Hugo Pereira

System for Posture Evaluation and Correction - Development of a Second Prototype for an Intelligent Chair

The sitting position has become one of the most common postures in developed countries. However, assuming a poor sitting posture leads to several health problems, namely back, shoulder and neck pain. In a previous work, an intelligent chair was developed and was shown to classify and correct the seating position. This work describes improvements on this intelligent chair prototype culminating with the development of a new prototype. The improvements of this new prototype are presented, resulting in new studies for posture identification. Pressure maps for 12 sitting postures were gathered in order to automatically detect user’s posture through a neural network algorithm, obtaining an overall posture classification of around 81%.

Sitting Posture Detection using Fuzzy Logic - Development of a Neuro-fuzzy Algorithm to Classify Postural Transitions in a Sitting Posture

In a previous work, a chair prototype was used to detect 11 standardized seating postures of users, using just 8 air bladders (4 in the chair’s seat and 4 in the backrest) and one pressure sensor for each bladder. In this paper we describe a new classification algorithm, which was developed in order to classify the postures using as input the Centre of Pressure, the Posture Adoption Time and the Posture Output from the existing Neural Network Algorithm. This new Posture Classification Algorithm is based on Fuzzy Logic and is able to determine if the user is adopting a good or a bad posture for specific time periods. The newly developed Classification Algorithms will prompt the improvement of new Posture Correction Algorithms based on

Optimization of sitting posture classification based on user identification

In a precursory work, an intelligent sensing chair prototype was developed to classify 12 standardized sitting postures using 8 pneumatic bladders (4 in the chairs seat and 4 in the backrest) connected to piezoelectric sensors to measure inner pressure. A Classification of around 80% was obtained using Neural Networks. This work aims to demonstrate how algorithmic optimization can be applied to a newly developed prototype to improve posture classification performance. The aforementioned optimization is based on the split of users by sex and use two different previously trained Neural Networks (one for Male and the other for Female). Results showed that the best neural network parameters had an overall classification 89.0% (from the 92.1% for Female Classification and 85.8% for Male, which translates into an overall optimization of around 8%). Automatic separation of these sets was achieved with Decision Trees with an overall classification optimization of 87.1%.

Optimization of Sitting Posture Classification based on Anthropometric Data

An intelligent chair prototype was developed in order to detect and correct the adoption of bad sitting postures during long periods of time. A pneumatic system was enclosed in the chair (4 air bladders inside the seat pad and 4 in the backrest) to classify 12 standardized sitting postures, with a classification score of 80.9%. Recently we used algorithmic optimization applied to the existing classification algorithm (based on Neural Networks) to split users (using Classification Trees) by their sex and used two different previously trained Neural Networks (Male and Female) to get an improved classification of 89.0% when the user was identified and 87.1% for unidentified users. In this work we aim to investigate the usage of the anthropometric information (height and weight) to further optimize our classification process. Here we use four Machine Learning Techniques (Neural Networks, Support Vector Machines, Classification Trees and Naive Bayes) to automatically split the users in 2 classes (above and below the specific anthropometric median value). Results showed that Classification Trees worked best on automatically separating the body characteristics (i.e. Height) with a global optimization of 88.3%. During the classification process, if the user is identified, we skip the splitting step, and this optimization increases to 90.2%.

Real-Time Fuzzy Monitoring of Sitting Posture: Development of a New Prototype and a New Posture Classification Algorithm to Detect Postural Transitions

In a previous work, a chair prototype was used to detect 11 standardized siting postures of users, using just 8 air bladders (4 in the chair’s seat and 4 in the backrest) and one pressure sensor for each bladder. In this paper we describe the development of a new prototype, which is able to classify 12 standard postures with an overall score of 80.9 % (using a Neural Network Algorithm). We tested how this Algorithm worked during postural transitions (frontal and lateral flexion) and in intermediate postures, identifying some limitation of this Algorithm. This prompted the development of a Posture Classification Algorithm based on Fuzzy Logic and is able to determine if the user is adopting a good or a bad posture for specific time periods, using as input the Centre of Pressure, the Posture Adoption Time and the Posture Output from the existing Neural Network Algorithm. This newly developed Classification Algorithms is advancing the development of new Posture Correction Algorithms based on Fuzzy Actuators.

The implementation and development of narrow-gauge railways in Portugal as a case of knowledge transfer (c. 1850–c. 1910)

When Portugal began building railways in its mainland territory in the 1850s, the main goal was to connect its harbours (mainly Lisbon) to the border with Spain (and beyond to Central Europe). This strategy left out of the network vast areas of the nation, some of which were perceived as very rugged, poor, and with low economic potential, where the construction of a railway was not cost effective. The same quandaries existed in the colonies, where investment in public works started in the 1870s. To bring railroads to these regions, it was necessary to find a low-cost technical solution. That solution was narrow-gauge railroads. In this paper, we analyse how this technology was transferred from Central Europe to Portugal and its colonies via a travel circuit of learning by Portuguese engineers and how it was developed through a mixture of Portuguese and foreign expertise.

The technodiplomacy of Iberian transnational railways in the second half of the nineteenth century

Abstract In the second half of the nineteenth century Portugal undertook an ambitious public works programme in order to develop the kingdom. In that programme, railways took a leading role, especially those routes that linked the main ports of the shoreline to Spain (and thence to France). To do so, a strenuous effort of diplomacy – or more specifically technodiplomacy – was required to convince Spain to accept cross-border links that served the goals of Portugal. In this paper I will analyse this technodiplomatic process and how two countries with different technological perceptions of railways managed to settle their differences and build five transnational links across their borders over the course of 40 years. I aim to add to the debate about the Iberian cross-border links from the point of view of the history of technology, in particular, and to the discussion about transnational technological systems, in general.