13474 research outputs found
Sort by
Abundance, distribution and bioaccumulation of microplastics and its potential impacts in mangrove environment / Priya Mohan
No full textPlastic pollution has become a global issue of transboundary contamination, necessitating comprehensive interdisciplinary research to comprehend the negative impacts. This research aims to identify the mobility of plastic bottles in the open oceans using GPS, to determine the prevalence and distribution of microplastics in mangrove sediment, water and Anadara granosa, to determine the microplastic uptake in Daphnia magna and A. granosa, and to evaluate the feasibility of valorisation plastic waste through hydrothermal liquefaction (HTL). To achieve the first objective, five tracking devices in PET bottles (B1, B2, B3, B4, and B5) were deployed in Cherating, Matang, and Kuala Selangor and their trajectory movement was monitored using a GPS system. For the second objective, sediment, water, and A. granosa were collected from Matang, Kuala Selangor, Sedili Besar, and Cherating mangroves. The sediment was collected using an auger at a depth of 1-50cm, and the microplastics in water were obtained by submerging a plankton net with a mesh size of 90μm for one hour. While A. granosa were obtained from the study sites. The microplastics from sediment, water and A. granosa were extracted using vacuum filtration and analyzed under a dissecting microscope to categorize them based on sizes, shapes, and colours, while polymer types were determined via FTIR. For the third objective, Daphnia magna and A. granosa were exposed to various shapes and sizes of PP microplastics for 96 and 264 hours, respectively. Microplastic uptake by Daphnia magna and A. granosa was observed using fluorescent and dissecting microscopes, respectively. As for the depolymerization of PP and PET (objective four), the experiment involved different alkaline concentrations and reaction times via a 2-factorial experimental design. The deployment of the tracking device revealed that B2 deployed in the Straits of Malacca travelled the longest distance of 8984 km. Conversely, the remaining B1, B3, B4 and B5 bottles beached at vegetation areas in Tittu Island (Philippines), Ao Talo Malaka (Thailand), Maldives Island and Mersing (Malaysia), respectively. Plastic beaching can cause polymer fragmentation and microplastic accumulation in the marine environment. Studies on microplastic pollution in mangroves found the highest levels in sediment (151 ± 1.91 particles/kg) during the Southwest Monsoon and in water (43400 ± 9.19 particles/m3) during the Intermonsoon. This study also found that A. granosa from Matang had the highest amount of microplastics (0.40 ± 0.2 particles/g). Overall, the dominant microplastic in the sediment, water and A. granosa were particles of <0.1mm, fragment, blue, and rayon polymer. A. granosa also accumulated microorganisms (Pseudomonas, Rhodococcus, Mycoplasma, and Candidatus thiophysa) and chlorinated organic pollutants (1-propene, 1,2,3-trichloro-, (Z)-; 1,1,2,3,3-pentachloropropane, and 1,1,1,2-tetrachloroethane) from its environment. Further laboratory investigation revealed that Daphnia magna and A. granosa preferred uptaking 0.1mm fragment particles. Microplastics pose a significant adverse impact on the marine environment and organisms. Thence, to address plastic pollution and reduce microplastic dispersion, depolymerizing PP (tetrapentacontane, 1,54-dibromo-, 1,54-dibromo-hexacontane, and acetic acid (2,4-dichlorophenyl) methyl ester) and PET (tetrapentacontane, 1,54-dibromo, and dotriacontane) produced fuel byproducts, highlighting sustainable approaches. Further research endeavours are essential to develop effective strategies for mitigating plastic pollution sustainably
Konflik di Yaman pasca Arab Spring (2011-2020): Kajian terhadap intervensi Arab Saudi dan kesannya ke atas Yaman / Muhammad Khairul Iman Hussin
No full textNaratif konflik di Yaman berlaku sejak berdekad lamanya sebelum penubuhan negara itu dengan berlakunya pertembungan internal antara suku kabilah setempat. Kemudian, ianya berterusan sehinggalah era Ali Abdullah Saleh diangkat menjadi Presiden yang pertama semasa penubuhan Republik Yaman pada tahun 1990, dan ketika ini Yaman berusaha memasuki fasa yang lebih harmoni. Namun, kegagalan Ali dalam menyantuni isu-isu dalaman negaranya secara responsif akhirnya membuka ruang kepada Arab Saudi untuk melakukan intervensi ke atas negaranya. Sejak itu, senario politik di Yaman bergolak kembali dan berlanjutan sehingga era Revolusi Arab pada tahun 2011 yang menyaksikan kebangkitan rakyat termasuk kumpulan Houthi menentang kerajaan Ali dan penggantinya setelah itu, Abdur Rabbuh Mansour al-Hadi. Tindakan Hadi yang turut melibatkan Saudi ke dalam urusan negaranya adalah satu bentuk usaha provokatif, dan ternyata ianya mendapat reaksi yang negatif dari rakyatnya sendiri terutama dari kumpulan Houthi dan blok haluan kiri. Lebih