@article{Jarumaneeroj2025,

title = {Eco-friendly long-haul perishable product transportation with multi-compartment vehicles},

author = {Pisit Jarumaneeroj and Supisara Krairiksh and Puwadol Oak Dusadeerungsikul and Dong Li and Çağatay Iris},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85217719766&doi=10.1016%2fj.cie.2025.110934&partnerID=40&md5=c69a7e194c2581a7efb0eaa0834acf4f},

doi = {10.1016/j.cie.2025.110934},

issn = {03608352},

year  = {2025},

date = {2025-01-01},

journal = {Computers and Industrial Engineering},

volume = {202},

publisher = {Elsevier Ltd},

abstract = {Multi-compartment refrigerated vehicles (MCVs) have been recently utilized in long-haul perishable product transportation, thanks to their flexibility in storage capacity with different temperature settings. To better understand trade-offs between economic and environmental aspects of long-haul transportation of perishable products with refrigerated vehicles, a Multi-Compartment Vehicle Loading and Scheduling Problem (MCVLSP) that minimizes three objectives—transportation cost, carbon emissions, and total food loss—is herein solved by mathematical modeling and genetic algorithm (GA) approaches. Our computational results indicate that larger MCVLSP instances cannot be solved to optimality using the mathematical model with off-the-shelf optimization software packages. The proposed GA delivers strong computational performance for MCVLSP with respect to solution quality and computational time. We find that, among three objectives, the environmental objective is the most sensitive one as slight difference in either vehicle loading or scheduling decisions could result in solutions with significantly varying carbon emissions. Moreover, solutions with fewer MCVs are not necessarily environmentally sustainable. Rather, deploying larger MCV fleets could potentially result in lower carbon emissions and food weight loss for perishable products—albeit a slight increase in total transportation cost—due to the changes in vehicle loading and scheduling decisions. © 2025 The Author(s)},

note = {Cited by: 0; All Open Access, Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Cao2025,

title = {Data-driven resilience analysis of the global container shipping network against two cascading failures},

author = {Yuhao Cao and Xuri Xin and Pisit Jarumaneeroj and Huanhuan Li and Yinwei Feng and Jin Wang and Xinjian Wang and Robyn Pyne and Zaili Yang},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85212391651&doi=10.1016%2fj.tre.2024.103857&partnerID=40&md5=d4cd91c89a48a5c737afcac571e12bc5},

doi = {10.1016/j.tre.2024.103857},

issn = {13665545},

year  = {2025},

date = {2025-01-01},

journal = {Transportation Research Part E: Logistics and Transportation Review},

volume = {193},

publisher = {Elsevier Ltd},

abstract = {Being a fundamental link in the global supply chain and logistics system, the global container shipping network (GCSN) is highly interconnected, which causes the network resilience challenges by the cascading failures triggered by extreme events (e.g., COVID-19 and regional conflicts). Within this dynamic process, the load redistribution behaviour is the core countermeasure for the propagation of cascading failures, however the diversified mechanism has not been systematically studied. To fill in these gaps, this study aims to develop a pioneering resilience analysis framework against cascading failures, to comprehensively explore the impact of port disruptions on the shipping network resilience. By pioneering the influence analysis of port betweenness, weight, and connectivity on load determination and target selection, a port importance assessment method is applied as the foundation for load redistribution decisions. Based on the global service routes data from 2020 to 2023, the GCSN resilience against the sequential cascading failures of 686 ports worldwide is quantified by three metrics. A scenario analysis is conducted to simulate the effects of cascading failures triggered by 5 historical port disruption events (e.g., the COVID-19 port lockdowns and the 2024 bridge collision at Baltimore port) on resilience of the network. Determining the identified critical capacity threshold is pivotal for effectively enhancing the system's resilience and preventing the likelihood of cascading failures. Additionally, this study offers cutting-edge perspectives to the global shipping industry stakeholders. It presents distinct strategies and preferences, offering actionable advice for port authorities in their risk response decisions. Moreover, this study delivers an economic rationale and critical evaluations, instrumental for the strategic maintenance, planning and augmentation of port infrastructures to prevent unforeseen risks. © 2024 The Author(s)},

