Faculty of Engineering

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/3710

Browse

Now showing 1 - 10 of 10

Embargo
Applicability of machine learning techniques to analyze Microplastic transportation in open channels with different hydro-environmental factors
(Elsevier Ltd, 2024-09-15) Fazil, A. Z; Gomes, P. I.A.; Sandamal, R.M. K
This research utilized machine learning to analyze experiments conducted in an open channel laboratory setting to predict microplastic transport with varying discharge, velocity, water depth, vegetation pattern, and microplastic density. Four machine learning (ML) models, incorporating Random Forest (RF), Decision Tree (DT), Extreme Gradient Boost (XGB) and K-Nearest Neighbor (KNN) algorithms, were developed and compared with the Linear Regression (LR) statistical model, using 75% of the data for training and 25% for validation. The predictions of ML algorithms were more accurate than the LR, while XGB and RF provided the best predictions. To explain the ML results, Explainable artificial intelligence (XAI) was employed by using Shapley Additive Explanations (SHAP) to predict the global behavior of variables. RF was the most reliable model, with a coefficient of correlation of 0.97 and a mean absolute percentage error of 1.8% after hyperparameter tuning. Results indicated that discharge, velocity, water depth, and vegetation all influenced microplastic transport. Discharge and vegetation enhanced and reduced microplastic transport, respectively, and showed a response to different vegetation patterns. A strong linear positive correlation (R2 = 0.8) was noted between microplastic density and retention. In the absence of dedicated microplastic transport analytical models and infeasibility of using classical sediment transport models in predicting microplastic transport, ML proved to be helpful. Moreover, the use of XAI will reduce the black-box nature of ML models with effective interpretation enhancing the trust of domain experts in ML predictions. The developed model offers a promising tool for real-world open channel predictions, informing effective management strategies to mitigate microplastic pollution.
Embargo
Comparative quantifications and morphological monitoring of the topical treatment approach for onychomycosis-affected in vivo toenail using optical coherence tomography: A case study
(Elsevier Ltd, 2024-02) Saleah, S.S; Gu, Y; Wijesinghe, R.E; Seong, D; Cho, H; Jeon, M; Kim, J
Onychomycosis is one of the most common toenail fungal infections that affect the quality of life of many patients. Long-term and noninvasive monitoring of morphological changes of onychomycosis-affected nail plate aids the medication process and provides comfort for patients. However, existing medical and dermatological imaging methods have various types of limitations in nail investigation due to low resolution, lack of volumetric data, the necessity of highly trained personnel for image analysis, and the variety of protocols. In this study, qualitative monitoring-based quantitative assessments were performed to assess the morphological changes of onychomycosis-affected toenail for 15 consecutive weeks using high-resolution optical coherence tomography (OCT). Layer intensity and surface roughness measuring algorithms were applied to two-dimensional OCT cross-sectional images to detect gradual changes in the morphological structure of the diseased toenail. A depth intensity profile and the angle formed between the nail plate and nail fold were also used to analyze the thickness and shape of the toenail plates, respectively. The quantitative and morphological monitoring results revealed significant changes in the toenail structure before and during the treatment process, confirming the healing of the diseased toenail. Therefore, the proposed noninvasive optical analysis approach can be applied to monitor nail abnormalities and evaluate the process of diseased toenail medication
Open Access
Data exploration on the factors associated with cost overrun on social housing projects in Trinidad and Tobago
(Elsevier Ltd, 2024-02) Chadee, A. A; Allis, C; Rathnayake, U; Martin, H; Azamathulla, H. M
This data article explores the factors that contribute to cost overrun on public sector projects within Trinidad and Tobago. The data was obtained through literature research, and structured questionnaires, designed using open-ended questions and the Likert scale. The responses were gathered from project actors and decision-makers within the public and private construction industry, mainly, project managers, contractors, engineers, architects, and consultants. The dataset was analysed using frequency, simple percentage, mean, risk impact, and fuzzy logic via the fuzzy synthetic evaluation method (FSE). The significance of the analysed data is to determine the critical root causes of cost overrun which affect public sector infrastructure development projects (PSIDPs), from being completed on time and within budget. The dataset is most useful to project and construction management professionals and academia, to provide additional insight into the understanding of the leading factors associated with cost overrun and the critical group in which they occur (political factors). Such understanding can encourage greater decisions under uncertainty and complexity, thus accounting for and reducing cost overrun on public sector projects. © 2023
Open Access
Eco-friendly mix design of slag-ash-based geopolymer concrete using explainable deep learning
(Elsevier, 2024-09) Ranasinghe, R.S.S.; Kulasooriya, W.K.V.J.B; Perera, U.S; Ekanayake, I.U.; Meddage, D.P.P.; Mohotti, D; Rathanayake, U
Geopolymer concrete is a sustainable and eco-friendly substitute for traditional OPC (Ordinary Portland Cement) based concrete, as it reduces greenhouse gas emissions. With various supplementary cementitious materials, the compressive strength of geopolymer concrete should be accurately predicted. Recent studies have applied deep learning techniques to predict the compressive strength of geopolymer concrete yet its hidden decision-making criteria diminish the end-users’ trust in predictions. To bridge this gap, the authors first developed three deep learning models: an artificial neural network (ANN), a deep neural network (DNN), and a 1D convolution neural network (CNN) to predict the compressive strength of slag ash-based geopolymer concrete. The performance indices for accuracy revealed that the DNN model outperforms the other two models. Subsequently, Shapley additive explanations (SHAP) were used to explain the best-performed deep learning model, DNN, and its compressive strength predictions. SHAP exhibited how the importance of each feature and its relationship contributes to the compressive strength prediction of the DNN model. Finally, the authors developed a novel DNN-based open-source software interface to predict the mix design proportions for a given target compressive strength (using inverse modeling technique) for slag ash-based geopolymer concrete. Additionally, the software calculates the Global Warming Potential (kg CO2 equivalent) for each mix design to select the mix designs with low greenhouse emissions.
