Amal Shehan Perera

Amal Shehan Perera
University of Moratuwa | UoM · Department of Computer Science and Engineering

Doctor of Philosophy

About

91
Publications
218,673
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
551
Citations
Citations since 2016
45 Research Items
448 Citations
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100

Publications

Publications (91)
Conference Paper
Full-text available
Since Speed is also a critical parameter in several transport studies, accurate speed detection has become very significant in increasing the studies' reliability. Hence, this study compares different speed detection techniques such as Vehicle Number Plate survey, Google Traffic data, Radar Gun and Deep Learning Vehicle Speeds using CCTV videos for...
Article
Full-text available
Video has rapidly become one of the most common sources of visual information transfer. The number of videos uploaded to YouTube in a single day is estimated to take over 82 years to watch. Automated tools and techniques for analyzing and understanding video content, thus, have become an essential requirement. This paper addresses the problem of vi...
Conference Paper
Full-text available
Video-based automated counting is a developing technology which will gradually replace the manual on-site counting. This study compares the accuracy of manual and video based automated classified traffic counting. Original Yolo V 4 and a Yolo V 4 model with some preliminary custom training are used as automated vehicle counting. Preliminary model t...
Conference Paper
Full-text available
In the field of natural language processing, domain-specific information retrieval using given documents has been a prominent and ongoing research area. Automatic extraction of the legal parties (petitioner and defendant sets) involved in a legal case has a significant impact on the proceedings of legal cases. This is a study proposing a novel way...
Preprint
Full-text available
Aspect-Based Sentiment Analysis (ABSA) has been prominent and ongoing research over many different domains, but it is not widely discussed in the legal domain. A number of publicly available datasets for a wide range of domains usually fulfill the needs of researchers to perform their studies in the field of ABSA. To the best of our knowledge, ther...
Preprint
Full-text available
A document which elaborates opinions and arguments related to the previous court cases is known as a legal opinion text. Lawyers and legal officials have to spend considerable effort and time to obtain the required information manually from those documents when dealing with new legal cases. Hence, it provides much convenience to those individuals i...
Conference Paper
Full-text available
In the field of natural language processing, domain specific information retrieval using given documents has been a prominent and ongoing research area. The automatic extraction of the legal parties involved in a legal case has a significant impact on the proceedings of legal cases. This is a study proposing a novel way to extract the legal parties...
Preprint
Full-text available
Analyzing the sentiments of legal opinions available in Legal Opinion Texts can facilitate several use cases such as legal judgement prediction, contradictory statements identification and party-based sentiment analysis. However, the task of developing a legal domain specific sentiment annotator is challenging due to resource constraints such as la...
Chapter
Full-text available
Understanding human mobility is essential for many fields, including transportation planning. Currently, surveys are the primary source for such analysis. However, in the recent past, many researchers have focused on Call Detail Records (CDR) for identifying travel patterns. CDRs have shown correlation to human mobility behavior. However, one of th...
Article
Full-text available
Information that are available in court case transcripts which describes the proceedings of previous legal cases are of significant importance to legal officials. Therefore, automatic information extraction from court case transcripts can be considered as a task of huge importance when it comes to facilitating the processes related to legal domain....
Preprint
Full-text available
Arguments, counter-arguments, facts, and evidence obtained via documents related to previous court cases are of essential need for legal professionals. Therefore, the process of automatic information extraction from documents containing legal opinions related to court cases can be considered to be of significant importance. This study is focused on...
Preprint
Full-text available
A data warehouse is used intensively in many industry domains to gain competitive advantage over it’s competitors. In modern data warehouses, linguistics analytics is an important aspect so that it has the ability to take more precious decisions. In most of the data warehouse implementations, it is designed for crisp analysis. Crisp analysis has it...
Chapter
Domain specific information retrieval process has been a prominent and ongoing research in the field of natural language processing. Many researchers have incorporated different techniques to overcome the technical and domain specificity and provide a mature model for various domains of interest. The main bottleneck in these studies is the heavy co...
Preprint
Full-text available
This study proposes a novel way of identifying the sentiment of the phrases used in the legal domain. The added complexity of the language used in law, and the inability of the existing systems to accurately predict the sentiments of words in law are the main motivations behind this study. This is a transfer learning approach, which can be used for...
Preprint
Full-text available
Case Law has a significant impact on the proceedings of legal cases. Therefore, the information that can be obtained from previous court cases is valuable to lawyers and other legal officials when performing their duties. This paper describes a methodology of applying discourse relations between sentences when processing text documents related to t...
Conference Paper
Full-text available
Case Law has a significant impact on the proceedings of legal cases. Therefore, the information that can be obtained from previous court cases is valuable to lawyers and other legal officials when performing their duties. This paper describes a methodology of applying discourse relations between sentences when processing text documents related to t...
Article
Full-text available
