Detecção de potenciais corticais antecipatórios em sinais de eletroencefalografia (EEG) durante a condução de carros

O reconhecimento da intenção do condutor a partir de sinais de eletroencefalografia (EEG) pode ser útil no desenvolvimento de interfaces cérebro computador (BCI) para serem usadas em sinergia com veículos inteligentes. Isso pode ser benéfico para melhorar a qualidade de interação entre o motorista e o carro, por exemplo, fornecendo uma resposta do carro inteligente alinhada com a intenção do motorista. Neste estudo, considera-se a antecipação como sendo o estado cognitivo que leva a ações especificas durante a condução de um automóvel. Portanto, propomos investigar a presença de padrões antecipatórios em sinais EEG durante a condução de veículos para determinar duas ações especifícas (1) virar à esquerda e (2) virar à direita, alguns milissegundos antes que tais ações aconteçam. Um protocolo experimental foi proposto para gravar sinais EEG de 5 indivíduos enquanto eles operam um simulador de realidade virtual não invasiva - que foi projetado para tal experimento - que simula a condução de um carro virtual. O protocolo experimental é uma variante do paradigma da variação negativa contingente (CNV) com condições Go e No-go no sistema de condução de realidade virtual. Os resultados apresentados neste estudo indicam a presença de padrões antecipatórios em potenciais corticais lentos observados no domínio do tempo (medias dos sinais EEG) e da frequência (Power Spectra e coerência de fase). Isso abre um leque de possibilidades no desenvolvimento de sistemas BCI - baseados em sinais antecipatórios - que conectem o motorista ao veiculo inteligente favorecendo uma tomada de decisão que analise as intenções dos condutores podendo eventualmente evitar acidentes durante a condução.

ExperNet: An Intelligent Multiagent System for WAN Management

This paper describes ExperNet, an intelligent multi-agent system that was developed under an EU funded project to assist in the management of a large-scale data network. ExperNet assists network operators at various nodes of a WAN to detect and diagnose hardware failures and network traffic problems and suggests the most feasible solution, through a web-based interface. ExperNet is composed by intelligent agents, capable of both local problem solving and social interaction among them for coordinating problem diagnosis and repair. The current network state is captured and maintained by conventional network management and monitoring software components, which have been smoothly integrated into the system through sophisticated information exchange interfaces. For the implementation of the agents, a distributed Prolog system enhanced with networking facilities was developed. The agents’ knowledge base is developed in an extensible and reactive knowledge base system capable of handling multiple types of knowledge representation. ExperNet has been developed, installed and tested successfully in an experimental network zone of Ukraine.

System definition report for the National Driver Register Design Study. Interim report.

National Highway Traffic Safety Administration, Traffic Safety Programs, Washington, D.C.

Giving Peru a productivity boost : towards a system of continuous education and training

In spite of impressive rates of economic growth, the quality of the labor force’s human capital is considered a major challenge for sustaining medium term economic growth in Peru. This note reviews the skills of the Peruvian labor force, and the status of the continuous education and training system. Based on such an assessment and on learnings from international best practices, it proposes a system of continuous education and training that draws from international best practices, but that addresses local capacity and institutional issues.

An Evaluative Model to Assess the Organizational Efficiency in Training Corporations

In an organisation any optimization process of its issues faces increasing challenges and requires new approaches to the organizational phenomenon. Indeed, in this work it is addressed the problematic of efficiency dynamics through intangible variables that may support a different view of the corporations. It focuses on the challenges that information management and the incorporation of context brings to competitiveness. Thus, in this work it is presented the analysis and development of an intelligent decision support system in terms of a formal agenda built on a Logic Programming based methodology to problem solving, complemented with an attitude to computing grounded on Artificial Neural Networks. The proposed model is in itself fairly precise, with an overall accuracy, sensitivity and specificity with values higher than 90 %. The proposed solution is indeed unique, catering for the explicit treatment of incomplete, unknown, or even self-contradictory information, either in a quantitative or qualitative arrangement.

