Browse Items (16481 total)
Sort by:
-
A Spiking Neural Network Approach to Electroencephalography based Consumer Preference Modeling
Neuromarketing is an emerging interdisciplinary field that applies neuropsychology in marketing to study consumer sensory-motor actions such as cognitive and affective responses to marketing stimuli through Brain Computer Interface (BCI) technology. While marketers spend over 750 billion dollars annually on traditional marketing procedures such as surveys, interviews, and consumers feedback, these methods are often criticized for their inability to capture genuine consumer preferences. Neuromarketing promises to overcome such issues by analyzing neural responses directly. This paper presents a novel framework for predicting consumer preferences by analyzing Electroencephalography (EEG) signals. EEG signals are acquired from 25 volunteers while administering 14 products with three different variations. The EEG signals are preprocessed using Modified Wavelet Thresholding (MWT) to remove noise while preserving neural activity patterns. A third-generation network, Spiking Neural Network (SNN) is designed to recognize consumer preferences based on EEG frequency bands. Unlike conventional models, SNN captures temporal dynamics through spike timing, which is crucial for EEG signals. The efficacy of the model is tested across individual EEG bands to identify the most influential frequency band in decision-making. Simulation outcomes demonstrate that the proposed model can effectively predict consumer preferences. The model achieved an accuracy of 90.91%, recall of 90.7%, a precision of 91.14%, a specificity of 91.12%, and an F1-score of 90.92%. The outcomes highlight the potential of EEG based neuromarketing systems to decode subconscious consumer responses, enabling brands and businesses to design more targeted marketing strategies based on objective neural data. 2025 Inventive Research Organization. -
Decoding Breast Cancer Mutational Signatures: A Hybrid ElasticNetXGBoost Approach Using Gene Expression Data
TP53, PIK3CA, and MUC16 are somatic mutations that are useful in breast cancer progression and prognosis, but direct mutation profiling based on sequencing is not always practicable in practice. The data about gene expression can contain indirect transcriptomic patterns linked with mutational underlying states. This paper proposes an expression-based machine learning model to predict the status of mutations using METABRIC breast cancer cohort. Instead of directly estimating genetic changes, the suggested method estimates statistical relationships between transcriptomic phenotypes and binary somatic mutation states. A multi-stage gene features selection pipeline using variance filtering, mutual information ranking, and correlation pruning was used to reduce the number of genes (19,000). A hybrid predictive architecture was trained using these features that combined ElasticNet logistic regression and XGBoost that allowed balancing between linear regularization and nonlinear interaction modeling. The hybrid model with a combination of five-fold stratified cross validation yielded mean ROC-AUC of 0.94 (TP53), 0.92 (PIK3CA), and 0.90 (MUC16) with the stability of the calibration and equal error rates. Coefficient analysis and SHAP-based explanations were used to investigate the interpretability of the models to describe the expression patterns on mutation status. The suggested framework is a hypothesis-generating, complementary method of transcriptomic analysis, which must be reevaluated by external validation to determine the wider generalizability. 2026, International Journal of Prognostics and Health Management. All rights reserved. -
Exploring the influence of Retail Value Chain Support Activities on Shoppers Behaviour: Ordered Probit Model Approach
The support activities that make up the retail value chain also play a role in defining the in-store experiences and their contentment of the customers. The underlying aim of this investigation is thus to explain the impact of core support functions, here firm infrastructure, human resource management, technology management as well as procurement practices in the customer satisfaction within formally-organised retail outlets. A total of 500 consumers visiting hypermarkets and department stores in Visakhapatnam were used to gather primary data through a structured questionnaire that used a five-point Likert scale. Empirical evidence shows that a few activities of the retail value-chain support have a tremendous impact on customer satisfaction, and such activities as technology-enabling services, efficient procurement practices and infrastructure-related service attributes are particularly significant. These findings support the argument that optimisations on the functional aspects in the value chain generate a measurable increase in consumer satisfaction and thereby serve to support the strategic relevance of support activities in the retail sector. This study enhances the existing body of literature on retail-management by integrating the value-chain perspective and consumer-behavioural analysis to provide relevant empirical support on the strategic contribution of support functions in creating shopper-satisfaction. 2026, PT Mattawang Mediatama Solution. All rights reserved. -
