Data-driven robust optimization based on kernel learning

Vigilance estimation using truncated l1 distance kernel-based sparse representation regression with physiological signals

BACKGROUND

With a large number of accidents caused by the decline in the vigilance of operators, finding effective automatic vigilance monitoring methods is a work of great significance in recent years. Based on physiological signals and machine learning algorithms, researchers have opened up a path for objective vigilance estimation.

METHODS

Sparse representation (SR)-based recognition algorithms with excellent performance and simple models are very promising approaches in this field. This paper aims to study the adaptability and performance improvement of truncated l1 distance (TL1) kernel on SR-based algorithm in the context of physiological signal vigilance estimation. Compared with the traditional radial basis function (RBF), the TL1 kernel has good adaptiveness to nonlinearity and is suitable for the discrimination of complex physiological signals. A recognition framework based on TL1 and SR theory is proposed. Firstly, the inseparable physiological features are mapped to the reproducing kernel Kreĭn space through the infinite-dimensional projection of the TL1 kernel. Then the obtained kernel matrix is converted into the symmetric positive definite matrix according to the eigenspectrum approaches. Finally, the final prediction result is obtained through the sparse representation regression process.

RESULTS

We verified the performance of the proposed framework on the popular SEED-VIG dataset containing physiological signals (electroencephalogram and electrooculogram) associated with vigilance. In the experimental results, the TL1 kernel is superior to the RBF kernel in both performance and kernel parameter stability.

CONCLUSIONS

This demonstrates the effectiveness of the TL1 kernel in distinguishing physiological signals and the excellent vigilance estimation capability of the proposed framework. Moreover, the contribution of our research motivates the development of physiological signal recognition based on kernel methods.

Adversarial Transferred Data-Assisted Soft Sensor for Enhanced Multigrade Quality Prediction

Although recent transfer learning soft sensors show promising applications in multigrade chemical processes, good prediction performance mainly relies on available target domain data, which is difficult to achieve for a start-up grade. Additionally, only employing a single global model is inadequate to characterize the inner relationship of process variables. A just-in-time adversarial transfer learning (JATL) soft sensing method is developed to enhance multigrade process prediction performance. The distribution discrepancies of process variables between two different operating grades are first reduced by the ATL strategy. Subsequently, by applying the just-in-time learning approach, a similar data set is selected from the transferred source data for reliable model construction. Consequently, with the JATL-based soft sensor, quality prediction of a new target grade is implemented without its own labeled data. Experimental results on two multigrade chemical processes validate that the JATL method can give rise to the improvement of model performance.

Artificial Intelligence and Its Application in Optimization under Uncertainty

Nowadays, the increase in data acquisition and availability and complexity around optimization make it imperative to jointly use artificial intelligence (AI) and optimization for devising data-driven and intelligent decision support systems (DSS). A DSS can be successful if large amounts of interactive data proceed fast and robustly and extract useful information and knowledge to help decision-making. In this context, the data-driven approach has gained prominence due to its provision of insights for decision-making and easy implementation. The data-driven approach can discover various database patterns without relying on prior knowledge while also handling flexible objectives and multiple scenarios. This chapter reviews recent advances in data-driven optimization, highlighting the promise of data-driven optimization that integrates mathematical programming and machine learning (ML) for decision-making under uncertainty and identifies potential research opportunities. This chapter provides guidelines and implications for researchers, managers, and practitioners in operations research who want to advance their decision-making capabilities under uncertainty concerning data-driven optimization. Then, a comprehensive review and classification of the relevant publications on the data-driven stochastic program, data-driven robust optimization, and data-driven chance-constrained are presented. This chapter also identifies fertile avenues for future research that focus on deep-data-driven optimization, deep data-driven models, as well as online learning-based data-driven optimization. Perspectives on reinforcement learning (RL)-based data-driven optimization and deep RL for solving NP-hard problems are discussed. We investigate the application of data-driven optimization in different case studies to demonstrate improvements in operational performance over conventional optimization methodology. Finally, some managerial implications and some future directions are provided.

