Nur Suhaili Mansor

Although the Delone and McLean IS Success Model (D&M) can explain the phenomenon of e-participation success (EPS), the model was initially created in an e-commerce setting and thus neglects external factors related to e-government services. To address the gap, this study revisits the D&M by extending it with four socio-cultural constructs of Trust (TR), Anonymity (AN), Nationalism (NT), and Culture (CR). Based on 428 survey data from Malaysian citizens, a hybrid methodology was employed, integrating Partial Least Squares-Structural Equation Modelling (PLS-SEM) and Multi-layer Perceptron (MLP) to capture non-linear relationships and enhance predictive accuracy. While hybrid modelling is common, past studies have often applied limited classification metrics, and the infrequent use of comprehensive metrics, such as Area Under the Receiver Operating Characteristic Curve (AUC-ROC), may potentially affect the reliability and generalizability of these models. A comparative R² analysis between the baseline and enhanced models in this study revealed significant improvements, with R² for e-participation intention (EPI) increased from 0.620 to 0.728, EPS from 0.330 to 0.345, while User Satisfaction (US) remained strong at 0.765. The analysis predicts a 94.80% success rate for e-participation, with the MLP model further demonstrating robust classification performance, achieving an accuracy of 90.1%, a precision of 0.909, a recall of 0.948, an F1 score of 0.928, and an AUC-ROC of 0.955, outperforming other benchmark classifiers. This study contributes theoretically by introducing underexplored socio-cultural variables into the D&M while methodologically extending the hybrid PLS-SEM and MLP through a robust model validation using AUC-ROC.

Geographic information systems (GIS) have gone through many phases of development since their inception several decades ago. GIS is a tool for analyzing and representing the geographic features of the Earth's surface and the events taking place using a computer system. The article concerns the presentation of the potential of GIS software and the increase in its use in scientific research. The first research area is the issue of air pollution, which is the main problem of highly urbanized regions. This research part presents a spatial analysis of changes in the level of pollution in the European Union countries. The second research area aims to present the functionality of GIS software in the field of mapping land use and socio-economic activities in the strongly changing process of urbanization and development of large urban agglomerations. Research in this area is a useful tool for visualizing dynamic changes related to urbanization changes in areas that can be used in spatial planning. The article presents the process of creating spatial development maps based on SPOT-5 covering the years 2000 and 2012 in order to develop spatial development maps and monitor changes in land use. Time series of SPOT-5 2000/2012 images will be compared to detect changes. This example was based on Sungai Petani from a selected city in Malaysia.

As the European Union’s energy systems are transforming towards achieving climate goals, this article examines the energy balances of EU member states. This analysis covers, among other things, the dynamics of energy dependence and strategies for decoupling economic growth from the level of emissions in the European Union (EU), with particular emphasis on Poland, which is strongly influenced by its historical reliance on coal in the energy balance. Using panel data from 1990 to 2022, the article investigates differences in energy dependence between individual countries, shaped by economic structures and national energy policies. The study results confirm significant heterogeneity between member states and emphasize that the stability and direction of decoupling economic growth from greenhouse gas (GHG) emissions are strongly dependent on the composition of the energy mix and vulnerability to external conditions. Based on scenario analysis, potential paths for Poland’s energy transition are assessed. We demonstrate that a high share of renewable energy sources (RES) significantly reduces CO₂ emissions, provided it is accompanied by infrastructure modernization and the development of energy storage. Furthermore, integrating nuclear energy as a stabilizing element of the energy mix offers an additional path to deep decarbonization while ensuring supply reliability. Finally, we demonstrate that improving energy efficiency and demand management can effectively increase energy security and reduce emissions, even in a scenario with a stable coal share. The study addresses a research gap by integrating decoupling analysis with scenario-based stochastic modeling for Poland, a country for which few comprehensive transition assessments exist. The results provide practical guidance for developing resilient, low-emission energy policies in Poland and the EU. Results are reported for 2025–2050 (with 2040 as an interim milestone).

