http://dlib.iit.ac.lk/xmlui/handle/123456789/824 2026-04-21T14:46:15Z 2026-04-21T14:46:15Z Ahamed, A http://dlib.iit.ac.lk/xmlui/handle/123456789/862 2022-03-07T07:00:14Z 2021-01-01T00:00:00Z

Automated Diagnosis of Alzheimer’s using Quantum Machine Learning Ahamed, A " Alzheimer’s Disease is one of the most common cause of dementia with ten million new cases every year. Early detection of the disease is being crucial thus, medical professionals can begin treatment to slow or halt the progression of the disease. Due to the criticality of the disease, accurate and precise diagnosis results are being a necessity. This dissertation aims to provide a system which automates the diagnosis process of the disease using neuroimaging biomarker mainly magnetic resonance imaging which has proven to be one of the earliest biomarkers used to diagnose the disease. This dissertation proposes and implements a novel approach to the problem in a quantum machine learning perspective. Quantum machine learning uses quantum mechanical properties such as super-position and entanglement to process data. Which is believed to outperform classical computing in processing quantum like data. We compare different quantum machine learning approaches and classical algorithms to select a suitable approach to automate the diagnosis process. The implemented system outperforms several state-of-the-art classical systems which shows promising application of quantum machine learning in disease diagnosis and neuroimaging."

2021-01-01T00:00:00Z Naheed, M. R. M http://dlib.iit.ac.lk/xmlui/handle/123456789/861 2022-03-07T06:56:44Z 2021-01-01T00:00:00Z

Forex prediction to reduce risks in investments Naheed, M. R. M " Forex (foreign exchange) is a unique financial industry in the financial world, with high risks and great return possibilities for traders. The market is also very simple, with traders able to profit simply by accurately predicting the direction of two currencies’ exchange rates. In comparison to other traditional financial mar kets, incorrect projections in the FX market can lead to far greater losses. This problem differs from more typical forms of time-series forecasting challenges in that it requires direction prediction. I used deep learning to create direction fore casts in the Forex market using a well-known deep learning approach known as ""long short-term memory"" (LSTM), which has been shown to be very successful in many time-series forecasting problems"

2021-01-01T00:00:00Z Liyanage, S http://dlib.iit.ac.lk/xmlui/handle/123456789/860 2022-03-07T06:52:59Z 2021-01-01T00:00:00Z

Detection of Social Engineering Attacks: Data Phishing Liyanage, S " Social Engineering is considered one of the most renowned and considered one of the easiest ways to implement an attack against computer systems in the cybersecurity domain. This is mainly due to the rapid advancements in digital communication technologies where it has become more accessible and easier to communicate between humans. The foundation of SE attacks is human weaknesses. Due to the availability of personal and sensitive information through online social networking platforms and services, consumers have become much more vulnerable to such malicious social engineering attacks in recent years. With parallel improvements in the Artificial Intelligence domain, considering Machine Learning which is a subset, automated SE attacks have become a new trend among SE attackers. Data Phishing is a subset of Social Engineering and it is one of the most known methods of attack. The motive of such attacks is to obtain the personal and sensitive information of a user by misleading them psychologically with legitimate-looking e-mails, website links, contact detail forms, shopping site checkouts, customer chat applications, etc. Detecting such phishing techniques is not an easy task as before since the technology used by phishing engineers have evolved considerably. There have been certain studies carried out by researchers to detect phishing attacks with a high rate of accuracy in recent times using Machine Learning techniques such as Natural Language Processing and Artificial Neural Networks. Although the existing systems have been able to generate highly accurate detection results with real as well as semi-synthetic datasets along with different machine learning algorithms. This research mainly focuses on a system where data phishing attack detection accuracy is increased reasonably as well as zero-day detection, which is the efficiency of the detection of malicious attacks, by using natural language processing and ML algorithms along with datasets. Further, the system is compared with other existing systems to determine whether any major or slight improvement has been accomplished in the process."

2021-01-01T00:00:00Z Ahmed, M. N. I. S http://dlib.iit.ac.lk/xmlui/handle/123456789/859 2022-03-07T06:46:10Z 2021-01-01T00:00:00Z

CRICKT20 – Squad machine learning approach to predicting a squad Ahmed, M. N. I. S " Cricket is a sport where teams of less than a dozen players compete against each other in the form of a match. Players in each team can be categorized based on their role in the field. Despite eleven players being on the field, an additional four players are added to the squad so that players can be swapped out in case of injuries or less than stellar form. These fifteen players in the squad are selected from a pool of players. The process involved in manual, involving selectors, coaching staff and the Captain. Due to the process being manual, several factors can affect the selection process such as personal biases and political influences which turns the process into subjective judgement instead of an objective judgement. This can result in better teams being snubbed of their opportunities in succeeding due to less than stellar players being selected. This process requires the elimination of personal judgement and a shift into a more objective process. Thus, the author proposes a solution for T20 Squad Selection by using Machine Learning Models to recommend squads from pools of players. Previous two years of performance, previous year performance in Premiere Leagues such as IPL, PSL, BPL, LPL, BBL and CPL, Performance in Domestic circuits and Under 19 performance are considered for each player to ensure that youngsters and well-experienced players aren’t disadvantaged in these processes."

2021-01-01T00:00:00Z