note = {Cited by: 20; All Open Access, Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Xin2025191,

title = {Vulnerability assessment of International Container Shipping Networks under national-level restriction policies},

author = {Xuri Xin and Yuhao Cao and Pisit Jarumaneeroj and Zaili Yang},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105001506707&doi=10.1016%2fj.tranpol.2025.03.020&partnerID=40&md5=d8c405f7ceba6804f4a0adbda508eaaa},

doi = {10.1016/j.tranpol.2025.03.020},

issn = {0967070X},

year  = {2025},

date = {2025-01-01},

journal = {Transport Policy},

volume = {167},

pages = {191 – 209},

publisher = {Elsevier Ltd},

abstract = {This study develops a systematic methodology to assess the vulnerability of International Container Shipping Networks (ICSNs) amid national-level restriction policies potentially caused by the increasing international trade disputes and health crises. It designed a holistic vulnerability assessment framework that explores the impact of two disruption scenarios—direct and complete trade restrictions, which incorporates new measures of vulnerability and centrality to evaluate a country's susceptibility to international restrictions and its impact on other countries' ICSNs. Subsequently, correlation and dependence analyses are conducted to explore relationships between vulnerability/centrality and eight international network characteristics, identifying key factors. Finally, an enhanced k-means algorithm classifies the impact degrees of various countries' restrictive policies on a country of interest, and examines the effects of both partial and collective disruptions of identified critical countries. Experimental results demonstrate the effectiveness in revealing the varied impacts of different restrictive policies on distinct performance metrics, identifying critical factors that influence vulnerability and centrality, and precisely classifying different countries' restriction impacts to help identify key influential countries. These insights not only deepen understanding of ICSNs under national-level disruptions but also aid in optimizing international shipping from an operational perspective and providing strategic guidance for proactive disruption management from a preventative standpoint. © 2025 The Authors},

note = {Cited by: 3},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Yudha2025,

title = {A systematic review and bibliometric analysis of the impacts of COVID-19 on economy and mobility from the geospatial data perspective},

author = {Alfan Kurnia Yudha and Natt Leelawat and Jing Tang},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105005182205&doi=10.1016%2fj.rineng.2025.105282&partnerID=40&md5=b0da3f68fe3fad4c74a18654be3ac488},

doi = {10.1016/j.rineng.2025.105282},

issn = {25901230},

year  = {2025},

date = {2025-01-01},

journal = {Results in Engineering},

volume = {26},

publisher = {Elsevier B.V.},

abstract = {The COVID-19 pandemic has greatly impacted the global economy, human health, and daily life. The World Health Organization declared it a pandemic on March 11, 2020. By May 2023, it had caused over seven million deaths. Until now, its economic and social effects are still felt. This systematic review and bibliometric analysis focuses on how COVID-19 has affected the economy and mobility using geospatial data. Geospatial data from sensors, social media, mobile apps, cars, and remote sensing give us near-real-time insights into people's behaviors and perceptions during the pandemic. The study examines how COVID-19 spread over time and space to help understand and reduce its impact. Even with challenges in combining different datasets, spatial analysis shows patterns of how humans and the pandemic interact. The finding answers key questions: How did COVID-19 affect economic activities and mobility? What common patterns do geospatial data show during the pandemic? By identifying common geospatial datasets and analyzing research trends, the study provides insights for policymakers and researchers to better prepare for future pandemics. This review helps understand the complex systems of pandemics and their effects on society using geospatial big data. Notably, the findings show that nighttime light intensity and mobile phone mobility data were the most consistently used indicators to monitor pandemic-driven disruptions and recovery, captured shifts in behavior and compliance with public health measures, offering a critical data source for real-time health surveillance, enabling health experts to better understand population responses, and adaptive policy interventions. © 2025},

note = {Cited by: 1},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Laosunthara2025,

title = {Initial observations and immediate lessons learned from Thailand's response to the 2025 Mandalay earthquake},

author = {Ampan Laosunthara and Kodchakorn Krutphong and Natt Leelawat and Wongsa Wararuksajja and Naruethep Sukulthanasorn and Anawat Suppasri and Ratchaneekorn Thongthip and Chatpan Chintanapakdee},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105010414313&doi=10.1016%2fj.ijdrr.2025.105675&partnerID=40&md5=0fc5e58eef5451c6ec4fbe6f61886754},