Open Access
Eco-friendly mix design of slag-ash-based geopolymer concrete using explainable deep learning
(Elsevier, 2024-09) Ranasinghe, R.S.S.; Kulasooriya, W.K.V.J.B.; Perera, U S; Ekanayake, I.U.; Meddage, D.P.P.; Mohotti, D; Rathanayake, U
Geopolymer concrete is a sustainable and eco-friendly substitute for traditional OPC (Ordinary Portland Cement) based concrete, as it reduces greenhouse gas emissions. With various supplementary cementitious materials, the compressive strength of geopolymer concrete should be accurately predicted. Recent studies have applied deep learning techniques to predict the compressive strength of geopolymer concrete yet its hidden decision-making criteria diminish the end-users’ trust in predictions. To bridge this gap, the authors first developed three deep learning models: an artificial neural network (ANN), a deep neural network (DNN), and a 1D convolution neural network (CNN) to predict the compressive strength of slag ash-based geopolymer concrete. The performance indices for accuracy revealed that the DNN model outperforms the other two models. Subsequently, Shapley additive explanations (SHAP) were used to explain the best-performed deep learning model, DNN, and its compressive strength predictions. SHAP exhibited how the importance of each feature and its relationship contributes to the compressive strength prediction of the DNN model. Finally, the authors developed a novel DNN-based open-source software interface to predict the mix design proportions for a given target compressive strength (using inverse modeling technique) for slag ash-based geopolymer concrete. Additionally, the software calculates the Global Warming Potential (kg CO2 equivalent) for each mix design to select the mix designs with low greenhouse emissions.
Open Access
Feasibility of Sediment Budgeting in an Urban Catchment with the Incorporation of an HEC—HMS Erosion Model: A Case Study from Sri Lanka
(Springer, 2024-09-16) Abeysiriwardana, H. D.; Pattiyage, I. A. Gomes
This study aimed at studying the feasibility of using a sediment model built in HEC – HMS incorporating Modified Universal Soil Loss Equation (MUSLE) in aiding the separation of sediment contribution as point and non-point, an important aspect in sediment pollution control. The model was developed and verified using a representative sub-catchment and a canal reach of a tropical climate. The field observations and model developed had a good agreement and indicated about 16% and 35% of total sediments in the canal may be from nonpoint sources for the dry and wet seasons, respectively. Results suggested that a major fraction of eroded sediment ended up in the main canal through the dense drainage network across the catchment. This meant sediment trapping should focus tributary drainage ditches or at point source inputs to canal rather than the main canal banks. The study recognized that HEC – HMS is also capable of simulating sediment generation with acceptable errors. Being a free software package, HEC – HMS would be an effective sediment modelling tool for jurisdictions where sediment analysis has been constrained by cost.
