Separation of Concerns Within Robotic Systems Through Proactive Computing

in Proceeding of the 4th IEEE International Conference on Robotic Computing (2020, November)

In this short paper, we first introduce a possible new model for designing and implementing software in robotic systems. This model is based on proactive scenarios, coded through dynamic sets of condition ... [more ▼]

In this short paper, we first introduce a possible new model for designing and implementing software in robotic systems. This model is based on proactive scenarios, coded through dynamic sets of condition-action rules. Each scenario embeds the required rules and can be assembled dynamically with others, allowing the proactive system to achieve a unique objective or behavior and instruct the robot accordingly. Furthermore, a scenario is not aware of the existence of the other scenarios. In fact, it only contains information about a predefined central scenario, which oversees global decision making. In addition, each scenario knows where to enter its suggestions, thus allowing for a high degree in terms of separating concerns and modularity of code. Consequently, allowing easier development, testing and optimization of each scenario independently, possible reuse in different robots, and finally, a faster achievement of robust and scalable robotics software. We then show how to apply this programming model and its functionalities during runtime, by a proof of concept consisting of a virtual robot deployed in the Webots™ simulator. This simulator is controlled with four proactive scenarios (plus the central one), in charge of three different objectives. [less ▲]

Proactive Model for Handling Conflicts in Sensor Data Fusion Applied to Robotic Systems

in Proceedings of the 14th International Conference on Software Technologies (ICSOFT), 2019 Prague, Czech Republic, 26 - 28 July, 2019 (2019)

Robots have to be able to function in a multitude of different situations and environments. To help them achieve this, they are usually equipped with a large set of sensors whose data will be used in ... [more ▼]

Robots have to be able to function in a multitude of different situations and environments. To help them achieve this, they are usually equipped with a large set of sensors whose data will be used in order to make decisions. However, the sensors can malfunction, be influenced by noise or simply be imprecise. Existing sensor fusion techniques can be used in order to overcome some of these problems, but we believe that data can be improved further by computing context information and using a proactive rule-based system to detect potentially conflicting data coming from different sensors. In this paper we will present the architecture and scenarios for a generic model taking context into account. [less ▲]

Context-aware and Attribute-based Access Control Applying Proactive Computing to IoT System

in Proceedings of the 3rd International Conference on Internet of Things, Big Data and Security (IoTBDS 2018) (2018)

ABAC allows for high flexibility in access control over a system through the definition of policies based on attribute values. In the context of an IoT-based system, these data can be supplied through its ... [more ▼]

ABAC allows for high flexibility in access control over a system through the definition of policies based on attribute values. In the context of an IoT-based system, these data can be supplied through its sensors connected to the real world, allowing for context-awareness. However, the ABAC model alone does not include proposals for implementing security policies based on verified and/or meaningful values rather than on raw data flowing from the sensors. Nor does it allow to implement immediate action on the system when some security flaw is detected, while this possibility technically exists if the system is equipped with actuators next to its sensors. We show how to circumvent these limitations by adding a proactive engine to the ABAC components, that runs rule-based scenarios devoted to sensor data pre-processing, to higher-level information storage in the PIP, and to real-time, automatic reaction on the system through its actuators when required. [less ▲]

Using Hidden Markov Models and Rule-based Sensor Mediation on Wearable eHealth Devices

in Procedings of the 11th International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies, Barcelona, Spain 12-16 November 2017 (2017)

Improvements in sensor miniaturization allow wearable devices to provide more functionality while also being more comfortable for users to wear. The Samsung Simband©, for example, has 6 different sensors ... [more ▼]

Improvements in sensor miniaturization allow wearable devices to provide more functionality while also being more comfortable for users to wear. The Samsung Simband©, for example, has 6 different sensors Electrocardiogram (ECG), Photoplethysmogram (PPG), Galvanic Skin Response (GSR), Bio-Impedance (Bio-Z), Accelerometer and a thermometer as well as a modular sensor hub to easily add additional ones. This increased number of sensors for wearable devices opens new possibilities for a more precise monitoring of patients by integrating the data from the different sensors. This integration can be influenced by failing or malfunctioning sensors and noise. In this paper, we propose an approach that uses Hidden Markov Models (HMM) in combination with a rule-based engine to mediate among the different sensors’ data in order to allow the eHealth system to compute a diagnosis on the basis of the selected reliable sensors. We also show some preliminary results about the accuracy of the first stage of the proposed model. [less ▲]

