arXiv subjects

Jitkomut Songsiri

Publications and source records attributed to Jitkomut Songsiri.

8 recordsLinked to original sources

arXiv2026

Barrier-enforced multi-objective optimization for direct point and sharp interval forecasting

This paper proposes a multi-step probabilistic forecasting framework using a single neural-network based model to generate simultaneous point and interval forecasts. Our approach ensures non-crossing prediction intervals (PIs) through a model structure design that strictly satisfy a target coverage probability (PICP) while maximizing sharpness. Unlike existing methods that rely on manual weight tuning for scalarized loss functions, we treat point and PI forecasting as a multi-objective optimization problem, utilizing multi-gradient descent to adaptively select optimal weights. Key innovations include a new PI loss function based on an extended log-barrier with an adaptive hyperparameter to guarantee the coverage, a hybrid architecture featuring a shared temporal model with horizon-specific submodels, and a training strategy. The proposed loss is scale-independent and universally applicable; combined with our training algorithm, the framework eliminates trial-and-error hyperparameter tuning for balancing multiple objectives. Validated by an intra-day solar irradiance forecasting application, results demonstrate that our proposed loss consistently outperforms those in current literature by achieving target coverage with the narrowest PI widths. Furthermore, when compared against LSTM encoder-decoder and Transformer architectures--including those augmented with Chronos foundation models--our method remains highly competitive and can be seamlessly adapted to any deep learning structure.

cs.LG↗

arXiv2026

Stochastic EMS for Optimal 24/7 Carbon-Free Energy Operations

This paper proposes a two-stage stochastic optimization formulation to determine optimal operation and procurement plans for achieving a 24/7 carbon-free energy (CFE) compliance at minimized cost. The system in consideration follows primary energy technologies in Thailand including solar power, battery storage, and a diverse portfolio of renewable and carbon-based energy procurement sources. Unlike existing literature focused on long-term planning, this study addresses near real-time operations using a 15-minute resolution. A novel feature of the formulation is the explicit treatment of CFE compliance as a model parameter, enabling flexible targets such as a minimum percentage of hourly matching or a required number of carbon-free days within a multi-day horizon. The mixed-integer linear programming formulation accounts for uncertainties in load and solar generation by integrating deep learning-based forecasting within a receding horizon framework. By optimizing battery profiles and multi-source procurement simultaneously, the proposed system provides a feasible pathway for transitioning to carbon-free operations in emerging energy markets.

eess.SY↗

arXiv2024

Large width penalization for neural network-based prediction interval estimation

Forecasting accuracy in highly uncertain environments is challenging due to the stochastic nature of systems. Deterministic forecasting provides only point estimates and cannot capture potential outcomes. Therefore, probabilistic forecasting has gained significant attention due to its ability to quantify uncertainty, where one of the approaches is to express it as a prediction interval (PI), that explicitly shows upper and lower bounds of predictions associated with a confidence level. High-quality PI is characterized by a high PI coverage probability (PICP) and a narrow PI width. In many real-world applications, the PI width is generally used in risk management to prepare resources that improve reliability and effectively manage uncertainty. A wider PI width results in higher costs for backup resources as decision-making processes often focus on the worst-case scenarios arising with large PI widths under extreme conditions. This study aims to reduce the large PI width from the PI estimation method by proposing a new PI loss function that penalizes the average of the large PI widths more heavily. The proposed formulation is compatible with gradient-based algorithms, the standard approach to training neural networks (NNs), and integrating state-of-the-art NNs and existing deep learning techniques. Experiments with the synthetic dataset reveal that our formulation significantly reduces the large PI width while effectively maintaining the PICP to achieve the desired probability. The practical implementation of our proposed loss function is demonstrated in solar irradiance forecasting, highlighting its effectiveness in minimizing the large PI width in data with high uncertainty and showcasing its compatibility with more complex neural network models. Therefore, reducing large PI widths from our method can lead to significant cost savings by over-allocation of reserve resources.

cs.LG↗

arXiv2024

Developing a Thailand solar irradiance map using Himawari-8 satellite imageries and deep learning models

This paper presents an online platform showing Thailand solar irradiance map every 30 minutes, available at https://www.cusolarforecast.com. The methodology for estimating global horizontal irradiance (GHI) across Thailand relies on cloud index extracted from Himawari-8 satellite imagery, Ineichen clear-sky model with locally-tuned Linke turbidity, and machine learning models. The methods take clear-sky irradiance, cloud index, re-analyzed GHI and temperature data from the MERRA-2 database, and date-time as inputs for GHI estimation models, including LightGBM, LSTM, Informer, and Transformer. These are benchmarked with the estimate from a commercial service X by evaluation of 15-minute ground GHI data from 53 ground stations over 1.5 years during 2022-2023. The results show that the four models exhibit comparable overall MAE performance to the service X. The best model is LightGBM with an overall MAE of 78.58 W/sqm and RMSE of 118.97 W/sqm, while the service X achieves the lowest MAE, RMSE, and MBE in cloudy condition. Obtaining re-analyzed MERRA-2 data for the whole Thailand region is not economically feasible for deployment. When removing these features, the Informer model has a winning performance in MAE of 78.67 W/sqm. The obtained performance aligns with existing literature by taking the climate zone and time granularity of data into consideration. As the map shows an estimate of GHI over 93,000 grids with a frequent update, the paper also describes a computational framework for displaying the entire map. It tests the runtime performance of deep learning models in the GHI estimation process.

