scholarly journals METODE STATE SPACE DALAM MERAMALKAN JUMLAH PENUMPANG KERETA API DI PULAU JAWA

2020 ◽  
Vol 9 (1) ◽  
pp. 8
Author(s):  
FITRI ANANDA DITA SARASWITA ◽  
I WAYAN SUMARJAYA ◽  
LUH PUTU IDA HARINI
Keyword(s):  
State Space ◽  
Time Series Data ◽  
Local Level ◽  
State Space Model ◽  
The State ◽  
Series Data ◽  
State Space Method ◽  
Dynamic Interactions ◽  
Level Model ◽  
Space Method

State space is an approach to model and predict together several time series data that are interconnected, and these variables have dynamic interactions. The purpose of this research is to model the number of train passengers in Java and find out the forecasting results using the state space method. The algorithm used to solve the state space model is the Kalman filter. In this research, a suitable final model is local level model with seasonal and produces MAPE value of 2%, this shows that the state space method is very accurately.

scholarly journals Estimating Distributions of Parameters in Nonlinear State Space Models with Replica Exchange Particle Marginal Metropolis–Hastings Method

Entropy ◽  
2022 ◽  
Vol 24 (1) ◽  
pp. 115
Author(s):  
Hiroaki Inoue ◽  
Koji Hukushima ◽  
Toshiaki Omori
Keyword(s):  
State Space ◽  
Latent Variables ◽  
Time Series Data ◽  
State Space Model ◽  
The State ◽  
Series Data ◽  
Replica Exchange ◽  
Space Model ◽  
Marginal Posterior Distribution ◽  
Exchange Particle

Extracting latent nonlinear dynamics from observed time-series data is important for understanding a dynamic system against the background of the observed data. A state space model is a probabilistic graphical model for time-series data, which describes the probabilistic dependence between latent variables at subsequent times and between latent variables and observations. Since, in many situations, the values of the parameters in the state space model are unknown, estimating the parameters from observations is an important task. The particle marginal Metropolis–Hastings (PMMH) method is a method for estimating the marginal posterior distribution of parameters obtained by marginalization over the distribution of latent variables in the state space model. Although, in principle, we can estimate the marginal posterior distribution of parameters by iterating this method infinitely, the estimated result depends on the initial values for a finite number of times in practice. In this paper, we propose a replica exchange particle marginal Metropolis–Hastings (REPMMH) method as a method to improve this problem by combining the PMMH method with the replica exchange method. By using the proposed method, we simultaneously realize a global search at a high temperature and a local fine search at a low temperature. We evaluate the proposed method using simulated data obtained from the Izhikevich neuron model and Lévy-driven stochastic volatility model, and we show that the proposed REPMMH method improves the problem of the initial value dependence in the PMMH method, and realizes efficient sampling of parameters in the state space models compared with existing methods.

scholarly journals LSTM-Guided Coaching Assistant for Table Tennis Practice

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4112 ◽  
Author(s):  
Se-Min Lim ◽  
Hyeong-Cheol Oh ◽  
Jaein Kim ◽  
Juwon Lee ◽  
Jooyoung Park
Keyword(s):  
Time Series ◽  
State Space ◽  
Time Series Data ◽  
State Space Model ◽  
Skill Assessment ◽  
Series Data ◽  
High Dimensional ◽  
Table Tennis ◽  
Space Model ◽  
Low Dimensional

Recently, wearable devices have become a prominent health care application domain by incorporating a growing number of sensors and adopting smart machine learning technologies. One closely related topic is the strategy of combining the wearable device technology with skill assessment, which can be used in wearable device apps for coaching and/or personal training. Particularly pertinent to skill assessment based on high-dimensional time series data from wearable sensors is classifying whether a player is an expert or a beginner, which skills the player is exercising, and extracting some low-dimensional representations useful for coaching. In this paper, we present a deep learning-based coaching assistant method, which can provide useful information in supporting table tennis practice. Our method uses a combination of LSTM (Long short-term memory) with a deep state space model and probabilistic inference. More precisely, we use the expressive power of LSTM when handling high-dimensional time series data, and state space model and probabilistic inference to extract low-dimensional latent representations useful for coaching. Experimental results show that our method can yield promising results for characterizing high-dimensional time series patterns and for providing useful information when working with wearable IMU (Inertial measurement unit) sensors for table tennis coaching.

A State Space Method for Optimal Design of Vibration Isolators

1979 ◽  
Vol 101 (2) ◽  
pp. 309-314 ◽  
Author(s):  
M. H. Hsiao ◽  
E. J. Haug ◽  
J. S. Arora
Keyword(s):  
Nonlinear Programming ◽  
Optimal Design ◽  
State Space ◽  
The State ◽  
Programming Approach ◽  
Time Interval ◽  
Numerical Comparison ◽  
State Space Method ◽  
Continuous State ◽  
Space Method

A state space method of optimal design of dynamic systems subjected to transient loads is developed and applied. In contrast to the conventional nonlinear programming approach of discretizing the time interval and constructing a high dimension nonlinear programming problem, a state space approach is employed which develops the sensitivity analysis and optimization algorithm in continuous state space, resorting to discretization only for efficient numerical integration of differential equations. A numerical comparison of the state space and conventional nonlinear programming methods is carried out for two test problems, in which the state space method requires only one-tenth the computing time reported for the nonlinear programming approach.

Structural condition assessment using entropy-based time series analysis

2017 ◽  
Vol 28 (14) ◽  
pp. 1941-1956 ◽  
Author(s):  
Mehrisadat Makki Alamdari ◽  
Bijan Samali ◽  
Jianchun Li ◽  
Ye Lu ◽  
Samir Mustapha
Keyword(s):  
Time Series ◽  
State Space ◽  
Structural Damage ◽  
Time Series Data ◽  
National Laboratory ◽  
The State ◽  
Frame Structure ◽  
Series Data ◽  
Symbol Space ◽  
Symbol Sequences

We present a time-series-based algorithm to identify structural damage in the structure. The method is in the context of non-model-based approaches; hence, it eliminates the need of any representative numerical model of the structure to be built. The method starts by partitioning the state space into a finite number of subsets which are mutually exclusive and exhaustive and each subset is identified by a distinct symbol. Partitioning is performed based on a maximum entropy approach which takes into account the sparsity and distribution of information in the time series. After constructing the symbol space, the time series data are uniquely transformed from the state space into the constructed symbol space to create the symbol sequences. Symbol sequences are the simplified abstractions of the complex system and describe the evolution of the system. Each symbol sequence is statistically characterized by its entropy which is obtained based on the probability of occurrence of the symbols in the sequence. As a consequence of damage occurrence, the entropy of the symbol sequences changes; this change is implemented to define a damage indicative feature. The method shows promising results using data from two experimental case studies subject to varying excitation. The first specimen is a reinforced concrete jack arch which replicates one of the major structural components of the Sydney Harbor Bridge and the second specimen is a three-story frame structure model which has been tested at Los Alamos National Laboratory. The method not only could successfully identify the presence of damage but also has potential to localize it.

Mathematical Modeling of the Membrane Concentration of Whey by the State Space Method

2020 ◽  
Vol 13 (4) ◽  
pp. 275
Author(s):  
Boris Lobasenko ◽  
Dmitry Borodulin ◽  
Roman Kotlyarov ◽  
Yana Golovacheva ◽  
Igor Bakin
Keyword(s):  
Mathematical Modeling ◽  
State Space ◽  
The State ◽  
State Space Method ◽  
Space Method ◽  
Membrane Concentration
Sign in / Sign up

Export Citation Format

Share Document