Kyushu University Academic Staff Educational and Research Activities Database
List of Papers
Yoshinobu Kawahara Last modified date:2019.08.06

Professor / Division for Intelligent Societal Implementation of Mathmatical Computation / Institute of Mathematics for Industry


Papers
1. K. Fujii, and Y. Kawahara, Dynamic mode decomposition in vector-valued reproducing kernel Hilbert spaces for extracting dynamical structure among observables, Neural Networks, 10.1016/j.neunet.2019.04.020, 117, 94-103, 2019.09, [URL].
2. K. Fujii, and Y. Kawahara, Supervised dynamic mode decomposition via multitask learning, Pattern Recognition Letters, 10.1016/j.patrec.2019.02.010, 122, 7-13, 2019.05, [URL].
3. M. Hojo, K. Fujii, and Y. Kawahara, Analysis of factors predicting who obtains a ball in basketball rebounding situations, International Journal of Performance Analysis in Sport, 10.1080/24748668.2019.1582892, 19, 2, 192-205, 2019.02, [URL].
4. M. Hojo, K. Fujii, Y. Inaba, Y. Motoyasu, and Y. Kawahara, Automatically recognizing strategic cooperative behaviors in various situations of a team sport, PLoS ONE, 10.1371/journal.pone.0209247, 13, 12, 2018.12, [URL].
5. I. Ishikawa, K. Fujii, M. Ikeda, Y. Hashimoto, and Y. Kawahara, Metric on nonlinear dynamical systems with Perron-Frobenius operators, Advances in Neural Information Processing Systems 31 (Proc. of NeurIPS'18), 2856-2866, 2018.12, [URL].
6. N. Takeishi, T. Yairo, and Y. Kawahara, Factorially-switching dynamic mode decomposition for Koopman analysis of time-variant systems, Proceedings of the 57th IEEE Conference on Decision and Control (CDC'18), 10.1109/CDC.2018.8619846, 6402-6408, 2018.12, [URL].
7. K. Fujii, T. Kawasaki, Y. Inaba, and Y. Kawahara, Prediction and classification in equation-free collective motion dynamics, PLoS Computational Biology, 10.1371/journal.pcbi.1006545, 14, 11, e1006545, 2018.11, [URL].
8. T. Wazawa, Y. Arai, Y. Kawahara, H. Takauchi, T. Washio, and T. Nagai, Highly biocompatible super-resolution fluorescence imaging using the fast photoswitching fluorescent protein Kohinoor and SPoD-ExPAN with Lp-regularized image reconstruction, Microscopy, 10.1093/jmicro/dfy004, 67, 2, 89-98, 2018.02, [URL].
9. N. Takeishi, Y. Kawahara, and T. Yairi, Learning Koopman invariant subspaces for dynamic mode decomposition, Advances in Neural Information Processing Systems 30 (Proc. of NIPS'17), 1131-1141, 2017.12, [URL].
10. K. Fujii, Y. Inaba, and Y. Kawahara, Koopman spectral kernels for comparing complex dynamics with application to multiagent in sports, Proceedings of the 2017 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD'17), 10.1007/978-3-319-71273-4_11, 127-139, 2017.12, [URL].
11. K. Takeuchi, Y. Kawahara, and T. Iwata, Structurally regularized non-negative tensor factorization for spatio-temporal pattern discoveries, Proceedings of the 2017 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD'17), 10.1007/978-3-319-71249-9_35, 582-598, 2017.12, [URL].
12. N. Takeishi, Y. Kawahara, and T. Yairi, Subspace dynamic mode decomposition for stochastic Koopman analysis, Physical Review E, 10.1103/PhysRevE.96.033310, 96, 033310, 2017.09, [URL].
13. N. Takeishi, Y. Kawahara, and T. Yairi, Sparse nonnegative dynamic mode decomposition, Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP'17), 10.1109/ICIP.2017.8296769, 2682-2686, 2017.09, [URL].
14. N. Takeishi, Y. Kawahara, Y. Tabei, and T. Yairi, Bayesian dynamic mode decomposition, Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI'17), 10.24963/ijcai.2017/392, 2814-2821, 2017.07, [URL].
15. H. Wang, Y. Kawahara, C. Weng, and J. Yuan, Representative Selection with Structured Sparsity, Pattern Recognition, 10.1016/j.patcog.2016.10.014, 63, 268-278, 2017.03, [URL].
16. Y. Kawahara, Dynamic Mode Decomposition with Reproducing Kernels for Koopman Spectral Analysis, Advances in Neural Information Processing Systems 29 (Proc. of NIPS'16), 911-919, 2016.12, [URL].
17. B. Xin, Y. Kawahara, Y. Wang, L. Hu, and W. Gao, Efficient generalized fused lasso and its applications, ACM Transactions on Intelligent Systems and Technology, 10.1145/2847421, 7, 4, 2016.05, [URL].
18. Marina Demeshko, Takashi Washio, Yoshinobu Kawahara, Yuriy Pepyolyshev, A novel continuous and structural VAR modeling approach and its application to reactor noise analysis, ACM Transactions on Intelligent Systems and Technology, 10.1145/2710025, 7, 2, 2015.12.
19. Shinichi Yamagiwa, Yoshinobu Kawahara, Noriyuki Tabuchi, Yoshinobu Watanabe, Takeshi Naruo, Skill grouping method
Mining and clustering skill differences from body movement BigData, Proceedings of the 2015 IEEE International Conference on Big Data (IEEE Big Data 2015), 10.1109/BigData.2015.7364049, 2525-2534, 2015.12.
20. Takehide Hirata, Yoshinobu Kawahara, Masashi Sugiyama, Kazuya Asano, A fault detection technique for the steel manufacturing process based on a normal pattern library, Proceedings of the9th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS 2015), 10.1016/j.ifacol.2015.09.636, 28, 21, 871-876, 2015.09.
21. M. Demeshko, A. Dokhane, T. Washio, H. Ferroukhi, Yoshinobu Kawahara, C. Aguirre, Application of Continuous and Structural ARMA modeling for noise analysis of a BWR coupled core and plant instability event, Annals of Nuclear Energy, 10.1016/j.anucene.2014.08.045, 75, 645-657, 2015.01.
