Natarajan Raja
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Natarajan Raja has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Asokan Vasudevan
INTI International University
18 shared publications - Sulieman Ibraheem Mohammad
Al al-Bayt University
12 shared publications - Yogeesh Nijalingappa
School of Engineering, Architecture and Interior Design, Amity University Dubai, Dubai P.O. Box 345019, United Arab Emirates; Department of Mathematics, Government First Grade College, Tumakuru 572101, India
11 shared publications - Anber Abraheem Shlash Mohammad
Digital Marketing Department, Faculty of Administrative and Financial Sciences, University of Petra, Amman, Jordan
3 shared publications - Hanan Jadallah
Zarqa University
3 shared publications - Mohammad Faleh Ahmmad Hunitie
Department of Public Administration, School of Business, University of Jordan, Amman 11942, Jordan
3 shared publications
Latest Publications
- Open Access
- 12 October 2026
- Published by Bilingual Publishing Group in Journal of Building Material Science
- Vol. 8 (4) , 21-37
Evaluation of Sustainable Waste-to-Material Pathways Using Fuzzy Cognitive Mapping
Waste-to-material (WtM) strategies are central to circular-economy planning, yet pathway selection is complicated by uncertain feedstock quality, policy variability, market fluctuations, and coupled operational trade-offs. Existing evaluations often treat key drivers independently, limiting their ability to represent feedback effects that shape long-run pathway performance. This study develops a fuzzy cognitive map (FCM) decision framework to compare four representative WtM pathways (mechanical recycling, chemical recycling, anaerobic digestion, and mineralization) using a system of interacting indicators: feedstock quality, collection rate, preprocessing efficiency, yield, energy intensity, market value, greenhouse-gas (GHG) impact, and circular uptake. For reproducibility, the resulting FCM adjacency structure is explicitly specified and all scenarios are parameterized following a defined set of node clamps to reflect policy push (feedstock expansion) and edge edits reflecting feedstock shock conditions. Pathway-specific environmental, economic and circularity indicators, as well as a comprehensive sustainability score with uncertainty bounds are reported for converged (steady-state) outputs. Results also indicate that pathway rankings and trade-off positions vary across scenarios, with policy developments leading to higher values of circular uptake and market value but lower values for preprocessing/yield (feedstock shocks) and GHG outcomes. The framework that we have proposed provides an interpretable and reproducible tool for WtM strategy selection under uncertainty, as well as a basis for policy-relevant sensitivity and robustness analysis.
- 12 October 2026
- Published by Bilingual Publishing Group in Journal of Building Material Science
- Vol. 8 (4) , 21-37
Open AccessEvaluation of Sustainable Waste-to-Material Pathways Using Fuzzy Cognitive Mapping
Waste-to-material (WtM) strategies are central to circular-economy planning, yet pathway selection is complicated by uncertain feedstock quality, policy variability, market fluctuations, and coupled operational trade-offs. Existing evaluations often treat key drivers independently, limiting their ability to represent feedback effects that shape long-run pathway performance. This study develops a fuzzy cognitive map (FCM) decision framework to compare four representative WtM pathways (mechanical recycling, chemical recycling, anaerobic digestion, and mineralization) using a system of interacting indicators: feedstock quality, collection rate, preprocessing efficiency, yield, energy intensity, market value, greenhouse-gas (GHG) impact, and circular uptake. For reproducibility, the resulting FCM adjacency structure is explicitly specified and all scenarios are parameterized following a defined set of node clamps to reflect policy push (feedstock expansion) and edge edits reflecting feedstock shock conditions. Pathway-specific environmental, economic and circularity indicators, as well as a comprehensive sustainability score with uncertainty bounds are reported for converged (steady-state) outputs. Results also indicate that pathway rankings and trade-off positions vary across scenarios, with policy developments leading to higher values of circular uptake and market value but lower values for preprocessing/yield (feedstock shocks) and GHG outcomes. The framework that we have proposed provides an interpretable and reproducible tool for WtM strategy selection under uncertainty, as well as a basis for policy-relevant sensitivity and robustness analysis.
