Search

Abstract The concept of the Human Digital Twin (HDT) has recently emerged as a new research area within the domain of digital twin technology. HDT refers to the replica of a physical-world human in the digital world. Currently, research on HDT is still in its early stages, with a lack of comprehensive and in-depth analysis from the perspectives of universal frameworks, core technologies, and applications. Therefore, this paper conducts an extensive literature review on HDT research, analyzing the underlying technologies and establishing typical frameworks in which the core HDT functions or components are organized. Based on the findings from the aforementioned work, the paper proposes a generic architecture for the HDT system and describes the core function blocks and corresponding technologies. Subsequently, the paper presents the state of the art of HDT technologies and their applications in the healthcare, industry, and daily life domains. Finally, the paper discusses various issues related to the development of HDT and points out the trends and challenges of future HDT research and development.

Abstract BackgroundParkinson disease (PD) is reported to be among the most prevalent neurodegenerative diseases globally, presenting ongoing challenges and increasing burden on health care systems. In an effort to support patients with PD, their carers, and the wider health care sector to manage this incurable condition, the focus has begun to shift away from traditional treatments. One of the most contemporary treatments includes prescribing assistive technologies (ATs), which are viewed as a way to promote independent living and deliver remote care. However, the uptake of these ATs is varied, with some users not ready or willing to accept all forms of AT and others only willing to adopt low-technology solutions. Consequently, to manage both the demands on resources and the efficiency with which ATs are deployed, new approaches are needed to automatically assess or predict a user’s likelihood to accept and adopt a particular AT before it is prescribed. Classification algorithms can be used to automatically consider the range of factors impacting AT adoption likelihood, thereby potentially supporting more effective AT allocation. From a computational perspective, different classification algorithms and selection criteria offer various opportunities and challenges to address this need. ObjectiveThis paper presents a novel hybrid multicriteria decision-making approach to support classifier selection in technology adoption processes involving patients with PD. MethodsFirst, the intuitionistic fuzzy analytic hierarchy process (IF-AHP) was implemented to calculate the relative priorities of criteria and subcriteria considering experts’ knowledge and uncertainty. Second, the intuitionistic fuzzy decision-making trial and evaluation laboratory (IF-DEMATEL) was applied to evaluate the cause-effect relationships among criteria/subcriteria. Finally, the combined compromise solution (CoCoSo) was used to rank the candidate classifiers based on their capability to model the technology adoption. ResultsWe conducted a study involving a mobile smartphone solution to validate the proposed methodology. Structure (F5) was identified as the factor with the highest relative priority (overall weight=0.214), while adaptability (F4) (D-R=1.234) was found to be the most influencing aspect when selecting classifiers for technology adoption in patients with PD. In this case, the most appropriate algorithm for supporting technology adoption in patients with PD was the A3 - J48 decision tree (M3 ConclusionsThe IF-AHP-IF-DEMATEL-CoCoSo approach helped to identify classification algorithms that do not just discriminate between good and bad adopters of assistive technologies within the Parkinson population but also consider technology-specific features like design, quality, and compatibility that make these classifiers easily implementable by clinicians in the health care system.

Heterogeneous cross-project defect prediction (HCPDP) aims to predict defects in new software projects using defect data from previous software projects where the source and target projects have some different metrics. Most existing methods only find linear relationships in the software defect datasets. Additionally, these methods use multiple defect datasets from different projects as source datasets. In this paper, we propose a novel method called heterogeneous cross-project defect prediction using encoder networks and transfer learning (ENTL). ENTL uses encoder networks to extract the important features from source and target datasets. Also, to minimize the negative transfer during transfer learning, we used an augmented dataset that contains pseudo-labels and the source dataset. Additionally, we have used a single dataset to train the model. To evaluate the performance of the ENTL approach, 16 datasets from four publicly available software defect projects were used. Furthermore, we compared the proposed method with four HCPDP methods namely EGW, HDP_KS, CTKCCA and EMKCA, and one WPDP method from existing literature. The proposed method on average outperforms the baseline methods in terms of PD, PF, F1-score, G-mean and AUC.

