Pub Date : 2021-07-27DOI: 10.1109/MERCon52712.2021.9525771
R. Perera, H. Weligampola, U. Marikkar, Suren Sritharan, R. Godaliyadda, Parakrama B. Ekanayake, V. Herath, A. Rathnayake, S. Dharmaratne
The spread of the global COVID-19 pandemic affected Sri Lanka similar to how it affected other countries across the globe. The Sri Lankan government took many preventive measures to suppress the pandemic spread. To aid policy makers in taking these preventive measures, we propose a novel district-wise clustering based approach. Using freely available data from the Epidemiological Department of Sri Lanka, a cluster analysis was carried out based on the COVID-19 data and the demographic data of districts. K-Means clustering and spectral clustering models were the selected clustering techniques in this study. From the many district-wise socio-economic factors, population, population density, monthly expenditure and the education level were identified as the demographic variables that exhibit a high similarity with COVID-19 clusters. This approach will positively impact the preventive measures suggested by the relevant policy making parties of the Sri Lankan government.
{"title":"Spatial analysis of COVID-19 and socio-economic factors in Sri Lanka","authors":"R. Perera, H. Weligampola, U. Marikkar, Suren Sritharan, R. Godaliyadda, Parakrama B. Ekanayake, V. Herath, A. Rathnayake, S. Dharmaratne","doi":"10.1109/MERCon52712.2021.9525771","DOIUrl":"https://doi.org/10.1109/MERCon52712.2021.9525771","url":null,"abstract":"The spread of the global COVID-19 pandemic affected Sri Lanka similar to how it affected other countries across the globe. The Sri Lankan government took many preventive measures to suppress the pandemic spread. To aid policy makers in taking these preventive measures, we propose a novel district-wise clustering based approach. Using freely available data from the Epidemiological Department of Sri Lanka, a cluster analysis was carried out based on the COVID-19 data and the demographic data of districts. K-Means clustering and spectral clustering models were the selected clustering techniques in this study. From the many district-wise socio-economic factors, population, population density, monthly expenditure and the education level were identified as the demographic variables that exhibit a high similarity with COVID-19 clusters. This approach will positively impact the preventive measures suggested by the relevant policy making parties of the Sri Lankan government.","PeriodicalId":6855,"journal":{"name":"2021 Moratuwa Engineering Research Conference (MERCon)","volume":"27 1","pages":"444-449"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80341159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-27DOI: 10.1109/MERCon52712.2021.9525685
Hasara Samarasinghe, S. Walpalage, D. Edirisinghe, S. Egodage
Today, it is obligatory to replace nitrosamine releasing traditional accelerators owing to the various health, safety and environment regulations and surviving with safe alternative is a one of the key challenges in the rubber industry. In this work four groups of commercially available nitrosamine free/safe accelerators were selected, i,e., diisopropyl xanthogen polysulfide (DIXP), tetrabenzyl thiuramdisulfide (TBzTD), zinc dibenzyl dithiocarbamate (ZBeC) and N-tert-butyl-2-benzothiazole sulfenamide (TBBS). The effect of accelerator type on cure, crosslink density, physico-mechanical and dynamic-mechanical properties of efficient sulfur vulcanized natural rubber (NR) compounds was investigated. Results reveal that accelerator type does not only affect the cure characteristics, but also has a great impact on physical and mechanical properties, DIXP possess the least modulus and strength properties while providing satisfactory optimum cure time for the vulcanization compared to the TBBS accelerator. Improvement in mechanical properties is observed in the order ZBeC, TBzTD, TBBS and corroborates well with the crosslink density. ZBeC and TBzTD show relatively higher hardness, storage modulus and lower hysteresis in the rubbery region indicating different microstructure arrangement compared to commonly use of non-regulated nitrosamine safe TBBS accelerated vulcanizates.