- Open Access
- 3 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 23770
Precision pharmacology: deep learning infused ontological framework with E-GRU enhancement for tailored medicine prescriptions
Advanced Clinical Decision Support Systems significantly influence patient care, with medicine prescriptions being a vital area of research. Ontology, a growing discipline in the semantic web, enables hierarchical domain representation, thereby allowing finer data access to be achieved. Deep Learning (DL) supports pattern recognition in Electronic Health Records (EHR), which include patient demographics and diagnosis histories. Prescribing medications with minimal adverse effects is crucial, particularly for patients who require multiple drugs, as drug interactions can result in more complex conditions. This study introduces an integrated approach that combines Ontology with DL neural networks to improve prescription accuracy. This study proposes NexusOpti, a model featuring an Enhanced Gated Recurrent Unit (E-GRU) layer. To understand drug–disease interactions, hierarchical data were extracted from the International Classification of Diseases (ICD) and Anatomical Therapeutic Chemical (ATC) ontologies. These structured data were processed using a self-attention mechanism to enhance the recommendation precision. This integration not only addresses data security concerns but also improves the accuracy of the medicine recommendations. The model was evaluated using key metrics such as the hit ratio and normalised discounted cumulative gain (NDCG). The NexusOpti model, incorporating the Enhanced Gated Recurrent Unit (E-GRU) layer, outperforms the existing GRU model in terms of NDCG and Hit Ratio metrics. 13% of improvement in performance was oberved to the comparison between NexusOpti with the E-GRU and the GRAM baseline model. These findings highlight the effectiveness of the model in advancing personalised, safer, and data-driven medication prescriptions.
- 3 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 23770
Open AccessPrecision pharmacology: deep learning infused ontological framework with E-GRU enhancement for tailored medicine prescriptions
Advanced Clinical Decision Support Systems significantly influence patient care, with medicine prescriptions being a vital area of research. Ontology, a growing discipline in the semantic web, enables hierarchical domain representation, thereby allowing finer data access to be achieved. Deep Learning (DL) supports pattern recognition in Electronic Health Records (EHR), which include patient demographics and diagnosis histories. Prescribing medications with minimal adverse effects is crucial, particularly for patients who require multiple drugs, as drug interactions can result in more complex conditions. This study introduces an integrated approach that combines Ontology with DL neural networks to improve prescription accuracy. This study proposes NexusOpti, a model featuring an Enhanced Gated Recurrent Unit (E-GRU) layer. To understand drug–disease interactions, hierarchical data were extracted from the International Classification of Diseases (ICD) and Anatomical Therapeutic Chemical (ATC) ontologies. These structured data were processed using a self-attention mechanism to enhance the recommendation precision. This integration not only addresses data security concerns but also improves the accuracy of the medicine recommendations. The model was evaluated using key metrics such as the hit ratio and normalised discounted cumulative gain (NDCG). The NexusOpti model, incorporating the Enhanced Gated Recurrent Unit (E-GRU) layer, outperforms the existing GRU model in terms of NDCG and Hit Ratio metrics. 13% of improvement in performance was oberved to the comparison between NexusOpti with the E-GRU and the GRAM baseline model. These findings highlight the effectiveness of the model in advancing personalised, safer, and data-driven medication prescriptions.
