Search

In general, an experienced operator or expert must deliver face-to-face industrial manual assembly (I-MA) training. There is a limited number and availability of expert trainers, making training less accessible to trainees. Industrial virtual training systems (I-VTS) from research communities and commercial systems are focused on providing task demonstrations with rich multimedia immersive content. These systems can significantly lessen the reliance on the expert, but they still require an expert to observe and provide feedback. This study presents the “EXpert Independent Manual AsseMbly Virtual Trainer” (EXAMINER), addressing these limitations by integrating vision-based digitization of I-MA skills, comparison of digitized operators, and providing augmented feedback assessing the training outcomes automatically. This approach enhances trainee access to training without expert dependency. The study discusses the rationale and implementation process for the EXAMINER framework and a simulated case study evaluating the EXAMINER framework’s ability to digitize and provide appropriate extrinsic augmented terminal feedback based on participant performance, marking a significant advancement in industrial training technology.

Ensuring the well-being of patients is paramount for the effective functioning of healthcare systems. This research focuses on developing a comprehensive framework aimed at improving hospital systems with a primary emphasis on enhancing patient satisfaction, specifically addressing Length of Stay (LOS) and physician assignment issues. To achieve this objective, a multi-faceted approach was employed. The data collection involved a combination of surveys, observations, and interviews, which enabled a thorough understanding of the hospital environment. A unique formula was derived to compute the satisfaction scores from the gathered survey data. Subsequently, a simulation model was developed. The research applies two distinct multi-objective optimization approaches, that is, a weighted max-min for fuzzy multi-objective optimization and the Torabi-Hassini (TH) approach to balance the importance of various objectives. The application of a multi-criteria decision guideline further streamlines the decision-making process. The outcomes of this study provide suggestions for tailored improvements for hospitals of different sizes. For large hospitals, this study indicates enhancements that positively impact both LOS and physician assignment satisfaction. Medium and small-sized hospitals are presented with two distinct choices: improvements geared toward LOS satisfaction or those focused on physician assignment satisfaction. While this study is based on a case analysis of the Ophthalmology Department at Thammasat University Hospital in Thailand, its implications extend beyond this specific department. This study offers an adaptable framework that can be applied to other hospital departments, promoting an integrated approach to healthcare system enhancement.

This paper develops a Chatbot conversational model that is aimed to achieve two goals: 1) utilizing contextual information to generate accurate and relevant responses, and 2) implementing strategies to make conversations human-like. We propose a supervised learning approach for model development and make use of a dataset consisting of multi-turn conversations for model training. In particular, we first develop a module based on deep reinforcement learning to maximize the utilization of contextual information serving as insurance for accurate response generation. Then, we incorporate the response generation process into an adversarial learning framework so as to make the generated response more human-like. Using these two phases in combination eventually results in a unified model that generates semantically appropriate responses that are also expressed naturally as human-generated in the conversation. We conducted various experiments and obtained a significant improvement compared to the baseline and other related studies.

Rescheduling is essential in real-world production to adjust schedules when significant disturbances render existing ones non-optimal. Manufacturers are often required to reschedule production tasks as quickly as possible. This paper proposes a rapid production rescheduling framework for flow shop under machine failure disturbance, called PPGA-ANNs, with the goal of minimizing makespan while ensuring sufficient computational efficiency. The framework begins with a scheduling knowledge creation phase conducted before starting production. It applies the proposed Perturbation Population Genetic Algorithm (PPGA) to solve generated scenarios of flow shop production with machine failure problems. The performance of the PPGA is compared to other research algorithms and to the standard genetic algorithm (GA). The same data set from a widely used scheduling benchmark is used for all algorithms to confirm the effectiveness of the PPGA. Artificial neural networks (ANNs) are then applied to store the scheduling knowledge obtained from the PPGA. In the knowledge implementation phase, when a machine failure problem occurs during production, the rescheduling solution is provided by the ANNs if the machine failure problem is identical to a generated scenario. Otherwise, the rescheduling solution is provided by the PPGA, using the initial solution obtained from the ANNs. Based on the experimental results, the PPGA-ANNs framework demonstrates better performance in makespans than benchmark algorithms. Additionally, it provides faster solutions, particularly for new machine failure problems. In conclusion, the proposed framework is capable of minimizing the makespan with a short computational time for real-world production, addressing the limitations of existing state-of-the-art meta-heuristic algorithms.

