MSc in Information Technology

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/2484

Students enrolled in the MSc in Information Technology programme are required to submit a thesis as a compulsory component of their degree requirements. This collection features merit-based theses submitted by postgraduate students specialising in Information Technology. Abstracts are available for public viewing, while the full texts can be accessed on-site within the library.

Theses and Dissertations of the Sri Lanka Institute of Information Technology (SLIIT) are licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License .

Browse

Now showing 1 - 20 of 102

Open Access
Opinion Mining and Sentiment Analysis, to Improve Legal Information Efficiency Analysis in Sri Lankan Legal cases
(2014) Jayaweera, D.A.N.
SriLanka Information Technology field is now growing faster and the other industries try to combine their work with Information Technology to gain more profit and publi ity. Sri Lanka law field is one of the most famous and oldest fields. Most of the industry field can combinewith Information Technology and do new things as an example store data analyzing data.They need to analyze data because of they need to get correct decision and decision making process. Current Lawyers in Sri Lanka, use manual way to store client details, organize their work etc. Because of that they need lots of document writings, document reading.When the new case acquire to Lawyer, they need to read all history cases and they needto analyze those cases and get the final decision. Searching documents, creating new case files, organize the documents they need to do in efficiency manner. I prop sed this systemto how to they analyze the legal cases opinion and mining legal cases. Opi ions are consequently important that whenever one needs to make a decision, one wants to hear others' opinions. This is true for both individuals and organizations. The technology of OpinionMining thus has a great scope for practical applications. The concept of opi ion is in thecontext of Sentiment Analysis, the main tasks of Sentiment Analysis, and the fr mework of opinion summarization. Along with them, two relevant and important concepts of subjectivityand emotion were also introduced.ewhich are highly related to but not e uivalent to opinion. Existing studies about them have mostly focused on their intersecti ns with opinion.I create a system to analyze legal information in proper manner. The researc is give designthe application in the world context 'and introduce interactive customizable application forthe purpose of analyze legal information. As the outcome of the research, it will present the statistics and survey outcomes of usage of the introducing application f r legal informationanalyze in Sri Lanka and make available the developing.
Open Access
Development of a Framework for Real- Time Business Intelligence for Managing Risk in Banking Industry
(2014) Mahasivam, Pavithra
There is no doubt that data management is a critical component of any financial se 'vices firm's risk management strategy in the current market climate. As financial strategies have become more complex, new financial instruments are added and businesses continue the r expansion across the globe, the need for a coherent and streamlined approach to data nanagement potentially including the use of real-time data has never been greater. As today's decisions in the business world have become more real-time, the systems that support those decisions need to keep up. It is only natural that Business Intelligence BI systems quickly begin to incorporate real-time data in order to increase risk transparency to make better and faster busines s decisions, evaluate and predict broader spectrum of risk scenarios, confidentially answer qi arries from regulatory bodies and internal stakeholders. Thisresearch is mainly focusing on risk management of banking industry. The resea 'ch delivers advanced analytics and reporting capabilities to help strategic decision makers for ns vigate data to identify new opportunities, manage and mitigate risks, and make fact-based ecisions in ~- timely manner. Every bank measure and monitor their performance against characteri tics which is known as Key Performance Indicators (KPls). KPIs help an organization define t re progress . towards the organization goals. Important KPls of bank are identified in the literature that is used by financial regulators to keep track of how well-protected a bank is against risk.The real-time business intelligence framework is emulated for the banking industry in order to mitigate risk. The framework consists of changed data capture (eDq routine and rule-based engine. eDe routine is used to capture the changed data from the source database and load it to data mart online real-time. The rule base engines identify pattern changes in the data, based on the defined parameters and provide advanced analytics and reporting capabilities.