- Open Access
- 15 January 2026
- Published by Research and Development Academy in Heritage and Sustainable Development
- Vol. 8 (1) , 529-548
A fuzzy DEMATEL approach to identify and mitigate barriers to consumer adoption of sustainable products
Despite increasing consumer interest in sustainable products, actual purchase and repeat usage of eco-friendly personal-care items remain disappointingly low. This study employs a fuzzy DEMATEL (Decision-Making Trial and Evaluation Laboratory) approach to systematically identify, quantify, and prioritize the causal relationships among barriers to sustainable-product adoption. A Delphi panel of 15 sustainability experts generated a consensus list of 12 key barriers (economic, psychological, social, technological, and policy-related). Experts provided pairwise influence judgments using a five-point linguistic scale, which were mapped to triangular fuzzy numbers, aggregated, defuzzified, and normalized to yield a crisp total-relation matrix. Cause–effect analysis (D–R and D+R indices) highlighted price premium, perceived greenwashing risk, and limited availability as the dominant root causes. A pilot consumer survey (n = 120 urban millennials in Bengaluru) validated these findings (Pearson’s r = 0.92). Sensitivity analyses across multiple ?-cut levels confirmed the stability of barrier rankings. Leveraging these systemic insights, we propose a three-stage mitigation roadmap—short-term (discount trials, transparency campaigns), medium-term (traceability via blockchain, retail partnerships), and long-term (in-house R&D, policy advocacy)—tailored for an eco-personal-care brand. This work advances fuzzy MCDM methodology by integrating pilot validation and offers actionable guidance for marketers and policymakers aiming to dismantle the complex web of obstacles hindering sustainable-consumption uptake.
- 15 January 2026
- Published by Research and Development Academy in Heritage and Sustainable Development
- Vol. 8 (1) , 529-548
Open AccessA fuzzy DEMATEL approach to identify and mitigate barriers to consumer adoption of sustainable products
Despite increasing consumer interest in sustainable products, actual purchase and repeat usage of eco-friendly personal-care items remain disappointingly low. This study employs a fuzzy DEMATEL (Decision-Making Trial and Evaluation Laboratory) approach to systematically identify, quantify, and prioritize the causal relationships among barriers to sustainable-product adoption. A Delphi panel of 15 sustainability experts generated a consensus list of 12 key barriers (economic, psychological, social, technological, and policy-related). Experts provided pairwise influence judgments using a five-point linguistic scale, which were mapped to triangular fuzzy numbers, aggregated, defuzzified, and normalized to yield a crisp total-relation matrix. Cause–effect analysis (D–R and D+R indices) highlighted price premium, perceived greenwashing risk, and limited availability as the dominant root causes. A pilot consumer survey (n = 120 urban millennials in Bengaluru) validated these findings (Pearson’s r = 0.92). Sensitivity analyses across multiple ?-cut levels confirmed the stability of barrier rankings. Leveraging these systemic insights, we propose a three-stage mitigation roadmap—short-term (discount trials, transparency campaigns), medium-term (traceability via blockchain, retail partnerships), and long-term (in-house R&D, policy advocacy)—tailored for an eco-personal-care brand. This work advances fuzzy MCDM methodology by integrating pilot validation and offers actionable guidance for marketers and policymakers aiming to dismantle the complex web of obstacles hindering sustainable-consumption uptake.
- Open Access
- 30 December 2025
- Published by Nan Yang Academy of Sciences Pte Ltd in Sustainable Marine Structures
- p. 255-275
Sustainable Marine Operations: Uncertainty-Aware Multi-Body Motion Analysis of Offshore Support Vessels
Offshore support operations must balance safety and sustainability under highly variable sea conditions. Deterministic motion analyses can underestimate extreme vessel responses, leading to insufficient operational limits and increased environmental impact. We develop a fuzzy‐enhanced multi‐body dynamics framework in which key inputs significant wave height, peak period, added mass, and radiation damping are represented as fuzzy numbers. An α-cut decomposition yields interval bounds at each confidence level, and a fourth-order Runge-Kutta scheme integrates the six-degree-of-freedom equations of motion for both lower and upper “vertex” systems. A case study off the Karnataka coast applies both full 6-DoF and single-DOF heave approximations to demonstrate methodology. The heave response envelopes under calm (nominal α = 1: 0.73 m; full range at α = 0: 0.64–1.64 m) and severe (nominal 1.58 m; range 1.32–2.36 m) sea states reveal potential underestimations of 124 % and 49 %, respectively, when using only nominal values. By selecting an operational α-level (e.g., α* = 0.35 to cap heave ≤ 1.8 m), decision-makers can balance risk tolerance and conservatism. Sensitivity analysis identifies significant wave height as the dominant uncertainty driver. Computational trade-offs and adaptive α-sampling strategies are discussed. This work provides a self-contained, uncertainty-aware tool for deriving operational envelopes that improve risk-informed planning and enable fuel-efficiency optimization. By embedding fuzzy uncertainty quantification into vessel dynamics, the methodology supports safer, more sustainable marine operations and can be extended to real-time sensor fusion, multi-vessel interactions, and frequency-dependent hydrodynamics.