physics.ao-ph↗

arXiv2021

Joint learning of multiple Granger causal networks via non-convex regularizations: Inference of group-level brain connectivity

This paper considers joint learning of multiple sparse Granger graphical models to discover underlying common and differential Granger causality (GC) structures across multiple time series. This can be applied to drawing group-level brain connectivity inferences from a homogeneous group of subjects or discovering network differences among groups of signals collected under heterogeneous conditions. By recognizing that the GC of a single multivariate time series can be characterized by common zeros of vector autoregressive (VAR) lag coefficients, a group sparse prior is included in joint regularized least-squares estimations of multiple VAR models. Group-norm regularizations based on group- and fused-lasso penalties encourage a decomposition of multiple networks into a common GC structure, with other remaining parts defined in individual-specific networks. Prior information about sparseness and sparsity patterns of desired GC networks are incorporated as relative weights, while a non-convex group norm in the penalty is proposed to enhance the accuracy of network estimation in low-sample settings. Extensive numerical results on simulations illustrated our method's improvements over existing sparse estimation approaches on GC network sparsity recovery. Our methods were also applied to available resting-state fMRI time series from the ADHD-200 data sets to learn the differences of causality mechanisms, called effective brain connectivity, between adolescents with ADHD and typically developing children. Our analysis revealed that parts of the causality differences between the two groups often resided in the orbitofrontal region and areas associated with the limbic system, which agreed with clinical findings and data-driven results in previous studies.

cs.LG↗

arXiv2019

A review of feature extraction and performance evaluation in epileptic seizure detection using EEG

Since the manual detection of electrographic seizures in continuous electroencephalogram (EEG) monitoring is very time-consuming and requires a trained expert, attempts to develop automatic seizure detection are diverse and ongoing. Machine learning approaches are intensely being applied to this problem due to their ability to classify seizure conditions from a large amount of data, and provide pre-screened results for neurologists. Several features, data transformations, and classifiers have been explored to analyze and classify seizures via EEG signals. In the literature, some jointly-applied features used in the classification may have shared similar contributions, making them redundant in the learning process. Therefore, this paper aims to comprehensively summarize feature descriptions and their interpretations in characterizing epileptic seizures using EEG signals, as well as to review classification performance metrics. To provide meaningful information of feature selection, we conducted an experiment to examine the quality of each feature independently. The Bayesian error and non-parametric probability distribution estimation were employed to determine the significance of the individual features. Moreover, a redundancy analysis using a correlation-based feature selection was applied. The results showed that the following features --variance, energy, nonlinear energy, and Shannon entropy computed on a raw EEG signal, as well as variance, energy, kurtosis, and line length calculated on wavelet coefficients-- were able to significantly capture the seizures. An improvement of 4.77--13.51% in the Bayesian error from the baseline was obtained.

eess.SP↗

arXiv2019

Convex Formulation for Regularized Estimation of Structural Equation Models

Path analysis is a model class of structural equation modeling (SEM), which it describes causal relations among measured variables in the form of a multiple linear regression. This paper presents two estimation formulations, one each for confirmatory and exploratory SEM, where a zero pattern of the estimated path coefficient matrix can explain a causality structure of the variables. The original nonlinear equality constraints of the model parameters were relaxed to an inequality, allowing the transformation of the original problem into a convex framework. A regularized estimation formulation was then proposed for exploratory SEM using an l1-type penalty of the path coefficient matrix. Under a condition on problem parameters, our optimal solution is low rank and provides a useful solution to the original problem. Proximal algorithms were applied to solve our convex programs in a large-scale setting. The performance of this approach was demonstrated in both simulated and real data sets, and in comparison with an existing method. When applied to two real application results (learning causality among climate variables in Thailand and examining connectivity differences in autism patients using fMRI time series from ABIDE data sets) the findings could explain known relationships among environmental variables and discern known and new brain connectivity differences, respectively.

math.OC↗

arXiv2016

Critical comments on EEG sensor space dynamical connectivity analysis

Many different analysis techniques have been developed and applied to EEG recordings that allow one to investigate how different brain areas interact. One particular class of methods, based on the linear parametric representation of multiple interacting time series, is widely used to study causal connectivity in the brain. However, the results obtained by these methods should be interpreted with great care. The goal of this paper is to show, both theoretically and using simulations, that results obtained by applying causal connectivity measures on the sensor (scalp) time series do not allow interpretation in terms of interacting brain sources. This is because 1) the channel locations cannot be seen as an approximation of a source's anatomical location and 2) spurious connectivity can occur between sensors. Although many measures of causal connectivity derived from EEG sensor time series are affected by the latter, here we will focus on the well-known time domain index of Granger causality (GC) and on the frequency domain directed transfer function (DTF). Using the state-space framework and designing two simulation studies we show that mixing effects caused by volume conduction can lead to spurious connections, detected either by time domain GC or by DTF. Therefore, GC/DTF causal connectivity measures should be computed at the source level, or derived within analysis frameworks that model the effects of volume conduction. Since mixing effects can also occur in the source space, it is advised to combine source space analysis with connectivity measures that are robust to mixing.

q-bio.NC↗