meruncingkan apabila tindakan intervensi Saudi tersebut adalah satu bentuk pelanggaran undang-undang dan hak asasi manusia, dan perkara ini meninggalkan kesan yang buruk ke atas Yaman. Senario sebegini mendapat perhatian daripada masyarakat global dengan pelbagai reaksi. Sehubungan dengan itu, objektif kajian bagi kajian ini adalah membincangkan konflik di Yaman pasca Arab Spring di samping mengkaji bentuk intervensi Arab Saudi terhadap konflik di Yaman secara jelas dan menganalisis kesan di sebalik intervensi Arab Saudi ke atas konflik di Yaman secara kolektif. Kajian ini mengaplikasi pendekatan kualitatif sebagai reka bentuk kajian melalui maklumat dan data dikumpul secara dokumentasi dengan merujuk pelbagai sumber. Kemudian, segala data tersebut dianalisis secara tematik dengan melihat kepada aspek sejarah dan analisis politik. Hasil kajian menjelaskan bahawa pergolakan konflik di Yaman berlaku disebabkan oleh Kerajaan yang lemah, Ketidaksatuan pemimpin politik, Kekurangan akauntabiliti dan integriti kerajaan, Transisi kuasa pemerintahan yang rapuh dan Kelemahan sistem federalisme dan nasionalisme di samping Pencabulan undang-undang dan hak asasi manusia. Hasil kajian seterusnya mendapati bahawa bentuk intervensi Saudi merangkumi kesemua aspek sosio iaitu politik, sosial, ekonomi dan agama. Seterusnya, hasil kajian terakhir mendapati bahawa mendapati bahawa kesan di sebalik intervensi tersebut adalah ketidakstabilan politik, kemunduran masyarakat sivil, negara berisiko muflis dan stereotaip agama dan mazhab yang menyebabkan ketidakcermatan orang ramai dalam memahami masalah sebenar yang berlaku di Yaman
Multidimensional poverty characteristics of zakat recipients based on Maqasid al-Shariah in Kuala Lumpur / Muhammad Nooraiman Zailani
No full textIt is widely recognised that the concept of poverty is complex and multifaceted. The narrow approach to defining poverty that is focused on a monetary approach neglects other key aspects such as access to education, access to healthcare, type of home, and others that are relevant and may affect the quality of life. Definitions and measurements of poverty are critical in determining if a certain level of income and living standard for a person is acceptable for both society and the national level. At present, Islamic financial institutions such as zakat institutions are applying the monetary approach to identify the poor and destitute. On a global front, the United Nations Development Program (UDNP) has unveiled the Multidimensional Poverty Index (MPI) method for measuring the deprivation aspect of poverty. Hence, the study adopted the Malaysia MPI (MMPI) released during the 11th Malaysia Plan (11MP) and tailored it according to the context of the study, with some additional and changes made to the dimensions and indicators applied. The study incorporated five dimensions namely religion, health, education, living standards and income with 18 indicators under the Zakat Multidimensional Poverty Index (ZMPI). The objectives of this study are (I) to identify the dimension and indicators of the proposed ZMPI (II) to examine the dimensions and the indicators that the poor and destitute asnaf in Kuala Lumpur are deprived of (III) to identify the multidimensional poverty level of the poor and destitute asnaf in Kuala Lumpur based on ZMPI and MMPI and (IV) to analyse the determinants of multidimensional poverty status among the poor and destitute asnaf in Kuala Lumpur based on ZMPI and MMP. The study constructed ZMPI to analyse the multidimensional poverty characteristics of the poor and destitute asnaf in Kuala Lumpur. Using multidimensional poverty measurement, the income dimension recorded the highest deprivation, followed by health and education dimension. iv
Since the study involves the poor and destitute asnaf, the highest deprivation indicator is household monthly income, followed by Islamic health insurance coverage, access to the internet for communication and access to health facilities. In addition, the MPI calculated using the ZMPI was recorded at 0.408% while the MPI calculated using the MMPI was recorded at 0.364%. Hence, the multidimensional poverty measurement, particularly the ZMPI is able to provide a more comprehensive picture of the poverty scenario of the targeted group of people in comparison to the unidimensional poverty measurement. The findings of the study demonstrate that the poor and destitute asnaf in Kuala Lumpur are still deprived in many aspects that are not measurable using the current applied poverty measurement. In addition, the household head’s education level, household size, and amount of zakat received significantly influence the multidimensional poverty status of the asnaf. Despite the declining trend of poverty incidence recorded in Malaysia, pockets of areas of deprivation that require more attention are worth highlighting. The outcome of the study is significant for the government and zakat institutions to better allocate and optimise the zakat resources in channelling zakat funds to qualified asnaf
