duration of both 1st and 2nd service was longest at the French Open. Players need different service strategy between the French Open and the other tournaments because of the difference of strategy. Time duration of ground strokes showed no significant differences between the three tournaments. Ground strokes and rally play followed similar rhythms at all three tournaments. These results were obtained using the computerized scorebook for tennis. The usefulness of the scorebook for tennis coaching was demonstrated.

Safety Driving Assessment Based on Video Image Sequence Analysis

In this paper, a driving assessment mechanism based on video image sequence analysis techniques, such as traffic signs and road markings detection, and inter-vehicular distance estimation, is proposed. A smart device connected to 3G wireless networks is used to collect and send sensory information. These data are analyzed in a cloud computing infrastructure to evaluate personal driving assessment. The traffic signs detection realized by utilizing SIFT feature descriptor and the inter-vehicular distance estimation technique based on simple geometric constraints, are shown in detail.

An analysis of the time duration of ground strokes in Grand Slam men’s singles using the computerised scorebook for tennis

The purpose of this study was to analyse the time duration of ground strokes in various court surfaces in men’s singles tennis. We used the computerised scorebook for tennis to collect the data from the three Grand Slam men’s singles tennis tournaments (French Open, Wimbledon, U.S. Open) held in 2003 and 2004. The total number of study matches was 41. The time duration of ground strokes was analysed from the data. The factor of the player’s situation showed a significant difference (p<0.01). The time duration of ground strokes on the server was 1.33±0.01 s and on receiver was 1.38±0.01 s. This result was influenced by the difference of tactics in service games and return games. The server has the advantage due to starting the rally by means of the serve. It leads the server to play more aggressively than the receiver.

Cloud Drive: A Computing Architecture for a Scalable Driving Safety Management System

In Japan, taxi, bus, and cargo truck operation companies are required by law to commit to driving safety management. Driving safety management is achieved by a cyclic process consisting of collecting sensory information, assessing driving safety, and improving driving based on the results. At this time, this is performed by transport company personnel. In this paper, an architecture and its implementation for a scalable driving safety management system are proposed. The system consists of smart devices and services provided by a cloud computing infrastructure. The smart devices are connected to 3G wireless networks used to collect and send sensory information such as video image sequences, acceleration, and GPS data. The services available in the cloud computing infrastructure are a time-series sensory data storage service, image analysis service for driving assessment, and real-time feedback service.