Just-In-Time Modeling Research Articles

Developing multifruit global near‐infrared model to predict dry matter based on just‐in‐time modeling

AbstractModeling near‐infrared (NIR) spectral data to predict fresh fruit properties is a challenging task. The difficulty lies in creating generalized models that can work on fruits of different cultivars, seasons, and even multiple commodities of fruit. Due to intrinsic differences in spectral properties, NIR models often fail in testing, resulting in high bias and prediction errors. One current solution for achieving generalized models is to use large calibration sets measured over multiple cultivars and harvest seasons. However, current practice primarily focuses on calibration sets for single fruit commodities, disregarding the rich information available from other fruit commodities. This study aims to demonstrate the potential of locally weighted partial least‐squares an example of just‐in‐time (JIT) modeling to develop real‐time models based on calibration sets consisting of multiple fruit commodities. The study also explores JIT modeling for leveraging relevant information from other fruit commodities or adapting the model based on new samples. The application demonstrated here predicts the dry matter in fresh fruit using portable NIR spectroscopy. The results show that JIT modeling is particularly effective for multiple fruit commodities in a single calibration set. The JIT models achieved a root mean squared error of prediction (RMSEP) of 0.69% fresh weight (FW), while the traditional partial least squares (PLS) modeling RMSEP was 0.93% FW. JIT modeling can be particularly beneficial when the user has multiple fruit datasets and wants to combine them into a single dataset to utilize all the relevant information available.

The response of the Irish pharmaceutical manufacturing sector to the COVID-19 pandemic with a focus on Lean and JIT.

Just in Time (JIT) and Lean manufacturing are concepts that originated in the automotive industry and were then adopted by pharmaceutical and biopharmaceutical companies during the 1990s. However, the Covid-19 pandemic and the urgent demand for pharmaceutical treatment challenged JIT and Lean manufacturing processes. Production of Covid-19-related medicines increased, putting pressure on global supply chains and operations. This also hindered the production of medicines using the same or similar materials. Thus, questions are raised concerning JIT and Lean supply chains in the pharmaceutical industry. The present study aimed to explore (1) if material and supply constraints occurred due to the Covid-19 pandemic, (2) how companies were impacted and managed and (3) if changes are required to future proof the JIT supply chain approach for future global events. A mixed-method cross-sectional survey design was used and focused on material supply, qualification and validation in Irish pharmaceutical manufacturing sites. Employees working in the Irish pharmaceutical manufacturing industry were recruited using convenience sampling through online advertisement using the social media platform 'LinkedIn'. Quantitative data was analysed using percentages and qualitative data from free-text responses were used to add context to the quantitative survey questions. A total of 41 participants were recruited. The results suggested that the pandemic had a negative effect on material availability according to 81% of participants. This translated to delays or stoppage of production activity and was mainly handled by sourcing new materials (70%). To cope with future global crises, 60% of participants recommended more flexibility in future validation processes while 78% of participants acknowledged the importance of validating additional suppliers. A hybrid model of manufacturing and supply chain management was also a preferred approach to exclusive Lean and JIT (42%). The production of non-Covid-19 medicines was adversely affected by the Covid-19 pandemic, but the pharmaceutical industry in Ireland demonstrated resilience and collaboration in response to these challenges. This study suggests that the JIT and Lean manufacturing model should be adjusted to ensure medicine supply chains are not disrupted during future global events.

Is it more convenient to waste? Trade‐offs between grocery shopping and waste behaviors

AbstractEfforts to reduce food loss and waste are being made across the supply chain, with households targeted as one of the most wasteful nodes in the chain. In this article, we consider the impact of changing one household food management behavior: grocery shopping. Households that shop more frequently typically incur less food waste. This has resulted in a call for households to adopt a just‐in‐time (JIT) grocery shopping approach, taking smaller trips to the store more frequently. While households may be able to reduce food waste by adopting a JIT shopping approach, their willingness to shop more frequently is less clear. The purpose of this research is to examine the trade‐offs between grocery shopping frequency and food waste behaviors among U.S. households. We employ a choice experiment to determine whether consumers are willing to reduce waste by adopting a JIT shopping approach. We explore heterogeneity across households and consider the potential welfare impacts associated with moving to a JIT model of shopping. Our results indicate that, on average, consumers were averse to adding extra shopping trips to their weekly grocery shopping routines and would need to be compensated to do so (mean: $24/week for one extra trip). Consumers would need to see approximately a 12 percentage point reduction in waste to be indifferent to adding one shopping trip to their weekly routine. Spending more to waste less resulted in more welfare gains, on average, yet there is significant heterogeneity in grocery shopping preferences.