A novel hybrid piezo-pyroelectric energy harvesting device by integration of micropatterned poly (vinylidene fluoride) using MEMS techniques / Iman Aris Fadzallah
No full textEnergy harvesting has been utilized in autonomous power technology in recent decades. This concept involves the capturing of ambient energy, converting it into electrical energy to power small devices. This innovative approach is significant in two main areas; firstly, reduction in battery recharging or replacement costs in remote areas and secondly, elimination of the need of battery disposal which addressing the environmental concerns. Past studies have demonstrated various piezoelectric materials were utilized to scavenge many forms of ambient energy such as mechanical vibration, thermal fluctuations and solar energy for energy harvesting systems. In this thesis, we propose poly(vinylidene fluoride) PVDF-based harvesting (EH) device to harvest hybrid piezo-pyroelectric energy from wind flow generated by a hot air blower. The novelty in this work lies in the integration of micropatterned PVDF film using microelectromechanical systems (MEMS) techniques. The initial part of EH device fabrication focuses on synthesizing electrospun PVDF nanofiber mats using a one-step electrospinning process with a variation of high voltages. To characterize the electrospun PVDF films, analyses were conducted using Fourier-transform infrared (FTIR) spectroscopy, x-ray diffraction (XRD) and field emission scanning electron microscope (FESEM). Findings from these characterizations provide insights into the β-phase fractions (F(β)), degree of crystallinity
Engineering properties of mortar and concrete using eco-processed pozzolan as partial cement replacement material / Lin Ying
No full textThis research aims to develop sustainable and structural-grade mortar and concrete by partially replacing conventional cement with two palm oil-based by-products namely, unprocessed eco-minerals (UEM), and ground and unground eco-processed pozzolan (GEPP and EPP). This study characterized the physical, chemical, morphological, and mineralogical properties of UEM, EPP, and GEPP. In addition, this research assessed the effect of cement replaced by UEM, EPP, and GEPP at various levels on workability, hardened properties, microstructural characteristics, and sustainability aspects of mortar. Additionally, this research examined the effect of varying EPP replacement levels on fresh and hardened properties, microstructure characteristics, and sustainability aspects of granite, electric arc furnace steel slag (SS), and palm oil clinker (POC) coarse aggregates concrete. The effect of EPP on selected durability properties of concrete was examined. The research findings demonstrate that incorporating UEM, EPP, and GEPP as SCMs has some effect on the flow, density, ultrasonic pulse velocity (UPV), and compressive strength compared to the control mortar. Based on the UPV test results, the quality of mortar containing up to 30% UEM and 70% EPP was classified as good. The compressive strengths of mortars with 30% UEM, 50% EPP, and 50% GEPP show that these can be classified as structural grade mortar. Based on the FESEM images, the control mortar exhibited a denser matrix compared to UEM, EPP, and GEPP mortars. Furthermore, the XRD test results depict that the GEPP consumed the highest amount of Ca(OH)2, followed by EPP and UEM. Incorporating UEM and EPP significantly reduces CO2 emissions and energy consumption of mortar. The inclusion of a higher volume of EPP, ranging from 30 to 50%, influenced the fresh and hardened properties of the concrete. On the concrete incorporating the EPP in granite and SS-based mixes, the UPV results show that the quality of granite and SS concrete with EPP generally was outstanding, while the quality of POC concrete with 0-50% EPP was good. The mixes with 0–50% EPP in concrete with granite, SS, and POC were classified as a structural-grade, especially POC concrete, which was classified as a lightweight structural-grade. The Ca(OH)2 peak intensity was high in the control concrete relative to 10% EPP concrete. Incorporating EPP prominently reduced CO2 emission and energy consumption of concrete. Regarding concrete durability, incorporating EPP rises water absorption, porosity, and electrical resistivity of granite, SS, and POC concrete. The HCl resistance of granite concrete increased with the improvement in the EPP replacement level. Notably, the FESEM images and XRD pattern of the control and 30% EPP concrete exposed to HCl solution showed an absence of CH and ettringite. However, when exposed to MgSO4 solution, there was a decrease in the compressive strength improvement of granite concrete as the EPP replacement level increased. Furthermore, the FESEM images demonstrated that the control concrete displayed a denser microstructure compared to the 30% EPP concrete when the concrete was exposed in MgSO4 solution. The XRD pattern revealed higher peak intensities of ettringite and gypsum in the control concrete exposed to MgSO4 solution