Model-Based validation of Driver Drowsiness Detection System for ADAS

The work described in this Master’s Degree thesis was born after the collaboration with the company Maserati S.p.a, an Italian luxury car maker with its headquarters located in Modena, in the heart of the Italian Motor Valley, where I worked as a stagiaire in the Virtual Engineering team between September 2021 and February 2022. This work proposes the validation using real-world ECUs of a Driver Drowsiness Detection (DDD) system prototype based on different detection methods with the goal to overcome input signal losses and system failures. Detection methods of different categories have been chosen from literature and merged with the goal of utilizing the benefits of each of them, overcoming their limitations and limiting as much as possible their degree of intrusiveness to prevent any kind of driving distraction: an image processing-based technique for human physical signals detection as well as methods based on driver-vehicle interaction are used. A Driver-In-the-Loop simulator is used to gather real data on which a Machine Learning-based algorithm will be trained and validated. These data come from the tests that the company conducts in its daily activities so confidential information about the simulator and the drivers will be omitted. Although the impact of the proposed system is not remarkable and there is still work to do in all its elements, the results indicate the main advantages of the system in terms of robustness against subsystem failures and signal losses.

Energy efficiency analysis considering the use of an intelligent systems management in a smart home

In this abstract is presented an energy management system included in a SCADA system existent in a intelligent home. The system control the home energy resources according to the players definitions (electricity consumption and comfort levels), the electricity prices variation in real time mode and the DR events proposed by the aggregators.

Contextual intelligent load management with ANN adaptive learning module

With the current increase of energy resources prices and environmental concerns intelligent load management systems are gaining more and more importance. This paper concerns a SCADA House Intelligent Management (SHIM) system that includes an optimization module using deterministic and genetic algorithm approaches. SHIM undertakes contextual load management based on the characterization of each situation. SHIM considers available generation resources, load demand, supplier/market electricity price, and consumers’ constraints and preferences. The paper focus on the recently developed learning module which is based on artificial neural networks (ANN). The learning module allows the adjustment of users’ profiles along SHIM lifetime. A case study considering a system with fourteen discrete and four variable loads managed by a SHIM system during five consecutive similar weekends is presented.

SCADA House Intelligent Management for Energy Efficiency Analysis in Domestic Consumers

The implementation of smart homes allows the domestic consumer to be an active player in the context of the Smart Grid (SG). This paper presents an intelligent house management system that is being developed by the authors to manage, in real time, the power consumption, the micro generation system, the charge and discharge of the electric or plug-in hybrid vehicles, and the participation in Demand Response (DR) programs. The paper proposes a method for the energy efficiency analysis of a domestic consumer using the SCADA House Intelligent Management (SHIM) system. The main goal of the present paper is to demonstrate the economic benefits of the implemented method. The case study considers the consumption data of some real cases of Portuguese house consumption over 30 days of June of 2012, the Portuguese real energy price, the implementation of the power limits at different times of the day and the economic benefits analysis.

A Learning Algorithm and System Approach to Address Exceptional Events in Domestic Consumption Management

The integration of the Smart Grid concept into the electric grid brings to the need for an active participation of small and medium players. This active participation can be achieved using decentralized decisions, in which the end consumer can manage loads regarding the Smart Grid needs. The management of loads must handle the users’ preferences, wills and needs. However, the users’ preferences, wills and needs can suffer changes when faced with exceptional events. This paper proposes the integration of exceptional events into the SCADA House Intelligent Management (SHIM) system developed by the authors, to handle machine learning issues in the domestic consumption context. An illustrative application and learning case study is provided in this paper.

Earthwork optimization system for sustainable highway construction

In highway construction, earthworks refer to the tasks of excavation, transportation, spreading and compaction of geomaterial (e.g. soil, rockfill and soil-rockfill mixture). Whereas relying heavily on machinery and repetitive processes, these tasks are highly susceptible to optimization. In this context Artificial Intelligent techniques, such as Data Mining and modern optimization can be applied for earthworks. A survey of these applications shows that they focus on the optimization of specific objectives and/or construction phases being possible to identify the capabilities and limitations of the analyzed techniques. Thus, according to the pinpointed drawbacks of these techniques, this paper describes a novel intelligent earthwork optimization system, capable of integrating DM, modern optimization and GIS technologies in order to optimize the earthwork processes throughout all phases of design and construction work. This integration system allows significant savings in time, cost and gas emissions contributing for a more sustainable construction.