Open Access
Uncertainty factors of the projects in Sri Lank n software industry and a controlling model
(2014) De Silva, Induneth
Uncertainty is an inevitable factor of most software projects, not only in Sri Lanka but when considering the global software industry. Most Project Managers make decisions, milestones to make sure that each and every stakeholder in the project team is working to make the desired delivera les but still the project ends up with an overrun schedule, overflowing budget and compromised specifications. Or it just dies. Software organizations should identify different kind of uncertainties where project can tolerate at different stages of the projects. For this study I w uld like to collect data through questionnaires from several software companies in Sri Lanka and find out what are the uncertainties that they face during various phases of the project. Also the management approaches they take wh n such instance occurred will also identified from the data collection from vario s stake holders of the projects. ...;p,r;r In this study the uncertainty factors were explored by conducting surveys based on interviews and questionnaires. From the interview based surveys the uncertanty factors affecting to projects in Sri Lanka software indus y were identified and to measure the significance of the responses actions n each impact level a questionnaire based mass surveys was conducted.There it is observed that there are response actions that can be taken independent of the impact level of the uncertainty of some uncertainty factors. Furthermore when selecting suitable response action when there is an uncertainty in a particular impact level, the order of preference can be taken into consideration. This study is significant because the data was collected from a large sample of professionals who involved in Sri Lankan software industry and inferential analysis techniques and hypothesis tests were performed under 95% signi icance level and the tests satisfied the requirements of validity of the data. Als from the mass questionnaire-based survey verifies the application of responses ctions for identified uncertainties in different impact levels.
Open Access
Geospatiallntelligence on a graph
(2014) Kanaka, Tharik
Geographical Information Systems (GIS) bas being used oyer few decades across various organizations and also used by public in the day to da. for scenarios such as map representations, road navigation and Global Positi ning System (GPS) tracking. There are so many commercial and free GIS softw re is available out there for enterprises and also there are applications for per onal usage which are becoming very popular with increased usage of computer and mobile devices. On the other hand with the rapid increment computer systems usage and internet usage data is getting piled in exponentially. As a result of that concepts such as big data and NoSQL came to the picture in order to manipulate those data effectively. Graph databases arc one data model of NoSQL datab iscs which delivers significant advantages such as agility, flexibility and performance. Since geographic data is naturally structured like a graph, representing a GIS data in a graph structure can be useful for spatial index g, storage and topology in much effective way compared to other database type. There is a gap when representing organizational on maps whereas there are limitations when it comes to details. For an instance when restaurant cl ain company is representing their branch outlets on a map. They have to stick to basic set of attributes allowed by mapping service provider. Tbey can ot represent beyond that such as types of food they are selling and curr nt availability of them in' branch wise. This research will develop a implementation by combining these two technologies GIS and graph databases in order to achieve a central Geospatial intelligence on graph which livers benefits in the context of multiple data source integration and querying and analyzing them to generate new knowledge. In the implementation architecture a graph database stands in the back end and all the transactions are exposed and carried out by a managed Representational state transfer (REST) application programming interface (API) implementation. This API facility mak s the implementation as an interoperable platform which can be integrated with many other applications. Front end is implemented in Javascripr and mapping libraries which co ect to REST API backend and loads mapping information from a map engine. From the front end map routing and graph searching can be carried out. For graph results an optimal routing algorithm will be carried to for effective result s. At the end this research work outcome is a geospatial intelligence platform wl ich is implemented on a graph database.
Open Access
AnyDbMobileSync : Database Agnostic Synchronization Framework for Mobile Application
(2014-12) Abeysingha Gunawardhana, Suminda
Implement database independent data synchronization middleware framework (AnyDBMobileSync) for Server side SQL server/oracle database/my s Ietc. and client side any data store (HTML5 local store/websql/sqllite etc). If an offline mobile application used this middleware sync framework then their backend Database can change without mobile application extra development. Framework handled different database type (Sql server/oracle/my QL) that communicates mobile clients' offline data. Framework and Mobile Client communicate using Rest-full service. because of that mobile client-side doesn't need to install extra API. Communicate data object type is JSON and JSON can use any application language to e tract data from JSON object.