Computer networks form much of the infrastructure supporting day-to-day life in this digital age. Computer networks, however, are prone to attack and therefore require intrusion detection systems. Intrusion detection systems provide a mechanism to detect network attacks at an early stage and generate alerts. These systems, however, are far from a panacea. Rather, they tend to overwhelm their operators with alerts, which in more than 90% of cases can be false positives. As such, the problem of false positives in intrusion detection systems is a costly issue. This paper presents research to design a hierarchical network intrusion detector, using deep learning, which protects against raising vast numbers of false positives through the design and implementation of a hierarchical NIDS. This paper presents a valuable advancement in performance by reducing the occurrence of false alarms by 87.52%. The research contained in this paper presents three contributions to knowledge. The first of these is the comparison between hierarchical systems and non-hierarchical systems to understand which would yield fewer false alarms. The second contribution is the formulation of a hierarchical approach, which was able to reduce false alarms by 87.52%. Lastly, the proposed hierarchical model was deployed in a live IoT environment, exposed to genuine threats, and the performance in this environment was analysed.

BackgroundIn 2020 Globocan reported nearly 1.4 million new cases of gynaecology cancer worldwide. Cancer related fatigue has been identified as a symptom that can be present for gynaecology cancer patients many years after treatment. The current evidence around the management of this symptom suggests that exercise has the most positive outcome. However, some ambiguity remains around the evidence and whether it can address all areas of fatigue effectively. More recently, other interventions such as mindfulness have begun to show a favourable response to the management of symptoms for cancer patients. To date there has been little research that explores the feasibility of using both these interventions together in a gynaecology cancer population. This study aims to explore the feasibility of delivering an intervention that involves mindfulness and mindfulness and exercise and will explore the effect of this on fatigue, sleep, mood and quality of life.Methods/designThis randomised control trial will assess the interventions outcomes using a pre and post design and will also include a qualitative process evaluation. Participants will be randomised into one of 2 groups. One group will undertake mindfulness only and the other group will complete exercise and mindfulness. Both groups will use a mobile application to complete these interventions over 8 weeks. The mobile app will be tailored to reflect the group the participants have drawn during randomisation. Self-reported questionnaire data will be assessed at baseline prior to commencing intervention and at post intervention. Feasibility will be assessed through recruitment, adherence, retention and attrition. Acceptability and participant perspective of participation (process evaluation), will be explored using focus groups.DiscussionThis trial will hope to evidence and demonstrate that combination of two interventions such as mindfulness and exercise will further improve outcomes of fatigue and wellbeing in gynaecology cancer. The results of this study will be used to assess (i) the feasibility to deliver this type of intervention to this population of cancer patients using a digital platform; (ii) assist this group of women diagnosed with cancer to manage fatigue and other symptoms of sleep, mood and impact their quality of life.Trial registrationNCT05561413.

Smartphone-based approaches for Human Activity Recognition have become prevalent in recent years. Despite the amount of research undertaken in the field, issues such as cross-subject variability are still posing an obstacle to the deployment of solutions in large scale, free-living settings. Personalized methods (i.e. aiming to adapt a generic classifier to a specific target user) attempt to solve this problem. The lack of labeled data for training purposes, however, represents a major barrier. This is especially the case when taking into consideration that personalization generally requires labeled data to be user-specific. This paper presents a novel personalization method combining a semi-population based approach with user adaptation. Personalization is achieved through the following. Firstly, the proposed method identifies a subset of users from the available population as best candidates for initializing the classifier to the target user. Subsequently, a semi-population Neural Network classifier is trained using data from this subset of users. The classifier's network weights are then updated using a small amount of labeled data from the target user subsequently implementing personalization. This approach was validated on a large publicly available dataset collected in a free-living scenario. The personalized approach using the proposed method has shown to improve the overall F-score to 74.4% compared to 70.9% when using a generic non-personalized approach. Results obtained, with statistical significance being confirmed on a set of 57 users, indicate that model initialization using the semi-population approach can reduce the amount of labeled data required for personalization. As such, the proposed method for model initialization could facilitate the real-world deployment of systems implementing personalization by reducing the amount of data needed for personalization.

