Fábio Silva

Ambient sensorization for the furtherance of sustainability

Energy efficiency is regarded as an important objective in a world of limited resources. The sustainable use of energy is necessary for the continuity of life styles that do not jeopardize the future. Nevertheless, due to poor information about the impact of human actions on the environment, it is hard to promote and warn for sustainability. This work focuses on the use of ambient intelligence as a mean to constantly revise sustainability indicators in a way they may be used for user awareness and recommendation systems within communities. The approach in this research makes use of sustainable indicators monitored through ambient sensors which enable user accountability concerning their actions inside each environment. Also, it is possible to compare the effect of user actions in the environment, enabling decision making based on such comparison factors.

Social Networks Gamification for Sustainability Recommendation Systems

Intelligent environments and ambient intelligence provide means to monitor physical environments and to learn from users, generating data that can be used to promote sustainability. With communities of intelligent environments, it is possible to obtain information about environment and user behaviors which can be computed and ranked. Such rankings are bound to be dynamic as users and environments exchange interactions on a daily basis. This work aims to use knowledge from communities of intelligent environments to their own benefit. The approach presented in this work uses information from each environment, ranking them according to their sustainability assessment. Recommendations are then computed using similarity and clustering functions ranking users and environments, updating their previous records and launching new recommendations in the process.

Ubiquitous sensorization for multimodal assessment of driving patterns

Sustainability issues and sustainable behaviours are becoming concerns of increasing significance in our society. In the case of transportation systems, it would be important to know the impact of a given driving behaviour over sustainability factors. This paper describes a system that integrates ubiquitous mobile sensors available on devices such as smartphones, intelligent wristbands and smartwatches, in order to determine and classify driving patterns and to assess driving efficiency and driver’s moods. It first identifies the main attributes for contextual information, with relevance to driving analysis. Next, it describes how to obtain that information from ubiquitous mobile sensors, usually carried by drivers. Finally, it addresses the multimodal assessment process which produces the analysis of driving patterns and the classification of driving moods, promoting the identification of either regular or aggressive driving patterns, and the classification of mood types between aggressive and relaxed. Such an approach enables ubiquitous sensing of personal driving patterns across different vehicles, which can be used in sustainability frameworks, driving alerts and recommendation systems.

Sensorization and Intelligent Systems in Energetic Sustainable Environments

Sustainability is an important topic of discussion in our world. However, measuring sustainability and assessing behaviors is not always easy. Indeed, and in order to fulfill this goal, in this work it will be proposed a multi-agent based architecture to measure and assess sustainable indicators taken from a given environment. These evaluations will be based on past and present behaviors of the users and the particularities of the setting, leading to the evaluation of workable indicators such as gas emissions, energetic consumption and the users fitting with respect to the milieu. Special attention is given to user interaction and user attributes to calculate sustainable indicators for each type of structure, i.e., the aim of this scheme is to promote sustainability awareness and sustainable actions through the use of sustainable markers calculated in terms of the information gathered from the environment.

Ubiquitous driving and community knowledge

Computer science paradigms such as internet of things and ubiquitous computing has led to the increase of data and information available for use in innovative projects. Smart cities are planned to harness the strengths of these technologies towards the benefit of society. In the case of urban transport, there are new opportunities for information dissemination and driving and traffic flow analysis. Smart devices, are an adequate choice to ubiquitously gather and transmit data unobtrusively. This fuels the opportunity to handle these data as an input for data analysis and fusion processes that discover and aggregate new information to notify users and communities of incorrect practices, thus aiming to effect behavioural change and intelligent planning. The PHESS driving platform is presented as a response to these requirements and as a realization of some of the potentials for ubiquitous computing in smart cities. Although, there are alternatives, this approach focuses on individual and community driving analysis, which differentiate it from other approaches.

Experimental Study of the Stress Level at the Workplace Using an Smart Testbed of Wireless Sensor Networks and Ambient Intelligence Techniques

This paper combines techniques of ambient intelligence and wireless sensor networks with the objective of obtain important conclusions to increase the quality of life of people. In particular, we oriented our study to the stress at the workplace, because stress is a leading cause of illness and disease. This article presents a wireless sensor network obtaining information of the environment, a pulse sensor obtaining hear rate values and a complete data analysis applying techniques of ambient intelligence to predict stress from these environment variables and people attributes. Results show promise on the identification of stressful situations as well as stress inference through the use of predictive algorithms.

Information fusion for context awareness in intelligent environments

The development of intelligent environments requires handling of data perceived from users, received from environments and gathered from objects. Such data is often used to implement machine learning tasks in order to predict actions or to anticipate needs and wills, as well as to provide additional context in applications. Thus, it is often needed to perform operations upon collected data, such as pre-processing, information fusion of sensor data, and manage models from machine learning. These machine learning models may have impact on the performance of platforms and systems used to obtain intelligent environments. In this paper, it is addressed the issue of the development of middleware for intelligent systems, using techniques from information fusion and machine learning that provide context awareness and reduce the impact of information acquisition on both storage and energy efficiency. This discussion is presented in the context of PHESS, a project to ensure energetic sustainability, based on intelligent agents and multi-agent systems, where these techniques are applied.

Traffic expression through ubiquitous and pervasive sensorization: Smart cities and assessment of driving behaviour

The number of portable and wearable devices has been increasing in the population of most developed countries. Meanwhile, the capacity to monitor and register not only data about peoples habits and locations but also more complex data such as intensity and strength of movements has created an opportunity to their contribution to the general wealth and sustainability of environments. Ambient Intelligence and Intelligent Decision Making processes can benefit from the knowledge gathered by these devices to improve decisions on everyday tasks such as planning navigation routes by car, bicycle or other means of transportation and avoiding route perils. Current applications in this area demonstrate the usefulness of real time system that inform the user of conditions in the surrounding area. Nevertheless, the approach in this work aims to describe models and approaches to automatically identify current states of traffic inside cities and relate such information with knowledge obtained from historical data recovered by ubiquitous and pervasive devices. Such objective is delivered by analysing real time contributions from those devices and identifying hazardous situations and problematic sites under defined criteria that has significant influence towards user well-being, economic and environmental aspects, as defined is the sustainability definition.

Credit scoring data for information asset analysis

Risk assessment is an important topic for financial institution nowadays, especially in the context of loan applications. Some of these institutions have already implemented their own credit scoring mechanisms to evaluate their clients’ risk and decide based in this indicator. In fact, the information gathered by financial institutions constitutes a valuable source of data for the creation of information assets from which credit scoring mechanisms can be developed. The purpose of this paper is to, from information assets, create a decision mechanism that is able to evaluate a client’s risk. Furthermore, upon this decision mechanism, a suggestive algorithm is presented to better explain and give insights on how the decision mechanism values attributes.

Computational sustainability and the PHESS platform: Using affective compting as social indicators

Abstract The use of ubiquitous devices on intelligent environment enables opportunities to solve complex problems and react to changes quicker. Namely the use of computational resources to assist the management of environment through predicament of parameters based on sustainable indicators applied to social indicators and intelligent environments. This paper considers a computational sustainability platform which manages contexts supported by principles of computational sustainability and the assurance of sustainable scenarios. An application case study based on the definition of social indicators based on mood analysis demonstrates the application of the platform and some of its innovative functionalities. It uses different types of indicators from classical sustainability dimensions in order to demonstrate the platform. Context gathering and predicative services are used based on these indicators obtained from the environment over public services, sensors networks and ubiquitous devices which are used to create indicators based on the fusion of data.