An ontology defines a set of representational primitives which model a domain of knowledge or discourse. With the arising fields such as information extraction and knowledge management, the role of ontology has become a driving factor of many modern day systems. Ontology population, on the other hand, is a inherently problematic process, as it need...
Preprint
Full-text available
Domain specific information retrieval process has been a prominent and ongoing research in the field of natural language processing. Many researchers have incorporated different techniques to overcome the technical and domain specificity and provide a mature model for various domains of interest. The main bottleneck in these studies is the heavy co...
Article
Full-text available
Large data sets are produced by the gene expression process which is done by using the DNA microarray technology. These gene expression data are recognized as a common data source which contains missing expression values. In this paper, we present a genetic algorithm optimized k- Nearest neighbor algorithm (Evolutionary kNNImputation) for missing d...
Conference Paper
Full-text available
This study proposes a novel way of identifying the sentiment of the phrases used in the legal domain. The added complexity of the language used in law, and the inability of the existing systems to accurately predict the sentiments of words in law are the main motivations behind this study. This is a transfer learning approach, which can be used for...
Article
Full-text available
Value at Risk (VaR) is a statistical method of predicting market risk associated with financial portfolios. There are numerous statistical models which forecast VaR and out of those, Monte Carlo Simulation is a commonly used technique with a high accuracy though it is computationally intensive. Calculating VaR in real time is becoming a need of sho...
Conference Paper
Semantic similarity measures are an important part in Natural Language Processing tasks. However Semantic similarity measures built for general use do not perform well within specific domains. Therefore in this study we introduce a domain specific semantic similarity measure that was created by the synergistic union of word2vec, a word embedding me...
Article
Full-text available
Defining a Membership Function in fuzzy systems is complex thus the most important activity. Though there exist several ways to define membership function such as artificial neural networks, genetic algorithm, fuzzy clustering etc. they are time consuming and there are complexities in implementation of these methods. This research has identified si...
Preprint
Full-text available
In many modern day systems such as information extraction and knowledge management agents, ontologies play a vital role in maintaining the concept hierarchies of the selected domain. However, ontology population has become a problematic process due to its nature of heavy coupling with manual human intervention. With the use of word embeddings in th...
Article
Full-text available
Many organizations are using Data warehouse as a strategical decision-making tool. Over the years, major emphasis was placed to analytics purposes. Uncertainty is one of the major challenge faced in many areas such as data warehouse, database etc. In case of uncertainty, fuzzy technique can be utilized. This research paper is to carry out a feasibi...
Conference Paper
Full-text available
Selecting a representative vector for a set of vectors is a very common requirement in many algorithmic tasks. Traditionally, the mean or median vector is selected. Ontology classes are sets of homogeneous instance objects that can be converted to a vector space by word vector embeddings. This study proposes a methodology to derive a representative...
Preprint
Full-text available
Selecting a representative vector for a set of vectors is a very common requirement in many algorithmic tasks. Traditionally, the mean or median vector is selected. Ontology classes are sets of homogeneous instance objects that can be converted to a vector space by word vector embeddings. This study proposes a methodology to derive a representative...
Preprint
Full-text available
Semantic similarity measures are an important part in Natural Language Processing tasks. However Semantic similarity measures built for general use do not perform well within specific domains. Therefore in this study we introduce a domain specific semantic similarity measure that was created by the synergistic union of word2vec, a word embedding me...
Conference Paper
Full-text available
Human mobility plays a significant role in spatio-temporal propagation of infectious diseases. But how much of an impact does human mobility have on propagating a dengue outbreak in a dengue endemic country such as Sri Lanka? We show that a proxy value for human mobility, derived from mobile network big data, has a significant correlation with deng...
Conference Paper
Congestion due to road traffic is a major issue in urban areas. Currently, there are methods to predict short-term traffic using data based on Global Positioning System (GPS). This research aims at finding a cost-effective solution to congestion using Visitor Location Registry (VLR) data gathered through mobile cell towers. Prediction models were b...
Conference Paper
Protein function annotation is vital for identifying disease causative factors and for solving mysteries behind biological system complexities. As manual annotation requires costly and laborious in vitro methods, in silico protein function prediction is preferred nowadays. According to literature, one in five yeast mitochondrial proteins are known...
Conference Paper
Full-text available
Gene expression data are recognized as a common data source which contains missing expression values. In this paper, we present a genetic algorithm optimized k- Nearest neighbor algorithm (Evolutionary kNNImputation) for missing data imputation. Despite the common imputation methods this paper addresses the effectiveness of using supervised learnin...
Conference Paper
Full-text available
This paper discusses about predicting Dengue out-breaks in Sri Lanka using heterogeneous data sets: Mobile Network Big data and epidemiological data. Up to now, Dengue epidemiological prediction was largely done using the past Dengue cases and weather data. However, very recently it was discovered that infection can propagate through humans, where...
Conference Paper
Self Organizing Maps (SOM) are widely used in data mining and high-dimensional data visualization due to its unsupervised nature and robustness. Growing Self Organizing Maps (GSOM) is a variant of SOM algorithm which allows nodes to be grown so that it can represent the input space better. Without using a fixed 2D grid like SOM, GSOM starts with fo...
