Science

Now showing 1 - 3 of 3

Study of machine learning algorithms for Sinhala speech recognition
(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Shaminda, S.; Jayalal, S.
Speech is the primary mode of communication among humans and the most natural and efficient form of exchanging information. Therefore, it is logical that the next technological development in natural language speech recognition for Human Computer Interaction is, Artificial Intelligence. Speech recognition can be defined as the process of converting speech signal to a sequence of words by an algorithm implemented using a computer program. Speech processing is one of the challenging areas of signal processing. The main objective of the study was to conduct a study on speech recognition approaches to improve the accuracy level of Sinhala speech recognition. This study was conducted in order to find the optimal algorithm for accurate Sinhala speech recognition. According to the implementation architecture of speech recognition, feature extraction and the pattern recognition phases can be varied with different algorithms. The study identified that Linear Predictive Coding (LPC) and Hidden Markov Model (HMM) gives most accurate results than other combine algorithms.
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.
Detection of cyber bullying on social media networks
(Faculty of Science, University of Kelaniya, Sri Lanka, 2016) Priyangika. S.; Jayalal, S.
Social Media is becoming an integral part of people’s daily lives today. It is an effective way of sharing one’s life experiences, special occasions, achievements and other events with their friends and family. Although it is a fruitful way to communicate with groups, some people find themselves being insulted or offended by others who are involved in certain post or conversations. These insulations can be based on racism, using profanity or any other vulgar or lewd language. This cyber bullying needs to be monitored and controlled by the social media site owners since it will highly effect on the number and safety of the active site membership. Currently, there is no automated process of identifying offensive comments by the social network site itself. It can be only diagnosed by humans after reading the comments, flagging or reporting them to the owner of the site or blocking the offender. Considering the massive big data set generated in social media daily, automatically detection of offensive statements is required to reduce insulation effectively. For this purpose, text classification approach can be applied where a given text will be categorized as insulting or not, through learning from a pre-learned model. In order to develop the model, data was collected from the popular data repository site named www.kaggle.com. The dataset consists of comments posted on Facebook and Twitter. Firstly the dataset was divided into training data set and test data set. Then the collected data was preprocessed by removing the unwanted strings, correcting words and eliminating duplicate data fields. In the next step, features or keywords were extracted which are qualified to distinguish a statement as ‘insulting’ using N-grams model and counting methods. Feature selection is done using Chi- Squared test and finally apply classification algorithms for separating insulting comments and non-insulting comments from a dataset given. Machine learning algorithms such as Support Vector Machines (SVM), Naïve Bayes, Logistic Regression and Random Forest are used for this. Out of the classification algorithms, SVM is to be performed better than other algorithms since this is a two-class classification problem and a comment is to be classified only into two separate classes which are ‘insulting’ and ‘neutral’. With an exact separation of a given comment into ‘insulting’ and ‘neutral’ category, cyberbullying happening through offensive comments posted on social media sites can be detected.

Science

Browse

Filters

Settings

Sort By

Results per page

Search Results