The Impact of Data Merging on the Interpretation of Cross-Project Just-In-Time Defect Models

Just-In-Time (JIT) defect models are classification models that identify the code commits that are likely to introduce defects. Cross-project JIT models have been introduced to address the suboptimal performance of JIT models when historical data is limited. However, many studies built cross-project JIT models using a pool of mixed data from multiple projects (i.e., data merging)—assuming that the properties of defect-introducing commits of a project are similar to that of the other projects, which is likely not true. In this paper, we set out to investigate the interpretation of JIT defect models that are built from individual project data and a pool of mixed project data with and without consideration of project-level variances. Through a case study of 20 datasets of open source projects, we found that (1) the interpretation of JIT models that are built from individual projects varies among projects; and (2) the project-level variances cannot be captured by a JIT model that is trained from a pool of mixed data from multiple projects without considering project-level variances (i.e., a global JIT model). On the other hand, a mixed-effect JIT model that considers project-level variances represents the different interpretations better, without sacrificing performance, especially when the contexts of projects are considered. The results hold for different mixed-effect learning algorithms. When the goal is to derive sound interpretation of cross-project JIT models, we suggest that practitioners and researchers should opt to use a mixed-effect modelling approach that considers individual projects and contexts.

Adaptive virtual metrology method based on Just-in-time reference and particle filter for semiconductor manufacturing

The prediction of the average Material Removal Rate (MRR) for Chemical Mechanical Planarization (CMP) process has been recognized to be a critical factor of Virtual Metrology (VM) modeling as well as wafer-to-wafer process control. In this paper, a novel method is proposed to dynamically predict MRR in CMP process by using a Just-in-time (JIT) model-based strategy. First, the proposed method applies a reference search procedure to query similar data samples from the historical dataset. Second, a Support Vector Regression (SVR) model is used to fuse the similar data samples with the past MRR. Finally, Particle Filter (PF) is employed to estimate and update the fusion result. The application of PF ensures that the method can track the CMP process change and continuously learn from the current dataset. Compared with static models, the proposed method, named JIT-PF model is an online dynamic method with enhanced accuracy. Compared with pure JIT model, JIT-PF model keeps the historical knowledge in the process. A public dataset is used to validate JIT-PF model with the benchmarks from the recent literature. The model outperforms other peer dynamic models and some static models from the literature.

Ensemble just-in-time model based on Gaussian process dynamical models for nonlinear and dynamic processes

Process data have a number of characteristics, such as noise, nonlinearity, process dynamics, and autocorrelation. Ideally, adaptive soft sensors would be used to solve model degradation problems resulting from changes in process characteristics. However, it is necessary to optimize the hyperparameters for each model and, depending on the state of the process, the optimal hyperparameters will change. In this study, we focus on a Gaussian process dynamical model (GPDM), a dimension-reduction method that considers all of the data characteristics. We combine a just-in-time (JIT) model and ensemble learning, and then predict y-values with multiple JIT models that have different sets of hyperparameters. Each JIT model is constructed using latent variables obtained by the GPDM. The weights of the JIT models are determined based on Bayes’ theorem in consideration of their predictive ability. Analysis of two industrial datasets confirms that the proposed model is more accurate than existing approaches.

Considering JIT in Assigning Task for Return Vehicle in Green Supply Chain

The purpose of this study was to achieve supply chain sustainability by considering Just in Time (JIT) in return vehicle usage. In response to a general increase in modern environmental awareness, consumer and government attention towards product and service compliance with environmental protection standards has increased. Consequently, manufacturers and stakeholders are pressured to use eco-friendly supply chains. In this paper, we analyzed the JIT model, a transportation network that ensure agile responses and delivery of goods in a supply chain, which reduces inventory costs. We then compared two return vehicle transportation scenarios. In the first, goods were transported from the central warehouse to the distribution base, and the return vehicle delivered recyclable packaging materials back to the central distribution warehouse. In the second scenario, goods were transported from the manufacturer to the distribution center (warehouse) more frequently, leading to reduced inventory. We then utilized the aforementioned JIT system with ILOG CPLEX12.4 to ascertain which scenario would produce the lowest carbon emissions for the lowest total cost.