Explainable Hybrid Deep Learning Framework with Multimodal Inputs for Diabetic Retinopathy Detection
Diabetic Retinopathy (DR) is a leading cause of vision loss, making accurate and interpretable detection critical. This study proposes a hybrid interpretable machinedeep learning framework that integrates multimodal data for enhanced DR severity classification. The model combines unstructured fundus images from EyePACS, Messidor, and APTOS with structured clinical and lifestyle variables such as age, sex, HbA1c, BMI, blood pressure, and diabetes duration. Fundus images undergo preprocessing through resizing, normalization, augmentation, and noise reduction, while clinical data are imputed, normalized, and one-hot encoded. For feature extraction, EfficientNetV2, ResNet50, and Swin Transformer are applied to images, and XGBoost, LightGBM, and TabNet to clinical data. Features are fused via concatenation and attention, followed by classification using Logistic Regression, Random Forest, and MLP. Explainability is provided by Grad-CAM for imaging data and SHAP/LIME for clinical data, supporting clinical interpretability. The proposed model outperformed unimodal baselines, achieving 99.34% accuracy, 98.5% precision, 98.0% recall, 99.0% specificity, 98.2% F1-score, and 0.99 AUC-ROC, with a 10% gain over ResNet50 alone. Performance improvements included a 9% increase in recall and 8% in F1-score, alongside excellent calibration. Confusion matrix analysis confirmed balanced severity detection, and clinicians validated the interpretability outputs. This framework demonstrates robust accuracy, generalization, and clinical applicability for DR screening. 2026, An-Najah National University. All rights reserved. -
A study on branding strategies (green innovation and international marketing) and their impact on purchase decision involvement of customers in the textile industry, with disposable income as a moderating factor; [Studiu privind strategiile de branding (inova?ie ecologic? ?i marketing interna?ional) ?i impactul acestora asupra implic?rii decizia de cump?rare a clien?ilor din industria textil?, cu venitul disponibil ca factor moderator]
Branding strategies and customer involvement have become central to Indian businesses as sustainability gains prominence across both offline and online businesses. Due to rising environmental concerns, companies are focusing on sustainable practices, energy-efficient solutions, and eco-friendly products to meet consumer demands and regulatory standards. Purchasing the products based on green innovative marketing strategies has attracted people from various nations, too. However, purchasing decisions vary from one individual to another based on the driving factors like persona, psychological, economic, payment mode, social, quality, trust, cost, reputation, reviews and offers. In this research, the association between branding strategies as an independent factor using green innovation and international marketing strategies against the dependent factor, customer involvement in the textile industry, is examined. The moderating factor disposable income is adopted here, which gives this research its uniqueness, significance and novelty. The research adopts SEM analysis for examining the variables and the Hayes Process for moderating factor analysis. The targets are people who are interested in fashion clothing. The sample size used is n=589. The findings showed that there exists an association between green innovation in marketing (GIM) and purchase decision involvement (PDI) and international marketing (IM) and PDI. Similarly, the moderating factor, disposable income (DI), moderates the association between GIM and PDI; whereas it doesnt moderate the IM and PDI. Thus, the research concluded that the disposable income as a moderating factor certainly impacts the purchase decision of the customers and international marketing strategies in the fashion clothing in textile industry. 2025, Institute National Cercetare-Dezvoltare Textiles Pielarie. All rights reserved. -
Bridging Science and Spirituality: Investigating the Effects of OM Chanting on Brain Waves