In the era of fierce competition under the evolution of advanced technologies, service innovation plays a decisive role in the survival of organizations. The service innovation evaluation problem becomes necessary for organizations to review their innovation performances for making according policies to develop innovative services to satisfy customer needs. This paper addresses the problem by developing a new methodology for evaluation of service innovation in banking organizations from the customer perspective. As service innovation is typically characterised by multiple indicators that are qualitative in nature with their performance being assessed subjectively by customers, we first formulate the evaluation problem of service innovation using customer surveys as that of multi-criteria decision making under uncertainty and then develop an evaluation model based on the evidential reasoning approach by means of Dempster-Shafer theory of evidence for solving it. We conducted an empirical study of three banks in Vietnam to illustrate the effectiveness and applicability of the proposed methodology. It has been shown that the evaluation outcome could provide banks with their competitive advantages compared with competitors in terms of service innovation.

The explosive growth of player-versus-player games and tournaments has catapulted esports games into a rapidly expanding force in the gaming industry. However, novice and armature players’ voices are often inadvertently overlooked because of a lack of effective analytical methods, despite the close collaboration between professional esports teams and operators. To ensure the quality of esports game services and establish a balanced gaming environment, it is essential to consider the opinions of unprofessional players and comprehensively analyze their reviews. This study proposes a new framework for analyzing esports reviews of players. It incorporates two key components: topic modeling and sentiment analysis. Utilizing the Latent Dirichlet Allocation (LDA) algorithm, the framework effectively identifies diverse topics within reviews. These identified topics were subsequently employed in a prevalence analysis to uncover the associations between players’ concerns and various esports games. Moreover, it leverages cutting-edge Bidirectional Encoder Representations from Transformers (BERT) in conjunction with a Transformer (TFM) downstream layer, enabling accurate detection of players’ sentiments toward different topics. We experimented using a dataset containing 1.6 million English reviews collected up to December 2021 for four esports games on Steam: TEKKEN7, Dota2, PUBG, and CS:GO. The experimental results demonstrated that the proposed framework can efficiently identify players’ concerns and reveal interesting keywords underlying their reviews. Consequently, it provides precise insights and valuable customer feedback to esports game operators, enabling them to enhance their services and provide an improved gaming experience for all players.

Accurate electricity demand forecasting is essential for global energy security, reducing costs, ensuring grid stability, and informing decision making in the energy sector. Disruptions often lead to unpredictable demand shifts, posing greater challenges for short-term load forecasting. Understanding electricity demand patterns during a pandemic offers insights into handling future disruptions. This study aims to develop an effective forecasting model for daily electricity peak demand, which is crucial for managing potential disruptions. This paper proposed a hybrid approach to address scenarios involving both government intervention and non-intervention, utilizing integration methods such as stepwise regression, similar day selection-based day type criterion, variational mode decomposition, empirical mode decomposition, fast Fourier transform, and neural networks with grid search optimization for the problem. The electricity peak load data in Thailand during the year of the COVID-19 situation is used as a case study to demonstrate the effectiveness of the approach. To enhance the flexibility and adaptability of the approach, the new criterion of separating datasets and the new criterion of similar day selection are proposed to perform one-day-ahead forecasting with rolling datasets. Computational analysis confirms the method’s effectiveness, adaptability, reduced input, and computational efficiency, rendering it a practical choice for daily electricity peak demand forecasting, especially in disrupted situations.

This paper introduces the demand-driven assembly line rebalancing problem (DDALRP) and proposes a non-linear, multi-objective, combinatorial optimization model to solve it. A DDALRP arises whenever the production output of the assembly line (AL) must be continuously readjusted along a planning horizon in order to satisfy as much as possible a given demand forecast; thus, dealing not with a one-time rebalance, but with a multi-period rebalance, fact that exponentially increases the complexity and combinatorial nature of the problem. Adapting or regulating the production output of the AL to a particular demand forecast or production plan is a relatively new idea in the assembly line balancing (ALB) / rebalancing (ALR) literature; and the novelty of this work is the rebalancing mechanism employed to solve the problem: we address the problem by reallocating workers to stations, taking into consideration their learning and forgetting (L&F) curves. Our proposed model was solved by implementing a genetic algorithm (GA) in 162 cases (three problem instances under 54 scenarios each), which produced useful insights about the dynamics of worker reallocation under different situations: optimistic, most-likely, pessimistic L&F coefficients; experienced and inexperienced workers; and different demand scenarios.

