Turkish Journal of Computer and Mathematics Education (TURCOMAT)

Prediction of Type 2 Diabetes using logistic regression techniques

Hussein Al-Rimmawi — 2024-01-11

Abstract

Diabetes is recognized as a significant public health concern and a global epidemic. It is a chronic condition resulting from insufficient insulin production by the pancreas. The long-term elevated blood sugar levels associated with diabetes lead to chronic damage and impaired function in multiple tissues, such as the eyes, kidneys, heart, blood vessels, and nerves.

The objective of this study is to demonstrate the utilization of machine-learning algorithms, specifically logistic regression, in predicting an individual's likelihood of having diabetes based on medical data. Furthermore, the study aims to develop a prediction model that determines whether a patient has diabetes by analyzing specific diagnostic measurements included in the dataset. Various techniques will be explored to enhance the performance and accuracy of the prediction model.

Results: The logistic regression algorithm for the dataset containing various patient data, found that the algorithm predicted whether people would be diagnosed with diabetes with an 82 percent success rate.

STOCK SELECTION USING SEMI-VARIANCE AND BETA TO CONSTRUCT PORTFOLIO AND EFFECT MACRO-VARIABLE ON PORTFOLIO RETURN

Prof. Adler Haymans Manurung — 2024-01-15

This research has aims to construct portfolio by varying method and using semi-variance and Beta for selection stocks. This research found 28 stocks to become member portfolio. Equal Weighted, Market Capitalization Weighted, Markowitz Method and Elton Gruber is used to construct portfolio. This research found that the efficient frontier similar to Markowitz Method. Roy Criterion found the portfolio return varying from 2.2% to 9.65% but Kataoka Criterion found the portfolio return varying from 5.4% to 11.12%. This research found that Elton Gruber has the highest portfolio return compared to others portfolio. There is no difference of average return for four portfolios. Market return significant affect to all portfolio return but the interest rate significant affect portfolio returns for equal weighted portfolio and Elton Gruber Method.

GENDER AND OTHER SIGNIFICANT FACTORS CAUSING DISPARITIES IN SENIOR HIGH SCHOOL STUDENTS’ MATHEMATICS PERFORMANCE

Emmanuel Amoah — 2024-01-16

Research findings on gender and other student related, teacher related and school related factors affecting students’ performance in mathematics are still debatable. With the recent trend of poor performance in mathematics recorded in both district and national performance statistics in the Assin North District, this present study examined gender factor and other significant factors causing disparities in mathematics performance among high school students. A mathematics achievement test and questionnaires were employed to collect data from a representative sample of 500 final-year students from three public senior high schools in the Assin North District, Ghana. Data were analysed descriptively and quantitatively using independent t-test and probit regression. Results show that male students did better than female students in the mathematics achievement test. The differences were statistically significant at .05 significance level. Aside gender, self-assurance and self-regard were identified as significant student related factors affecting the mathematics performance among senior high school students in the Assin North District. Teacher subject matter knowledge, teacher methods and teacher-student interaction were also significant teacher related factors affecting performance in mathematics. Finally, teacher motivation and school environment were identified as significant school related factors affecting mathematics performance among the senior high school. Other factors such as students’ socioeconomic background and teaching resources had effect on students’ performance but they were not statistically significant. The study recommends that senior high school mathematics teachers should employ gender responsive pedagogies in their teaching practices. It is also recommended that professional learning communities should also be formed at school levels to enable mathematics teachers improve upon their knowledge, motivation and teaching styles.