22. Koh Takeuchi, Yoshinobu Kawahara, Tomoharu Iwata, Higher order fused regularization for supervised learning with grouped parameters, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2015 Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2015, Proceedings, 10.1007/978-3-319-23528-8_36, 577-593, 2015.01, We often encounter situations in supervised learning where there exist possibly groups that consist of more than two parameters. For example, we might work on parameters that correspond to words expressing the same meaning, music pieces in the same genre, and books released in the same year. Based on such auxiliary information, we could suppose that parameters in a group have similar roles in a problem and similar values. In this paper, we propose the Higher Order Fused (HOF) regularization that can incorporate smoothness among parameters with group structures as prior knowledge in supervised learning. We define the HOF penalty as the Lovász extension of a submodular higher-order potential function, which encourages parameters in a group to take similar estimated values when used as a regularizer. Moreover, we develop an efficient network flow algorithm for calculating the proximity operator for the regularized problem. We investigate the empirical performance of the proposed algorithm by using synthetic and real-world data..
23. Yoshinobu Kawahara, Rishabh Iyer, Jeffery A. Bilmes, On approximate non-submodular minimization via tree-structured supermodularity, 18th International Conference on Artificial Intelligence and Statistics, AISTATS 2015 Journal of Machine Learning Research, 38, 444-452, 2015.01, We address the problem of minimizing non-submodular functions where the supermodularity is restricted to tree-structured pair-wise terms. We are motivated by several real world applications, which require submodu-larity along with structured supermodular-ity, and this forms a rich class of expressive models, where the non-submodularity is restricted to a tree. While this problem is NP hard (as we show), we develop several practical algorithms to find approximate and near-optimal solutions for this problem, some of which provide lower and others of which provide upper bounds thereby allowing us to compute a tightness gap. We also show that some of our algorithms can be extended to handle more general forms of supermodular-ity restricted to arbitrary pairwise terms. We compare our algorithms on synthetic data, and also demonstrate the advantage of the formulation on the real world application of image segmentation, where we incorporate structured supermodularity into higher-order submodular energy minimization..
24. Keisuke Nagata, Takashi Washio, Yoshinobu Kawahara, Akira Unami, Toxicity prediction from toxicogenomic data based on class association rule mining, Toxicology Reports, 10.1016/j.toxrep.2014.10.014, 1, 1133-1142, 2014.12, While the recent advent of new technologies in biology such as DNA microarray and next-generation sequencer has given researchers a large volume of data representing genome-wide biological responses, it is not necessarily easy to derive knowledge that is accurate and understandable at the same time. In this study, we applied the Classification Based on Association (CBA) algorithm, one of the class association rule mining techniques, to the TG-GATEs database, where both toxicogenomic and toxicological data of more than 150 compounds in rat and human are stored. We compared the generated classifiers between CBA and linear discriminant analysis (LDA) and showed that CBA is superior to LDA in terms of both predictive performances (accuracy: 83% for CBA vs. 75% for LDA, sensitivity: 82% for CBA vs. 72% for LDA, specificity: 85% for CBA vs. 75% for LDA) and interpretability..
25. Bo Xin, Yoshinobu Kawahara, Yizhou Wang, Wen Gao, Efficient generalized fused lasso and its application to the diagnosis of Alzheimer's disease, 28th AAAI Conference on Artificial Intelligence, AAAI 2014, 26th Innovative Applications of Artificial Intelligence Conference, IAAI 2014 and the 5th Symposium on Educational Advances in Artificial Intelligence, EAAI 2014 Proceedings of the National Conference on Artificial Intelligence, 2163-2169, 2014.01, Generalized fused lasso (GFL) penalizes variables with L1norms based both on the variables and their pairwise differences. GFL is useful when applied to data where prior information is expressed using a graph over the variables. However, the existing GFL algorithms incur high computational costs and they do not scale to highdimensional problems. In this study, we propose a fast and scalable algorithm for GFL. Based on the fact that fusion penalty is the Lovász extension of a cut function, we show that the key building block of the optimization is equivalent to recursively solving parametric graph-cut problems. Thus, we use a parametric flow algorithm to solve GFL in an efficient manner. Runtime comparisons demonstrated a significant speed-up compared with the existing GFL algorithms. By exploiting the scalability of the proposed algorithm, we formulated the diagnosis of Alzheimer's disease as GFL. Our experimental evaluations demonstrated that the diagnosis performance was promising and that the selected critical voxels were well structured i.e., connected, consistent according to cross-validation and in agreement with prior clinical knowledge..
26. Mahito Sugiyama, Chloé Agathe Azencott, Dominik Grimm, Yoshinobu Kawahara, Karsten M. Borgwardt, Multi-task feature selection on multiple networks via maximum flows, 14th SIAM International Conference on Data Mining, SDM 2014 SIAM International Conference on Data Mining 2014, SDM 2014, 10.1137/1.9781611973440.23, 199-207, 2014.01, We propose a new formulation of multi-task feature selection coupled with multiple network regularizers, and show that the problem can be exactly and efficiently solved by maximum flow algorithms. This method contributes to one of the central topics in data mining: How to exploit structural information in multivariate data analysis, which has numerous applications, such as gene regulatory and social network analysis. On simulated data, we show that the proposed method leads to higher accuracy in discovering causal features by solving multiple tasks simultaneously using networks over features. Moreover, we apply the method to multi-locus association mapping with Arabidopsis thaliana genotypes and flowering time phenotypes, and demonstrate its ability to recover more known phenotype-related genes than other state-of-the-art methods..
27. Yunzhu Zheng, Haruka Suematsu, Takayuki Itoh, Ryohei Fujimaki, Satoshi Morinaga, Yoshinobu Kawahara, Scatterplot layout for high-dimensional data visualization, Journal of Visualization, 10.1007/s12650-014-0230-5, 18, 1, 111-119, 2014.01, Abstract: Multi-dimensional data visualization is an important research topic that has been receiving increasing attention. Several techniques that apply scatterplot matrices have been proposed to represent multi-dimensional data as a collection of two-dimensional data visualization spaces. Typically, when using the scatterplot-based approach it is easier to understand relations between particular pairs of dimensions, but it often requires too large display spaces to display all possible scatterplots. This paper presents a technique to display meaningful sets of scatterplots generated from high-dimensional datasets. Our technique first evaluates all possible scatterplots generated from high-dimensional datasets, and selects meaningful sets. It then calculates the similarity between arbitrary pairs of the selected scatterplots, and places relevant scatterplots closer together in the display space while they never overlap each other. This design policy makes users easier to visually compare relevant sets of scatterplots. This paper presents algorithms to place the scatterplots by the combination of ideal position calculation and rectangle packing algorithms, and two examples demonstrating the effectiveness of the presented technique..
