Enhancing Human Activity Recognition in Smart Homes with Self-Supervised Learning and Self-Attention.

Deep learning models have gained prominence in human activity recognition using ambient sensors, particularly for telemonitoring older adults' daily activities in real-world scenarios. However, collecting large volumes of annotated sensor data presents a formidable challenge, given the time-consuming and costly nature of traditional manual annotation methods, especially for extensive projects. In response to this challenge, we propose a novel AttCLHAR model rooted in the self-supervised learning framework SimCLR and augmented with a self-attention mechanism. This model is designed for human activity recognition utilizing ambient sensor data, tailored explicitly for scenarios with limited or no annotations. AttCLHAR encompasses unsupervised pre-training and fine-tuning phases, sharing a common encoder module with two convolutional layers and a long short-term memory (LSTM) layer. The output is further connected to a self-attention layer, allowing the model to selectively focus on different input sequence segments. The incorporation of sharpness-aware minimization (SAM) aims to enhance model generalization by penalizing loss sharpness. The pre-training phase focuses on learning representative features from abundant unlabeled data, capturing both spatial and temporal dependencies in the sensor data. It facilitates the extraction of informative features for subsequent fine-tuning tasks. We extensively evaluated the AttCLHAR model using three CASAS smart home datasets (Aruba-1, Aruba-2, and Milan). We compared its performance against the SimCLR framework, SimCLR with SAM, and SimCLR with the self-attention layer. The experimental results demonstrate the superior performance of our approach, especially in semi-supervised and transfer learning scenarios. It outperforms existing models, marking a significant advancement in using self-supervised learning to extract valuable insights from unlabeled ambient sensor data in real-world environments.

Perceived needs and difficulties in meal preparation of people living with traumatic brain injury in a chronic phase: Supporting long-term services and interventions.

INTRODUCTION: Traumatic brain injury (TBI) is a chronic medical condition with life-long consequences. Meal preparation is one of the most significant activities impacted by TBI even after more than 10 years post-trauma. However, substantial gaps exist in our understanding of how exactly it is affected. This study examines the perceived needs and difficulties regarding meal preparation in individuals with severe TBI living in the community. This is done in an effort to justify long-term community-based interventions offered to the TBI population with regard to a task involving many safety issues. METHODS: The study used a descriptive qualitative design where five adults (28-50 years old) living with a severe TBI (9-37 years post-injury) were interviewed. Data analysis was completed using an inductive method. RESULTS: Participants living alone were all involved in meal preparation to diverse levels. Only two participants lived with a family member. Six categories of perceived needs were identified, of which two emerged as priorities: (i) Need for recipes to be compatible with cognitive abilities, knowledge and energy level to optimise motivation and (ii) Need to adapt complexity of grocery shopping to cognitive abilities and knowledge. The main difficulty expressed by participants was to manage their motivation to cook when tired, as it tends to diminish and fade when the person is exhausted. CONCLUSION: Many situations were considered difficult for our participants, which calls for adaptation of the tasks and of their environment. Considering these unmet needs in the interventions offered will help individualise follow-up and ultimately optimise the social integration of individuals living with severe TBI.

Research Priorities for Optimizing Long-term Community Integration after Brain Injury.

OBJECTIVE: This paper reports on a funded summit, which convened a multidisciplinary group of experts to provide consensus on the research priorities necessary for improving long-term community integration of individuals with traumatic brain injury (TBI) and their caregivers. METHODS: The 2-day summit was directed using the World Café Methodology, to engage stakeholders and collaboratively arrive at a consensus on the problems to be targeted in research. Participants (n=54), drawn from two Canadian provinces, included an interdisciplinary group of researchers, clinicians, representatives from brain injury associations, individuals with TBI, and caregivers. In small groups, participants discussed challenges to long-term community integration and potential initiatives that would address these barriers. Field notes from the discussions were analyzed using qualitative content analysis. RESULTS: The consensus on prioritized research directions included developing interventions to optimize the functioning and participation of individuals with TBI, reducing caregiver burden, and evaluating how emerging technology can facilitate delivery of care. CONCLUSIONS: The World Café Methodology was an effective method for developing research priorities. The breadth of expertise of participants and the collegial environment allowed for the identification of a broad perspective on important future research directions with potential to enhance the long-term community integration of individuals with brain injury.

