Science

Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/1

Browse

Has files: YesSubject: search.filters.subject.ANN

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Handwritten signature verification
    (International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Abewardana, H.M.H.P.; Ranathunga, L.
    A number of biometric methods can be used to authenticate a human identity such as using fingerprint detection, face detection, iris inspection and voice recognition. The verification of the signature of a human is the most prominent and prevalent method among those. The banking and insurance sector manually uses this verification method. It is a critical biometric attribute, which may differ from time to time due to the age and emotional state of the person. Because of the absence of the time feature of the signature, offline signature verification has a risk than online signature verification. The paper introduces six features for an alternate solution. They include scale and rotation invariant such as signature pixel ratio of concentric circles and number of cross points while others are rotation variant such as baseline slant angle, aspect ratio, normalized area and slope of the line connecting center of gravities of left and right halves of the bounding box of the signature. Back-propagation neural network is used to train and test the signature images. Experimentation and results of this methodology presents the possibility of using this system in relevant sectors.
  • Thumbnail Image
    Item
    A New Financial Time Series Approach for Volatility Forecasting
    (Department of Statistics & Computer Science, University of Kelaniya, Sri Lanka, 2016) Rathnayaka, R.M.K.T.; Seneiratna, D.M.K.N.; Arumawadu, H.I.
    The investment in capital market is easiest, fastest and securable way for building healthy financial foundation today. Because of the economic outlooks causing directly on these market fluctuations, the making decisions in the equity market has been regarding as one of the biggest challenges in the modern economy. The main purpose of this study is to take an attempt to understand the behavioral patterns and seek to develop a new hybrid forecasting approach under the volatility. The results are successfully implemented on Colombo stock exchange (CSE), Sri Lanka over the three year period from January 2013 to December 2015. The empirical results indicated that the new proposed hybrid approach is more suitable for forecasting price indices than traditional time series forecasting methodologies under the high volatility.