A Proactive Solution, using Wearable and Mobile Applications, for Closing the Gap between the Rehabilitation Team and Cardiac Patients

in Proceedings of the IEEE International Conference on Healthcare Informatics 2016 (ICHI 2016) (2016)

Exercise training (ET) is one of the decisive and crucial factors for reducing and preventing unexpected cardiac events. The aim of this work is to implement a proactive e-Health system that will allow ... [more ▼]

Exercise training (ET) is one of the decisive and crucial factors for reducing and preventing unexpected cardiac events. The aim of this work is to implement a proactive e-Health system that will allow patients, following a Cardiac Rehabilitation (CR) program outside the hospital, to exercise safely, according to their recommended training zones. The e-Health system includes a smartwatch application, a smartphone application and several server-side applications, working on predefined personalised scenarios, which are alerting, guiding and supporting the patients. The heart rate (HR) of patients is continuously measured, recorded and analysed during ET with the help of wearable devices. While training, patients benefit from multiple levels of feedback. Communities of patients are created for stimulating and motivating patients to perform according to their CR program. Opposed to traditional home-based CR e-Health applications, profiles and training zones are created and handled dynamically for each patient. [less ▲]

SilentMeet - A Prototype Mobile Application for Real-Time Automated Group-Based Collaboration

in Proceedings of the 5th International Conference on Advanced Collaborative Networks, Systems and Applications (COLLA 2015) (2015)

Today’s growing world of mobile devices offers all the necessary elements for developing collaborative mobile applications. However, this brings new challenges like how to handle the high complexity of ... [more ▼]

Today’s growing world of mobile devices offers all the necessary elements for developing collaborative mobile applications. However, this brings new challenges like how to handle the high complexity of efficient collaborative mechanisms or automatize part of the user’s interaction with the applications, as too many actions are required from the users in order to perform even the most basic operations. This paper describes an experimental mobile application, i.e., SilentMeet, that uses a rule-based middleware architecture for mobile devices and a new technique for exchanging information, for coordinating and for taking distributed decisions. More precisely, the application is designed to detect, based on collaboration, possible meetings or events with more than 2 participants and automatically switch the smartphone into silent mode. The goal of SilentMeet can be divided into 2 two main parts: 1) to develop a collaborative application with the help of rule-based systems; and 2) implement and evaluate Global Proactive Scenarios (GPaSs) in a real-case example. [less ▲]

Evaluating the Probabilistic side of Proactive Computing using Cognitive Modelling Methodology and the Statistical Inference of User’s Cognitive States

in Proceedings of 2014 IEEE 13th International Conference on Cognitive Informatics and Cognitive Computing - London, UK (2014)

In the following paper we present the work in progress, which aims to validate through theoretical and em- pirical study the probabilistic side of proactive computing. We choose the cognitive modelling ... [more ▼]

In the following paper we present the work in progress, which aims to validate through theoretical and em- pirical study the probabilistic side of proactive computing. We choose the cognitive modelling methodology as an approach to implement the probabilistic inference of user’s cognitive states during online activity. We create four cognitive models, which simulate various cognitive states of a user during the task of online search of medical terminology. Additionally, we elaborate several potential scenarios, which may take place during the given task, and we associate these scenarios with our models as the integral elements of the proactive system behaviour. Ultimately, by applying the rules of the Bayesian statistics, we envision to test the principles of proactive computing in the frame of probabilistic approach. [less ▲]

A Proactive Approach for Information Sharing Strategies in an Environment of Multiple Connected Ubiquitous Devices

in Proceedings of the 11th IEEE International Conference on Ubiquitous Intelligence and Computing (UIC 2014) (2014)

The current trend in Ubiquitous Computing is to develop smaller, smarter and adaptive devices that are continuously connected to the Internet through wireless technologies. This offers a great opportunity ... [more ▼]

