Detecting Mental Health Behaviors Using Mobile Interactions: Exploratory Study Focusing on Binge Eating

BACKGROUND

Binge eating is a subjective loss of control while eating, which leads to the consumption of large amounts of food. It can cause significant emotional distress and is often accompanied by purging behaviors (eg, meal skipping, overexercising, or vomiting).

OBJECTIVE

The aim of this study was to explore the potential of mobile sensing to detect indicators of binge-eating episodes, with a view toward informing the design of future context-aware mobile interventions.

METHODS

This study was conducted in 2 stages. The first involved the development of the DeMMI (Detecting Mental health behaviors using Mobile Interactions) app. As part of this, we conducted a consultation session to explore whether the types of sensor data we were proposing to capture were useful and appropriate, as well as to gather feedback on some specific app features relating to self-reporting. The second stage involved conducting a 6-week period of data collection with 10 participants experiencing binge eating (logging both their mood and episodes of binge eating) and 10 comparison participants (logging only mood). An optional interview was conducted after the study, which discussed their experience using the app, and 8 participants (n=3, 38% binge eating and n=5, 63% comparisons) consented.

RESULTS

The findings showed unique differences in the types of sensor data that were triangulated with the individuals' episodes (with nearby Bluetooth devices, screen and app use features, mobility features, and mood scores showing relevance). Participants had a largely positive opinion about the app, its unobtrusive role, and its ease of use. Interacting with the app increased participants' awareness of and reflection on their mood and phone usage patterns. Moreover, they expressed no privacy concerns as these were alleviated by the study information sheet.

CONCLUSIONS

This study contributes a series of recommendations for future studies wishing to scale our approach and for the design of bespoke mobile interventions to support this population.

Smart Health-Enhanced Early Mobilisation in Intensive Care Units

Critically ill patients that stay in Intensive Care Units (ICU) for long periods suffer from Post-Intensive Care Syndrome or ICU Acquired Weakness, whose effects can decrease patients’ quality of life for years. To prevent such issues and aiming at shortening intensive care treatments, Early Mobilisation (EM) has been proposed as an encouraging technique: the literature includes numerous examples of the benefits of EM on the prevention of post-operative complications and adverse events. However, the appropriate application of EM programmes entails the use of scarce resources, both human and technical. Information and Communication Technologies can play a key role in reducing cost and improving the practice of EM. Although there is rich literature on EM practice and its potential benefits, there are some barriers that must be overcome, and technology, i.e., the use of sensors, robotics or information systems, can contribute to that end. This article reviews the literature and analyses on the use of technology in the area of EM, and moreover, it proposes a smart health-enhanced scenario.

Multi-Sensor Context-Aware Based Chatbot Model: An Application of Humanoid Companion Robot

In aspect of the natural language processing field, previous studies have generally analyzed sound signals and provided related responses. However, in various conversation scenarios, image information is still vital. Without the image information, misunderstanding may occur, and lead to wrong responses. In order to address this problem, this study proposes a recurrent neural network (RNNs) based multi-sensor context-aware chatbot technology. The proposed chatbot model incorporates image information with sound signals and gives appropriate responses to the user. In order to improve the performance of the proposed model, the long short-term memory (LSTM) structure is replaced by gated recurrent unit (GRU). Moreover, a VGG16 model is also chosen for a feature extractor for the image information. The experimental results demonstrate that the integrative technology of sound and image information, which are obtained by the image sensor and sound sensor in a companion robot, is helpful for the chatbot model proposed in this study. The feasibility of the proposed technology was also confirmed in the experiment.

IMSC-EIoTD: Identity Management and Secure Communication for Edge IoT Devices

The Internet of things (IoT) will accommodate several billions of devices to the Internet to enhance human society as well as to improve the quality of living. A huge number of sensors, actuators, gateways, servers, and related end-user applications will be connected to the Internet. All these entities require identities to communicate with each other. The communicating devices may have mobility and currently, the only main identity solution is IP based identity management which is not suitable for the authentication and authorization of the heterogeneous IoT devices. Sometimes devices and applications need to communicate in real-time to make decisions within very short times. Most of the recently proposed solutions for identity management are cloud-based. Those cloud-based identity management solutions are not feasible for heterogeneous IoT devices. In this paper, we have proposed an edge-fog based decentralized identity management and authentication solution for IoT devices (IoTD) and edge IoT gateways (EIoTG). We have also presented a secure communication protocol for communication between edge IoT devices and edge IoT gateways. The proposed security protocols are verified using Scyther formal verification tool, which is a popular tool for automated verification of security protocols. The proposed model is specified using the PROMELA language. SPIN model checker is used to confirm the specification of the proposed model. The results show different message flows without any error.