From conception to evaluation of mobile services for people with head injury: A participatory design perspective.

Adults with cognitive impairments lack the means to organise their daily life, plan their appointments, cope with fatigue, and manage their budget. They manifest interest in using new technologies to be part of society. Unfortunately, the applications offered on smart phones are often beyond their cognitive abilities. The goal of this study was to design a mobile cognitive assistant to enhance autonomy of people living with acquired traumatic brain injury. Participatory design methodologies guided this research by involving adults with cognitive impairments (CI) and their caregivers in the early stages of the design process. The population of the study is composed of four male adults who present cognitive impairments (three with head injury and one with stroke) and three caregivers. The first phase of this research was to design the Services Assistance Mobile and Intelligent (SAMI) application based on the needs expressed by the participants. During three focus groups, needs emerged concerning planning, health monitoring and money management and led to the implementation of assistive solutions on an Android mobile phone. During the second phase, the participants evaluated the mobile assistant SAMI at home for eight weeks. The results demonstrate that the participants were able to participate actively in the conception of SAMI and to use it successfully. People with CI showed a slight improvement in their life satisfaction. Due to the small number of participants, these promising results need to be confirmed by a larger-scale study.

Impact of AP@LZ in the daily life of three persons with Alzheimer's disease: long-term use and further exploration of its effectiveness.

AP@LZ is an electronic organiser that was designed to support the day-to-day activities of persons with Alzheimer's disease. To assess the potential of this technology, three participants (NI, JB, RD) were approached to take part in the study. They benefited from a structured cognitive intervention to learn how to operate AP@LZ; the intervention included the following learning stages: Acquisition, Application and Adaptation. Pre- and post-intervention measures were collected. NI, for whom a longitudinal study was conducted, still continued to use AP@LZ 24 months post-intervention. JB and RD also showed a gradual improvement in their performance throughout the intervention phase (sessions 1 to 19 for JB: performance increased from 50 to 100%; sessions 1 to 25 for RD: from 56 to 89%). The results of the use of AP@LZ in activities of daily living suggest that the application was beneficial for three persons with Alzheimer's disease whose profiles differed notably (age, cognitive and social profiles). Thus, results indicate that they were all able to learn how to operate AP@LZ's functions and to use them in their activities of daily living. Cognitive intervention appears to play an important role for the promotion of learning and adoption of such technology.

Special issue on technology and neuropsychological rehabilitation: Overview and reflections on ways to conduct future studies and support clinical practice.

In this editorial, we wish to highlight and reflect on research advances presented in the articles comprising this special issue on technology and neuropsychological rehabilitation, which happens to be published more than a decade after the first special issue on the subject. In 2004, the journal recognised the great potential of information technology for increasing the support provided to people with cognitive deficits, and published emerging state-of-the art practices in the field. Since that time, research and technology have made tremendous progress, and the influence of information technology on research methods has transformed the field of neurorehabilitation. The aim of this editorial is thus to shed light on methodological and conceptual issues requiring further attention from researchers and clinicians in the fields of neuropsychological rehabilitation and technology, and to stimulate debate on promising avenues in clinical research.

Electronic organiser and Alzheimer's disease: fact or fiction?

Alzheimer's disease is a degenerative disease characterised by a progressive loss of cognitive functions and impairment of activities of daily living severe enough to interfere with normal functioning. To help persons with this disease perform a variety of activities, our research team developed AP@LZ, an electronic organiser specifically designed for them. Two participants with Alzheimer's disease learned how to use AP@LZ in their daily lives by following a structured learning method. After the learning phase, the participants were able to use AP@LZ efficiently and facilitate their day-to-day activities for several months, despite the steady progression of the disease. These results suggest that persons with Alzheimer's disease can learn to use new technologies to compensate for their everyday memory problems, which opens up new rehabilitation possibilities in dementia care.