Embargo
Non-destructive morphological screening for the assessment of postharvest storage effect on pears stored with apples using optical coherence tomography
(Elsevier GmbH, 2024-04) Luna, J.A; Wijesinghe, R.E; Lee, S.Y; Ravichandran, N.K; Saleah, S.A; Seong, D; Jung, H.Y; Jeon, M; Kim, J
The use of a limited and inadequate storage facility for the storage of multiple food items for an extended period of time results in the loss of structural integrity and freshness while storing fruit in confined single storage without adequate individual packaging methods can result in morphological changes and the degradation of the quality of the fruit. In this study, the effects of postharvest storage on pears co-stored with apples were investigated via non-invasive screening of the structural deformation of pears and the respective anatomical changes of the sub-surface. The anatomical changes were monitored for a prolonged time (12 d) under inadequate and confined storage conditions using swept-source optical coherence tomography (SS-OCT) and the results were comparatively analyzed using appropriately stored specimens. In addition, the OCT cross-sectional images were analyzed for the assessment of the dispersed intensity profile using a customized intensity-based image-processing algorithm. The results revealed the internal morphological variations and corresponding intensity fluctuations, thickness variations, and internal gap formations. This confirmed the potential applicability of OCT as a real-time, non-invasive high-resolution assessment technique for determining fruit quality in diverse environments, such as post-harvest storage and transportation systems.
Embargo
OTFS modulated massive MIMO with 5G NR LDPC coding: Trends, challenges and future directions
(Elsevier, 2024-12) Jayakody, D N K; Yang, F; Ullah, W
This paper investigates the performance of coded massive multiple-input multiple-output (MIMO) systems utilizing Orthogonal Time Frequency and Space modulation (OTFS). Our innovative approach harnesses the power of OTFS modulation, a cutting-edge modulation technique renowned for its capacity to mitigate the detrimental effects of time-varying channels. Additionally, we introduce a comprehensive system model that incorporates the pivotal elements of channel coding and decoding The system model incorporates channel coding and decoding to improve the bit error rate and enhance the overall performance. The numerical results show that the proposed scheme outperforms existing techniques in terms of BER and spectral efficiency, especially in high-mobility scenarios. The proposed system demonstrates significant robustness against channel estimation errors and Doppler spread. This indicates that coded massive MIMO employing OTFS modulation offers a highly effective solution for future wireless communication systems. The findings highlight the potential of this approach to enhance the reliability and performance of next-generation networks.
Embargo
Tactical Conflict Prevention Strategies in Public-Private Partnerships: Lessons from Experts
(American Society of Civil Engineers (ASCE), 2024-02-01) Liyanapathirana, D; Adeniyi, O; Rathnasiri, P
Conflicts are frequent in public–private partnerships (PPP) due to the involvement of multidisciplined parties within the process.Individual parties among the numerous stakeholders often work toward achieving their own desired goals. Early identification andelimination of potential conflicts are significant to achieving a smooth delivery process of PPP projects. PPP offers imperative benefitsfor economic development, especially in developing countries. However, despite the huge potentials of PPP in infrastructure develop-ment, limited attention still exists in the early stage on the prevention of conflict. Aside from that, a more focused investigation is requiredacross different locations. Therefore, this study aims to enhance the understanding of conflict occurrenceand articulate steps to conflictprevention in PPPs through preconstruction stage practices. Expert interviews were carried out in two phases. Phase I identified thecurrent process and triggers of conflicts and Phase 2 identified thestrategies, and recommendationsto eliminate the conflicts. Thepurposive sampling method was used for the selection of experts in Sri Lanka and findings were analyzed using the content analysismethod. This study identified and categorized the triggers of conflicts in PPP as political interference and public interruption, lack ofknowledge about PPP, contractual agreement,and commitment of professionals. Further, the strategies to prevent conflicts werediscussed under key headings such as proper professional practice, use of lessons learned, thorough contract drafting, a well-defined program,precontract practices, project-long audits, awareness programs, and government support.DOI:10.1061/JLADAH.LADR-996.© 2023American Society of Civil Engineers
Open Access
Waste-based composites using post-industrial textile waste and packaging waste from the textile manufacturing industry for non-structural applications
(Elsevier, 2024-09-26) Sulochani, R.M.N.; Jayasinghe, R.A.; Priyadarshana, G.; Nilmini, A.H.L.R.; Ashokcline, M.; Dharmaratne, P.D.
The textile industry significantly contributes to environmental pollution, generating substantial amounts of waste. The prevailing linear model exacerbates this issue, accumulating a significant portion of the waste in landfills. This research aimed to tackle these challenges by developing value-added composites from postindustrial textile waste and packaging materials, for non-structural building applications. To achieve this, shredded polyester textile waste fibers served as the reinforcement, while waste packaging was used as the matrix. Varying fiber-matrix weight percentages seven composite types were developed. The physical, mechanical, and thermal properties of the composites were evaluated. The findings indicated that these composites exhibited properties comparable to those of commercial partition boards. Notably, composites with fiber weight percentages of 7.5 % and 10 % demonstrated the most favorable performance among the tested variations. Emphasizing the application of sustainable chemistry, this study highlights the potential of these composites to develop substitute materials for non-structural building applications. Moreover, it presents a promising solution to address the textile waste management challenge and value-added materials for the construction industry in a developing context.