This paper discusses the opportunities and challenges associated with collection of a large scale, diverse dataset for Activity Recognition. The was collected by 141 undergraduate students, in controlled environment. Students triaxial accelerometer data from wearable whilst each carrying out 3 18 investigated activities, categorized into 6 scenarios daily living. subsequently labelled, anonymized uploaded to shared repository. presents an analysis quality, through outlier detection assesses...

The effectiveness of document Information Extraction (IE) is greatly affected by the structure and layout documents being considered. In case legal relating to commercial law, an additional challenge many different varied formats, structures layouts used. this paper, we present work on a flexible scalable IE environment, CLIEL (Commercial Law based Layout) for application law documentation that allows rules be derived then utilised support IE. proposed environment operates using NLP (Natural...

Abstract Objective The aim of the study was to evaluate a technological solution in form an App implement and measure person-centredness nursing. focus enhance knowledge transfer set person-centred key performance indicators corresponding measurement framework used inform improvements experience care. Design evaluation approach derived from work Medical Research Council assess feasibility establish degree which meeting aims out development phase. Evaluation data were collected using groups...

Activity recognition is one of the most active areas research in ubiquitous computing. In particular, gait activity useful to identify various risk factors people’s health that are directly related their physical activity. One issues recognition, and often datasets unbalanced (i.e., distribution classes not uniform), due this disparity, models tend categorize into class with more instances. present study, two methods for classifying activities using accelerometer gyroscope data from a...

The classifier selection problem in Assistive Technology Adoption refers to selecting the classification algorithms that have best performance predicting adoption of technology, and is often addressed through measuring different single indicators. Satisfactory can help reducing time costs involved technology process. As there are multiple criteria from domains several candidate algorithms, process now a be using Multiple-Criteria Decision-Making (MCDM) methods. This paper proposes novel...

Modelling Activities of Daily Living (ADLs) is an important step in the process to design and implement reliable sensor systems that effectively monitor activities ageing population. Once modelled, unusual may be detected have potential impacting upon a person's well-being. The use Petri nets model ADLs considered this research as means capture intricate behaviours ambient systems. To our best knowledge there has not been extensive work related literature, hence novelty work. developed net...

Activity recognition, a key component in pervasive healthcare monitoring, relies on classification algorithms that require labeled data of individuals performing the activity interest to train accurate models. Labeling can be performed lab setting where an individual enacts under controlled conditions. The ubiquity mobile and wearable sensors allows collection large datasets from activities naturalistic Gathering labels for recognition is typically expensive time-consuming process. In this...

Abnormal behaviour in the performance of Activities Daily Living (ADLs) can be an indicator a progressive health problem or occurrence hazardous incident. This paper presents initial fusion approach data collected from ambient (contact and thermal) wearable (accelerometer) sensors smart environment to improve recognition main steps ADLs. An accurate these support detecting abnormal form deviations expected steps. The used is kitchen ADLs considered are (i) prepare drink tea, (ii) coffee....

This paper presents a probabilistic approach for the identification of abnormal behaviour in Activities Daily Living (ADLs) from sensor data collected 30 participants. The ADLs considered are: (i) preparing and drinking tea, (ii) coffee. Abnormal identified context these activities can be an indicator progressive health problem or occurrence hazardous incident. presented considers temporal aspect sequences actions that are part each ADL vary between average standard deviation durations...

Mental health in everyday life can be supported using ambient and wearable sensors, which could detect when a person is feeling well (e.g. happy or calm) not stressed sad). Identifying positive negative moods useful for interventions to reinforce improve them respectively. Previous work that used data from sensors (accelerometers) personalized way successfully identified mood while users performed Activities of Daily Living (ADLs). This paper presents general approach (contact thermal)...

