arXiv subjects

Kengo Nakai

Publications and source records attributed to Kengo Nakai.

12 recordsLinked to original sources

arXiv2026

Geometric structure of ideal data-driven dynamical model using RfR method

The Gaussian radial function-based Regression (RfR) method is a data-driven modeling approach that utilizes physically understandable variables from scalar time series, constructed using delay coordinates and Gaussian radial basis functions. Even when a model successfully describes an approximate trajectory of the original system, data-driven models rarely reconstruct negative Lyapunov exponents of chaotic dynamics. An ''ideal model'' should reconstruct the dynamical structure, including the negative (physically dominant) Lyapunov exponents. Comparing the ideal model and the non-ideal model, we investigate the geometric structure of the attractor of such models using the Lyapunov exponents and the corresponding Lyapunov vectors. Our investigation suggests that the ideal model reconstructs the original system's attractor as a time-delay embedding. By applying the results, we search for a method to construct an ideal model, which persists against the change in hyperparameters.

nlin.CD↗

arXiv2026

On the attractor in a high-dimensional neural network dynamics of reservoir computing: Lyapunov analysis viewpoint

Recent theoretical developments of reservoir computing have clarified a sufficient condition about which reservoir computing can capture the dynamics of a target system, enabling the reconstruction of dynamical invariants. Even when the condition is relaxed, the reservoir computing is found to succeed in reconstructing time series. In this study, we investigate numerically the dynamical structures underlying the embedding structure by comparing the Lyapunov spectrum of a high-dimensional neural network in a reservoir computing model with that of the actual system. We also compute Lyapunov exponents restricted to the tangent space of the inertial manifold in a high-dimensional neural network. Our results provide numerical evidence that reservoir computing can accurately identify the Lyapunov spectrum of the target system, including all negative exponents.

nlin.CD↗

arXiv2025

ManzaiSet: A Multimodal Dataset of Viewer Responses to Japanese Manzai Comedy

We present ManzaiSet, the first large scale multimodal dataset of viewer responses to Japanese manzai comedy, capturing facial videos and audio from 241 participants watching up to 10 professional performances in randomized order (94.6 percent watched >= 8; analyses focus on n=228). This addresses the Western centric bias in affective computing. Three key findings emerge: (1) k means clustering identified three distinct viewer types: High and Stable Appreciators (72.8 percent, n=166), Low and Variable Decliners (13.2 percent, n=30), and Variable Improvers (14.0 percent, n=32), with heterogeneity of variance (Brown Forsythe p < 0.001); (2) individual level analysis revealed a positive viewing order effect (mean slope = 0.488, t(227) = 5.42, p < 0.001, permutation p < 0.001), contradicting fatigue hypotheses; (3) automated humor classification (77 instances, 131 labels) plus viewer level response modeling found no type wise differences after FDR correction. The dataset enables culturally aware emotion AI development and personalized entertainment systems tailored to non Western contexts.

cs.CV↗

arXiv2025

Long-term prediction of El Niño-Southern Oscillation using reservoir computing with data-driven realtime filter

In recent years, the application of machine learning approaches to time-series forecasting of climate dynamical phenomena has become increasingly active. It is known that applying a band-pass filter to a time-series data is a key to obtaining a high-quality data-driven model. Here, to obtain longer-term predictability of machine learning models, we introduce a new type of band-pass filter. It can be applied to realtime operational prediction workflows since it relies solely on past time series. We combine the filter with reservoir computing, which is a machine-learning technique that employs a data-driven dynamical system. As an application, we predict the multi-year dynamics of the El Niño-Southern Oscillation with the prediction horizon of 24 months using only past time series.

physics.comp-ph↗

arXiv2024

Data-driven ODE modeling of the high-frequency complex dynamics via a low-frequency dynamics model

In our previous paper [N. Tsutsumi, K. Nakai and Y. Saiki, Chaos 32, 091101 (2022)], we proposed a method for constructing a system of differential equations of chaotic behavior from only observable deterministic time series, which we call the radial function-based regression (RfR) method. However, when the targeted variable's behavior is rather complex, the direct application of the RfR method does not function well. In this study, we propose a novel method of modeling such dynamics, including the high-frequency intermittent behavior of a fluid flow, by considering another variable (base variable) showing relatively simple, less intermittent behavior. We construct an autonomous joint model composed of two parts: the first is an autonomous system of a base variable, and the other concerns the targeted variable being affected by a term involving the base variable to demonstrate complex dynamics. The constructed joint model succeeded in not only inferring a short trajectory but also reconstructing chaotic sets and statistical properties obtained from a long trajectory such as the density distributions of the actual dynamics.

nlin.CD↗

arXiv2024

Data-driven modeling from biased small training data using periodic orbits

In this study, we investigate the effect of reservoir computing training data on the reconstruction of chaotic dynamics. Our findings indicate that a training time series comprising a few periodic orbits of low periods can successfully reconstruct the Lorenz attractor. We also demonstrate that biased training data does not negatively impact reconstruction success. Our method's ability to reconstruct a physical measure is much better than the so-called cycle expansion approach, which relies on weighted averaging. Additionally, we demonstrate that fixed point attractors and chaotic transients can be accurately reconstructed by a model trained from a few periodic orbits, even when using different parameters.

