Browse
Recent Submissions
Item OPTIMIZING LAST-MILE DELIVERY BY DEEP Q-LEARNING APPROACH FOR AUTONOMOUS DRONE ROUTING IN SMART LOGISTICS(Regional Association for Security and crisis management, 2024) Pannee Suanpang; Pitchaya Jamjuntr; P. Suanpang; Department of Information Technology, Faculty of Science and Technology, Suan Dusit University, Bangkok, 10300, Thailand; email: pannee_sua@dusit.ac.thThe advancement technology of artificial intelligence and e-commerce has increased and this has called for new ways to improve last-mile transportation, which is regarded as an essential part of the logistics value chain, especially in smart logistics. This paper addresses the problem of developing effective routes for autonomous drones in last-mile logistics using deep Q-learning. This paper aims to improve the process of delivery by utilizing the flexibility and intelligence of self-driven autonomous drones in smart logistics transportation. The key challenge for the effective provision of last-mile delivery services remains the decision on the routing of many aerial drones in an indoor urban environment, concerning the restrictions of a time window for delivery, energy consumption and traffic. This paper implements a deep Q-learning paradigm that allows drones to relearn their flight paths and delivery strategy during the lifecycle, thereby reducing the cost in the long run while using the costing strategies as part of the reengineering process. The approach has been validated through extensive experimentation and simulations. Results obtained indicate that the delivery drones modified for the study attained the designed requirements of deep Q-learning, including optimal navigation and performance that attained 12.8% shorter delivery time, an increase in energy efficiency by 8.4%, and a route quality improvement of 20.1%. Furthermore, highlights the performance of the system in various situations where deep Q-learning and standard routing approaches are compared. This paper not only aids in the minimization of the last-mile delivery constraint by the use of shipping drones but also emphasizes the capacities of reinforcement learning strategies such as deep Q-learning in tackling the routing problems in smart logistics systems. At last, it advocates carrying on deeper into the application of reinforcement learning in the solving of complex optimization problems in various other fields. © 2024 Regional Association for Security and crisis management. All rights reserved.Item Integrating Generative AI and IoT for Sustainable Smart Tourism Destinations(Multidisciplinary Digital Publishing Institute (MDPI), 2024) Pannee Suanpang; Pattanaphong Pothipassa; P. Suanpang; Department of Information Technology, Faculty of Science & Technology, Suan Dusit University, Bangkok, 10300, Thailand; email: pannee_sua@dusit.ac.thThis paper aims to develop a groundbreaking approach to fostering inclusive smart tourism destinations by integrating generative artificial intelligence (Gen AI) with natural language processing (NLP) and the Internet of Things (IoT) into an intelligent platform that supports tourism decision making and travel planning in smart tourism destinations. The acquisition of this new technology was conducted using Agile methodology through requirements analysis, system architecture analysis and design, implementation, and user evaluation. The results revealed that the synergistic combination of these technologies was organized into three tiers. The system provides information, including place names, images, descriptive text, and an audio option for users to listen to the information, supporting tourists with disabilities. Employing advanced AI algorithms alongside NLP, developed systems capable of generating predictive analytics, personalized recommendations, and conducting real-time, multilingual communication with tourists. This system was implemented and evaluated in Suphan Buri and Ayutthaya, UNESCO World Heritage sites in Thailand, with 416 users participating. The results showed that system satisfaction was influenced by (1) the tourism experience, (2) tourism planning and during-trip factors (attention, interest, and usage), and (3) emotion. The relative Chi-square (_2/df) of 1.154 indicated that the model was suitable. The Comparative Fit Index (CFI) was 0.990, the Goodness-of-Fit Index (GFI) was 0.965, and the model based on the research hypothesis was consistent with the empirical data. This paper contributions significant advancements in the field of smart tourism by demonstrating the integration of Gen AI, NLP, and the IoT and offering practical solutions and theoretical insights that enhance accessibility, personalization, and environmental sustainability in tourism. © 2024 by the authors.Item