This paper presents a probabilistic approach for the identification of abnormal behaviour in Activities Daily Living (ADLs) from dense sensor data collected 30 participants. The ADLs considered are related to preparing and drinking (i) tea, (ii) coffee. Abnormal identified context these activities can be an indicator progressive health problem or occurrence hazardous incident. presented considers temporal sequential aspects actions that part each ADL vary between average standard deviation...

Abstract Background Office work generally consists of high amounts sedentary behaviour (SB) which has been associated with negative health consequences. We developed the “WorktivIty” mobile app to help office workers reduce their SB through self-monitoring and feedback on time, prompts break educational facts. The aim this paper is report feasibility delivering Worktivity intervention desk-based in workplace setting describe methodological considerations for a future trial. Methods conducted...

The scale of Internet Things (IoT) systems has expanded in recent times and, tandem with this, IoT solutions have developed symbiotic relationships technologies, such as edge Computing. leveraged computing capabilities to improve the solutions, facilitating quick data retrieval, low latency response, and advanced computation, among others. However, contrast benefits offered by capabilities, there are several detractors, centralized storage, ownership, privacy, auditability, security, which...

In fuzzy systems, membership functions determine the groups to which a variable can belong to, and these are static or only have one setting in some aspect. However, systems typically require model dynamic environment they represent. Still, this behavior does not reflect conventional way. Thus, capable of reflecting dynamics real-time context. The approach presented consists system where transformations, according contextual variables that influence them, adjusts real time. functions'...

As high amounts of occupational sitting have been associated with negative health consequences, designing workplace interventions to reduce sedentary behaviour (SB) is public interest. Digital technology may serve as a cost-effective and scalable platform deliver such an intervention. This study describes the iterative development theory-based, digital change intervention SB.The wheel The Behaviour Change Technique Taxonomy were used guide design process form basis for selecting components....

Activities of daily living (ADL) systems have been playing an important role in assessing and monitoring the quality life elderly people for many years. With recent advancement integration Internet Things (IoT) devices within ADL systems, number services offered has increased significantly. One these vital is abnormal behaviour detection based on data collected from IoT smart homes. However, could enormous privacy implications home users if not handled properly. We address this issue by...

There is a global challenge related to the increasing number of People with Dementia (PwD) and diminishing capacity governments, health systems, caregivers provide best care for them. Cost-effective technology solutions that enable ensure good quality life PwD via monitoring interventions have been investigated comprehensively in literature. The objective this study was investigate challenges design deployment Smart Home In Box (SHIB) approach wellbeing within home. This could then support...

The accurate recognition of activities is fundamental for following up on the health progress people with dementia (PwD), thereby supporting subsequent diagnosis and treatments. When monitoring daily living (ADLs), it feasible to detect behaviour patterns, parse out disease evolution, consequently provide effective timely assistance. However, this task affected by uncertainties derived from differences in smart home configurations way which each person undertakes ADLs. One adjacent pathway...

Foot ulcers are a common complication of diabetes and the leading cause amputation amongst those with diabetes. Research has shown that, an increase two degrees Celsius in skin temperature on plantar surface foot can be early indication injury or inflammation. Early detection treatment hotspot region may reduce risk ulcer developing. This paper presents thermography-based approach for detecting hotspots foot. The system comprises bespoke application thermal camera attachment which captures...

Inadvertent falls can cause serious, and potentially fatal injuries, to at risk individuals. One such community of at-risk individuals is the elderly population where age related complications, as osteoporosis dementia, further increase incidence negative impact falls. Notably, within that has been identified leading injury preventable death, hospitalization reduction quality life. In cases, rapid detection of, reaction, fall events shown be critical reduce effects this community. Currently,...

Knee Osteoarthritis (OA) is one of the most prominent diseases in an ageing society and has affected over 10 million people Thailand. When suffer from OA, it very difficult to recover. Therefore, early detection prevention are important. The typical way detect OA by using X-ray imaging. This research study focused on applying image processing classification techniques knee imagery. fundamental concept find a region interest, use feature extraction build classifier that can classify between...