Department of Computer Systems Engineering-Scopes

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/2354

Browse

Filters

20195

Advanced Search

Filter by

Settings

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    PublicationEmbargo
    On the scaling of virtualized network functions
    (IEEE, 2019-05-20) Rankothge, W; Ramalhinho, H; Lobo, J
    Offering Virtualized Network Functions (VNFs) as a service requires automation of cloud resource management to allocate cloud resources for the VNFs dynamically. Most of the existing solutions focus only on the initial resource allocation. However, the allocation of resources must adapt to dynamic traffic demands and support fast scaling mechanisms. There are three basic scaling models: vertical where re-scaling is achieved by changing the resources assigned to the VNF in the host server, horizontal where VNFs are replicated or removed to do rescaling, and migration where VNFs are moved to servers with more resources. In this paper, we present an Iterated Local Search (ILS) based framework for automation of resource reallocation that supports the three scaling models. We, then, use the framework to run experiments and compare the different scaling approaches, specifically how the optimization is affected by the scaling approach and the optimization objectives.
  • Thumbnail Image
    PublicationEmbargo
    Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction
    (2019 1st International Conference on Advancements in Computing (ICAC), SLIIT, 2019-12-05) Aryal, S.; Nadarajah, D.; Kasthurirathna, D.; Rupasinghe, L.; Jayawardena, C.
    Forecasting the financial time series is an extensive field of study. Even though the econometric models, traditional machine learning models, artificial neural networks and deep learning models have been used to predict the financial time series, deep learning models have been recently employed to do predictions of financial time series. In this paper, three different deep learning models called Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Temporal Convolution Network (TCN) have been used to predict the United States Dollar (USD) to Sri Lankan Rupees (LKR) exchange rate and compared the accuracy of the models. The results indicate the superiority of CNN model over other models. We conclude that CNN based models perform best in financial time series prediction.
  • Thumbnail Image
    PublicationEmbargo
    Automated Smart Checkup Portal Network System to Check the Vision and Hearing of the Patients.
    (2019 1st International Conference on Advancements in Computing (ICAC), SLIIT, 2019-12-05) Dias, A.A.T.K.; Vithusha, J.; Liyadipita, L.A.M.T.J.; Abeygunawardhana, P.K.W.
    The human eye and ear are impressive systems in the body. Vision and Hearing are the main functions of those organs. We should regularly check our vision and hearing, It's the most reliable ways to maintain good vision and hearing. Not only that, every patient must keep a medical history and previous checkup records, those related to vision and hearing and those results should be real-time processed. Therefore, we have built an Automated Centralized Smart EE (eye and ear) Checkup Portal Network System. We have designed and developed an automated centralized vision and hearing checkup rooms network, Automated centralized live traffic indicating cloud-based web application to establish in every hospital.
  • Thumbnail Image
    PublicationEmbargo
    An Automated Tool for Memory Forensics
    (2019 1st International Conference on Advancements in Computing (ICAC), SLIIT, 2019-12-05) Murthaja, M.; Sahayanathan, B.; Munasinghe, A.N.T.S.; Uthayakumar, D.; Rupasinghe, L.; Senarathne, A.
    In the present, memory forensics has captured the world’s attention. Currently, the volatility framework is used to extract artifacts from the memory dump, and the extracted artifacts are then used to investigate and to identify the malicious processes in the memory dump. The investigation process must be conducted manually, since the volatility framework provides only the artifacts that exist in the memory dump. In this paper, we investigate the four predominant domains of registry, DLL, API calls and network connections in memory forensics to implement the system ‘Malfore,’ which helps automate the entire process of memory forensics. We use the cuckoo sandbox to analyze malware samples and to obtain memory dumps and volatility frameworks to extract artifacts from the memory dump. The finalized dataset was evaluated using several machine learning algorithms, including RNN. The highest accuracy achieved was 98%, and it was reached using a recurrent neural network model, fitted to the data extracted from the DLL artifacts, and 92% accuracy was reached using a recurrent neural network model,fitted to data extracted from the network connection artifacts.
  • Thumbnail Image
    PublicationEmbargo
    AI Based Depression and Suicide Prevention System
    (2019 1st International Conference on Advancements in Computing (ICAC), SLIIT, 2019-12-05) Kulasinghe, S.A.S.A.; Jayasinghe, A.; Rathnayaka, R.M.A.; Karunarathne, P.B.M.M.D.; Silva, P.D.S.; Anuradha Jayakodi, J.A.D.C.
    Suicide is a major issue in the world. The number one reason for suicide is untreated depression. That is why it was decided to focus on depression symptoms more and identify them in order to prevent suicidal attempts. To cure depression, the best way is to talk about their feelings with someone they trusted and release their pain inside of them. Because of that this system has a Chat-bot for the user to interact with. Chat-bot will gather information about the users feelings through text and voice analysis. Also by analyzing their Facebook statuses and recent web history, the application gather more information about their mental state so that the system take more accurate conclusions. After analyzing all the information from each component the back brain will decide on how the chat-bot should act on the user. At the end, the product was able to give more than 75% accurate results for each component.