doi = {10.1016/j.ijdrr.2025.105675},

issn = {22124209},

year  = {2025},

date = {2025-01-01},

journal = {International Journal of Disaster Risk Reduction},

volume = {127},

publisher = {Elsevier Ltd},

abstract = {On March 28, 2025, a magnitude 7.7 earthquake struck central Myanmar, with tremors widely felt across Thailand. Bangkok, in particular, experienced severe disruption due to long-period ground motion (LPGM), highlighting the city's vulnerability to distant seismic events. This earthquake represents the most wide-reaching seismic disruption to affect Thailand since the 2004 Aceh Tsunami. This study presents preliminary observations of Thailand's response during the critical first 72 h, focusing on structural damage, emergency coordination, evacuation challenges, and public risk communication. In Bangkok, the collapse of a 30-story construction site resulted in 19 fatalities and 78 missing persons. Vulnerable groups, including people with limited mobility, faced heightened risks due to inaccessible infrastructure. Hospitals struggled to maintain operations while evacuating patients, and misinformation on social media intensified public confusion. This research identifies key policy implications: enhancing building standards to address non-structural elements, institutionalizing regular evacuation drills for high-rise buildings, and accelerating the deployment of nationwide cell broadcast alert systems. The 2025 Mandalay earthquake revealed that seismic events beyond national borders can cascade into multi-dimensional urban crises. The findings underscore the urgency of integrated risk governance frameworks and strengthened regional collaboration across Southeast Asia to prepare for and mitigate cross-border disaster impacts. © 2025 Elsevier Ltd},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Pongsethpaisal202511,

title = {Employing Neuroevolution of Augmenting Topologies (NEAT) in Linear Multi-Echelon Inventory Systems},

author = {Yanvaroj Pongsethpaisal and Naragain Phumchusri and Paveena Chaovalitwongse},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105002468604&doi=10.4186%2fej.2025.29.3.11&partnerID=40&md5=d7799e5a5f4fdc7c974b4d5f64f797af},

doi = {10.4186/ej.2025.29.3.11},

issn = {01258281},

year  = {2025},

date = {2025-01-01},

journal = {Engineering Journal},

volume = {29},

number = {3},

pages = {11 – 26},

publisher = {Chulalongkorn University, Faculty of Fine and Applied Arts},

abstract = {Reinforcement learning has emerged as a leading algorithmic approach due to its successful applications across various domains. While many implementations favour the model-free approach for its aptitude for handling complex problems, its learning curve tends to be slower. Given the intricacies of the Linear Multi-Echelon Inventory System, a model-based approach might be more fitting, offering faster learning rates. This study seeks to integrate Neuroevolution of Augment Topologies (NEAT) – a hybrid of model-based reinforcement learning and evolutionary algorithms – into such an inventory system. Furthermore, the research delves into hyperparameter tuning, experimenting with seven specific hyperparameters to discern the most efficient combination and understand their inter-play. Benchmarking against the model-free Proximal Policy Optimisation (PPO) serves as a measure of NEAT’s effectiveness. Findings indicate that when optimally tuned, NEAT can slash total costs by 25.02% compared to PPO. Impressively, NEAT achieves this peak performance in a mere 1,000 generations, significantly outpacing PPO’s learning trajectory. © 2025, Chulalongkorn University, Faculty of Fine and Applied Arts. All rights reserved.},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Wongkamphu202527,

title = {Hybrid Approaches to Machine Learning for Improved Battery Sales Forecasting: A Case Study in Thailand},

author = {Santi Wongkamphu and Naragain Phumchusri},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105000148099&doi=10.4186%2fej.2025.29.2.27&partnerID=40&md5=ddfdc08c3e9395cf76d0a3106ac47ba8},