{"title":"Comparative Study on Cure, Mechanical and Dynamic-Mechanical Properties of Natural Rubber Compounds Formulated with DIXP, TBzTD, ZBeC and TBBS Accelerators","authors":"Hasara Samarasinghe, S. Walpalage, D. Edirisinghe, S. Egodage","doi":"10.1109/MERCon52712.2021.9525685","DOIUrl":"https://doi.org/10.1109/MERCon52712.2021.9525685","url":null,"abstract":"Today, it is obligatory to replace nitrosamine releasing traditional accelerators owing to the various health, safety and environment regulations and surviving with safe alternative is a one of the key challenges in the rubber industry. In this work four groups of commercially available nitrosamine free/safe accelerators were selected, i,e., diisopropyl xanthogen polysulfide (DIXP), tetrabenzyl thiuramdisulfide (TBzTD), zinc dibenzyl dithiocarbamate (ZBeC) and N-tert-butyl-2-benzothiazole sulfenamide (TBBS). The effect of accelerator type on cure, crosslink density, physico-mechanical and dynamic-mechanical properties of efficient sulfur vulcanized natural rubber (NR) compounds was investigated. Results reveal that accelerator type does not only affect the cure characteristics, but also has a great impact on physical and mechanical properties, DIXP possess the least modulus and strength properties while providing satisfactory optimum cure time for the vulcanization compared to the TBBS accelerator. Improvement in mechanical properties is observed in the order ZBeC, TBzTD, TBBS and corroborates well with the crosslink density. ZBeC and TBzTD show relatively higher hardness, storage modulus and lower hysteresis in the rubbery region indicating different microstructure arrangement compared to commonly use of non-regulated nitrosamine safe TBBS accelerated vulcanizates.","PeriodicalId":6855,"journal":{"name":"2021 Moratuwa Engineering Research Conference (MERCon)","volume":"34 1","pages":"321-326"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80409839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-27DOI: 10.1109/MERCon52712.2021.9525674
U. L. M. A. Uswaththa, H. Pasindu, J. Bandara, D. Jayaratne
Highway capacity is an essential element in highway planning and traffic management. There are a number of methods developed to estimate highway capacity. Most of them focus on identifying the maximum flow or throughput using a traffic speed-flow model. However, it has been found that these capacity estimates are not practical as they cannot be sustained for long, under normal flow conditions. This research mainly focuses on using the breakdown probability approach, in capacity estimation methods which are currently used to estimate the capacity mainly for freeways. Breakdown probability methods such as the Product Limit Method (PLM), the Sustained Flow Index (SFI), the Highway Capacity Manual (HCM) method are used to check the applicability of the breakdown probability approach in calculating highway capacity under heterogeneous conditions. These breakdown probability methods were applied for data collected from two multilane highway locations where heterogeneous flow conditions were observed. The capacity values obtained through the breakdown probability approach were compared with the capacity values obtained from the Greenberg model which is the considered conventional method. The breakdown approach resulted in capacity values which are less by an overall range of 7.4% to 30.9% for both locations.
{"title":"Study On The Applicability Of Capacity Estimation Methods To Evaluate Multilane Highway Capacity Under Heterogeneous Conditions","authors":"U. L. M. A. Uswaththa, H. Pasindu, J. Bandara, D. Jayaratne","doi":"10.1109/MERCon52712.2021.9525674","DOIUrl":"https://doi.org/10.1109/MERCon52712.2021.9525674","url":null,"abstract":"Highway capacity is an essential element in highway planning and traffic management. There are a number of methods developed to estimate highway capacity. Most of them focus on identifying the maximum flow or throughput using a traffic speed-flow model. However, it has been found that these capacity estimates are not practical as they cannot be sustained for long, under normal flow conditions. This research mainly focuses on using the breakdown probability approach, in capacity estimation methods which are currently used to estimate the capacity mainly for freeways. Breakdown probability methods such as the Product Limit Method (PLM), the Sustained Flow Index (SFI), the Highway Capacity Manual (HCM) method are used to check the applicability of the breakdown probability approach in calculating highway capacity under heterogeneous conditions. These breakdown probability methods were applied for data collected from two multilane highway locations where heterogeneous flow conditions were observed. The capacity values obtained through the breakdown probability approach were compared with the capacity values obtained from the Greenberg model which is the considered conventional method. The breakdown approach resulted in capacity values which are less by an overall range of 7.4% to 30.9% for both locations.","PeriodicalId":6855,"journal":{"name":"2021 Moratuwa Engineering Research Conference (MERCon)","volume":"46 1","pages":"474-479"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83691347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-27DOI: 10.1109/MERCon52712.2021.9525679
Sadna Dissanayake, T. Rupasinghe
This paper presents an overview of integrating warehouse design and optimization modelling approach to enhance the supply chain performance. The approach is derived through a literature review as well as by considering the practitioners approach in the Sri Lankan context. The method is explained along with the framework to integrate the isolated solutions and derive the overall warehouse design solution, simulation, and optimization models. The main contribution of this paper is to guide the practitioners in consistently maintaining an optimum warehouse operation through warehouse design to enhance supply chain performance.