- 30 December 2025
- Published by Nan Yang Academy of Sciences Pte Ltd in Sustainable Marine Structures
- p. 255-275
Open AccessSustainable Marine Operations: Uncertainty-Aware Multi-Body Motion Analysis of Offshore Support Vessels
Offshore support operations must balance safety and sustainability under highly variable sea conditions. Deterministic motion analyses can underestimate extreme vessel responses, leading to insufficient operational limits and increased environmental impact. We develop a fuzzy‐enhanced multi‐body dynamics framework in which key inputs significant wave height, peak period, added mass, and radiation damping are represented as fuzzy numbers. An α-cut decomposition yields interval bounds at each confidence level, and a fourth-order Runge-Kutta scheme integrates the six-degree-of-freedom equations of motion for both lower and upper “vertex” systems. A case study off the Karnataka coast applies both full 6-DoF and single-DOF heave approximations to demonstrate methodology. The heave response envelopes under calm (nominal α = 1: 0.73 m; full range at α = 0: 0.64–1.64 m) and severe (nominal 1.58 m; range 1.32–2.36 m) sea states reveal potential underestimations of 124 % and 49 %, respectively, when using only nominal values. By selecting an operational α-level (e.g., α* = 0.35 to cap heave ≤ 1.8 m), decision-makers can balance risk tolerance and conservatism. Sensitivity analysis identifies significant wave height as the dominant uncertainty driver. Computational trade-offs and adaptive α-sampling strategies are discussed. This work provides a self-contained, uncertainty-aware tool for deriving operational envelopes that improve risk-informed planning and enable fuel-efficiency optimization. By embedding fuzzy uncertainty quantification into vessel dynamics, the methodology supports safer, more sustainable marine operations and can be extended to real-time sensor fusion, multi-vessel interactions, and frequency-dependent hydrodynamics.
- Open Access
- 10 November 2025
- Published by Bilingual Publishing Group in Forum for Linguistic Studies
- Vol. 7 (12) , 651-665
Harnessing AI Tools to Enhance English Writing Skills in Undergraduate Education
AI tools, especially ChatGPT, play a vital role in enhancing English writing skills. The objective centers on probing how it assists undergraduate learners in improving their writing skills, from making useful notes to drafting formal letters in their daily life. The study explores the efficiency of AI tool ChatGPT upon improving writing skills among undergraduate learners through a quasi-experiment in a few selected topics: letter writing, email writing, paragraph writing, and report writing. The research gap is that the undergraduates lack adequate skills in drafting the above topics in English language. Insights are also drawn from the real-life instances of the drafted letters by the undergraduate learners to the higher authorities, i.e., the Principal and the HoDs requesting them to issue various certificates, such as study, bonafide, transfer, and late fee payment permission letters. With the help of Quasi-experiment method of pre-test and post-test, students were subjected to formal letter drafting, email writing, paragraph writing, and report writing. The post-tests gave better results that the students have improved on grammar, sentence structure, vocabulary, accuracy coherence. Hence, the study suggests that AI-driven tools can enhance writing skills of undergraduates in English Language. To sum up, the study highlights the need of harnessing AI tool ChatGPT to write better writing skills in English Language.
