ANALYSIS OF SINGLE AND ENSEMBLE MACHINE LEARNING CLASSIFIERS FOR PHISHING ATTACKS DETECTION

Phishing attacks have been used in different ways to harvest the confidential information of unsuspecting internet users. To stem the tide of phishing-based attacks, several machine learning techniques have been proposed in the past. However, fewer studies have considered investigating single and ensemble machine learning-based models for the classification of phishing attacks. This study carried out performance analysis of selected single and ensemble machine learning (ML) classifiers in phishing classification.The focus is to investigate how these algorithms behave in the classification of phishing attacks in the chosen dataset. Logistic Regression and Decision Trees were chosen as single learning classifiers while simple voting techniques and Random Forest were used as the ensemble machine learning algorithms. Accuracy, Precision, Recall and F1-score were used as performance metrics. Logistic Regression algorithm recorded 0.86 as accuracy, 0.89 as precision, 0.87 as recall and 0.81 as F1-score. Similarly, the Decision Trees classifier achieved an accuracy of 0.87, 0.83 for precision, 0.88 for recall and 0.81 for F1-score. In the voting ensemble, accuracy of 0.92 was achieved. 0.90 was obtained for precision, 0.92 for recall and 0.92 for F1-score. Random Forest algorithm recorded 0.98, 0.97, 0.98 and 0.97 as accuracy, precision, recall and F1-score respectively. From the experimental analyses, Random Forest algorithm outperformed simple averaging classifier and the two single algorithms used for phishing url detection. The study established that the ensemble techniques that were used for the experimentations are more efficient for phishing url identification compared to the single classifiers.

MACHINE LEARNING AND DEEP LEARNING-BASED APPROACHES ON VARIOUS BIOMARKERS FOR ALZHEIMER’S DISEASE EARLY DETECTION: A REVIEW

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder. It can cause a massive impact on a patient's memory and mobility. As this disease is irreversible, early diagnosis is crucial for delaying the symptoms and adjusting the patient's lifestyle. Many machine learning (ML) and deep learning (DL) based-approaches have been proposed to accurately predict AD before its symptoms onset. However, finding the most effective approach for AD early prediction is still challenging. This review explored 24 papers published from 2018 until 2021. These papers have proposed different approaches using state of the art machine learning and deep learning algorithms on different biomarkers to early detect AD. The review explored them from different perspectives to derive potential research gaps and draw conclusions and recommendations. It classified these recent approaches in terms of the learning technique used and AD biomarkers. It summarized and compared their findings, and defined their strengths and limitations. It also provided a summary of the common AD biomarkers. From this review, it was found that some approaches strove to increase the prediction accuracy regardless of their complexity such as using heterogeneous datasets, while others sought to find the most practical and affordable ways to predict the disease and yet achieve good accuracy such as using audio data. It was also noticed that DL based-approaches with image biomarkers remarkably surpassed ML based-approaches. However, they achieved poorly with genetic variants data. Despite the great importance of genetic variants biomarkers, their large variance and complexity could lead to a complex approach or poor accuracy. These data are crucial to discover the underlying structure of AD and detect it at early stages. However, an effective pre-processing approach is still needed to refine these data and employ them efficiently using the powerful DL algorithms.

FORMAL MODELING AND ANALYSIS OF ENTITY FRAMEWORK USING ALLOY

Formal methods provide multiple benefits when applied in the software development process. For instance, they enable engineers to verify and validate models before working on their implementation, leading to earlier detection of design defects. However, most of them lack flexibility to be applied in agile software development projects. Alloy is a lightweight formal modeling language with a friendly tool that facilitates the agile approaches application. Unfortunately, its industrial adoption is hampered by the lack of methods and tools for current software development frameworks, such as Entity Framework. This platform is usually chosen by agile projects following the code-first approach that allows automatic generation of a database from domain classes coded in the C# language. We present a new method and tool for the formal specification and analysis of Entity Framework projects with Alloy. The proposal allows engineers to start the software development using Alloy for modeling, validation and verification, automatically translate Alloy specifications to C# domain classes and then generate the corresponding database with Entity Framework. We validate our approach with a real case study: an application required by a gas supplier company.