Virtual Learning Environment - Evaluation of LearnerÕs Behavior Using Topic Models(Institute of Electrical and Electronics Engineers Inc., 2024) N.A. Deepak; Gyanendra Kumar; Aunkrisa Sangchumnong; R.S. Chaithra; Sur Singh Rawat; Aziz Nanthaamornphong; Girish B.C. Kumar; Manoj Gupta; N.A. Deepak; RV Institute of Technology and Management, Bengaluru, India; email: deepakna.rvitm@rvei.edu.inOnline learning platforms come with a number of difficulties. To identify the student who does not do the given assignment within the allotted time. Researchers have been attempting to solve this issue in the literature of late, however most algorithms are unable to produce linearly separable learner clusters and correctly classify the input documents. In an attempt to overcome these problems, the suggested methodology builds clusters of linearly separable learners by applying topic models such as Latent Dirichlet Allocation (LDA). First, the necessary features are retrieved and converted into an appropriate LDA of words and phrases. The topic-modeling algorithm (LDA) is then fed the words to create clusters of related content or learners. A number of experiments were carried out to assess how well various predictive models performed. The results show the topic-modeling algorithm LDA attains significant clustering of documents over the other state-of-art. © 2024 IEEE.Item EXTENDING NETWORK INTRUSION DETECTION WITH ENHANCED PARTICLE SWARM OPTIMIZATION TECHNIQUES(Academy and Industry Research Collaboration Center (AIRCC), 2024) Surasit Songma; Watcharakorn Netharn; Siriluck LorpunmaneeThe present research investigates how to improve Network Intrusion Detection Systems (NIDS) by combining Machine Learning (ML) and Deep Learning (DL) techniques, addressing the growing challenge of cybersecurity threats. A thorough process for data preparation, comprising activities like cleaning, normalization, and segmentation into training and testing sets, lays the framework for model training and evaluation. The study uses the CSE-CIC-IDS 2018 and LITNET-2020 datasets to compare ML methods (Decision Trees, Random Forest, XGBoost) and DL models (CNNs, RNNs, DNNs, MLP) against key performance metrics (Accuracy, Precision, Recall, and F1-Score). The Decision Tree model performed better across all measures after being fine-tuned with Enhanced Particle Swarm Optimization (EPSO), demonstrating the model's ability to detect network breaches effectively. The findings highlight EPSO's importance in improving ML classifiers for cybersecurity, proposing a strong framework for NIDS with high precision and dependability. This extensive analysis not only contributes to the cybersecurity arena by providing a road to robust intrusion detection solutions, but it also proposes future approaches for improving ML models to combat the changing landscape of network threats. © (2024), (Academy and Industry Research Collaboration Center (AIRCC)). All Rights Reserved.Item Upgrading the Grass-roots Economy Through Community-Based Tourism under the Concepts of Innovative Business and Creative Economy(Research and Development Institute Suan Dusit University, 2024) Wanphen Kuensman; Wipada Mukda; W. Mukda; Faculty of Management Science, Suan Dusit University, Bangkok, 10300, Thailand; email: Wanphen_3956@hotmail.comThis academic paper aims to study the upgrading of the grass-roots economy through community-based tourism under the concepts of innovative business and the creative economy. The grass-roots economy at the local community level needs to be strong and increase competitiveness this means it must be self-reliant through economic and behavioral restructuring by promoting the learning process of the community such as educating open exchange platform and organizing a community learning center or community information center to collect history. These efforts provide the community with a foundation for driving community-based tourism, enabling them to innovate, add value, and elevate the quality of products and services, thereby building trust among stakeholders. © 2024, Research and Development Institute Suan Dusit University. All rights reserved.Item A Bibliometric Analysis of Keywords of HyFlex Learning for the English Language Learning Skills of Teacher Students(School of Liberal Arts, King Mongkut's University of Technology Thonburi, 2024) Thip Khumyoo; Niroumon Suwannasri; Akkrawat Wongthitikun; Jira Jitsupa; Jittree Jampeetong; J. Jitsupa; Faculty of Education, Suan Dusit University, Thailand; email: jira_jit@dusit.ac.thListening, speaking, reading, and writing are important skills in English language learning. However, some students are not successful in learning English due to several factors. The model for improving the English learning skills of