ICATC 2022

Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/25969

Browse

Now showing 1 - 20 of 20

A Cost-Effective Remote Saline Level Monitoring Device for Local Hospitals
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Pathirana, P.H.P.U.R.; Arachchi, Shanika
Continuous patient monitoring plays an important role in healthcare industry. The purpose of this research was to develop a new device to remotely monitor the saline level of a patient in cost-effective manner. For that, a prototype has been developed using an IR sensor, load cell, LCD display, servo motor embedded gripper mechanism and a GSM/GPRS module. The load cell is used to measure the weight of the saline bag and the IR sensor is used to detect and count the saline drops that fall through the drip chamber. The saline drop count is displayed on LCD at each time and when level of saline in the bottle reaches the critical level, then the servo motor embedded gripper mechanism is automatically turned on to control the blood backflow and at that time, the clinician will receive an SMS alert to his/her mobile phone through the GSM/GPRS module. To validate the developed system, a test was done using the load cell with standard weights and then, counted the saline droplets with the load cell, servo motor, LCD display, GSM/GPRS module and two LEDs as indicators. Furthermore, an experiment was done with the actual saline fluid with desired drop rate and weights at each time were observed. Arduino Uno has been used as the main controller in this saline level monitoring system. The validated results of this prototype showed that, this system can be installed in the local hospitals and care homes.
Assessment of deforestation and forest degradation in Sri Lanka: Application of the DPSIR framework
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Herath, H. M. T. C.; Dunusinghe, D. N. L.; Pathirana, S. M.
Globally, forests provide habitat for a wide variety of species on earth and play a significant role in helping control global warming by sinking CO2. However, the world is facing a dual problem of deforestation and forest degradation, which are depleting forest biodiversity and ecosystem services everywhere and eventually leading to forest cover loss. Sri Lanka’s Forest cover, a developing country in the South Asian region, has been changing rapidly for two decades. Sri Lanka needs a detailed DPSIR framework with contemporary data and robust analytical descriptions to understand the changing patterns of forest coverage and address the underlying factors affecting them. Hence, this study analyzed the key causes of deforestation and forest degradation in Sri Lanka according to drivers, pressures, state, and impact between 2000 and 2020. Through this study, we have recommended suitable and realistic responses for Sri Lanka to minimize deforestation and forest degradation.
IOT & Cloud Based Attendance Collection and Student Information Chatbot
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Perera, L.A. Tharuka Ravishan; Welhenge, A.M.
The system proposed in this paper addresses two main concerns in the higher education system. One is efficient attendance monitoring of students, and the other concern is implementing an effective mechanism to interact with students to clarify their issues. As for the first concern, an IOT based attendance collection system will be proposed and for the second concern a cloud based chatbot is proposed. The main purpose of the proposed attendance collection system is to provide more efficient methodology to both students and lecturers while eliminating frequent issues such as buddy signing, loss of attendance sheets while improving student attendance scores. There are two parts to the attendance collection system. One is an IOT based device with biometric authentication for attendance collection which was developed using Arduino, microcontrollers, and fingerprint sensors. Second part is a web-based attendance system designed for lecturers or administrators for report generation, which was developed using Structured Query Language (SQL), PHP, JavaScript and HTML. The generated reports can be converted into excel or PDF files as required. As students are more familiar with smart devices than ever, a student information chatbot is proposed as a mechanism to interact with students to clarify their issues. The system establishes transparent and efficient communications with students for their general questions. The prototype chatbot was implemented in google cloud infrastructure and it is integrated with an android application which was built using android studio. The application can be used to interact with the chatbot and have the scalability for more features in the future.
Computer Applications for Asset Management in Passenger Terminals
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Manamperi, Shanika Kanchani; Perera, Asoka Jayalath
At present asset management has become one of the significant areas demarcating its key concepts in every nook and corner of the local industries even though it has branches in worldwide. Condition assessment is a major discipline of the asset management that makes the foundation to develop systematic models that many of the organizations are experimented for, since maintenance of the assets have made real-time challenges for them. The objective of this study is to introduce a Computerized Maintenance Management System developed for asset management in Kandy Multimodal Transit Terminal. Hence, the outcome of this study facilitates the users to monitor and record any and all maintenance work, as well as to keep a historical record of work and track the asset conditions for future references.