There is a global challenge related to the increasing number of People with Dementia (PwD) and the diminishing capacity of governments, health systems, and caregivers to provide the best care for them. Cost-effective technology solutions that enable and ensure a good quality of life for PwD via monitoring and interventions have been investigated comprehensively in the literature. The objective of this study was to investigate the challenges with the design and deployment of a Smart Home In a Box (SHIB) approach to monitoring PwD wellbeing within a care home. This could then support future SHIB implementations to have an adequate and prompt deployment allowing research to focus on the data collection and analysis aspects. An important consideration was that most care homes do not have the appropriate infrastructure for installing and using ambient sensors. The SHIB was evaluated via installation in the rooms of PwD with varying degrees of dementia at Kirk House Care Home in Belfast. Sensors from the SHIB were installed to test their capabilities for detecting Activities of Daily Living (ADLs). The sensors used were: (i) thermal sensors, (ii) contact sensors, (iii) Passive Infrared (PIR) sensors, and (iv) audio level sensors. Data from the sensors were collected, stored, and handled using a ‘SensorCentral’ data platform. The results of this study highlight challenges and opportunities that should be considered when designing and implementing a SHIB approach in a dementia care home. Lessons learned from this investigation are presented in addition to recommendations that could support monitoring the wellbeing of PwD. The main findings of this study are: (i) most care home buildings were not originally designed to appropriately install ambient sensors, and (ii) installation of SHIB sensors should be adapted depending on the specific case of the care home where they will be installed. It was acknowledged that in addition to care homes, the homes of PwD were also not designed for an appropriate integration with ambient sensors. This study provided the community with useful lessons, that will continue to be applied to improve future implementations of the SHIB approach.

Objectives: To describe and critique a systematic multidisciplinary approach to user engagement, and selection and evaluation of sensor technologies for development of a sensor-based Digital Toolkit for assessment of movement in children with cerebral palsy (CP).Methods: A sequential process was employed comprising three steps: Step 1: define user requirements, by identifying domains of interest; Step 2: map domains of interest to potential sensor technologies; and Step 3: evaluate and select appropriate sensors to be incorporated into the Digital Toolkit. The process employed a combination of principles from frameworks based in either healthcare or technology design.Results: A broad range of domains were ranked as important by clinicians, patients and families, and industry users. These directly informed the device selection and evaluation process that resulted in three sensor-based technologies being agreed for inclusion in the Digital Toolkit, for use in a future research study.Conclusion: This report demonstrates a systematic approach to user engagement and device selection and evaluation during the development of a sensor-based solution to a healthcare problem. It also provides a narrative on the benefits of employing a multidisciplinary approach throughout the process. This work uses previous frameworks for evaluating sensor technologies and expands on the methods used for user engagement.

The accurate recognition of activities is fundamental for following up on the health progress of people with dementia (PwD), thereby supporting subsequent diagnosis and treatments. When monitoring the activities of daily living (ADLs), it is feasible to detect behaviour patterns, parse out the disease evolution, and consequently provide effective and timely assistance. However, this task is affected by uncertainties derived from the differences in smart home configurations and the way in which each person undertakes the ADLs. One adjacent pathway is to train a supervised classification algorithm using large-sized datasets; nonetheless, obtaining real-world data is costly and characterized by a challenging recruiting research process. The resulting activity data is then small and may not capture each person’s intrinsic properties. Simulation approaches have risen as an alternative efficient choice, but synthetic data can be significantly dissimilar compared to real data. Hence, this paper proposes the application of Partial Least Squares Regression (PLSR) to approximate the real activity duration of various ADLs based on synthetic observations. First, the real activity duration of each ADL is initially contrasted with the one derived from an intelligent environment simulator. Following this, different PLSR models were evaluated for estimating real activity duration based on synthetic variables. A case study including eight ADLs was considered to validate the proposed approach. The results revealed that simulated and real observations are significantly different in some ADLs (p-value < 0.05), nevertheless synthetic variables can be further modified to predict the real activity duration with high accuracy (R2(pred)>90%).