{"title":"An Analytical Design & Optimization approach to enhance Warehouse Operations","authors":"Sadna Dissanayake, T. Rupasinghe","doi":"10.1109/MERCon52712.2021.9525679","DOIUrl":"https://doi.org/10.1109/MERCon52712.2021.9525679","url":null,"abstract":"This paper presents an overview of integrating warehouse design and optimization modelling approach to enhance the supply chain performance. The approach is derived through a literature review as well as by considering the practitioners approach in the Sri Lankan context. The method is explained along with the framework to integrate the isolated solutions and derive the overall warehouse design solution, simulation, and optimization models. The main contribution of this paper is to guide the practitioners in consistently maintaining an optimum warehouse operation through warehouse design to enhance supply chain performance.","PeriodicalId":6855,"journal":{"name":"2021 Moratuwa Engineering Research Conference (MERCon)","volume":"16 1","pages":"356-361"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73010192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-27DOI: 10.1109/MERCon52712.2021.9525758
D. Kariyawasam, Chandana Siriwardana
Even though the implementation of lean practices into the construction framework have many advantages, thus far, the use of lean in the Sri Lankan construction industry is seldom and infrequent. Though many success stories exist around the world on implementing Lean Construction (LC), why the concept is untapped in Sri Lankan context require a thorough and in-depth understanding on the Barriers for LC implementation. In this study, a comprehensive analysis is done on identifying and assessing the possible factors that affect the application of LC, and factors to overcome those barriers based on an extensive literature review followed by a statistical analysis of data from a questionnaire survey which targeted professionals in the industry. From the results obtained from the questionnaire a recommendation was made on integrating Visual Management (VM) practices through means of digital communication as a lean tool, and the feasibility of the application was appraised through a questionnaire survey where a favourable result was obtained. The outcome of this study could help companies to overcome barriers and focus their attention and resources on the significant issues, crucial to support the successful implementation of LC and develop a framework to integrate Visual Management practices into digital communication.