Estudi i implementació d'un sistema multiagent intel·ligent i la seva aplicació a sistemes difusos

Estudi i implementació d'un sistema multiagent intel·ligent i la seva aplicació a sistemes difusos. Utilització de les llibreries JADE i JFuzzyLogic.

High Performance Electrical Drive System for a Biomechanical Test and Rehabilitation Equipment

Suunniteltiin ja rakennettiin suoraa vääntömomenttisäätöä soveltava taajuudenmuuttajakäyttö oikosulkumoottorin ohjaukseen korvaamaan passiivinen jarrukäyttö. Laite on kuntoutuslaite, jolla tehdään lihasvoiman mittauksia ja voimaharjoituksia. Selvitettiin kaupallisten moottoreiden ja taajuudenmuuttajien suoritusominaisuuksia ja tämän perusteella valittiin käyttöön sopivat laitteet. Työssä esitetään kaksi oikosulkumoottorin ohjaustapaa: vektorisäätö ja suora vääntömomenttisäätö. Merkittävin osa tästä työstä käsittelee - tarkan turvallisuussuunnitelman lisäksi - kuntoutuslaitteen prototyypin komponentteja, kokoamista ja suoritustestien tuloksia.

Effect of trellising system on grape and wine composition of Syrah vines grown in the cerrado region of Minas Gerais

Based on the concept that the trellising system affects not only sunlight interception and carbon assimilation, but also the fruitzone microclimate, which has a great impact on fruit composition and consequently on wine quality, the effect of two trellising systems - Vertical Shoot Position (VSP) and modified Geneva Double Curtain (GDC) - on wine and berry composition of Syrah grapes grown in João Pinheiro, Northeast region of Minas Gerais State, Brazil was investigated. The parameters such as pH, berry size and weight, and seeds total phenolic contents were not affected by the training system. The GDC system produced fruits with the highest Brix and lowest titratable acidity. Berries from the VSP system presented lower anthocyanin concentration than those from the GDC system. Similar results were found for the total phenolic content of the skin of grape berries from the VSP system. GDC wines were characterized by high anthocyanin content and red color, resulting in wines with high color intensity. These data suggest that in the tropical region of Minas Gerais state, with high temperature and high sunlight intensity, the trellising system, which protects bunches against excessive radiation, should be chosen.

Development of a New Welding Product Quality Control and Management System Model for China

The Chinese welding industry is growing every year due to rapid development of the Chinese economy. Increasingly, companies around the world are looking to use Chinese enterprises as their cooperation partners. However, the Chinese welding industry also has its weaknesses, such as relatively low quality and weak management. A modern, advanced welding management system appropriate for local socio-economic conditions is required to enable Chinese enterprises to enhance further their business development. The thesis researches the design and implementation of a new welding quality management system for China. This new system is called ‗welding production quality control management model in China‘ (WQMC). Constructed on the basis of analysis of a survey and in-company interviews, the welding management system comprises the following different elements and perspectives: a ‗Localized congenital existing problem resolution strategies‘ (LCEPRS) database, a ‗human factor designed training system‘ (HFDT) training strategy, the theory of modular design, ISO 3834 requirements, total welding management (TWM), and lean manufacturing (LEAN) theory. The methods used in the research are literature review, questionnaires, interviews, and the author‘s model design experiences and observations, i.e. the approach is primarily qualitative and phenomenological. The thesis describes the design and implementation of a HFDT strategy in Chinese welding companies. Such training is an effective way to increase employees‘ awareness of quality and issues associated with quality assurance. The study identified widely existing problems in the Chinese welding industry and constructed a LCEPRS database that can be used in efforts to mitigate and avoid common problems. The work uses the theory of modular design, TWM and LEAN as tools for the implementation of the WQMC system.