Research interests spanning numerous domains increasingly rely upon computational systems which can store and process a large volume of variable data that is stored at high velocity-representing a big data problem. This is particularly notable within the domain of ubiquitous and pervasive computing. This domain increasingly relies on storage and retrieval of sensor data to enable outcomes such as predictive analytics and activity recognition. Several current big data platforms exist; however, they have a range of deficiencies including lack of generic interoperability with agnostic sensors and an absence of features supporting academic research. Due to these deficiencies a custom, research oriented, high performance, and big data platform was devised and implemented. This platform is called SensorCentral and is presented within this paper. SensorCentral provides a framework which enables interoperability with a large range of agnostic sensor devices whilst simultaneously providing features which support research. Research supporting features include; facility to define experiments, ability to annotate experimental instances via purpose-built mobile applications, integrated machine learning functionality, facility to export data sets, rule-based classification and an extensible platform. The flagship implementation of this platform has been in operation for over 28 months within a University research group and has been successfully integrated with a range of sensors from a variety of manufacturers. This implementation currently stores over 850 million records and has been central to several research and industrial projects. Future work will integrate this platform into the open data initiative enabling collaboration with the international community of researchers.

INTRODUCTION: Dementia is a syndrome characterised by a decline in memory, language, and problem-solving thataffects the ability of patients to perform everyday activities. Patients with dementia tend to experience episodes of anxietyand remain for extended periods, which affects their quality of life.OBJECTIVES: To design AnxiDetector, a system capable of detecting patterns of sounds associated before and during themanifestation of anxiety in patients with dementia.METHODS: We conducted a non-participatory observation of 70 diagnosed patients in-situ, and conducted semi-structuredinterviews with four caregivers at a residential centre. Using the findings from our observation and caregiver interviews, wedeveloped the AnxiDetector prototype and tested this in an experimental setting where we defined nine classes of audio torepresent two groups of sounds: (i) Disturbance which includes audio files that characterise sounds that trigger anxiety inpatients with dementia, and (ii) Expression which includes audio files that characterise sounds expressed by the patientsduring episodes of anxiety. We conducted two experimental classifications of sounds using (i) a Neural Network modeltrained and (ii) a Support Vector Machine model. The first evaluation consists of a binary discriminating between the twogroups of sounds; the second evaluation discriminates the nine classes of audio. The audio resources were retrieved frompublicly available datasets.RESULTS: The qualitative results present the views of the caregivers on the adoption of AnxiDetector. The quantitativeresults from our binary discrimination show a classification accuracy of 98.1% and 99.2% for the Deep Neural Network andSupport Vector Machine models, respectively. When classifying the nine classes of sound, our model shows a classificationaccuracy of 92.2%. Whereas, the Support Vector Machine model yielded an overall classification accuracy of 93.0%.CONCLUSION: In this paper, we presented the outcomes from an observational study in-site at a residential care centre,qualitative findings from interviews with caregivers, the design of AnxiDetector, and preliminary qualitative results of amethodology devised to detect relevant acoustic events associated with anxiety in patients with dementia. We conclude bysignalling future plans to conduct in-situ validation of the effectiveness of AnxiDetector for anxiety detection.

Activity recognition has received considerable attention in many research fields, such as industrial and healthcare fields. However, many researches about activity recognition have focused on static activities and dynamic activities in current literature, while, the transitional activities, such as stand-to-sit and sit-to-stand, are more difficult to recognize than both of them. Consider that it may be important in real applications. Thus, a novel framework is proposed in this paper to recognize static activities, dynamic activities, and transitional activities by utilizing stacked denoising autoencoders (SDAE), which is able to extract features automatically as a deep learning model rather than utilize manual features extracted by conventional machine learning methods. Moreover, the resampling technique (random oversampling) is used to improve problem of unbalanced samples due to relatively short duration characteristic of transitional activity. The experiment protocol is designed to collect twelve daily activities (three types) by using wearable sensors from 10 adults in smart lab of Ulster University, the experiment results show the significant performance on transitional activity recognition and achieve the overall accuracy of 94.88% on three types of activities. The results obtained by comparing with other methods and performances on other three public datasets verify the feasibility and priority of our framework. This paper also explores the effect of multiple sensors (accelerometer and gyroscope) to determine the optimal combination for activity recognition.

