Registered Data

[CT087]

  • Session Time & Room
    • CT087 (1/1) : 3E @E505 [Chair: Joaquim Ferreira]
  • Classification
    • CT087 (1/1) : Applications of statistics (62P) / Numerical problems in dynamical systems (65P)

[01068] Reverse engineering controller area network using the Pearson correlation coefficient

  • Session Time & Room : 3E (Aug.23, 17:40-19:20) @E505
  • Type : Industrial Contributed Talk
  • Abstract : Controller Area Network \(CAN\) is a communication bus widely adopted in road vehicles. However, car manufacturers adopt proprietary CAN message sets, complicating message decoding by third-party applications, e.g., for indirectly detecting adverse road-weather conditions. This talk presents an algorithm for reverse engineering CAN messages based on the Pearson correlation coefficient between CAN messages from an annotated and interpolated dataset. The proposed algorithm was experimentally validated with data collected from different vehicle brands.
  • Classification : 62P30, 68P20, 62-04
  • Format : Talk at Waseda University
  • Author(s) :
    • David Rocha (Instituto de Telecomunicacoes, Universidade de Aveiro)
    • João Almeida (Instituto de Telecomunicações, Universidade de Aveiro)
    • José Fonseca (Instituto de Telecomunicações, Universidade de Aveiro)
    • Joaquim Ferreira (Instituto de Telecomunicações, Universidade de Aveiro)

[02487] Asset Forecasting Using Geometric Brownian Motion and Variance Gamma Models

  • Session Time & Room : 3E (Aug.23, 17:40-19:20) @E505
  • Type : Contributed Talk
  • Abstract : The basic assumption in the Black-Scholes-Merton model is log returns assets normally distributed. In reality, asset price movements are so fluctuating that the data is not normally distributed. This paper proposes a way to forecast using the variance gamma (VG) model. The VG model has three parameters to control volatility, skewness, and kurtosis. We compare results with the geometric Brownian motion (GBM) model. The accuracy of the model used the mean absolute percentage error (MAPE).
  • Classification : 62P20
  • Format : Online Talk on Zoom
  • Author(s) :
    • Abdul Hoyyi (Gadjah Mada University)
    • Abdurakhman Abdurakhman (Gadjah Mada University)
    • Dedi Rosadi (Gadjah Mada University)

[02572] LDA Hyper-parameters Regulation for Qualitative Studies in Management

  • Session Time & Room : 3E (Aug.23, 17:40-19:20) @E505
  • Type : Contributed Talk
  • Abstract : The suitability of the number of topics in management qualitative research is a complex problem. Topic models on textual data often require judgment expertise in determining suitability for management problems. One of the things to note is the determination of hyperparameter values. We have designed various hyper-parameter value conditions as an experiment and calculated the document match probability based on the topic grouping results. Different hyperparameter values indicate different levels of probability.
  • Classification : 62P25, 68W99, 91C20
  • Format : Online Talk on Zoom
  • Author(s) :
    • Evita Purnaningrum (Mathematics Department, Gadjah Mada University)
    • Abdurakhman Abdurakhman (Mathematics Department, Gadjah Mada University)
    • Nanang Susyanto (Mathematics Department, Gadjah Mada University)

[00129] Anomalous diffusion in standard maps with extensive chaotic phase spaces

  • Session Time & Room : 3E (Aug.23, 17:40-19:20) @E505
  • Type : Contributed Talk
  • Abstract : In this work, we investigate the long-term diffusion transport and chaos properties of single and coupled standard maps (SMs). We analyze parameters that are known to produce anomalous diffusion in the phase spaces of maps, with the presence of so-called accelerator modes. We study how different ensembles affect the behavior, asymptotic diffusion rates, and time scales required for these maps. We also explore the global diffusion properties and chaotic dynamics of various coupled SM configurations.
  • Classification : 65Pxx
  • Format : Talk at Waseda University
  • Author(s) :
    • Henok Tenaw Moges (University of Cape Town)
    • Henok Tenaw Moges (University of Cape Town)
    • Charalampos Skokos (University of Cape Town)

[02022] Use of jet transport for high order methods

  • Session Time & Room : 3E (Aug.23, 17:40-19:20) @E505
  • Type : Contributed Talk
  • Abstract : The use of multivariate polynomial, called jet, in conjunction with numerical solvers, called transport, has recently become a new baseline to address computations based on high order methods. Jet transport provides more accurate, efficient, and reliable results through automatizing several crucial parts. In this talk, I will explain these most recent results and supported by examples in areas in dynamical systems.
  • Classification : 65Pxx, 37Mxx, 37M21, Numerical integrators for dynamical systems
  • Format : Online Talk on Zoom
  • Author(s) :
    • Joan Gimeno (University of Barcelona)
    • Angel Jorba (University of Barcelona)
    • Marc Jorba (Centre de Recerca Matemàtica)
    • Narcís Miguel (PAL Robotics S.L.)
    • Maorong Zou (University of Texas at Austin)