Open Access
An Approach towards Password Protection Based On Typing Style
(2014-12) Arnarasena, Nelum Chathuranga
The most common user authentication mechanism is password verification. other words, characterswhich types as text in a password field. However, the aim of this research is to find outwhether the rhythm and/or the style of typing; how types instead of what pes (Keystroke Dynamics), is sufficiently reliable as a security enhancement. This is a biometric approach. Biometric solutions are costly; requires at least one additional sensor. But this study focuses on an economical biometric solution that does not necessitate any additional sens r other than the keyboard.Keystroke dynamics is an interesting biometric because it always invisible for users, unlessthey are physically present, and also it is not depending on a dedicated device or hardware infrastructure. When a person is typing at a keyboard, the detailed timing information that describes exactly when each key was pressed and when it was released and va .ation of speed movingbetween two keys are continuously monitoring in order to recognizes a unique pattern. Thenanother pattern recognition part is operating in stealth mode with the passw rd verification. Thereforeafter the password is verified successfully, the pattern recognition part also needs to be completedin order to authenticate the user. Significance of this research is the way of generating and storing the pattern. As I explained thrgJ.,lghthe literature study keystroke dynamics is not a veryreliable biometric. So the challenge was to make a strong pattern which i hard to reveal usinga less reliable building block which I achieved successfully through this study.
Open Access
Analysis of Human Interpretability in Document Classification
(2018) Kumari, P.K.Suriyaa
With high use of computers, the collection of textual data generated, exchanged, stored and accessed increased in massive amount and became one of the richest sources of data for the organization. As a result, people are tending to use natural language processing application to categorize this large volume of data efficient and accurate manner. Their application of machine learning models. When it comes to Natural Language processing (NLP) applications where most of them follows supervised learning techniques, automatic document classification models developed to do content-based assignment here the materials are assigned into predefined categories. This makes it easier to find the relevant information at the right time and for filtering and routing documents directly to correct users. Mostly these learning models are operating in black-box manner wh re there is no way to interpret how the model has decided which class an instarce should assigned. understanding the reason behind how learning makes these redictions ~7 are very important to trust such learning models in real application. [his thesis presents the work related to the experimental work been carried with set of text classifiers to interpret text classifiers predictions, so any classifier can be evaluated based on how well they support classification purpose.
Open Access
lOT enabled Recognition based attendance Management System
(2018) Swarnakantha, N.H.P. Ravi Supunya
Attendance management is a very important task for each and every university or an institute. Most of institutes doing this attendance marking manually and it is time-consuming as well as it many causes to many errors. Therefore, r searchers tried to come up with automated attendance systems as a result of this issue. Researchers developed different systems using finger print technology, radio frequency identification (RFIO) and face recognition. Many of them used those technologies separately but it is not suitable for places like education in titutes. The purpose of the following research is to design and develop a new system using different technologies together and enable the internet of things to the system. So, this system uses face recognition and radio frequency identification t gether to come up with a proper solution. The system is using an online MySQL database to store entire data of the system. Python is used to program the system and Open CV is used for face recognition. One main finding of the research is to identify the student with different angles of face after getting the RFIO tag value. When getting attendance, the stude t should place his or her RFIO tag on the reader and then the system identifies the student with the tag value. The system then retrieves student's registration details and start compare student's face with sa$faces of that student. If the system identifies the student, then it checks for the subject's time slot to ensure that the student comes to the correct class. If all of them are correct, the system marks attendance for the student and sends a .notification email to the student so the student can know his or her attendance marked successfully for the class. There IS a web application also developed to register courses and subjects on the system and to view attendance details
Embargo
Implementing Stackable Open-Source Firewall Security and Network Traffic Monitoring System
(2020) Ariyarathne, K.A.S.
