não competitivo

PIDI/CISeD/2022/007 • Modelos de Machine Learning para Deteção de Padrões e Preferências Alimentares

[DDSS] Digital Decision Support Systems, concluído, interno, nacional, não competitivo, não financiado, viseu /

Principal Researcher: Rui Pedro Duarte
Duration: 2022 – 2024

Cised team members
Carlos Augusto da Silva Cunha
Ricardo Luís da Costa Gama

Food assumes an increasingly important role in people's lives, and adequate nutrition associated with a healthy lifestyle increases the average life expectancy. To this end, there has been an increase in the number of people whom nutritionists are following to have a food plan suited to their needs, which vary according to each person's goals: from the purely aesthetic component, through the improvement of the quality of life, for professional reasons (such as sportsmen or high competition athletes), even people with special needs, in which a correct diet impacts on the aggravation of previously diagnosed diseases. There are, however, some associated problems that can impact noncompliance with a previously defined meal plan. One of them is defining a food plan made up of foods people don't like. The other relates to real-time notification of the nutritionist of the correct fulfilment of the plan in terms of the proper intake of recommended macronutrients in each meal of the food plan.

Regarding the first, the combination of foods is a factor mainly linked to people's preferences, far beyond the rules of food combinations recommended by nutritionists. Thus, patterns for each individual may vary over time and as a function of other conditions (e.g., temperature, season). People's sensitivity to these combinations is one of the factors responsible for abandoning eating plans and not matching their food tastes. With this work, we intend to develop an Artificial Intelligence model to detect food patterns to adapt a food plan defined by a nutritionist in an evolutionary way and in real-time to allow the correct management of the plan. Thus, it becomes possible to provide a better quality of life to people who need to define food plans in various types of contexts.

, ,

PIDI/CISeD/2022/006 • STORYTur – O uso do storytelling em vídeos promocionais turísticos

[CDS] Connected Digital Society, concluído, interno, nacional, não competitivo, não financiado, viseu /

Principal Researcher:
Sara Santos
Duration: 2022 – 2024

Cised team members
Luísa Augusto

Currently, more and more cities and regions differentiate themselves through the creation of a positive identity and image, developing territorial branding. The use of storytelling can also be an asset when used to promote tourist destinations. It is essential that the entities that manage the tourist image of Portuguese regions rethink their dissemination strategies and give priority to “storytelling”, emotions, and involvement with the public in building the image of the territories. Territorial marketing, and in particular the focus on tourism promotion videos, allows to demonstrate the unique characteristics of the territory and its differentiation from the others. Through the story told about the region, the audience identifies with the characters and is “transported” by the narrative.

In Portugal, the Centro region has stood out for the promotional films (with storytelling techniques) that it uses to promote the Center of Portugal. In recent years, “Turismo do Centro” has won dozens of international awards related to tourism promotion. For its part, the “Aldeias Históricas de Portugal” also won the world award for best tourism film in the world, in 2021.

Considering this worldwide recognition, this project will have the partnership of “Turismo do Centro” and “Aldeias Históricas de Portugal”, as examples of good practices in tourism promotion of regions through storytelling in promotional videos.

STORYtur's main objective is to understand the strategies for promoting tourism in Portuguese regions, especially in the Center region.

The project comprises the development of studies through interviews (to the representatives of “Turismo do Centro” and “Aldeias Históricas de Portugal”) and the application of questionnaires to the public.

, ,

PIDI/CISeD/2023/011 • Modelos de Inteligência Artificial para Deteção de Stress Crónico e Padrões de Movimento em Ambientes de Atividades da Vida Diária

Leave a Comment / [CDS] Connected Digital Society, concluído, interno, nacional, não competitivo, não financiado, viseu /

Principal Researcher:
Rui Pedro Duarte
Duration: 2022 – 2024

Cised team members
Carlos Augusto da Silva Cunha

For a long time, stress has been considered an important health factor that affects the quality of life. Several studies indicate that excessive and continuous stress can trigger or worsen several diseases, such as cancer and cardiovascular. Stress is a response to a stressor, an external stimulus or condition that causes an emotional, physical, or psychological change in the individual. However, even though momentary stress can be easily identified, it is hard for people to recognize that they are living a stressful life. Multiple sclerosis (MS) is a chronic disease that affects individuals. It has symptoms on diverse levels, such as vision, fatigue, numbness and tingling, muscle spasms, stiffness and weakness, mobility problems, problems with thinking, learning, planning, and even depression and anxiety. With this, a few critical questions need to be raised: Is there any relation between stress and MS exacerbations? What are the relevant biomarkers to identify continuous stress? Are they reliable? Are their measurements little intrusive?
Thus, it is vital to measure stress and identify its types, in order to monitor and help people to deal with the manifestations of stress. It becomes crucial to identify continuous stress, as there are studies that indicate that it has a negative impact, while a systemic stress situation may even be rewarded. The monitoring process of this continuous stress needs to be controlled and with low intrusion in the user, so that it does not have negative effects on their lifestyle. For that, there are several biomarkers to identify stress in people, but not all are recommended. The most indicated biomarkers are heart rate (HR) and electrical conductivity, which can be monitored by devices such as smart watches. With this, it is possible to train artificial intelligence models to create a solution to detect long-term stress, which does not harm people's quality of life.