In Hindu tradition, the syllable "OM" holds significant spiritual and cultural value in Hindu tradition and is believed to produce positive psychological and physiological effects. Despite its prominence in spiritual practices, the neurophysiological basis for these benefits remains underexplored. In this study, electroencephalography (EEG), a non-invasive method for measuring electrical activity in the cerebral cortex, was employed to investigate the physical changes in brain wave patterns that occur when listening to OM chanting. Five frequency bands, namely delta, theta, alpha, beta, and gamma, are associated with brainwaves recorded through EEG, which define different states of cognitive and emotional nature. With these, this research analyzes EEG signals before and after chanting to identify and quantify changes, and to discuss the therapeutic implications. Several signal processing techniques, such as time and frequency domain analysis, assess variations in amplitude, frequency, and coherence across different brain regions. These findings show an increase in alpha amplitudes (34.2%) and an 85.4% improvement in the theta/beta ratio, related to relaxation, emotional regulation, and additional focus, as well as a decrease in beta waves, linked to stress and cognitive overload. This would show stronger neural integration between the brain hemispheres. The OM chanting evoked these results as a possible neurotherapeutic tool for stress management and cognitive enhancement. In bridging ancient spiritual practices with modern neuroscience, this study provides information on how such seemingly nonsensical meditations as OM chanting can enhance brain function, which is favorable for the third Sustainable Development Goal (SDG) of the United Nations, regarding the goal of healthy life and wellbeing throughout all ages. Further research should be done into these effects in different populations and over long periods to confirm that this is a long-term therapeutic effect. 2025, Sakarya University. All rights reserved. -
LungDxNet: AI-Powered Low-Dose CT Analysis for Early Lung Cancer Detection
Early and accurate diagnosis, however, is still lacking for the most common form of lung cancer, and this remains one of the leading cancers leading to mortality. CT scans are widely used for lung cancer screening; however, their manual interpretation is time-consuming and prone to variability. This study introduces LungDxNet, a deep learning-based framework that integrates transfer learning to enhance diagnostic accuracy and efficiency. Using a large dataset of Low Dose CT (LDCT) scans, the system is built with fine-tuned pre-trained Convolutional Neural Networks (CNNs) such that feature extraction is reliable though minimal reducing radiation exposure. Consequently, LungDxNet involves the integration of component segmentation techniques that have been used to isolate the lung regions and discriminate the cancerous nodules from the malignant and benign cases. Very rigorous evaluations were performed on the model against both conventional machine learning and state of the art deep learning architectures. Results show that there is a substantial reduction of false positive and false negative resulting in a superior accuracy (98.88), sensitivity, and specificity. This design is to be scaled, robust and clinically applicable, making it a potential real world lung cancer diagnosis tool. Deep learning and transfer learning has excellent power to transform lung cancer detection, and this research brings awareness of how far we can optimise and integrate into clinical workflow. The model is enhanced for future work and adapted for real time diagnostic applications. 2025, Sakarya University. All rights reserved. -
Frames of Isolation: A Reading Through HIV/AIDS Documentaries
The question is: how can a documentary create social impact on its audience and, in turn, on society? Film critics and social scientists have considered this question since the inception of documentary filmmaking. Moreover, in the context of disseminating knowledge about infectious diseases, particularly during the HIV/AIDS epidemic, documentaries played a significant role in educating the public about the disease. Following the epidemic, documentaries were used to understand the disease and to witness the lives of people living with the virus. This article further extends the discourse of documentary studies by critically analysing two specific HIV/AIDS documentaries, 5B (2018) and Desert Migration (2015). This analysis provides insight into how the frames of the moving image capture the isolated spaces occupied by people with HIV/AIDS. For this study, Edward Branigans concept of frames is adopted to explore the essence of isolation. This is achieved by examining frames captured by the filmmakers through the camera lens, with a focus on the immediate surroundings of the person being interviewed. The article terms these frames Frames of Isolation, as the images reflect the spatial and emotional isolation associated with the virus. 2025 House of the Book of Science. All rights reserved. -
Urban cooling optimization in Ahmedabad: Defining optimal radius for the thermal performance of water bodies and green spaces