{"title":"Feasibility Study on, Enablers and Barriers for the Implementation of Lean Construction and the Applicability of Visual Management Practices Through Forms of Digital Communication in the Sri Lankan Industry","authors":"D. Kariyawasam, Chandana Siriwardana","doi":"10.1109/MERCon52712.2021.9525758","DOIUrl":"https://doi.org/10.1109/MERCon52712.2021.9525758","url":null,"abstract":"Even though the implementation of lean practices into the construction framework have many advantages, thus far, the use of lean in the Sri Lankan construction industry is seldom and infrequent. Though many success stories exist around the world on implementing Lean Construction (LC), why the concept is untapped in Sri Lankan context require a thorough and in-depth understanding on the Barriers for LC implementation. In this study, a comprehensive analysis is done on identifying and assessing the possible factors that affect the application of LC, and factors to overcome those barriers based on an extensive literature review followed by a statistical analysis of data from a questionnaire survey which targeted professionals in the industry. From the results obtained from the questionnaire a recommendation was made on integrating Visual Management (VM) practices through means of digital communication as a lean tool, and the feasibility of the application was appraised through a questionnaire survey where a favourable result was obtained. The outcome of this study could help companies to overcome barriers and focus their attention and resources on the significant issues, crucial to support the successful implementation of LC and develop a framework to integrate Visual Management practices into digital communication.","PeriodicalId":6855,"journal":{"name":"2021 Moratuwa Engineering Research Conference (MERCon)","volume":"34 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77115114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-27DOI: 10.1109/MERCon52712.2021.9525699
H. Rajapakse, S. Adikary
Chitosan/nanohydroxyapatite composite was synthesized by co-precipitation of nanohydroxyapatite onto a chitosan scaffold. The aim of this research was to extract chitosan from locally sourced shrimp shells species Penaeus Monodon and to synthesize chitosan/nanohydroxyapatite composite. The morphology, crystalline structure and composition of the composites were investigated using Scanning electron microscopic analysis, X-ray diffractometry, Fourier transform infrared spectroscopy, and thermogravimetric analysis. Hydroxyapatite nanoparticles dispersed in the chitosan matrix were observed in the scanning electron microscope (SEM). The size of the nanohydroxyapatite particles was estimated to be 13 nm by the X-ray diffractometer pattern using the Halder-Wagner method and this value was confirmed by the SEM images. From the energy dispersive X-ray analysis, the Ca/P weight ratio obtained was around 2 which equivalents to that of hydroxyapatite. The thermogravimetric analysis measurements of the composites concluded that the decomposition temperature decreases with increasing Hydroxyapatite content.
{"title":"Synthesis and Characterization of Chitosan/Hydroxyapatite Nanocomposite for Bone Tissue Engineering Applications","authors":"H. Rajapakse, S. Adikary","doi":"10.1109/MERCon52712.2021.9525699","DOIUrl":"https://doi.org/10.1109/MERCon52712.2021.9525699","url":null,"abstract":"Chitosan/nanohydroxyapatite composite was synthesized by co-precipitation of nanohydroxyapatite onto a chitosan scaffold. The aim of this research was to extract chitosan from locally sourced shrimp shells species Penaeus Monodon and to synthesize chitosan/nanohydroxyapatite composite. The morphology, crystalline structure and composition of the composites were investigated using Scanning electron microscopic analysis, X-ray diffractometry, Fourier transform infrared spectroscopy, and thermogravimetric analysis. Hydroxyapatite nanoparticles dispersed in the chitosan matrix were observed in the scanning electron microscope (SEM). The size of the nanohydroxyapatite particles was estimated to be 13 nm by the X-ray diffractometer pattern using the Halder-Wagner method and this value was confirmed by the SEM images. From the energy dispersive X-ray analysis, the Ca/P weight ratio obtained was around 2 which equivalents to that of hydroxyapatite. The thermogravimetric analysis measurements of the composites concluded that the decomposition temperature decreases with increasing Hydroxyapatite content.","PeriodicalId":6855,"journal":{"name":"2021 Moratuwa Engineering Research Conference (MERCon)","volume":"50 1","pages":"555-560"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77115252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-27DOI: 10.1109/MERCon52712.2021.9525735
H.P.A. Jayamini, J. Weliwita, M. Narayana, S. Witharana, N. Hettiarachchi
In an era where the conservation of energy is paramount, one cannot overlook the substantial amount of energy consumed by domestic cooking processes. Rice cooking is one of them, in the East in particular, where rice is a staple food. In this work, pre-soaking and boiling processes of white raw rice were investigated through experimentation followed by CFD simulation. Temperature profiles while boiling and the moisture gain during cooking were obtained. The findings reconfirmed the two underlying mechanisms, i.e., gelatinization-driven cooking at lower temperatures, and, diffusion-driven cooking at elevated temperatures. Moreover it was revealed that by fine-tuning the rice cooking process, the cooking duration could be reduced by nearly 15%, saving the cooking energy as much. Finally the moisture diffusion coefficient was accurately modeled using the OpenFoam software.