From Detection to Prediction: AI-powered SIEM for Proactive Threat Hunting and Risk Mitigation

Srinivas Reddy Pulyala — 2024-01-11

The evolution of cybersecurity has witnessed a transformative shift from reactive defense measures to proactive threat-hunting and risk-mitigation strategies. In response to the rapidly evolving threat landscape, the integration of Artificial Intelligence (AI) into Security Information and Event Management (SIEM) tools has emerged as a crucial solution. Historically, SIEMs primarily aggregated security data but struggled to analyze the vast, complex datasets effectively. The integration of AI, especially Machine Learning (ML) and Deep Learning (DL), revolutionized these systems. AI algorithms enable SIEMs to extract meaningful insights from massive datasets, allowing for the identification of subtle anomalies and hidden threats that may not be detected by traditional detection methods. This transition marks a fundamental shift from simple data aggregation to intelligent analysis, empowering SIEMs to move beyond detection toward
proactive threat hunting. This paper highlights the role of AI in predicting threats, leveraging historical data to forecast potential risks, and continuously learning to adapt to evolving threat landscapes. It also explores the real-world use cases of AI-powered SIEMs in proactive threat hunting and risk mitigation.

Unveiling Hidden Threats with ML-Powered User and Entity Behavior Analytics (UEBA)

Avinash Gupta Desetty — 2024-01-11

The ever-growing cost of cybercrime has created the need for proactive solutions for organizations seeking to protect their digital assets. While traditional security systems struggle to detect anomalies buried within vast datasets, new solutions like User and Entity Behavior Analytics (UEBA) emerge as a game-changer. By leveraging the power of machine learning, UEBA analyzes diverse data sources like user logins, file accesses, event logs, business context, external
threat intelligence, and network activity, to unveil hidden threats most traditional methods could miss. The ability to analyze multiple data sources enables UEBA solutions to effectively detect malicious insiders, compromised users, Advanced Persistent Threats (APTs), and zero-day attacks. By using various analytics techniques like supervised learning, unsupervised learning, and statistical modeling, UEBA solutions can detect subtle anomalies that deviate from
established behavior baselines. Despite the many benefits, UEBA solutions still have limitations like data quality concerns, high implementation costs, and the need for model maintenance. Integration with System Information and Event Management (SIEM) systems helps mitigate some of these challenges to further enhance UEBA's capabilities and provide a unified platform for threat identification and response. This paper provides a detailed insight into the capabilities of
UEBA, its three pillars, significance, and limitations.

Exploring Factors Contributing to Indifference Towards Learning Mathematics Among Secondary School Students in Nepal

Maheshwor Pokhrel — 2024-01-22

Mathematics is a compulsory subject at the school level in Nepal, deemed essential for everyday life and higher studies, particularly in the fields of science and technology. However, there is a noticeable apathy among students when it comes to learning mathematics. This qualitative research aims to identify the factors that contribute to this indifference towards learning mathematics. Data was collected through in-depth interviews with four participants from both public and private schools, all enrolled in the tenth grade. Analysis and interpretation of the data revealed several factors that lead to this indifference. These factors can be classified as student-related, school-related, and home and society-related. Student-related factors include mathematics anxiety, negative perceptions, insufficient effort, poor academic achievements, limited real-world applications, low self-efficacy, and perpetuation of misconceptions about mathematics. School-related factors encompass teaching practices, teacher qualifications, traditional methods focused on rote learning, impractical curriculum and courses, inadequate school administration, and subpar physical facilities. Home and society-related factors have a negative effect on mathematics engagement, such as unfavorable home environments, low socioeconomic status, and parental education. Together, these factors contribute to the observed indifference towards learning mathematics.

Keywords: Indifference, Qualitative, Mathematics, Factors, Home, Students, School

POLYMER FLAT PLATE SOLAR COLLECTOER: A REVIEW

Noora Hashim — 2024-01-27

A brief description on polymer flat plat solar collector manufacturing, design, and applications are given in this work. The main obstacles that face these collectors type, and how can be processed are also discussed. It is found that polymer low thermal conductivity, and degradation are the most essential difficulties in this industry, and increase heat transfer area and additives are the best common solutions. While stabilizers can be added to increase polymer life time.