Urban water bodies and vegetation are integral components of urban landscapes. They contribute to thermal comfort, providing essential cooling effects that alleviate the impacts of rapid urbanization. The study emphasizes the importance of planning and performance assessment of these landscapes to achieve maximum cooling and extend their influence effectively. It is well-documented that urban vegetation and water bodies reduce local temperatures which can be evaluated through various landscape indices suggesting that the shape and configuration of these areas greatly impact their cooling capabilities and influence. To explore this further, a spatio-temporal analysis focusing on Land Surface Temperature (LST) is conducted by using high-resolution satellite imagery in 39 water bodies and 130 dense vegetation sites in Ahmedabad, Gujarat to identify thermal patterns and assess the cooling performance of landscape features. The analysis aimed to understand the relationship between temperature changes and the radius of landscape sites leading to the identification of the Radius of Saturation (R_sat) which is the maximum distance around a water body or green space where its cooling effect is most effective. The results indicated that the R_sat is 150 meters for water bodies and 130 meters for dense vegetation. These radii mark the points at which further increases in size do not significantly enhance the cooling effect, signifying the saturation point for thermal influence. This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/). -
A bibliometric analysis of compact city for sustainable urban development
This work provides a detailed bibliometric review of compact city literature for sustainable urbanism from 1983 to 2023. The compact city concept has received considerable attention as a possible approach towards solving sustainable city issues. Hence, based on the documents obtained from the Scopus database, we studied the research topics and authors, as well as the thematic development of this topic. The research used the bibliometric approach of citation analysis, keyword cooccurrence, and thematic evolution mapping. Research indicates that there is an Increased research productivity over the recent past especially in the last two decades. Among developed countries, China has become one of the most active participants in the provision of new knowledge. The thematic focus has shifted from pure and applied to complex themes like sustainability, GIS and urban design. The current trends show increasing concern about sustainability, development, and the 15-minute city model. The proposed analysis also reveals the unequal Within the group of countries, citation rates vary significantly, and the scope of methodological approaches is insufficient. In summary, this review finds that although compact city research has evolved to a certain extent, typological models are still lacking context sensitivity; international cooperation remains rather limited; and finally, many long-term outcomes have not been adequately investigated in order to unleash the full potential of compact cities as a global model of sustainable urban development. This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/). -
Valorisation of starfruit waste derived pectin for biodegradable sheet fabrication: A comprehensive study on extraction and characterization
This research work focuses on the extraction and characterization of pectin from starfruit peel and its application for fabrication of pectin film. Starfruit is chosen as the source for pectin extraction as the data regarding pectin extraction starfruit is relatively scarce in the available literature. Conventional organic acid based extraction using citric acid is employed for pectin extraction as it is eco-friendly and cost effective. The yield of pectin was found to be 8.22 1.018 (w/w). Fourier-transform infrared spectroscopy (FT-IR), analysis is used to identify functional groups present in the extracted pectin and X-ray Powder Diffraction (XRD) is done to check its crystallinity. Furthermore, scanning electron microscopy (SEM) characterization was performed to deduce the morphological characteristics of the extracted biopolymer. The particle size was found to be between 1m and 20 m. Fabrication of pectin based film was done using solvent cast method. The biodegradable film developed was found to be transparent and flexible. This work highlights the use of starfruit as a cost effective substrate for pectin extraction. Future studies should aim at exploring various applications of pectin and utilizing its potential in diverse applications. This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/). -
Revisiting the PushPull Tourist Motivation Model: A Theoretical and Empirical Justification for a ReflectiveFormative Structure