students is essential. However, except for the HyFlex learning model, no suitable model for learners has been found following the new normal. This research, therefore, identify the bibliographic keywords of HyFlex learning for the English learning skills of teacher students. According to a total of 465 documents published in the Scopus database, 40 articles met the research inclusion criteria and keywords related to HyFlex learning could be used to guide the development of the model of English language learning skills of students. Findings, the keywords of HyFlex learning for the English learning skills of teacher students 42 keywords related to Hyflex learning that clustered into seven categories: Higher education, Learning environment, Teaching and learning model, Digital technology for learning, Teacher, Student, and English language. © 2024, School of Liberal Arts, King Mongkut's University of Technology Thonburi. All rights reserved.Item A new Approach of Generalized Fractional Integrals in Multiplicative Calculus and Related Hermite-Hadamard-Type Inequalities with Applications(Walter de Gruyter GmbH, 2024) Muhammad Aamir Ali; Michal Fe_kan; Chanon Promsakon; Thanin Sitthiwirattham; M. Fe_kan; Department of Mathematical Analysis and Numerical Mathematics, Comenius University in Bratislava, Bratislava, Mlynsk‡ dolina, 842 48, Slovakia; email: michal.feckan@fmph.uniba.skThe primary goal of this paper is to define Katugampola fractional integrals in multiplicative calculus. A novel method for generalizing the multiplicative fractional integrals is the Katugampola fractional integrals in multiplicative calculus. The multiplicative Hadamard fractional integrals are also novel findings of this research and may be derived from the special situations of Katugampola fractional integrals. These integrals generalize to multiplicative Riemann-Liouville fractional integrals and multiplicative Hadamard fractional integrals. Moreover, we use the Katugampola fractional integrals to prove certain new Hermite-Hadamard and trapezoidal-type inequalities for multiplicative convex functions. Additionally, it is demonstrated that several of the previously established inequalities are generalized from the newly derived inequalities. Finally, we give some computational analysis of the inequalities proved in this paper. © 2024 Mathematical Institute Slovak Academy of Sciences.Item Development of sweet fermented rice (Khao-Mak) production using a pure culture of Amylomyces rouxii TISTR 3182 by the mixture design approach(Springer, 2024) Sujaya Rittisorn; Manida Chorum; Sorayaporn Ratchakit; Nattawan Klaeabangthong; Srisuda Samaimai; Thanasak Lomthong; T. Lomthong; Division of Biology, Faculty of Science and Technology, Rajamangala University of Technology, Thanyaburi, Pathum Thani, 12110, Thailand; email: thanasak_l@rmutt.ac.thA mixture design approach was used to investigate how different types of glutinous rice impacted the production of sweet fermented rice (Khao-Mak) using a pure culture of Amylomyces rouxii TISTR 3182. White glutinous rice provided the highest total soluble solids (TSS) and alcohol content (24.3 ± 0.35oBrix and 2.0 ± 0.14%, respectively). The combination of black glutinous rice (88%) with white glutinous rice (12%) gave the highest total phenolic content (TPC) at 120.21 ± 2.20ʵg GAE/mL. The optimal combination was chosen for large-scale production, yielding 22.00 ± 0.5oBrix, 1.63 ± 0.23%, and 102.98 ± 0.76ʵg GAE/mL of TSS, alcohol, and TPC, respectively. Thin-layer chromatography (TLC) revealed that the sugar obtained from the fermentation was glucose. Scanning electron microscopy (SEM) showed that growth of the fungal strain hydrolyzed the rice structure during fermentation. The crude extract of sweet fermented rice, fermented using a pure fungal strain culture through a biotechnological approach, suppressed the growth of Staphylococcus aureus DMST 2933 and Salmonella sp. ATCC 13311. © Association of Food Scientists & Technologists (India) 2024.Item Exploring the Association Between Loneliness, Subjective Cognitive Decline, and Quality of Life Among Older Thai Adults: A Convergent Parallel Mixed-Method Study(SAGE Publications Inc., 2024) Panawat Sanprakhon; Wachira Suriyawong; Orranuch Chusri; Peerayut Rattanaselanon; W. Suriyawong; Faculty of Nursing, Chiang Mai University, Chiang Mai, Thailand; email: suriyawo@msu.eduExamining the rising prevalence of subjective cognitive decline as an early indicator of dementia in adults, this study investigates its complex interaction with loneliness and quality of life in individuals with preclinical dementia. Using a convergent parallel mixed-method approach, we employed Structural Equation Modeling on a cohort of 149 older adults. Qualitative insights were derived