MERCon - 2023

Permanent URI for this collectionhttp://192.248.9.226/handle/123/22081

Browse

Now showing 1 - 20 of 137

item: Conference-Full-text
Moratuwa Engineering Research Conference 2023 (Pre Text)
(IEEE, 2023-12-09) Abeysooriya, R; Adikariwattage, V; Hemachandra, K
item: Conference-Full-text
Implementation of a large piezoresistive sensor array scanning mechanism based on xilinx zynq apsoc
(IEEE, 2023-12-09) Warnakulasuriya, A; De Silva, AC; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
The foremost complication of scanning a large sensor array is the increased number of sensors which generate large volumes of data. Hence, a suitable hardware based implementation is necessary to manage such data efficiently. We formulated a scanning mechanism for a large piezoresistive sensor array using a Xilinx Zynq device and custom developed RTL modules. The zynq device acts as the brain of the scanning mechanism issuing control signals and acquiring ADC readings. Therefore, we developed a scanning mechanism using a combination of Xilinx standard IP cores and custom made RTL modules, and deployed it in a zynq device. Performance of the implemented mechanism depends primarily on the developed adc 0 module. It inherits bulk of the functionality of the developed system. Hence, behavioral simulations were conducted on Vivado design suite with respect to data buffering capability, control signal issuance, data alignment and transmission for the adc 0 module. Subsequent overall analysis conducted on the system indicated that the developed system is efficiently functioning.
item: Conference-Full-text
Development of ai-based optimum energy resource management system for prosumers with solar rooftops
(IEEE, 2023-12-09) Weerasekara, DHNR; Wella Arachchi, WAPK; Wellala, SRG; Rodrigo, AS; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
Solar installations are becoming popular around the world and have emerged as a promising solution to address the increased energy needs while reducing carbon emissions. To harness the full potential of solar photovoltaic (PV) systems, efficient resource management systems play a vital role. This research paper proposes an efficient solar PV energy resource management system to optimize performance and increase the profits of the prosumers. Utility providers have introduced several tariff systems for the financial motivation of customers. In the proposed method, the load demand and Solar PV generation are forecasted for the next 48 hours using the Long Short-Term Memory (LSTM) model. Then, the cost function is optimized using the Sequential Least Squares Programming (SLSQP) algorithm, and an energy dispatch schedule is provided for the customer. The results of the study show that the electricity cost is reduced for the prosumer by the proposed method than the conventional rule-based energy management systems.
item: Conference-Full-text
Development of a software tool for grounding system design in regular and irregular shaped areas
(IEEE, 2023-12-09) Rodrigo, AS; Harshamal, VGY; Kawmadie, PRU; Vidanapathirana, TS; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
In this paper, primary focus is the computation of grounding parameters essential for both regular and irregular grounding grid designs. The key grounding parameters under examination encompass ground resistance, surface voltage, touch voltage, and step voltage. To fulfill this objective, a specialized software tool is introduced, consisting of a computer program. This software is underpinned by mathematical models specifically engineered to facilitate the precise determination of grounding parameters tailored to varying soil structures. Our approach entails a rigorous comparative analysis, wherein the outcomes generated by our methodology are compared with existing methods documented in the literature.
item: Conference-Full-text
Vision attentive robot for elderly room
(IEEE, 2023-12-09) Sudasinghe, SATN; Sooriyabandara, IKS; Banadara, AHMDPM; Rajendran, H; Jayasekara, AGBP; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
With people's busy schedules, elderly people have to stay alone in their houses in the daytime. There are a large number of accidents have happened to elderly people when they are alone at home. It is crucial to have a monitoring system to identify the potential hazards for the protection of elders to address this risk. In this research, we propose a method to identify postural behaviors, walking abnormalities, and falling situations using the skeleton data obtained from the Microsoft Kinect camera. In this paper, we discuss the identification of the falling of an older person. For that, we used an LSTM model, and the features of the model are velocities of angles and joints of the skeleton. This system achieved a validation accuracy of 88.34%, and it offers a promising solution for keeping an eye on and recognizing potential dangers for elderly people.
