IIC University of Technology

The optimization of reinforced concrete (RC) structural elements remains a fundamental aspect of sustainable and resilient building design. However, traditional methodologies are often constrained by manual heuristics, deterministic load assumptions, and a lack of transparency in computational modeling. This study introduces an integrated framework that combines nonlinear multi-objective evolutionary optimization with interpretable machine learning (ML) to derive and predict the optimal beam and column configurations for mid-rise residential buildings. The structural design space was derived from full-scale STAAD.Pro simulations of two reinforced concrete buildings, incorporating real-world boundary conditions, code-based loading (IS 875 and IS 1893), and ductility requirements as per IS 13920. Pareto-optimal designs were initially identified by minimizing the total cost and material usage while maximizing a safety index that reflects flexural, shear, and axial performance. The resulting configurations were subsequently used to train two predictive models: extreme learning machines (ELM) and elastic net regression (ENR) to estimate the optimal cross-sections and reinforcement requirements under varying design scenarios. ELM consistently outperformed ENR, achieving a higher predictive accuracy with lower mean errors across all target variables. The SHAP analysis further elucidated the structural influence of input variables such as span, end condition, and floor level, ensuring model transparency and physical interpretability. Interaction surface plots derived from the trained models revealed highly nonlinear and position-sensitive relationships between geometric attributes and reinforcement demands, aligned with structural mechanics principles such as moment redistribution, load path variation, and biaxial force interaction. This framework advances the paradigm of data-informed, human-centric design in accordance with Industry 5.0 objectives by integrating AI-driven optimization with rigorous compliance to structural codes. It offers a scalable and deployable path toward real-time, sustainable, and explainable structural engineering solutions.

This study evaluated the effect of sleep quality on perceived academic performance of postgraduate students in Sri Lanka. Postgraduate students often juggle complicated schedules of overload from of advanced studies, part-time jobs, family obligations, and self-initiated studies, creating a situation where sleep may be inadequate or disrupted and therefore may impact academic performance. A quantitative survey was performed on 385 postgraduate students covering postgraduate programs. Data analysis was carried out using IBM SPSS Statistics Version 29. Descriptive statistics, distributional diagnostics, internal consistency, Pearson and Spearman correlations, one-way Analysis of Variance, Tukey HSD, and Ordinary Least Squares regressions were applied. The average sleep quality was 2.21 (SD = 0.41) with lower scores representing better quality of sleep and average performance 3.19 (SD = 0.47). The disturbance of sleep scale was found to have limited internal consistency (Cronbach’s α = .504), while the sleep performance beliefs scale showed good internal consistency (α = .965). There was a statistically significant weak negative correlation of sleep quality and perceived academic performance (Pearson’s r = − .122, p = .016; Spearman’s ρ = − .120, p = .018). The reported simple regression model was not significant (R² = .003, F(1, 383) = 1.27, p = .260), and there was no difference in the level of study and sleep quality (F(2, 382) = 2.557, p = .079). Sleep may be a relevant concern regarding postgraduate students’ academic performance; however, sleep should not be the only consideration. Regular sleep, combined with the mental well-being influenced by a combination of stress, self-regulation, and context, is likely to be the primary driver of academic performance. The study suggests postgraduate student support systems should include sleep awareness and sustainable study practices and encourages longitudinal research in Sri Lanka.

Practitioner-level primary data on blockchain adoption in emerging markets are scarce; the literature is dominated by conceptual work, case studies, and evidence from institutions in advanced economies. This study reports a cross-sectional survey of 114 fintech leaders and entrepreneurs working on blockchain and digital- asset initiatives across 60 emerging and developing economies, recruited purposively between October and December 2024. The author-developed instrument captured self-rated familiarity and belief in transformative potential on 0 to 10 scales, and 21 perception statements on a five-point agreement scale organised around the technological, organisational, and environmental dimensions of the Technology-Organisation-Environment (TOE) framework. Analysis is descriptive and exploratory at the item level. Respondents endorsed technological, organisational, and environmental drivers and barriers; perceived benefits in transparency, cost, and efficiency; and clear regulatory guidance, sandboxes, and consumer protection. Fintech leaders reported greater familiarity and stronger belief than entrepreneurs, although the strong association between role and firm age limits attribution of these differences to role independently of organisational maturity. The distribution of responses is itself a finding: all 21 item means fell within a band of 0.29 scale points, between 4.26 and 4.55, with standard deviations between 0.58 and 0.70, and closely related regulatory propositions attracted near-identical endorsement. The instrument produced a severely compressed distribution and limited differentiation among substantively distinct propositions, illustrating the restricted discriminating capacity of survey designs that combine sector-engaged samples with uniformly agreement-keyed items. Findings describe the perceptions of engaged practitioners and do not support inference about adoption outcomes, cross-national variation, or causal relationships.

This paper presents a hybrid unsupervised machine learning model for real-time anomaly detection and dynamic risk defense in the cloud environment. Traditional security mechanisms such as Intrusion Detection Systems (IDS) and fixed firewall rules are often not sufficient to deal with the emerging threats in cloud computing, especially zero-day exploits and polymorphic malware that evade signature-based detection. The proposed system combines Isolation Forest (IF), Local Outlier Factor (LOF) and Density Based Spatial Clustering of Applications with Noise (DBSCAN) to identify both point and cluster anomalies from unlabeled cloud traffic. Integration with AWS Web Application Firewall (WAF) allows it to update its rules automatically and independently mitigate the threats detected. The model was trained and validated on 2.3 million AWS EC2 traffic records, in addition to the CICIDS2017 dataset which was split into a 70- 30 training-validation split. The computation environment consisted of AWS EC2 t2.xlarge (4vCPUs, 16GB RAM) instances of Python 3.8, scikit-learn 0.24.2, MongoDB 4.4, and TensorFlow 2.6. Experiments showed a detection accuracy of 92 per cent with a false positive rate of four per cent. The comparative analysis demonstrated better adaptability and less manual intervention in comparison to traditional IDS (Snort, Suricata: 88 -90% accuracy, 7-9% false positives) and standalone ML models (IF: 87 -90% accuracy, LOF: 86 -90% accuracy, DBSCAN: 84 -90% accuracy). The system was able to detect and block port scanning, DDoS, brute-force and data exfiltration patterns in real time with latency of less than 50ms. The reduction of false-positive by 43-56% led to 150-200 alerts per day being reduced in enterprise settings. The hybrid unsupervised model makes the cloud more resilient with adaptive defense without the need for labeled data. Removing manual firewall updates will save 15-20 hours per week for security teams. Future directions are encrypted traffic analysis based on metadata-based behavioral profiling, largescale distributed data processing (10M+ requests/minute), and multi-cloud integration between AWS, Azure, and GCP.