Codevelopment and Deployment of a System for the Telemonitoring of Activities of Daily Living Among Older Adults Receiving Home Care Services: Protocol for an Action Design Research Study.

BACKGROUND: Telemonitoring of activities of daily living (ADLs) offers significant potential for gaining a deeper insight into the home care needs of older adults experiencing cognitive decline, particularly those living alone. In 2016, our team and a health care institution in Montreal, Quebec, Canada, sought to test this technology to enhance the support provided by home care clinical teams for older adults residing alone and facing cognitive deficits. The Support for Seniors' Autonomy program (SAPA [Soutien à l'autonomie des personnes âgées]) project was initiated within this context, embracing an innovative research approach that combines action research and design science. OBJECTIVE: This paper presents the research protocol for the SAPA project, with the aim of facilitating the replication of similar initiatives in the future. The primary objectives of the SAPA project were to (1) codevelop an ADL telemonitoring system aligned with the requirements of key stakeholders, (2) deploy the system in a real clinical environment to identify specific use cases, and (3) identify factors conducive to its sustained use in a real-world setting. Given the context of the SAPA project, the adoption of an action design research (ADR) approach was deemed crucial. ADR is a framework for crafting practical solutions to intricate problems encountered in a specific organizational context. METHODS: This project consisted of 2 cycles of development (alpha and beta) that involved cyclical repetitions of stages 2 and 3 to develop a telemonitoring system for ADLs. Stakeholders, such as health care managers, clinicians, older adults, and their families, were included in each codevelopment cycle. Qualitative and quantitative data were collected throughout this project. RESULTS: The first iterative cycle, the alpha cycle, took place from early 2016 to mid 2018. The first prototype of an ADL telemonitoring system was deployed in the homes of 4 individuals receiving home care services through a public health institution. The prototype was used to collect data about care recipients' ADL routines. Clinicians used the data to support their home care intervention plan, and the results are presented here. The prototype was successfully deployed and perceived as useful, although obstacles were encountered. Similarly, a second codevelopment cycle (beta cycle) took place in 3 public health institutions from late 2018 to late 2022. The telemonitoring system was installed in 31 care recipients' homes, and detailed results will be presented in future papers. CONCLUSIONS: To our knowledge, this is the first reported ADR project in ADL telemonitoring research that includes 2 iterative cycles of codevelopment and deployment embedded in the real-world clinical settings of a public health system. We discuss the artifacts, generalization of learning, and dissemination generated by this protocol in the hope of providing a concrete and replicable example of research partnerships in the field of digital health in cognitive aging. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR1-10.2196/52284.

Potential of using an assistive technology to address meal preparation difficulties following acquired brain injury: clients' and caregivers' perspectives.

OBJECTIVES: This study explored difficulties in meal preparation experienced by adults with moderate to severe acquired brain injury (ABI) and available compensatory strategies from both ABI individuals' and caregivers' perspectives. Further, this study investigated their opinions on potential benefits, barriers and facilitators to the use of the Cognitive Orthosis for coOKing (COOK) in their living environment. METHODS: Using a qualitative descriptive approach, semi-structured individual interviews and focus groups were carried out with adults with moderate to severe ABI (n = 20) and formal and informal caregivers (n = 13) in Ontario and Quebec, Canada. A qualitative analysis based on Miles et al.'s approach was used. RESULTS: According to participants, cognitive, physical, psychosocial dysfunctions and lack of availability of supportive caregivers were the main difficulties that impede persons with ABI from engaging effectively in meal preparation tasks. Memory aids on smartphones, and caregivers' direct support were reported as the most commonly used compensatory strategies, though the latter do not provide adequate support. COOK was identified as a technology with great potential to improve independence and increase safety in meal preparation for these clients while decreasing caregiver burden. However, psychosocial issues and limited access to funding were considered as the main barriers to the use of COOK. Providing training and the availability of financial support were mentioned as the main facilitators to the use of this technology. CONCLUSIONS: Findings of this study on difficulties of meal preparation following ABI and potential benefits and barriers of COOK will help improve this technology and customize it to the needs of clients with ABI and their caregivers.Implications for RehabilitationCurrent compensatory strategies are not tailored to the specific needs of clients with ABI and cannot provide sufficient support for caregivers.COOK shows a high potential for increasing independence and safety during meal preparation in a living environment for clients with ABI via a sensor-based autonomous safety system and a cognitive assistance application.COOK has the potential to decrease caregivers' burden by proving remote access to a stove/oven.

