Papers by Jun Okamoto Jr.
Zenodo (CERN European Organization for Nuclear Research), Oct 15, 2016
teve como foco o crescente uso de dispositivos móveis pelos usuários das bibliotecas que tem gera... more teve como foco o crescente uso de dispositivos móveis pelos usuários das bibliotecas que tem gerado um profundo efeito sobre a forma como se busca, acessa e processa as informações. Através de uma análise de logs de uso durante o ano de 2015 foi possível obter como resultados parciais dados quantitativos relativos aos usos anual, mensal, por dia da semana e por horários, além dos termos mais buscados no aplicativo. Por fim, considera-se que as bibliotecas precisam se apropriar dos recursos tecnológicos existentes, aproximando-se efetivamente das necessidades de acesso e uso da informação da sua comunidade de usuários.
Design and Application
From the academia viewpoint, the process of qualifying engineering students demands they acquire ... more From the academia viewpoint, the process of qualifying engineering students demands they acquire a deep understanding of basic sciences and technological aspects. On the other hand, it is quite a challenge to keep them motivated throughout their graduation period. Taking into account these issues, an integrated approach for teaching can provide good results. Basically, the way that such integration might be accomplished requires a single project per period. In addition, the disciplines taken by the students in a specific period should provide them the necessary background to conclude that project. Focusing on teaching robotics, this chapter describes the authors’ experience with mechatronics engineering students in the 7th-period of their graduation.
2018 International Conference on Information and Computer Technologies (ICICT), 2018
There is a necessity to anticipate and identify changes in events points to a new direction in th... more There is a necessity to anticipate and identify changes in events points to a new direction in the stock exchange markets in line with the analysis of the oscillations of prices of financial assets. This need leads to argue about new alternatives in the prediction of financial time series using machine learning methods. This paper aims to describe the development of the SVR-wavelet model, an adaptive and hybrid prediction model, which integrates wavelet models and Support Vector Regression (SVR), for prediction of financial time series, particularly applied to Foreign Exchange Market (FOREX), obtained from a public knowledge base. The method consists of using the Discrete Wavelets Transform (DWT) to decompose data from FOREX time series, that are used as SVR input variables to predict new data. The adjusted series are compared with traditional models such as ARIMA and ARFIMA Model. In Addition, statistical tests like normality and unit root are performed to prove that the series in question have non-linear distribution and also to verify the level of correlation between the periods of the series.
Rio Oil and Gas Expo and Conference, 2020
2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), 2017
The University of São Paulo has faced public safety issues a long the years. Due to its size prev... more The University of São Paulo has faced public safety issues a long the years. Due to its size preventive surveillance by the campus security guard cannot be effective all the times. In order to bring a safer environment to its public of more than 60,000 daily users, a smart public safety system is being developed. This is a complex system, spread throughout all the University's campuses. It is composed of a smart surveillance cameras system, a back office system with a workflow engine and a mobile application within a collaborative concept. The smart cameras system is being deployed and the mobile application together with the back office system is being used this past year with satisfactory results. The mobile application is the user entry point to report several security and campus maintenance related issues that are automatically directed to the responder team for immediate action in the case of security or enters an automated workflow engine in the case of campus maintenance. This paper presents the structure created towards achieving a smarter public safety environment, details of the implementation, presents statistical data collected by the system showing its effectiveness and concludes showing the improvements introduced in the university community safety and welfare.
IFAC-PapersOnLine, 2015
The combination of multi-functional machines and mobile robots supports the emergence of highly f... more The combination of multi-functional machines and mobile robots supports the emergence of highly flexible intelligent manufacturing systems (IMS). In this kind of manufacturing system, some machines must stay fixed at previously established positions (heavy equipment) but some types of multi-functional machines (small flexible equipment and mobile robots) can stay in one position for one or several periods and change their position for others periods, or change permanently their position in the shop floor. Moreover, using mobile robots allows performing transportation and operation simultaneously. This possibility may change the decision processes and manufacturing system configuration, calling into question the existing decision methods in strategic, tactical and operational levels. This paper concerns the specific production systems in which mobile robots operate in the same shop floor and at the same time with conventional and multi-functional machines and humans. This kind of production system is more sophisticated than conventional manufacturing chain (as cellular manufacturing system) and can decrease the reactivity time and new products can be quickly introduced (as for dynamic cellular manufacturing system). However, the configuration and optimization of this kind of system is very different from conventional production systems. In this paper, in one hand, the advantages of this kind of system and then several difficulties and challenges from operation management and industrial engineering point of view in configuration, organization, planning and optimization of IMS is discussed and developed. As a first step it is considered that localization is a key issue in the highly flexible intelligent manufacturing. Several approaches exist for outdoor localization, but indoor localization is an open problem. In this work, it is presented and discussed the highly flexible intelligent manufacturing system and the indoor localization.
