Multiple Personal Devices Research Articles

AI CHATBOT FOR MENTAL HEALTH

Modern artificial intelligence (AI), and machine learning in particular, is being utilized to develop prediction, detection, and treatment solutions for mental health care with the emergence of digital approaches to mental health. AI is being used in therapy to improve user experience and maximize individualized mental health care through digital interventions, including web and smartphone apps. Modern sources of copious amounts of data allow for the development of prediction/detection models for mental health disorders through the use of data-driven AI techniques. Specifically, behavioral or mental health insights can be extracted from an individual's "digital exhaust," which is the data obtained from their multiple personal digital devices and social media activities. Language has traditionally been seen as a window into the human mind, but with the help of potent computer-based natural language processing, it can now be statistically used as data to infer mental health. Furthermore, conversational agents for therapeutic intervention can be created using natural language processing

Federated Dynamic Graph Neural Networks with Secure Aggregation for Video-based Distributed Surveillance

Distributed surveillance systems have the ability to detect, track, and snapshot objects moving around in a certain space. The systems generate video data from multiple personal devices or street cameras. Intelligent video-analysis models are needed to learn dynamic representation of the objects for detection and tracking. Can we exploit the structural and dynamic information without storing the spatiotemporal video data at a central server that leads to a violation of user privacy? In this work, we introduce Federated Dynamic Graph Neural Network (Feddy), a distributed and secured framework to learn the object representations from graph sequences: (1) It aggregates structural information from nearby objects in the current graph as well as dynamic information from those in the previous graph. It uses a self-supervised loss of predicting the trajectories of objects. (2) It is trained in a federated learning manner. The centrally located server sends the model to user devices. Local models on the respective user devices learn and periodically send their learning to the central server without ever exposing the user’s data to server. (3) Studies showed that the aggregated parameters could be inspected though decrypted when broadcast to clients for model synchronizing, after the server performed a weighted average. We design an appropriate aggregation mechanism of secure aggregation primitives that can protect the security and privacy in federated learning with scalability. Experiments on four video camera datasets as well as simulation demonstrate that Feddy achieves great effectiveness and security.

Personalized Information Gathering in a Multiple Personal Device Environment

We propose a personalized information gathering system PerIGS that exploits implicit user feedback in a multiple personal device environment. PerIGS extracts imposing words that induce user's choice from recommended news articles, and constructs user preference profile based on observed user behaviors. A user profile is shared by multiple personal devices, and PerIGS gathers, filters, and recommends news articles according to this shared profile. We organize the user profile in a hierarchical category structure to deal with the uncertainty of user interests. This structure also enables the system to track and recognize the changes of user interests for each domain more effectively. The results of a series of experiments measuring user satisfaction for recommended news articles indicated that PerIGS can effectively utilize user profiles for news filtering and recommendation.

Natural User Interfaces to Teach Math on Higher Education

A common and known problem among students on higher education (in general throughout the scholar life) is the difficulty of learning math. Nowadays the teaching methods for learning math remain relatively the same. Though, with the emerging of new technologies like portable devices (smart phones and tablets) and movement interaction devices (Nintendo WiiMote, Microsoft Kinect and PlayStation Move), learners and teachers have big interest on new ways of interacting through the teaching-learning process. In this sense the Natural User Interactions (NUIs) offer a great potential to facilitate new ways of computer enhanced learning, these have the potential to enhance classroom interactions, by increasing learners participation, facilitating the teachers’ presentations and creating opportunities for discussion. We present a system that combines gestural and touch interactions to support teaching math across multiple personal devices and public displays to enhance and support math education for college students. In a formative usability study, learners and teachers were positive about the interaction design and the learning possibilities for math education. Thus, this created good intentions in the users of continuing using it.

Personal Event Management among Multiple Devices Based on User Intention Recognition Using Dynamic Bayesian Networks

This paper proposes a proactive management system for the events that occur across multiple personal user devices, including desktop PCs, laptops, and smart phones. We implemented the Personal Event Management Service using Dynamic Bayesian Networks (PEMS-DBN) system that proactively executes appropriate tasks across multiple devices without explicit user requests by recognizing the user's device reuse intention, based on the observed actions of the user for specific devices. The client module of PEMS-DBN installed on each device monitors the user actions and recognizes user intention by using dynamic Bayesian networks. The server provides data sharing and maintenance for the clients. A series of experiments were performed to evaluate user satisfaction and system accuracy, and also the amounts of resource consumption during intention recognition and proactive execution are measured to ensure the system efficiency. The experimental results showed that the PEMS-DBN system can proactively provide appropriate, personalized services with a high degree of satisfaction to the user in an effective and efficient manner.

P2P architecture over IPv6 for personal internetworking

The purpose of this paper is to study the feasibility of Personal Internetwork (PIN) and find the approach to achieve the real cooperation of multiple personal devices and improve the usability of Hybrid and Pure P2P architecture within a personal scope. We proposed an IPv6 based Node Discovery Stack (NDS) to make the usage of Personal P2P application possible. This paper clarifies the architecture of the PIN and shows how NDS could enhance the personal communication with co-working devices.