COOK technology to support meal preparation following a severe traumatic brain injury: a usability mixed-methods single-case study in a real-world environment.

INTRODUCTION: Following a traumatic brain injury (TBI), meal preparation may become challenging as it involves multiple cognitive abilities and sub-tasks. To support this population, the Cognitive Orthosis for coOKing (COOK) was developed in partnership with an alternative residential resource for people with severe TBI. However, little is known about the usability of this technology to support people with TBI living in their own homes. METHODS: A usability study was conducted using a mixed-methods single-case design with a 35-year-old man with severe TBI living alone at home. The number of assistances provided, time taken and the percentage of unnecessary actions during a meal preparation task were documented nine times to explore the usability of COOK. Interviews were also conducted with the participant to document his satisfaction with COOK. Potential benefits were explored via the number of meals prepared per week. RESULTS: The usability of COOK was shown to be promising as the technology helped the participant prepare complex meals, while also reducing the number of assistances needed and the percentage of unnecessary actions. However, several technical issues and contextual factors influenced the efficiency and the participant's satisfaction with COOK. Despite improving his self-confidence, COOK did not help the participant prepare more meals over time. CONCLUSION: This study showed that COOK was easy to use and promising, despite technical and configuration issues. Results suggest the importance of further technological developments to improve COOK's usability and fit with the needs of people with TBI living in their own homes.

Cognitive Orthosis for coOKing (COOK) is a promising technology to support people with TBI when preparing meals within their homes, though usability issues need to be corrected.Factors such as current meal-preparation related habits, expectations and availability of technical support were found to influence the usability of COOK.Various questions to consider in future studies involving an assistive technology for cognition to support meal preparation were identified.

Implementation of an assistive technology for meal preparation within a supported residence for adults with acquired brain injury: a mixed-methods single case study.

OBJECTIVES: This study aimed to investigate the feasibility of implementing an assistive technology for meal preparation called COOK within a supported community residence for a person with an acquired brain injury. METHODS: Using a mixed-methods approach, a multiple baseline single-case experimental design and a descriptive qualitative study were conducted. The participant was a 47-year-old woman with cognitive impairments following a severe stroke. She received 21 sessions of training on using COOK within a shared kitchen space. During meal preparation, independence and safety were evaluated using three target behaviours: required assistance, task performance errors, and appropriate responses to safety issues, which were compared with an untrained control task, making a budget. Benefits, barriers, and facilitators were assessed via three individual interviews with the client and three focus groups with the care team. RESULTS: Both quantitative and qualitative analyses showed that COOK significantly increased independence and safety during meal preparation but not in the control task. Stakeholders suggested that the availability of a training toolkit to a greater number of therapists at the residence and installation of COOK within the client's apartment would help with successful adoption of this technology. CONCLUSION: COOK is a promising assistive technology for individuals with cognitive deficits who live in supported community residences.Implication For RehabilitationCOOK is a promising assistive technology for cognition to increase independence and safety in meal preparation for clients with ABI within their supported living contexts.Receiving training from an expert and the availability of technical support are imperative to the successful adoption of COOK.

Is research on 'smart living environments' based on unobtrusive technologies for older adults going in circles? Evidence from an umbrella review.