Generalization and comparative studies of similarity measures for Just-in-Time modeling

Abstract Just-in-Time (JIT) modeling has become one of the most effective data analytic approaches for nonlinear time-varying process modeling. Locally weighted partial least squares method (LW-PLS) is the most representative of the JIT modeling methods. It has been widely applied to the development of the virtual sensors that can cope with abrupt changes in process characteristic as well as nonlinearity. LW-PLS has been investigated and applied successfully in various industrial processes. The accuracy of its prediction performance is however strongly dependent on how the similarity between data is determined. Usually, the Euclidean distance or the Mahalanobis distance between input data is used to determine the similarity, but they have a clear limitation, that is, they do not take into account of the relationship between the input variables and output variables when selecting data for modeling. Other advanced methods to determine the similarities with the considerations of the relationship between input and output have also been proposed in the literature in a specific form. This work further investigates the properties of these advanced methods and proposes extensions as well as points out opportunities for further research. The comparison and effectiveness of these methods along with their generalizations are demonstrated through a numerical example and an industrial application example.

Missing RRI Interpolation Algorithm based on Locally Weighted Partial Least Squares for Precise Heart Rate Variability Analysis.

The R-R interval (RRI) fluctuation in electrocardiogram (ECG) is called heart rate variability (HRV), which reflects activities of the autonomic nervous system (ANS) and has been used for various health monitoring services. Accurate R wave detection is crucial for success in HRV-based health monitoring services; however, ECG artifacts often cause missing R waves and deteriorate the accuracy of HRV analysis. The present work proposes a new missing RRI interpolation technique based on Just-In-Time (JIT) modeling. In the JIT modeling framework, a local regression model is built by weighing samples stored in the database according to the distance from a query and output is estimated only when an estimate is requested. The proposed method builds a local model and estimates missing RRI only when an RRI detection error is detected. Locally weighted partial least squares (LWPLS) is adopted for local model construction. The proposed method is referred to as LWPLS-based RRI interpolation (LWPLS-RI). The performance of the proposed LWPLS-RI was evaluated through its application to RRI data with artificial missing RRIs. We used the MIT-BIH Normal Sinus Rhythm Database for nominal RRI dataset construction. Missing RRIs were artificially introduced and they were interpolated by the proposed LWPLS-RI. In addition, MEAN that replaces the missing RRI by a mean of the past RRI data was compared as a conventional method. The result showed that the proposed LWPLS-RI improved root mean squared error (RMSE) of RRI by about 70% in comparison with MEAN. In addition, the proposed method realized precise HRV analysis. The proposed method will contribute to the realization of precise HRV-based health monitoring services.

Transforming Monograph Collections with a Model of Collections as a Service

Financial pressures, changes in scholarly communications, the rise of online content, and the ability to easily share materials have provided libraries the opportunity to rethink their collections practices. This article provides an overview of these changes and outlines a framework for viewing collections as a service. It describes how libraries have begun to use this framework to move from traditional stand-alone print monograph collections toward a user-centric, just-intime model that leverages technology and today's networked environment to efficiently connect users with resources. It also includes a discussion of what steps libraries should take to continue this evolution.

Missing RRI interpolation for HRV analysis using locally-weighted partial least squares regression.

The R-R interval (RRI) fluctuation in electrocardiogram (ECG) is called heart rate variability (HRV). Since HRV reflects autonomic nervous function, HRV-based health monitoring services, such as stress estimation, drowsy driving detection, and epileptic seizure prediction, have been proposed. In these HRV-based health monitoring services, precise R wave detection from ECG is required; however, R waves cannot always be detected due to ECG artifacts. Missing RRI data should be interpolated appropriately for HRV analysis. The present work proposes a missing RRI interpolation method by utilizing using just-in-time (JIT) modeling. The proposed method adopts locally weighted partial least squares (LW-PLS) for RRI interpolation, which is a well-known JIT modeling method used in the filed of process control. The usefulness of the proposed method was demonstrated through a case study of real RRI data collected from healthy persons. The proposed JIT-based interpolation method could improve the interpolation accuracy in comparison with a static interpolation method.