This study introduces a novel reflectiveformative hierarchical model specification for the classic pushpull tourist motivation construct, aligning its measurement with the theoretical distinction between intrinsic push drives and external pull attributes. Unlike the traditional reflective-reflective structuring of tourist motivation we defied the higher order factors (novelty, knowledge and facilities as formative. Using partial least squares structural equation modeling (PLS-SEM) on a purposive sample of 319 international tourists, we empirically validate the reflectiveformative (reflective first-order, formative second-order) model. The reflectiveformative model showed a superior fit and predictive power: it explained substantially more variance in key outcome constructs (social motives (R2 = 53.60) and self-actualization (R2 = 23.10)) than the traditional reflectivereflective specification (social motives (R2 = 49.30) and self-actualization (R2 = 21.70)), which is consistent with best-practice guidelines for theoretically grounded models. In contrast, the incorrectly specified reflectivereflective model showed stronger effects between unrelated constructs, supporting concerns that choosing the wrong type of measurement model can lead to incorrect conclusions. By reconciling the pushpull theory with measurement design, this works main contributions are a theoretically justified reflectiveformative model for tourist motivation, and evidence of its empirical benefits. These findings highlight a methodological innovation in motivation modeling and underscore that modeling pushpull motives formatively yields more accurate insights for theory and practice. 2025 by the authors. -
A Gauss Hypergeometric-Type Model for Heavy-Tailed Survival Times in Biomedical Research
In this study, we introduced and analyzed the SlashLogLogistic (SlaLL) distribution, a novel statistical model developed by applying the slash methodology to loglogistic and beta distributions. The SlaLL distribution is particularly suited for modeling datasets characterized by heavy tails and extreme values, frequently encountered in survival time analyses. We derived the mathematical representation of the distribution involving Gauss hypergeometric and beta functions, explicitly established the probability density function, cumulative distribution function, hazard rate function, and reliability function, and provided clear definitions of its moments. Through comprehensive simulation studies, the accuracy and robustness of maximum likelihood and Bayesian methods for parameter estimation were validated. Comparative empirical analyses demonstrated the SlaLL distributions superior fitting performance over well-known slash-based models, emphasizing its practical utility in accurately capturing the complexities of real-world survival time data. 2025 by the authors. -
Design and Analysis of Reliability Sampling Plans Based on the ToppLeone Generated Weibull Distribution
As part of this study, we design a reliability acceptance sampling plan under the assumption that the lifetime of a product follows the ToppLeone generated Weibull (TLGW) distribution, a model that exhibits structural symmetry in its hazard rate behavior and distributional form. The fundamental procedures for constructing such a plan are described. We compute and tabulate the minimum sample sizes required for given risk criteria using both binomial and Poisson models for the number of failures. We also provide the operating characteristic (OC) values for the proposed sampling plans, and determine the minimum ratios of true mean life to specified mean life needed to satisfy a given producers risk. The role of symmetry in the TLGW distribution is highlighted in its balanced tail properties and shape characteristics, which influence the performance of the acceptance sampling plan. Finally, we illustrate the applicability of the proposed plan with real-world data. 2025 by the authors. -
A Predictive Framework for Sustainable Human Resource Management Using tNPS-Driven Machine Learning Models
This study proposes a predictive framework that integrates machine learning techniques with Transactional Net Promoter Score (tNPS) data to enhance sustainable Human Resource management. A synthetically generated dataset, simulating real-world employee feedback across divisions and departments, was used to classify employee performance and engagement levels. Six machine learning models such as XGBoost, TabNet, Random Forest, Support Vector Machines, K-Nearest Neighbors, and Neural Architecture Search were applied to predict high-performing and at-risk employees. XGBoost achieved the highest accuracy and robustness across key performance metrics, including precision, recall, and F1-score. The findings demonstrate the potential of combining real-time sentiment data with predictive analytics to support proactive HR strategies. By enabling early intervention, data-driven workforce planning, and continuous performance monitoring, the proposed framework contributes to long-term employee satisfaction, talent retention, and organizational resilience, aligning with sustainable development goals in human capital management. 2025 by the authors. -