doi = {10.4186/ej.2025.29.2.27},

issn = {01258281},

year  = {2025},

date = {2025-01-01},

journal = {Engineering Journal},

volume = {29},

number = {2},

pages = {27 – 43},

publisher = {Chulalongkorn University, Faculty of Fine and Applied Arts},

abstract = {Battery sales forecasting is a critical component of demand planning in the automotive battery industry, directly influencing production, inventory management, and supply chain optimization. This study presents a comprehensive evaluation of traditional forecasting methods and machine learning techniques to predict monthly sales for a battery manufacturer in Thailand. Utilizing a dataset of monthly sales for the 10 best-selling products from January 2018 to December 2023, the research investigates the performance of traditional models such as Holt’s Linear Trend, Holt-Winters Seasonal, ARIMA, SARIMA, and SARIMAX. Advanced machine learning approaches, including Long Short-Term Memory (LSTM) networks and Artificial Neural Networks (ANN), are also explored. Additionally, hybrid models combining traditional and machine learning techniques are developed to leverage their respective strengths. The study integrates external factors such as economic indicators, industry-specific variables, and lagged data during feature selection to enhance predictive accuracy. Model performance is rigorously evaluated using Mean Absolute Percentage Error (MAPE). The results demonstrate that the hybrid ANN-LSTM model achieves the highest accuracy, with an average MAPE of 8.83%, significantly outperforming individual models, including the best-performing traditional model, ANN, at 9.43%. This research contributes to the field by providing a robust analytics framework that integrates traditional and advanced machine learning methodologies, offering actionable insights for battery sales forecasting and enhancing decision-making processes in the automotive industry. © 2025, Chulalongkorn University, Faculty of Fine and Applied Arts. All rights reserved.},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Binsriavanich202560,

title = {An analysis of retail promotional pricing effectiveness using agent-based modeling},

author = {Chutima Binsriavanich and Naragain Phumchusri},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85211935209&doi=10.1057%2fs41272-024-00512-7&partnerID=40&md5=fb87bdd84c73aeee7fa60475fb557f63},

doi = {10.1057/s41272-024-00512-7},

issn = {14766930},

year  = {2025},

date = {2025-01-01},

journal = {Journal of Revenue and Pricing Management},

volume = {24},

number = {1},

pages = {60 – 79},

publisher = {Palgrave Macmillan},

abstract = {In contemporary urban contexts, retail establishments have emerged as essential components of city life, engaging in fierce competition to capture consumer attention and augment their financial gains. Implementing a price promotion strategy is essential for efficaciously appealing customers. Nonetheless, the complex interaction between consumer preferences and product attributes, particularly in environments characterized by competitive product offerings, complicates the development of effective promotional strategies. This paper aims to present an agent-based simulation model for capturing the results of strategic approaches for retails offering competitive products, thereby sidestepping the need for empirical testing or data collection in real-world settings. In this model, consumer decision-making processes are initially influenced by two primary factors: the effectiveness of advertising and the impact of word-of-mouth communication. Subsequent decisions are then depending on the degree of price reduction encountered in-store. The simulation assesses various promotional tactics, examining the depth of price reductions, the frequency and timing of promotions, and the resultant impact on store profitability. The outcomes reveal that distinct strategies yield varying levels of effectiveness depending on the price elasticity of products. Moreover, non-overlapping promotional happenings yield superior profit margins as compared to concurrent promotions. The insights garnered from this study are anticipated to provide helpful guidance for future strategic planning for retails. © The Author(s), under exclusive licence to Springer Nature Limited 2024.},

note = {Cited by: 1},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Bodhidatta2025,

title = {Understanding unnecessary stops and police use of force in NYPD Stop, Question, and Frisk with machine learning techniques},

author = {Passiri Bodhidatta and Daricha Sutivong},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-86000624761&doi=10.1007%2fs10506-025-09444-y&partnerID=40&md5=cb643b7adb5d47c6b58bb0166c8c0e0e},