The recognition of activities of daily living (ADL) in smart environments is a well-known and an important research area, which presents the real-time state of humans in pervasive computing. The process of recognizing human activities generally involves deploying a set of obtrusive and unobtrusive sensors, pre-processing the raw data, and building classification models using machine learning (ML) algorithms. Integrating data from multiple sensors is a challenging task due to dynamic nature of data sources. This is further complicated due to semantic and syntactic differences in these data sources. These differences become even more complex if the data generated is imperfect, which ultimately has a direct impact on its usefulness in yielding an accurate classifier. In this study, we propose a semantic imputation framework to improve the quality of sensor data using ontology-based semantic similarity learning. This is achieved by identifying semantic correlations among sensor events through SPARQL queries, and by performing a time-series longitudinal imputation. Furthermore, we applied deep learning (DL) based artificial neural network (ANN) on public datasets to demonstrate the applicability and validity of the proposed approach. The results showed a higher accuracy with semantically imputed datasets using ANN. We also presented a detailed comparative analysis, comparing the results with the state-of-the-art from the literature. We found that our semantic imputed datasets improved the classification accuracy with 95.78% as a higher one thus proving the effectiveness and robustness of learned models.

Human activity recognition (HAR) is a popular field of study. The outcomes of the projects in this area have the potential to impact on the quality of life of people with conditions such as dementia. HAR is focused primarily on applying machine learning classifiers on data from low level sensors such as accelerometers. The performance of these classifiers can be improved through an adequate training process. In order to improve the training process, multivariate outlier detection was used in order to improve the quality of data in the training set and, subsequently, performance of the classifier. The impact of the technique was evaluated with KNN and random forest (RF) classifiers. In the case of KNN, the performance of the classifier was improved from 55.9% to 63.59%.

Automatic detection and recognition of Activities of Daily Living (ADL) are crucial for providing effective care to frail older adults living alone. A step forward in addressing this challenge is the deployment of smart home sensors capturing the intrinsic nature of ADLs performed by these people. As the real-life scenario is characterized by a comprehensive range of ADLs and smart home layouts, deviations are expected in the number of sensor events per activity (SEPA), a variable often used for training activity recognition models. Such models, however, rely on the availability of suitable and representative data collection and is habitually expensive and resource-intensive. Simulation tools are an alternative for tackling these barriers; nonetheless, an ongoing challenge is their ability to generate synthetic data representing the real SEPA. Hence, this paper proposes the use of Poisson regression modelling for transforming simulated data in a better approximation of real SEPA. First, synthetic and real data were compared to verify the equivalence hypothesis. Then, several Poisson regression models were formulated for estimating real SEPA using simulated data. The outcomes revealed that real SEPA can be better approximated ( R pred 2 = 92.72 % ) if synthetic data is post-processed through Poisson regression incorporating dummy variables.

In this paper we discuss the design and evaluation of a mobile based tool to collect activity data on a large scale. The current approach, based on an existing activity recognition module, recognizes class transitions from a set of specific activities (for example walking and running) to the standing still activity. Once this transition is detected the system prompts the user to provide a label for their previous activity. This label, along with the raw sensor data, is then stored locally prior to being uploaded to cloud storage. The system was evaluated by ten users. Three evaluation protocols were used, including a structured, semi-structured and free living protocol. Results indicate that the mobile application could be used to allow the user to provide accurate ground truth labels for their activity data. Similarities of up to 100% where observed when comparing the user prompted labels and those from an observer during structured lab based experiments. Further work will examine data segmentation and personalization issues in order to refine the system.