Latino/Hispanic Alzheimer's caregivers experiencing dementia-related dressing issues: corroboration of the Preservation of Self model and reactions to a "smart dresser" computer-based dressing aid

OBJECTIVE

To gain an understanding of Latino/Hispanic caregivers' dementia-related dressing issues, their impressions of using a "smart" context-aware dresser to coach dressing, and recommendations to improve its acceptability.

METHOD

The same Latina moderator conducted all the caregiver focus groups. She followed a semi-structured interview guide that was previously used with White and African American family caregivers who experienced Alzheimer's disease related dressing challenges. From that study, the Preservation of Self model emerged. Using a deductive qualitative analytic approach, we applied the thematic domains from the Preservation of Self model to ascertain relevance to Latino/Hispanic caregivers.

RESULTS

Twenty Latino/Hispanic experienced caregivers were recruited, enrolled, and participated in one of three focus groups. The majority were female (75%) and either the spouse (25%) or adult child (35%). Striking similarities occurred with the dressing challenges and alignment with the Preservation of Self model. Ethnic differences arose in concerns over assimilation weakening the Latino culture of family caregiving. Regional clothing preferences were noted. Technology improvement recommendations for our system, called DRESS, included developing bilingual prompting dialogs and video modules using the local vernacular to improve cultural sensitivity. Caregivers identified the potential for the technology to enable user privacy, empowerment, and exercise as well as offering respite time for themselves.

CONCLUSION

Findings suggest dementia-related dressing issues were shared in common by different racial/ethnic groups but the response to them was influenced by cultural dynamics. For the first time Latino/Hispanic voices are heard to reflect their positive technology impressions, concerns, and recommendations in order to begin to address the cultural digital disparities divide.

A novel software architecture for the provision of context-aware semantic transport information

The effectiveness of Intelligent Transportation Systems depends largely on the ability to integrate information from diverse sources and the suitability of this information for the specific user. This paper describes a new approach for the management and exchange of this information, related to multimodal transportation. A novel software architecture is presented, with particular emphasis on the design of the data model and the enablement of services for information retrieval, thereby obtaining a semantic model for the representation of transport information. The publication of transport data as semantic information is established through the development of a Multimodal Transport Ontology (MTO) and the design of a distributed architecture allowing dynamic integration of transport data. The advantages afforded by the proposed system due to the use of Linked Open Data and a distributed architecture are stated, comparing it with other existing solutions. The adequacy of the information generated in regard to the specific user's context is also addressed. Finally, a working solution of a semantic trip planner using actual transport data and running on the proposed architecture is presented, as a demonstration and validation of the system.

Security enhancement mechanism based on contextual authentication and role analysis for 2G-RFID systems

The traditional Radio Frequency Identification (RFID) system, in which the information maintained in tags is passive and static, has no intelligent decision-making ability to suit application and environment dynamics. The Second-Generation RFID (2G-RFID) system, referred as 2G-RFID-sys, is an evolution of the traditional RFID system to ensure better quality of service in future networks. Due to the openness of the active mobile codes in the 2G-RFID system, the realization of conveying intelligence brings a critical issue: how can we make sure the backend system will interpret and execute mobile codes in the right way without misuse so as to avoid malicious attacks? To address this issue, this paper expands the concept of Role-Based Access Control (RBAC) by introducing context-aware computing, and then designs a secure middleware for backend systems, named Two-Level Security Enhancement Mechanism or 2L-SEM, in order to ensure the usability and validity of the mobile code through contextual authentication and role analysis. According to the given contextual restrictions, 2L-SEM can filtrate the illegal and invalid mobile codes contained in tags. Finally, a reference architecture and its typical application are given to illustrate the implementation of 2L-SEM in a 2G-RFID system, along with the simulation results to evaluate how the proposed mechanism can guarantee secure execution of mobile codes for the system.