KUGLER Mauricio

写真a

Affiliation Department etc.

Department of Computer Science
Department of Computer Science

Title

Assistant Professor

Graduating School

  •  
    -
    2001.02

    Federal Technological University of Parana   Faculty of Engineering   Department of Electronics   Graduated

Graduate School

  •  
    -
    2007.03

    Nagoya Institute of Technology  Graduate School, Division of Information Engineering  Doctor's Course  Completed

  •  
    -
    2003.02

    Federal Technological University of Paraná  Graduate School, Division of Engineering  Master's Course  Completed

Degree

  • Nagoya Institute of Technology -  Doctor of Philosophy

External Career

  • 2014.03
    -
    2014.04

    ESIGELEC   Graduate School of Engineering   Lecturer  

  • 2013.11
     
     

    ESIGELEC   Graduate School of Engineering   Lecturer  

  • 2013.05
     
     

    ESIGELEC   Graduate School of Engineering   Lecturer  

  • 2012.11
    -
    2012.12

    ESIGELEC   Graduate School of Engineering   Lecturer  

  • 2012.05
     
     

    ESIGELEC   Gradiate School of Engineering   Lecturer  

Academic Society Affiliations

  • 2005.01
    -
    2014.04

    Institute of Electrical and Electronics Engineers (IEEE)

 

Papers

  • Design of a compact sound localization device on a stand-alone FPGA-based platform

    Mauricio Kugler, Teemu Tossavainen, Susumu Kuroyanagi, Akira Iwata

    電子情報通信学会論文誌 ( 電子情報通信学会 )  E99-D ( 11 ) 2682 - 2693   2016.11  [Refereed]

    Research paper (scientific journal)   Multiple Authorship

    Sound localization systems are widely studied and have several potential applications, including hearing aid devices, surveillance and robotics. However, few proposed solutions target portable systems, such as wearable devices, which require a small unnoticeable platform, or unmanned aerial vehicles, in which weight and low power consumption are critical aspects. The main objective of this research is to achieve real-time sound localization capability in a small, self-contained device, without having to rely on large shaped platforms or complex microphone arrays. The proposed device has two surface-mount microphones spaced only 20 mm apart. Such reduced dimensions present challenges for the implementation, as differences in level and spectra become negligible, and only time-difference of arrival (TDoA) can be used as a localization cue. Three main issues have to be addressed in order to accomplish these objectives. To achieve real-time processing, the TDoA is calculated using zero-crossing spikes applied to the hardware-friendly Jeffers model. In order to make up for the reduction in resolution due to the small dimensions, the signal is upsampled several-fold within the system. Finally, a coherence-based spectral masking is used to select only frequency components with relevant TDoA information. The proposed system was implemented on a field-programmable gate array (FPGA) based platform, due to the large amount of concurrent and independent tasks, which can be efficiently parallelized in reconfigurable hardware devices. Experimental results with white-noise and environmental sounds show high accuracies for both anechoic and reverberant conditions.

  • Real-time hardware implementation of a sound recognition system with in-field learning

    Mauricio Kugler, Teemu Tossavainen, Miku Nakatsu, Susumu Kuroyanagi, Akira Iwata

    電子情報通信学会論文誌 ( 電子情報通信学会 )  E99-D ( 7 ) 1885 - 1894   2016.07  [Refereed]

    Research paper (scientific journal)   Multiple Authorship

    The development of assistive devices for automated sound recognition is an important field of research and has been receiving increased attention. However, there are still very few methods specifically developed for identifying environmental sounds. The majority of the existing approaches try to adapt speech recognition techniques for the task, usually incurring high computational complexity. This paper proposes a sound recognition method dedicated to environmental sounds, designed with its main focus on embedded applications. The pre-processing stage is loosely based on the human hearing system, while a robust set of binary features permits a simple k-NN classifier to be used. This gives the system the capability of in-field learning, by which new sounds can be simply added to the reference set in real-time, greatly improving its usability. The system was implemented in an FPGA based platform, developed in-house specifically for this application. The design of the proposed method took into consideration several restrictions imposed by the hardware, such as limited computing power and memory, and supports up to 12 reference sounds of around 5.3 s each. Experimental results were performed in a database of 29 sounds. Sensitivity and specificity were evaluated over several random subsets of these signals. The obtained values for sensitivity and specificity, without additional noise, were, respectively, 0.957 and 0.918. With the addition of +6 dB of pink noise, sensitivity and specificity were 0.822 and 0.942, respectively. The in-field learning strategy presented no significant change in sensitivity and a total decrease of 5.4% in specificity when progressively increasing the number of reference sounds from 1 to 9 under noisy conditions. The minimal signal-to-noise ration required by the prototype to correctly recognize sounds was between -8 dB and 3 dB. These results show that the proposed method and implementation have great potential for several real life applications.