Lagrange formula conjugate third order differential equation

Farhad Nasri — 2024-02-05

The paper considers a boundary value problem for a third order with no smooth coefficients and pure derivatives. Odds. This is due to the fact to introduce the concept of the conjugate Green's function. It is very difficult to write the form of the conjugate differential operator corresponding to equation in the Lagrange sense. Therefore, in this work, without using strict conditions smoothness under the conditions and boundedness, an explicit form is found conjugate operator since the initial-boundary value problem for integral-differential equations has been studied based on the introduction special conjugate systems in the form of an integral-algebraic equations’ system. In this article, it can be said that Green's function is considered based on Lagrange's formula for the third-order differential equation with boundary conditions and its conjugate.

The Impact Of Using 5G Technology In The Development Of Information Technology Applications

Yasir khudheyer Abass Aloubade — 2024-01-31

Our study aims To apply 5G technology in the fields of information technology, where the study includes the application of 5G technology in information technology applications and artificial intelligence applications, where an algorithm is created to determine the extent of development taking place in developing programs over the Internet and managing them remotely and controlling them as a result of the speed of 5G technology, which is equivalent to hundreds of times from previous technologies (4G / 3G / 2G) Heading over the advantages and disadvantages of using 5G technology, through the use of the algorithm, the extent of development is evaluated and the use of this evaluation in developing other areas of technology to create a technological environment that can be controlled remotely that carries out all electronic governance activities as well as multiple areas of life.

Applying Software Engineering Based on Peer to Peer ‎‎Communication

Asma Salim Yahya — 2024-03-04

The JavaScript programming language was selected to create software creation that facilitates the creation of a video connection between users because it enables the creation of cross-platform apps relatively quickly. For example, “Web Real-Time Communication (WebRTC)” standards do not specify exactly how two browsers initiate and manage communication with one another. The reason for this is that WebRTC does not specify the signaling technique or protocol. This paper's main goal is to design and construct a WebRTC simultaneous video conference between peers utilizing Google Chrome and the Socket.io signaling technology. A Local Area Network was used in this experiment (LAN). Furthermore, an assessment was conducted on the quality of experience (QoE), the Socket.io signaling method, and resources, including bandwidth consumption. This paper describes the simultaneous execution of peer-to-peer video calls with user identification (user-id).

DETECTION OF CRIME SCENE OBJECTS FOR EVIDENCE ANALYSIS USING DEEP LEARNING TECHNIQUES

Dr. A. BALAJI — 2024-03-04

Research on the detection of objects at crime scenes has flourished in the last two decades. Researchers have been concentrating on colour pictures, where lighting is a crucial component, since this is one of the most pressing issues in computer vision, with applications spanning surveillance, security, medicine, and more. However, nighttime monitoring is crucial since most security problems cannot be seen by the naked eye. That's why it's crucial to record a dark scene and identify the things at a crime scene. Even when its dark out, infrared cameras are indispensable. Both military and civilian sectors will benefit from the use of such methods for nighttime navigation. On the other hand, IR photographs have issues with poor resolution, lighting effects, and other similar issues. Surveillance cameras with infrared (IR) imaging capabilities have been the focus of much study and development in recent years. This research work has attempted to offer a good model for object recognition by using IR images obtained from crime scenes using Deep Learning. The model is tested in many scenarios including a central processing unit (CPU), Google COLAB, and graphics processing unit (GPU), and its performance is also tabulated.

AN EFFICIENT IMAGE PROCESSING BASED IMAGE TO CARTOON GENERATION BASED ON DEEP LEARNING

Dr. A. BALAJI — 2024-03-04

This paper proposes an approach to convert real life images into cartoon images using image processing. The cartoon images have sharp edges, reduced colour quantity compared to the original image, and smooth colour regions. With the rapid advancement in artificial intelligence, recently deep learning methods have been developed for image to cartoon generation. Most of these methods perform extremely huge computations and require large datasets and are time consuming, unlike traditional image processing which involves direct manipulation on the input images. In this paper, we have developed an image processing based method for image to cartoon generation. Here, we perform parallel operations of enhancing the edges and quantizing the colour. The edges are extracted and dilated to highlight them in the output colour image. For colour quantization, the colours are assigned based on proposed formulation on separate colour channels. Later, these images are combined and the highlighted edges are added to generate the cartoon image. The generated images are compared with existing image processing approaches and deep learning based methods. From the experimental results, it is evident that the proposed approach generates high quality cartoon images which are visually appealing, have superior contrast and are able to preserve the contextual information at lower computational cost.