28. Haruka Suematsu, Zheng Yunzhu, Takayuki Itoh, Ryohei Fujimaki, Satoshi Morinaga, Yoshinobu Kawahara, Arrangement of low-dimensional parallel coordinate plots for high-dimensional data visualization, 2013 17th International Conference on Information Visualisation, IV 2013 Proceedings - 2013 17th International Conference on Information Visualisation, IV 2013, 10.1109/IV.2013.7, 59-65, 2013.12, Multidimensional data visualization is an important research topic that has been receiving increasing attention. Several techniques that use parallel coordinate plots have been proposed to represent all dimensions of data in a single display space. In addition, several other techniques that apply scatter plot matrices have been proposed to represent multidimensional data as a collection of low-dimensional data visualization spaces. Typically, when using the latter approach it is easier to understand relations among particular dimensions, but it is often difficult to observe relations between dimensions separated into different visualization spaces. This paper presents a framework for displaying an arrangement of low-dimensional data visualization spaces that are generated from high-dimensional datasets. Our proposed technique first divides the dimensions of the input datasets into groups of lower dimensions based on their correlations or other relationships. If the groups of lower dimensions can be visualized in independent rectangular spaces, our technique packs the set of low-dimensional data visualizations into a single display space. Because our technique places relevant low-dimensions closer together in the display space, it is easier to visually compare relevant sets of low-dimensional data visualizations. In this paper, we describe in detail how we implement our framework using parallel coordinate plots, and present several results demonstrating its effectiveness..
29. Yasuhiro Sogawa, Tsuyoshi Ueno, Yoshinobu Kawahara, Takashi Washio, Active learning for noisy oracle via density power divergence, Neural Networks, 10.1016/j.neunet.2013.05.007, 46, 133-143, 2013.10, The accuracy of active learning is critically influenced by the existence of noisy labels given by a noisy oracle. In this paper, we propose a novel pool-based active learning framework through robust measures based on density power divergence. By minimizing density power divergence, such as β-divergence and γ-divergence, one can estimate the model accurately even under the existence of noisy labels within data. Accordingly, we develop query selecting measures for pool-based active learning using these divergences. In addition, we propose an evaluation scheme for these measures based on asymptotic statistical analyses, which enables us to perform active learning by evaluating an estimation error directly. Experiments with benchmark datasets and real-world image datasets show that our active learning scheme performs better than several baseline methods..
30. Chloé Agathe Azencott, Dominik Grimm, Mahito Sugiyama, Yoshinobu Kawahara, Karsten M. Borgwardt, Efficient network-guided multi-locus association mapping with graph cuts, Bioinformatics, 10.1093/bioinformatics/btt238, 29, 13, 2013.07, Motivation: As an increasing number of genome-wide association studies reveal the limitations of the attempt to explain phenotypic heritability by single genetic loci, there is a recent focus on associating complex phenotypes with sets of genetic loci. Although several methods for multi-locus mapping have been proposed, it is often unclear how to relate the detected loci to the growing knowledge about gene pathways and networks. The few methods that take biological pathways or networks into account are either restricted to investigating a limited number of predetermined sets of loci or do not scale to genome-wide settings.Results: We present SConES, a new efficient method to discover sets of genetic loci that are maximally associated with a phenotype while being connected in an underlying network. Our approach is based on a minimum cut reformulation of the problem of selecting features under sparsity and connectivity constraints, which can be solved exactly and rapidly.SConES outperforms state-of-the-art competitors in terms of runtime, scales to hundreds of thousands of genetic loci and exhibits higher power in detecting causal SNPs in simulation studies than other methods. On flowering time phenotypes and genotypes from Arabidopsis thaliana, SConES detects loci that enable accurate phenotype prediction and that are supported by the literature..
31. Yasuhiro Sogawa, Tsuyoshi Ueno, Yoshinobu Kawahara, Takashi Washio, Active learning for regression via density power divergence, Transactions of the Japanese Society for Artificial Intelligence, 10.1527/tjsai.28.13, 28, 1, 13-21, 2013.01, The accuracy of active learning is crucially influenced by the existence of noisy labels given by a real-world noisy oracle. In this paper, we propose a novel pool-based active learning framework through density power divergence. It is known that density power divergence, such as β-divergence and γ-divergence, can be accurately estimated even under the existence of outliers (noisy labels) within data. In addition, we propose an evaluation scheme for these measures based on those asymptotic statistical analyses, which enables us to perform active learning by evaluating an estimation variance. Experiments on artificial and real-world datasets show that our active learning scheme performs better than state-of-the-art methods..
32. Akiko Takeda, Mahesan Niranjan, Jun ya Gotoh, Yoshinobu Kawahara, Simultaneous pursuit of out-of-sample performance and sparsity in index tracking portfolios, Computational Management Science, 10.1007/s10287-012-0158-y, 10, 1, 21-49, 2013.01, Index tracking is a passive investment strategy in which a fund (e. g., an ETF: exchange traded fund) manager purchases a set of assets to mimic a market index. The tracking error, i. e., the difference between the performances of the index and the portfolio, may be minimized by buying all the assets contained in the index. However, this strategy results in a considerable transaction cost and, accordingly, decreases the return of the constructed portfolio. On the other hand, a portfolio with a small cardinality may result in poor out-of-sample performance. Of interest is, thus, constructing a portfolio with good out-of-sample performance, while keeping the number of assets invested in small (i. e., sparse). In this paper, we develop a tracking portfolio model that addresses the above conflicting requirements by using a combination of L0- and L2-norms. The L2-norm regularizes the overdetermined system to impose smoothness (and hence has better out-of-sample performance), and it shrinks the solution to an equally-weighted dense portfolio. On the other hand, the L0-norm imposes a cardinality constraint that achieves sparsity (and hence a lower transaction cost). We propose a heuristic method for estimating portfolio weights, which combines a greedy search with an analytical formula embedded in it. We demonstrate that the resulting sparse portfolio has good tracking and generalization performance on historic data of weekly and monthly returns on the Nikkei 225 index and its constituent companies..
