Search

Prostate cancer is the most common cancer in men and it is estimated that over 350,000 men worldwide die of prostate cancer every year. There remains an unmet clinical need to improve how clinically significant prostate cancer is diagnosed and develop new treatments for advanced disease. Aberrant glycosylation is a hallmark of cancer implicated in tumour growth, metastasis, and immune evasion. One of the key drivers of aberrant glycosylation is the dysregulated expression of glycosylation enzymes within the cancer cell. Here, we demonstrate using multiple independent clinical cohorts that the glycosyltransferase enzyme GALNT7 is upregulated in prostate cancer tissue. We show GALNT7 can identify men with prostate cancer, using urine and blood samples, with improved diagnostic accuracy than serum PSA alone. We also show that GALNT7 levels remain high in progression to castrate-resistant disease, and using in vitro and in vivo models, reveal that GALNT7 promotes prostate tumour growth. Mechanistically, GALNT7 can modify O-glycosylation in prostate cancer cells and correlates with cell cycle and immune signalling pathways. Our study provides a new biomarker to aid the diagnosis of clinically significant disease and cements GALNT7-mediated O-glycosylation as an important driver of prostate cancer progression.

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.

Nurses welcome innovative training and assessment methods to effectively interpret physiological vital signs. The objective is to determine if eye-tracking technology can be used to develop biometrics for automatically predict the performance of nurses whilst they interact with computer-based simulations. A total of 47 nurses were recruited, 36 nursing students (training group) and 11 coronary care nurses (qualified group). Each nurse interpreted five simulated vital signs scenarios whilst “thinking-aloud.” The participant's visual attention (eye-tracking metrics), verbalisation, heart rate, confidence level (1–10, 10 = most confident), and cognitive load (NASA-TLX) were recorded during performance. Scenario performances were scored out of ten. Analysis was used to find patterns between the eye-tracking metrics and performance score. Multiple linear regression was used to predict performance score using eye tracking metrics. The qualified group scored higher than the training group (6.85 ± 1.5 versus 4.59 ± 1.61, p = p = R 2 = 0.80, p =

Situation awareness may be inferred from user context such as body posture transition and location data. Smartphones and smart homes incorporate sensors that can record this information without significant inconvenience to the user. Algorithms were developed to classify activity postures to infer current situations; and to measure user's physical location, in order to provide context that assists such interpretation. Location was detected using a subarea-mapping algorithm; activity classification was performed using a hierarchical algorithm with backward reasoning; and falls were detected using fused multiple contexts (current posture, posture transition, location, and heart rate) based on two models: “certain fall” and “possible fall.” The approaches were evaluated on nine volunteers using a smartphone, which provided accelerometer and orientation data, and a radio frequency identification network deployed at an indoor environment. Experimental results illustrated falls detection sensitivity of 94.7% and specificity of 85.7%. By providing appropriate context the robustness of situation recognition algorithms can be enhanced.

The use of Convolutional Neural Networks (CNNs) as a feature learning method for Human Activity Recognition (HAR) is becoming more and more common. Unlike conventional machine learning methods, which require domain-specific expertise, CNNs can extract features automatically. On the other hand, CNNs require a training phase, making them prone to the cold-start problem. In this work, a case study is presented where the use of a pre-trained CNN feature extractor is evaluated under realistic conditions. The case study consists of two main steps: (1) different topologies and parameters are assessed to identify the best candidate models for HAR, thus obtaining a pre-trained CNN model. The pre-trained model (2) is then employed as feature extractor evaluating its use with a large scale real-world dataset. Two CNN applications were considered: Inertial Measurement Unit (IMU) and audio based HAR. For the IMU data, balanced accuracy was 91.98% on the UCI-HAR dataset, and 67.51% on the real-world Extrasensory dataset. For the audio data, the balanced accuracy was 92.30% on the DCASE 2017 dataset, and 35.24% on the Extrasensory dataset.