{"title":"Study of Moisture Transport in Rice Cooking","authors":"H.P.A. Jayamini, J. Weliwita, M. Narayana, S. Witharana, N. Hettiarachchi","doi":"10.1109/MERCon52712.2021.9525735","DOIUrl":"https://doi.org/10.1109/MERCon52712.2021.9525735","url":null,"abstract":"In an era where the conservation of energy is paramount, one cannot overlook the substantial amount of energy consumed by domestic cooking processes. Rice cooking is one of them, in the East in particular, where rice is a staple food. In this work, pre-soaking and boiling processes of white raw rice were investigated through experimentation followed by CFD simulation. Temperature profiles while boiling and the moisture gain during cooking were obtained. The findings reconfirmed the two underlying mechanisms, i.e., gelatinization-driven cooking at lower temperatures, and, diffusion-driven cooking at elevated temperatures. Moreover it was revealed that by fine-tuning the rice cooking process, the cooking duration could be reduced by nearly 15%, saving the cooking energy as much. Finally the moisture diffusion coefficient was accurately modeled using the OpenFoam software.","PeriodicalId":6855,"journal":{"name":"2021 Moratuwa Engineering Research Conference (MERCon)","volume":"40 1","pages":"240-244"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80351747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-27DOI: 10.1109/MERCon52712.2021.9525789
Charmy Weerakoon, Surangika Ranathunga
Question answering can be considered as a key area in Natural Language Processing and Information Retrieval, where users construct queries in natural language and receive suitable answers in return. In the travel domain, most questions are “content questions”, where the expected answer is not the equivalent of “yes” or “no”, but rather factual information. Replying to a free-form factual question based on a large collection of text is challenging. Previous research has shown that the accuracy of question answering systems can be improved by adding a classification phase based on the expected answer type. This paper focuses on implementing a multi-level, multi-class question classification system focusing on the travel domain. Existing research for the travel domain is conducted using language-specific features and traditional Machine Learning models. In contrast, this research employs transformer-based state-of-the-art deep contextualized word embedding models for question classification. The proposed method improves the coarse class Micro F1-Score by 5.43% compared to the baseline. Fine-grain Micro F1-Score has also improved by 3.8%. We also present an empirical analysis of the effectiveness of different transformer-based deep contextualized word embedding models for multi-level multi-class classification.
{"title":"Question Classification for the Travel Domain using Deep Contextualized Word Embedding Models","authors":"Charmy Weerakoon, Surangika Ranathunga","doi":"10.1109/MERCon52712.2021.9525789","DOIUrl":"https://doi.org/10.1109/MERCon52712.2021.9525789","url":null,"abstract":"Question answering can be considered as a key area in Natural Language Processing and Information Retrieval, where users construct queries in natural language and receive suitable answers in return. In the travel domain, most questions are “content questions”, where the expected answer is not the equivalent of “yes” or “no”, but rather factual information. Replying to a free-form factual question based on a large collection of text is challenging. Previous research has shown that the accuracy of question answering systems can be improved by adding a classification phase based on the expected answer type. This paper focuses on implementing a multi-level, multi-class question classification system focusing on the travel domain. Existing research for the travel domain is conducted using language-specific features and traditional Machine Learning models. In contrast, this research employs transformer-based state-of-the-art deep contextualized word embedding models for question classification. The proposed method improves the coarse class Micro F1-Score by 5.43% compared to the baseline. Fine-grain Micro F1-Score has also improved by 3.8%. We also present an empirical analysis of the effectiveness of different transformer-based deep contextualized word embedding models for multi-level multi-class classification.","PeriodicalId":6855,"journal":{"name":"2021 Moratuwa Engineering Research Conference (MERCon)","volume":"24 1","pages":"573-578"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77828962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-27DOI: 10.1109/MERCon52712.2021.9525684
A. Selvaratnam, K. K. Arachchi, J. Gamage
EPS (Expanded Polystyrene) is a well-established insulation material in the Civil Engineering Industry. This paper presents an experimental and numerical investigation of cementitious insulation developed using EPS for Carbon Fiber Reinforced Polymer (CFRP) – Concrete composites. An EPS blended insulation was applied to the CFRP/Concrete composites and tested at elevated temperatures. A numerical model was also developed to predict the heat transfer behavior of the CFRP/Concrete composites with the developed insulation under standard fire conditions. The simulations showed that the bond line has reached the glass transition temperature within a short period of time while the insulated members withstood more time. The model results indicated that the CFRP/Concrete which composites with coarser EPS can achieve 75% to 94% of fire resistance, and composites with finer EPS can achieve 83% to 99% of fire resistance than the insulation materials already commercially available.
