Machine diagnosis based on artificial immune systems

Nowadays, many of the manufactory and industrial system has a diagnosis system on top of it, responsible for ensuring the lifetime of the system itself. It achieves this by performing both diagnosis and error recovery procedures in real production time, on each of the individual parts of the system. There are many paradigms currently being used for diagnosis. However, they still fail to answer all the requirements imposed by the enterprises making it necessary for a different approach to take place. This happens mostly on the error recovery paradigms since the great diversity that is nowadays present in the industrial environment makes it highly unlikely for every single error to be fixed under a real time, no production stop, perspective. This work proposes a still relatively unknown paradigm to manufactory. The Artificial Immune Systems (AIS), which relies on bio-inspired algorithms, comes as a valid alternative to the ones currently being used. The proposed work is a multi-agent architecture that establishes the Artificial Immune Systems, based on bio-inspired algorithms. The main goal of this architecture is to solve for a resolution to the error currently detected by the system. The proposed architecture was tested using two different simulation environment, each meant to prove different points of views, using different tests. These tests will determine if, as the research suggests, this paradigm is a promising alternative for the industrial environment. It will also define what should be done to improve the current architecture and if it should be applied in a decentralised system.

Consulting project for Câmara Municipal de Cascais street vending in Portugal- creation and development of a new sales channel

Field lab: Consulting lab

Contributions towards smart cities : exploring block level census data for the characterization of change in Lisbon

The interest in using information to improve the quality of living in large urban areas and its governance efficiency has been around for decades. Nevertheless, the improvements in Information and Communications Technology has sparked a new dynamic in academic research, usually under the umbrella term of Smart Cities. This concept of Smart City can probably be translated, in a simplified version, into cities that are lived, managed and developed in an information-saturated environment. While it makes perfect sense and we can easily foresee the benefits of such a concept, presently there are still several significant challenges that need to be tackled before we can materialize this vision. In this work we aim at providing a small contribution in this direction, which maximizes the relevancy of the available information resources. One of the most detailed and geographically relevant information resource available, for the study of cities, is the census, more specifically the data available at block level (Subsecção Estatística). In this work, we use Self-Organizing Maps (SOM) and the variant Geo-SOM to explore the block level data from the Portuguese census of Lisbon city, for the years of 2001 and 2011. We focus on gauging change, proposing ways that allow the comparison of the two time periods, which have two different underlying geographical bases. We proceed with the analysis of the data using different SOM variants, aiming at producing a two-fold portrait: one, of the evolution of Lisbon during the first decade of the XXI century, another, of how the census dataset and SOM’s can be used to produce an informational framework for the study of cities.

How could marketing automation impact the business performance of Comexposium?

Comexposium continues to exhibit strong growth through global acquisition of key events. However, the company identified the need to increase the renewal rate of its exhibitors. In order to do so, Comexposium determined marketing automation software could have enormous value. However, the company currently does not have the appropriate data to determine to specific returns the software could provide. Thus, this report focused on assessing the impact of marketing automation on the business performance of a B2B enterprise and the best methods to implement and measure it. The main findings were that the software could be of immense value to Comexposium, if the company is ready to invest in internal resources and take the time to adapt to the changes the tool will incur.

Ontology-based representation and generation of workflows for micro-task human-machine computation

Doctoral Program in Computer Science

Operation modes of battery chargers for electric vehicles in the future smart grids

This paper presents an on-board bidirectional battery charger for Electric Vehicles (EVs), which operates in three different modes: Grid-to- Vehicle (G2V), Vehicle-to-Grid (V2G), and Vehicle-to-Home (V2H). Through these three operation modes, using bidirectional communications based on Information and Communication Technologies (ICT), it will be possible to exchange data between the EV driver and the future smart grids. This collaboration with the smart grids will strengthen the collective awareness systems, contributing to solve and organize issues related with energy resources and power grids. This paper presents the preliminary studies that results from a PhD work related with bidirectional battery chargers for EVs. Thus, in this paper is described the topology of the on-board bidirectional battery charger and the control algorithms for the three operation modes. To validate the topology it was developed a laboratory prototype, and were obtained experimental results for the three operation modes.

Smart platform towards batteries analysis based on internet-of-things

This paper presents a new approach of pre-defined profiles, based in different voltage and current values, to control the charging and discharging processes of batteries in order to assess their performance. This new approach was implemented in a prototype that was specially developed for such purpose. This prototype is a smart power electronics platform that allows to perform batteries analysis and to control the charging and discharging processes through a web application using pre-defined profiles. This platform was developed aiming to test different batteries technologies. Considering the relevance of the energy storage area based in batteries, especially for the batteries applied to electric mobility systems, this platform allows to perform controlled tests to the batteries, in order to analyze the batteries performance under different scenarios of operation. Besides the results obtained with the batteries, this work also intends to produce results that can contribute to an involvement in the strengthening of the Internet-of-Things.

Smart charging management for electric vehicle battery chargers

This paper proposes a smart battery charging strategy for Electric Vehicles (EVs) targeting the future smart homes. The proposed strategy consists in regulate the EV battery charging current in function of the total home current, aiming to prevent overcurrent trips in the main switch breaker. Computational and experimental results were obtained under real-time conditions to validate the proposed strategy. For such purpose was adapted a bidirectional EV battery charger prototype to operate in accordance with the aforementioned strategy. The proposed strategy was validated through experimental results obtained both in steady and transient states. The results show the correct operation of the EV battery charger even under heavy load variations.