Rapid serial visual presentation (RSVP) based brain-computer interfaces (BCIs) can detect target images among a continuous stream of rapidly presented images, by classifying a viewer’s event related potentials (ERPs) associated with the target and non-targets images. Whilst the majority of RSVP-BCI studies to date have concentrated on the identification of a single type of image, namely pictures , here we study the capability of RSVP-BCI to detect three different target image types: pictures, numbers and words . The impact of presentation duration (speed) i.e., 100–200ms (5–10Hz), 200–300ms (3.3–5Hz) or 300–400ms (2.5–3.3Hz), is also investigated. 2-way repeated measure ANOVA on accuracies of detecting targets from non-target stimuli (ratio 1:9) measured via area under the receiver operator characteristics curve (AUC) for ${N}={15}$ subjects revealed a significant effect of factor Stimulus-Type ( pictures, numbers, words ) (F (2,28) = 7.243, ${p} = {0.003}$ ) and for Stimulus-Duration (F (2,28) = 5.591, p = 0.011). Furthermore, there is an interaction between stimulus type and duration: F (4,56) = 4.419, ${p} = {0.004}$ ). The results indicate that when designing RSVP-BCI paradigms, the content of the images and the rate at which images are presented impact on the accuracy of detection and hence these parameters are key experimental variables in protocol design and applications, which apply RSVP for multimodal image datasets.

Life-logging utilises sensor technology to automate the capture of a person’s interaction with their environment. This produces useful information to assess wellbeing, but this information is often buried within the volume of data. In this chapter, we analyse a life-log comprising image data and contextual information and apply algorithms to collate, mine and categorise the data. Four approaches were investigated: (i) Self-reporting of important events by the person who collected the data; (ii) Clustering of images into location-based events using GPS metadata, (iii) Face detection within the images and (iv) Physiological monitoring using Galvanic Skin Response (GSR); as a way to identify more meaningful images. Using a bespoke wearable system, comprising a smartphone and smartwatch, six healthy participants recorded a life-log in the form of images of their surroundings coupled with metadata in the form of timestamps, GPS locations, accelerometer data and known social interactions. Following approximately 2.5 h of recording, the data reduction methodologies outlined above were applied to each participant’s dataset, yielding an 80–86% reduction in size which facilitates more realistic self-quantification. However, each approach has some shortcomings and the data reduction method used will need personalisation and depend on the intended application.

Prostate is the most frequent cancer in men. Prostate cancer progression is driven by androgen steroid hormones, and delayed by androgen deprivation therapy (ADT). Androgens control transcription by stimulating androgen receptor (AR) activity, yet also control pre-mRNA splicing through less clear mechanisms. Here we find androgens regulate splicing through AR-mediated transcriptional control of the epithelial-specific splicing regulatorESRP2. BothESRP2and its close paralogESRP1are highly expressed in primary prostate cancer. Androgen stimulation induces splicing switches in many endogenous ESRP2-controlled mRNA isoforms, including a key splicing switch in the metastatic regulatorFLNBwhich is associated with disease relapse.ESRP2expression in clinical prostate cancer is repressed by ADT, which may thus inadvertently dampen epithelial splice programmes. Supporting this,FLNBsplicing was reciprocally switched by the AR antagonist bicalutamide (Casodex®). Our data reveal a new mechanism of splicing control in prostate cancer with important implications for metastatic disease progression.Key pointsTranscriptional regulation of ESRP2 by the androgen receptor controls splice isoform patterns in prostate cancer cells.Splicing switches regulated by the androgen-ESRP2 axis include a splice isoform in theFLNBgene that is a known metastatic driver.Both ESRP1 and ESRP2 are highly expressed in prostate cancer tissue.Ectopic expression of ESRP1 and 2 inhibits prostate cancer cell growth.By repressing ESRP2 expression androgen deprivation therapy (ADT) may dampen epithelial splicing programmes to inadvertently prime disease progression towards metastasis.