Ontology Based Knowledge Management Portal for Coconut Plantation Care
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Ganeshakumaran, Saraga; Wijegunasekara, M. Carmel; Vishwajith, Tharuka
Coconut (Cocos nucifera) is one of Sri Lanka's most significant plantation crops. Different coconut tree parts are used for numerous activities. Decision making is critical in the treatment method of coconut plantation. So, ontology modelling will help in decision making to diagnose causes and treatment methods easily. It is designed and developed to support agriculture engineers, coconut planters, and researchers. The ontology model is designed by using the Delphi method. Data was collected from research papers, articles, coconut research institute’s websites, and through the discussion with farmers, agriculture experts, and coconut research officers. The ontology model is evaluated and validated by tools OOPS! Evaluation editor, DL query & SPARQL Query, and ontology experts. Future work is planned to develop a knowledge management system for the coconut plantation care.
Students’ Perception on using e-Learning Resources as Educational Support Material: A Case study
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Dissanayeke, Uvasara; Swarnathilake, Chanuka; Madujith, Terence
Blended learning is regarded as an effective and low risk strategy which help universities to gradually transform the study programs with the latest technological developments. This study attempts to analyze user perception and requirements of e-learning as part of an ongoing research to develop e-Learning material for a Moodle based e-Learning Management System (ELMS). Student community of an agriculture higher education institution was selected as the study community. A questionnaire survey was used to gather data from a study sample of 182 undergraduates from a selected higher education institution. Data were analyzed using descriptive methods. According to the findings, electronic learning resources were more popular among students when compared to library material. Majority of the students used their personal devices such as mobile phones and laptop computers to access the ELMS. The students preferred to use electronic learning resources and suggested producing more interactive learning materials such as video lectures, which they can use for self-studying.
Production of Garden and Wood Waste-Based Biochar Using Double-Barrel Carbonization Technique
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Herath, Timeshi; Udayanga, Chanaka
Presently, Sri Lankan society is facing a severe challenge in effectively managing the increasing amount of produced wood and garden waste portion of municipal solid wastes. This problem led to serious socio-economic and environmental concerns, which in turn resulted in this project's actions aiming to promote sustainable wood and garden waste management solutions domestically. The main objective of this project is to develop an engineering application for converting Wood and garden-based waste to energy and biochar as a valuable product. Thus, this study guarantees that the double-barrel pyrolysis technique is effective as an urban household application to produce wood and garden waste-based biochar. When selecting a suitable design and dimensions for the double barrel working module, significant considerations included the effectiveness of biochar production (percent conversion), pollution prevention, ease of use, safety, durability, labor, and material expenses. Used discarded wood chips, coconut shells, and husks were carefully cleaned and dried for three days in the scorching sun when preparing the mixed waste samples for experiments. The inner barrel was filled tightly with dry wood and garden waste and placed upside down inside the outer barrel [1]. Therefore, the garden waste will not be exposed to O2 during the heating process. The volume between the containers was filled with wood, which was burnt for heating the inner barrel [1]. After the pyrolysis of garden waste, the solid produced is called biochar. The actual double barrel working model was manufactured using mild steel, which has a high melting point of 1350°C-1530°C [2] and, a thermal conductivity of 42 W/m K at 400 °C [3], with an inner barrel dimension of 0.25 m × 0.09 m × 0.003 m and outer barrel dimensions of 0.28 m × 0.19 m ×0.005 m (height× diameter ×thickness). The selected material, mild steel, was able to withstand without any deformation around 350°C to 450°C+ pyrolysis temperatures, and it was able to cool for the next experiment rapidly. Figure I depicts the finished mild steel double barrel working module. Based on the data obtained during the experiment, the graph of the upward average temperature over time (Figure II) is used to calculate the heating ratio for the wood and garden waste-based biochar product, It is 0.06875ºC/s. The conclusion reached here is that the small-scale double-barrel model can be used to obtain more than 30 wt% of wood and garden waste-based biochar yield from the input sample, through an hour of heating at a temperature range of 390°C to 420°C. Analysis of the produced biochar provided significant data and increased the overall understanding of slow pyrolysis technology. Figure III shows a picture of the yield of wood and garden waste-based biochar produced by using the double barrel working module under zero oxygen conditions. The double barrel pyrolysis experiments in this study indicated that wood and garden waste-based biochar were successfully produced domestically, providing a sustainable solution for municipal solid waste management.