from focused group discussions and in-depth semi-structured interviews with a cohort of 23 older adults. Loneliness emerges as a pivotal contributor, exerting a discernible partial indirect effect on quality of life through subjective cognitive decline (indirect effect = _0.145, p =.006). Noteworthy differentials surfaced, with the impact of subjective cognitive decline on quality of life heightened in those with chronic diseases (__2 = 6.139, p =.013). Loneliness, wielding a palpable impact, intricately interlaces with quality of life, the nexus of which is intricately mediated by subjective cognitive decline. © The Author(s) 2024.Item A STUDY OF FRACTIONAL HERMITE-HADAMARD-MERCER INEQUALITIES FOR DIFFERENTIABLE FUNCTIONS(World Scientific, 2024) Thanin Sitthiwirattham; Miguel Vivas-Cortez; Muhammad Aamir Ali; HŸseyin Budak; Ibrahim Avci; M. Vivas-Cortez; School of Physical and Mathematical Sciences, Faculty of Exact and Natural Sciences Pontifical Catholic, University of Ecuador, Quito, Av. 12 October 1076, Section, 17-01-2184, Ecuador; email: mjvivas@puce.edu.ecIn this work, we prove a parameterized fractional integral identity involving differentiable functions. Then, we use the newly established identity to establish some new parameterized fractional Hermite-Hadamard-Mercer-type inequalities for differentiable function. The main benefit of the newly established inequalities is that these inequalities can be converted into some new Mercer inequalities of midpoint type, trapezoidal type, and Simpson's type for differentiable functions. Finally, we show the validation of the results with the help of some mathematical examples and their graphs. © The Author(s)Item On Implicit Atangana-Baleanu-Caputo Fractional Integro-Differential Equations with Delay and Impulses(Hindawi Limited, 2024) Panjaiyan Karthikeyann; Sadhasivam Poornima; Kulandhaivel Karthikeyan; Chanon Promsakon; Thanin Sitthiwirattham; K. Karthikeyan; Department of Mathematics, Kpr Institute of Engineering and Technology, Coimbatore, Tamil Nadu, 641407, India; email: karthi_phd2010@yahoo.co.in; T. Sitthiwirattham; Research Group for Fractional Calculus Theory and Applications, Science and Technology Research Institute, King Mongkut's University of Technology North Bangkok, Bangkok, 10800, Thailand; email: thanin_sit@dusit.ac.thIn this paper, we study the existence and uniqueness of solutions for impulsive Atangana-Baleanu-Caputo ABC fractional integro-differential equations with boundary conditions. Schaefer's fixed point theorem and Banach contraction principle are used to prove the existence and uniqueness results. An example is presented to illustrate the results. © 2024 Panjaiyan Karthikeyann et al.Item Digital Technology Landscape for Vocational Education: Learning Loss Recovery(Penerbit UTHM, 2024) Jira Jitsupa; Venus Skunhom; Prachyanun Nilsook; Kanitta Hinon; Watcharee Sangboonraung; Srisuda Daungtod; Wilawan Phumee; Kitiya Promsron; V. Skunhom; Faculty of Education, Suan Dusit University, Bangkok, Thailand; email: venus_sku@dusit.ac.thThe research aimed to; 1) study the expectations of teachers on the behavioral conditions of vocational education learners, 2) Study the ability of teachers to achieve the expected behavioral conditions of vocational education, 3) Comparison of the use of digital technology in teaching by teachers to recover the learning loss of vocational learners during the new normal and next normal periods, 4) Study the teachers need to use digital technology in teaching to recover the learning loss of vocational learners during the new normal and next normal periods, and 5) Create digital technology landscape for learning loss recovery on vocational education. Data were collected with an online questionnaire that passed the validity and reliability with 301 vocational teachers. The results of the research showed teachers have higher expectations of learnersÕ behavioral conditions. Teachers can make vocational learners experience the expected behavioral conditions to a greater extent. Teachers use digital technology to organize teaching to recover the learning loss of vocational learners during the new normal rather than during the next normal. However, the demand for digital technology for teaching to recover the learning loss problem of learners during the next normal is increasing more than during the new normal. The study suggests improving the knowledge and ability of teachers to use digital technology for teaching to recover the problem of learning loss among learners. © 2024, Penerbit UTHM. All rights reserved.Item ON SOME NEW AND GENERAL q-HERMITEÐHADAMARD TYPE INEQUALITIES FOR CONVEX FUNCTIONS(University of Miskolc, 2024) Zoya Abdullah; Awais Yousaf; Chanon Promsakon; Thanin Sitthiwirattham; A. Yousaf; Department