  • Construction of multi-scale spatiotemporal model of pancreas tumor from pathology images and time series MR images

    TRIQUET, V., KUGLER, M., KOBAYASHI, H., YOKOTA, T., IWAMOTO, C., OUCHIDA, K., HASHIZUME, M., HONTANI, H.

    Proceedings of the 31st International Congress on Computer Assisted Radiology and Surgery ( Springer International Publishing )  12   S58 - S59   2017.06  [Refereed]

    Research paper (research society, symposium materials, etc.)   Multiple Authorship

  • The Impact of Memory Dependency on Precision Forecast - An Analysis on Different Types of Time Series Databases

    Ricardo Moraes Muniz da Silva, Mauricio Kugler, Taizo Umezaki

    Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods     575 - 582   2017.02  [Refereed]

    Research paper (research society, symposium materials, etc.)   Multiple Authorship

    Time series forecasting is an important type of quantitative method in which past observations of a set of variables are used to develop a model describing their relationship. The Autoregressive Integrated Moving Average (ARIMA) model is a commonly used method for modelling time series. It is applied when the data show evidence of nonstationarity, which is removed by applying an initial differencing step. Alternatively, for time series in which the long-run average decays more slowly than an exponential decay, the Autoregressive Fractionally Integrated Moving Average (ARFIMA) model is used. One important issue on time series forecasting is known as the short and long memory dependency, which corresponds to how much past history is necessary in order to make a better prediction. It is not always clear if a process is stationary or what is the influence of the past samples on the future value, and thus, which of the two models, is the best choice for a given time series. The objective o f this research is to have a better understanding this dependency for an accurate prediction. Several datasets of different contexts were processed using both models, and the prediction accuracy and memory dependency were compared.

  • Wearable sound localization assistive device for the hearing impaired

    Mauricio Kugler, Hiroyuki Sakamoto, Masatoki Suto

    Proceedings of the 25th Brazilian Congress on Biomedical Engineering ( Brazilian Society of Biomedical Engineering )    1374 - 1377   2016.10  [Refereed]

    Research paper (research society, symposium materials, etc.)   Multiple Authorship

    The sense of hearing can provide immediate information about remote events, even when outside of the field of vision and beyond obstacles, facilitating functioning in uncontrolled environments. Hearing impairment can thus have a huge disabling effect on an individual. This paper proposes a wearable selfcontained dedicated device capable of full-plane sound localization. The system, shaped as a glass frame, uses only four microphones spaced by 10 mm, and is initially targeted at a resolution of 45°. The individual binaural angles are calculated by a process loosely based on the human hearing system. These angles are then combined in order to determine the final direction. A prototype of the proposed system was implemented using 3D printing and MEMS microphones. Experiments with the prototype in a reverberant environment show an error of 6.73° when it is tested standalone and 21.16° when tested in a dummy head.

  • Sound-based Evaluation Index for Early Warning Systems

    Ryunosuke Koike, Mauricio Kugler, Susumu Kuroyanagi

    IEICE Technical Report NC2013-120   113 ( 500 ) 183 - 188   2014.03

    Research paper (international conference proceedings)   Multiple Authorship

  • Lung Auscultation Signal Analysis Using the "Sound Watcher" Method

    Tetsuya Aoyama, Mauricio Kugler, Susumu Kuroyanagi

    IEICE Technical Report NC2013-118   113 ( 500 ) 171 - 176   2014.03

    Research paper (international conference proceedings)   Multiple Authorship

  • Musical-Instruments and Notes Recognition on Polyphonic Music Transcription System using an Equal Temperament Scale Filter

    Shota Nakagawa, Mauricio Kugler, Susumu Kuroyanagi

    IEICE Technical Report NC2013-119   113 ( 500 ) 177 - 182   2014.03

    Research paper (international conference proceedings)   Multiple Authorship

  • An Approach for Sound Source Localization by Complex-Valued Neural Network

    Hirofumi Tsuzuki, Mauricio Kugler, Susumu Kuroyanagi, Akira Iwata

    IEICE Transactions on Information & Systems   E96-D ( 10 ) 2257 - 2265   2013.10  [Refereed]

    Research paper (scientific journal)   Single Author

  • A study for applying sound localization system to multiple sounds classification using pulsed neural network

    HAMADA, Y., KUGLER, M., KUROYANAGI, S., IWATA, A.