ESG Narrative Quality in Green Bond Disclosures: Implications for Risk Perception, Transparency, and Market Trust
This research evaluates the extent to which firms green bond disclosures create and convey a meaningful representation of their Environmental, Social, and Governance (ESG) commitments. Additionally, this research explores how investors distinguish between disclosures that represent genuine commitment to sustainability and those that may be indicative of greenwashing, and how such distinctions impact their assessment of an issuers credibility as well as the issuers performance subsequent to the issuance of a green bond. The methodology employed in this research employs a convergent mixed-methods approach that combines quantitative methods (Natural Language Processing (NLP), financial modeling, etc.) with qualitative methodologies (case studies, interviews). The NLP methodology employed in this research includes sentiment analysis, topic modeling, and ambiguity measurement in order to determine the tone, thematic content, and linguistic clarity of the disclosure texts. Subsequently, the results of the NLP methodologies are correlated with firm level outcomes using cross validated partial least squares regression (PLS-R), event study methodologies, and one way ANOVA to test for temporal and industrial variability. Finally, the results of the computational and financial methodologies are supplemented by qualitative case studies and interviews to provide context for the patterns identified in the computational and financial methodologies. In summary, the results of this research demonstrate that firms that communicate in a clear, balanced, and verifiable manner experience better market reaction and more favorable accounting results subsequent to the issuance of a green bond than do firms whose communications are vague, overly optimistic, or lacking in consistency. Conversely, the findings suggest that investors have become increasingly sensitive to potential greenwashing and therefore are less likely to respond favorably to communications characterized by the aforementioned characteristics. 2025 by the authors. -
K???an???am Performance: K???a Devotion, Ritual Ecology, and Colonial Transformation in South India
This paper critically explores K???an???am, a Sanskrit ritual dance-theater tradition from Kerala, as a product of socio-political and religious transformations in early modern South India. Conceived in the mid-17th century by the Zamorin King M?nav?da, author of the Sanskrit text K???ag?ti, K???an???am was both a devotional offering to Lord K???a and a strategic expression of ritual sovereignty. Rooted in K???a bhakti (devotion), the tradition reflects how religious performance was mobilized to assert political legitimacy, particularly amid rivalry with regional powers such as Travancore. The Guruvayur Sri Krishna Temple, situated in the Malabar region of northern Kerala and central to the performance of K???an???am, emerged as a vital sacred space where royal patronage, ritual authority, and caste hierarchy intersected. The performances exclusivity restricted to Hindu audiences within temple premises reinforced patterns of spatial control and caste-based exclusion. Institutional support codified the tradition, sustaining it across generations within a narrow sociocultural framework. With the decline of Zamorin rule and the onset of colonialism, K???an???am faced structural disruptions. Colonial interventions in temple administration, landholding, and religious patronage weakened its ritual foundations. Guruvayurs transformation into a public devotional center reflected wider shifts in ritual ecology and sacred geography under colonial modernity. In both the colonial and postcolonial periods, K???an???am struggled to survive, nearly facing extinction before its revival under the Guruvayur temples custodianship. By examining K???a devotion, royal ambition, caste dynamics, and colonial transformation, this paper offers a critical lens on Keralas evolving religious and cultural landscapes. 2025 by the authors. -
Enhancement of Phenolic and Polyacetylene Production in Chinese Lobelia (Lobelia chinensis Lour.) Plant Suspension Culture by Employing Silver, Iron Oxide Nanoparticles and Multiwalled Carbon Nanotubes as Elicitors