Sparse Sample Regression Based Just-In-Time Modeling (SSR-JIT): Beyond Locally Weighted Approach

In the present work, a new method for just-in-time (JIT) modeling is proposed. To develop virtual sensors or soft-sensors that can cope with changes in process characteristics as well as nonlinearity, JIT modeling such as locally weighted regression (LWR) and locally weighted partial least squares (LW-PLS) has been investigated and successfully used in various industries. The conventional JIT modeling methods predict output variables by constructing a local model by using past samples located in the neighborhood around the new target sample (query) every time when the output prediction is required; the modeling samples are selected or weighted according to the similarity between the samples and the query. The similarity is usually determined on the basis of the distance from the query. However, the use of distance does not assure the high prediction accuracy. To overcome this limitation of the conventional JIT methods, the proposed method selects past samples that are useful for constructing an accurate local model by using elastic net, which builds a sparse regression model to estimate the query, and uses the derived regression coefficients to evaluate the similarity for conducting LW-PLS. This sparse sample regression based just-in-time modeling (SSR-JIT) has a potential for surpassing the conventional distance-based JIT modeling. In fact, it was demonstrated that SSR-JIT outperformed LW-PLS in the prediction accuracy through two case studies with real industrial data.

Improvement for Large scale database-based Online Modelling of Melting Furnace

Recently, attention has been drawn by the local modeling techniques of an idea called “Just-In-Time (JIT) modeling". To apply “JIT modeling” to a large amount of database online, “Large-scale database-based Online modelling (LOM)” has been proposed. LOM is a technique that makes the retrieval of neighboring data more efficient by using stepwise method and quantization. This paper reports the improvement of LOM, a computerized sequential prediction method which uses a local regression model by PLS, on the shaft-furnace direct melting system (melting furnace). The gas temperature prediction of the furnace is done without delay.

A GENETIC ALGORITHM FOR A SIMULTANEOUS OPTIMISATION OF COST-RISK REDUCTION UNDER A JUST-IN-TIME ADAPTION

Just-In-Time (JIT) as a lean manufacturing approach plays a significant role in minimising costs and performances of products and services supplied to the global marketplace. However, there are many potential risks that cause significant disruptions to all supply chain members. This study proposes a genetic approach for optimising a novel mathematical model for simultaneously minimising the total cost of a final product and the potential risks related to these benefits. Specifically, it demonstrates the effectiveness of a genetic algorithm in optimising the JIT model developed in our previous paper. Genetic operators adopted to improve the genetic search algorithm are introduced and discussed. Experiments are carried out to evaluate the performance of the proposed algorithm using a simplified example. Comparison of four selection methods is done to define the best method that can be used in the proposed GA. The findings demonstrate the superiority of the proposed approach in the JIT system with focus on simultaneous cost-risk reduction.

Novel Just-In-Time Learning-Based Soft Sensor Utilizing Non-Gaussian Information

This brief develops a novel just-in-time (JIT) learning-based soft sensor for modeling of industrial processes. The recorded data is assumed to exhibit non-Gaussian signal components, which are extracted by a non-Gaussian regression (NGR) technique. Unlike previous work on JIT modeling which uses distance-based similarity measure for local modeling, this brief introduces a new similarity measure for the extracted non-Gaussian components using support vector data description. Based on the similarity measure, a JIT modeling procedure called NGR_JIT is proposed. Application studies on a numerical example as well as an industrial process demonstrate the proposed soft sensor can give better predictive accuracy when the predictor and response sets are non-Gaussian distributed.