    IEICE Technical Report NC2011-182     359 - 364   2012.03

    Research paper (international conference proceedings)   Multiple Authorship

display all >>

Presentations

  • Construction of multi-scale spatiotemporal model of pancreas tumor from pathology images and time series MR images

    TRIQUET, V., KUGLER, M., KOBAYASHI, H., YOKOTA, T., IWAMOTO, C., OUCHIDA, K., HASHIZUME, M., HONTANI, H.

    31st International Congress on Computer Assisted Radiology and Surgery  (Barcelona, Spain)  2017.06  -  2017.06 

  • The Impact of Memory Dependency on Precision Forecast - An Analysis on Different Types of Time Series Databases

    Ricardo Moraes Muniz da Silva

    6th International Conference on Pattern Recognition Application and Methods  (Porto, Portugal)  2017.02  -  2017.02 

  • Wearable sound localization assistive device for the hearing impaired

    Mauricio Kugler

    25th Brazilian Congress on Biomedical Engineering  (Foz do Iguaçu, Brazil)  2016.10  -  2016.10  Brazilian Society of Biomedical Engineering

  • Lung Auscultation Signal Analysis Using the "Sound Watcher" Method

    Tetsuya Aoyama, Mauricio Kugler, Susumu Kuroyanagi

    2014.03  -  2014.03 

  • Sound-based Evaluation Index for Early Warning Systems

    Ryunosuke Koike, Mauricio Kugler, Susumu Kuroyanagi

    2014.03  -  2014.03 

  • Musical-Instruments and Notes Recognition on Polyphonic Music Transcription System using an Equal Temperament Scale Filter

    Shota Nakagawa, Mauricio Kugler, Susumu Kuroyanagi

    2014.03  -  2014.03 

  • Sound Watcher: A Sound Recognition Support System For The Hearing Impaired

    Mauricio Kugler, Yazan Badran, Jana Makovnikova, Susumu kuroyanagi, Akira Iwata

    第22回神経回路学会全国大会  (名古屋工業大学)  2012.09  -  2012.09 

  • Multiple sounds classification system for hearing impaired people support

    Yosuke KAGAy, Mauricio KUGLERy, Susumu KUROYANAGIy, and Akira IWATA

    2011.03  -  2011.03 

  • 品詞情報を用いたCombNET-III の手書き文章認識への適用

    比嘉優一, マウリシオクグレ, 黒柳奨, 岩田彰

    ニューロコンピューティング研究会  (玉川大学)  2011.03  -  2011.03  電子情報通信学会

  • Sound localization embedded system based on neural networks for hearing impaired people support

    Takanobu HISHIDAy, Mauricio KUGLERy, Susumu KUROYANAGI and Akira IWATA

    2011.03  -  2011.03 

display all >>

Industrial Property

Other research activities

  • Development of a Wearable Brain Stimulation Device for Gait Rehabilitation

    2013.04  -  2015.03

  • Sound recognition & visualization using a head mount display

    2013.04  -  2014.03

  • Sound Watcher: hardware and software development for a consumer product.

    2011.01  -  Now

Grant-in-Aid for Scientific Research

  • Wearable Brain Stimulation Device for Gait Rehabilitation

    Grant-in-Aid for challenging Exploratory Research

    Project Year: 2013.04  -  2015.03  Investigator(s): Satoshi Tanaka

    This project's main objective is to develop a wearable device that generates the necessary electrical stimulation during such sessions, being wirelessly controlled by the operator by the means of a smartphone or a tablet computer. The hardware device has to generate a constant DC current through the scalp of the subject, independently of its resistance. It has to be light and small, able to be fixed on the back of the head of the subject.

  • Visualization of sound using head-mounted display

    Grant-in-Aid for Scientific Research(C)

    Project Year: 2011.04  -  2014.03  Investigator(s): Masatoki Suto