Development of sweet potato starch-based thin films to produce biodegradable packaging materials
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Sasikala, K.L.N.S.; Kondarage, Y.G.; Diyabalanage, S.
Starch-based bioplastics are widely used due to their renewability, sustainability, and cost-effectiveness. On the other hand, native starch films have some barriers to creating good and effective products because of their excessive water absorption and weak mechanical characteristics. In this study it was developed an acid hydrolyzed, sweet potato starch-based thin film as a biodegradable packaging material, and the physiochemical properties of the acid hydrolyzed thin films were also investigated. The sweet potato starch was extracted, and acid hydrolyzed by HCl for 30, 60, and 90 minutes. The results of Fourier Transform Infrared spectrometry (FTIR) show that increasing the acid reaction time considerably reduces water absorption and that the best acid reaction time is resolved at 60 minutes. Films were prepared through gelatinization, using glycerin as a plasticizer. The thin films were characterized through FTIR, X-ray diffraction (XRD), and thermogravimetric analysis (TGA) tests. The FTIR test results indicate that in acid reaction, moisture absorbance decreases. The water absorption test results showed that after 24 hours, the acid hydrolyzed sweet potato starch films have lower water absorption than the native sweet potato starch thin films, with 26. 39% and 46.88%, respectively. The acid hydrolyzed film will increase the strength to 5.7 MPa and reduce elongation. It is conclusive that acid hydrolyzed starch-based thin films have increased tensile strength and durability due to their lower water absorption. Further, these films are introduced as non-toxic, low-cost, and biodegradable materials for packaging applications.
Stack Ensemble Model to Detect the Stress in Humans by Considering the Sleeping Habits
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Kanagarathnam, Mauran; Premisha, P.; Prasanth, Senthan; Banujan, Kuhaneswaran; Kumara, B.T.G.S.
Recently, one of the big challenges encountered by humans is experiencing and managing stress. Beyond the age restriction, people of all ages, from teenagers to seniors, experience issues as a result of stress. Acute and chronic stress are the two main categories of stress. Acute stress is a typical human response that aids in your body’s adaptation to a new situation. In actuality, this form of stress has positive effects. However, the second type of stress, chronic stress, is a crucial type of stress, and this study focused on determining the stress level of this type in advance. This research examined eight attributes related to chronic stress to investigate the chosen person’s sleeping patterns. The Kaggle website provided the dataset that was used in this study. The user’s snoring range, body temperature, limb movement rate, blood oxygen levels, eye movement, number of hours of sleep, heart rate, and stress levels (0-low/normal, 1-medium low, 2-medium, 3-medium high, 4 - high) were all taken into account. The stack ensemble approach was utilized with two levels during this approach. At level 0, the classifiers such as Random Forest, Decision tree, K-nearest neighbour, and XGBoost were considered. At level 1, as a Metamodel, Logistic regression was adopted. Moreover, the predictions obtained from the level 0 models added an additional attribute to the original dataset and fed it to the level 1 model as a new training dataset. Additionally, five folds of fold cross-validation were performed along with the basic assessment to validate further the model for various ratios of training and testing data. Following the cross-validation, the model’s mean accuracy obtained for RF, DT, KNN, XGB and stack ensemble models. From the results discovered, it was represented that the combined model (stack ensemble model) produced more precise results rather than the models considered in isolation.
LSTM Based Emotion Analysis of Text in Tamil Language
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Ahamed, M.R. Faiyaz; Arachchi, S. P. Kasthuri
The sentiments and emotions expressed by users on the internet greatly influence the decision-making process of business firms. Recent studies show that emotion analysis yields more precise information than sentiment analysis. Text emotion analysis has become popular for higher-demand languages like English, Chinese, French, and Arabic. However, no prior studies have been conducted on locally speaking languages, including Tamil, Malayalam, and Sinhala. Therefore, this paper presents a deep learning based novel model to identify the emotions expressed in Tamil texts using a Long Short-Term Memory (LSTM) network. Besides, to enhance the robustness of our proposed model, we conducted experiments with machine learning classifiers, including Support Vector Machine (SVM), Naïve Bayes (NB), Logistic Regression (LR), and Random Forest Classifier (RFC). The experimental results prove that our Tamil text emotion analysis model significantly outperforms other machine learning models, achieving an accuracy of 80%.