Monitoring air quality is set to become more important at home, in the workplace and at social venues, particularly regarding promoting wellness and safeguarding social interaction. We present a didactic approach to implementing indoor air quality monitoring using an Internet of Things (IoT) solution, based upon low cost air quality sensors and edge computing nodes. We provide a tutorial that allows this solution to be replicated; similar solutions could have widespread use. Our test implementation monitored kitchen and study, each equipped with a Bosch BME680 sensor connected to a microcontroller for data transmission to a local server for storage on a database. A web based dashboard allowed for the feedback of sensor data. Two, 2-week data collection periods were undertaken to demonstrate the proof of concept. The first period was in the summer 2020 and the second in the autumn 2020 (during coronavirus ‘lockdown’ conditions). Analysis of the data showed a strong relationship between humidity and air quality (correlation coefficients of −0.624 in summer and −0.692 in autumn), with air quality degrading in the autumn. As humidity increases, air quality decreases; temperature has a weaker relationship with air quality. Further analysis showed that cleaning products can adversely impact on the air quality. Poor air quality can be mitigated by opening a window to speed up the dissipation rate of pollutants. The quantification of indoor air quality can inform activities such as cooking, heating, usage of disinfectants and monitoring of ventilation, which can potentially benefit of people with respiratory illness.

Introduction Unobtrusive metrics that can auto-assess performance during clinical procedures are of value. Three approaches to deriving wearable technology-based metrics are explored: (1) eye tracking, (2) psychophysiological measurements [e.g. electrodermal activity (EDA)] and (3) arm and hand movement via accelerometry. We also measure attentional capacity by tasking the operator with an additional task to track an unrelated object during the procedure. Methods Two aspects of performance are measured: (1) using eye gaze and psychophysiology metrics and (2) measuring attentional capacity via an additional unrelated task (to monitor a visual stimulus/playing cards). The aim was to identify metrics that can be used to automatically discriminate between levels of performance or at least between novices and experts. The study was conducted using two groups: (1) novice operators and (2) expert operators. Both groups made two attempts at a coronary angiography procedure using a full-physics virtual reality simulator. Participants wore eye tracking glasses and an E4 wearable wristband. Areas of interest were defined to track visual attention on display screens, including: (1) X-ray, (2) vital signs, (3) instruments and (4) the stimulus screen (for measuring attentional capacity). Results Experts provided greater dwell time (63% vs 42%, p = 0.03) and fixations (50% vs 34%, p = 0.04) on display screens. They also provided greater dwell time (11% vs 5%, p = 0.006) and fixations (9% vs 4%, p = 0.007) when selecting instruments. The experts’ performance for tracking the unrelated object during the visual stimulus task negatively correlated with total errors (r = − 0.95, p = 0.0009). Experts also had a higher standard deviation of EDA (2.52 µS vs 0.89 µS, p = 0.04). Conclusions Eye tracking metrics may help discriminate between a novice and expert operator, by showing that experts maintain greater visual attention on the display screens. In addition, the visual stimulus study shows that an unrelated task can measure attentional capacity. Trial registration This work is registered through clinicaltrials.gov, a service of the U.S. National Health Institute, and is identified by the trial reference: NCT02928796.

In Human Activity Recognition (HAR), supervised Machine Learning methods are predominantly used, making availability of datasets a major issue for research in the field. In particular, the majority of available datasets are collected under controlled conditions. Consequently, models trained under similar circumstances, generally exhibit a significant decrease in recognition accuracy when they are moved to final deployment in the wild, within unconstrained settings. This paper presents a new dataset for HAR, collected in free-living and unconstrained conditions. 10 subjects were recruited for the purpose of data collection. Data was recorded over a 6 week period using a smartphone app, and a wristband activity monitor. During the first and last week of observation, participants also wore an ActivPAL" activity logger. The data collected have been partially self-labeled by participants, by means of the mobile app provided for data collection. The dataset collected can be used to evaluate HAR algorithm and models in real-world unconstrained settings. Together with the description of the dataset, this work presents some preliminary results, obtained cross-validating a model trained on the publicly available Extrasensory dataset, and testing its performance on our newly collected dataset. Results obtained highlighted high cross-subject variability when testing on new subjects, with a balanced accuracy varying between 53.33% and 90.01%, with an average balanced accuracy of 71.73%.