item: Conference-Full-text
Numerical study on the blast performance of composite foam-filled re-entrant auxetic honeycomb-cored sandwich panels under air blast loading
(IEEE, 2023-12-09) Rajapakse, Y; Muthulingam, V; Kulathunga, T; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
The study combines the re-entrant auxetic honeycomb with a foam infill to introduce the composite foam-filled re-entrant auxetic honeycomb-cored sandwich panel (FRAP) with the aim of developing a further enhanced blast protection system. The blast performance was numerically evaluated using the general-purpose finite element package ABAQUS/Explicit. This paper discusses the development and validation of the numerical model, parametric analysis, minimum weight design, behaviour and performance of the proposed sandwich panel under air blast loading. The results depict, increase in both face-sheet thickness and re-entrant auxetic honeycomb wall thickness enhances the blast performance of FRAP, the optimum face-sheet and re-entrant auxetic honeycomb wall thicknesses for the proposed most feasible FRAP configuration to be 3.4 mm and 1.9 mm respectively. The proposed FRAP exhibits 66% and 98.5% respective enhanced blast performance compared to monolithic re-entrant auxetic honeycomb-cored sandwich panel (RAHP) and monolithic foam-cored sandwich panel (MFSP), with a total mass expense of only 1.2% compared to RAHP.
item: Conference-Full-text
Assessment of ni phytomining potential in Ginigalpelessa serpentinite deposit, southeast Sri Lanka
(IEEE, 2023-12-09) Dilshara, P; Senarath, S; Ratnayake, N; Abeysinghe, B; Premasiri, R; Dushyantha, N; Ratnayake, A; Batapola, N; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
Nickel (Ni) phytomining is an emerging mining technique that uses hyperaccumulator plants to recover Ni from low-grade metal-rich soils such as serpentine. The Ginigalpelessa serpentinite deposit in Sri Lanka contains high concentrations of Ni, Cr, and Co where the phytomining potential is not well-documented. Therefore, the present study determines Ni, Cr, and Co contents in the soil and assesses the relationship between Ni content and plant diversity to identify potential areas for phytomining in the deposit. Thirty-one soil and twenty-five rock samples were collected from the deposit to analyze their metal contents. The abundant plant species were recorded at each location to analyze the plant diversity and species evenness using the Shannon Weiner Diversity Index. Based on soil analysis, Ni concentration in Ginigalpelessa serpentine soil ranged from 4,005 to 17,352 mg/kg which is within the range of global Ni phytomining grade (6,000 – 12,000 mg/kg). Moreover, areas having low diversity (0.0919 - 0.3061) showed high enrichment of Ni (7,000 - 12,000 mg/kg), emphasizing that low diversity areas with high Ni-enriched soils are suitable for in-situ Ni phytomining. However, further studies are required to assess the Ni hyperaccumulation ability of the abundant plant species to implement Ni phytomining in the Ginigalpelessa serpentinite deposit.
item: Conference-Full-text
Possible influences of covid-19 on infrastructure
(IEEE, 2023-12-09) Wijekoon, U; Dias, P; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
During the coronavirus (COVID-19) outbreak, there was a sharp rise in the number of persons working from home (WFH), which eventually became the "new normal". The aim of this study was to fill the gap in detailed quantitative knowledge regarding space and travel savings as a result of WFH, albeit via a specific case study. The main objectives were to (i) Identify relevant issues via a systematic literature review; (ii) Compute the office space and fuel savings accrued when using hybrid working techniques; (iii) Explore employee preferences and attitudes towards WFH after categorizing the employees and (iv) Seek correlations between responses from the various employee responses. The findings show that, considering the reduced number of days of office space usage, 59% of office area can be saved from WFH. The employees' fuel savings were calculated for five separate groups of staff. The fuel savings ranged from 52% to 69% across the groups. The data indicated that employees are happy to work from home in general, and that there is potential to save office space. There is also some evidence that existing social differences across the workforce may have widened.
item: Conference-Full-text
Utilization of pre-gelatinized lesser yam flour to formulate coconut milk yoghurt
(IEEE, 2023-12-09) Umayangani, GDS; Silva, M; Sandaruwani, A; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
This study employs pre-gelatinized lesser yam (Dioscorea esculanta) flour to make coconut milk yoghurt. Coconut milk of 22% fat was supplemented with 2%, 4%, 6% of lesser yam flour and corn starch for control. pH, syneresis, LAB, TA, and sensory characteristics were analysed to determine the suitable flour concentration throughout 21 days at 4°C. Syneresis differed in samples with lesser yam flour. Commercial coconut milk yoghurt exhibited less syneresis than lesser yam flour added yoghurt. 2% reduced yam flour lowers sensory preference values, some of which are statistically significant. 4% and 6% lesser yam flour samples tasted identical to the control sample. 4% and 6% reduced yam flour had identical pH, syneresis, LAB count, and sensory results. Thus, 4% yam flour produces high-quality yoghurt sample with less flour amount. This study suggested that the yoghurt product made from coconut milk can be obtained utilizing lesser yam flour as a yogurt stabilizer.
