Deep Learning for Classifying Physical Activities from Accelerometer Data

Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the two models on two physical movement datasets collected from several volunteers who carried tri-axial accelerometer sensors. The first dataset is from the UCI machine learning repository, which contains 14 different activities-of-daily-life (ADL) and is collected from 16 volunteers who carried a single wrist-worn tri-axial accelerometer. The second dataset includes ten other ADLs and is gathered from eight volunteers who placed the sensors on their hips. Our experiment results show that the RNN model provides accurate performance compared to the state-of-the-art methods in classifying the fundamental movement patterns with an overall accuracy of 84.89% and an overall F1-score of 82.56%. The results indicate that our method provides the medical doctors and trainers a promising way to track and understand a patient’s physical activities precisely for better treatment.

Fusion of Unobtrusive Sensing Solutions for Sprained Ankle Rehabilitation Exercises Monitoring in Home Environments

The ability to monitor Sprained Ankle Rehabilitation Exercises (SPAREs) in home environments can help therapists to ascertain if exercises have been performed as prescribed. Whilst wearable devices have been shown to provide advantages such as high accuracy and precision during monitoring activities, disadvantages such as limited battery life, users' inability to remember to charge and wear the devices are often the challenges for their usage. Also, video cameras, which are notable for high frame rates and granularity, are not privacy-friendly. This paper, therefore, proposes the use and fusion of unobtrusive and privacy-friendly sensing solutions for data collection and processing during SPAREs in home environments. Two Infrared Thermopile Array (ITA-32) thermal sensors and two Frequency Modulated Continuous Wave (FMCW) Radar sensors were used to simultaneously monitor 15 healthy participants during SPAREs which involved twisting their ankle in 4-fundamental movement patterns namely (i) extension, (ii) flexion, (iii) eversion and (iv) inversion. Experimental results indicated the ability to identify thermal blobs of participants performing the 4 fundamental movement patterns of the human ankle. Cluster-based analysis of data gleaned from the ITA-32 sensors and the FMCW Radar sensors indicated average classification accuracy of 96.9% with K-Nearest Neighbours, Neural Network, AdaBoost, Decision Tree, Stochastic Gradient Descent and Support Vector Machine, amongst others.

Deep Learning for Classifying Physical Activities from Accelerometer Data

Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify the physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the proposed models on two physical movement datasets collected from several volunteers who carried tri-axial accelerometer sensors. The first dataset is from the UCI machine learning repository, which contains 14 different activities-of-daily-life (ADL) and is collected from 16 volunteers who carried a single wrist-worn tri-axial accelerometer. The second dataset includes ten other ADLs and is gathered from 8 volunteers who placed the sensors on their hips. Our experiment results show that the RNN model provides the accuracy performance compared to the state-of-the-art methods in classifying the fundamental movement patterns with an overall accuracy of 84.89% and an overall F1-score of 82.56%. Our results indicate that the proposed method will provide the medical doctors and trainers a promising way to precisely track and understand a patient’s physical activities for better treatment.

A Process Evaluation of A UK Classroom-Based Physical Activity Intervention—‘Busy Brain Breaks’

The gap between development of effective physical activity interventions and the wide-scale adoption of these interventions in real-world settings has been reported since the early 2000s. Evaluations have been criticised for failing to report details of context, implementation, adoption and maintenance. ‘Busy Brain Breaks’ was an intervention designed to improve fundamental movement patterns whilst increasing physical activity within the classroom. This evaluation study used a mixed-methods approach including questionnaires, observations, semi-structured interviews and quantification of class-level dose. Findings suggest that giving teachers flexibility and autonomy over the way in which they implement physical activity interventions may increase the likelihood of adoption. Time was frequently perceived as a significant barrier to the intervention, giving the teachers flexibility to implement the intervention when they thought most suitable allowed teaching staff to retain their autonomy and make the intervention work with their schedule. Children’s behaviour appeared to be both a facilitator and barrier to implementing physical activity interventions within the classroom. Whilst misbehaviour can pose as a barrier, children’s enjoyment acts as a key facilitator to implementation for teaching practitioners. Teachers interviewed (n = 17) observed that movement ability had developed as a result of the intervention and recognised co-ordination, balance and stability as areas that had noticeably improved. Conducting an in-depth process evaluation has allowed for greater insight and understanding as to how, and to what extent, the intervention was implemented within the school-based setting.

Dance on the Brain: Enhancing Intra- and Inter-Brain Synchrony

Dance has traditionally been viewed from a Eurocentric perspective as a mode of self-expression that involves the human body moving through space, performed for the purposes of art, and viewed by an audience. In this Hypothesis and Theory article, we synthesize findings from anthropology, sociology, psychology, dance pedagogy, and neuroscience to propose The Synchronicity Hypothesis of Dance, which states that humans dance to enhance both intra- and inter-brain synchrony. We outline a neurocentric definition of dance, which suggests that dance involves neurobehavioral processes in seven distinct areas including sensory, motor, cognitive, social, emotional, rhythmic, and creative. We explore The Synchronicity Hypothesis of Dance through several avenues. First, we examine evolutionary theories of dance, which suggest that dance drives interpersonal coordination. Second, we examine fundamental movement patterns, which emerge throughout development and are omnipresent across cultures of the world. Third, we examine how each of the seven neurobehaviors increases intra- and inter-brain synchrony. Fourth, we examine the neuroimaging literature on dance to identify the brain regions most involved in and affected by dance. The findings presented here support our hypothesis that we engage in dance for the purpose of intrinsic reward, which as a result of dance-induced increases in neural synchrony, leads to enhanced interpersonal coordination. This hypothesis suggests that dance may be helpful to repattern oscillatory activity, leading to clinical improvements in autism spectrum disorder and other disorders with oscillatory activity impairments. Finally, we offer suggestions for future directions and discuss the idea that our consciousness can be redefined not just as an individual process but as a shared experience that we can positively influence by dancing together.

A systematic approach to athletic development

Since the dawn of social media, sports performance professionals have had the ability to share ideas and display training methodologies to anyone across the globe. Research problem/aim: The problem with this connectedness is much of this information is baseless. Coaches, athletes and parents are too often misinformed, confused, and duped by fad exercise programs and gimmicks that put can puts their athletes under too much stress (physical and emotional) too fast, putting them at risk of injury. Findings: In order to be successful on the sporting field, athletes need to be able to make it to the playing field first. Sports performance specialists need to focus on long term development not just pushing their athletes to the limit. Athletes need a structured training progression that builds a solid foundation of strength, endurance, and coordination to give them the tools to be successful in the weight room before placing them under a loaded bar or implementing advanced training techniques. With athletes at any level, high school, collegiate, or professional, even the most talented of athletes on the field may not necessarily have a very strong background in the weight room. Conclusion: A systematic pattern of athletic development would allow adaptation in fundamental movement patterns and develops requisite physical qualities, and allow the athletes to advance safely and effectively.