, ,

PIDI/CISeD/2021/002 • Combinações de relações bancárias e detentores do seu capital, custos de financiamento, performance e estrutura de capital das empresas

[DDSS] Digital Decision Support Systems, concluído, interno, nacional, não competitivo, não financiado, viseu /

Principal Researcher:
Pedro Manuel Nogueira Reis
António Pedro Soares Pinto

Duration: 2021 – 2023

A revisão da literatura identifica o efeito do poder de mercado do sistema bancário nos custos de financiamento da empresa (Wang et al., 2020; Abubakr & Esposito, 2012; Han et al., 2015), na estrutura de capital das pequenas empresas (Degryse et al., 2012), da inclusão financeira – acesso adequado, atempado e a custos reduzidos a um conjunto de produtos e serviços financeiros regulados, aumentando o bem-estar financeiro (Banco de Portugal, 2017) – e no desempenho da empresa (Chauvet & Jacolin, 2017). Contudo, pelo que seja do nosso conhecimento, ainda não foi realizado qualquer estudo que avalie o impacto das possíveis combinações das relações com as diversas instituições bancárias, bem como com as características dos seus detentores de capital, com as quais as empresas estabelecem relações, na sua atividade. O estudo incide sobre Pequenas e Médias Empresas (PME´s), que representam cerca de 99,9% do tecido empresarial português em 2019 (PORDATA, 2021) e 99,9% do tecido empresarial espanhol em janeiro de 2020 (MINISTERIO DE INDUSTRIA, COMERCIO Y TURISMO, 2021), constituindo este o grande impulso e motivação para a realização desta investigação. Para além, das características da carteira de credores de financiamento remunerado, o estudo contempla diferentes variáveis de controlo, tais como, a idade das empresas, o número de empregados, total de ativos, localização da empresa, quantidade de bancos de relação da empresa, entre outras características que se tornem relevantes para a análise.

OBJETIVOS
Este estudo procura avaliar de que forma as características das principais instituições bancárias que concedem crédito à empresa e, as relações de combinação entre elas, condicionam a estrutura de capital, os custos de financiamento e o desempenho das empresas, nomeadamente, nas de menor dimensão. Para além deste objetivo, também as características dos detentores de capital que controlam as instituições financeiras com as quais as empresas estabelecem relação será propósito de análise, no que respeita à sua influência na atividade financeira e operacional da empresa.
O universo da amostra em análise, será constituído por PME’s ibéricas, recolhido na base de dados SABI – Bureau Van Dijk, com recurso à análise de dados seccionados. Pretende-se também, aferir a prevalência, ou não, de diferenças significativas no comportamento das empresas portuguesas e espanholas.
Os dados serão analisados recorrendo a técnicas de inferência estatística como testes de hipóteses paramétricos e não paramétricos, regressão multivariada com recurso a equações simultâneas, modelando pelo estimador de 2 ou 3 estágios dos mínimos quadrados, procurando dar resposta às questões em investigação.

, ,

PIDI/CISeD/2021/001 • Industrial Augmented Reality (IAR)

[DDSS] Digital Decision Support Systems, concluído, interno, nacional, não competitivo, não financiado, viseu /

Principal Researcher:
José Silva
Duration: 2021 – 2023

Cised team members
Olga Contente
Serafim Oliveira
Daniel Gaspar

The constant changes in the contextual environment and the continuous globalization cause changes in the market, which push the companies to look for new technologies to increase productivity and profitability. In addition, customer requirements force companies to make their production systems more flexible, efficient and competitive.

It is due to these changes that the need arises to implement interconnected systems, integrated into an industrial IoT platform (IIoT - Industrial Internet of Things), supported by the connection of equipment and production systems so that companies can create networks along the value chain and thus control and command processes independently and in real-time.

The implementation in organizations of intelligent and interconnected ecosystems allows making decisions in a decentralized way. However, it is necessary to provide tools to assist in decision-making, monitoring operations, and reducing errors by the operator.
This project aims to respond to this challenge with the application of solutions developed in augmented reality (AR) in an industrial environment.

The integration of AR in a production system allows to reduce production errors and increase the efficiency of product development since there is constant monitoring during the performance of tasks.