- 10 November 2025
- Published by Bilingual Publishing Group in Forum for Linguistic Studies
- Vol. 7 (12) , 651-665
Open AccessHarnessing AI Tools to Enhance English Writing Skills in Undergraduate Education
AI tools, especially ChatGPT, play a vital role in enhancing English writing skills. The objective centers on probing how it assists undergraduate learners in improving their writing skills, from making useful notes to drafting formal letters in their daily life. The study explores the efficiency of AI tool ChatGPT upon improving writing skills among undergraduate learners through a quasi-experiment in a few selected topics: letter writing, email writing, paragraph writing, and report writing. The research gap is that the undergraduates lack adequate skills in drafting the above topics in English language. Insights are also drawn from the real-life instances of the drafted letters by the undergraduate learners to the higher authorities, i.e., the Principal and the HoDs requesting them to issue various certificates, such as study, bonafide, transfer, and late fee payment permission letters. With the help of Quasi-experiment method of pre-test and post-test, students were subjected to formal letter drafting, email writing, paragraph writing, and report writing. The post-tests gave better results that the students have improved on grammar, sentence structure, vocabulary, accuracy coherence. Hence, the study suggests that AI-driven tools can enhance writing skills of undergraduates in English Language. To sum up, the study highlights the need of harnessing AI tool ChatGPT to write better writing skills in English Language.
- Open Access
- 6 November 2025
- Published by Bilingual Publishing Group in Forum for Linguistic Studies
- Vol. 7 (12) , 441–453
AI is Ineludible in Alleviating English Language Learning at Government Secondary Schools: An Action Research
The study, "AI is Ineludible in Alleviating English Language Learning at Zill Parishad Secondary Schools: An Action Research," was implemented at the high school level in Kovvuru Mandal, East Godavari District, Andhra Pradesh. The study collaboratively integrated AI (Artificial Intelligence) tools to enhance students' language acquisition levels to meet the learning outcomes of NEP 2020. The study conducted a quantitative and qualitative analysis of the data to see the effect of AI on language improvement. The quantitative analysis showed a significant improvement in the students' academic achievements in English. The qualitative analysis conducted included both Likert Scale analysis of the questionnaire and an unstructured interview. The study considered teachers’ opinions on the integration of AI to generate lesson plans, to present the digital content in an interesting, joyful way, and to prepare question papers to assess students' learning improvements. It also obtained the teachers' views on how far they are succeeding in integrating AI to make English learning an easy way. The study also confronts the challenges of technology interventions in rural students, especially where there is no free internet and power failures. The paper proposes suggestions to the system to achieve the required aims of equity, quality, and inclusiveness outlined in NEP 2020.
- 6 November 2025
- Published by Bilingual Publishing Group in Forum for Linguistic Studies
- Vol. 7 (12) , 441–453
Open AccessAI is Ineludible in Alleviating English Language Learning at Government Secondary Schools: An Action Research
The study, "AI is Ineludible in Alleviating English Language Learning at Zill Parishad Secondary Schools: An Action Research," was implemented at the high school level in Kovvuru Mandal, East Godavari District, Andhra Pradesh. The study collaboratively integrated AI (Artificial Intelligence) tools to enhance students' language acquisition levels to meet the learning outcomes of NEP 2020. The study conducted a quantitative and qualitative analysis of the data to see the effect of AI on language improvement. The quantitative analysis showed a significant improvement in the students' academic achievements in English. The qualitative analysis conducted included both Likert Scale analysis of the questionnaire and an unstructured interview. The study considered teachers’ opinions on the integration of AI to generate lesson plans, to present the digital content in an interesting, joyful way, and to prepare question papers to assess students' learning improvements. It also obtained the teachers' views on how far they are succeeding in integrating AI to make English learning an easy way. The study also confronts the challenges of technology interventions in rural students, especially where there is no free internet and power failures. The paper proposes suggestions to the system to achieve the required aims of equity, quality, and inclusiveness outlined in NEP 2020.