item: Conference-Full-text
Beyond the run-rate: forecasting framework for first innings score in t20 cricket
(IEEE, 2023-12-09) Abeysuriya, D; Fernando, S; Navarathna, R; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
With the popularity of the T20 cricket format, the game of cricket has dramatically changed compared to several decades ago. Every year there are more than 100s matches played, which results in thousands of data that can be used by sports analysts in cricket. Several studies have attempted various analyses of the game, such as predicting the likelihood of a team’s victory, analyzing individual player performances and forecasting scores. However, forecasting scores has not been studied extensively and limited to specific teams, rather than a generalized approach. Our paper presents a generalised novel deep neural network-based method to predict the score of the first innings in a T20 international cricket match. The model utilizes various attributes in three categories namely a) current status of the match b) performance of the current batsmen and c) performance of the bowler and provides predictions for each over. We have used recent 5 years T20 international matches from 14 teams and tested our method in the 2022 ICC Men’s T20 World Cup. We demonstrate our findings quantitatively and qualitatively in this paper.
item: Conference-Full-text
Flight dynamics of a 'v' shape boomerang: effect of wind on boomerang trajectory
(IEEE, 2023-12-09) Rajathurai, R; Kumara, KJC; Baduge, S; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
Boomerangs have captured attention because of the mechanical structure that realises such complex movements of the boomerang. The perfect prediction of the path leads to the application of boomerangs in the field. The external environment is always unsteady; therefore, the dynamics of boomerangs should be studied in unsteady wind conditions. The main aim of this research is to study the steady and unsteady wind effects on the boomerang trajectory by developing an unsteady input-based mathematical model. A traditional 'V' shape boomerang is designed using CATIA V5, and 2D steady state ANSYS Computational Fluid Dynamics Simulation (CFD) was performed to derive the aero dynamical coefficients of the boomerang. Finally, the newly developed mathematical model is numerically simulated using MATLAB. The trajectory of the boomerang in different wind conditions is plotted and compared. The results show that the steady and unsteady wind highly influences the boomerang path. Results show the capabilities of the model under both the steady and unsteady flow of wind in predicting a boomerang trajectory.
item: Conference-Full-text
A decision support model to manage demand disruptions of fast-moving consumer goods during a pandemic in Sri Lanka
(IEEE, 2023-12-09) Pathirawasam, D; Hewage, U; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
Decision support models play a crucial role within an organization’s demand planning process when emerging pandemics cause disturbances in demand. The increasing trend of pandemics and the long-lasting struggle it create with unpredicted consumer demand and behaviors necessitate the identification of solutions for sudden demand fluctuations during a disruption. The study addresses the absence of quantitative models in the Sri Lankan context to mitigate disruptions in the demand for fast-moving consumer goods caused by pandemics. The results highlight a substantial difference between the aggregate consumption of "Personal Care" and "Home Care" commodities before and after the pandemic. A literature review identified 23 factors that influence demand disruption during a pandemic globally. Then, validated factors for the Sri Lankan context and assessed using Grey relational analysis. The results highlight inflation, consumer wages, prices, and government regulations have a significant impact on disrupting demand during a pandemic in Sri Lanka. The Grey model with 2-AGO is the most suitable model to manage demand disruptions of ‘Personal Care’ and ‘Home Care’ commodities during a pandemic when compared to traditional time series models. The results will assist companies in managing demand disruptions with rapid demand forecasts and taking precautionary actions against fluctuating influencing factors.
item: Conference-Full-text
Personalized mood-based song recommendation system using a hybrid approach
(IEEE, 2023-12-09) Ranasingha, SS; Silva, T; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
Music recommendation systems are becoming a crucial concern for the music industry because of the rise of digitization and the subsequent increase in music consumption. Music applications continuously strive to enhance their recommendation systems to ensure that users have an exceptional listening experience and remain loyal to their platform. In the early days, the recommendation system used collaborative filtering and content-based approaches to achieve this goal, but these approaches have an issue with a cold start, and context awareness of these approaches is less. Researchers identified in the context of the personalization of songs, Emotion, and mood can play a huge role. Research has shown that a user's current emotional state significantly influences their musical preferences in the short term. Therefore, the recommendation system moves toward mood-based recommendation approaches. The vast variety and context-dependent character of the data that must be considered present the main difficulty for moodbased recommendation systems. This information can vary greatly and is depending on several variables, including the user's environment and personal circumstances. Hybrid approaches have shown very good results in this domain. Therefore, in this paper, we are proposing a hybrid approach for a mood-based personalized song recommendation system. This approach combines content-based and context-based approaches together. The proposed solution produces the output as a personalized song recommendation for the music listener. This output is determined by several parameters including user mood, the profile of the user, and history of previously listened to songs. This solution impacts all the stakeholders. it improves the quality of service of music streaming platforms and improves the user experience.