Rigorous peer-review is the corner-stone of high-quality academic publishing [...]

Deep learning techniques such as Convolutional Neural Networks (CNNs) have shown good results in activity recognition. One of the advantages of using these methods resides in their ability to generate features automatically. This ability greatly simplifies the task of feature extraction that usually requires domain specific knowledge, especially when using big data where data driven approaches can lead to anti-patterns. Despite the advantage of this approach, very little work has been undertaken on analyzing the quality of extracted features, and more specifically on how model architecture and parameters affect the ability of those features to separate activity classes in the final feature space. This work focuses on identifying the optimal parameters for recognition of simple activities applying this approach on both signals from inertial and audio sensors. The paper provides the following contributions: (i) a comparison of automatically extracted CNN features with gold standard Human Crafted Features (HCF) is given, (ii) a comprehensive analysis on how architecture and model parameters affect separation of target classes in the feature space. Results are evaluated using publicly available datasets. In particular, we achieved a 93.38% F-Score on the UCI-HAR dataset, using 1D CNNs with 3 convolutional layers and 32 kernel size, and a 90.5% F-Score on the DCASE 2017 development dataset, simplified for three classes (indoor, outdoor and vehicle), using 2D CNNs with 2 convolutional layers and a 2x2 kernel size.

In this chapter, we discuss the motivation for the hybrid brain–computer interface (BCI) and review progress toward more robust user interaction from existing studies. In addition, we discuss the design and development of a hybrid brain–computer interface (hBCI) example that combines two symbiotic modalities: steady-state visual evoked potential and eye gaze technology. By adopting a modular design, we show that it has been possible to implement such hybridization by integrating mostly existing software components and, indeed, facilitate future updates to the system that will be necessary as hardware, software, and interfaces continue to evolve.

Sedentary lifestyle and inadequate levels of physical activity represent two serious health risk factors. Nevertheless, within developed countries, 60% of people aged over 60 are deemed to be sedentary. Consequently, interest in behavior change to promote physical activity is increasing. In particular, the role of emerging mobile apps to facilitate behavior change has shown promising results. Smart technologies can help in providing rich context information including an objective assessment of the level of physical activity and information on the emotional and physiological state of the person. Collectively, this can be used to develop innovative persuasive solutions for adaptive behavior change. Such solutions offer potential in reducing levels of sedentary behavior. This work presents a study exploring new ways of employing smart technologies to facilitate behavior change. It is achieved by means of (i) developing a knowledge base on sedentary behaviors and recommended physical activity guidelines, and (ii) a context model able to combine information on physical activity, location, and a user's diary to develop a context-aware virtual coach with the ability to select the most appropriate behavior change strategy on a case by case basis.

BackgroundHome-based self-monitoring has failed to show intended savings to healthcare budgets yet it continues to emerge and gain popularity.ObjectiveWe set out to verify stakeholders’ perspectives of remote vital sign telemonitoring.DesignAn observational design was adopted by devising a survey for distribution to service users and their informal carers.SampleService users in South Eastern Health and Social Care Trust were included. A total of 274 questionnaires were issued. Data from 97 patients (35% response rate) and 49 carers were analysed. Of these, 81 patients and 48 of their carers experienced a monitoring service known as TF3 and 16 patients and 1 carer experienced a service known as U-Tell. The cohorts comprised people living with a number of long-term conditions: diabetes, hypertension after stroke, chronic heart failure, chronic obstructive pulmonary disorder, bronchiectasis and those requiring anticoagulation using warfarin.ResultsAnalysis showed that respondents were supportive of the technology with 90.7% of patients agreeing or strongly agreeing with the statement: the remote monitoring system assisted me in managing my health on a day-to-day basis. The patients liked the technology largely because it provided empowerment and control for self-management and allowed them to continue with their lives without major disruption. These views were independent of the technology used and not associated with the patient’s long-term conditions, gender or age. There were no reported adverse incidents.ConclusionAs self-monitoring becomes more relevant to healthcare delivery, the technology will be accepted by many in the population with long-term conditions.