33. Akiko Takeda, Mahesan Niranjan, Jun ya Gotoh, Yoshinobu Kawahara, Simultaneous pursuit of out-of-sample performance and sparsity in index tracking portfolios, Computational Management Science, 10.1007/s10287-012-0158-y, 10, 1, 21-49, 2013.01, Index tracking is a passive investment strategy in which a fund (e. g., an ETF: exchange traded fund) manager purchases a set of assets to mimic a market index. The tracking error, i. e., the difference between the performances of the index and the portfolio, may be minimized by buying all the assets contained in the index. However, this strategy results in a considerable transaction cost and, accordingly, decreases the return of the constructed portfolio. On the other hand, a portfolio with a small cardinality may result in poor out-of-sample performance. Of interest is, thus, constructing a portfolio with good out-of-sample performance, while keeping the number of assets invested in small (i. e., sparse). In this paper, we develop a tracking portfolio model that addresses the above conflicting requirements by using a combination of L0- and L2-norms. The L2-norm regularizes the overdetermined system to impose smoothness (and hence has better out-of-sample performance), and it shrinks the solution to an equally-weighted dense portfolio. On the other hand, the L0-norm imposes a cardinality constraint that achieves sparsity (and hence a lower transaction cost). We propose a heuristic method for estimating portfolio weights, which combines a greedy search with an analytical formula embedded in it. We demonstrate that the resulting sparse portfolio has good tracking and generalization performance on historic data of weekly and monthly returns on the Nikkei 225 index and its constituent companies..
34. Tsuyoshi Ueno, Kohei Hayashi, Takashi Washio, Yoshinobu Kawahara, Weighted likelihood policy search with model selection, 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012 Advances in Neural Information Processing Systems 25 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012, 2357-2365, 2012.12, Reinforcement learning (RL) methods based on direct policy search (DPS) have been actively discussed to achieve an efficient approach to complicated Markov decision processes (MDPs). Although they have brought much progress in prac- tical applications of RL, there still remains an unsolved problem in DPS related to model selection for the policy. In this paper, we propose a novel DPS method, weighted likelihood policy search (WLPS), where a policy is efficiently learned through the weighted likelihood estimation. WLPS naturally connects DPS to the statistical inference problem and thus various sophisticated techniques in statis- tics can be applied to DPS problems directly. Hence, by following the idea of the information criterion, we develop a new measurement for model comparison in DPS based on the weighted log-likelihood..
35. Yasuhiro Sogawa, Tsuyoshi Ueno, Yoshinobu Kawahara, Takashi Washio, Robust active learning for linear regression via density power divergence, 19th International Conference on Neural Information Processing, ICONIP 2012 Neural Information Processing - 19th International Conference, ICONIP 2012, Proceedings, 10.1007/978-3-642-34487-9_72, 594-602, 2012.11, The performance of active learning (AL) is crucially influenced by the existence of outliers in input samples. In this paper, we propose a robust pool-based AL measure based on the density power divergence. It is known that the density power divergence can be accurately estimated even under the existence of outliers within data. We further derive an AL scheme based on an asymptotic statistical analysis on the M-estimator. The performance of the proposed framework is investigated empirically using artificial and real-world data..
36. Satoshi Hara, Yoshinobu Kawahara, Takashi Washio, Paul von Bünau, Terumasa Tokunaga, Kiyohumi Yumoto, Separation of stationary and non-stationary sources with a generalized eigenvalue problem, Neural Networks, 10.1016/j.neunet.2012.04.001, 33, 7-20, 2012.09, Non-stationary effects are ubiquitous in real world data. In many settings, the observed signals are a mixture of underlying stationary and non-stationary sources that cannot be measured directly. For example, in EEG analysis, electrodes on the scalp record the activity from several sources located inside the brain, which one could only measure invasively. Discerning stationary and non-stationary contributions is an important step towards uncovering the mechanisms of the data generating system. To that end, in Stationary Subspace Analysis (SSA), the observed signal is modeled as a linear superposition of stationary and non-stationary sources, where the aim is to separate the two groups in the mixture. In this paper, we propose the first SSA algorithm that has a closed form solution. The novel method, Analytic SSA (ASSA), is more than 100 times faster than the state-of-the-art, numerically stable, and guaranteed to be optimal when the covariance between stationary and non-stationary sources is time-constant. In numerical simulations on wide range of settings, we show that our method yields superior results, even for signals with time-varying group-wise covariance. In an application to geophysical data analysis, ASSA extracts meaningful components that shed new light on the Pi 2 pulsations of the geomagnetic field..
37. Y. Kawahara, and M. Sugiyama, Sequential change-point detection based on direct density-ratio estimation, Statistical Analysis and Data Mining, 10.1002/sam.10124, 5, 2, 114-127, 2012.04, [URL].
38. Yoshinobu Kawahara, Takashi Washio, Prismatic algorithm for discrete D.C. programming problem, 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011 Advances in Neural Information Processing Systems 24 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011, 2011.12, In this paper, we propose the first exact algorithm for minimizing the difference of two submodular functions (D.S.), i.e., the discrete version of the D.C. programming problem. The developed algorithm is a branch-and-bound-based algorithm which responds to the structure of this problem through the relationship between submodularity and convexity. The D.S. programming problem covers a broad range of applications in machine learning. In fact, this generalizes any set-function optimization. We empirically investigate the performance of our algorithm, and illustrate the difference between exact and approximate solutions respectively obtained by the proposed and existing algorithms in feature selection and discriminative structure learning..
39. Masao Joko, Yoshinobu Kawahara, Takehisa Yairi, Learning non-linear dynamical systems by alignment of local linear models, Transactions of the Japanese Society for Artificial Intelligence, 10.1527/tjsai.26.638, 26, 6, 638-648, 2011.10, In this paper, we present an algorithm for learning non-linear dynamical systems which works by aligning local linear models, based on a probabilistic formulation of subspace identification. This is achieved by the fusion of the recent works in the fields of machine learning and system control. Because the procedure for constructing a state sequence in subspace identification can be interpreted as the Canonical Correlation Analysis(CCA) between past and future observation sequences, we can derive a latent variable representation for this problem. Therefore, as in a similar manner to the recent works on learning a mixture of probabilistic models, we obtain a framework for constructing a state space by aligning local linear coordinates. This leads to a prominent algorithm for learning non-linear dynamical systems. Finally, we apply our method to motion capture data and telemetry data, and then show how our algorithm works well..