Information fusion and data augmentation with deep features for a deep learning-based baby cry recognition / Zhang Ke
No full textDeep learning theory has made remarkable advancements in baby cry recognition, significantly enhancing its accuracy. Nonetheless, existing research faces three challenges. Firstly, the limited size of the database increases the risk of overfitting for a deep learning model. Secondly, the current research still suffers from data imbalance problem, which leads to bias in model learning. Thirdly, there is a limited study on information fusion. Therefore, the objectives of this study are firstly, to develop a model based on transfer learning to solve the model overfitting problem; secondly, to develop a generative adversarial network model to generate new baby cry data to solve the data imbalance problem; and thirdly to develop an information fusion method to improve the recognition accuracy. To address these issues, the contribution of this study is elaborated in the following three points. (1) A novel approach called BCRNet is proposed, which combines transfer learning and feature fusion. The BCRNet model takes multi-domain features as input and extracts deep features using a transfer learning model. Subsequently, a multilayer autoencoder is utilized for feature reduction, and a Support Vector Machine (SVM) is employed to select the transfer learning model with the highest classification accuracy. Then two features are concatenated to form fused features. Finally, the fused features are fed into a deep neural network (DNN) for classification. Experimental results show that the proposed model is effective in mitigating the model overfitting problem due to small datasets. The fused features of the proposed method are better than the existing methods using single domain features. (2) Sparse Autoencoder Long Short-Term Memory based Generative Adversarial Network (SLGAN) is proposed to solve the data imbalance problem. The proposed SLGAN model generates new baby cry data to ensure the number of samples for every cry class is equal. Speech features are extracted using Mel spectrograms and Short-Time Fourier
Transform (STFT). Two deep learning models, i.e. VGG16 and VGG19 are used to extract the deep features. The deep features are then dimensionally reduced by using Principal Component Analysis (PCA). A sparse autoencoder model is used to fuse the deep features. Finally, the fused features are trained and classified using the DNN. The experimental results show that the proposed method outperforms the existing methods. (3) An improved Dempster-Shafer evidence theory (DST) based on Wasserstein distance and Deng entropy is proposed to solve the evidence conflict by combining the credibility degree between evidence and the uncertainty degree of evidence. To validate the effectiveness of the proposed method, examples are analyzed, and applied in baby cry recognition. The Whale optimization algorithm-Variational mode decomposition is used to optimally decompose the baby cry signals. The deep features of decomposed components are extracted using the VGG16 model. The long Short-Term Memory model is used to classify the baby cry signals. An improved DST decision method is used to obtain the decision fusion. The experiment results show that the proposed fusion method can reach the highest recognition accuracy of 90.15%, which is higher than the results of other studies
Impact of bin weather data and climate change on air conditioning in the tropics / Wong Chun Mun
No full textThis study addressed several research gaps in academic field of bin weather data due to a lack of conducted studies that comprehensively explores the impact of bin weather data and climate change on air conditioning in tropics. Bin weather data are generated for four cities in Malaysia: Bayan Lepas, Kuala Terengganu, Kuching, and Senai, spanning from 2001 to 2018. Bin method simulations are computed, indicating deviations of under 1.6% when utilising the mean temperature of occupied period instead of the bin weather data. However, the application of annual mean outdoor temperature yields a larger deviation, ranging from 11.55% to 16.68%. Results show that mean temperature of occupied period is a viable alternative to bin weather data. Experimental works are conducted to investigate the energy consumption of HVAC system while operating under both the Energy Recovery Ventilation (ERV) and conventional ventilation systems. ERV system in heat exchange mode consume 32.64% less daily A/C energy per ΔT and 27.04% less daily total HVAC system energy per ΔT than exhaust fans, at a similar ventilation rate. Based on the parameters of experiments conducted, energy consumption is simulated with bin method. The percentage error between calculated