{"title":"Fire performance of CFRP/Concrete composites insulated with recycled EPS-cement blend","authors":"A. Selvaratnam, K. K. Arachchi, J. Gamage","doi":"10.1109/MERCon52712.2021.9525684","DOIUrl":"https://doi.org/10.1109/MERCon52712.2021.9525684","url":null,"abstract":"EPS (Expanded Polystyrene) is a well-established insulation material in the Civil Engineering Industry. This paper presents an experimental and numerical investigation of cementitious insulation developed using EPS for Carbon Fiber Reinforced Polymer (CFRP) – Concrete composites. An EPS blended insulation was applied to the CFRP/Concrete composites and tested at elevated temperatures. A numerical model was also developed to predict the heat transfer behavior of the CFRP/Concrete composites with the developed insulation under standard fire conditions. The simulations showed that the bond line has reached the glass transition temperature within a short period of time while the insulated members withstood more time. The model results indicated that the CFRP/Concrete which composites with coarser EPS can achieve 75% to 94% of fire resistance, and composites with finer EPS can achieve 83% to 99% of fire resistance than the insulation materials already commercially available.","PeriodicalId":6855,"journal":{"name":"2021 Moratuwa Engineering Research Conference (MERCon)","volume":"1 1","pages":"142-147"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88644357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-27DOI: 10.1109/MERCon52712.2021.9525670
D. Haputhanthri, A. Wijayasiri
Accurate short-term traffic volume forecasting has become a component with growing importance in traffic management in intelligent transportation systems (ITS). A significant amount of related works on short-term traffic forecasting has been proposed based on traditional learning approaches, and deep learning-based approaches have also made significant strides in recent years. In this paper, we explore several deep learning models that are based on long-short term memory (LSTM) networks to automatically extract inherent features of traffic volume data for forecasting. A simple LSTM model, LSTM encoder-decoder model, CNN-LSTM model and a Conv-LSTM model were designed and evaluated using a real-world traffic volume dataset for multiple prediction horizons. Finally, the experimental results are analyzed, and the Conv-LSTM model produced the best performance with a MAPE of 9.03% for the prediction horizon of 15 minutes. Also, the paper discusses the behavior of the models with the traffic volume anomalies due to the Covid-19 pandemic.
{"title":"Short-Term Traffic Forecasting using LSTM-based Deep Learning Models","authors":"D. Haputhanthri, A. Wijayasiri","doi":"10.1109/MERCon52712.2021.9525670","DOIUrl":"https://doi.org/10.1109/MERCon52712.2021.9525670","url":null,"abstract":"Accurate short-term traffic volume forecasting has become a component with growing importance in traffic management in intelligent transportation systems (ITS). A significant amount of related works on short-term traffic forecasting has been proposed based on traditional learning approaches, and deep learning-based approaches have also made significant strides in recent years. In this paper, we explore several deep learning models that are based on long-short term memory (LSTM) networks to automatically extract inherent features of traffic volume data for forecasting. A simple LSTM model, LSTM encoder-decoder model, CNN-LSTM model and a Conv-LSTM model were designed and evaluated using a real-world traffic volume dataset for multiple prediction horizons. Finally, the experimental results are analyzed, and the Conv-LSTM model produced the best performance with a MAPE of 9.03% for the prediction horizon of 15 minutes. Also, the paper discusses the behavior of the models with the traffic volume anomalies due to the Covid-19 pandemic.","PeriodicalId":6855,"journal":{"name":"2021 Moratuwa Engineering Research Conference (MERCon)","volume":"58 1","pages":"602-607"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90926130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：