This paper addresses the problem of fuzzy clustering for categorical data. During the last two decades, many attempts have been made to extend the $k$ -means algorithm, making it applicable to clustering for categorical data, due to its simplicity and efficiency. However, as $k$ -means-like algorithms are local optimization methods, their clustering results are highly sensitive to initialization. In this paper, we propose to use Locality-Sensitive Hashing (LSH) to reduce the categorical data dimensions and predict the initial fuzzy clusters in low-dimensional space. Different from the existing cluster initialization optimization methods that aim to create only crisp initial clusters, the proposed method aims at predicting ‘high quality’ fuzzy clusters at the initialization step before proceeding in the $k$ -means-like fashion. The numerical results show that the proposed method yields relatively accurate results on 16 UCI datasets and outperforms all other related approaches in terms of both crisp and fuzzy clustering effectiveness.

This paper addresses the problem of multi-criteria recommendation in the hotel industry. The main focus is to analyze user preferences from different aspects based on multi-criteria ratings and develop a new multi-criteria collaborative filtering method for hotel recommendations. Particularly, the proposed recommendation system integrates matrix factorization into a deep learning model to predict the multi-criteria ratings, and then the evidential reasoning approach is adopted to model the uncertainty of those ratings represented as mass functions in Dempster-Shafer theory of evidence. Finally, Dempster’s rule of combination is utilized to aggregate those multi-criteria ratings to obtain the overall rating for recommendation. Extensive experiments conducted on a real-world dataset demonstrate the effectiveness and efficiency of the proposed method compared with other multi-criteria collaborative filtering methods.

This paper proposes a new outlier detection approach that measures the degree of outlierness for each instance in a given dataset. The proposed model utilizes a mass-based dissimilarity measure to address the weaknesses of neighbor-based outlier models while detecting local outliers in the dataset within a variety of data point densities. In particular, it first applies a hierarchical partitioning technique to generate a set of tree-like nested structure partitions for the input dataset, and then a mass-based dissimilarity measure is defined to quantify the dissimilarity between two data instances given the generated hierarchical partition structure. After that, for each data instance, a context set is obtained by gathering the neighbors around it with the k lowest mass dissimilarities, and based on those context sets, a mass-based local outlier score model is introduced to compute the outlierness for each individual instance. The proposed approach fundamentally changes the perspective of the outlier model by using the mass-based measurement instead of the distance-based functions used in most neighbor-based methods. A comprehensive experiment conducted on both synthetic and real-world datasets demonstrates that the proposed approach is not only competitive with the existing state-of-the-art outlier detection models but is also an efficient and effective alternative for local outlier detection methods.

Currently, the number of deliveries handled by transportation logistics is rapidly increasing because of the significant growth of the e-commerce industry, resulting in the need for improved functional vehicle routing measures for logistic companies. The effective management of vehicle routing helps companies reduce operational costs and increases its competitiveness. The vehicle routing problem (VRP) seeks to identify optimal routes for a fleet of vehicles to deliver goods to customers while simultaneously considering changing requirements and uncertainties in the transportation environment. Due to its combinatorial nature and complexity, conventional optimization approaches may not be practical to solve VRP. In this paper, a new optimization model based on reinforcement learning (RL) and a complementary tree-based regression method is proposed. In our proposed model, when the RL agent performs vehicle routing optimization, its state and action are fed into the tree-based regression model to assess whether the current route is feasible according to the given environment, and the response received is used by the RL agent to adjust actions for optimizing the vehicle routing task. The procedure repeats iteratively until the maximum iteration is reached, then the optimal vehicle route is returned and can be utilized to assist in decision making. Multiple logistics agency case studies are conducted to demonstrate the application and practicality of the proposed model. The experimental results indicate that the proposed technique significantly improves profit gains up to 37.63% for logistics agencies compared with the conventional approaches.