A NOVEL CORONARY HEART STROKE PREDICTION SYSTEM USING MACHINE LEARNING TECHNIQUES

Dr. A. BALAJI — 2024-03-04

Over the past few decades, cardiovascular diseases have surpassed all other causes of death as the main killers in industrialised, underdeveloped, and developing nations. Early detection of heart conditions and clinical care can lower the death rate. Based on the patient's various cardiac features, we proposed a model for forecasting heart disease and identifying impending heart disease using machine learning techniques In most cases,input is received through numerical data of various parameters, and output findings are generated in real-time, predicting whether or notthe patient has a disease. We'll use a variety of supervised machine learning methods before deciding which one is best for the model. Existing systems rely on classical deep learning models, which are inefficient and imprecise. They aren't as accurate as the proposed model and take a little longer to process.

DETECTION OF FRAUDULENT OR DECEPTIVE PHONE CALLS USING ARTIFICIAL INTELLIGENCE

Mrs J. RATNAKUMARI — 2024-03-04

With an increase advancement of technology, fraud phone calls, including spam’s and malicious calls have become a major concern in telecommunication industry and causes millions of global financial losses every year. Fraudulent phone calls or scams and spams via telephone or mobile phone have become a common threat to individuals and organizations. Artificial Intelligence (AI) and Machine Learning (ML) has emerged as powerful tools in detecting and analyzing fraud or malicious calls. This project presents an overview of AI-based fraud or spam detection and analysis techniques, along with its challenges and potential solutions. The novel fraud call detection approach is proposed that achieved high accuracy and precision. The Proposed approach was evaluated using a dataset of real-world fraudulent calls. And results demonstrate that the approach achieved high accuracy in detecting malicious calls and identifying potential indicators of frauds or spam’s. The analysis of fraud calls also provided insights into the tactics and methods employed by fraudsters, which can be used to develop countermeasures.

A ROBUST DETECTION OF CYBER INCIDENTS UTILIZING MACHINE LEARNING TECHNIQUES

Mrs J. RATNAKUMARI — 2024-03-04

A reliable Cyber Attack Detection Model (CADM) is a system that works as safeguard for the users of modern technological devices and assistant for the operators of networks. The research paper aims to develop a CADM for analyzing the network data patterns to classify cyber-attacks. CADM finds out attack wise detection accuracy using ensemble classification method. LASSO has been used to extract important features. It can work with large datasets, and it has more visualization capability. Gradient Boosting and Random Forest algorithms have been used for classification of network traffic data to build an ensemble method. Gradient Boosting algorithm trains weak learning models and select the best decision trees to deliver more improved prediction accuracy and Random Forest algorithm trains each tree in parallel manner. In this research work, Jive datasets such as NSL-KDD, KDD Cup 99, UNSWNB15, URL 2016 and CICIDS 2017 are also applied to check the efficiency of the proposed model.

AN EFFCIENT SYSTEM FOR DETECTING TRAFFIC VIOLATIONS SUCH AS OVER SPEED, DISREGARDING SIGNALS, AND INSTANCES OF TRIPLE RIDING

Mrs J. RATNA KUMARI — 2024-03-04

In recent time surveys, the deaths and injuries due to traffic violations have increased chiefly in Indian roads. So, this needed the assistance of an automated computer vision-based object detection model, as manually identifying the vehicles violating traffic is hectic. The principle of this paper is to detect multiple violations using single video frames. The input video stream obtained from the surveillance camera is processed and annotated to carry out multiple processes. The dataset used for red-light jumping is COCO and the dataset for over boarding is created by annotating the images obtained from google. The model is trained, and the output is visualized using tensor board. The accuracy for red light skipping is 93% and the mAP value for over boarding is 0.5:0.95. This system utilizes the video stream at its maximum to detect various violations.