40. Kiyohito Nagano, Yoshinobu Kawahara, Kazuyuki Aihara, Size-constrained submodular minimization through minimum norm base, 28th International Conference on Machine Learning, ICML 2011 Proceedings of the 28th International Conference on Machine Learning, ICML 2011, 977-984, 2011.10, A number of combinatorial optimization problems in machine learning can be described as the problem of minimizing a submodular function. It is known that the unconstrained submodular minimization problem can be solved in strongly polynomial time. However, additional constraints make the problem intractable in many settings. In this paper, we discuss the submodular minimization under a size constraint, which is NP-hard, and generalizes the densest subgraph problem and the uniform graph partitioning problem. Because of NP-hardness, it is difficult to compute an optimal solution even for a prescribed size constraint. In our approach, we do not give approximation algorithms. Instead, the proposed algorithm computes optimal solutions for some of possible size constraints in polynomial time. Our algorithm utilizes the basic polyhedral theory associated with submodular functions. Additionally, we evaluate the performance of the proposed algorithm through computational experiments..
41. Masao Joko, Yoshinobu Kawahara, Takehisa Yairi, Learning non-linear dynamical systems by alignment of local linear models, Transactions of the Japanese Society for Artificial Intelligence, 10.1527/tjsai.26.638, 26, 6, 638-648, 2011.10, In this paper, we present an algorithm for learning non-linear dynamical systems which works by aligning local linear models, based on a probabilistic formulation of subspace identification. This is achieved by the fusion of the recent works in the fields of machine learning and system control. Because the procedure for constructing a state sequence in subspace identification can be interpreted as the Canonical Correlation Analysis(CCA) between past and future observation sequences, we can derive a latent variable representation for this problem. Therefore, as in a similar manner to the recent works on learning a mixture of probabilistic models, we obtain a framework for constructing a state space by aligning local linear coordinates. This leads to a prominent algorithm for learning non-linear dynamical systems. Finally, we apply our method to motion capture data and telemetry data, and then show how our algorithm works well..
42. Kiyohito Nagano, Yoshinobu Kawahara, Kazuyuki Aihara, Size-constrained submodular minimization through minimum norm base, 28th International Conference on Machine Learning, ICML 2011 Proceedings of the 28th International Conference on Machine Learning, ICML 2011, 977-984, 2011.10, A number of combinatorial optimization problems in machine learning can be described as the problem of minimizing a submodular function. It is known that the unconstrained submodular minimization problem can be solved in strongly polynomial time. However, additional constraints make the problem intractable in many settings. In this paper, we discuss the submodular minimization under a size constraint, which is NP-hard, and generalizes the densest subgraph problem and the uniform graph partitioning problem. Because of NP-hardness, it is difficult to compute an optimal solution even for a prescribed size constraint. In our approach, we do not give approximation algorithms. Instead, the proposed algorithm computes optimal solutions for some of possible size constraints in polynomial time. Our algorithm utilizes the basic polyhedral theory associated with submodular functions. Additionally, we evaluate the performance of the proposed algorithm through computational experiments..
43. Yoshinobu Kawahara, Shohei Shimizu, Takashi Washio, Analyzing relationships among ARMA processes based on non-Gaussianity of external influences, Neurocomputing, 10.1016/j.neucom.2011.02.008, 74, 12-13, 2212-2221, 2011.06, The analysis of a relationship among variables in data generating systems is one of the important problems in machine learning. In this paper, we propose an approach for estimating a graphical representation of variables in data generating processes, based on the non-Gaussianity of external influences and an autoregressive moving-average (ARMA) model. The presented model consists of two parts, i.e., a classical structural-equation model for instantaneous effects and an ARMA model for lagged effects in processes, and is estimated through the analysis using the non-Gaussianity on the residual processes. As well as the recently proposed non-Gaussianity based method named LiNGAM analysis, the estimation by the proposed method has identifiability and consistency. We also address the relation of the estimated structure by our method to the Granger causality. Finally, we demonstrate analyses on the data containing both of the instantaneous causality and the Granger (temporal) causality by using our proposed method where the datasets for the demonstration cover both artificial and real physical systems..
44. Shohei Shimizu, Takanori Inazumi, Yasuhiro Sogawa, Aapo Hyvärinen, Yoshinobu Kawahara, Takashi Washio, Patrik O. Hoyer, Kenneth Bollen, DirectLiNGAM
A direct method for learning a linear non-gaussian structural equation model, Journal of Machine Learning Research, 12, 1225-1248, 2011.04, Structural equation models and Bayesian networks have been widely used to analyze causal relations between continuous variables. In such frameworks, linear acyclic models are typically used to model the data-generating process of variables. Recently, it was shown that use of non-Gaussianity identifies the full structure of a linear acyclic model, that is, a causal ordering of variables and their connection strengths, without using any prior knowledge on the network structure, which is not the case with conventional methods. However, existing estimation methods are based on iterative search algorithms and may not converge to a correct solution in a finite number of steps. In this paper, we propose a new direct method to estimate a causal ordering and connection strengths based on non-Gaussianity. In contrast to the previous methods, our algorithm requires no algorithmic parameters and is guaranteed to converge to the right solution within a small fixed number of steps if the data strictly follows the model, that is, if all the model assumptions are met and the sample size is infinite..
45. Yoshinobu Kawahara, Kiyohito Nagano, Yoshio Okamoto, Submodular fractional programming for balanced clustering, Pattern Recognition Letters, 10.1016/j.patrec.2010.08.008, 32, 2, 235-243, 2011.01, We address the balanced clustering problem where cluster sizes are regularized with submodular functions. The objective function for balanced clustering is a submodular fractional function, i.e; the ratio of two submodular functions, and thus includes the well-known ratio cuts as special cases. In this paper, we present a novel algorithm for minimizing this objective function (submodular fractional programming) using recent submodular optimization techniques. The main idea is to utilize an algorithm to minimize the difference of two submodular functions, combined with the discrete Newton method. Thus, it can be applied to the objective function involving any submodular functions in both the numerator and the denominator, which enables us to design flexible clustering setups. We also give theoretical analysis on the algorithm, and evaluate the performance through comparative experiments with conventional algorithms by artificial and real datasets..