Composition Analysis for Implementing Small Scale Sawdust Briquette Manufacturing Process
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Liyanage, H.L.J.M.; Peiris, R.L.
A compressed block of flammable biomass material, such as charcoal, sawdust, wood chips, peat, or paper, is called a briquette and is used as kindling and fuel for a fire. The study was conducted with the objective of improving product quality, testing domestic briquette production in Sri Lanka, and providing a solution to the current fuel crisis. Production process analysis was done here, and the production of briquettes was evaluated using a homemade production machine. Several primary (sawdust and planner scraps), secondary (Jack fruit leaves) and binding (Paper waste and cow dung) materials were used as raw materials and briquettes were manufactured under various compositions. Several home-based tests were performed to determine the physical and combustion properties of the briquette samples produced. These are density, boiling and firing, ash content and shatter resistance tests. Based on the results of the experiments, it was found that adding a binder to the briquette product rather than using only the primary material would increase the quality of the final product. Paper waste and cow dung were used as binders, and it was found that adding 30% - 40% more paper to the primary material than cow dung would increase the stability of the product. Also, jackfruit leaves were used as a secondary material and it was found that using 15% of jackfruit leaves does not harm the quality of the final product, which can reduce the cost of production. According to correlations between all results, the optimum composition found was 45% of primary material + 15% of secondary material (Jack fruit leave) + 40% of binding material (paper waste). These tested small briquettes can be easily used to light a fire during excursions. It can also be concluded that medium-sized products can be used for cooking.
Power Factor Improvement of Industrial Loads using a Capacitor Bank and a Solar PV System
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Kalhari, Madhushika; Bandara, Hasitha Eranda; Ediriweera, Sampath
A significant portion of the cost of manufacturing in the industry is related to electrical power. An electrical system with a low power factor is typically less effective and may also be less profitable for end users and system operators. Therefore, power factor correction is essential for effective system performance and for lowering the cost of electricity. This paper presents a study on the technical and financial benefits of power factor improvement, which is supported by a real-world industrial load with a combination of a capacitor bank and a solar photovoltaic system. A load flow software is used to model and analyse the electrical system of the site with the dynamic loads. The capacitor bank’s connected duration is calculated by keeping track of the power factor, active power, and reactive power values during the day. The capacitor bank is sized to meet the reactive power needed at night. By examining the 24-hour solar irradiance data at the location, the solar system is designed to meet the peak active power consumption of the site. The voltage source converter coupled to the solar system is adjusted to produce the reactive power required to maintain the power factor during the day. The findings demonstrate that the suggested 40 kvar capacitor bank and 553 kW solar system successfully increase power factor by 39%. A simple payback period for the suggested system is six years, and it also results in monthly savings of 905806 LKR.
Adult Learners’ Perceptions of a Blog-based Assessment in an English as a Second Language Course
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Embogama, R. M. S. N.
This study was conducted in order to gather adult learners’ perceptions on the use of blogs for assessing their English writing skills in terms of the perceived benefits, drawbacks, and technical constraints. Being a case study, the research involved a group of adult ESL learners following an English proficiency course at the undergraduate level in a state university in Sri Lanka. It was conducted by using a survey-type questionnaire shared with the purposive sample of year one arts undergraduates who were in the second semester of study. Descriptive statics were used for data tabulation and percentages were generated to decipher the sample’s reaction to a blog-based assessment given to them during the first semester of study. The findings from the data analysis indicate that these students perceived blogs as a valid, acceptable, and beneficial form of assessment that can also improve and motivate them to write in the second language. However, they also admitted that challenges remain when authoring blogs, such as poor bandwidth and lack of connectivity, difficulty in understanding instructions on creating blog accounts, having their content plagiarized, and technical constraints. From the findings, there is a suggestion to first promote the use of blog entries to assess students’ writing skills as a continued practice and second to formulate strategies to counteract the challenges. To sum up, the main findings reveal that in spite of some difficulties, these ESL learners had a highly positive attitude towards the use of blog-based assessments for testing their English writing skills.