Multifunctional converter to interface renewable energy sources and electric vehicles with the power grid in smart grids context

This paper proposes a multifunctional converter to interface renewable energy sources (e.g., solar photovoltaic panels) and electric vehicles (EVs) with the power grid in smart grids context. This multifunctional converter allows deliver energy from the solar photovoltaic panels to an EV or to the power grid, and exchange energy in bidirectional mode between the EV and the power grid. Using this multifunctional converter are not required multiple conversion stages, as occurs with the traditional solutions, where are necessary two power converters to integrate the solar photovoltaic system in the power grid and also two power converters to integrate an off-board EV battery charger in the power grid (dc-dc and dc-ac power converters in both cases). Taking into account that the energy provided (or delivered) from the power grid in each moment is function of the EV operation mode and also of the energy produced from the solar photovoltaic system, it is possible to define operation strategies and control algorithms in order to increase the energy efficiency of the global system and to improve the power quality of the electrical system. The proposed multifunctional converter allows the operation in four distinct cases: (a) Transfer of energy from the solar photovoltaic system to the power grid; (b) Transfer of energy from the solar photovoltaic system and from the EV to the power grid; (c) Transfer of energy from the solar photovoltaic system to the EV or to the power grid; (d) Transfer of energy between the EV and the power grid. Along the paper are described the system architecture and the control algorithms, and are also presented some computational simulation results for the four aforementioned cases. It is also presented a comparative analysis between the traditional and the proposed solution in terms of operation efficiency and estimated cost of implementation.

Hand gesture recognition system based in computer vision and machine learning

"Lecture notes in computational vision and biomechanics series, ISSN 2212-9391, vol. 19"

Detection of dangerous situations using a smart internet of things system

The Internet of Things (IoT) is a concept that can foster the emergence of innovative applications. In order to minimize parents’s concerns about their children’s safety, this paper presents the design of a smart Internet of Things system for identifying dangerous situations. The system will be based on real time collection and analysis of physiological signals monitored by non-invasive and non-intrusive sensors, Frequency IDentification (RFID) tags and a Global Positioning System (GPS) to determine when a child is in danger. The assumption of a state of danger is made taking into account the validation of a certain number of biometric reactions to some specific situations and according to a self-learning algorithm developed for this architecture. The results of the analysis of data collected and the location of the child will be able in real time to child’s care holders in a web application.

Towards "green" smart materials for force and strain sensors: The case of polyaniline

Stress/strain sensors constitute a class of devices with a global ever-growing market thanks to their use in many fields of modern life. They are typically constituted by thin metal foils deposited on flexible supports. However, the low inherent resistivity and limited flexibility of their constituents make them inadequate for several applications, such as measuring large movements in robotic systems and biological tissues. As an alternative to the traditional compounds, in the present work we will show the advantages to employ a smart material, polyaniline (PANI), prepared by an innovative environmentally friendly route, for force/strain sensor applications wherein simple processing, environmental friendliness and sensitivity are particularly required.

Discrimination of Brazilian propolis according to the seasoning using chemometrics and machine learning based on UV-Vis scanning data

Propolis is a chemically complex biomass produced by honeybees (Apis mellifera) from plant resins added of salivary enzymes, beeswax, and pollen. The biological activities described for propolis were also identified for donor plants resin, but a big challenge for the standardization of the chemical composition and biological effects of propolis remains on a better understanding of the influence of seasonality on the chemical constituents of that raw material. Since propolis quality depends, among other variables, on the local flora which is strongly influenced by (a)biotic factors over the seasons, to unravel the harvest season effect on the propolis chemical profile is an issue of recognized importance. For that, fast, cheap, and robust analytical techniques seem to be the best choice for large scale quality control processes in the most demanding markets, e.g., human health applications. For that, UV-Visible (UV-Vis) scanning spectrophotometry of hydroalcoholic extracts (HE) of seventy-three propolis samples, collected over the seasons in 2014 (summer, spring, autumn, and winter) and 2015 (summer and autumn) in Southern Brazil was adopted. Further machine learning and chemometrics techniques were applied to the UV-Vis dataset aiming to gain insights as to the seasonality effect on the claimed chemical heterogeneity of propolis samples determined by changes in the flora of the geographic region under study. Descriptive and classification models were built following a chemometric approach, i.e. principal component analysis (PCA) and hierarchical clustering analysis (HCA) supported by scripts written in the R language. The UV-Vis profiles associated with chemometric analysis allowed identifying a typical pattern in propolis samples collected in the summer. Importantly, the discrimination based on PCA could be improved by using the dataset of the fingerprint region of phenolic compounds ( = 280-400m), suggesting that besides the biological activities of those secondary metabolites, they also play a relevant role for the discrimination and classification of that complex matrix through bioinformatics tools. Finally, a series of machine learning approaches, e.g., partial least square-discriminant analysis (PLS-DA), k-Nearest Neighbors (kNN), and Decision Trees showed to be complementary to PCA and HCA, allowing to obtain relevant information as to the sample discrimination.