46. Yasuhiro Sogawa, Shohei Shimizu, Yoshinobu Kawahara, Takashi Washio, An experimental comparison of linear non-Gaussian causal discovery methods and their variants, 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010, 10.1109/IJCNN.2010.5596737, 2010.12, Many multivariate Gaussianity-based techniques for identifying causal networks of observed variables have been proposed. These methods have several problems such that they cannot uniquely identify the causal networks without any prior knowledge. To alleviate this problem, a non-Gaussianity-based identification method LiNGAM was proposed. Though the LiNGAM potentially identifies a unique causal network without using any prior knowledge, it needs to properly examine independence assumptions of the causal network and search the correct causal network by using finite observed data points only. On another front, a kernel based independence measure that evaluates the independence more strictly was recently proposed. In addition, some advanced generic search algorithms including beam search have been extensively studied in the past. In this paper, we propose some variants of the LiNGAM method which introduce the kernel based method and the beam search enabling more accurate causal network identification. Furthermore, we experimentally characterize the LiNGAM and its variants in terms of accuracy and robustness of their identification..
47. Kiyohito Nagano, Yoshinobu Kawahara, Satoru Iwata, Minimum average cost clustering, 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010 Advances in Neural Information Processing Systems 23 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010, 2010.12, A number of objective functions in clustering problems can be described with submodular functions. In this paper, we introduce the minimum average cost criterion, and show that the theory of intersecting submodular functions can be used for clustering with submodular objective functions. The proposed algorithm does not require the number of clusters in advance, and it will be determined by the property of a given set of data points. The minimum average cost clustering problem is parameterized with a real variable, and surprisingly, we show that all information about optimal clusterings for all parameters can be computed in polynomial time in total. Additionally, we evaluate the performance of the proposed algorithm through computational experiments..
48. Satoshi Hara, Yoshinobu Kawahara, Takashi Washio, Paul Von Bünau, Stationary subspace analysis as a generalized eigenvalue problem, 17th International Conference on Neural Information Processing, ICONIP 2010 Neural Information Processing Theory and Algorithms - 17th International Conference, ICONIP 2010, Proceedings, 10.1007/978-3-642-17537-4_52, 422-429, 2010.12, Understanding non-stationary effects is one of the key challenges in data analysis. However, in many settings the observation is a mixture of stationary and non-stationary sources. The aim of Stationary Subspace Analysis (SSA) is to factorize multivariate data into its stationary and non-stationary components. In this paper, we propose a novel SSA algorithm (ASSA) that extracts stationary sources from multiple time series blocks. It has a globally optimal solution under certain assumptions that can be obtained by solving a generalized eigenvalue problem. Apart from the numerical advantages, we also show that compared to the existing method, fewer blocks are required in ASSA to guarantee the identifiability of the solution. We demonstrate the validity of our approach in simulations and in an application to domain adaptation..
49. Masao Joko, Yoshinobu Kawahara, Takehisa Yairi, Learning non-linear dynamical systems by alignment of local linear models, 2010 20th International Conference on Pattern Recognition, ICPR 2010 Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010, 10.1109/ICPR.2010.271, 1084-1087, 2010.11, Learning dynamical systems is one of the important problems in many fields. In this paper, we present an algorithm for learning non-linear dynamical systems which works by aligning local linear models, based on a probabilistic formulation of subspace identification. Because the procedure for constructing a state sequence in subspace identification can be interpreted as the CCA between past and future observation sequences, we can derive a latent variable representation for this problem. Therefore, as in a similar manner to the recent works on learning a mixture of probabilistic models, we obtain a framework for constructing a state space by aligning local linear coordinates. This leads to a prominent algorithm for learning non-linear dynamical systems. Finally, we apply our method to motion capture data and show how our algorithm works well..
50. Takehisa Yairi, Minoru Inui, Akihiro Yoshiki, Yoshinobu Kawahara, Noboru Takata, Spacecraft telemetry data monitoring by dimensionality reduction techniques, Proceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers, 1230-1234, 2010.01, In this paper, we consider a "data-driven" anomaly detection framework for spacecraft systems using dimensionality reduction and reconstruction techniques. This method first learns a mapping from the original data space to a low dimensional space and its reverse mapping by applying linear or non-linear dimensionality reduction algorithms to a normal training data set. After the training, it applies the learned pair of mappings to a test data set to obtain a reconstructed data set, and then evaluate the reconstruction errors. We will show the results of applying several representative linear and non-lineardimensionality reduction algorithms with this framework to the electrical power subsystem (EPS) data of actual artificial satellites..
51. Yoshinobu Kawahara, Masashi Sugiyama, Change-point detection in time-series data by direct density-ratio estimation, 9th SIAM International Conference on Data Mining 2009, SDM 2009 Society for Industrial and Applied Mathematics - 9th SIAM International Conference on Data Mining 2009, Proceedings in Applied Mathematics 133, 385-396, 2009.12, Change-point detection is the problem of discovering time points at which properties of time-series data change. This covers a broad range of real-world problems and has been actively discussed in the community of statistics and data mining. In this paper, we present a novel non-parametric approach to detecting the change of probability distributions of sequence data. Our key idea is to estimate the ratio of probability densities, not the probability densities themselves. This formulation allows us to avoid non-parametric density estimation, which is known to be a difficult problem. We provide a change-point detection algorithm based on direct density-ratio estimation that can be computed very efficiently in an online manner. The usefulness of the proposed method is demonstrated through experiments using artificial and real datasets..
52. Takehisa Yairi, Minoru Inui, Akihiro Yoshiki, Yoshinobu Kawahara, Noboru Takata, Spacecraft telemetry data monitoring by dimensionality reduction techniques, Proceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers, 1230-1234, 2010.01, In this paper, we consider a "data-driven" anomaly detection framework for spacecraft systems using dimensionality reduction and reconstruction techniques. This method first learns a mapping from the original data space to a low dimensional space and its reverse mapping by applying linear or non-linear dimensionality reduction algorithms to a normal training data set. After the training, it applies the learned pair of mappings to a test data set to obtain a reconstructed data set, and then evaluate the reconstruction errors. We will show the results of applying several representative linear and non-lineardimensionality reduction algorithms with this framework to the electrical power subsystem (EPS) data of actual artificial satellites..
