Journal of Applied Computing Research

MaPS: A framework to aid the development of collaborative applications for ubiquitous environments

2016-08-16T13:37:43-03:00

A research topic of growing interest is the convergence between Collaborative Systems and Ubiquitous Computing, where context awareness is becoming a tool for enhancing collaboration processes. The application of Ubiquitous Computing concepts in the improvement of collaboration strategies created a research front called Ubiquitous Collaboration. This article proposes a framework to aid the development of collaborative applications for ubiquitous environments, called MaPS. MaPS works at one relevant stage of the collaboration. It uses context information and user profiles to improve the search for peers and the selection of communication channels. The article proposes the framework, its requirements and its architecture. Moreover, we describe a prototype and two applications which were developed with it. The framework was evaluated considering software development, based on the experience got in the implementation of the applications and aspects of functionalities. It was made through a scenario involving active participants. The results of both evaluations show the potential for using MaPS.

Keywords: collaboration, collaborative applications, ubiquitous computing, ubiquitous collaboration, ubiquitous environments, context awareness.

Enabling Dynamic Crowdsensing through Models@Runtime

2016-08-16T13:37:43-03:00

The complexity of applications in the mobile crowdsensing domain is due to factors such as interoperability among heterogeneous devices, recruiting of devices, collection of data from these devices, and adaptation of application operation in dynamic environments. This paper introduces a platform based on models at runtime (M@RT) for the development of the mobile crowdsensing functionality of applications. The platform supports model-based creation and processing of queries that target a distributed and dynamic set of sensor-capable devices. The paper also presents the results of an evaluation that shows the impact of runtime model processing on the performance of applications in mobile crowdsensing scenarios.

Keywords: participatory sensing, models at runtime, model execution engine, mobile computing.

A food allergy risk detection model based on situation awareness

2016-08-16T13:37:43-03:00

Advances in ubiquitous computing are enabling the emergence of opportunities in many areas; among them we highlight the health-related applications. In this area, there is a trend toward developing many applications that enable care wherever you are and whenever you need, called ubiquitous healthcare. A detailed survey of existing and proposed models has shown that none of these applications meets the needs of people who suffer from food allergy. Thus, this article proposes an allergy detection ubiquitous model based on situation awareness. This model, called Allergy Detector, focuses on food allergy, in particular the eight major allergens (peanut, milk, egg, wheat, soy, fish, crustacean and tree nuts) and their derivatives, which cause about 90% of all food allergies. The main scientific contribution of the Allergy Detector is the use of situation awareness for detecting allergies anytime and anywhere in a transparent manner. In order to assess the model, we designed some case studies. We also carried out a profiling, accessing the Allergy Detector in terms of performance and identifying the main bottlenecks. The results showed the feasibility of using the model for detecting allergy ubiquitously.

Keywords: ubiquitous computing, context awareness, ubiquituos health.

MHARS: A mobile system for human activity recognition and inference of health situations in ambient assisted living

2016-08-16T13:37:43-03:00

This paper presents MHARS (Mobile Human Activity Recognition System), a mobile system designed to monitor patients in the context of Ambient Assisted Living (AAL), which allows the recognition of the activities performed by the user as well as the detection of the activities intensity in real time. MHARS was designed to be able to gather data from different sensors, to recognize the activities and measure their intensity in different user mobility scenarios. The system allows the inference of situations regarding the health status of the patient and provides support for executing actions, reacting to events that deserve attention from the patient’s caregivers and family members. Experiments demonstrate that MHARS presents good accuracy and has an affordable consumption of mobile resources.

Keywords: Ambient Assisted Living, Human Activity Recognition, situation inference, mobile computing.

A context-aware model for human activity prediction and risk inference in actions

2016-08-16T13:37:43-03:00

Even though human activities may result in injuries, there is not much discussion in the academy of how ubiquitous computing could assess such risks. So, this paper proposes a model for the Activity Manager layer of the Activity Project, which aims to predict and infer risks in activities. The model uses the Activity Theory for the composition and prediction of activities. It also infers the risk in actions based on changes in the user’s physiological context caused by the actions, and such changes are modeled according to the Hyperspace Analogue to Context model. Tests were conducted and the developed models outperformed proposals found for action prediction, with an accuracy of 78.69%, as well as for risk situation detection, with an accuracy of 98.94%, showing the efficiency of the proposed solution.

Keywords: activities of daily living, Activity Theory, activity recognition, activity prediction, risk in actions.