Silver nanoparticles (AgNPs), iron oxide nanoparticles (Fe2O4NPs), and multiwalled carbon nanotubes (MWCNTs) are widely used in various applications, such as biomedicine, environmental remediation, and agriculture. In addition, these nanomaterials can affect the production of bioactive compounds in plants that have pharmacological activities. In the current study, the in vitro plant cultures of Chinese lobelia (Lobelia chinensis Lour.) were established in MS medium and treated with 0, 12.5, 25, 37.5, and 50 mg L?1 AgNPs or Fe2O4NPs, or MWCNTs. Initially, plants were grown for four weeks without any elicitors, and after that, the cultures were treated with nano-elicitors for one week. After five weeks, the effects of nano-elicitors were estimated on growth, total phenolic, flavonoids, polyacetylenes, and ABTS/DPPH/FRAP antioxidant activity was investigated. The results showed that lower levels of AgNPs (25 mg L?1), Fe2O4NPs (25 mg L?1), and MWCNTs (12.5 mg L?1) favored the accumulation of fresh and dry biomass. Whereas, 37.5 mg L?1 AgNPs, 25 mg L?1 Fe2O4NPs, and 37.5 mg L?1 MWCNTs enhanced the accumulation of total phenolics, flavonoids, specific phenolic compounds including chlorogenic acid, catechin, phloretic acid, coumaric acid, salicylic acid, naringin, myricetin, linarin, and polyacetylenes viz. lobetylonin and lobetyolin in higher concentrations. The plant extracts elicited by nanomaterials also depicted very good antioxidant activities according to ABTS, DPPH, and FRAP assays. These results suggest that specific nanomaterials, and at specific levels, could be used for the production of bioactive compounds from shoot cultures of Chinese lobelia. 2025 by the authors. -
AI-Driven Stacking Ensemble for Predicting Total Power Output of Wave Energy Converters: A Data-Driven Approach to Renewable Energy Processes
This study develops and evaluates an AI-driven stacked hybrid machine learning model for predicting the total power output of wave energy converters (WECs) across four Australian coastal locations: Adelaide, Perth, Sydney, and Tasmania. This research enhances prediction accuracy through advanced ensemble learning techniques while addressing spatial variability in wave energy processes. The dataset comprises spatial coordinates and power output readings from 16 fully submerged WECs per location, capturing the variability of wave energy across different coastal regions. Data preprocessing included missing value imputation, duplicate removal, and spatial feature transformation via Euclidean distance calculation. Principal component analysis (PCA) was employed to reduce dimensionality while preserving critical features influencing power generation. To develop an accurate prediction model, we employed a stacking ensemble approach using XGBoost, LightGBM, and CatBoost as base learners, optimized via Optuna hyperparameter tuning with 10-fold cross-validation. A Ridge regression meta-learner combined the outputs of these models, leveraging their complementary strengths to enhance predictive performance. Experimental results demonstrate that the hybrid model consistently outperforms individual models, enhancing predictive accuracy across all locations. Sydney exhibited the highest accuracy (RMSE = 9089.58 W, R2 = 0.8576), while Tasmania posed the greatest challenge (RMSE = 45,032.37 W, R2 = 0.8378). The ensemble approach mitigated overfitting and improved generalization by leveraging the complementary strengths of XGBoost, LightGBM, and CatBoost. By leveraging AI-driven ensemble learning, this study provides a scalable and reliable framework for wave energy forecasting, facilitating more efficient grid integration and resource planning in renewable energy systems. 2025 by the authors. -
StructureProperty Relationships Governing Rheological, Damping, and Thermal Behaviour of Immiscible Natural Rubber/Nitrile Rubber Blend Nanocomposites
Polymer nanocomposites have been attracting significant interest over the last three decades. One of the most intriguing applications is related to the preparation of clay-filled nanocomposites based on rubber blend matrices. Although several studies already exist on the subject, there is limited information available regarding their rheological, thermal, and, particularly, damping behaviour of rubber blend systems. In this work, the rheological, viscoelastic, and thermal behaviour of a natural rubber/nitrile rubber (NR/NBR) blend nanocomposite containing organically modified nanoclay was systematically investigated, and the damping characteristics were also assessed. At a lower nanoclay concentration (5 phr), network formation through fillerfiller and fillerpolymer interactions led to partial immobilization of polymer chains, resulting in a pronounced increase in viscosity and enhanced viscoelastic response. In contrast, at higher nanoclay loading (10 phr), strong agglomeration of filler particles occurred, corresponding to a stacked clay morphology, which hindered effective fillerfiller network formation and weakened fillerpolymer interactions, leading to lower viscosity and reduced damping efficiency. The blend composition and filler content were found to significantly influence the investigated properties, especially the hysteresis loss and the thermal conductivity, which is explained by matrixfiller interactions and the resulting morphology of the system. 2026 by the authors.