The school of computing, in collaboration with the institute of nursing and health research and the school of engineering, recently established the connected health living lab (CH:LL) at Ulster University. CH:LL offers a dedicated environment to support user and clinical engagement, access to state-of-the-art technology to assess usability and interaction with innovative technologies, in addition to being a dedicated environment to record user behaviours with new connected health solutions. The creation of such a dedicated environment offers a range of benefits to support multi-disciplinary research in the area of connected health. This paper illustrates the design, development, and implementation of CH:LL, including a description of the various technologies associated with the living lab at Ulster University. To conclude, the paper highlights how these resources have been used to date within various research projects.

Pressure ulcers affect the quality of life and health level of patients while causing a cost increase for the health system. Despite all of this, there is no monitoring system for this disease, even though it is very common in hospitalized patients. To resolve this issue, in this work, we present a prototype for monitoring and caring of pressure ulcers, through an intelligent system based on wearable inertial devices. The system detects the position of patients with reduced mobility while in bed, walking, or standing; providing, to medical staff and caregivers, useful information by means of mobile devices, in particular: (i) A historical record of body activity and (ii) notifications when a single position persists for a prolonged period of time. The following contributions are presented in this paper. Firstly, a technological survey of healthcare systems applied to pressure ulcers is presented. Secondly, an architecture and a methodology for modelling wearable inertial sensors for classifying body position are proposed. Finally, experimental tests with real cases were conducted to evaluate machine learning approaches and to validate the position estimation of the case study developed with four participants.

Activity recognition, a key component in pervasive healthcare monitoring, relies on classification algorithms that require labeled data of individuals performing the activity of interest to train accurate models. Labeling data can be performed in a lab setting where an individual enacts the activity under controlled conditions. The ubiquity of mobile and wearable sensors allows the collection of large datasets from individuals performing activities in naturalistic conditions. Gathering accurate data labels for activity recognition is typically an expensive and time-consuming process. In this paper we present two novel approaches for semi-automated online data labeling performed by the individual executing the activity of interest. The approaches have been designed to address two of the limitations of self-annotation: (i) The burden on the user performing and annotating the activity, and (ii) the lack of accuracy due to the user labeling the data minutes or hours after the completion of an activity. The first approach is based on the recognition of subtle finger gestures performed in response to a data-labeling query. The second approach focuses on labeling activities that have an auditory manifestation and uses a classifier to have an initial estimation of the activity, and a conversational agent to ask the participant for clarification or for additional data. Both approaches are described, evaluated in controlled experiments to assess their feasibility and their advantages and limitations are discussed. Results show that while both studies have limitations, they achieve 80% to 90% precision.

This article describes an investigation to determine the optimal placement of accelerometers for the purpose of detecting a range of everyday activities. The paper investigates the effect of combining data from accelerometers placed at various bodily locations on the accuracy of activity detection. Eight healthy males participated within the study. Data were collected from six wireless tri-axial accelerometers placed at the chest, wrist, lower back, hip, thigh and foot. Activities included walking, running on a motorized treadmill, sitting, lying, standing and walking up and down stairs. The Support Vector Machine provided the most accurate detection of activities of all the machine learning algorithms investigated. Although data from all locations provided similar levels of accuracy, the hip was the best single location to record data for activity detection using a Support Vector Machine, providing small but significantly better accuracy than the other investigated locations. Increasing the number of sensing locations from one to two or more statistically increased the accuracy of classification. There was no significant difference in accuracy when using two or more sensors. It was noted, however, that the difference in activity detection using single or multiple accelerometers may be more pronounced when trying to detect finer grain activities. Future work shall therefore investigate the effects of accelerometer placement on a larger range of these activities.

Activity recognition (AR) is a subtask in pervasive computing and context-aware systems, which presents the physical state of human in real-time. These systems offer a new dimension to the widely spread applications by fusing recognized activities obtained from the raw sensory data generated by the obtrusive as well as unobtrusive revolutionary digital technologies. In recent years, an exponential growth has been observed for AR technologies and much literature exists focusing on applying machine learning algorithms on obtrusive single modality sensor devices. However, University of Jaén Ambient Intelligence (UJAmI), a Smart Lab in Spain has initiated a 1st UCAmI Cup challenge by sharing aforementioned varieties of the sensory data in order to recognize the human activities in the smart environment. This paper presents the fusion, both at the feature level and decision level for multimodal sensors by preprocessing and predicting the activities within the context of training and test datasets. Though it achieves 94% accuracy for training data and 47% accuracy for test data. However, this study further evaluates post-confusion matrix also and draws a conclusion for various discrepancies such as imbalanced class distribution within the training and test dataset. Additionally, this study also highlights challenges associated with the datasets for which, could improve further analysis.