Binary decisions and emotional EEG based virtual assistant for speech impairments
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Halpe, Prashadi H.; Aththanayake, Probodha.S.; Haddela, Prasanna S.; Abeywardhana, Lakmini; Bogahawatte, Jinendra; Disanayaka, Sanduni
The potential for brain computer intervention to provide effective and exciting technology for persons with impairments is growing because of the constant advancements in information technology. To help those who have difficulty communicating in a high school environment, our research will develop a wearable assistive device called SPEAK. It is a compact, portable equipment that is lightweight and simple to use. It comes with the Muse 2 headband and a deep learning based assistance program that operates on a mobile device. Sometimes people are unable to communicate vocally for a variety of reasons, yet their minds (brains) nonetheless speak normally. This approach would be really helpful and perfectly acceptable to help such mute individuals who are unable to communicate. This research puts forth the effort to detect and collect the frequency ranges of two significant analytical components that have been particularly chosen, such as binary decision yes/no analysis and emotional analysis. The examined frequencies are compared to the freshly emerging brain signal excitements in order to recognize and comprehend the phrases in accordance with the relevant brain signal. The virtual assistant produces voice for the muted person whenever a word is recognized from a brain signal and is transformed into speech sound.
Lightweight Full-stack Web-based Solution for An Educational Organization
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Bandara, J.M.C.M.; Wijegunasekara, M. Carmel
This paper discusses the web application of the Zonal Education Office, Katugastota and the development and deployment process. The problem statement is discussed using two main parts. They are organizational problems and general problems. The organizational problems discuss the current problems in the organization which needed to be overcome using a web application. The general problems describe the problems that the majority of the organizational web applications were facing. Considering the problem domain, the main aims and objectives were identified. Consequently, the proposed web application provides a lightweight, customizable, usable, cost-effective and secure web experience to the client by ensuring improved decision supportability, productivity and user experience for the organizational stakeholders. The lightweight approach benefited to use of a small amount of disk space for greater productivity, and reduce the loading time of the overall web application. LAMP stack was used to develop this web application. Furthermore, this web application used a few SaaS (Software As a Service). This web application was tested over unit testing, integration testing, system testing and user acceptance testing. The evaluation of the web application was done by design review, questionnaire and comparing similar systems. Since the client was satisfied with the current functionality of the final web application, the web application was deployed.
Production of Cardboard Waste-Based Biochar Using Double-Barrel Carbonization Technique
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Dunusinghe, Navod; Udayanga, Chanaka
With rising population and urbanization, cardboard use has also expanded significantly over the years, resulting in an increase in cardboard waste generation. According to the Environmental Protection Agency, paper goods and corrugated cardboard (CCB) account for 25% of municipal solid waste (MSW) [1]. A practical answer to the waste management issue is the thermal conversion of MSW, particularly the paper and packaging materials; CCB. The primary output from this thermochemical decomposition is bio char which has a number of uses, including improving soil fertility, cleaning up water and soil contaminants. CCB is a better agent for this thermal conversion process because of its high percentage of lignocellulose [2]. The project's main goal is to use the double-barrel pyrolysis technology as a thermo conversion process that is easily applicable to Sri Lankan households to convert cardboard waste into biochar and to investigate the impact of the operating temperature on the yield of produced biochar. The double barrel was designed by considering the several factors including the ease of use, durability, safety, material cost, and the efficiency of the production of biochar. As shown in Figure 1, two mild steel double barrels which had outer barrel dimensions of 280 mm in height and 190 mm in diameter and an inner barrel of 90 mm diameter and 250 mm. height was developed. Inner barrel was filled with 75g of 80mm*40mm (area) cut pieces of CCB and mounted with a thermoscope. Outer barrel was filled with charcoal and burned for 50 min in 4000C. Following that yield was calculated and tea test was used to assess the biochar’s absorption process. our study was carried out in two trials. Trial 01 was done in the temperature range of 380- 4000C for 30 min and the yield was 40% and trial 02 was done at the 380-4100C for 50 min and obtained 26.77%. The results of our experiment have deviations from the literature because the literature had used an auger reactor, which can control temperature and feeding rate over time and the temperature was constantly maintained. However, when it comes to our experiment, the main objective was to introduce a household simple setup, so that the supplied temperature, heat and the federates were varying. The average temperature of each trial shown in figure 2. Hence in our study at average heating rate of 8.5186 0C /min, an average of 33.4 % of yield was produced, Further research should be carried out to improve the double barrel design such as more air intake holes for facilitate the burning process inside the barrel and to keep the set up on a stand that is opened to the atmosphere and a web made of a metal that can withstand temperatures of 400 0C or higher can be placed beneath the inner barrel to avoid difficulties in separating the yield.