This project is based on three fundamental objectives.
One of the objectives of this project is the implementation of solutions developed in AR, in various industrial applications, namely, in carrying out maintenance interventions (inspection with remote support or access to instructions in virtual windows), in guiding employees through procedures, either be it the first time or a recurring task, using holographic step-by-step instructions and issuing alerts to users with the details necessary for the execution of operations.
The other objective is the integration of the AR system with an existing IIoT platform, which will allow obtaining and viewing in real-time the desired information for each equipment, such as the operating temperature, energy consumption, or the condition of the components. that integrate the equipment.
It is also the objective of this project to develop the best visualization solution taking into account the particularities of each application so that the interaction with the projections is fluid and with reduced latency.
Digital objects, from industrial equipment, will be developed using programming algorithms and spatial digitization for referencing the anchoring points of the real space where these objects are immersed.

, , , ,

PROJ/IPV/ID&I/002 • Sistema Inteligente de Controlo de Planos Alimentares para Doentes de Alzheimer e Outras Demências

[CDS] Connected Digital Society, concluído, interno, não competitivo, não financiado, viseu /

Principal Researcher: Carlos Augusto Cunha
Duration: 2020 – 2022

Cised team members
Valter Alves
Rui Pedro Duarte

Funding
CGD; PV

Alzheimer's disease is a progressive loss of mental function, characterized by degeneration of brain tissue, including loss of nerve cells, accumulation of an abnormal protein, and development of neurofibrillary braids. Alzheimer's patients become dependent on other people, even for the most basic tasks. Controlling feeding and hydrating an Alzheimer's patient is thus a crucial task performed by the person who supports their daily routine, called Informal Caregiver (IC).

Conditions of malnutrition, super nutrition, and dehydration are common in people with diseases causing dementia since the loss of their autonomy also manifests itself in the level of their inability to demonstrate food needs. The support of a nutritionist in the preparation and follow-up of a food plan aligned with the needs of the patient is, therefore, fundamental. The monitoring of the food plan is undoubtedly a process that demands from Cl a lot of discipline and the ability to deal with possible circumstantial adaptations, such as replacing foods prescribed in the food plan with other equivalents or changing the quantity of water consumed as a function of ambient temperature.

This project addresses the problem of the creation and monitoring of diet plans in patients with dementia such as Alzheimer's, through the creation of a computer solution. It allows the creation of nutritional plans by the nutritionists using a Web application and the follow-up of these plans by the ICs through an app to significantly increase the quality of life of the patient. The mobile app will be able to send to the CI notifications regarding proper nutrition and hydration in due moments, accompanied by the control of hydration using an intelligent water bottle, will allow ensuring the compliance of the indications of the nutritionist. Besides, the application will suggest alternatives to plan foods if they are unavailable. Another central feature of the solution is the dynamic adaptation of water administration to the patient as a function of the environmental conditions automatically collected by temperature and humidity sensors.

In scientific terms, the project includes the creation of innovative models for adapting food plans using machine learning algorithms and integration approaches, preprocessing and evaluation of data quality collected by external sensors.

, , ,

PROJ/IPV/ID&I/007 • Sistema Inteligente de Controlo de Planos Alimentares para o Desporto

[CDS] Connected Digital Society, concluído, interno, nacional, não competitivo, não financiado, viseu /

Principal Researcher:
Carlos Cunha
Duration: 2019 – 2022

Cised team members
Rui Pedro Duarte
Valter Alves

Funding
CGD; PV

The recent growth in the pursuit of sporting activities, motivated by a widespread increase in the perception of the importance of maintaining physical fitness, campaigns specifically aimed at combating physical inactivity, and opportunities created by the revelation of lesser known modalities, brought forward fundamental questions such as the correct nutrition of the practitioners. Numerous institutions involved in the practice of physical activity, which have since flourished, have been integrating these concerns into their scope, including through nutritionists.

For a nutritionist, the elaboration and monitoring of a food plan in line with the needs of the individual present two critical problems: 1) obtaining biometric data, eating habits and energy consumption to create the food plan, and 2) monitoring and the dynamic adaptation of the food plan.

Sports nutrition is one of the most complex areas of nutrition, since it requires observation of a rather comprehensive set of metrics, encompassing the athlete's physical aspects, physical activity, and eating habits. The use of measuring devices for specific parameters of physical activity represents a common practice among athletes. The integration of data automatically collected by these devices with other data not directly observable, such as dietary habits and subjective metrics, is part of the complexity of creating a global register that can be used by the nutritionist during the development of the plan to feed. Also, at a stage after the preparation of the food plan, the need to adapt it may arise. For example, variations in temperature or physical intensity may involve quick changes in the energy or hydration needs of an individual. In such situations, the data collected by the devices could be used to dynamically adjust the plan and send alerts, informing the sportsman of the need to eat food or water at the right time.

The objectives of this project include the creation of (a) a Web application where the nutritionist can record and follow up on dietary plans and (b) a mobile app for sportspersons, which can collect data provided by smart devices or manually entered, and where they can plan and receive notifications. In scientific terms, the project includes the creation of innovative models for adapting food plans using machine learning algorithms and integration approaches, preprocessing and evaluation of data quality collected by external devices.

, , ,
Scroll to Top