Abstract:Three wheelers (3Ws) are widely used in low and middle-income countries, particularly in Asia Pacific region as a comparatively cheap method to passenger transportation and goods delivery. The frequent use of 3Ws in day-to-day activities have caused a large number of accidents causing injuries to their passengers. Less research has been carried out to identify the reasons behind 3W accidents. The survey carried out prior to this research has identified that the stability control and speed control are the two key factors which the 3W accidents attributed to. 3W fork is the main mechanical element that controls the balance and the stability of the vehicle. A damaged 3W fork (a physical damage or a slight deformation) unbalances the 3W and had been identified as one of the reasons for large number of accidents. Therefore, correctly reforming the damaged fork is of paramount importance, when concerning the safety of the 3Ws. Traditionally, both heat-treating and cold-working techniques are used in the mending processes. Not only this manual-labor repairing process weakens the strength of the fork, but also the profile produced is inaccurate. This paper discusses a hydraulic operated fork mending machine with an image processing technique to reform the damaged forks in 3Ws. An image comparator-based imaging technique is used for this machine vision-based visually guided fork repairing process. Three cameras have been used to capture the images from three perpendicular directions. A contour sketch of the original fork (before the deformation occurs) has been compared against the faulty fork, to assist the worker to carry out the repairing process. The preliminary experimentations have shown that the proposed technique can improve the repositioning of the camber angle by repairing the damaged fork.

Abstract:This paper involves the systematic, integrated and unified design of an automatic apple grading system. Apples are placed on a constant-speed conveyor system and graded based on 2 parameters: weight and colour. For weight detection, a piezo-resistive load cell (ELAF-T1-M-10L) is used. For colour detection, an RGB colour sensor (46CLR-D5LAC3-D5) is used. If the apples are equal to or above a pre-set weight threshold of 0.08kg and if the colour of the apple is red, green or yellow, they are graded in to three bins (bin 1: red apples, bin 2: green apples, bin 3: yellow apples). If the weight is below the threshold and/or if the colour of the apple is not red, green or yellow, they are sent to a reject bin. Both weight and colour requirements have to be met to be successfully graded, otherwise the apple is re-jected. Electric linear actuators (PA-15), actuated by combined signals from load cell, colour sensor and photoelectric sensors (OBR2000-R2) positioned very close to the actuators, are used to eject the apples to the correct bins. A digital magnetic speed sensor (DIGISPEC 0090/0091) is used to monitor the speed of the motor and maintain the required constant conveyor speed. Food grade conveyor belt (NS20 UFMT) is used to design the conveyor and direct drive DC motor (DMS07G) is used to move the conveyor belt. In this paper, the functionality, operation, important parameters and justifications for choosing individual components have been provided as well as detailed explanations of the overall system operation, along with potential drawbacks of proposed system. Relevant calculations necessary for system design are also provided.

Abstract:The global financial and economic market is now made up of several structures that are powerful and complex. In the last few decades, a few techniques and theories have been implemented that have revolutionized the understanding of those systems to forecast financial markets based on time series analysis. However still, none has been shown to function successfully consistently. In this project, a special form of Neural Network Modeling called LSTM to forecast the foreign exchange rate of currencies. In several different forecasting applications, this method of modelling has become popular as it can be defined complex non-linear relationships between variables and the outcome it wishes to predict. In compare to the stock market, exchange rates tend to be more relevant due to the availability of macroeconomic data that can be used to train the network to learn the impact of particular variables on the rate to be predicted. The information was collected using Quandl, an economic and financial platform that offers quantitative indicators for a wide variety of countries. Model is compared with three different metrics by exponential moving average and an autoregressive inte-grated moving average. then compare and validate the ability of the model to reliably predict future values and compare which of the models predicted the most correctly.

Abstract:At present, Sri Lanka is home to about 5,000-6,000 wild elephants roaming over close to 70% of the country’s land. Despite this blessing, around 150 elephants die each year due to many reasons. The main reasons for the altercations between humans and elephants are the drastic increase in the human population, human encroachment upon elephant territory for agriculture and settlements and unplanned development and transportation efforts. Elephants are long lived herbivores, and their survival depends upon regular migration over large distances to search for food, water, and social and reproductive partners. According to the Sri Lanka railways the average number of elephants that get killed due to elephant-railway accidents is about 9 per year. As a solution for this problem, we have proposed a novel system to pass a signal to indicate the train arrival. The proposed system detects the vibration of the locomotives and after detecting the vibration, alarm system will generate a high frequency signal within the frequency range, where the elephants are sensitive. The proposed system is a low cost device and this can be placed anywhere at any time. Moreover, this project aims to protect elephants from being harmed which usually happen due to various human activities.

Abstract:Pali is considered as the language of the canon continued to be influenced by analysts and grammarians, and by the native languages of the countries like Sri Lanka, in which Theravāda Buddhism became established over many years. The Pali language has been used to write many stone inscriptions in ancient times. For ordinary travelers the recognition of the content of ancient inscriptions and some other written material are not possible. This study has focused to find a solution with a mobile application to recognize Pali characters in a user-friendly User Interface. The character recognition in real time is the most essential part of the study. Machine learning and neural networks are trending technologies adapted for handwriting recognition in some languages. But for many languages this technology has not been developed yet. Pali is one of such languages that had survived until the eighteenth century. In this study the images of Pali letters are identified through a trained Convolution Neural Network (CNN). Python and Android Studio software were used for training process and identifying letters respectively with the developed mobile application. The limited capacity and the pro-cessing power of a mobile phone makes it more challenging to run the application. TensorFlow Lite is end to end open source platform in machine learning. Therefore, TensorFlow Lite was used in this study. Since the Android mobile is a common equipment which everybody has in modern societies, using this Off-line Pali character Recognition mobile application the archelogy researchers and travelers can use them conveniently to understand the content written in ancient documents.

Abstract:A ballistic impact is a potential threat faced by military personnel in a battle-field, which includes fragmented munitions from explosive material. A wide array of material including woven structures, laminated structures and non-woven structures have been developed for protection against potential impacts. However, the kinetic energy of the bullet at the point of impact causes heat dissipation, which is an existing problem at hand when developing reinforcement material. Therefore, this research is focused on developing a conceptual model and design for a shape memory polymer reinforced knitted spacer structure, where the impact energy is to be absorbed by the polymeric yarn, when the thermal energy raises the temperature of the SMP above its glass transition temperature. A theoretical model has been developed to establish the fabric parameters of the structure to facilitate the purpose while, a comprehensive design methodology, including determining the SMPhas been introduced for the design of the ballistic protection structure. Additionally, a MATLAB simulation was conducted to model the relationship between the dissipated heat energy and the required fabric pa-rameters.