CONTEXT AND AIMS: To enable ageing in place, innovative and integrative technologies such as smart living environments may be part of the solution. Despite extensive published literature reviews on this topic, the effectiveness of smart living environments in supporting ageing in place, and in particular involving unobtrusive technologies, remains unclear. The main objective of our umbrella review was to synthesize evidence on this topic. METHODS: According to the PRIOR process, we included reviews from multiple databases that focused on unobtrusive technologies used to analyze and share information about older adults' behaviors and assessed the effectiveness of unobtrusive technologies to support ageing in place. Selection, extraction and quality appraisal were done independently by two reviewers. RESULTS: By synthesizing 17 published reviews that covered 191 distinct primary studies, we found that smart living environments based on unobtrusive technologies had low to moderate effectiveness to support older adults to age in place. Effectiveness appears to be strongest in the recognition of activities of daily living. The results must, however, be interpreted in light of the low overall level of evidence, i.e., low methodological value of the primary studies and poor methodological quality of the literature reviews. Most reviews concluded that unobtrusive technologies are not mature enough for widespread adoption. CONCLUSION: There is a necessity to support primary studies that can move beyond the proof-of-concept or pilot stages and expand scientific knowledge significantly on the topic. There is also an urgent need to publish high quality literature reviews to better support policy makers and funding agencies in the field of smart living environments.

Ecological assessments of activities of daily living and personal experiences with Mobus, an assistive technology for cognition: a pilot study in schizophrenia.

Mobus is a cognitive orthotic designed for people with difficulties managing Activities of Daily Living (ADL), as encountered in schizophrenia. It provides a schedule manager as well as the possibility to report occurrences of symptomatic experiences. Receiving this information by Internet, caregivers can assist the patient rehabilitation process. Our aim was to explore the use and satisfaction of Mobus by people with schizophrenia. Nine outpatients tested Mobus for 6 weeks. Indicators of cognitive functioning and autonomy were measured with the CAmbridge Neuropsychological Tests Automated Battery (CANTAB) and the Independant Living Skills Scale (ILSS). On average, 42.6% of the planned ADL were validated and more than 1 symptom per week were reported. Mainly because of technical breakdown, more than 50% of the outpatients evaluated the Mobus satisfaction below 1.7/5, nevertheless 3 participants appreciated it greatly. Some enhancements were found on subscales of CANTAB and ILSS and some participants reported that they acquired planning skills by using Mobus. To ensure ease of use, refinements are needed from rehabilitation and technical approaches, especially to personalize the device. Discussions on ethical and methodological issues lead to an improved version of Mobus that will be tested with a larger sample size.

Development of an Assistive Technology for Cognition to Support Meal Preparation in Severe Traumatic Brain Injury: User-Centered Design Study.

BACKGROUND: Although assistive technology for cognition (ATC) has enormous potential to help individuals who have sustained a severe traumatic brain injury (TBI) prepare meals safely, no ATC has yet been developed to assist in this activity for this specific population. OBJECTIVE: This study aims to conduct a needs analysis as a first step in the design of an ATC to support safe and independent meal preparation for persons with severe TBI. This included identifying cooking-related risks to depict future users' profiles and establishing the clinical requirements of the ATC. METHODS: In a user-centered design study, the needs of 3 future users were evaluated in their real-world environments (supported-living residence) using an ecological assessment of everyday activities, a review of their medical files, a complete neuropsychological test battery, individual interviews, observational field notes, and log journals with the residents, their families, and other stakeholders from the residence (eg, staff and health professionals). The needs analysis was guided by the Disability Creation Process framework. RESULTS: The results showed that many issues had to be considered for the development of the ATC for the 3 residents and other eventual users, including cognitive issues such as distractibility and difficulty remembering information over a short period of time and important safety issues, such as potential food poisoning and risk of fire. This led to the identification of 2 main clinical requirements for the ATC: providing cognitive support based on evidence-based cognitive rehabilitation to facilitate meal preparation and ensuring safety at each step of the meal preparation task. CONCLUSIONS: This needs analysis identified the main requirements for an ATC designed to support meal preparation for persons with severe TBI. Future research will focus on implementing the ATC in the residence and evaluating its usability.

Smart Assistive Technology for Cooking for People With Cognitive Impairments Following a Traumatic Brain Injury: User Experience Study.