doi = {10.1007/s10506-025-09444-y},

issn = {09248463},

year  = {2025},

date = {2025-01-01},

journal = {Artificial Intelligence and Law},

publisher = {Springer Nature},

abstract = {Even though the New York Police Department (NYPD) reform in 2013 led to a substantial reduction in the total number of stops, unnecessary stops and weapon use against innocent citizens remain critical issues. This study analyzes stop-and-frisk records during 2014 – 2019 using tree-based machine learning approaches along with logistic regression and Multi-Layer Perceptron (MLP) models, in order to discover patterns and insights. By developing predictive models for both suspect convictions and the level of force applied by police, this study provides a basis for a discussion whether weapon usage aligns with indicators of guilt or conviction. Findings show that XGBoost outperforms other machine learning techniques in predicting both conviction and the level of force used. Key factors associated with a suspect’s conviction include weapon possession, carrying suspicious objects, and trespassing. However, an excessive number of unnecessary stops appear to be associated with inaccurate assumptions about suspects’ weapon possession, which are also linked to police gunfire against innocent citizens. Refining suspicion criteria for Criminal Possession of Weapon and suspect actions could help reduce unnecessary stops and excessive force. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Yoonirundorn2025,

title = {Predicting Bearing Capacity Factors of Multiple Shallow Foundations Using Finite Element Limit Analysis and Machine Learning Approaches},

author = {Kittiphan Yoonirundorn and Teerapong Senjuntichai and Angsumalin Senjuntichai and Suraparb Keawsawasvong},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85219550535&doi=10.1007%2fs40515-025-00560-5&partnerID=40&md5=f64787ca0b73879af42609a3a7481b38},

doi = {10.1007/s40515-025-00560-5},

issn = {21967202},

year  = {2025},

date = {2025-01-01},

journal = {Transportation Infrastructure Geotechnology},

volume = {12},

number = {3},

publisher = {Springer},

abstract = {This study presents the prediction of bearing capacity factors for multiple square shallow foundations in cohesive-frictional soils, utilizing finite element limit analysis (FELA), and machine learning (ML) techniques. The footings are considered to be of equal spacing s, and constant width B. Results from FELA, based on upper and lower bound theorems, were presented in dimensionless charts, showing the correlation between three bearing capacity factors (Nc, Nq, and Nγ), the angle of internal friction (ϕ), and the spacing ratio (S/B). ML techniques, namely ANN and XGBoost, were employed to estimate bearing capacity factors using ϕ and S/B as inputs. The developed models were assessed against FELA data through various metrics, with both ML models showing good agreement with FELA. Among the two models, XGBoost demonstrates slightly higher consistency with FELA data, with R2 values exceeding 99.9% across all datasets. Besides, a feature importance analysis identified the friction angle as the dominant parameter with permutation importance of more than 85% in the estimation of three bearing capacity factors. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Sangjinda2025,

title = {Optimized ANN-based surrogate models for evaluating the stability of trapdoors in Hoek‒Brown rock masses},

author = {Kongtawan Sangjinda and Suraparb Keawsawasvong and Pitthaya Jamsawang and Angsumalin Senjuntichai and Teerapong Senjuntichai},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85213036933&doi=10.1007%2fs12145-024-01550-w&partnerID=40&md5=bf614b214226b941490f5886137f6df3},

doi = {10.1007/s12145-024-01550-w},

issn = {18650473},

year  = {2025},

date = {2025-01-01},

journal = {Earth Science Informatics},

volume = {18},

number = {1},

publisher = {Springer Science and Business Media Deutschland GmbH},

abstract = {One of the main concerns of underground engineering works, such as subsurface structures and mining in rock formations, is ensuring their safety. The objective of this work is to present the stability analysis of trapdoors in Hoek-Brown (HB) rock masses, and to propose an innovative soft-computing approach utilizing optimized ANN-based surrogate models for evaluating the stability of trapdoors. The stability factor serves as a key parameter in formulating both lower bound (LB) and upper bound (UB) solutions for two-dimensional trapdoor through the finite element limit analysis (FELA). Furthermore, this paper introduces hybrid machine learning models that integrate artificial neural networks (ANNs) with diverse optimization algorithms (OAs), such as the ant lion optimizer (ALO), imperialist competitive algorithm (ICA), shuffled complex evolution algorithm (SCE), and teaching learning-based optimization (TLBO). Rigorous optimization ensures the accuracy and efficiency of these models in capturing the intricate dynamics of stability investigation. The performance of the proposed models is rigorously evaluated using metrics, convergence curves, regression plot, Taylor diagram, and rank analysis. Consequently, The ANN-SCE model achieved the highest performance (Testing Set), with R2 of 0.9630, MAE of 2.7416, RMSE of 0.3696, VAF(%) of 96.2834, IOS of 0.0269, and RSR of 0.0172, respectively. These results demonstrate the accuracy and efficiency of the proposed models in capturing the complex dynamics of stability investigations. This research provides practical tools for engineers to assess road stability, plan mitigation for sinkholes, and account for rock strength using the Hoek-Brown criterion. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.},

