An orientation free adaptive step detection algorithm using a smart phone in physical activity monitoring

In this paper we present an Orientation Free Adaptive Step Detection (OFASD) algorithm for deployment in a smart phone for the purposes of physical activity monitoring. The OFASD algorithm detects individual steps and measures a user’s step counts using the smart phone’s in-built accelerometer. The algorithm considers both the variance of an individual’s walking pattern and the orientation of the smart phone. Experimental validation of the algorithm involved the collection of data from 10 participants using five phones (worn at five different body positions) whilst walking on a treadmill at a controlled speed for periods of 5 min. Results indicated that, for steps detected by the OFASD algorithm, there were no significant differences between where the phones were placed on the body (p > 0.05). The mean step detection accuracies ranged from 93.4 % to 96.4 %. Compared to measurements acquired using existing dedicated commercial devices, the results demonstrated that using a smart phone for monitoring physical activity is promising, as it adds value to an accepted everyday accessory, whilst imposing minimum interaction from the user. The algorithm can be used as the underlying component within an application deployed within a smart phone designed to promote self-management of chronic disease where activity measurement is a significant factor, as it provides a practical solution, with minimal requirements for user intervention and less constraints than current solutions.

The physical activity loyalty card scheme:Development and application of a novel system for incentivizing behaviour change

In the Public Health White Paper "Healthy Lives, Healthy People" (2010), the UK Government emphasised using incentives and "nudging" to encourage positive, healthy behaviour changes. However, there is little evidence that nudging is effective, in particular for increasing physical activity. We have created a platform to research the effectiveness of health-related behaviour change interventions and incentive schemes. The system consists of an outward-facing website, incorporating tools for incentivizing behaviour change, and a novel physical activity monitoring system. The monitoring system consists of the "Physical Activity Loyalty Card", which contains a passive RFID tag, and a contactless sensor network to detect the cards. This paper describes the application of this novel web-based system to investigate the effectiveness of non-cash incentives to "nudge" adults to undertake more physical activity. © 2012 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering.

Clustering-Based Ensemble Learning for Activity Recognition in Smart Homes

Application of sensor-based technology within activity monitoring systems is becoming a popular technique within the smart environment paradigm. Nevertheless, the use of such an approach generates complex constructs of data, which subsequently requires the use of intricate activity recognition techniques to automatically infer the underlying activity. This paper explores a cluster-based ensemble method as a new solution for the purposes of activity recognition within smart environments. With this approach activities are modelled as collections of clusters built on different subsets of features. A classification process is performed by assigning a new instance to its closest cluster from each collection. Two different sensor data representations have been investigated, namely numeric and binary. Following the evaluation of the proposed methodology it has been demonstrated that the cluster-based ensemble method can be successfully applied as a viable option for activity recognition. Results following exposure to data collected from a range of activities indicated that the ensemble method had the ability to perform with accuracies of 94.2% and 97.5% for numeric and binary data, respectively. These results outperformed a range of single classifiers considered as benchmarks.

Data-Augmentation for Reducing Dataset Bias in Person Re-identification

In this paper we explore ways to address the issue of dataset bias in person re-identification by using data augmentation to increase the variability of the available datasets, and we introduce a novel data augmentation method for re-identification based on changing the image background. We show that use of data augmentation can improve the cross-dataset generalisation of convolutional network based re-identification systems, and that changing the image background yields further improvements.

Simultaneous, long-term monitoring of valve and cardiac activity in the blue mussel Mytilus edulis exposed to copper

Valve and cardiac activity were simultaneously measured in the blue mussel (Mytilus edulis) in response to 10 d copper exposure. Valve movements, heart rates and heart-rate variability were obtained non-invasively using a Musselmonitor(R) (valve activity) and a modified version of the Computer-Aided Physiological Monitoring system (CAPMON; cardiac activity). After 2 d exposure of mussels (4 individuals per treatment group) to a range of dissolved copper concentrations (0 to 12.5 mu M as CuCl2) median valve positions (% open) and median heart rates (beats per minute) declined as a function of copper concentration. Heart-rate variability (coefficient of variation for interpulse durations) rose in a concentration-dependent manner. The 48 h EC50 values (concentrations of copper causing 50% change) for valve positions, heart rates and heart-rate variability were 2.1, 0.8, and 0.06 mu M, respectively. Valve activity was weakly correlated with both heart rate (r = 0.48 +/- 0.02) and heart-rate variability (r = 0.32 +/- 0.06) for control individuals (0 mu M Cu2+). This resulted from a number of short enclosure events that did not coincide with a change in cardiac activity. Exposure of mussels to increasing copper concentrations (greater than or equal to 0.8 mu M) progressively reduced the correlation between valve activity and heart rates (r = 0 for individuals dosed with greater than or equal to 6.3 mu M Cu2+), while correlations between valve activity and heart-rate variability were unaffected. The poor correlations resulted from periods of valve flapping that were not mimicked by similar fluctuations in heart rate or heart-rate variability. The data suggest that the copper-induced bradycardia observed in mussels is not a consequence of prolonged valve closure.

Electrical Based Sensors and Remote Monitoring System for Assessing the Corrosion Related Activity in Concrete at Hangzhou Bay Bridge

Concrete structures in marine environments are subjected to cyclic wetting and drying, corrosion of reinforcement due to chloride ingress and biological deterioration. In order to assess the quality of concrete and predict the corrosion activity of reinforcing steel in concrete in this environment, it is essential to monitor the concrete continuously right from the construction phase to the end of service life of the structure. In this paper a novel combination of sensor techniques which are integrated in a sensor probe is used to monitor the quality of cover concrete and corrosion of the reinforcement. The integrated sensor probe was embedded in different concrete samples exposed to an aggressive marine environment at the Hangzhou Bay Bridge in China. The sensor probes were connected to a monitoring station, which enabled the access and control of the data remotely from Belfast, UK. The initial data obtained from the monitoring station reflected the early age properties of the concretes and distinct variations in these properties were observed with different concrete types.

An Integrated Sensing System for Monitoring the Corrosion Activity in Concrete Blocks Exposed at Hangzhou Bay Bridge

This paper discusses the importance of integrated sensing systems comprising techniques that give different types of data from a structure exposed to the marine environment so that its service life could reliably be predicted. For this purpose, a novel sensor combination was designed and installed in concrete panels which were exposed to Hangzhou Bay Bridge in China. The integrated sensor probe was used to monitor the cover concrete as well as the reinforcement. The sensor probes were connected to a monitoring station, which enabled access and control of the data remotely from Belfast, UK. The initial data obtained from the monitoring station gives interesting information on the early age properties of concrete and distinct variations in these properties with different types of concrete. This paper also reports the variation in electrical properties of different concrete samples and environmental data in response to the marine exposure condition at Hangzhou bay bridge.

Indoor and Outdoor monitoring of photocatalytic activity using a mobile phone app. and a photocatalytic activity indicator ink (paii)

A resazurin (Rz) based photocatalyst activity indicator ink (paii) is used to test the activity of commercial self-cleaning materials. The semiconductor photocatalyst driven colour change of the ink is monitored indoors and outside using a simple mobile phone application that measures the RGB colour components of the digital image of the paii-covered, irradiated sample in real time. The results correlate directly with those generated using a traditional, lab-bound method of analysis (UV–vis spectrophotometry).