Department of Information Technology-Scopes

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/2179

Browse

Filters

20213

Advanced Search

Filter by

Settings

Start date: 2021Subject: search.filters.subject.Machine Learning

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    PublicationEmbargo
    SalFix: Solutions for Small Businesses Using Artificial Intelligence and Machine Learning
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Perera, T.; Kuganandamurthy, L.; Ameen, T.; Dassanayake, T.; Ganegoda, D.
    Every large organization was a small business before. There are many businesses starting every day. Most of them are small businesses. Managing a business is always a challenge. The owners face lots of challenges when they engage with a business. Small business owners do not have enough knowledge about advertising or promoting a product. New owners do not know the trendiest product at present, and they need to know to sell which product to be profitable. L ack o f communication with the customers will impact the customer base. These are the main problems that owners face. By introducing SalFix, these challenges can be conquered. SalFix is a web application that is suitable for current owners and new owners. SalFix uses Artificial I ntelligence t o g enerate a utomated a d i mages, predict what will happen to the business next year, predict which product is the trendiest. To improve customer communication, SalFix is embedded with a chatbot plugin that can be integrated into the small business’s website. SalFix can perform a SWOT analysis as well. Owners can use SalFix to fix t heir s ales and boost their income. SalFix is a yearly subscription service and will provide more accurate results.
  • Thumbnail Image
    PublicationEmbargo
    Mobile Medical Assistant and Analytical System for Dengue Patients
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Jayampathi, K.T.K.; Jananjaya, M.A.C.; Fernando, E.P.C.; Liyanage, Y.A.; Pemadasa, M.G.N.M.; Gunarathne, G.W.D.A.
    Dengue fever is a vector-borne viral disease spread by the mosquito Aedes Aegypti. It is a public health problem, with an estimated 50-500 million infections each year and no effective vaccination. People's hectic schedules may not have enough time to see a doctor every time they have a fever. They may overlook their disease, believing it to be a common ailment. Prior medical assistance for dengue patients with fever to check their conditions reliably is a major problem. There is no easily accessible proper system to identify dengue patients at an early stage. This paper presents a mobile medical assistant and analytical system for dengue patients. With a novel approach, using the most appropriate technologies, the mobile application supports identifying dengue patients using the chatbot, analyzing skin conditions, analyzing blood reports, and analyzing dengue-infected areas' functionalities. The registered users can log in to the system and check their dengue condition. The development is carried out with Natural Language Processing, Artificial Neural Network (ANN), Machine Learning, Image Processing, Convolutional Neural Network (CNN), and Android technologies. A mobile application prototype is created and tested, with the possibility of future testing and implementation. The results show effective performances in analyzing dengue conditions.
  • Thumbnail Image
    PublicationEmbargo
    Event-Driven Malicious URL Extractor
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Jonathan, S.W.S.; Arunaasalam, R.H.; Senarathne, A. N.; Wishvajith, V.; Ramanayaka, A.M.; Yapa, K.
    Cyber-attacks are attacks that are commonly carried out in order to obtain sensitive information or disrupt internet-based services. Recent occurrences, both internationally and locally, have shown an influx of these attacks expanding rapidly through the use of malicious URLs (Uniform Resource Locators). Traditional measures, including such blacklisting malicious URLs, make it extremely difficult to respond to such attacks in a timely and efficient manner. Most existing solutions remain restricted in terms of scalability and proactive user safeguarding in situations when freshly formed URLs are correlated with a recent event, such as Covid-19 related frauds. The proposed solution is presented with the primary aim of addressing traditional system limitations and offering an interface for users to protect themselves by detecting phishing/malicious URLs in real time. In this research, we will examine extracting user-input eventrelated keywords and leveraging NLP (Natural Language Processing) algorithms to match them with the accompanying URL (Uniform Resource Locator) token data to determine whether the URLs are malicious or benign.