note = {Cited by: 4},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Phulsawat202527,

title = {Data-Driven Solutions for Backcalculating Elastic Moduli of Flexible Pavements from FWD Test},

author = {Barami Phulsawat and Teerapong Senjuntichai and Angsumalin Senjuntichai and Wichirat Kaewjuea},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105002421417&doi=10.4186%2fej.2025.29.3.27&partnerID=40&md5=a4ea276d6851bef476543747d306014a},

doi = {10.4186/ej.2025.29.3.27},

issn = {01258281},

year  = {2025},

date = {2025-01-01},

journal = {Engineering Journal},

volume = {29},

number = {3},

pages = {27 – 44},

publisher = {Chulalongkorn University, Faculty of Fine and Applied Arts},

abstract = {Traditional methods for calculating pavement layers elastic moduli from falling weight deflectometer (FWD) tests often rely on computationally intensive iterative processes and lack struggle to capture complex variable relationships. This article highlights the utilization of machine learning (ML) algorithms, which include artificial neural networks (ANN), long-short-term memory (LSTM), and random forests (RF), to predict the elastic moduli of multi-layered flexible pavement based on FWD test. All ML algorithms were developed using synthetic databases derived from the exact stiffness matrix scheme, which was employed for the analysis of multi-layered pavements under axisymmetric surface loading. The development of ML models involves preprocessing of data, hyperparameter optimization, and performance evaluation. The input variables consist of the FWD surface deflections, the magnitude of applied loading, and the layer thicknesses, while the output variables represent the predicted layered elastic moduli of the pavement structure. The ANN and LSTM models capture complicated relations more effectively than the RF model in the backcalculation of the layered elastic modulus based on the FWD test. Among the two, LSTM achieves higher accuracy, with the average values across all layer moduli of R2 and MAPE being 99.04% and 2.41%, respectively, in the test set. The applicability of LSTM model is further demonstrated by comparing with the backcalculated elastic modulus based on the FWD field experiments performed on the infrastructure of roads in Thailand. Furthermore, a sensitivity analysis reveals that deflections near the center of loading predominantly impact the predictions of upper layer moduli, while the moduli of lower layers are influenced by deflections across all geophones. © 2025, Chulalongkorn University, Faculty of Fine and Applied Arts. All rights reserved.},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Tangjitsitcharoen2025,

title = {Leveraging Intelligent Machines for Sustainable and Intelligent Manufacturing Systems},

author = {Somkiat Tangjitsitcharoen and Nattawut Suksomcheewin and Alessio Faccia},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105006619808&doi=10.3390%2fjmmp9050153&partnerID=40&md5=a336e5d0ce219d6adf44fa05c12921de},

doi = {10.3390/jmmp9050153},

issn = {25044494},

year  = {2025},

date = {2025-01-01},

journal = {Journal of Manufacturing and Materials Processing},

volume = {9},

number = {5},

publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},

abstract = {This study presents an intelligent machine developed for real-time quality monitoring during CNC turning, aimed at improving cutting efficiency and reducing production energy. A dynamometer integrated into the CNC machine captures decomposed cutting forces using the Daubechies wavelet transform. These force ratios are correlated with key workpiece dimensions: surface roughness, average roughness, straightness, and roundness. Two predictive models—nonlinear regression and a feed-forward neural network with Levenberg–Marquardt backpropagation—are employed to estimate these parameters under varying cutting conditions. Experimental results indicate that nonlinear regression models outperform neural networks in predictive accuracy. The proposed system offers effective in-process control of machining quality, contributing to shorter cycle times, lower defect rates, and more sustainable manufacturing practices. © 2025 by the authors.},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}