3rd International Conference on Advancements in Computing [ICAC] 2021

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/947

Browse

Filters

20214

Advanced Search

Filter by

Settings

Has files: YesSubject: search.filters.subject.Deep Learning

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    PublicationEmbargo
    Smart Intelligent Floriculture Assistant Agent (SIFAA)
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Samaratunge, U.S.S.; Amarasinghe, D.H.L.; Kirindegamaarachchi, M.C.; Asanka, B.L.
    Technology has become a vital aspect for various functional purposes throughout the world and some industries like floriculture have not adapted technology to solve and facilitate currently facing problems and provide the supply to the demand. Consequently, we have identified and implemented a solution that will address major aspects of such industry barriers. To address these major aspects we proposed a system Smart Intelligent Floriculture Assistant Agent (SIFAA), which uses expert knowledge with solutions and guideline such as identify diseases based on deep learning techniques. It also suggests remedies for diseases based on the expert knowledge, recommend best products for customers by using Reinforcement Learning (RL) technique, motivate cultivators by using demand forecasting, and apply feature engineering by using Linear Regression (LR) and ensemble advance LightGBM Regressors techniques.
  • Thumbnail Image
    PublicationEmbargo
    Machine Learning-based Prediction Model for Academic Performance
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Tharsha, S.; Dilogera, J.; Mohanashiyaam, B.; Kirushan, S.; Chathurika, K.B.A.B.; Swarnakantha, N.H.P.R.S.
    This paper represents the work of a new integrated and collaborative Smart application for managing students online through data mining techniques. Nowadays especially in this pandemic situation, there is a necessity for academic management to incorporate and change all study methods online. By considering all these conditions this research is focused to discuss the solution to manage and engage students smartly and easily. Thou technology advancements have a serious impact on the day-to-day life people face troubles when using complex applications, this implemented Smart application is simple to use and a great tool for Student Management systems. The survey feedback from students, academic staff, and the public illustrate that this project helps to improve the effectiveness and efficiency of learning capability among the targeted group. The main objective of this project is to build up a smart model using Machine Learning, Deep Learning, and Artificial Intelligence to overcome generic learning problems. Therefore, this paper aims to present the concept behind the development and implementation of the Smart Study Application for Student Management System.
  • Thumbnail Image
    PublicationEmbargo
    Guided Vision: A High Efficient And Low Latent Mobile App For Visually Impaired
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Rizan, T.; Siriwardena, V.; Raleen, M.; Perera, L.; Kasthurirathna, D.
    This paper presents a novel solution for visually impaired individuals. A mobile app is connected to an ESP32CAM and a remote server to help visually impaired individuals to navigate around their environment safely. A deep learning model is deployed in the mobile app to detect obstacles in real-time without connecting to the internet. Other tasks such as reading texts, recognizing people, and describing objects are done in the remote server. We managed to connect the mobile app to the ESP32CAM and the remote server simultaneously. This was possible because the ESP32CAM is connected to the mobile app through Bluetooth. This gave the mobile the ability to connect to the remote server via the internet. To the best of our knowledge, no research has been done using Bluetooth to stream images to do object detection in a mobile app locally. Hence, our solution can detect obstacles locally and do other tasks mentioned previously in the remote server. This paper discusses how the ESP32CAM, obstacle detection module, face recognition module, text reading module, and object description module was implemented such that a low latent and highly efficient mobile app is created using minimal resources.
  • Thumbnail Image
    PublicationEmbargo
    Crime Analysis, Prediction and Simulation Platform Based on Machine Learning
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12) Herath, I.S.; Dinalankara, R.; Wijenayake, U.
    As a global social-economical problem, crime has shown complex correlations with spatial-temporal, socio-economical, and environmental factors. Understanding patterns and interactions in the crimes is essential to prepare better to respond to those criminal activities. This study is focused on research and development of crime analysis, prediction and simulation platform that provides descriptive analysis, predictive crime analysis, Reinforcement learning based crime entity simulations and safest route navigation services based on crime data from the city of San Francisco. Ultimately, the proposed crime analysis, prediction and simulation platform provides critical information on root causes and statistical patterns of crime and future crime predictions for the policymakers and security officials to create strategies to minimise the crimes.