BLOCKCHAIN ADOPTION: APPLICATIONS AND CHALLENGES

In recent times, more scholastic and social attention have been paid to blockchain and its distributed ledger system mechanism. The reasons for this ever-increasing attention cannot be far-fetched: blockchain now occupies a copious position in the present-day ways of doing things economically, digitally and ‘digital-socially’. Blockchain could be described as a distributed ledger system that allows secure transactions without a central management system. In this distributed ledger system, transactions are coded into blocks, which are linked to each other in the form of a chain. The first application of blockchain is in the bitcoin cryptocurrency. Though not limited to bitcoin, blockchain finds usefulness in security and trusts for instance, digital assets could be coded into blocks to ensure and enforce quality of trust. Consequent upon the quality of trust the blockchain confers on a digital asset, transparency among participating nodes is guaranteed. This is because, any change made to any record in a given block automatically initiates and enforces a corresponding change in all other blocks in the chain hence tampering or breach is almost impossible. Owing to its impressive prospects in the socioeconomic and political ecosystem, this paper was conceived to examine the current developments around this novel technology with particular emphasis on its benefits and proposed challenges and needs to fill the gap created in the vital socioeconomic domains. The paper concludes that the blockchain technology is a plausible approach to restoring the trust, confidentiality, availability and integrity in transactions in the cyberspace and the world at large as majority of the global economy thrives in the cloud.

PHISHING WEBSITES CLASSIFICATION USING ARTIFICIAL NEURAL NETWORK

Internet users might be exposed to various forms of threats that can create economic harm, identity fraud, and lack of faith in e-commerce and online banking by consumers as the internet has become a necessary part of everyday activities. Phishing can be regarded as a type of web extortions described as the skill of imitating an honest company's website aimed at obtaining private information for example usernames, passwords, and bank information. The accuracy of classification is very significant in order to produce high accuracy results and least error rate in classification of phishing websites. The objective of this research is to model a suitable neural network classifier and then use the model to class the phishing website data set and evaluate the performance of the classifier. This research will use a phishing website data set which was retrieved from UCI repository and will be experimented using Encog Workbench tool. The main expected outcome from this study is the preliminary ANN classifier which classifies the target class of the phishing websites data set accurately, either phishy, suspicious or legitimate ones. The results indicate that ANN (9-5-1) model outperforms other models by achieving the highest accuracy and the least MSE value which is 0.04745.

Web Engagement Strategies In Business, Government And Education Sector: Review

Web engagement is a user experience related to emotional, cognitive and behavioural interaction that connect to the goals and interests of the customers. There are seven (7) engagement metrics listed that used to measure web engagement. However, not all of these engagement metrics will help to achieve the objectives because each website have different purpose. There are various web engagement strategies used in business, government and education sectors that has their own way of engaging the web to ensure their success. In business sector, positive communication and experience with customers can make the customers stay long with the brand. In government, most of the services provided are to facilitate the people and to maintain the trust and support of the people. The E-Government 2.0 model was presented with an additional element of Web 2.0 technology. In education, Learning Management System (LMS) and Massive Open Online Courses (MOOCs) are some of the approach in online learning. There are four (4) main features of online learning that are distance learning, connectivity and involvement, support and flexibility control to ensure the continuity of online learning. This reviewing will lead having in attention the aim of developing high-performance in online engagement.