Big data analytics opportunities for applications in process engineering

Big data is an expression for massive data sets consisting of both structured and unstructured data that are particularly difficult to store, analyze and visualize. Big data analytics has the potential to help companies or organizations improve operations as well as disclose hidden patterns and secret correlations to make faster and intelligent decisions. This article provides useful information on this emerging and promising field for companies, industries, and researchers to gain a richer and deeper insight into advancements. Initially, an overview of big data content, key characteristics, and related topics are presented. The paper also highlights a systematic review of available big data techniques and analytics. The available big data analytics tools and platforms are categorized. Besides, this article discusses recent applications of big data in chemical industries to increase understanding and encourage its implementation in their engineering processes as much as possible. Finally, by emphasizing the adoption of big data analytics in various areas of process engineering, the aim is to provide a practical vision of big data.

Prediction of cooling moisture content after cut tobacco drying process based on a particle swarm optimization-extreme learning machine algorithm

The stability of the moisture content of the cigarette is an important index to evaluate the quality of the cigarette. The cooling moisture content after cut tobacco drying process is a key factor affecting the stability of the moisture content of the cigarette. In order to realize its accurate prediction and ensure the stability, in Honghe cigarette factory, a cooling moisture content prediction model is built based on a particle swarm optimization-extreme learning machine (PSO-ELM) algorithm via the historical production data. Besides, the proposed PSO-ELM algorithm is also compared with multiple linear regression (MLR), support vector machine (SVM) and the traditional extreme learning machine (ELM) algorithms in the same data set on the prediction. The prediction accuracy of PSO-ELM method is the highest and the average error of the prediction standard is the lowest. The results indicated the proposed method can achieve a better prediction performance over compared methods and it provides a new method to realize the prediction of the cooling moisture content after cut tobacco drying process.

A novel two-phase robust portfolio selection and optimization approach under uncertainty: A case study of Tehran stock exchange

Portfolio construction is one of the most critical problems in financial markets. In this paper, a new two-phase robust portfolio selection and optimization approach is proposed to deal with the uncertainty of the data, increasing the robustness of investment process against uncertainty, decreasing computational complexity, and comprehensive assessments of stocks from different financial aspects and criteria are provided. In the first phase of this approach, all candidate stocks’ efficiency is measured using a robust data envelopment analysis (RDEA) method. Then in the second phase, by applying robust mean-semi variance-liquidity (RMSVL) and robust mean-absolute deviation-liquidity (RMADL) models, the amount of investment in each qualified stock is determined. Finally, the proposed approach is implemented in a real case study of the Tehran stock exchange (TSE). Additionally, a sensitivity analysis of all robust models of this study is examined. Illustrative results show that the proposed approach is effective for portfolio selection and optimization in the presence of uncertain data.

Data envelopment analysis and robust optimization: A review

This paper reviews the milestone approaches for handling uncertainty in data envelopment analysis (DEA). This paper presents the detailed classifications of robust data envelopment analysis (RDEA). RDEA is appropriate for measuring the efficiencies of decision‐making units in the presence of the data and distributional uncertainties. This paper reviews scenario‐based and uncertainty set of DEA models. It covers 73 studies from 2008 to 2019. The paper concludes with suggestions about the guidelines for future researches in the field of RDEA.

Data-Driven Robust Optimization for Steam Systems in Ethylene Plants under Uncertainty

In an ethylene plant, steam system provides shaft power to compressors and pumps and heats the process streams. Modeling and optimization of a steam system is a powerful tool to bring benefits and save energy for ethylene plants. However, the uncertainty of device efficiencies and the fluctuation of the process demands cause great difficulties to traditional mathematical programming methods, which could result in suboptimal or infeasible solution. The growing data-driven optimization approaches offer new techniques to eliminate uncertainty in the process system engineering community. A data-driven robust optimization (DDRO) methodology is proposed to deal with uncertainty in the optimization of steam system in an ethylene plant. A hybrid model of extraction–exhausting steam turbine is developed, and its coefficients are considered as uncertain parameters. A deterministic mixed integer linear programming model of the steam system is formulated based on the model of the components to minimize the operating cost of the ethylene plant. The uncertain parameter set of the proposed model is derived from the historical data, and the Dirichlet process mixture model is employed to capture the features for the construction of the uncertainty set. In combination with the derived uncertainty set, a data-driven conic quadratic mixed-integer programming model is reformulated for the optimization of the steam system under uncertainty. An actual case study is utilized to validate the performance of the proposed DDRO method.