Urban expansion and the corresponding increase in land surface temperature (LST) are significant environmental concerns worldwide. In Malaysia, the urbanisation rate has increased dramatically from 1970 to 2020, according to the Statistics Department. This rapid development, particularly in states such as Selangor, Johor, and Penang, has intensified surface heating and reduced ecological resilience, exacerbating the effects of climate change. Despite growing recognition of these impacts, many existing studies rely on static or predictive models that lack spatial precision and real-time monitoring. Malaysia has recorded an average LST increase since 2000, highlighting the urgent need for systematic, ICT-enabled frameworks to monitor and respond to thermal and environmental changes. This study aims to develop a scalable and replicable framework for monitoring LST changes linked to urbanisation by integrating vegetation-based indices and remote sensing technologies. The framework is demonstrated through a case study of Perak, Malaysia, which is an area experiencing accelerated urban growth and ecological stress. The study was conducted in four structured phases. First, satellite imagery from Landsat 8 and Moderate Resolution Imaging Spectroradiometer (MODIS) was collected using Google Earth Engine (GEE). Second, data preprocessing was performed to derive NDVI, Vegetation Cover Proportion (Pv), and surface Emissivity (Em). Third, spatial and temporal patterns were visualised. Finally, analysis was conducted to examine correlations between LST variation and land cover changes from 2019 to 2023. Findings reveal a consistent rise in LST and a decline in vegetation health in urbanising and deforested zones, confirming a reinforcing feedback loop of surface heat accumulation and ecological degradation. This ICT-driven framework provides a practical model for real-time environmental monitoring, supporting data-informed strategies in urban planning, reforestation, and climate adaptation, particularly in rapidly developing, climate-vulnerable contexts such as Malaysia.

Accurate and dynamic prediction of water quality indicators is increasingly critical due to rising pollution and water resource insecurity, particularly when dealing with high-dimensional, nonlinear time series data. Dissolved oxygen (DO), a key indicator of aquatic ecosystem health and pollution, requires high prediction accuracy for effective environmental management. This study aims to enhance the accuracy and adaptability of DO prediction by addressing the limitations of traditional deep learning methods, such as slow convergence and local optima. We propose a novel hybrid optimization framework that combines Nesterov-accelerated Adaptive Moment Estimation (Nadam) with the differential evolution algorithm. A dual-population cooperation strategy and an information exchange mechanism were incorporated during the training of a long short-term memory (LSTM) network to achieve a dynamic balance between global exploration and local exploitation. This improves the model’s optimization efficiency and generalization. The research utilized a multivariate water quality time series dataset from Kaggle based on official data monitoring. Correlation analysis was conducted to ensure the scientific validity and effectiveness of the selected input variables. Experimental results demonstrated that the proposed method significantly outperforms traditional optimization strategies for DO prediction. Compared to the original Nadam optimizer, it reduced the mean squared prediction error by 47.8%, exhibiting enhanced adaptability and robustness in complex pollution scenarios. This study presents an effective optimization strategy to improve LSTM performance in water quality forecasting, along with a scalable and interpretable intelligent analysis framework. It provides both theoretical and practical support for water quality forecasting, early warning systems, and intelligent environmental monitoring.

Accurate prediction of key environmental parameters is crucial for intelligent control and optimization, yet it remains challenging due to gradient instability in deep learning models, like Long Short-Term Memory (LSTM), during time series forecasting. This study introduces a novel adaptive optimization algorithm, NadamClip, which integrates gradient clipping directly into the Nadam framework to address the trade-off between convergence efficiency and gradient explosion. NadamClip incorporates an adjustable gradient clipping threshold strategy that permits manual tuning. Through systematic experiments, we identified an optimal threshold range that effectively balances model performance and training stability, dynamically adapting to the evolving convergence characteristics of the network across different training phases. Aquaculture systems are regarded as similar to modern biomanufacturing systems. The study evaluated an aquaculture dataset for ammonia concentration prediction in aquaculture environmental control processes. NadamClip achieved outstanding results on key metrics, including a Root Mean Square Error (RMSE) of 0.2644, a Mean Absolute Error (MAE) of 0.6595, and a Coefficient of Determination (R²) score of 0.9743. Compared to existing optimizer enhancements, NadamClip pioneers the integration of gradient clipping with adaptive momentum estimation, overcoming the traditional paradigm where clipping primarily serves as an external training control rather than an intrinsic algorithmic component. This study provides a practical and reproducible optimization framework for intelligent modeling of dynamic process systems, thereby contributing to the broader advancement of machine learning methods in predictive modeling and optimization for data-driven manufacturing and environmental processes.