DETECTING AND CLASSIFYING FRAUDULENT SMS AND EMAIL WITH A ROBUST MACHINE LEARNING APPROACH

Dr. P. BUJJI BABU — 2024-03-04

Spam is an unwanted message or SMS sent onmobile phones whose content may bemalicious. Scammers sendfake text messages to trick people into responding to their SMSand they may hack personal information, password, accountnumber, etc. To avoid being tricked by scammers, proposed amodel based on Machine learning Algorithms. The proposedmodel is implemented using the Naïve Bayes algorithm and termfrequency-inverse document frequency vectorizer. Obtainedthe dataset from Kaggle and trained the model using it. Thismodel consists of a local host website which is obtained throughPyCharm IDE. Obtained results show that the model accuracyof 95% and a precision of 100%

AUTOMATIC CLASSIFICATION AND DETECTION OF COUNTERFEIT BANKNOTES BASED AI

Dr. P. BUJJI BABU — 2024-03-04

On the basis of the look, people can easilydifferentiate banknotes and coin denominations. The coincurrencies can be identified visually impaired people basedon touch, but the note currencies cannot be identified easilyas it has similar texture and appearance, it can be challengingfor visually challenged people to distinguish the currencies. Demonetization has boosted the availability of fake cash inrecent years. People face difficulty in distinguishing betweenreal and fake banknotes because they are unaware of thesecurity elements utilized in modern currencies. Additionally, these fake cash mislead persons who don’t haveproper vision. So, it becomes important to identify thedenominations and detect fake and real banknotes in-orderto avoid the problems caused due to these currencies orbanknotes. This issue highlights the requirement for anaccurate banknote identification model. By spotting thecounterfeit currency, inflation and currency devaluation canbe stopped. The suggested model aims to identify thedenomination and categorize if a money note is real orfraudulent. The banknote denomination is determined using the machine learning algorithms.

A ROBUST DETECTION FRAUDULENT TRANSACTIONS IN BANKING USING MACHINE LEARNING

Mr N. KISHORE KUMAR — 2024-03-04

Vulnerability in banking systems has exposed us to fraudulent acts, which cause severe damage to both customers and the bank in terms of loss of money and reputation. Financial fraud in banks is estimated to result in a significant amount of financial loss annually. Early detection of this helps to mitigate the fraud, by developing a counter strategy and recovering from such losses. A machine learning-based approach is proposed in this paper to contribute to fraud detection successfully. The artificial intelligence (AI) based model will speed up the check verification to counteract the counterfeits and lower the damage. In this paper, we analyzed numerous intelligent algorithms trained on a public dataset to find the correlation of certain factors with fraudulence. The dataset utilized for this research is resampled to minimize the high class of imbalance in it and analyzed the data using the proposed algorithm for better accuracy.

DETECTING PANCREATIC CANCER WITH MACHINE LEARNING AND DEEP LEARNING TECHNIQUES

Dr. V. NAGAGOPIRAJU — 2024-03-04

The great majority of the computer systems that are now being utilized for research on medical health systems are based on the most recent technical breakthroughs. Because of the prevalence of pancreatic cancer, a significant number of novel approaches and techniques have emerged in the field of medicine. There are several various classifications that may be applied to the pancreatic cancer that can be found. Utilization of the deep learning technology is going to be the means by which the classification of pancreatic cancer is going to be completed. The classification of pancreatic cancer may be tackled from a variety of angles, each of which can be accomplished via using either technology for machine learning or technology for deep learning. In the past, a diagnosis of pancreatic cancer could be made by using methods such as the Support Vector Machine (SVM), Artificial Neural Networks, Convolution Neural Networks (CNN), and Twin Support Vector Machines. As a result, this study has implemented an Advanced Convolution Neural Networks (ACNN), which are examples of the type of technology known as deep learning. In the vast majority of the existing research works, the classification has been determined by analyzing the images of the patient, With the help of constant values and ACNN strategies, the performance rate was enhanced in contrast to the approaches that were currently being used.