physics.data-an↗

arXiv2023

Constructing low-dimensional ordinary differential equations from chaotic time series of high/infinite-dimensional systems using radial function-based regression

In our previous study (N. Tsutsumi, K. Nakai and Y. Saiki (2022)) we proposed a method of constructing a system of differential equations of chaotic behavior only from observable deterministic time series, which we will call radial function-based regression (RfR) method. The RfR method employs a regression using Gaussian radial basis functions together with polynomial terms to facilitate the robust modeling of chaotic behavior. In this paper, we apply the RfR method to several types of relatively high-dimensional deterministic time series generated by a partial differential equation, a delay differential equation, a turbulence model, and intermittent dynamics. The case when the observation includes noise is also tested. We have effectively constructed a system of differential equations for each of these examples, which is assessed from the point of view of time series forecast, reconstruction of invariant sets, and invariant densities. We find that in some of the models, an appropriate trajectory is realized on the chaotic saddle and is identified by the Stagger-and-Step method.

math.DS↗

arXiv2022

Machine learning prediction of the MJO extends beyond one month

The prediction of the Madden-Julian Oscillation (MJO), a massive tropical weather event with vast global socio-economic impacts, has been infamously difficult with physics-based weather prediction models. Here we construct a machine learning model using reservoir computing technique that forecasts the real-time multivariate MJO index (RMM), a macroscopic variable that represents the state of the MJO. The training data was refined by developing a novel filter that extracts the recurrency of MJO signals from the raw atmospheric data and selecting a suitable time-delay coordinate of the RMM. The model demonstrated the skill to forecast the state of MJO events for a month from the pre-developmental stages. Best-performing cases predicted the RMM sequence over two months, which exceeds the expected inherent predictability limit of the MJO.

physics.ao-ph↗

arXiv2022

Constructing differential equations using only a scalar time-series about continuous time chaotic dynamics

We propose a simple method of constructing a system of differential equations of chaotic behavior based on the regression only from a scalar observable time-series data. The estimated system enables us to reconstruct invariant sets and statistical properties as well as to infer short time-series. Our successful modeling relies on the introduction of a set of Gaussian radial basis functions to capture local structure. The proposed method is used to construct a system of ordinary differential equations whose orbit reconstructs a time-series of a variable of the well-known Lorenz system as a simple but typical example. A system for a macroscopic fluid variable is also constructed.

math.DS↗

arXiv2021

Dynamical system analysis of a data-driven model constructed by reservoir computing

This study evaluates data-driven models from a dynamical system perspective, such as unstable fixed points, periodic orbits, chaotic saddle, Lyapunov exponents, manifold structures, and statistical values. We find that these dynamical characteristics can be reconstructed much more precisely by a data-driven model than by computing directly from training data. With this idea, we predict the laminar lasting time distribution of a particular macroscopic variable of chaotic fluid flow, which cannot be calculated from a direct numerical simulation of the Navier-Stokes equation because of its high computational cost.

math.DS↗

arXiv2019

Machine-learning construction of a model for a macroscopic fluid variable using the delay-coordinate of a scalar observable

We construct a data-driven dynamical system model for a macroscopic variable the Reynolds number of a high-dimensionally chaotic fluid flow by training its scalar time-series data. We use a machine-learning approach, the reservoir computing for the construction of the model, and do not use the knowledge of a physical process of fluid dynamics in its procedure. It is confirmed that an inferred time-series obtained from the model approximates the actual one in each of various time-intervals, and that some characteristics of the chaotic invariant set mimic the actual ones. We investigate the appropriate choice of the delay-coordinate, especially the delay-time and the dimension, which enables us to construct a model having a relatively high-dimensional attractor easily.

physics.flu-dyn↗

arXiv2018

Machine-learning inference of fluid variables from data using reservoir computing

We infer both microscopic and macroscopic behaviors of a three-dimensional chaotic fluid flow using reservoir computing. In our procedure of the inference, we assume no prior knowledge of a physical process of a fluid flow except that its behavior is complex but deterministic. We present two ways of inference of the complex behavior; the first called partial-inference requires continued knowledge of partial time-series data during the inference as well as past time-series data, while the second called full-inference requires only past time-series data as training data. For the first case, we are able to infer long-time motion of microscopic fluid variables. For the second case, we show that the reservoir dynamics constructed from only past data of energy functions can infer the future behavior of energy functions and reproduce the energy spectrum. It is also shown that we can infer a time-series data from only one measurement by using the delay coordinates. These implies that the obtained two reservoir systems constructed without the knowledge of microscopic data are equivalent to the dynamical systems describing macroscopic behavior of energy functions.

physics.comp-ph↗