IFAC Proceedings Volumes, 2006
In these networked days cooperative perception means that multiple robots with multiple sensors c... more In these networked days cooperative perception means that multiple robots with multiple sensors can share their data creating a common knowledge base so that they can plan and interact with the environment in a more appropriate and efficient way. We propose in this work an architecture for cooperative perception for mobile robots based on distributed objects in a network. The implementation follow the CORBA specification, created to facilitate development of distributed applications in heterogeneous network. Objects could be the sensors and actuators of a robot or processes that treat common sensor data. An implementation of an image acquisition and distribution service is presented and others are proposed to compose the architecture.
International Journal of Modeling and Optimization, 2018
This paper presents the relationship between the Hurst Exponent (H) and the Rescaled Range Analys... more This paper presents the relationship between the Hurst Exponent (H) and the Rescaled Range Analysis (R/S) in the classification of Foreign Exchange Market (FOREX) time series by the supposition of the existence of a Fractal Market in an alternative to the traditional theory of Capital Markets. In such a way, the Hurst Exponent is a metric capable of providing information on correlation and persistence in a time series. Many systems can be described by self-similar fractals as Fractional Brownian Motion, which are well characterized by this statistic.
To achieve a fully autonomous robot several individual sensory based tasks can be composed to acc... more To achieve a fully autonomous robot several individual sensory based tasks can be composed to accomplish a complete autonomous mission. These sensory based tasks can be distance detection with ultrasonic sensors to avoiding collision or stereo vision acquisition and processing for environment mapping. In this context, the sensory based task that is subject of this paper is a moving target following in real time based with an omnidirectional vision system supplying data for a visual servo controlled mobile robot. This paper shows some background information on omnidirectional vision system, object tracking and visual servo control. Then the implemented solution for performing this specific task is presented and the experimental results are shown and discussed.
The problem of SLAM (simultaneous localization and mapping), is a fundamental problem in autonomo... more The problem of SLAM (simultaneous localization and mapping), is a fundamental problem in autonomous robotics. It arises when a robot must create a map of the regions it has navigated while localizing itself on it, using results from one step to increase precision in the other by eliminating errors inherent to the sensors. One common solution consists of establishing landmarks in the environment that are used as reference points for absolute localization estimates and form a sparse map that is iteratively refined as more information is obtained. This paper introduces a method of landmark selection in omnidirectional images for online SLAM, using the SIFT algorithm for initial feature extraction and assuming no prior knowledge of the environment. Visual sensors are an attractive way of collecting information from the environment, but tend to create an excessive amount of landmarks that are individually propense to false matches due to image noise and object similarities. By clustering...
Autonomously guided mobile robots are dependent on sensor information for internal decision makin... more Autonomously guided mobile robots are dependent on sensor information for internal decision making processes. Important information for the robot is the distances between its sensors and the objects in its working environment. One way of obtaining this information is through the use of stereo vision which allows the determination of depth (range) information from two or more images. Stereo can be achieved with omnidirectional vision systems that produce panoramic images with a field of view of 360 o around the camera. Basically three steps compose the process of obtaining depth information through a pair of images: features extraction, matching and triangulation. This paper presents the method of obtaining range information from a pair of omnidirectional images. It uses a CCD camera and a hyperbolic mirror mounted on a mobile robot. The environment is considered static and the robot with the camera moves to acquire the stereo pair. In this work the processing is done directly on the...