BACKGROUND: User experience (UX), including usability, should be formally assessed multiple times throughout the development process to optimize the acceptability and integration of a new technology before implementing it within the home environment of people living with cognitive impairments. OBJECTIVE: The aim of this study is to identify UX issues, notably usability issues, and factors to consider for the future implementation of the COOK (Cognitive Orthosis for Cooking) within the home of individuals with traumatic brain injury (TBI) to identify modifications to improve the technology. METHODS: This study comprised two rounds of UX evaluations, including extensive usability testing, which were completed in a laboratory context: 3 sessions with 5 experts and, after improvement of COOK, 2 sessions with 10 participants with TBI. Each session included the use of scenarios and questionnaires on UX and usability. RESULTS: Both rounds demonstrated good usability outcomes and hedonic qualities. Various usability issues were identified by participants, such as navigation inconsistencies, technical bugs, and the need for more feedback. Factors to consider in the future implementation of COOK were also mentioned by participants with TBI, including environmental (eg, space available and presence of pets) and personal factors (eg, level of comfort with technology, presence of visual deficits, and preferences). CONCLUSIONS: By evaluating UX, including usability, various times throughout the development process and including experts and end users, our research team was able to develop a technology that was perceived as usable, pleasant, and well-designed. This research is an example of how and when people with cognitive impairments (ie, people with TBI) can be involved in evaluating the UX of new technology.

Potential advantages, barriers, and facilitators of implementing a cognitive orthosis for cooking for individuals with traumatic brain injury: the healthcare providers' perspective.

PURPOSE: Considering the key role of health care providers in integrating assistive technologies into clinical settings (e.g., in/outpatient rehabilitation) and home, this study explored the care providers' perspectives on benefits, barriers and facilitators to the implementation of the Cognitive Orthosis for coOking (COOK) for adults with traumatic brain injury (TBI) within clinical contexts and homes. METHODS: Using a qualitative descriptive approach, semi-structured individual interviews and focus groups were carried out with experienced care providers of adults with TBI (n = 30) in Ontario-Canada. Qualitative analysis based on the Miles et al approach was used. RESULTS: According to the participants, COOK could potentially be used with individuals with cognitive impairments (TBI and non-TBI) to increase safety and independence in meal preparation and support healthcare providers. However, limited access to funding, clients' lack of motivation/knowledge, and the severity of their cognitive and motor impairments were perceived as potential barriers. Facilitators to the use of COOK include training sessions, availability of private/provincial financing, and comprehensive assessments by a clinical team prior to use. CONCLUSIONS: Health care providers' perspectives will help develop implementation strategies to facilitate the adoption of COOK within homes and clinical contexts for individuals with TBI and improve the next version of this technology.IMPLICATIONS FOR REHABILITATIONCOOK shows a high potential for increasing independence and safety during meal preparation with its sensor-based monitoring of the environment and cognitive-based assistance, for adults with TBI.Comprehensive clinical assessments to identify individuals' therapeutic goals, clinical characteristics, and living environments are necessary to facilitate the deployment of COOK.

Cooking "shrimp à la créole": a pilot study of an ecological rehabilitation in semantic dementia.

New learning in semantic dementia (SD) seems to be tied to a specific temporal and spatial context. Thus, cognitive rehabilitation could capitalise upon preserved episodic memory and focus on everyday activities which, once learned, will have an impact in everyday life. This pilot study thus explores the effectiveness of an ecological approach in one patient suffering from SD. EC, a 68-year-old woman with SD, stopped cooking complex meals due to a substantial loss of knowledge related to all food types. The therapy consisted of preparing a target recipe. She was asked to generate semantic attributes of ingredients found in one target, one control and two no-therapy recipes. The number of recipes cooked by EC between therapy sessions was computed. She was also asked to prepare a generalisation recipe combining ingredients from the target and control recipes. EC's generated semantic attributes (GSA) of ingredients pertaining to the target and control recipes increased significantly (p < .001), compared to the no-therapy recipes (ps > .79). The proportion of meals cooked also increased significantly (p = .021). For the generalisation recipe, she could not succeed without assistance. Frequent food preparation may have provided EC with new memories about the context, usage and appearance of some concepts. These memories seem very context-bound, but EC nonetheless re-introduced some recipes into her day-to-day life. The impact of these results on the relationship between semantic, episodic and procedural memory is discussed, as well as the relevance of an ecological approach in SD.

Design and usability evaluation of COOK, an assistive technology for meal preparation for persons with severe TBI.