- Open Access
- 4 November 2025
- Published by Bilingual Publishing Group in Forum for Linguistic Studies
- Vol. 7 (12) , 166–183
Corpus-based Uncertainty Analysis of Multilingual Media under Language Policy
This paper presents a mathematical framework for quantifying graded language mixing in media texts surrounding a policy reform. We model each document as generated by probabilistic n-gram models for two languages, interpret the resulting posterior probabilities as soft-membership degrees, and apply Shannon entropy to measure per-document mixing. A fuzzification exponent controls assignment sharpness, and aggregate entropy across documents yields a corpus-level metric tracked over pre- and post-reform intervals. In a case study of 20 headlines, mean entropy rose from 0.52 to 0.68 nats (∆ = 0.16), indicating increased code-mixing after the policy change. Statistical validation via a paired t-test (t = 3.27, p < 0.01) and a permutation test (p = 0.005) confirms the significance of this shift. Analysis of soft-membership distributions reveals a drop in average English membership from 0.77 to 0.52, further illustrating editorial adaptation. The modular implementation enables scalable analysis of large corpora, and an open-source toolkit is provided to promote reproducibility and extension to other bilingual or multilingual settings. We discuss limitations related to parameter sensitivity, model assumptions, and sample size, and outline future extensions involving imprecise-probability bounds, contextual embeddings, dynamic time-series modeling, and topic-augmented uncertainty. Our results demonstrate the power of information-theoretic tools for detecting subtle shifts in media discourse in response to regulatory changes.
- 4 November 2025
- Published by Bilingual Publishing Group in Forum for Linguistic Studies
- Vol. 7 (12) , 166–183
Open AccessCorpus-based Uncertainty Analysis of Multilingual Media under Language Policy
This paper presents a mathematical framework for quantifying graded language mixing in media texts surrounding a policy reform. We model each document as generated by probabilistic n-gram models for two languages, interpret the resulting posterior probabilities as soft-membership degrees, and apply Shannon entropy to measure per-document mixing. A fuzzification exponent controls assignment sharpness, and aggregate entropy across documents yields a corpus-level metric tracked over pre- and post-reform intervals. In a case study of 20 headlines, mean entropy rose from 0.52 to 0.68 nats (∆ = 0.16), indicating increased code-mixing after the policy change. Statistical validation via a paired t-test (t = 3.27, p < 0.01) and a permutation test (p = 0.005) confirms the significance of this shift. Analysis of soft-membership distributions reveals a drop in average English membership from 0.77 to 0.52, further illustrating editorial adaptation. The modular implementation enables scalable analysis of large corpora, and an open-source toolkit is provided to promote reproducibility and extension to other bilingual or multilingual settings. We discuss limitations related to parameter sensitivity, model assumptions, and sample size, and outline future extensions involving imprecise-probability bounds, contextual embeddings, dynamic time-series modeling, and topic-augmented uncertainty. Our results demonstrate the power of information-theoretic tools for detecting subtle shifts in media discourse in response to regulatory changes.
- Open Access
- 28 October 2025
- Published by Bilingual Publishing Group in Forum for Linguistic Studies
- Vol. 7 (11)
Approximate State-Transition Modeling of Language Disorder Portrayals in Media
Quantitative analysis of how cognitive-linguistic impairments are depicted in broadcast and digital outlets requires dynamic models that capture both disfluency patterns and sampling noise. This paper presents a first-order Markov-chain framework enhanced by a controlled smoothing operator to mitigate spurious low-frequency transitions. We define an empirical transition matrix from annotated utterance segments (fluent, hesitation, error) and apply a Gaussian-kernel–based approximation to produce a smoothed stochastic matrix with provable perturbation bounds. Theoretical results guarantee that the t-step transition error grows at most linearly with the smoothing magnitude and that stationary-distribution shifts remain bounded by the ratio of approximation error to the spectral gap. On a large, multi-source corpus (≈20,000 segments), cross-validated smoothing achieves a 12% perplexity reduction over the unsmoothed chain and reduces cumulative error-state estimation deviation by 19% compared to a threshold-based baseline. A compact case study further illustrates the bias–variance trade-off inherent in smoothing: aggressive approximation on small sequences can dramatically inflate unlikely transitions, underscoring the need for corpus-sensitive parameter tuning. These findings demonstrate that kernel-smoothed stochastic models offer interpretable, computationally efficient tools for analyzing disfluency dynamics over time. Future work will explore higher-order dependencies, nonstationary transition matrices, and hybrid deep‐learning integrations to capture richer contextual patterns in discourse sequences.