of Mathematics, The Islamia University of Bahawalpur, Bahawalpur, Pakistan; email: awais.yousaf@iub.edu.pkIn this paper, we establish a new version of HermiteÐHadamard type inequality for convex functions. Moreover, we establish a general version of q-integral identity involving qdifferentiable functions to prove some new q-midpoint and q-trapezoidal type inequalities for q-differentiable convex functions. It is also shown that the newly established inequalities can be converted into some existing inequalities within the literature. Finally, we add some mathematical examples to show the validation of newly established inequalities. © 2024 The Author(s). Published by Miskolc University Press. This is an open access article under the license CC BY 4.0.Item Controllability of Hilfer fractional neutral impulsive stochastic delayed differential equations with nonlocal conditions(Elsevier Ltd, 2024) Sadam Hussain; Muhammad Sarwar; Kamaleldin Abodayeh; Chanon Promsakon; Thanin Sitthiwirattham; M. Sarwar; Department of Mathematics, University of Malakand, Dir Lower, Pakistan; email: sarwar@uom.edu.pk; C. Promsakon; Department of Mathematics, Faculty of Applied Science, King Mongkut's University of Technology North Bangkok, Bangkok, 10800, Thailand; email: chanon.p@sci.kmutnb.ac.thIn this paper, the controllability for Hilfer fractional neutral stochastic differential equations with infinite delay and nonlocal conditions has been investigated. Using concepts from fractional calculus, semigroup of operators, fixed-point theory, measures of noncompactness, and stochastic theory the main controllability conclusion is attained. The applications of the key findings are finally illustrated with two examples. © 2024 The Author(s)Item Adaptive Multi-Agent Reinforcement Learning for Optimizing Dynamic Electric Vehicle Charging Networks in Thailand(Multidisciplinary Digital Publishing Institute (MDPI), 2024) Pitchaya Jamjuntr; Chanchai Techawatcharapaikul; Pannee Suanpang; P. Suanpang; Department of Information Technology, Faculty of Science & Technology, Suan Dusit University, Bangkok, 10300, Thailand; email: pannee_sua@dusit.ac.thThe rapid growth of electric vehicles (EVs) necessitates efficient management of dynamic EV charging networks to optimize resource utilization and enhance service reliability. This paper explores the application of adaptive multi-agent reinforcement learning (MARL) to address the complexities of EV charging infrastructure in Thailand. By employing MARL, multiple autonomous agents learn to optimize charging strategies based on real-time data by adapting to fluctuating demand and varying electricity prices. Building upon previous research that applied MARL to static network configurations, this study extends the application to dynamic and real-world scenarios, integrating real-time data to refine agent learning processes and also evaluating the effectiveness of adaptive MARL in maximizing rewards and improving operational efficiency compared to traditional methods. Experimental results indicate that MARL-based strategies increased efficiency by 20% and reduced energy costs by 15% relative to conventional algorithms. Key findings demonstrate the potential of extending MARL in transforming EV charging network management, highlighting its benefits for stakeholders, including EV owners, operators, and utility providers. This research contributes insights into advancing electric mobility and energy management in Thailand through innovative AI-driven approaches. The implications of this study include significant improvements in the reliability and cost-effectiveness of EV charging networks, fostering greater adoption of electric vehicles and supporting sustainable energy initiatives. Future research directions include enhancing MARL adaptability and scalability as well as integrating predictive analytics for proactive network optimization and sustainability. These advancements promise to further refine the efficacy of EV charging networks, ensuring that they meet the growing demands of ThailandÕs evolving electric mobility landscape. © 2024 by the authors.Item Comparison of Pebbles Growing Media from Agricultural Waste Materials on Productivity Growth of Melon (cv. Orange Man and cv. Galia 248) Cultivated in Greenhouse Conditions(Research and Development Institute Suan Dusit University, 2024) Suchaya Kiattiprajuksa; Yuttaya Yuyen; Y. Yuyen; Research and Development Institute, Suan Dusit University, Bangkok, 10300, Thailand; email: yuttaya_yuy@dusit.ac.thThe objective of this research project was to compare the results from the use of pebbles growing media made from agricultural waste suitable for the growth and productivity of two cultivars, Orange Man melon and Galia 248 melon in a