AIM: In Canada, 100,000 people suffer a traumatic brain injury (TBI) every year. The prevalence of moderate to severe TBI is highest for young men, who will live an average of 50 years with this chronic condition associated with physical, emotional and cognitive deficits. Meal preparation, a complex activity with high safety risks, is one of the most significant activities impacted by TBI. Technology shows great promise to support their overall functioning, but no context-aware technology is available to support meal preparation for this population. The main goal of this study was to design and test a technology to support meal preparation with and for persons with severe TBI living in a supported-living residence. METHODOLOGY: As part of a transdisciplinary technology project linking rehabilitation and informatics, COOK (Cognitive Orthosis for coOKing) was designed with and for future users and stakeholders with a user-centred design methodology. COOK was implemented in three participants' apartments, and its usability was evaluated at 1, 3 and 6 months post-implementation. RESULTS: COOK is a context-aware assistive technology consisting of two main systems: security and cognitive support system. After implementation of COOK, participants were able to resume safe preparation of meals independently. Usability testing showed good effectiveness and an acceptable level of satisfaction. CONCLUSION: COOK appears promising for rehabilitating clients with cognitive disabilities, improving safety in a home environment, and diminishing the need for human supervision. Future studies will need to explore how COOK can be adapted to a broader TBI population, other environments, and other clienteles.Implications for rehabilitationThis paper presents a promising context-aware assistive technology for cognition designed with and for clients with severe brain injury to support their independence in meal preparation;COOK, (Cognitive Orthesis for coOKing) is the first cooking assistant in which evidence-based cognitive rehabilitation interventions have been translated into smart technological assistance, to support cognition and ensure safety in a real-life context;Its context-aware characteristic ensures that users receive the assistance they need at the right time and at the right moment.The long-term perspective regarding the use of COOK in clinical practice is promising as this technology has the potential of becoming an additional means of supporting the rehabilitation of people with cognitive impairments and becoming part of a comprehensive solution to help them live at home more independently.

Joining semantic and augmented reality to design smart homes for assistance.

INTRODUCTION: Smart homes for assistance help compensate cognitive deficits, thus favoring aging in place. However, to be effective, the assistance must be adapted to the abilities, deficits, and habits of the person. Beside the elder, caregivers are the ones who know the person's needs best. This article presents a Do-it-Yourself approach for helping caregivers designing a smart home for assistance. METHODS: A co-construction process between a caregiver and a virtual adviser was designed. The knowledge of the virtual adviser about smart homes, activities of daily living and assistance is organized in an ontology. The caregiver interacts with the virtual adviser in augmented reality to describe the home and the resident's habits inside it. The process is illustrated with an ordinary activity: 'Drink water'. RESULTS: The proposed process highlights two main steps: describing the environment and determining the resident's habits and the assistance required to improve activity performance. Visual guidance and feedback are provided to ease the process. CONCLUSION: Designing a co-construction process with a virtual adviser allows interactive knowledge sharing with the caregivers who are experts of the person's needs. Future work should focus on evaluating the prototype presented and providing deeper advice such as highlighting incomplete or incorrect scenarios, or navigation aid.

Context awareness architecture for ambient-assisted living applications: Case study of nighttime wandering.

OBJECTIVES: This work presents an ambient-assisted living application that encourages seniors during nocturnal wandering episodes to return to bed in calm and comfort reassurance. METHODS: Structuring knowledge by designing a software architecture capable of delivering high-level analysis and processing. A senior's home has been upgraded into a smart home enabling the gathering of habits for two weeks and set up for personalized assistance over four weeks. Home automation devices associated with Actigraph monitors and self-reported sleep were used for more accuracy. RESULTS: The architectural model can be used in ambient-assisted living applications for which data collection is permanent and continuous. Its layered organization facilitates the management of specific and general activities of daily life. The results of the home experience show that the system gave a notification whenever the need arose. On the other hand, it allowed the caregiver to get more information about the lifestyle of the senior. CONCLUSIONS: Future work should focus on providing more services to contextualize assistance. Ontology is used to structure all the ambient knowledge of the smart home. We also plan to do more home experiments.