item: Conference-Full-text
Integration of low-cost sensing systems for autonomous vessel detection: leveraging acoustic and vision information
(IEEE, 2023-12-09) Ranasinghe, P; Satharasinghe, A; Amarasinghe, R; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
The paper presents a novel framework for automatic classification and detection of waterborne vessels, tailored explicitly to integrate with low-cost, low-power off-the-shelf sensors and hardware. This framework demonstrates the practicality of incorporating affordable hardware and sensors into unmanned surface vehicles (USVs) to achieve dependable real-time surveillance and reconnaissance capabilities. This initiative marks a significant achievement as it is the first to successfully extract both auditory and visual signatures of bottom trawling vessels, presenting compelling evidence to identify vessels engaged in the detrimental practice. The acoustic signal classification model utilizes the Mel Frequency Cepstral Coefficients (MFCCs) and employs a multi-class neural network model for accurate classification. The proposed model achieves an impressive testing accuracy of 95.42%, highlighting the effectiveness of MFCCs in clustering underwater acoustic signals. The visual component of the system utilizes the YOLOv3-tiny model and is optimized to facilitate faster inferencing. It is seamlessly integrated with the DeepSORT tracking algorithm, enhancing the overall detection capabilities. By combining the strengths of visual and acoustic subsystems, this integrated approach overcomes the limitations of each component individually. It provides a powerful solution for the detection of vessels and activities while offering a practical approach to maritime defence and ocean conservation
item: Conference-Full-text
Development of conductive sensing material for accurate quantitative and qualitative detection of phthalates in aqueous environments
(IEEE, 2023-12-09) Anuchani, P; Abeysinghe, H; Etampawala, TNB; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
Recently, rapid, quick and in-situ phthalate detection methods have gained significant attention over already existing complex, sophisticated phthalate detecting techniques. In this study, an easy to-use sensing material was developed by incorporating multi-walled carbon nanotubes (MWCNT) in a silver modified cellulose matrix. The conductive sensing material was fabricated as a composite paper, and its electrical conductivity was duly confirmed. With the adsorption of phthalate owing to the formation of phi-phi interactions, the conductivity of the composite decreased. The reduction of conductivity of the composite papers was measured using four probe conductivity meter. The morphology of the sensing material was studied using scanning electron spectroscopy while Raman analysis was conducted to determine phthalate adsorption to MWCNT. The developed sensing material shows the ability to distinguish phthalate molecules qualitatively. Using the simple four-probe conductivity technique, the composite paper can quantitatively determine phthalate content in aqueous solutions down to 0.1 ppm.
item: Conference-Full-text
Coordination of pv smart inverters for grid voltage regulation
(IEEE, 2023-12-09) Latani, T; Parameswaran, G; Priyanthan, G; Hemapala, KTMU; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
In the contemporary energy market, the utilization of photovoltaic (PV) is increasing considerably. This change brings new challenges to the power grid because of its variable and intermittent nature. One of the main issues is voltage violations and PV curtailment. A smart inverter (SI) provides a fast response method to regulate the voltage by varying real or reactive power at the point of common coupling (PCC). When multiple SIs operate under an autonomous control scheme, the reactive power level exceeds the threshold level. This creates an undesirable situation in the system. This paper mainly considers the coordination of the SI using a deep reinforcement learning algorithm (DRL). The DRL agent learns the policy through interaction with the IEEE-37 test feeder in the OpenDSS simulation to find out the optimal action. By defining the rewards scheme of the action carefully, the reactive power of SI can be utilized optimally, and the PV voltage will be maintained within the normal operating zone. Validation of the DRL agent’s performance is done with the local autonomous control scheme. The results assure that a well-trained DRL agent can coordinate multiple SIs for voltage regulation and PV curtailment reduction.