greenhouse. Pebbles growing media could reduce cost from the traditional material used for growing melon and have higher productivity for farmers. The experiment was divided into 5 experimental sets, namely, set that uses 100% of pebbles from agricultural waste (T1), set that uses normal planting material (coconut husk and chopped coconut coir in the ratio of 2 to 1), 25% mixed with pebbles from agricultural waste at 75% (T2), 50% mixed with pebbles from agricultural waste at 50% (T3), 75% mixed with pebbles from agricultural waste at 25% (T4), and normal planting material 100% (T5).The research methodology is CRD, with one-way and two-way analysis of variance (ANOVA). In addition, the pair test with ScheffeÕs method to compare the difference that affects fruit weight of the melon at 42 days after pollination was used. The comparison of the means and standard deviation were performed by ScheffeÕs method at P ² 0.05 significance level. From the growth and productivity records of two cultivars melon, it was found that the experimental set that is most suitable is T2 which gave high yield of fruit width, fruit length, fruit weight and Brix value. Orange Man cultivars grown with T2 exhibited the average fruit width, fruit length, fruit weight and Brix value at 23.6±1.8 cm, 23.7±1.9 cm, 1.9±0.1 kg and 16±0.0¡Brix, respectively. Galia 248 cultivars grown with T2 exhibited the average fruit width, fruit length, fruit weight and Brix value at 23.2±0.8 cm, 24.4±1.2 cm, 1.9±0.1 kg and 15±0.6¡Brix, respectively. These results indicated that the factors of cultivar and treatment at the time of pollination are not different from each other with the statistical significance and confidence level of 95% compared with melons grown with T5 (normal planting material). These findings can lead to benefit farmers by reducing the cost of growing material for as much as 75% per time. The new material are easily manageable as well as having a long service life. © 2024, Research and Development Institute Suan Dusit University. All rights reserved.Item Inertial iterative method for solving equilibrium problems and fixed point problems(Springer Nature, 2024) Min Li; Zhongbing Xie; Prasit Cholamjiak; Kunrada Kankam; Z. Xie; School of Mathematics and Statistics, Wuhan University, Wuhan, 430072, China; email: xzbmath@163.comIn this paper, we present an inertial iterative method for solving pseudomonotone equilibrium and fixed point problems in Banach spaces. Under appropriate conditions, we improve the convergence efficiency of our proposed algorithm by introducing a new step size and iteration rule, and further derive a strong convergence theorem. Finally, we demonstrate through numerical experiments that our new algorithm compares favourably with existing methods in terms of convergence behaviour. © 2024, The Author(s) under exclusive licence to Sociedade Brasileira de Matem‡tica Aplicada e Computacional.Item Hyperparameters optimization XGBoost for network intrusion detection using CSE-CIC-IDS 2018 dataset(Institute of Advanced Engineering and Science, 2024) Witcha Chimphlee; Siriporn Chimphlee; S. Chimphlee; Department of Data Science and Analytics, Faculty of Science and Technology, Suan Dusit University, Bangkok, Thailand; email: siriporn.chi@gmail.comWith the introduction of high-speed internet access, the demand for security and dependable networks has grown. In recent years, network attacks have gotten more complex and intense, making security a vital component of organizational information systems. Network intrusion detection systems (NIDS) have become an essential detection technology to protect data integrity and system availability against such attacks. NIDS is one of the most well-known areas of machine learning software in the security field, with machine learni ng algorithms constantly being developed to improve performance. This research focuses on detecting abnormalities in societal infiltration using the hyperparameters optimization XGBoost (HO-XGB) algorithm with the Communications Security Establishment-The Canadian Institute for Cybersecurity-Intrusion Detection System2018 (CSE-CIC-IDS2018) dataset to get the best potential results. When compared to typical machine learning methods published in the literature, HO-XGB outperforms them. The study shows that XGBoost outperforms other detection algorithms. We refined the HO-XGB model's hyperparameters, which included learning_rate, subsample, max_leaves, max_depth, gamma, colsample_bytree, min_child_weight, n_estimators, max_depth, and reg_alpha. The experimental findings reveal that HO-XGB1 outperforms multiple parameter settings for intrusion detection, effectively optimizing XGBoost's hyperparameters.Item Antioxidant and Anti-Inflammatory Activities of the Extract