The Human Health and Activity Laboratory (H2Al) is a new research facility at Luleå University of Technology implemented during 2018 as a smart home environment in an educational training apartment for nurses and therapists at the Luleå campus. This paper presents the design and implementation of the lab together with a discussion on potential impact. The aim is to identify and overcome economical, technical and social barriers to achieve an envisioned good and equal health and welfare within and from home environments. The lab is equipped with multiple sensor and actuator systems in the environment, worn by persons and based on digital information. The systems will allow for advanced capture, filtering, analysis and visualization of research data such as A/V, EEG, ECG, EMG, GSR, respiration and location while being able to detect falls, sleep apnea and other critical health and wellbeing issues. The resulting studies will be aimed towards supporting and equipping future home environments and care facilities, spanning from temporary care to primary care at hospitals, with technologies for activity and critical health and wellness issue detection. The work will be conducted at an International level and within a European context, based on a collaboration with other smart labs, such that experiments can be replicated at multiple sites. This paper presents some initial lessons learnt including design, setup and configuration for comparison of sensor placements and configurations as well as analytical methods.

The global population is ageing, as a consequence of this there will be a greater incidence of ageing related illnesses which cause cognitive impairment–such as Alzheimer’s disease. Within residential care homes, such cognitive impairment can lead to wandering of individuals beyond the boundaries of safety provided. This wandering, particularly in urban areas can be life threatening. This study introduces a novel solution to detect, and alert caregivers of, egress of at-risk inhabitants of a care home. This solution operates through a combination of wearable Bluetooth beacons and beam-formed listening devices. In an evaluation process involving 275 egress events, this solution proved to offer accurate operation with no incidence of false positives. Notably, this solution has been deployed within a real residential care home environment for over 12 months. Proposed future work discusses improvements to this solution.

Data driven approaches for human activity recognition learn from pre-existent large-scale datasets to generate a classification algorithm that can recognize target activities. Typically, several activities are represented within such datasets, characterized by multiple features that are computed from sensor devices. Often, some features are found to be more relevant to particular activities, which can lead to the classification algorithm providing less accuracy in detecting the activity where such features are not so relevant. This work presents an experimentation for human activity recognition with features derived from the acceleration data of a wearable device. Specifically, this work analyzes which features are most relevant for each activity and furthermore investigates which classifier provides the best accuracy with those features. The results obtained indicate that the best classifier is the k-nearest neighbor and furthermore, confirms that there do exist redundant features that generally introduce noise into the classification, leading to decreased accuracy.

Data annotation is a time-consuming process posing major limitations to the development of Human Activity Recognition (HAR) systems. The availability of a large amount of labeled data is required for supervised Machine Learning (ML) approaches, especially in the case of online and personalized approaches requiring user specific datasets to be labeled. The availability of such datasets has the potential to help address common problems of smartphone-based HAR, such as inter-person variability. In this work, we present (i) an automatic labeling method facilitating the collection of labeled datasets in free-living conditions using the smartphone, and (ii) we investigate the robustness of common supervised classification approaches under instances of noisy data. We evaluated the results with a dataset consisting of 38 days of manually labeled data collected in free living. The comparison between the manually and the automatically labeled ground truth demonstrated that it was possible to obtain labels automatically with an 80–85% average precision rate. Results obtained also show how a supervised approach trained using automatically generated labels achieved an 84% f-score (using Neural Networks and Random Forests); however, results also demonstrated how the presence of label noise could lower the f-score up to 64–74% depending on the classification approach (Nearest Centroid and Multi-Class Support Vector Machine).