Network security is the main feature in network management. For that firewall and network monitoring systems are the main ingredients. Around the world millions of dollars annually are spent by the organizations for safeguards their data and information from unauthorized accesses. In the current market there are two type firewall and monitoring tools available for users, commercial and open source. But all these tools are not suitable for entry level, small and medium sized enterprises (SME’s). The commercial Firewalls and Network monitoring tools are dead weight for entry level and small size businesses, both financially and functionally. For that most efficient and available solution for that is to move to open-source firewall and network traffic monitoring systems. But the firewall should be armed with next generation firewall features such as UTM filtering, URL filtering, antivirus, anti-spyware, anti-spam, network firewalling, intrusion detection and prevention, content filtering, leak prevention, remote routing, NAT, and VPN support. And Network traffic monitoring should be included with network devices, links and connections, mission critical servers, external service providers, passive/active network health monitoring, automatic alerts, automatic load balancing and failover, monitor abnormal behaviors, etc. And finally, as a tool kit open-source firewall and network traffic monitoring systems work as a single unit to prevent, detect, and disable network attacks
Embargo
Developing common sense model for mobile service robot
(2021) De Silva, G.W.M.H.P.
Enhance the chance to identify the instructions or incomplete sentence given by a human as a command sentence by using the Natural Language processing and model creating. It would be facilitating the interaction between the human and mobile service robot. However, when human give the instruction there can be incompleteness or else missing. Which information that are related to the environment. That because of human normally based on the common sense depend on the environment. Then human brain will complete all those incomplete sentences by using the commonsense knowledge. In this research project itself, introduced a model of a service robot who can compete the given incomplete instructions and display the related sentences or words and finally move to the related objects which are in the environment of the robot. All those things happen by using a simulator. To this first it will consider and identify the objects in environment and then consider the given natural language instruction by human. As a first step of the approach complete the incomplete sentences those sentences are coming as natural language instructions. By parsing it into as the frame can identify the related words by using the created model or can call as language model and here used some identify words from the human common sense also, using those identified words as a first step create the code and then implement the model. then the service robot will learn about the commonsense knowledge automatically from the parsing sentences as a speaker. Considering all the parsing sentences it calculates and measure the accuracy of this service robot model. Simply this is a commonsense reasoning model. The result of the provided solution can enable the robot model who works in ROS environment to identify and automatically perform to the tasks.
Embargo
“FireX” – A Low Cost Raspberry Pi Based Open-Source Firewall Appliance for Sri Lanka Post
(2021) Fernando, G.G.U
Recent statistics on data breach shows millions of data get stolen or lost every year and larger organizations are moving in to complex IT security solutions to protect their data from the intruders. However, organizations with limited financial capabilities remain unprotected to lack of available funds to invest on decent IT security solution for their organization. Department of Posts Sri Lanka (Sri Lanka POST) is also in a situation where seeking a low cost IT security firewall solution to protect their post offices located around the country. The open source firewall solutions are the most popular world-wide methodology for used to empower the overall security of a medium scale home and office computing network as well as large scale cooperate networks without spending a large amount of funds. Open Source Firewall Controls embedded to a hardware device provides more centralized approach for IT Engineers when managing a network. Furthermore, most of other Government Organizations in Sri Lanka faces the same issues when protecting their cooperate network infrastructure due to financial capabilities. As a solution, The Researcher designed an open source low cost embedded hardware device to act as a corporate firewall where the device can govern the network access while catering the business requirements whereas protecting the IT assets from the intruders. The designed firewall solution is based on multiple open source packages which can run on a raspberry pi model 3b+ single-board computer (SBC). The open source firewall package ‘IPFire’ was used to act as the firewalling module for this project. At the end of this research project the Researcher is planning to locate on post offices around Sri Lanka.
Embargo
Post Disaster Damage Assessment Model using Geospatial Data in the Satellite Images
(2021) Kanchana, J. A. B. C.
Natural disasters can happen without prior warning at any time. It is important to identify and analyses the post disaster situation to manage the disaster with quick response. Traditional approaches for disaster analyzing using field surveys are not suitable due to its high risk, time consuming, labor consuming and costly. In that case Satellite imagery data is ideal to use for identifying the disaster situation, risk mitigation and post disaster recovery because it's easy to get the data at anyplace, anytime. However, the processing of satellite imagery is a significant difficulty and identifying things in a satellite image is crucial in this field. By using satellite imagery with the newest technologies like the deep learning approaches can be used to identify the disaster area. Accuracy and efficiency are a very important factor for making damage assessments and providing relief services. This research focused at how deep learning can be used to assess building damage using satellite imageries. The objective of this research is to develop a building damage assessment model by using deep learning, which can be use in post disaster analysis. According to the literature survey encoder – decoder model and Siamese model used for process the pre and post disaster satellite images and assess the damage
Embargo
Prediction Model For Young Drug Abuse Using CNN
(2021) Perera, A.S.