item: Conference-Full-text
Frequency stability analysis of non-conventional renewable integrated power systems
(IEEE, 2023-12-09) Wijethunga, WMRM; Wijesena, PAHK; Samarawickrama, TD; Wadduwage, DP; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
Integrating intermittent non-conventional renewable energy sources such as wind and solar into power systems presents unique challenges for its operation. To address this, effective frequency control mechanisms are crucial. This study presents a comprehensive analysis investigating the performance of hydro and steam, in a non-conventional renewable integrated power system. The analysis aimed to enhance power system stability through the collective operation of wind and solar power plants of varying capacities, while maintaining a stable frequency. In addition, the study investigated the maximum penetration level of these resources under different contingencies. Preliminary results indicate that the hydro turbine exhibits a longer settling time and higher steady-state error compared to its steam turbine counterpart. Using a 12 bus test system simulated in PSCAD software, this research provides valuable insights into turbine performance and the feasibility of integrating renewable resources, aiding in the improvement of power system stability.
item: Conference-Full-text
Application of noise filter mechanism for t5-based text-to-sql generation
(IEEE, 2023-12-09) Aadhil Rushdy, MR; Thayasivam, U; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
The objective of the text-to-SQL task is to convert natural language queries into SQL queries. However, the presence of extensive text-to-SQL datasets across multiple domains, such as Spider, introduces the challenge of effectively generalizing to unseen data. Existing semantic parsing models have struggled to achieve notable performance improvements on these crossdomain datasets. As a result, recent advancements have focused on leveraging pre-trained language models to address this issue and enhance performance in text-to-SQL tasks. These approaches represent the latest and most promising attempts to tackle the challenges associated with generalization and performance improvement in this field. This paper proposes an approach to evaluate and use the Seq2Seq model providing the encoder with the most pertinent schema items as the input and to generate accurate and valid cross-domain SQL queries using the decoder by understanding the skeleton of the target SQL query. The proposed approach is evaluated using Spider dataset which is a well-known dataset for text-to-sql task and able to get promising results where the Exact Match accuracy and Execution accuracy has been boosted to 72.7% and 80.2% respectively compared to other best related approaches.
item: Conference-Full-text
Suitable passive design strategies for residential high-rise buildings in Sri Lanka
(IEEE, 2023-12-09) Perera, US; Tharaka, MGI; Weerasuriya, AU; Weerasuriya, AU; Lewangamage, CS; Ruparathna, R; Mallawaarachchi, R; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
Despite the potential to reduce Energy Use Intensity (EUI), passive design strategies (PDS) have been sparsely integrated into residential high-rise buildings in Sri Lanka partly due to the lack of scientific knowledge available for the construction industry professionals. To bridge this knowledge gap, this study presents a set of guidelines for choosing suitable PDSs for residential high-rise buildings in Sri Lanka. The guidelines are based on the findings of local (LSA) and global (GSA) sensitivity analyses, which evaluated seven popular PDSs in the Sri Lankan construction industry. LSA revealed how EUI varied with PDSs and the most and least reductions for low e-coating on glasses (WS) and multiple glazing (GU). GSA ranked WS and GU as the most and least influential PDSs and categorized the seven PDSs into three groups based on the effect of PDS on EUI in the presence of other PDSs. An evaluation of six PDSs: five combinations and one individual PDS (WS) suggested the combinations should be established between the most influential parameters in the same group to maximize EUI saving. A significant difference in popularity and efficiency was found for the seven PDSs, as the most popular PDSs are the least effective in saving EUI.
item: Conference-Full-text
Effects of covid-19 lockdown on lst, ndvi, lulc, and uhi: Dehiwala-Mount Lavinia case study
(IEEE, 2023-12-09) Madhurshan, R; Mushmika, PAS; Edirisooriya, KVUI; Ishankha, WCA; Dauglas, DLPM; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
The COVID-19 pandemic has had a profound global impact since its outbreak in late 2019. To curb the spread of the virus, measures were implemented to control its transmission, such as reducing human activities, shutting down industries, minimizing transportation, and practicing social distancing. A case study focused on the Dehiwala-Mount Lavinia suburb analyzed various environmental indicators during normal working days in April 2019 and the lockdown phase in April 2020. Landsat 8 (TIRS/OLI) images, processed with ArcMap 10.8.2 software, were used to examine the impact of the lockdown on environmental conditions by comparing Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), Land Use/Land Cover (LULC), and Urban Heat Island (UHI). The results revealed a decrease in LST and an increase in NDVI during the lockdown. The analysis of LULC showed increased vegetation growth near the Aththidiya wetland area. A relatively cooler UHI was observed in 2020 compared to the year 2019. These findings underscore the influence of human activities on UHI and highlight the importance of urban planning and mitigation strategies to address UHI effects on local climates.

Browse

Recent Submissions