A real-time activity monitoring system within an Android based smartphone is proposed and evaluated. Motion and motionless postures may be classified using principles of kinematical theory, which underpins hierarchical rule-based algorithms, based on accelerometer and orientation data. Falls detection was implemented by analyzing whether the postures classified as `lying' or `sit-tilted' posture are deemed normal or abnormal, based on the analysis of time, users' current position and posture transition. Experimental results demonstrate that the approach can detect various types of falls efficiently (i.e., in real-time within a smart phone processor) and also correctly (95 % and 93 % true positives for falls ending with `lying' and `sit-tilted' respectively). The approach is reliable for different subjects and different situations, since it is not only based on empirical thresholds and subject-based training models, but in addition it is underpinned by theory.

Strategies to support people living with dementia are broad in scope, proposing both pharmacological and non-pharmacological interventions as part of the care pathway. Assistive technologies form part of this offering as both stand-alone devices to support particular tasks and the more complex offering of the “smart home” to underpin ambient assisted living. This paper presents a technology-based system, which expands on the smart home architecture, orientated to support people with daily living. The system, NOCTURNAL, was developed by working directly with people who had dementia, and their carers using qualitative research methods. The research focused primarily on the nighttime needs of people living with dementia in real home settings. Eight people with dementia had the final prototype system installed for a three month evaluation at home. Disturbed sleep patterns, night-time wandering were a focus of this research not only in terms of detection by commercially available technology but also exploring if automated music, light and visual personalized photographs would be soothing to participants during the hours of darkness. The NOCTURNAL platform and associated services was informed by strong user engagement of people with dementia and the service providers who care for them. NOCTURNAL emerged as a holistic service offering a personalised therapeutic aspect with interactive capabilities.

There is growing interest in the development of ambient assisted living services to increase the quality of life of the increasing proportion of the older population. We report on the Night Optimised Care Technology for UseRs Needing Assisted Lifestyles project, which provides specialised night time support to people at early stages of dementia. This article explains the technical infrastructure, the intelligent software behind the decision-making driving the system, the software development process followed, the interfaces used to interact with the user, and the findings and lessons of our user-centred approach.

Brain Computer Interface (BCI) technology offers potential for human augmentation in areas ranging from communication to home automation, leisure and gaming. This paper addresses ethical challenges associated with the wider scale deployment of BCI as an assistive technology by documenting issues associated with the development of non-invasive BCI technology. Laboratory testing is normally carried out with volunteers but further testing with subjects, who may be in vulnerable groups is often needed to improve system operation. BCI development is technically complex, sometimes requiring lengthy recording sessions to achieve the necessary personalisation of the paradigms, and this can present ethical challenges that vary depending on the subject group. The paper contributes to the on-going ethical discussion surrounding the deployment BCI outside the specialist laboratory and suggests some tentative guidelines for BCI research teams, appropriate to those deploying the technology, derived from experience on a multisite project. Any tension between deployment and technical progress must be managed by a formal process within a multidisciplinary consortium.

This fictional prototype explores two of the future's major societal challenges: the delivery of healthcare to an increasingly ageing society; and the policing of a society, in which digital surveillance may predominate. It contrasts the author's vision of what life could be like in the United Kingdom in a decade's time (just as he contemplates retirement) with the simpler values of the 1980's, when he began his postgraduate career. The lyrics of the poignant 1982 Bruce Springsteen song, “Highway Patrolman”1 are used to bridge the epochs. The prototype relocates the two main ‘middle-America’ characters, brothers Joe and Frank Roberts, in London in the year 2025. Much has already changed politically and socially in ‘Western societies’ in the intervening period up to 2012, driven by the inexorable advances of technology. As further scientific advances drive us to an anticipated paradigm change2, one can only speculate on how society will advance, posing serious ethical dilemmas. Many of the changes will be positive. However, the story explores the potential negative consequences to the ageing population, in what appears to be a successful economy. Although somewhat pessimistic in outlook, a hopeful conclusion is that the ‘ties that bind’ will still predominate.

