My current research interests are

  • dynamical models for explaining brain connectivity
    • Granger causality on state-space models
    • stability constraints in an estimation of causal models
  • system identification and machine learning techniques in solar forecasting

  • seizure detection techniques from EEG signals

  • developing a dynamical model for knee vibroartrographic signals

Research Projects

running from the newest.

  1. Chula Engineering Grant: (May 16, 2016- May 16, 2017)
    • Title: Statistical learning methods of knee joint vibroarthrographic signals for chondromalacia screening and diagnosis
    • Thai: การเรียนรู้เชิงสถิติจากสัญญาณสั่นสะเทือนข้อเข่าเพื่อการคัดกรองและช่วยวินิจฉัยโรคกระดูกอ่อนหุ้มผิวข้อเข่าเสียสภาพ
  2. Chula RA scholarship for grad student: with Anupon Pruttiakaravanich
    • Title: Sparse Dynamical Models for Investigating Brain Connectivity
  3. New Researcher Grant by NTSDA : Sep 2014 - Apr 2016 (ก.ย. 2557-เม.ย.2559)
    • Title: Learning multiple graphical models for time series: Application to fMRI time series
    • Thai: การเรียนรู้แบบจำลองเชิงกราฟสำหรับกลุ่มข้อมูลอนุกรมเวลา: งานประยุกต์กับข้อมูล fMRI


The followings are the list of my publications and some of them can be found from my Google Scholar profile.

    1. Layanun, S. Suksamosorn, and J. Songsiri, Missing-data Imputation for Solar Irradiance Forecasting in Thailand, To Appear in the Proceedings of SICE Annual Conference 2017.
    1. Raksasri and J. Songsiri, Guaranteed Stability of Autoregressive Models with Granger Causality Learned from Wald Tests, Accepted to Engineering Journal.
    1. Raksasri and J. Songsiri, Exploring Granger Causality for Time series via Wald Tests on Estimated Models with Guaranteed Stability, Proc. of Electrical Engineering Conference (EECON), 2016 (in Thai).
    1. Aranchayanont, J. Songsiri, and K. Srungboonmee, Spectral Analysis on Vibroartrographic Signal of Total Knee Arthroplasty, Proc. of IEEE Region 10 Conference (TENCON), 2016.
    1. Pruttiakaravanich and J. Songsiri, A Review on Exploring Brain Networks from fMRI Data, Engineering Journal, Vol.20, No.3, 2016 .
    1. Pruttiakaravanich and J. Songsiri, A Convex Formulation for Path Analysis in Structural Equation Modeling, Proc. of SICE Annual Conference (SICE 2016), Japan, 2016.
    1. Songsiri, Learning Multiple Granger Graphical Models via Group Fused Lasso, Proc. of the 10th Asian Control Conference (ASCC2015), Kinabalu, Malaysia, Jun 2015.
    1. Songsiri, Sparse Optimization Problems in System Identification, Engineering Journal, vol 5, issue 1, page 51-75, 2014 (in Thai).
    1. Pongrattarakul, P. Lerdkultanon and J. Songsiri, Sparse System Identification for Discovering Brain Connectivity from fMRI Time Series, Proc. of SICE Annual Conference, Japan, Sep 2013.
    1. Songsiri, Sparse autoregressive model estimation for learning Granger causality in time series, Proc. of the 38th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Canada, May 2013.
    1. Suwanwimolkul, J. Songsiri, P. Sermwuthisarn and S. Auethavekiat, L1-norm of high frequency components as a regularization term for compressed sensing reconstruction of image signals, Proc. of IEEE Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Taiwan, 2012.
    1. Songsiri, Projection onto an l1-norm ball with application to identification of sparse autoregressive models, Asean Symposium on Automatic Control, Vietnam, 2011.
    1. Songsiri and L. Vandenberghe, Topology selection in graphical models of autoregressive processes, Journal of Machine Learning Research, 11, 2671-2705, 2010.
    1. Songsiri, J. Dahl, and L. Vandenberghe, Graphical models of autoregressive processes, In: Y. Eldar and D. Palomar (Editors), Convex Optimization in Signal Processing and Communications, Cambridge University Press (2010), 89-116
    1. Songsiri, J. Dahl, and L. Vandenberghe, Maximum-likelihood estimation of autoregressive models with conditional independence constraints, Proc. of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Taiwan, 2009.
    1. Songsiri, D. Banjerdpongchai, Dynamic Models of Servo-Driven Conveyor System, Proc. of the 2004 IEEE Region 10 Conference on Analog and Digital Techniques in Electrical Engineering, 2004.
    1. Pakdeepattarakorn, P. Thamvechvitee, J. Songsiri, M. Wongsaisuwan, D.Banjerdpongchai, Dynamic Models of A Rotary Double Inverted Pendulum System, Proc. of the 2004 IEEE Region 10 Conference on Analog and Digital Techniques in Electrical Engineering, 2004.
    1. Songsiri, W. Khovidhungij, Feedback Stabilization of One-Link Flexible Robot Arms: An Infinite-Dimensional System Approach, Proc. of the 42nd SICE Annual Conference, 2003.
    1. Songsiri, W. Khovidhungij, Feedback Control of an Euler-Bernoulli Beam with a Tip Mass: An Infinite-Dimensional Control System Approach, Proc. of the 25th Thailand’s Electrical Engineering Conference, 2002 (In Thai).
    1. Songsiri, N. Phasukvanich, K. Sombatvilailert, W. Apichartwallop, W. Khovidhungij, Adaptive Control for a One-Link Flexible Robot Arms Using Wavelet Networks, Proc. of the 25th Thailand’s Electrical Engineering Conference, 1999 (In Thai).

Summer internship

Each summer I’ll take 2nd-year students to learn on a selected topic that involves programming or developing models. The lists here are shown from the most recent one.

  1. <Summer 2017> A Study of brain connectivity using statistical methods We had an SPM workshop with Dr. Witaya Sungkarat, AIMAC, Ramathibodi Hospital. Our group has learned how to process brain images using SPM and to learn a brain connectivity by Granger causality toolbox and Graphical lasso.
    • Anawin Opasatian อนาวิล โอภาสเสถียร
    • Parinthorn Manomaisaowapak ปรินทร มโนมัยเสาวภาคย์
    • Peeranat Worasart พีรณัฐ วรศาสตร์
    • Phisanu Kongkam พิษณุ คงขำ
  2. <Summer 2016> Our students have been assigned to practice writing JULIA codes.
    • ภัทริน มณีสุวรรณ์
    • รัฐพงษ์ ขันธ์ชัยธรรม
    • พลอยรุ้ง เกษร
    • วรินทร ไหลภาภรณ์
    • พิสิฐพงศ์ เทพหัสดิน ณ อยุธยา
    • รุจฐิระ ชุมแก้ว
    • โทนี่ ฟาง
  3. <Summer 2012> Pancheewa Arayacheeppreecha had performed an experiment on learning Granger causality from Google Flu data set.

Undergrad Final-Year Project

Any students who wish to do a project with me must read this instruction first.

PhD Thesis

Graphical Models of Time Series: Parameter Estimation and Topology Selection

Electrical Engineering, UCLA, 2010

Advisor: Lieven Vandenberghe