Illicit drug abuse is now a major public health issue. In society, some people use drugs abuse. It is no secret that it is already very prevalent, especially among young people. Young people are turning to illegal drugs for a variety of reasons, and a number of different drugs are currently in use. Among them is the rapid spread of the illicit drug methamphetamine, or ice, which is seen as one of the most harmful of these drugs. It has already been found that there is a high prevalence of high addiction among young students in schools and higher education, as well as among various youth groups in other societies. Various organizations have pointed out that this has had a negative impact on Student‘s health and education. It's just as short-lived, it's long-lasting. A number of studies have already been conducted using a variety of techniques for this purpose, both successful and unsuccessful. In the world of picture data, convolutional neural network models are everywhere. They excel in computer vision tasks like as picture categorization, object identification, and image recognition, among others. In this study, discussed about the illicit drug, specifically as an ice or methamphetamine drug, and a proposal is made for a algorithm using convlutional neural network that can be used as an alternative. This suggested modal will be develop, specifically for younger‘s in order to detect their abuse, enhance their health, and gain more benefits. This study, using CNN technology, a widely used in-depth learning technology for solving image classification challenges, using long and short term changes in appearance based on evolutionary algorithms, Identify whether ice drugs have been used by people not included in the database, as drug users have pointed out above.
Embargo
Development of a Virtual Learning Environment (VLE) During the COVID -19 Pandemic: A Study with special reference to Advanced Technological Institute.
(2021) Nowfeek, M.R.M.
In this Covid-19 pandemic, Information and Communication Technology (ICT) plays a major role, and the use of IT tools such as the Virtual Learning Environment (VLE) has become vital. Virtual Learning Environment (VLE) integrates several tools that provide higher educational institutions in an effective and efficient method to manage, share, store, its academic resources and enhance their traditional way of teaching in pandemic situation. The implementation of VLE During the COVID -19 Pandemic has become a need at Advanced Technological institute in the learning and teaching environment. Although there is an increased willingness to its widespread implementation among higher educational institutes in this pandemic situation. The main objective of this research is to develop a Virtual Learning Environment (VLE) for Advanced Technological Institute during the COVID -19 Pandemic, as well as to identify the existing virtual learning environment status of other higher educational institutes and the benefits of implementing a Virtual Learning Environment (VLE) at Advanced Technological Institute during the COVID -19 Pandemic. The conduct of this research involved qualitative method, the finding of the research presented that existing system used only for downloading the notes of lectures. As per the finding, virtual system developed using the following features such as conducing online examination, quizzes, discussion forum and automatic question generation using natural language processing to enhance the learning and teaching process. further the finding of this research helps to implement a virtual Learning system at Advanced Technological institutes in the pandemic situation to enhance the learning and teaching process. Adobe photoshop for image editing purpose, MySQL for creating database, Apache Web Server, WordPress, Google colab for prototype question generation and php for virtual environment development as well as Microsoft Visio for diagram drawing were utilized to develop this system development.
Embargo
Unsupervised Sinhala Cyberbullying Categorization
(2021) Chandrasena, B.G.M
The objective of unsupervised machine learning is to categorize the social media comments into a given number of pre-learned categories. The earlier studies of this domain have used many the dataset for supervised learning & introduced a large number of techniques, methodologies. A major challenge there was training labels. Although words with training comments are easy to find, separating them manually is not an easy task. Through this research, we hope to find a solution to this using unsupervised machine learning techniques. the proposed technique divides the comments into words and removed special characters, emojis, and links from the comments & categorized each comment using a keyword list of each category and similarity findings. And then this was used to categorize comments for training. The implemented method shows the same performance, by Comparison with other supervised machine learning techniques for cyberbullying. Therefore, this mechanism can be used in any other places where low-cost cyberbullying identification is needed. This also can be used to create train comments.