International audience; Rapid serial visual presentation (RSVP) combined with the detection of event related brain responses facilitates the selection of relevant information contained in a stream of images presented rapidly to a human. Event related potentials (ERPs) measured non-invasively with electroencephalography (EEG) can be associated with infrequent targets amongst a stream of images. Human-machine symbiosis may be augmented by enabling human interaction with a computer, without overt movement, and/or enable optimization of image/information sorting processes involving humans. Features of the human visual system impact on the success of the RSVP paradigm, but pre-attentive processing supports the identification of target information post presentation of the information by assessing the co-occurrence or time-locked EEG potentials. This paper presents a comprehensive review and evaluation of the limited but significant literature on research in RSVP-based brain-computer interfaces (BCIs). Applications that use RSVP-based BCIs are categorized based on display mode and protocol design, whilst a range of factors influencing ERP evocation and detection are analyzed. Guidelines for using the RSVP-based BCI paradigms are recommended, with a view to further standardizing methods and enhancing the inter-relatability of experimental design to support future research and the use of RSVP-based BCIs in practice.

Proceedings of the 7th Graz Brain-Computer Interface Conference 2017, From Vision to Reality

Serous carcinomas most commonly arise within the uterine corpus or ovary/fallopian tube, but there are 2 prior case reports of primary vaginal serous carcinoma. We report 2 examples of high-grade serous carcinoma arising within the urethra or a urethral diverticulum (1 case each). Both neoplasms exhibited the classic morphologic features of high-grade serous carcinoma, and a combination of clinical, radiologic, and pathologic examination excluded other possible sites of primary neoplasm.

Introduction: It has yet to be determined whether visual attention, measured via eye tracking metrics (ETMs) can be indicative of performance level in coronary care nursing when interpreting patient vitals. Methods: This study captures the visual attention of nurses when interpreting five scenarios using simulated text and vital signs. Baseline performance was marked using detailed criteria and scored 0–10. Self-rated confidence from 1–10 was also collected for each scenario. Cognitive workload was assessed by measuring a participant's heart rate and post-performance NASA-TLX responses. Eleven coronary care nurses were recruited providing 55 interpretations/observations in total. 45 of which, post data quality filtering, were used to analyse ETMs. sResults: Mean performance score = 6.86±1.50 and mean confidence rating = 7.51±1.2. A subset of ETMs significantly correlate with performance across all scenarios. Individual scenarios also provide significant correlations. Three of six regression models were statistically significant with R2 ≥ 0.5. Conclusion: Correlations between specific ETMs and performance have been found across all scenarios and for individual scenarios. Further work is needed to confirm the benefit of ETM in assessing simulation-based training performance.

