Search Results (5)

Background/Objectives: Preschool children from low-income, ethnically diverse communities face disproportionate rates of behavioral challenges and early expulsion from early care and education (ECE) programs. This study evaluated the efficacy, feasibility, and utility of Jump Start on the Go (JS Go), a bilingual, AI-enabled mobile application. JS Go is designed to deliver a 14-week early childhood mental health consultation model in under-resourced ECE settings. Methods: This mixed-methods study compared JS Go to the standard in-person Jump Start (JS) program. Participants included 28 teachers and 114 children from six centers (three JS Go, three JS). Quantitative measures assessed teacher classroom practices and child psychosocial outcomes at baseline and post-intervention. App usability and acceptability were only evaluated post-intervention. Seven semi-structured interviews were conducted post-intervention with JS Go directors/teachers to assess the app’s feasibility for implementing the four program pillars: safety, behavior support, self-care, and communication. Results: JS Go was more effective than JS in promoting teacher classroom practices related to behavior support and resiliency. Both programs were similar in improving children’s protective factors and reducing internalizing behaviors, with consistent effects across English and Spanish-speaking children. Teachers rated the JS Go app with high acceptability, though predicted future usage showed greater variability. Rapid qualitative analysis showed that participants found the app easy to use, frequently accessed its resources, and considered it helpful for reinforcing key strategies across the four program pillars. Conclusions: JS Go is a novel approach to providing mental health consultation. It represents a promising mobile adaptation of the established JS consultation model, with important implications for future practice and research. Full article

To tailor and predict the outcomes of smoking cessation treatment, it is essential to identify the nature of motivation, as it is the basis for long-term change in healthy behaviors according to self-determination theory (SDT). The purpose of this study is to examine the psychometric properties of the French Smoking Cessation Motivation Scale (F-SCMS). The factorial structure and the psychometric properties were assessed with French-speaking users who had started a 9-step preparation program through a mobile app for smoking cessation (n = 13,044). The results of the present study confirmed content validity (CFI = 0.905, SRMR = 0.045, RMSEA = 0.087) and good internal consistency (α = 0.86, ωh = 0.7, ωt = 0.89) with CFA. The convergent validity was very small, but there were highly significant positive correlations between the willingness and readiness to quit with integrated and intrinsic subscales (rs = 0.25–0.37, p < 0.001). The amotivation subscale significantly had no correlation with any degree of willingness (r = 0.01, p < 0.001), ability (r = 0.01, p < 0.001), and readiness to quit (r = 0.02, p < 0.001). This scale facilitates future research regarding the nature of motivation to quit smoking in the French-speaking population. Full article

Wearable technology has been developed in recent years to monitor biomechanical variables in less restricted environments and in a more affordable way than optical motion capture systems. This paper proposes the development of a 3D printed knee wearable goniometer that uses a Hall-effect sensor to measure the knee flexion angle, which works with a mobile app that shows the angle in real-time as well as the activity the user is performing (standing, sitting, or walking). Detection of the activity is done through an algorithm that uses the knee angle and angular speeds as inputs. The measurements of the wearable are compared with a commercial goniometer, and, with the Aktos-t system, a commercial motion capture system based on inertial sensors, at three speeds of gait (4.0 km/h, 4.5 km/h, and 5.0 km/h) in nine participants. Specifically, the four differences between maximum and minimum peaks in the gait cycle, starting with heel-strike, were compared by using the mean absolute error, which was between 2.46 and 12.49 on average. In addition, the algorithm was able to predict the three activities during online testing in one participant and detected on average 94.66% of the gait cycles performed by the participants during offline testing. Full article

At present, most mobile App start-up prediction algorithms are only trained and predicted based on single-user data. They cannot integrate the data of all users to mine the correlation between users, and cannot alleviate the cold start problem of new users or newly installed Apps. There are some existing works related to mobile App start-up prediction using multi-user data, which require the integration of multi-party data. In this case, a typical solution is distributed learning of centralized computing. However, this solution can easily lead to the leakage of user privacy data. In this paper, we propose a mobile App start-up prediction method based on federated learning and attributed heterogeneous network embedding, which alleviates the cold start problem of new users or new Apps while guaranteeing users’ privacy. Full article

Many local governments have started using smartphone applications to more effectively inform and communicate with citizens. This trend is of interest, as cities can only be smart if they are responsive to their citizens. In this paper, the intention to use such a mobile application among adult residents (n = 420) of a mid-sized city in the southeastern United States was examined using hierarchical linear regression analysis. The regression model that was tested indicated significant predictors of the intention to use the app in order to report municipal problems, such as power outages, and to request services for one’s home or community, including: Performance expectancy (e.g., citizens’ beliefs that the app would be efficient, helpful, convenient), effort expectancy (citizens’ beliefs about difficulty of using the app), social influence, perceived cost (e.g., privacy loss, storage space, unwanted notifications), and prior use of city apps. Consistent with current research on technology adoption, performance expectancy had the strongest influence on app-use intentions. Additionally, citizens’ trust in their city government’s ability to effectively manage an app was a weak, positive predictor of app-use intentions; general trust in the city government did not predict app-use intentions. Implications for city governments and city app developers are discussed. Full article