Embargo
Cryptographic Issues and Vulnerabilities in Web Applications
(2021) Herath, H M P Kavinda Ranjan Kumara
Web application security is the most controversial and crucial factor to be concentrated on considering the security aspect of cyberspace. Cryptography takes critical parts of security by implementing encryption and decryption phenomena on data at rest, in moving, and in use to be protected the security breaches. Cryptographic concepts had developed over the last few decades as a result of well-known series of mathematical and logical functions. Weakness of poor programming techniques or leakiness of traditional software development life cycles is a crucial element of the security vulnerabilities that can be a huge impact on several web applications which are currently in existence. The cryptographic vulnerabilities of the web application would depend on several factors such as lack of knowledge on particular subject matters of cryptography, least privilege and contribution of security techniques while cording, unable to proceed with proper standardized vulnerability assessment criteria, the improper adaptation of cryptographic concepts, unable to intended with high secure framework like DevSecOps, depend on the procedures rather than empirical approaches, etc. Sophisticated tools and techniques are necessary factors of driving through the rectification and mitigation of the security vulnerabilities that exist in the web applications whereas implementation process, testing and monitoring of the System Development Life Cycle. This dissertation emphasized indeed a further illustration of cryptographic vulnerability assessment in several specimens collected from different domains from enterprise web applications and related APIs (Application Protocol Interface) currently established. The tools are the critical elements used to evaluate errors on the codes whereas statistical or dynamic analysis. Static tools are given in high percentage of accuracy of the results whereas automated tools are well suited for mega scripting projects such as millions of code evaluated for errors. Java-based code scripting has been dominated still among the huge percentage of the web sources. Python will be established gradually due to the high inbuilt security system on it. Java and Python are the programming languages still being dominated of existence to discuss in the cryptographic vulnerabilities on the process of web application developments. The ultimate goal of this dissertation could be retain valuable sources of documents enriched with sophisticated technics to be used a reference guide for the developers and the security engineers to fulfilled their gaps between code and security requirements
Embargo
Design and Development of an Agent Based Centralized Tool for Analyzing and Managing Security Enhanced Linux Policies
(2021) Kularatna, Ishara Madushanka
Security Enhanced Linux also known as the SELinux, facilitates and includes an extensible Mandatory-Access-Control which is called, “MAC” structure/system built within the Linux kernel. An application or a process life cycle which runs as a user (UID or SUID) has the specific authority to access objects such as files, sockets and other processes with Linux’s default Discretionary-Access-Control (DAC). SELinux prescribes the access and the progress privileges of each user, application, process, and the files on the system and administers the communications of these elements utilizing a security strategy that determines how severe or indulgent a given Red Hat EnterpriSELinux establishment ought to be. However, due to its constraints such as, not being user friendly, having too complicated policies and convoluted policy description language, are limiting the implementation of SELinux policies in the IT industry. As a result, there is only few research available on the subject of UI based policy management tools and even those research have limitations such as, inability to remotely manage a host/server, manual documentation and inability to monitor the systems automatically from a dashboard.In order to overcome the said research gap and problems, this research will implement a system, using a web-socket technology that facilitates ability to conversation in full duplex through a just one TCP connection. This system is included with a web socket-agent, which can be installed in server endpoints and has the ability to change SELinux policies, a web-socket server: which can do live communication with the agent to perform policy changes, UI component: to manage policies using user interface and a database component to store policy details.
Embargo
Fuzzy Logic Controller Based Automated Drip Irrigation System Using Field Capacity Measurements
(2021) SENTHUJA, K.