PurposeThis paper describes the research underpinning the development and evaluation of a brain computer interface (BCI) system designed to be suitable for domestic use by people with acquired brain injury in order to facilitate control of their home environment. The purpose of the research is to develop a robust and user‐friendly BCI system which was customisable in terms of user ability, preferences and functionality. Specifically the human interface was designed to provide consistent visual metaphors in usage, while applications change, for example, from environmental control to entertainment and communications.Design/methodology/approachThe research took a user centred design approach involving representative end‐users throughout the design and evaluation process. A qualitative study adopting user interviews alongside interactive workshops highlighted the issues that needed to be addressed in the development of a user interface for such a system. User validation then underpinned prototype development.FindingsThe findings of the research indicate that while there are still significant challenges in translating working BCI systems from the research laboratories to the homes of individuals with acquired brain injuries, participants are keen to be involved in the deign and development of such systems. In its current stage of development BCI is multi‐facetted and uses complex software, which poses a significant usability challenge. This work also found that the performance of the BCI paradigm chosen was considerably better for those users with no disability than for those with acquired brain injury. Further work is required to identify how and whether this performance gap can be addressed.Research limitations/implicationsThe research had significant challenges in terms of managing the complexity of the hardware and software set‐up and transferring the working systems to be tested by participants in their home. Furthermore, the authors believe that the development of assistive technologies for the disabled user requires a significant additional level of personalisation and intensive support to the level normally required for non‐disabled users. Coupled with the inherent complexity of BCI, this leads to technology that does not easily offer a solution to both disabled and non‐disabled users.Originality/valueThe research contributes additional findings relating to the usability of BCI systems. The value of the work is to highlight the practical issues involved in translating such systems to participants where the acquired brain injury can impact on the ability of the participant to use the BCI system.

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.

Demographic aging, as a result of people living for longer, has put an increased burden on health and social care provision across most of the economies of the developed and developing world. In order to cope with the greater numbers of older people, together with increasing prevalence of chronic diseases, governments are looking to new ways to provide care and support to older people and their care providers. A growing trend is where health and social care providers are moving towards the use of assisted living technologies to provide care and assistance in the home. In this article, the research area of Ambient Assisted Living (AAL) systems is examined and the data, information and the higher-level contextual knowledge quality issues in relation to these systems, is discussed. Lack of quality control may result in an AAL system providing assistance and support based upon incorrect data, information and knowledge inputs, and this may have a detrimental effect on the person making use of the system. We propose a model whereby contextual knowledge gained during the AAL system’s reasoning cycle can be fed back to aid in further quality checking at the various architectural layers, and a realistic AAL scenario is provided to support this. Future research should be conducted in these areas, with the requirement of building quality criteria into the design and implementation of AAL systems.

The development of technology based interventions for healthcare requires collaborative working between multidis- ciplinary groups of scientists, engineers, designers, healthcare professionals, and of course end users. This necessitates transfer of knowledge between the various disciplines, preferably underpinned by defined methodologies. Exploitation and uptake of the technology requires participation of industry, typically a small to medium size enterprise (SME) or research department of a larger company and use of the technology requires flexibility of working and often change in healthcare practices. This paper documents the experiences of developing and evaluating two prototypes: the first for telerehabilitation of stroke and the second for self management of long term conditions (stroke, pain and coronary heart failure). We have identified two challenges: (a) knowledge transfer from domain specialists to engineers to facilitate technology development and (b) knowledge transfer back to the domain specialists to facilitate prototype evaluation and exploitation. The use of appropriate ICT tools and the incorporation of principles of human computer interaction have underpinned this approach. Users should influence the choice and functionality of the technology, but decisions must also be informed by technical considerations and possibilities for both hardware and software design. This is a two-way flow of information. How a prototype is taken forward into mainstream practice requires knowledge transfer from academia into the clinical and commercial sectors. Research funding enables both formative and summative prototype evaluation, but does not generally extend to examination of population based effectiveness, which is the evidence most often sought by health commissioners. Hence a process which provides the necessary underpinning for robust evaluation is proposed.

With current advances in sensing technology, communication networks and software applications, the use of connected health technology within the home environment has become both more affordable and widespread. Nevertheless, the introduction of this new care paradigm has brought with it many challenges, with one of the most notable being assessing of the impact or otherwise of its usage. The assessment of efficiency, benefit and utility of such technology is recognised as still being in its infancy. Traditional evaluation protocols may fail to address the specific challenges associated with increased use of networks, databases and home deployments, in addition to the multitude of factors influencing successful adoption. This article aims to delineate the required steps of connected health technology evaluations and move towards a common framework that can be used to support future evaluations. A series of recommendations are presented based on previous experience in the domain.