Arsénio Reis

Feature extraction via multiresolution analysis for short-term load forecasting

The importance of short-term load forecasting has been increasing lately. With deregulation and competition, energy price forecasting has become a big business. Bus-load forecasting is essential to feed analytical methods utilized for determining energy prices. The variability and nonstationarity of loads are becoming worse, due to the dynamics of energy prices. Besides, the number of nodal loads to be predicted does not allow frequent interactions with load forecasting experts. More autonomous load predictors are needed in the new competitive scenario. This paper describes two strategies for embedding the discrete wavelet transform into neural network-based short-term load forecasting. Its main goal is to develop more robust load forecasters. Hourly load and temperature data for North American and Slovakian electric utilities have been used to test the proposed methodology.

NeuroDem-a neural network based short term demand forecaster

The application of Neural Network (NN) based short-term load forecasting (STLF) has developed to sophisticated practical systems over the years. However, the question of how to maximize the generalization ability of such machines, together with the choice of architecture, activation functions, training set data and size, etc. makes up a huge number of possible combinations for the final NN design, whose optimal solution has not been figured yet. This paper describes a STLF system (NeuroDem) which has been used by Brazilian electric utilities for 3 years. It uses a nonparametric model based on a linear model coupled with a polynomial network, identified by pruning/growing mechanisms. NeuroDem has special features of data pre-processing and confidence intervals calculations, which are also described. Results of load forecasts are presented for one year with forecasting horizons from 15 min to 168 hours ahead.

Supporting accessibility in higher education information systems

Higher education institutions (HEI) and students are highly dependent of information systems, implemented as web applications. Students must be able to access this applications, thought accessible web interfaces, in order to perform their academic activities. This paper presents an overview of a typical set of web applications used by students and the main concerns regarding accessibility compliance. The analysis was conducted using the systems at the University of Tras-os-Montes e Alto Douro.

Developing a System for Post-Stroke Rehabilitation: An Exergames Approach

Stroke episodes are a major health issue worldwide for which most patients require an initial period of special rehabilitation and functional treatment, involving medical doctors and specialized therapists, followed by ambulatory physiotherapy exercise. In this second period most do not fulfil the prescribed recovery plan, resulting in setbacks in their recovery. This paper reports on the design of a methodology to develop a system to support the ambulatory rehabilitation therapy, providing constant feedback to the clinicians, by means of an information system platform, and maintaining the patient motivation by using an exergames approach to design and deliver the therapy exercises to the patient.

Assessment of Microsoft Kinect in the Monitoring and Rehabilitation of Stroke Patients

Telerehabilitation is an alternative way for physical therapy of stroke patients. The monitoring and correction of exercises can be done through the analysis of body movements recorded by an optical motion capture system. This paper presents a first study to assess the use of Microsoft Kinect in the monitoring and rehabilitation of patients who have suffered a stroke. A comparative study was carried out to assess the accuracy of joint angle measurement with the Microsoft Kinect (for Windows and for Xbox One) and Optitrack™. The results obtained in the first experiment showed a good agreement in the measurements between the three systems, in almost all movements. These results suggest that Microsoft Kinect, a low cost and markerless motion capture system, can be considered as an alternative to complex and high cost motion capture devices for the monitoring and rehabilitation of stroke patients.

Autonomous systems to support social activity of elderly people a prospective approach to a system design

The reduction in physical and social activity in elderly people degrades the aging process, causing or increasing suffering to the individual and to his family and friends. Most times, the individual well-being is related to the strength of the social bonds with the family and friends group, so it is important to keep this bonds in the various stages of life, especially in the later life, when the individual has health limitations and is living in a community centre. This paper proposes an exploratory approach, regarding the use of information technologies systems, as autonomous systems, to assist in supporting and encouraging elderly people to preserve and develop their social activities and the relationships with their family and friends social group. During the course of the aging process, some aging people have their social activity degraded due to health limitations and institutionalization in elderly care centers, in which they are admitted as residents. We propose the design of a software system, capable of running in autonomous devices, such as, robots and other consumer appliances, enabling them to recognize and interact with the users, according to their state of mind and the specific current moment context. The interactions should be simple and focused on keeping the users informed about the current life events of their family and friends, and create the opportunities for the users to interact with the participants of those events by creating interaction proposals. The systems would monitor the users family and friends group, regarding their information and actions on the social media. The systems interactions with the user would be based on that knowledge and on the knowledge of the users current context. An adaptive user interface would present and manage the user interactions, acting as a mediator between the user and his family and friends group.

Supporting Accessibility in Higher Education Information Systems: A 2016 Update

Higher Education Institutions (HEIs) have come a long way on the usage of Information Systems (IS) at the several phases of the execution of their business plan. These organizations are very peculiar in the sense that most of the IS technologies have been developed as a consequence of the research work of the HEIs, positioning them as creators and as consumers of IS technologies. In fact, a considerable part of the IS products, currently available for the education sector, was initially created in a HEI as an in-house development. For these reason, the adoption of IS technologies by HEIs has followed two distinct paths: the in-house creation, previously described; and a current market adoption, similarly to most other companies IS adoption.

Management of surgery waiting lists in the Portuguese public healthcare network: The information system for waiting list recovery programs

This paper presents the evolution of the process for management of surgery waiting lists in the Portuguese public hospital network. We use the perspective of the software development and deployment by UTAD, as a partner of the Ministry of Health, to create an information system to manage list recovery programs. We describe the early status and work, when data harvesting was the core challenge, up to the current automated situation. This paper bridges the PERLE, PPMA, PECLEC and SIGIC programmes, and concludes with lessons learned and suggestions for evolution of the process.

AppVox: An Application to Assist People with Speech Impairments in Their Speech Therapy Sessions

In this study an application to assist people with speech impairments in their speech therapy sessions is presented. AppVox simulates a vocalizer (audio stimulus feature) that can be used to train speech by repeating different words. In this paper, we aim at presenting the application as an assistive technology option and assess if this is a usable option for digital interaction for children with speech impairment. To assess the application we present a case study in which the participants were asked to perform tasks using the AppVox application. The results showed that this group of participants attained a good performance when interacting with the application.

Using Intelligent Personal Assistants to Strengthen the Elderlies’ Social Bonds

Social isolation and loneliness are among the important factors for the degradation of the life quality as the persons’ aging process advances. These factors can have a pronounced effect on the general health and are caused by the decrease in social interaction by the person with the friends, family and ex-co-workers groups. On the other hand, the software and hardware technologies has reached a maturation point were the electronic assistants can acquire information from the user through camera images, as well as to communicate with the user by means of natural voice language. In this context, a model for the adoption of electronic intelligent assistants by the elderlies has been proposed in previous work. In the current work, it is assessed the possibility of using the current consumer assistants to implement the proposed model. Several assistants are analyzed (Amazon, Google, Microsoft and Apple), assessing their functionalities and how they could be used to assist the elderly in strengthening their social bonds with the family, friends and ex-co-workers groups.