Gregory C. May

A Sensing Platform for Physiological and Contextual Feedback to Tennis Athletes

In this paper we describe our work on creating a multimodal sensing platform for providing feedback to tennis coaches and players. The platform includes a fixed installation around a tennis court consisting of a video camera network and a localisation system as well as wearable sensing technology deployed to individual athletes. We describe the various components of this platform and explain how we can capture synchronised multi-modal sensor data streams for games or training sessions. We then describe the content-based retrieval system we are building to facilitate the development of novel coaching tools. We provide some examples of the queries that the system can support, where these queries are chosen to be suitably expressive so as to reflect a coach’s complex information needs regarding tennis-related performance factors.

Knowledge acquisition from sensor data in an equine environment

Recent advances in sensor technology have led to a rapid growth in the availability of accurate, portable and low-cost sensors. In the Sport and Health Science domains, this has been used to deploy multiple sensors in a variety of situations in order to monitor participant and environmental factors of an activity or sport. As these sensors often output their data in a raw, proprietary or unstructured format, it is difficult to identify periods of interest, such as events or actions of interest to the Sport and Exercise Physiologists. In our research, we deploy multiple sensors on horses and jockeys while they engage in horse-racing training exercises. The Exercise Physiologists aim to identify events which contribute most to energy expenditure, and classify both the horse and jockey movement using basic accelerometer sensors. We propose a metadata driven approach to enriching the raw sensor data using a series of Profiles. This data then forms the basis of user defined algorithms to detect events using an Event-Condition-Action approach. We provide an Event Definition interface which is used to construct algorithms based on sensor measurements both before and after integration. The result enables the end user to express high level queries to meet their information needs.

Expanding sensor networks to automate knowledge acquisition

The availability of accurate, low-cost sensors to scientists has resulted in widespread deployment in a variety of sporting and health environments. The sensor data output is often in a raw, proprietary or unstructured format. As a result, it is often difficult to query multiple sensors for complex properties or actions. In our research, we deploy a heterogeneous sensor network to detect the various biological and physiological properties in athletes during training activities. The goal for exercise physiologists is to quickly identify key intervals in exercise such as moments of stress or fatigue. This is not currently possible because of low level sensors and a lack of query language support. Thus, our motivation is to expand the sensor network with a contextual layer that enriches raw sensor data, so that it can be exploited by a high level query language. To achieve this, the domain expert specifies events in a tradiational event-condition-action format to deliver the required contextual enrichment.

Correlating Multimodal Physical Sensor Information with Biological Analysis in Ultra Endurance Cycling

The sporting domain has traditionally been used as a testing ground for new technologies which subsequently make their way into the public domain. This includes sensors. In this article a range of physical and biological sensors deployed in a 64 hour ultra-endurance non-stop cycling race are described. A novel algorithm to estimate the energy expenditure while cycling and resting during the event are outlined. Initial analysis in this noisy domain of “sensors in the field” are very encouraging and represent a first with respect to cycling.

An Analysis of the Impact of Acute Sleep Deprivation on Repeat Cycling Time Trial Performance: 1023 June

Ultra-endurance cycling events, such as the Race Around Ireland (RAI), involve performing periods of intermittent high intensity cycling for extended durations. The ability to maintain a consistently high mean power output whilst in a sleep deprived state is a critical factor in optimising performance. Purpose: To evaluate the effects of acute sleep deprivation, over 24 hours, on a repeat cycling time trial performance. Methods: Six trained male cyclists (mean ± SD: age 33 ± 4 years; height 1.82 ± 0.03 m; mass 79.3 ± 8 kg) were tested on 3 occasions; each testing bout was separated by 7 days, within a 21 day period. During the first test, subjects performed a maximal incremental test on an electromagnetically braked cycle ergometer. Following a standardised recovery period, each subject then completed a baseline 20 minute self-paced maximal performance test (MPT). The subjects subsequently returned on two further occasions to perform two 24 hour trials. During the course of each 24 hour trial the subjects performed a total of 4 MPTs at set time points in either a sleep deprived (SDep) and or sleep normal (SNorm) state using a randomised crossover design. The MPT’s were undertaken at 0 (T1); 8 (T2); 17 (T3); and 24 hours (T4). During the SDep trial subjects accrued no sleep, while during the SNorm trial they were allocated an 8 hour sleep period between T2 and T3. Results: SNorm resulted in a mean sleep duration of 365 ± 38 minutes. No significant differences were found across baseline trials for each of the 3 tests or for the mean cumulative distance covered over the 4 MPT’s (T1-T4) for SDep compared to SNorm. Further analysis of the data revealed a significant decrease in the total distance covered during the MPT at T3 when compared with T2 (13331m ± 1139m vs. 13867m ± 1234m, p<0.05) for the SDep trial. In contrast, no significant differences were observed across trials in the SNorm group. Conclusions: Despite a 4 % decrease in the MPT observed during a time period usually associated with sleep (T2-T3), acute sleep deprivation over 24 hours had no significant impact in overall time trial performance.

Physiological, Haematological and Performance Characteristics of Ultra-endurance Cyclists Competing in the Inaugural Race Around Ireland: 2238

Ultra-endurance events are a growing area within the sport of cycling. The Race Around Ireland (RAI) is a non-stop event where cyclists must complete the 2,170km route in under 96 hours. Purpose: The purpose of this study was to investigate the physiological, haematological and performance characteristics of members of a 4 man team before, during, and after the RAI. Methods: Four trained male cyclists were tested on 2 separate occasions within a 14 day period, with the second bout of testing performed within 7 days of the start of the race, to determine baseline values. Each cyclist completed a maximal incremental test on an electromagnetically braked cycle ergometer, commencing at 100W and increasing in intensity by 50W every 3 minutes until volitional exhaustion. Heart rate, VO2, power output and blood lactate were measured during the test. Following a standardized recovery period, each cyclist then completed a 20 minute maximal performance test (MPT) designed to mimic the demands of the RAI. Baseline blood samples were taken prior to each testing session to facilitate a detailed haematological analysis. Blood samples were also taken before the start of the race, at set intervals during the race, as well as on the race completion. Subjects were also weighed and urine samples collected at the same time points in order to assess hydration status using urine specific gravity (Usg). Further testing was carried out 7 days (haematology), and 14 days (haematology and MPT) post race. Results: No significant differences were found between the MPT results pre and post race. Significant differences were found for white blood cells (WBC) and granulocyte count (p<0.01), haematocrit, haemoglobin, lymphocytes, and red blood cells (p<0.05). No significant difference was observed for changes in body mass or Usg. Conclusions: Variations in WBC and other immune function markers showed initial decrease followed by a gradual elevation during the race. However this did not seem have an impact on the post race MPT. Although there appears to be a significant change in immune function during ultra endurance cycling, this may not lead to a subsequent performance decrement. However, analysis may be complicated by the specific race tactics adopted by the team during the race and the time course of post race assessment.