Improving the Accuracy of Static Source Code Based Software Change Impact Analysis Through Hybrid Techniques: A Review

Change is an inevitable phenomenon of life. This inevitability of change in the real world has made a software change an indispensable characteristic of software systems and a fundamental task of software maintenance and evolution. The continuous evolution process of software systems can greatly affect the systems’ quality and reliability if proper mechanisms to manage them are not adequately provided. Therefore, there is a need for automated techniques to effectively make an assessment of proposed software changes that may arise due to bug fixes, technological advancements, changing user requirements etc., before their implementation. Software Change Impact Analysis (CIA) is an essential activity for comprehending and identifying potential change impacts of software changes that can help prevent the system from entering into an erroneous state. Despite the emergence of different CIA techniques, they are yet to reach an optimal level of accuracy desired by software engineers. Consequently, researchers in recent years have come up with hybrid CIA techniques which are a blend of multiple CIA approaches, as a way of improving the accuracy of change impacts analysis techniques. This study presents these hybrid CIA techniques and how they improve accuracy. They are also compared and areas for further research are identified.

Se-LMS: Secured learning management systems for smart school

One of the research topics that focus on Information Communication Technology in Education is Learning Management System (LMS). LMS is a web-based software application developed to create, manage, and delivered e-learning courses. Many research works have been conducted on different learning options in LMS. However, the increased use of LMS has brought with it the security issues such as the denial of service attack, malware and privacy. In order to protect the different actors of LMS such as students, instructors and controlling authorities, this paper proposes a multi-factor authentication and identity management for securing LMS. Se-LMS is capable of dynamically authenticating users using different methods such as a seamless combination of Oauth2.0 and 2FA or Username/Password and 2FA as proposed. Also, the paper explains the situation and existing research relating to security in Learning Management Systems in smart school. The proposed framework has been applied to cloud-based LMS to show the ability to mitigate an attack.

An Information System Design Product Theory for Student Academic Self-Service University Management System

The role of Information System Design Theory in software development is enormous. With the help of design theory, developers could estimate how the system will be and the reasons why the system reacts that way. The focus of the article is to revised and re-establish the design theory of a self-service university management system. The objectives of this publication are to identify the most relevant publication that will act as a guideline to generate the design theory artifacts and to establish the artifacts which will consist of three components named kernel theory, meta-requirements, and meta-design for the stated system. The system scope will be focused on enabling self-service functions. Validation will be done through FEDS framework with the inclusion of a traceability matrix between the meta-requirement against the real-world user requirement. The significance of this article is to provide an initial set of design theory artifacts to be utilized by software developers in the development or evaluation of a University Management System.

Intelligent Software-Aided Contact Tracing Framework: Towards Real-Time Model-Driven Prediction of Covid-19 Cases in Nigeria

As many countries around the world are trying to live with the deadly coronavirus by adhering to the safety measures put in place by their government as regulated by World Health Organization (WHO), it becomes very vital to continuously trace patients with COVID-19 symptoms for isolation, quarantine and treatment. In this work, an intelligent software-aided contact tracing for real-time model-driven prediction of COVID-19 cases is proposed utilizing COVID-19 dataset from kaggle.com. The dataset is preprocessed using One-Hot encoding and Principal Component Analysis. Isolation Forest algorithm is used to train and predict COVID-19 cases. The performance of the model is evaluated using Accuracy, Precision, Recall and F1-Score. The intelligent software-aided contact tracing framework has four layers: symptoms, modeling/prediction, cloud storage/contact routing and contact tracers. The contact tracing system is an android application that receives symptom values, predict it and automatically send the prediction result together with user’s contact and location details to the closest contact tracer via the Firebase real-time database. The closest contact tracer is determined by employing a dynamic routing algorithm (contact routing algorithm) that uses Open Shortest Path First (OSPF) protocol to compute the distance between two geographic locations (user and contact tracer) and chooses a contact tracer with shortest distance to the patient utilizing a unicast routing technique (routing a patient to a contact tracer in a one-to-one relationship). The predictive model along with the android application for software-aided contact tracing is implemented using the python, and Java programming language on Pycharm and Android Studio IDE respectively. This Framework is capable of predicting COVID-19 patients, notifying contact tracers of positive cases for proper follow-up which can subsequently curtail the spread of the virus.