Conference Paper
Full-text available
E-Learning systems have caused a rapid increase to the amount of learning content available on the web. It has become a time consuming and a daunting task for e-learners to find the relevant content that they should study. Existing e-learning technology lacks the automated capability to provide guidance for students to prioritize and engage in the...
Conference Paper
Full-text available
In Natural Language Processing and Text mining related works, one of the important aspects is measuring the sentence similarity. When measuring the similarity between sentences there are three major branches which can be followed. One procedure is measuring the similarity based on the semantic structure of sentences while the other procedures are b...
Conference Paper
Humans learn in an incremental manner. Due to this reason, humans continuously refine their knowledge of the environment with the experience gained. Many strides have been made in the machine learning area to exploit the power of incremental learning. Incremental learning, in contrast to onetime learning is far more useful and effective when data i...
Conference Paper
Full-text available
Word lists that contain closely related sets of words is a critical requirement in machine understanding and processing of natural languages. Creating and maintaining such closely related word lists is a critical and complex process that requires human input and carried out manually in the absence of tools. We describe a supervised learning mechani...
Conference Paper
Predicting customer churn is a critical requirement of many if not all companies dependent on customer subscription services. The telecommunication sector is especially impacted due to the rival competition being very high and since tariff rates are maintained at a lower level. This paper describes the efforts made by researchers to build successfu...
Conference Paper
Full-text available
Ever growing knowledge bases of enterprises present a demanding challenge of proper organization of information that would enable fast retrieval of related and intended information. Document repositories of enterprises consist of large collections of documents of varying sizes, formats and writing styles.This diversified and unstructured nature of...
Conference Paper
Full-text available
An informative digital map is a prerequisite for future Intelligent Transportation System (ITS) applications such as lane level navigation systems. Preparing and updating such detailed digital maps by using existing methods such as surveying and image digitization is not practical due to the time and cost involved. We propose a method that statisti...
Conference Paper
Full-text available
This paper presents an algorithmic tool that was used to create panels of experts for the synoptic assessment of a software engineering project course that is targeted towards fostering innovation and creativity in software engineering students. Synoptic assessments succeed with the ability to formulate expert evaluation panels. Yet many industry e...
Conference Paper
Full-text available
The Bachelor of Engineering (Honours) program of the Department of Computer Science and Engineering at the University of Moratuwa has a compulsory software engineering project course in the 5th semester. This course has been designed to foster creativity and software engineering rigor. Since the design of this course (CS3202) straddles several prog...
Conference Paper
We present the design of a software engineering project course targeted towards fostering innovation and creativity and in instilling a sense of software engineering rigor in students. The discussion includes our experiences in conducting this course over the past three years for the students following the Bachelor of Engineering (Honors) degree pr...
Article
Full-text available
With vast amounts of data being produced, present world is overwhelmed with information and searching for appropriate content has turned out to be harder than ever before. Semantics, which typically focuses on the relationship between signifiers, such as words, phrases, signs and symbols, and what they stand for is now being used more and more in s...
Conference Paper
Full-text available
We describe the refactoring process of the RelEx2Frame component of OpenCog AGI Framework, a method for expanding concept variables used in RelEx and automatic generation of a common sense knowledge base specifically with relation to concept relationships. The wellknown Drools rule engine is used instead of hand-coded rules; an asynchronous concurr...
Technical Report
Full-text available
Ever growing knowledge bases of enterprises present the demanding challenge of proper organization of information that would enable fast retrieval of related and intended information. Document repositories of enterprises consist of large collections of documents of varying size, format and writing styles. This diversified and unstructured nature of...
Conference Paper
Full-text available
Analysing the data warehouses to foresee the patterns of the transactions often needs high computational power and memory space due to the huge set of past history of the data transactions. Apriori algorithm is a mostly learned and implemented algorithm that mines the data warehouses to find the associations. Frequent item set mining with vertical...
Chapter
In today’s fiercely competitive and dynamic market scenario, business enterprises are facing many problems due to increasing complexity of the decision making process. Besides, the amount of data to be analyzed has increased substantially. This has resulted in Artificial Intelligence stepping into decision making to make better business decisions,...
Article
Full-text available
Classification of spatial data can be difficult with existing methods due to the large numbers and sizes of spatial data sets. The task becomes even more difficult when we consider continuous spatial data streams. Data streams require a classifier that can be built and rebuilt repeatedly in near real time. This paper presents an approach to deal wi...
Conference Paper
Full-text available
Wide availability of electronic data has led to the vast interest in text analysis, information retrieval and text categorization methods. To provide a better service, there is a need for non-English based document analysis and categorizing systems, as is currently available for English text documents. This study is mainly focused on categorizing I...