Monitoring and Evaluation of Dementia-Friendly Neighborhoods Using a Walkshed Approach: Protocol for a Scoping Review.

BACKGROUND: The number of people in society living with dementia is growing. In Canada, most people who live with dementia live at home, often in a neighborhood setting. Neighborhood environments can be a source of independence, social engagement, and well-being. They can also contain barriers that limit physical activity, social engagement, and well-being. A dementia-friendly neighborhood includes assets that support persons living with dementia and their caregivers in multiple life domains, including those that support walking within the neighborhood environment. OBJECTIVE: The objectives for this scoping review are twofold. First, focusing on walkshed analysis, we aim to extend scholarly understandings of methodological practices used in the monitoring and evaluation of dementia-friendly neighborhoods. Second, we aim to provide clear and practical guidance for those working in planning, design, and public health fields to assess the neighborhood context in support of evidence-based action to improve the lives of persons living with dementia. METHODS: The study design follows Arksey and O'Malley's scoping review framework and PRISMA-P (Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols) guidelines. We will conduct a search of peer-reviewed studies in 6 electronic databases to identify the use of Geographic Information System analysis to measure the walkshed of persons living with dementia in a community setting. As age is a primary risk factor associated with dementia, we will also include studies that focus more broadly on community-dwelling older adults aged 65 years and older. Data will be extracted, analyzed, and represented according to 3 domains. This includes study details, walkshed analysis methods, and criteria and indicators used to measure dementia-friendly neighborhoods. RESULTS: The results of the study and the submission of a manuscript for peer review are expected in June 2024. The results of the review are expected to contribute to an understanding of methods for monitoring and evaluating dementia-friendly neighborhoods. Expected findings will include a detailed breakdown of current parameters and routines used to conduct walkshed analysis. Findings will also convey criteria that can be operationalized in a Geographic Information System as indicators to assess barriers and facilitators to walking in a neighborhood setting. CONCLUSIONS: As far as we are aware, the proposed scoping review will be the first to provide comprehensive methodological or technical guidance for conducting walkshed analysis specific to persons living with dementia. Both the scalability and objective nature of walkshed analysis are likely to be of direct interest to public health practitioners, planners, and allied professionals. Clearly documenting methods used in walkshed analysis can spur increased collaboration across these disciplines to enable an evidence-informed approach to improving neighborhood environments for persons living with dementia. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/50548.

Point-of-Interest Preference Model Using an Attention Mechanism in a Convolutional Neural Network.

In recent years, there has been a growing interest in developing next point-of-interest (POI) recommendation systems in both industry and academia. However, current POI recommendation strategies suffer from the lack of sufficient mixing of details of the features related to individual users and their corresponding contexts. To overcome this issue, we propose a deep learning model based on an attention mechanism in this study. The suggested technique employs an attention mechanism that focuses on the pattern's friendship, which is responsible for concentrating on the relevant features related to individual users. To compute context-aware similarities among diverse users, our model employs six features of each user as inputs, including user ID, hour, month, day, minute, and second of visiting time, which explore the influences of both spatial and temporal features for the users. In addition, we incorporate geographical information into our attention mechanism by creating an eccentricity score. Specifically, we map the trajectory of each user to a shape, such as a circle, triangle, or rectangle, each of which has a different eccentricity value. This attention-based mechanism is evaluated on two widely used datasets, and experimental outcomes prove a noteworthy improvement of our model over the state-of-the-art strategies for POI recommendation.