- 28 October 2025
- Published by Bilingual Publishing Group in Forum for Linguistic Studies
- Vol. 7 (11)
Open AccessApproximate State-Transition Modeling of Language Disorder Portrayals in Media
Quantitative analysis of how cognitive-linguistic impairments are depicted in broadcast and digital outlets requires dynamic models that capture both disfluency patterns and sampling noise. This paper presents a first-order Markov-chain framework enhanced by a controlled smoothing operator to mitigate spurious low-frequency transitions. We define an empirical transition matrix from annotated utterance segments (fluent, hesitation, error) and apply a Gaussian-kernel–based approximation to produce a smoothed stochastic matrix with provable perturbation bounds. Theoretical results guarantee that the t-step transition error grows at most linearly with the smoothing magnitude and that stationary-distribution shifts remain bounded by the ratio of approximation error to the spectral gap. On a large, multi-source corpus (≈20,000 segments), cross-validated smoothing achieves a 12% perplexity reduction over the unsmoothed chain and reduces cumulative error-state estimation deviation by 19% compared to a threshold-based baseline. A compact case study further illustrates the bias–variance trade-off inherent in smoothing: aggressive approximation on small sequences can dramatically inflate unlikely transitions, underscoring the need for corpus-sensitive parameter tuning. These findings demonstrate that kernel-smoothed stochastic models offer interpretable, computationally efficient tools for analyzing disfluency dynamics over time. Future work will explore higher-order dependencies, nonstationary transition matrices, and hybrid deep‐learning integrations to capture richer contextual patterns in discourse sequences.
- Open Access
- 15 October 2025
- Published by Nan Yang Academy of Sciences Pte Ltd in Sustainable Marine Structures
- p. 36-55
Predictive Motion Envelopes for Offshore Logistics via α-Cut Intervals
Offshore logistics operations must continuously balance safety, fuel efficiency, and emissions reduction while navigating under uncertain and highly variable sea states. To address this challenge, we present an α-cut interval framework in which environmental uncertainties, specifically wave height and wind speed, are modeled as fuzzy numbers. Their corresponding α-level intervals are systematically propagated through a discrete vessel dynamics model, focusing on surge and heave responses. This procedure generates families of nested motion envelopes that tighten monotonically with increasing α, thereby producing deterministic yet progressively refined safety bounds without relying on full probabilistic distributions. A case study off the Karnataka coast is used to demonstrate the approach for a 20 km offshore supply voyage. Route planning constrained by α-envelopes ensures adherence to vessel structural and stability limits while enabling optimized transit speed. Comparative evaluation indicates that, relative to standard interval analysis, α-cut propagation substantially reduces over-conservatism, while against Monte Carlo-based envelopes it achieves similar coverage with significantly lower computational effort. Sensitivity analyses further quantify the influence of α-grid resolution, membership-function design, and hydrodynamic coupling coefficients on envelope width, fuel use, and emissions. In the tested scenario, higher α levels allow up to ~15% reduction in worst-case energy consumption and nearly 10% reduction in CO₂ emissions, all while preserving safety margins. Overall, the proposed framework is transparent, computationally efficient, and easily integrable into digital-twin-enabled operational workflows, providing a practical and sustainable decision-support tool for adaptive offshore logistics planning.