A Machine Learning Influenced Recommendation System for Predicting the Rainfall and Price for Crops in Badulla District
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Nandasiri, K.P. Sasindu Madushan; Banujan, Kuhaneswaran; Kumara, B.T.G.S.; Jayasinghe, Sadeeka; Ekanayake, E.M.U.W.J.B.; Senthan, Prasanth
Every day, agriculture becomes more vital to the global economy. Daily population expansion necessitates substantial crop output for human existence. But as the population has increased, human activity has also altered the environment. Therefore, it has resulted in challenges with weather forecasting, which is crucial for crop planting in the agricultural sector. Thus, the globe needs a method to forecast agrarian weather. In addition, it is highly advantageous for farmers to understand the production rate they can achieve and the price range they may expect for their efforts. As a result, Machine learning technologies have become unique and fashionable in the agricultural industry due to their ability to provide accurate farming predictions. Selecting suitable plants for planting has evolved into a necessity. This study focuses on the application of machine learning to estimate the optimal crop for a given period. In this work, the author addresses the beginning part of the study: precipitation prediction under the weather forecast and pricing forecast. The authors have employed six distinct machine-learning models to forecast rainfall and crop prices.
Production of Food Waste-Based Biochar Using Double-Barrel Carbonization Technique
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Vidusanka, Deshan; Udayanga, Chanaka
The high amount of solid waste generation is a critical challenge in Sri Lanka to maintain an effective waste management strategy. Among them, the first largest percentage of waste generated which is food waste generation has become a challenging task for food management due to the high consumption of food waste, and the lack of waste-collecting methods. The major aim of this project was to perform the effective pyrolysis of food waste generated in the household, using the double-barrel carbonization technique to achieve biochar yields that meet the specifications of the final applications. A review of the literature was carried out to identify an acceptable design for the double-barrel working module and dimensions that would fit that design [1]. The mild steel double barrel experimental unit is shown in Figure 1. Dimensions of the outer barrel were 280 mm ×190 mm (height × diameter) and the inner barrel consisted of 90 mm × 250 mm (height × diameter). The household's disposable food waste, including banana peels, rice, and peanut shells, was collected. For the first and second experiments, 60 g of each trash was collected. Then, 25 g of each waste (Banana peels 25 g, rice 25 g, peanut shells 25 g ) was measured for each experiment on an electronic scale. A thermocouple was placed in the inner barrel and filled with 25 g of each food waste (banana peels, rice, and peanut shells). Then, charcoal was filled in the outer barrel and burnt to get the desired temperature (400 °C) and dwelled for 30 more minutes to ensure complete conversion of food waste. Finally, a preliminary experiment was done to evaluate the behavior of biochar during the absorption process. The rising temperature of the thermometer is influenced by the height of the thermocouple placed inside the inner barrel. Hence, measured the height of 4 inches of the thermocouple that was placed inside the inner barrel and observed data of the temperature rising over time for both the first and second experiments. The inability to move the thermocouple to monitor the temperatures at different points inside the inner barrel is one of the challenges in doing this experiment. In order to be able to measure the temperature at each location on the inside of the barrel, it is crucial to improve the modification of the thermocouple in future investigations. The temperature fluctuation overtime during the production of the food waste-biochar was separately demonstrated for two experiments as shown in Figure 2. Throughout the experiment, linear behavior is visible in the graph of the rising average temperature with time. A temperature range of 398–406 °C was used to obtain biochar yield, and an approximate heating rate of 2.9 °C/min was used to ensure slow pyrolysis. The production rate of pyrolytic biochar decreased with rising temperatures and the impact of the heating rate for the pyrolysis of food waste, which continuously reduced the yield of the biochar with increasing the heating rate. Therefore, the persistence of a high-temperature range for an extended period of time may be the cause of the lower biochar output in the second experiment than the first.