High-utility itemset mining (HUIM) has become a key phase of the pattern mining process, which has wide applications, related to both quantities and profits of items. Many algorithms have been proposed to mine high-utility itemsets (HUIs). Since these algorithms often return a large number of discovered patterns, a more compact and lossless representation has been proposed. The recently proposed closed high utility itemset mining (CHUIM) algorithms were designed to work with certain types of databases (e.g., those without probabilities). In fact, real-world databases might contain items or itemsets associated with probability values. To effectively mine frequent patterns from uncertain databases, several techniques have been developed, but there does not exist any method for mining CHUIs from this type of databases. This work presents a novel and efficient method without generating candidates, named CPHUI-List, to mine closed potential high-utility itemsets (CPHUIs) from uncertain databases. The proposed algorithm is DFS-based and utilizes the downward closure property of high transaction-weighted probabilistic mining to prune non-CPHUIs. It can be seen from the experiment evaluations that the proposed algorithm has better execution time and memory usage than the CHUI-Miner.

Multimodal transportation has become a main focus of logistics systems due to environmental concerns, road safety issues, and traffic congestion. Consequently, research and policy interests in multimodal freight transportation problems are increasing. However, there are major challenges in the development of multimodal transportation associated with inherent risks and numerous uncertainties. Since risks are potential threats that directly impact logistics and transportation systems, comprehensive risk analysis should be carried out. Risk analysis is a critical process of identifying and analyzing significant issues to help industry mitigate those risks. However, identifying and prioritizing risks is more complex because of the ambiguity of the relevant data. This study proposes the integration of the fuzzy analytic hierarchy process (FAHP) and data envelopment analysis (DEA) for identifying and assessing quantitative risks. The proposed FAHP-DEA methodology uses the FAHP method to determine the weights of each risk criterion. The DEA method is employed to evaluate the linguistic variables and generate the risk scores. The simple additive weighting (SAW) method is used to aggregate risk scores under different risk criteria into an overall risk score. A case study of the coal industry demonstrates that the proposed risk analysis model is practical and allows users to more accurately prioritize risks while selecting an optimal multimodal transportation route. The process raises user's attention to the high-priority risks and is useful for industries in optimizing a multimodal transportation route under risk decision criteria.

Machine learning and data mining techniques have been developed rapidly in recent times. In tasks such as classification, machine learning techniques have been shown to equal to and even surpass human performance. However, high performance models are usually complex, opaque and have low interpretability thus making it difficult to explain the underlying behaviors of those models that lead to the final outcomes. In many domains such as medicine and healthcare, interpretability is one of the most important factors when considering the adoption of those models. In this paper, we propose a two-stage binary classification system applicable for healthcare (or general) data that benefits from a high level of interpretability and can at the same time achieve the results comparable to commonly used classification techniques. The motivation behind the proposed system is the lack of effective classification methods for handling data generated by various distributions (such as healthcare or banking data) that can harmonize both performance and interpretability perspectives. In this work, we tackle the problem by applying divide and conquer strategy on a new disentangled representation of the underlying data. The merit of our system is evaluated by a classification experiment with a wide range of real data and popular transparent and black-box models. Furthermore, a use case in data of sepsis patients staying in the ICU (Intensive Care Unit) is depicted to prove the interpretability of the proposed model.

Daily electricity peak load forecasting is important for electricity generation capacity planning. Accurate forecasting leads to saving on excessive electricity generating capacity, while maintaining the stability of the power system. The main challenging tasks in this research field include improving forecasting accuracy and reducing computational time. This paper proposes a hybrid model involving variational mode decomposition (VMD), empirical mode decomposition (EMD), fast Fourier transform (FFT), stepwise regression, similar days selection (SD) method, and artificial neural network (ANN) for daily electricity peak load forecasting. Stepwise regression and similar days selection method are used for input variable selection. VMD and FFT are applied for data decomposition and seasonality capturing, while EMD is employed for determining an appropriate decomposition level for VMD. The hybrid model is constructed to effectively forecast special holidays, which have different patterns from other normal weekdays and weekends. The performance of the hybrid model is tested with real electricity peak load data provided by the Electricity Generating Authority of Thailand, the leading power utility state enterprise under the Ministry of Energy. Experimental results show that the hybrid model gives the best performance while saving computation time by solving the problems in input variable selection, data decomposition, and imbalance data of normal and special days in the training process.