energy consumption and actual energy consumption varies from 3.89% to 30.55%. Factors that can influence the performance of bin method include differences between the set temperature and the actual indoor temperature, insensitivity of air conditioner temperature sensors, application of non-identical operating characteristics, variations in air conditioner loads, CLTD/SCL/CLF method limitations, granularity of bin temperature basket, and energy recovery function for the ERV system. This research also studied the climate change impacts on bin weather data and determine the recommended lifespan of bin weather data for the selected cities. In Bayan Lepas, the percentage difference of bin weather data for the years 2001 to 2015 ranges from -1.93% to 8.08%, showing no apparent trend of climatic change. Bin weather data of Kuala Terengganu and Senai has a recommended lifespan of 2 years based on a data variation threshold of 5%. However, if higher threshold of 10% is applied, the recommended lifespan for Kuala Terengganu and Senai could be extended to 4 and 8 years respectively. Kuching has a recommended lifespan of at least 15 years for bin weather data due to its lack of apparent climatic change. A total of 61 simulation cases are conducted to analyse the climate change impacts on bin method. Although simulated cases for Bayan Lepas did not show any consistency, the deviation of total energy consumption for other cities ranges from -1.36% to -4.69% in Kuala Terengganu, from -0.74% to -4.61% in Kuching, and from -2.24% to -7.35% in Senai. This research has successfully developed updated bin weather data for cities located in tropics, identified the significance of bin weather data and compatibility of mean temperatures, evaluated the performance of bin method simulations, and investigated the climate change impacts on bin weather
Friction stir alloying of AZ61 magnesium alloy and SPHC mild steel with ZN-CNT additive / Muhammad Zulhiqmi Mohd Jamil
No full textJoining dissimilar materials is one of the effective techniques and solutions for materials enhancement in strength and durability that could give more design flexibility. Different materials are joined together to produce a new lightweight combination that can be applied in various manufacturing and production related to aerospace, automotive, shipping and other industries. Magnesium alloy and mild steel were selected as the combinations as both materials have advantageous material characteristics and properties. Magnesium is lightweight and has vast applications used in the industry, meanwhile, mild steel has good strength and durability. The critical challenges in joining both materials are their vast differences in physical, mechanical, and chemical properties. The immiscibility of the two materials presents a challenge in their joining process. In this study, 1.5 mm of dissimilar AZ61 and SPHC mild Steel were welded in the butt joint configuration with different percentages of zinc-carbon nanotube powder added as an additive to promote and enhance the strength of the joint. Zinc is soluble with both Mg and Fe. Based on the phase diagrams of Zn–Mg and Zn–Fe, it shows well interactions between the elements. The joint was evaluated in terms of tensile strength, microhardness, and microstructural observation through Scanning Electron Microscopy with Energy Dispersive X-ray Spectroscopy (SEM-EDS) and Transmission Electron Microscopy (TEM). Tensile test & microhardness results showed a significant enhancement of 125% and 495 HV for samples with 1 % CNT-Zn (balance) additive, respectively. Microstructural analysis revealed that the CNT was well dispersed in the joint interface at 15 mm/min welding speed. The addition of CNT, coupled with the intermetallic compound detected, is assumed to have contributed to the joining strength
A mean convolution layer for network intrusion detection systems / Leila Mohammadpour
No full textOver the past two decades, the remarkable advancement of Internet applications has underscored the paramount importance of securing the information network. To safeguard this vital infrastructure, the deployment of a robust intrusion detection system (IDS) has become imperative. Such a system must continuously adapt to the ever-evolving threat landscape, accurately discerning novel attacks while minimizing false alarms. Researchers have delved into the realms of data mining and machine learning, devising several supervised and unsupervised methods for the reliable detection of anomalies. Within this domain, deep learning emerges as a potent subfield, leveraging a neuron-like structure to learn and execute complex tasks. Notably, the convolution neural network (CNN) stands as one of the most successful deep learning techniques. However, its suitability for detecting anomalies remains limited. The essence of the issue lies in the CNN's innate propensity to excel in identifying anticipated input flow content, rendering it less