A ROBUST CYBER SECURITY THREAT DETECTION MODEL USING ARTIFICIAL INTELLIGENCE TECHNOLOGY

Dr. V. NAGAGOPIRAJU — 2024-03-04

The difficulty of ensuring cyber-security is steadily growing as a result of the alarming development in computer connectivity and the sizeable number of applications associated to computers in recent years. The system also requires robust defines against the growing number of cyber threats. As a result, a possible role for cyber-security might be performed by developing intrusion detection systems (ids) to detect inconsistencies and threats in computer networks. An effective data-driven intrusion detection system has been created with the use of artificial intelligence, particularly machine learning techniques. This research proposes a novel twin support vector machine (tsvm) based security model which first considers the security features ranking according to their relevance before developing an ids model based on the significant features that have been selected. By lowering the feature dimensions, this approach not only improves predictive performance for unidentified tests but also lowers the model's computational expense. Trials are conducted using four common ml techniques to compare the results to those of the current approaches (decision tree, random decision forest, random tree, and artificial neural network). The experimental findings of this study confirm that the suggested methods may be used as learning-based models for network intrusion detection and demonstrate that, when used in the real world, they outperform conventional ml techniques.

MACHINE LEARNING AND BLOCKCHAIN-BASED REAL-TIME FACIAL RECOGNITION ATTENDANCE SYSTEM

Dr. V. NAGAGOPIRAJU — 2024-03-04

In a vast majority of fields, the use of facial recognition for authentication is expanding. In this information age, authentication has become vital, and the need for faster and more secure methods of user authentication has been on the rise. The introduction of image processing technologies such as OpenCV has increased society’s reliance on face recognition. Using blockchain, information could be stored in blocks throughout the blockchain network. Blockchain is an extremely secure means for storing and protecting data from intruders. It is a highly disruptive technology that has the ability to alter every plane of society. This paper intends to implement opensource computer vision (OpenCV) to construct a facial detection model that will be employed in a blockchain-secured Attendance Monitoring System. It will not only automate the attendance procedure but also give the system unassailable security. This system will take a live video feed from a camera using OpenCV and identify the faces of students and record their attendance along with the entry time. The data will be kept in a distributed way over the blockchain network that will be accessible to everyone, but data cannot be manipulated.

A EFFCIET DEEP FAKE FACE DETECTION USING DEEP INCEPTION NET LEARNING ALGORITHM

Dr. V. NAGAGOPIRAJU — 2024-03-04

A Deep Fake Is Digital Manipulation Techniques That Use Deep Learning to Produce Deep Fake (Misleading) Images and Videos. Identifying Deep Fake Images Is the Most Difficult Part of Finding the Original. Due To the Increasing Reputation of Deep Fakes, Identifying Original Images and Videos Is More Crucial to Detect Manipulated Videos. This Paper Studies and Experiments with Different Methods That Can Be Used to Detect Fake and Real Images and Videos. The Convolutional Neural Network (Cnn) Algorithm Named Inception Net Has Been Used to Identify Deep Fakes. A Comparative Analysis Was Performed in This Work Based on Various Convolutional Networks. This Work Uses the Dataset from Kaggle With 401 Videos of Train Sample And 3745 Images Were Generated by Augmentation Process. The Results Were Evaluated with The Metrics Like Accuracy and Confusion Matrix. The Results of The Proposed Model Produces Better Results in Terms of Accuracy With 93% On Identifying Deep Fake Images and Videos.

ADVANCED WILD ANIMAL DETECTION AND ALERT SYSTEM USING THE YOLO V5 MODEL POWERED BY AI

Dr. V. NAGAGOPIRAJU — 2024-03-04

An advanced wild animal detection and alert system using you only look once version5 (YOLO V5) model. The system utilizes you only look once version5 (YOLO V5) object detection algorithm to identify wild animals and alert users to their presence in real-time. The system employs a camera to capture real-time video, which is then sent to a computer running you only look once version5 (YOLO V5) algorithm. When the system detects a wild animal, it sends an alert to the wild animal by playing any sounds like bullets firing. The system is expected to have a significant impact on the safety of people in areas with high wildlife populations. This advanced wild animal detection and alert system using you only look once version5 (YOLO V5) model has the potential to improve the safety of people in areas with high wildlife populations. Future work will focus on improving the accuracy of the system and implementing it in real-world scenarios.