The current trend in Ubiquitous Computing is to develop smaller, smarter and adaptive devices that are continuously connected to the Internet through wireless technologies. This offers a great opportunity for cooperation between these devices. Although much related work has been performed on collaboration techniques between smart devices, most of the work is not suited for large-scale networks, where their number can increase significantly. Following this context, we investigate how information is exchanged and handled in a distributed way in a Collaborative Ubiquitous Environment. To be perceived as collaborative and proactive, each single component has to coordinate with the others in smart way. In order to achieve these key features, we introduce the concept of Global Proactive Scenarios (GPASs). To support the deployment of these scenarios, we propose a specially designed intelligent architecture for ubiquitous systems that allows them to be context-aware, proactive and self-adaptive. Furthermore, we provide an example of joint effort for illustrating the full potential of a network of interconnected proactive systems. [less ▲]

SUPPORTING COLLABORATIVE LEARNING INSIDE COMMUNITIES OF PRACTICE THROUGH PROACTIVE COMPUTING

in Proceedings of the 5th annual International Conference on Education and New Learning Technologies, Barcelona, Spain 1-3 July, 2013 (2013)

This work focuses on a particular area of Computer-Supported Collaborative Learning (CSCL) which looks at how to create, organize and develop Communities of Practice inside a Virtual Learning Management ... [more ▼]

This work focuses on a particular area of Computer-Supported Collaborative Learning (CSCL) which looks at how to create, organize and develop Communities of Practice inside a Virtual Learning Management System (VLMS), i.e. Moodle™, with the help of Proactive Computing. The goal is to increase the on-line participation of students, stimulate the learning process and address common issues in higher education institutions, like transportation, housing, health concerns and students social activities. To achieve this goal, we propose different ways of organizing students into virtual communities with a clear purpose and we provide the tools for building and sharing the knowledge, while our system informs, guides and assists students through the whole process. The current level of involvement of the students at our university’s local Moodle™ platform is quite low, despite the fact the students are obliged to use the platform for extracting, viewing and submitting assignments and other course-related materials. This is why we consider Moodle™ quite static and limited from the point of view of the interface and from the existing ways of creating learning communities. By employing Proactive Computing ([11]), the system becomes aware to the actions or lack of actions of its users, and, on the basis of predefined proactive scenarios, takes appropriate actions for steering users towards enhanced collaboration and social learning. Using the structure of the proactive rule defined in ([13]), we have developed a new set of proactive rules which aims to automatically initiate, maintain and expand social interactions inside communities of students. Each rule is part of one of the stages of the Proactive Cycle, the whole model of proactive scenarios meant to support collaborative techniques for sharing experience, news and practices. The Proactive Cycle is divided into three main categories: “Setting-up Social Groups”, “Enhancing Social Life” and “Adjusting the Social Groups”. Each community starts its life-cycle in the first category and then, after developing over a certain period of time, it will either become a significant community or the system will merge it with another group, or even ending its life-cycle if there are not so many members or the group is inactive. The set of rules will run on the Proactive Engine, developed by Zampunieris ([13]), and aside the local Moodle™ server at our university. A new Java Web Socket Server will ensure an encrypted real-time connection between the Proactive Engine and the Moodle™ blocks (parts of the user interface) developed specially for these experiments. These first series of experiments are taking into account around 1300 real students who currently use the Moodle™ platform over a full semester. We believe our study will be significant in terms of understanding the evolution of virtual study communities, for providing a better learning experience to the users, and in terms of integrating new technologies into an existing learning management system (LMS). The results of this study, which is deployed over the summer semester, are expected to emphasize the importance of having a dynamic, proactive and intuitive learning environment. The Proactive Engine is capable to be integrated with other LMS systems, which would help the whole learning community. [less ▲]

Proactive Computing Based Implementation of Personalized and Adaptive Technology Enhanced Learning over Moodle(TM)

in Proceedings of the 12th IEEE International Conference on Advanced Learning Technologies, Rome, Italy 4-6 July, 2012 (2012)

In this paper, we show how to implement a system that adds proactivity to MoodleTM to reach a personalized and adaptive support for both students and teachers, by providing an engine to run proactive ... [more ▼]

In this paper, we show how to implement a system that adds proactivity to MoodleTM to reach a personalized and adaptive support for both students and teachers, by providing an engine to run proactive rules, based on events and non-events, to enhance the users’ e-learning process. [less ▲]