Systematic Approach to Housing Price Prediction and Recommendations-Case Study Based on Sri Lankan Housing Prices
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Ekanayake, Sulochana; Vidanagama, Dushyanthi
Machine learning is a technology that is currently being popular. It can be used to increase effectiveness in every field. Real estate has had a big impact on all aspects of our society. As today's society relies more and more on technology, its dependability for precise prediction and application recommendations has become more important. Most people prefer to purchase a home rather than build one. By manually calculating the influencing parameters necessary for estimating the rate of property, it is challenging to determine the price of a property. Customers who rely on real estate agents are taken advantage of because agents may quote prices that are significantly higher than the going rate. People with a budget for a home purchase are unable to purchase due to the disparity in prices their agent provided. The project's goal is to improve communication between buyers and sellers. As the Main improvement of the project, the solution was given to the better Searching Options. After reviewing various ML models, the Random Forest Regression model was chosen to train the data set. The Housing Price Prediction and Recommendation System were developed using a dataset of Sri Lankan real estate prices. RPA was used to extract the data set. Future home price predictions were made using the ARIMA model. Housing suggestions were generated using Hybrid recommendations. Collaborative filtering and Content-based filtering have been identified as major recommendation methods. In our proposed system hybrid recommendation has been used to increase the accuracy. The buying and selling platforms have integrated prediction, forecasting, and recommendation features together. This system will aid in the development of trust between buyers and Sellers
Development of a Portable Device for Students’ Attendance Marking Based on Facial Recognition
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Kuruppu, Anushka; Jayathilake, Chamishka; Bhanuka, Janith; Viduravi, Kunchana; Bandara, Shakya
Today, a wide variety of institutions, including colleges, industries, offices, and schools, use identifying techniques for access control and attendance collection of their students/employers. These identification methods include handwritten signatures, punch cards, fingerprints, facial recognition systems, etc. Among these, the facial recognition technique has grown in acceptance. However, the majority of Sri Lankan universities, colleges and academic institutions continue to use the outdated method of gathering student attendance, which entails obtaining their handwritten signatures on an attendance sheet. When using with students, this strategy has a number of practical problems [1] such as distracting the student and lecturer during the exam or lecture, wasting resources, and illegally signing on behalf of another student. In order to overcome these drawbacks, this paper presents a low cost, portable device to collect students’ attendance using a facial recognition system. The proposed device uses a web camera and a Raspberry Pi module (the embedded system) to capture images, which are then processed to identify the student. When developing the code, the following steps were followed. 1)Capture the image of the student. 2)Load the student image and extract the facial features. 3)Recognize the face using the face recognition library.4) Use ‘Openpyxl’ to create workbooks with the required column names, then mark attendance on the Excel sheet. 5) Capture the object file (dataset_faces.dat) in Python. 6) Run different scripts by clicking buttons. The "dlib" library in Python was utilized for the face detection part, due to its higher accuracy in a variety of situations, including detecting faces with face masks, beards and identical twins. Dlib library is an open-source C++ library that provides machine learning algorithms, including classification, regression, clustering, data transformation, and structured prediction. It has shown an accuracy of 99.38% [2] on the Labeled Faces in the Wild (LFW) dataset. Labeled Faces in the Wild is a public benchmark for face verification, also known as pair matching [3]. The "OpenCV" library can be used to implement the image capture program. The system records the student's attendance once it has identified them. The Python 'Tkinter' library was used as the user interface, making it simple to use the device screen. The system has several unique features compared to other products currently available on the market, such as portability, having a simple, user-friendly graphical user interface (GUI), cost-effectiveness, ability to use with any available Wi-Fi network for data logging, and capability of face recognition even with the face mask, which enables this device to use in a situation such as COVID 19 epidemic. Also, this device is equipped with an inbuilt rechargeable battery pack which eliminates the requirement for an additional power supply. Even though there are only a few products with similar features on the market, they are more expensive than the proposed product. The system was able to identify the same person (male or female) during the experimental stage under various test conditions, including different facial expressions, hairstyles, headwear, angles, backgrounds, with/without spectacles, and with/without a face mask; however, the system produced unacceptable results due to poor lighting and the use of a low-quality web camera. By eliminating backdrop challenges like connecting a light source to the system, then it can control the environment's varying levels of illumination, or by connecting a high-quality web camera with low-light and adjustable light correction capabilities, the system can acquire accurate facial detection.