and Bioaccessible Fraction of Mango Peel in Muffins(University of Zagreb, 2024) Yossaporn Plaitho; Aikkarach Kettawan; Hataichanok Sriprapai; Aurawan Kringkasemsee Kettawan; Phakpoom Kooprasertying; P. Kooprasertying; School of Culinary Arts, Suan Dusit University, Bangkok, Sirinthon Road, Bang Phlat, 10700, Thailand; email: np_kool@hotmail.comResearch background. Mango peel is a production waste and can cause environmental problems, but its nutritional value consists of bioactive compounds that could be benefi-cial for human health. The aim of this study is to determine the bioactive compounds, an-tioxidant and anti-inflammatory activities of mango peels and their use in muffins. Experimental approach. The content of polyphenols, carotenoids and total phenols as well as the antioxidant activity of mango peel extract were evaluated. The anti-inflamma-tory activity of the extract was investigated using Caco-2 cell assay. The mango peel powder was then incorporated into muffin formulations. The sensory properties of these for-tified muffins were evaluated. The total phenolic content, antioxidant activity and anti-inflammatory properties of the muffin extracts and their bioaccessible fractions were also analysed. Results and conclusions. The mango peel contained quercetin, phenolic compounds, _-carotene, _-carotene and lutein, which have antioxidant potential. In Caco-2 cells ex-posed to induced inflammation, the mango peel powder extract (_=10, 50 and 100 µg/ mL) attenuated the production of reactive oxygen species (ROS), tumour necrosis factor-alpha (TNF-_) and interleukin-8 (IL-8), while maintaining cell viability. Muffins supplemented with 5 % mango peel powder showed good sensory properties, but not as good as those of plain muffins without mango peel powder. The total phenolic content and anti-oxidant activities in both the extract and the bioaccessible fraction of the supplemented muffins were higher than those observed in the standard muffins. Moreover, the extract and bioaccessible fraction of the supplemented muffins resulted in a higher reduction of ROS, IL-8 and TNF-_ production in Caco-2 cells than those obtained from the standard muffins. Novelty and scientific contribution. This study is the first to investigate the protective effects of mango peel and muffins supplemented with mango peel powder against IL-1_--induced oxidative damage in Caco-2 cells. The results confirm that both mango peel and the supplemented muffins inhibited the production of inflammatory markers, including ROS and cytokines. These findings suggest that mango peel could be a valuable compo-nent of functional food formulations including dietary supplements. © 2024, University of Zagreb. All rights reserved.Item Improving Mechanical Behavior of Compacted Cement Sand Mixed with Glass Powder from Glass Industry and Glass Fiber for Green Construction Materials(Springer, 2024) Prapatsorn Prathungthai; Chalermpon Wungsumpow; Sakol Pochalard; Keeratikan Piriyakul; K. Piriyakul; Department of Civil and Environmental Engineering Technology, Center of Excellence in Structural Dynamics and Urban Management, Science and Technology Research Institute, College of Industrial Technology, King MongkutÕs University of Technology North Bangkok, Bangkok, Thailand; email: keeratikan.p@cit.kmutnb.ac.thThe purpose of this research is to examine the mechanical behavior of compacted cement sand with the addition of glass fibers, glass powder from the glass industry, and Ordinary Portland Cement (OPC). Finding the optimal proportions of OPC, glass powder, and glass fibers in the soilÐcement mixture to create a novel green building material is the aim of this study. Every sample of compacted cement sand was created with a glass fiber content of 0.5, 1.0, 1.5, 2.0, and 2.5% by volume, and a variation in glass fiber lengths of 3, 6, and 12Êmm. The optimal moisture content for the samples was 6.19%. OPC content was applied at weights of 2, 4, 6, 8, and 10%. At 10, 20, 30, 40, and 50% of the cement, glass powder was added. After that, the samples of compacted cement were left for 7, 14, and 28Êdays in order to examine how the green building materials aged. The unconfined compression test was conducted on these samples of compacted cement sand in accordance with ASTM D1633-17. Based on the testing findings, it was determined that 8% cement is the right amount to combine with clayey soil, 1.0% glass fibers with a length of 6Ð12Êmm, and 20% glass powder with a curing period up to 28Êdays are the right amounts. As a result, it has been demonstrated that glass fiber and powder are green building materials. By lowering the required amount of cement, our findings help ThailandÕs future cement demand. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.