effective in pinpointing the subtle deviations characteristic of anomalies. To address this challenge, a specific methodology is needed to discern these slight deviations accurately. Thus, this study proposes a new approach – the mean convolution layer CNN (MCL-CNN) architecture. Designed specifically to grasp the unique content features of anomalies, MCL-CNN enables effective detection of abnormal patterns. By introducing an innovative form of the convolutional layer, MCL-CNN excels in capturing low-level abnormal characteristics, bolstering the design of a robust network intrusion detection system. Empirical evaluations on the CICIDS2017 and NSL-KDD datasets validate the superior performance of the recommended MCL-CNN model. Notably, it exhibits outstanding real-world application potential, boasting highly accurate anomaly detection capabilities and significantly reducing false-alarm rates when compared to existing state- of-the-art models. The evaluation results reveal that the MCL-CNN model achieved an impressive accuracy rate of 99.82% in identifying anomalies, demonstrating its exceptional precision and reliability. Moreover, the false alarm rate was remarkably low, standing at a mere 0.06%, showcasing the model's ability to discern genuine anomalies from normal network activities with great precision and efficiency. In conclusion, this study pioneers an innovative approach to anomaly detection, harnessing the power of deep learning while specifically addressing the challenges posed by abnormal data patterns. The MCL-CNN model represents a promising leap forward in fortifying information network security and proactively countering ever-evolving cybersecurity threats
Development of XGboost model for wave overtopping using enhanced clash database / Mohamed Tarek Mohamed Fouad
No full textThe accurate prediction of wave overtopping is crucial for designing resilient coastal structures. This thesis presents a comprehensive study on estimation of wave overtopping using (XGB) algorithm, with a focus on both model development and experimental validation. In the first part of the thesis, the focus was on the development of the XGB model for wave overtopping prediction. The methodology started with exploring the database parameters, followed by rigorous data preprocessing to ensure data quality. The model tuning process was elaborated, incorporating the utilization of hyperparameters to enhance predictive performance. After the preprocessing phase, the number of parameters chosen for the model development was 36 parameters, while the number of data points taken from the dataset was 5670 tests. The preprocessed database was split into 70% for training and 30% for testing in the XGB model. The model attained high predictive accuracy with RMSE of 0.28 m3/s/m, a percentage error of 4.9%, and a high correlation coefficient (R) of 0.95. Percentage error was used as the primary error metric, underpinning its effectiveness in quantifying differences in prediction. The thesis examined model performance in different conditions by categorizing wave overtopping rate (q) data into low, medium, and high ranges. The low range consisted of 893 points while the medium and high range contained 772 and 36 points respectively. RMSE values for low, medium, and high q ranges were 0.34 m3/s/m, 0.23 m3/s/m, and 0.17 m3/s/m, respectively. The percentage error statistics for these ranges were 4.9%, 4.9%, and 7.4%, respectively. Model validation is executed via the bootstrap resampling technique to reveal the model inherent robustness. Following the implementation of the resampling technique, the model showed a poorer result, with an RMSE of 0.31 m3/s/m, an R value of 0.94, and a percentage error of 5.4%. To validate the performance of the model, the results were compared to an existing XGB model developed by Den Bieman (DB) that used the same database. Achieving similar results confirmed the good performance of the model and the XGB technique reliability. The second part of the thesis delved into the experimental aspect, contributing novel data to the existing database. A thorough designed experiment was conducted within the National Hydraulic Research Institute of Malaysia (NAHRIM), featuring comprehensive information about the wave flume, wave generator system, and data acquisition setup. The experimental design, encompassing wave conditions and data collection procedures, was outlined. Adding 49 new tests to the existing database had a small impact on predictive performance, with a percentage error of 10.09% for the original dataset and 10.43% for the updated dataset. The combination of model development and physical experiment contributed to a better understanding of wave overtopping phenomena. The results underscored the potential of the XGB algorithm in accurate wave overtopping prediction, while also emphasized the challenges and considerations when integrating experimental data into existing predictive frameworks