- 15 October 2025
- Published by Nan Yang Academy of Sciences Pte Ltd in Sustainable Marine Structures
- p. 36-55
Open AccessPredictive Motion Envelopes for Offshore Logistics via α-Cut Intervals
Offshore logistics operations must continuously balance safety, fuel efficiency, and emissions reduction while navigating under uncertain and highly variable sea states. To address this challenge, we present an α-cut interval framework in which environmental uncertainties, specifically wave height and wind speed, are modeled as fuzzy numbers. Their corresponding α-level intervals are systematically propagated through a discrete vessel dynamics model, focusing on surge and heave responses. This procedure generates families of nested motion envelopes that tighten monotonically with increasing α, thereby producing deterministic yet progressively refined safety bounds without relying on full probabilistic distributions. A case study off the Karnataka coast is used to demonstrate the approach for a 20 km offshore supply voyage. Route planning constrained by α-envelopes ensures adherence to vessel structural and stability limits while enabling optimized transit speed. Comparative evaluation indicates that, relative to standard interval analysis, α-cut propagation substantially reduces over-conservatism, while against Monte Carlo-based envelopes it achieves similar coverage with significantly lower computational effort. Sensitivity analyses further quantify the influence of α-grid resolution, membership-function design, and hydrodynamic coupling coefficients on envelope width, fuel use, and emissions. In the tested scenario, higher α levels allow up to ~15% reduction in worst-case energy consumption and nearly 10% reduction in CO₂ emissions, all while preserving safety margins. Overall, the proposed framework is transparent, computationally efficient, and easily integrable into digital-twin-enabled operational workflows, providing a practical and sustainable decision-support tool for adaptive offshore logistics planning.
- Open Access
- 9 September 2025
- Published by Nan Yang Academy of Sciences Pte Ltd in Sustainable Marine Structures
- p. 209-226
Interval-Based Multi-Body Dynamics Simulation of Special-Purpose Vessels in Rough Sea Conditions
Vessel motions in offshore operations are heavily influenced by uncertain wave loads and hydrodynamic parameters. Yet, traditional deterministic or probabilistic models often fail to capture epistemic ambiguity when data are scarce. We introduce a fuzzy–set framework using α-cut interval analysis to represent imprecise wave heights, periods, added mass, damping, and stiffness as fuzzy numbers. These are incorporated into the multi-body equations of motion and solved via a fuzzy Runge–Kutta scheme across nested α-levels. A simulation architecture iterates over α-cuts and time-steps to produce interval bounds on heavy responses. A case study off the Karnataka coast, with realistic sea-state data for moderate and severe scenarios, yields heave-amplitude envelopes whose widths quantify response uncertainty. At mid-confidence (α = 0.5), moderate seas produce amplitudes of 8.30–9.65 m (± 15 %), while severe seas yield 7.15–8.90 m (± 22 %). Envelope narrowing as α→1 confirms that increased parameter confidence reduces prediction spread, and bias analysis against crisp baselines highlights the impact of imprecision on mean responses. This non-probabilistic approach provides interpretable, worst- and best-case motion bounds without requiring large datasets, offering marine engineers robust safety margins and guidance for targeted data collection and real-time uncertainty updating.
- 9 September 2025
- Published by Nan Yang Academy of Sciences Pte Ltd in Sustainable Marine Structures
- p. 209-226
Open AccessInterval-Based Multi-Body Dynamics Simulation of Special-Purpose Vessels in Rough Sea Conditions
Vessel motions in offshore operations are heavily influenced by uncertain wave loads and hydrodynamic parameters. Yet, traditional deterministic or probabilistic models often fail to capture epistemic ambiguity when data are scarce. We introduce a fuzzy–set framework using α-cut interval analysis to represent imprecise wave heights, periods, added mass, damping, and stiffness as fuzzy numbers. These are incorporated into the multi-body equations of motion and solved via a fuzzy Runge–Kutta scheme across nested α-levels. A simulation architecture iterates over α-cuts and time-steps to produce interval bounds on heavy responses. A case study off the Karnataka coast, with realistic sea-state data for moderate and severe scenarios, yields heave-amplitude envelopes whose widths quantify response uncertainty. At mid-confidence (α = 0.5), moderate seas produce amplitudes of 8.30–9.65 m (± 15 %), while severe seas yield 7.15–8.90 m (± 22 %). Envelope narrowing as α→1 confirms that increased parameter confidence reduces prediction spread, and bias analysis against crisp baselines highlights the impact of imprecision on mean responses. This non-probabilistic approach provides interpretable, worst- and best-case motion bounds without requiring large datasets, offering marine engineers robust safety margins and guidance for targeted data collection and real-time uncertainty updating.