スケジュール化された局所重み付き回帰によるフィードフォワード学習制御

Feedback Error Learning (FEL) has been actively studied in an adaptive control framework. When the plant is a time-variant or nonlinear system, however, conventional FEL schemes do not work any more because a single inverse model is not enough. As a remedy to this problem, Just-In-Time (JIT) modeling has been proposed, where we memorize regression data for all input/output behavior of the plant and construct local models as required in real time. However, a scheme for implementing JIT modeling, Locally Weighted Regression (LWR), has problems that it is computationally heavy to search for query point among huge amount of the past input/output data, and that regression calculation is difficult when the number of information vectors is insufficient. In view of these points, this paper proposes a new scheme. In the proposed scheme, we seek local models by a schedule parameter, instead of searching time series by input/output data. We call this scheme Scheduled LWR. By applying it to the FEL, we can reduce the search time without losing practicality and also solve the lack of sample number. We verify the effectiveness of the proposed scheme by simulation using a 2-link robot arm model.

Long-Term Industrial Applications of Inferential Control Based on Just-In-Time Soft-Sensors: Economical Impact and Challenges

Many research works on soft-sensors have been conducted. Although it is common practice to evaluate the estimation performance of soft-sensors by using industrial process data, few papers have reported long-term application results of process control using soft-sensors in real processes. In the present work, a practical configuration of an inferential control system was developed that integrated a commercial model predictive control (MPC) software and a just-in-time (JIT) soft-sensor. The developed system has adopted locally weighted partial least squares (LW-PLS) to build soft-sensors. LW-PLS is a kind of JIT modeling method that can cope with changes in process characteristics as well as process nonlinearity. Thus, LW-PLS helps engineers to reduce their burden of model maintenance, which has been recognized as the most serious problem in practice. The usefulness of the developed LW-PLS-based soft-sensors and inferential control systems is demonstrated through their successful industrial applications to a cracked gasoline (CGL) fractionator and a purification section for an acetyl plant. Inferential control systems have been used for more than a year at Showa Denko K.K. (SDK) in Japan. The operation cost and environmental burden have been significantly reduced. In the CGL fractionator, for example, about 0.6% of operation cost was cut successfully. In addition, the present work aims to describe challenges, revealed by the long-term applications of JIT soft-sensors: the parameter tuning, the selection of input variables, the definition of similarity in JIT modeling, the management of the database, and the assessment and enhancement of soft-sensor reliability.

Development of soft-sensor using locally weighted PLS with adaptive similarity measure

Recently, just-in-time (JIT) modeling, such as locally weighted partial least squares (LW-PLS), has attracted much attention because it can cope with changes in process characteristics as well as nonlinearity. Since JIT modeling derives a local model from past samples similar to a query sample, it is crucial to appropriately define the similarity between samples. In this work, a new similarity measure based on the weighted Euclidean distance is proposed in order to cope with nonlinearity and to enhance estimation accuracy of LW-PLS. The proposed method can adaptively determine the similarity according to the strength of the nonlinearity between each input variable and an output variable around a query sample. The usefulness of the proposed method is demonstrated through numerical examples and a case study of a real cracked gasoline fractionator of an ethylene production process.

Application for Large scale database-based Online Modeling of Melting Furnace

Recently, attention has been drawn by the local modeling techniques of a idea called ``Just-In-Time (JIT) modeling''. To apply ``JIT modeling'' to a large amount of database online, ``Large-scale database-based Online modeling (LOM)'' has been proposed. LOM is such a technique that makes the retrieval of neighboring data more efficient by using stepwise method and quantization. This paper reports the application of LOM, a computerized sequential prediction method which uses a local regression model, on the shaft-furnace direct melting system (melting furnace) to systematically support and enhance the operation procedure compared to conventional methods of relying only human skills and experiences.

Application of Large-Scale Database-Based Online Modeling to Plant State Long-Term Estimation

Recently, attention has been drawn to the local modeling techniques of a new idea called “Just-In-Time (JIT) modeling”. To apply “JIT modeling” to a large amount of database online, “Large-scale database-based Online Modeling (LOM)” has been proposed. LOM is a technique that makes the retrieval of neighboring data more efficient by using both “stepwise selection” and quantization. In order to predict the long-term state of the plant without using future data of manipulated variables, an Extended Sequential Prediction method of LOM (ESP-LOM) has been proposed. In this paper, the LOM and the ESP-LOM are introduced.