Route selection strategy has become the main aspect in the multimodal transportation system. The transport cost and time as well as the inherent risks must be considered when determining a corrective design plan. The selection of a multimodal transportation network route is a complex multi-objective decision problem. Therefore, considering the impact factors such as the transport cost, time, and comprehensive risk assessment model were further created. This paper develops a decision support model using an analytic hierarchy process (AHP) and zero-one goal programing (ZOGP) to determine an optimal multimodal transportation route. AHP is employed to determine weights of each factor, which rely on expert judgments. The significant weights of criteria obtained from AHP can be integrated in the objective function of ZOGP which is used to generate the optimal route. The empirical case study of coal manufacturing is conducted to demonstrate the proposed model. This methodology can provide a guidance for effectively determining the multimodal transportation routes to improve performance of logistics systems.

The sensory evaluation of food quality using a machine learning approach provides a means of measuring the quality of food products. Thus, this type of evaluation may assist in improving the composition of foods and encouraging the development of new food products. However, human intervention has been often required in order to obtain labeled data for training machine learning models used in the evaluation process, which is time-consuming and costly. This paper aims at incorporating active learning into machine learning techniques to overcome this obstacle for sensory evaluation task. In particular, three algorithms are developed for sensory evaluation of wine quality. The first algorithm called Uncertainty Model (UCM) employs an uncertainty sampling approach, while the second algorithm called Combined Model (CBM) combines support vector machine with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, and both of which are aimed at selecting the most informative samples from a large dataset for labeling during the training process so as to enhance the performance of the classification models. The third algorithm called Noisy Model (NSM) is then proposed to deal with the noisy labels during the learning process. The empirical results showed that these algorithms can achieve higher accuracies in this classification task. Furthermore, they can be applied to optimize food ingredients and the consumer acceptance in real markets.

This paper proposes a novel hybrid forecasting model combining autoregressive integrated moving average (ARIMA) and artificial neural network (ANN) with incorporating moving average and the annual seasonal index for Thailand's cassava export (i.e., native starch, modified starch, and sago). The comprehensive experiments are conducted to investigate the appropriate parameters of the proposed model as well as other forecasting models compared. In particular, the proposed model is experimentally compared to the ARIMA, the ANN and the other hybrid models according to three popular prediction accuracy measures, namely mean square error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). The empirical results show that the proposed model gives the lowest error in all three measures for the native starch and the modified starch which are major cassava exported products (98% of the total export volume). However, the Khashei and Bijari's model is the best model for the sago (2% of the total export volume). Therefore, the proposed model can be used as an alternative forecasting method for stakeholders making a decision in cassava international trading to obtain better accuracy in predicting future export of native starch and modified starch which are the majority of the total export.

This study presents a class-based approach developed to evaluate the financial performance of companies that have undergone public listing on the stock market. By employing both statistical analysis and machine learning methods, the models consider two important determinants, which are the company's internal capability determinants prior to going public and the amount of funds raised through the Initial Public Offering (IPO) to predict the company’s financial performance after joining the stock market. The study demonstrates that the machine learning method (random forest algorithm) outperforms the statistical method (logistic regression) in predicting financial performance. The findings also reveal that certain determinants significantly influence the predicted financial performance in a specific period. Furthermore, the study examines the impact of IPO funds on financial performance and observes that while the first year after listing does not exhibit a significant effect, a subsequent positive correlation emerges in the subsequent two to three years, up to a certain threshold, with excessive funds potentially leading to adverse effects. Overall, the predictive models provide valuable insights for companies, enabling them to prioritize resources towards significant determinants in a specific relative year, make informed decisions, and enhance their long-term success in the stock market.

Decision-making for shelter location-allocation influences the success of disaster response and affects the security of victims. This paper proposes a multi-objective optimization model for determining shelter location-allocation in response to humanitarian relief logistics. Three objective functions are formulated to improve both efficiency and effectiveness. The first objective is to minimize total costs, including fixed costs for opening the shelters, transportation costs, and service costs. The second objective is to minimize the total time for evacuating victims from all affected areas to allocated shelters. The third objective is to minimize the number of shelters required to provide thorough service to victims. The Epsilon Constraint method (EC) and Goal Programming (GP) are employed for solving the proposed model. The applicability of the proposed model is validated through a case study of flooding in Surat Thani, Thailand. The Pareto efficiency obtained from solving the proposed model is compared with current shelter location-allocation plans determined by the government sector. The comparisons reveal that the results obtained from solving the proposed model outperform current shelter location-allocation plans. Furthermore, the results of this study could provide an advantage to decision-makers considering appropriate strategies for disaster response.