AN EFFCIET FORCASTING MENTAL HEALTH CONDITION USING MACHINE LEARNING

Dr. P. BUJJI BABU — 2024-03-04

Nowadays, people are becoming more and more concerned with their physical health, but mental health is not given the same level of attention. Even if they are aware that they have been afflicted by chronic mental illnesses, many people choose not to seek treatment out of fear of what others would think, a belief that they have lost their minds, a dislike of doctors, or all three. These circumstances make it urgently necessary to find a solution so that more individuals are not inclined to mental diseases. This paper focuses on forecasting mental health using deep learning approaches and machine learning algorithm that is support vector machine. Support vector machine is used to solve the existing problem, as many machine learning and deep learning techniques are helping to solve these contemporary difficulties. SVM gives more accuracy compared to other machine learning algorithms to predict the mental illness.

FORCASTING ACADMIC PERFORMANCE IN COMPUTER SCIENCE STUDENTS BASEDON FUTURE ANALYSIS METHOD

N.KISHORE KUMAR — 2024-03-04

The ever increasing importance of education has drivenresearchers and educators to seek innovative methods forenhancing student performance and understanding the factorsthat contribute to academic success. This paper presents a methodology for predicting CGPA SGPA that leverages machine learning techniques to forecast students'academic achievements based on a variety of features, such asdemographic information, academic history, and behavioural patterns. The proposed students academic performance method utilizes a real-world collected dataset from multiple educational institutions toensure an accurate and comprehensive analysis. The proposed methodology starts with a data preparationstage, where the data is cleansed and organized for analysis. This process encompasses tasks such as handling missing values, scaling the data, and transforming variables ifnecessary. The feature analysis technique was used to select the most important features for the students academic performance model. A number ofmachine learning classifiers were tested, and the feature analysis was found to be the best performer. The results of this study demonstrate the potential of algorithms in predicting student performance andidentifying key factors that influence academic success. This information can be leveraged by educators and academicinstitutions to develop targeted intervention strategies, tailoredlearning experiences, and personalized recommendations forstudents, ultimately fostering a more effective learningenvironment and improving overall educational outcomes.

A ROBUST DETECTION OF CYBER INCIDENTS UTILIZING MACHINE LEARNING TECHNIQUES

RATNAKUMARI JOGI — 2024-03-04

Characteristic Mode Solution of Complex-Coefficient Complex-Solution Differential Equations

Khalid Youssef — 2024-04-12

Computation of complex-coefficient complex-solution differential equations is a problem that arises in various domains of science and engineering. This paper aims at applying the Theory of Characteristic Modes (TCM) approach along with the Method of Moments (MoM) in solving these problems with emphasis on procedures for higher differential equations. Several available methods, known in literatures, are available for solving the problem. The complexity of the available methods differs based on the accuracy of the solution. In this paper, the general method is first presented and then a simplified version of it is proposed to solve high order differential equations. Two examples are illustrated, a third and a fourth order complex-coefficients complex-solution differential equations, to show the simplicity of the proposed method. The proposed approach can be also introduced along with other methods to solve these special occurrences differential equations and other boundary value problems.

Depth reduction of RGB image data and reduction of point noise based on metric learning method

Riyadh Alsaeedi — 2024-04-18

In this paper, a method of data depth reduction based on metric learning method in reducing point noise in different images is proposed. In order to be more accurate in reviving depth from data, noise variance is also calculated for each separate scale. In this way, our method becomes more sensitive to noise detection. The quantitative and qualitative results obtained from the implementation and calculation of the PSNR parameter of this method show that the proposed method of this paper has given a good answer compared to previous methods for noise elimination and has performed better in maintaining sharp corners and sharp features.