53. Yoshinobu Kawahara, Kiyohito Nagano, Koji Tsuda, Jeff A. Bilmes, Submodularity cuts and applications, 23rd Annual Conference on Neural Information Processing Systems, NIPS 2009 Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference, 916-924, 2009.12, Several key problems in machine learning, such as feature selection and active learning, can be formulated as submodular set function maximization. We present herein a novel algorithm for maximizing a submodular set function under a cardinality constraint - the algorithm is based on a cutting-plane method and is implemented as an iterative small-scale binary-integer linear programming procedure. It is well known that this problem is NP-hard, and the approximation factor achieved by the greedy algorithm is the theoretical limit for polynomial time. As for (non-polynomial time) exact algorithms that perform reasonably in practice, there has been very little in the literature although the problem is quite important for many applications. Our algorithm is guaranteed to find the exact solution finitely many iterations, and it converges fast in practice due to the efficiency of the cutting-plane mechanism. Moreover, we also provide a method that produces successively decreasing upper-bounds of the optimal solution, while our algorithm provides successively increasing lower-bounds. Thus, the accuracy of the current solution can be estimated at any point, and the algorithm can be stopped early once a desired degree of tolerance is met. We evaluate our algorithm on sensor placement and feature selection applications showing good performance..
54. Yoshinobu Kawahara, Masashi Sugiyama, Change-point detection in time-series data by direct density-ratio estimation, 9th SIAM International Conference on Data Mining 2009, SDM 2009 Society for Industrial and Applied Mathematics - 9th SIAM International Conference on Data Mining 2009, Proceedings in Applied Mathematics 133, 385-396, 2009.12, Change-point detection is the problem of discovering time points at which properties of time-series data change. This covers a broad range of real-world problems and has been actively discussed in the community of statistics and data mining. In this paper, we present a novel non-parametric approach to detecting the change of probability distributions of sequence data. Our key idea is to estimate the ratio of probability densities, not the probability densities themselves. This formulation allows us to avoid non-parametric density estimation, which is known to be a difficult problem. We provide a change-point detection algorithm based on direct density-ratio estimation that can be computed very efficiently in an online manner. The usefulness of the proposed method is demonstrated through experiments using artificial and real datasets..
55. Y. Kawahara, K. Nagano, K. Tsuda, and J.A. Bilmes, Submodularity cuts and applications, Advances in Neural Information Processing Systems 22 (Proc. of NIPS'09), 916-924, 2009.12, [URL].
56. Yoshinobu Kawahara, Takehisa Yairi, Kazuo Machida, Change-point detection algorithms based on subspace methods, Transactions of the Japanese Society for Artificial Intelligence, 23, 2, 76-84, 2008.04, In this paper, we propose a class of algorithms for detecting the change-points in time-series data based on subspace identification, which is originaly a geometric approach for estimating linear state-space models generating time-series data. Our algorithms are derived from the principle that the subspace spanned by the columns of an observability matrix and the one spanned by the subsequences of time-series data are approximately equivalent. In this paper, we derive a batch-type algorithm applicable to ordinary time-series data, i.e., consisting of only output series, and then introduce the online version of the algorithm and the extension to be available with input-output time-series data. We illustrate the superior performance of our algorithms with comparative experiments using artificial and real datasets..
57. Yoshinobu Kawahara, Takehisa Yairi, Kazuo MacHida, A kernel subspace method by stochastic realization for learning nonlinear dynamical systems, 20th Annual Conference on Neural Information Processing Systems, NIPS 2006 Advances in Neural Information Processing Systems 19 - Proceedings of the 2006 Conference, 665-672, 2007.12, In this paper, we present a subspace method for learning nonlinear dynamical systems based on stochastic realization, in which state vectors are chosen using kernel canonical correlation analysis, and then state-space systems are identified through regression with the state vectors. We construct the theoretical underpinning and derive a concrete algorithm for nonlinear identification. The obtained algorithm needs no iterative optimization procedure and can be implemented on the basis of fast and reliable numerical schemes. The simulation result shows that our algorithm can express dynamics with a high degree of accuracy..
58. Yoshinobu Kawahara, Takehisa Yairi, Kazuo Machida, Change-point detection in time-series data based on subspace identification, 7th IEEE International Conference on Data Mining, ICDM 2007 Proceedings of the 7th IEEE International Conference on Data Mining, ICDM 2007, 10.1109/ICDM.2007.78, 559-564, 2007.12, In this paper, we propose series of algorithms for detecting change points in time-series data based on subspace identification, meaning a geometric approach for estimating linear state-space models behind time-series data. Our algorithms are derived from the principle that the subspace spanned by the columns of an observability matrix and the one spanned by the subsequences of time-series data are approximately equivalent. In this paper, we derive an batch-type algorithm applicable to ordinary time-series data, i.e. consisting of only output series, and then introduce the online version of the algorithm and the extension to be available with input-output time-series data. We illustrate the effectiveness of our algorithms with comparative experiments using some artificial and real datasets..
59. Yoshinobu Kawahara, Takehisa Yairi, Kazuo MacHida, A kernel subspace method by stochastic realization for learning nonlinear dynamical systems, 20th Annual Conference on Neural Information Processing Systems, NIPS 2006 Advances in Neural Information Processing Systems 19 - Proceedings of the 2006 Conference, 665-672, 2007.12, In this paper, we present a subspace method for learning nonlinear dynamical systems based on stochastic realization, in which state vectors are chosen using kernel canonical correlation analysis, and then state-space systems are identified through regression with the state vectors. We construct the theoretical underpinning and derive a concrete algorithm for nonlinear identification. The obtained algorithm needs no iterative optimization procedure and can be implemented on the basis of fast and reliable numerical schemes. The simulation result shows that our algorithm can express dynamics with a high degree of accuracy..