At present and more so in the future, irrigated agriculture will take the place of the scarcity of groundwater. Difficulty to provide adequate water supply than expected for irrigation will be the norm. The irrigation management, "production per unit” will shift towards emphasizing maximizing the production per unit of water consumed, the "water productivity". Hence, to find an optimum point of irrigation with the consideration of the quantity of water application, growth and yield of a plant a test was conducted. This smart irrigation system optimizes water usage for agriculture and also To improve agricultural water resources utilization, crop’s automatic, location, time, and appropriate drip irrigation is a good choice. In this study, an automatic control drip irrigation system based on a wireless sensor network and fuzzy control would be introduced. This system uses soil moisture, temperature, humidity, light, pH value, and wind information and sends the drip irrigation instructions via a wireless network. It puts the above six soil factors into the input fuzzy controller, creates a fuzzy control rule base, and finishes crop irrigation time through the fuzzy control. The Humidity sensor’s data helps to predict the rain and harvest the rainwater which helps the agriculture purpose.According the sensor’s data, to identify the best method of predict the rain forecast from logistic regression, KNN classifiers, random forest classifier, and Gradient Boosting Classifier algorithms and Random Forest is the Best method compare to the predict the rain forecast. Weeds are the plants which grow in the wrong place in agricultural land. Focusing on detecting the weeds in the crop using computer vision and Image processing to create the application and then notify the user. Fix the physical system to agricultural land and compare the productivity of the particular plant with the past data
Embargo
Improved Round Robin Algorithm for an Efficient CPU Scheduling
(2021) Bandara, A.M.O.P.
The algorithm policy applied by a CPU, to schedule running processes has an impact on the efficiency of an operating system (OS). As a result, a superior CPU scheduling algorithm leads to higher OS performance while using limited resources and for shorter periods of time. As a result, several strategies have been suggested and implemented to improve CPU scheduling performance. Any scheduler's primary responsibility is to assign jobs to the most effective and reliable resource available. It's also a fact that if jobs and resources aren't planned properly, the entire operating system's productivity suffers significantly. The “Round Robin” is deemed an effective and fair approach because of each process are allocated the same amount of time quantum. Nevertheless, the effectiveness of the system is determined by the selected timequantum. The major goal of this research is to develop the present round robin algorithm by enhancing the time quantum for candidate processes in real time in such a way that its impartiality is maintained. There is no loss of property. This paper's proposed algorithm finds the time left in a process's last turn, and then Determines whether it is time based on a certain threshold value, should quantum be expanded or not. An arithmetic simulation has been created to demonstrate that the suggested method is correct. It outperforms the traditional round robin algorithm. In words of several performing metrics such as average waiting time, contextswitches and number of turnaround time, the suggested adjusted version of round robin algorithm outperforms the traditional round robin algorithm, according to the results of the experimental investigation.
Embargo
A hybrid approach on phishing URL Detection using Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) ”
(2021) Dilhara, B.A.S.
Phishing is one of the oldest types of cyber-attack which mostly comes in the form of camouflaged URLs to delude the users in order to get their personal information for malevolent purposes of the attacker. In addition, it is one of the easiest ways of inducing people into disclosing their personal credentials including credit card details. Since people use web applications on a daily basis, most phishing attacks comes up as fake websites pretending to mimic a trustworthy website. Moreover, emails are being used by the attackers to send the phishing website URL (Uniform Resource Locator) to the victim. Such type of URLs is termed as malicious URLs and most phishing attackers use them for successful data breaches. Therefore, it is a necessity to filter up, which URLs are benign, and which are malicious. In order to determine these factors, the concepts including traditional mechanisms used for URL detection, the drawbacks that those mechanisms had, and machine learning approaches used by different authors and their novelty approaches for effective detection are reviewed through this paper. Moreover, this will be focusing on cumulative deep learning approaches to build up hybrid deep learning models. Furthermore, this study proposes 4 hybrid deep learning models namely GRU-LSTM, LSTM-LSTM, bidirectional (GRU)-LSTM, and bidirectional (LSTM)-LSTM. In addition, the study also proposes 3 non hybrid deep learning models namely CNN(1D), LSTM and GRU. Hence, the main objective of this research is to provide a new insight to the hybrid deep learning approaches in URL detection by evaluating their accuracy, precision, recall and f1 score. In conclusion, this research recognizes Bi (GRU) – LSTM as the best mechanism to join hybrid models to detect phishing URLs and classify them as malicious or benign.