Proceedings of the 25th International Congress of Mechanical Engineering
Anais do Encontro Nacional de Inteligência Artificial e Computacional (ENIAC)
A classificação estética de fotografias é um problema a respeito da separação de imagens entre as... more A classificação estética de fotografias é um problema a respeito da separação de imagens entre as esteticamente atraentes das não atraentes através de algoritmos que descrevem e avaliam os fatores emocionais e técnicos. Desde a adoção em massa de modelos de redes convolucionais profundas (DCNN) para problemas de classificação de imagens, diferentes arquiteturas foram desenvolvidas, fazendo com que o estado da arte de performance de classificação tivesse suas fronteiras ampliadas. Este artigo avalia como as arquiteturas e atributos que foram inicialmente desenvolvidos para a ImageNet Object Classification Challenge performam quando analisados sob o ponto de vista de estética. Uma arquitetura de alto nível de transferência de conhecimento composta por uma camada de DCNN e uma camada final que se comporta como uma SVM linear é proposta e sete diferentes arquiteturas de DCNN são treinadas usando-a. Cenários com apenas transferência de conhecimento e com fine tuning são avaliados e um mo...
... An architecture describes what components or building blocks the system should have, how thes... more ... An architecture describes what components or building blocks the system should have, how these ... this reason only an obstacle avoidance reactive behavior was tested in the implementation. ... Design and Testing of a low-cost robotic wheelchair prototype", Autonomous Robots ...
In the first part of this paper, we present a brief review on catadioptric omnidirectional system... more In the first part of this paper, we present a brief review on catadioptric omnidirectional systems. The special case of the hyperbolic omnidirectional system is analysed in depth. The literature shows that a hyperboloidal mirror has two clear advantages over alternative geometries. Firstly, a hyperboloidal mirror has a single projection centre [1]. Secondly, the image resolution is uniformly distributed along the mirror's radius [2]. In the second part of this paper we show empirical results for the detection and tracking of faces from the omnidirectional images using Viola-Jones method. Both panoramic and perspective projections, extracted from the omnidirectional image, were used for that purpose. The omnidirectional image size was 480x480 pixels, in greyscale. The tracking method used regions of interest (ROIs) set as the result of the detections of faces from a panoramic projection of the image. In order to avoid losing or duplicating detections, the panoramic projection was extended horizontally. Duplications were eliminated based on the ROIs established by previous detections. After a confirmed detection, faces were tracked from perspective projections (which are called virtual cameras), each one associated with a particular face. The zoom, pan and tilt of each virtual camera was determined by the ROIs previously computed on the panoramic image. The results show that, when using a careful combination of the two projections, good frame rates can be achieved in the task of tracking faces reliably.
Anais Do Computer on the Beach, 2012
Virtual presence is more and more important in communications and entertainment. Videocalls are p... more Virtual presence is more and more important in communications and entertainment. Videocalls are possible nowadays; avatars are commonplace in computer games. This paper try to contribute to demonstrate the use the Active Appearance Model (AAM) technique to synthetize faces poses of persons. Results allow to foresee the use of AAM to add someone's face to a computer game, making interactivity even greater. Resumo. A virtualização da presença é cada vez mais importante na comunicação entre pessoas e na indústria de entretenimento. As videochamadas já são uma realidade, bem como se encontram avatares em jogos de computador. Neste artigo, busca-se demonstrar o uso da técnica Active Appearance Model (AAM) para gerar poses de faces de pessoas. Os resultados permitem antever a aplicação da técnica em situações como a utilização da face de uma pessoa em jogos de computador, tornando a interatividade ainda maior.
Trabalho de Formatura do curso de graduação do Departamento de Engenharia Mecânica da Escola Poli... more Trabalho de Formatura do curso de graduação do Departamento de Engenharia Mecânica da Escola Politécnica da Universidade de São Paulo.
Mobile robots have attracted researcher's interest as an important mean for obtaining informa... more Mobile robots have attracted researcher's interest as an important mean for obtaining information about hostile environments to man, such as radioactive plants, planets with inappropriate atmosphere for humans and deep mines. The precise control of the robot's movement is essential for the success of such missions. In this area, the Laboratory of Automation and Systems (Mechatronics) of the Department of Mechanical Engineering of the Escola Politécnica of the University of São Paulo is carrying on activities related to the development of mobile robots and their position control. This paper presents a work of modeling of the robot control system and implementation of a real time control software for a mobile base for transporting sensors inside the laboratory. The developed software interacts with the user through a programming language for the robot and controls the positioning of a DC motor in a digital control loop. The results are presented for the simulation of the contr...
Uploads
Papers by Jun Okamoto Jr.