60. Rei Fujiki, Hideyuki Tanaka, Yoshinobu Kawahara, Takehisa Yairi, Kazuo Machida, Autonomous recognition of multiple cable topology with image, 2006 SICE-ICASE International Joint Conference 2006 SICE-ICASE International Joint Conference, 10.1109/SICE.2006.315754, 1425-1430, 2006.12, From industrial situation to ordinary life, there are a lot of cables in today's society. There, however, are not many studies that describe the topological relationship between multibple cables for autonomous operation of robotics device. In this paper, an autonomous computing way to create 3-D topological model of multiple cables using image is discussed. Cable model is described by probablity density function and optimized its parameters via EM Algorithm, that indicates the configuration and topological relationships. In order to manipulate the object cables then, depth from sensor to points are added to the unique points in topological graph structure derived from EM model. The quantitative results of basic experiment that was aimed to prove the recognition possibility via the algorithm are reported..
61. Takehisa Yairi, Yoshinobu Kawahara, Ryohei Fujimaki, Yuichi Sato, Kazuo Machida, Telemetry-mining
A machine learning approach to anomaly detection and fault diagnosis for space systems, SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology Proceedings - SMC-IT 2006 2nd IEEE International Conference on Space Mission Challenges for Information Technology, 10.1109/SMC-IT.2006.79, 466-473, 2006.12, For any space mission, safety and reliability are the most important issues. To tackle this problem, we have studied anomaly detection and fault diagnosis methods for spacecraft systems based on machine learning (ML) and data mining (DM) technology. In these methods, the knowledge or model which is necessary for monitoring a spacecraft system is (semi-)automatically acquired from the spacecraft telemetry data. In this paper, we first overview the anomaly detection / diagnosis problem in the spacecraft systems and conventional techniques such as limit-check, expert systems and model-based diagnosis. Then we explain the concept of ML/DM-based approach to this problem, and introduce several anomaly detection / diagnosis methods which have been developed by us..
62. Yuichi Sato, Yoshinobu Kawahara, Takehisa Yairi, Kazuo Machida, Visualization of spacecraft data based on interdependency between changing points in time series, 2006 SICE-ICASE International Joint Conference 2006 SICE-ICASE International Joint Conference, 10.1109/SICE.2006.315124, 3414-3418, 2006.12, A support technology for spacecraft operators is one of the important themes for reliable operation. We suggest a framework for visualization of relations among sequences based on "changing points". First, we employ auto-regression model for detecting changing points from data. And next, we apply a structure learning of dynamic Bayesian Net to the change-detected data for getting the graph structure, which stands for dependency among sequences. We applied this approach to two kinds of actual telemetry data of a communication satellite, and verified graph structures rightly showed the relation among sequences..
63. Spacecraft diagnosis method using dynamic Bayesian networks.
64. Yoshinobu Kawahara, Takehisa Yairi, Kazuo Machida, Diagnosis method for spacecraft using dynamic bayesian networks, i- SAIRAS 2005 - The 8th International Symposium on Artificial Intelligence, Robotics and Automation in Space European Space Agency, (Special Publication) ESA SP, 603, 649-656, 2005.12, Development of sophisticated anomaly detection and diagnosis methods for spacecraft is one of the important problems in space system operation. In this study, we propose a diagnosis method for spacecraft using probabilistic reasoning and statistical learning with Dynamic Bayesian Networks (DBNs). In this method, the DBNs are initially from prior-knowledge, then modified or partly re-constructed by statistical learning with operation data, as a result adaptable and in-depth diagnosis is performed by probabilistic reasoning using the DBNs. The proposed method was applied to the telemetry data that simulates the malfunction of thrusters in rendezvous maneuver of spacecraft, and the effectiveness of the method was confirmed..
65. Rei Fujiki, Hideyuki Tanaka, Yoshinobu Kawahara, Takehisa Yairi, Kazuo Machida, Autonomous recognition of multiple cable topology with image, 2006 SICE-ICASE International Joint Conference 2006 SICE-ICASE International Joint Conference, 10.1109/SICE.2006.315754, 1425-1430, 2006.12, From industrial situation to ordinary life, there are a lot of cables in today's society. There, however, are not many studies that describe the topological relationship between multibple cables for autonomous operation of robotics device. In this paper, an autonomous computing way to create 3-D topological model of multiple cables using image is discussed. Cable model is described by probablity density function and optimized its parameters via EM Algorithm, that indicates the configuration and topological relationships. In order to manipulate the object cables then, depth from sensor to points are added to the unique points in topological graph structure derived from EM model. The quantitative results of basic experiment that was aimed to prove the recognition possibility via the algorithm are reported..
66. Takehisa Yairi, Yoshinobu Kawahara, Ryohei Fujimaki, Yuichi Sato, Kazuo Machida, Telemetry-mining
A machine learning approach to anomaly detection and fault diagnosis for space systems, SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology Proceedings - SMC-IT 2006 2nd IEEE International Conference on Space Mission Challenges for Information Technology, 10.1109/SMC-IT.2006.79, 466-473, 2006.12, For any space mission, safety and reliability are the most important issues. To tackle this problem, we have studied anomaly detection and fault diagnosis methods for spacecraft systems based on machine learning (ML) and data mining (DM) technology. In these methods, the knowledge or model which is necessary for monitoring a spacecraft system is (semi-)automatically acquired from the spacecraft telemetry data. In this paper, we first overview the anomaly detection / diagnosis problem in the spacecraft systems and conventional techniques such as limit-check, expert systems and model-based diagnosis. Then we explain the concept of ML/DM-based approach to this problem, and introduce several anomaly detection / diagnosis methods which have been developed by us..
67. Yuichi Sato, Yoshinobu Kawahara, Takehisa Yairi, Kazuo Machida, Visualization of spacecraft data based on interdependency between changing points in time series, 2006 SICE-ICASE International Joint Conference 2006 SICE-ICASE International Joint Conference, 10.1109/SICE.2006.315124, 3414-3418, 2006.12, A support technology for spacecraft operators is one of the important themes for reliable operation. We suggest a framework for visualization of relations among sequences based on "changing points". First, we employ auto-regression model for detecting changing points from data. And next, we apply a structure learning of dynamic Bayesian Net to the change-detected data for getting the graph structure, which stands for dependency among sequences. We applied this approach to two kinds of actual telemetry data of a communication satellite, and verified graph structures rightly showed the relation among sequences..