Babylonian Journal of Machine Learning <p>The Babylonian Journal of Machine Learning (BJML) (EISSN: 3006-5429) is a specialized publication dedicated to the exploration and integration of modern machine learning methodologies. As a platform for researchers and scholars, the journal focuses on the intersection of cutting-edge advancements in machine learning. Through high-quality articles, it fosters interdisciplinary discussions aimed at propelling forward the field of machine learning research.</p> Mesopotamian Academic Press en-US Babylonian Journal of Machine Learning 3006-5429 Intrusion Detection System Based on Machine Learning Algorithms:( SVM and Genetic Algorithm) <p>The widespread utilization of the internet and computer systems has resulted in notable security concerns, characterized by a surge in intrusions and vulnerabilities. Malicious users manipulate internal systems, resulting in the exploitation of software flaws and default setups.&nbsp;&nbsp; With the integration of the internet into society, there is an emergence of new risks such as viruses and worms, which highlights the importance of implementing robust security measures.&nbsp;&nbsp; Intrusion detection systems (IDS) are security technologies utilized to monitor and analyze network traffic or system activity with the purpose of identifying hostile behavior.&nbsp;&nbsp; This article presents a proposed method for detecting intrusion in network traffic using a hybrid approach, which combines a genetic algorithm and an SVM algorithm.&nbsp;&nbsp; The model underwent training and testing on the KDDCup99 dataset, with a reduction in features from 42 to 29 using the hybrid approach.&nbsp;&nbsp; The results demonstrated that throughout the system testing, it exhibited a remarkable accuracy of 0.999. Additionally, it achieved a true positive value of 0.9987 and a false negative rate of 0.012.</p> Abdulazeez Alsajri Amani Steiti Copyright (c) 2023 Abdulazeez Alsajri, Amani Steiti 2024-01-18 2024-01-18 2024 15 29 10.58496/BJML/2024/002 Random Forest Algorithm Overview <p>A random forest is a machine learning model utilized in classification and forecasting. To train machine learning algorithms and artificial intelligence models, it is crucial to have a substantial amount of high-quality data for effective data collecting. System performance data is essential for refining algorithms, enhancing the efficiency of software and hardware, evaluating user be-havior, enabling pattern identification, decision-making, predictive modeling, and problem-solving, ultimately resulting in improved effectiveness and accuracy. The integration of diverse data collecting and processing methods enhances precision and innovation in problem-solving. Utilizing diverse methodologies in interdisciplinary research streamlines the research process, fosters innovation, and enables the application of data analysis findings to pattern recognition, decision-making, predictive modeling, and problem-solving. This approach also encourages in-novation in interdisciplinary research. This technique utilizes the concept of decision trees, con-structing a collection of decision trees and aggregating their outcomes to generate the ultimate prediction. Every decision tree inside a random forest is constructed using random subsets of data, and each individual tree is trained on a portion of the whole dataset. Subsequently, the outcomes of all decision trees are amalgamated to derive the ultimate forecast. One of the bene-fits of random forests is their capacity to handle unbalanced data and variables with missing values. Additionally, it mitigates the issue of arbitrary variable selection seen by certain alterna-tive models. Furthermore, random forests mitigate the issue of overfitting by training several de-cision trees on random subsets of data, hence enhancing their ability to generalize to novel data. Random forests are highly regarded as one of the most efficient and potent techniques in the domain of machine learning. They find extensive use in various applications such as automatic categorization, data forecasting, and supervisory learning.</p> Hasan Ahmed Salman Ali Kalakech Amani Steiti Copyright (c) 2024 Hasan Ahmed Salman , Ali Kalakech , Amani Steiti 2024-06-08 2024-06-08 2024 69 79 10.58496/BJML/2024/007 A Proposed Method of Gesture-controlled presentation software design <p>This paper introduces an innovative method for developing a presentation application that empowers users to seamlessly control slide transitions and other essential actions through intuitive hand gestures. The approach integrates sophisticated computer vision algorithms capable of real-time gesture detection and interpretation from a standard webcam feed. Furthermore, machine learning techniques personalize the system to individual users' unique gestures, enhancing usability and accuracy. The proposed method is a groundbreaking innovation that seamlessly integrates with existing presentation tools. Furthermore, the research delves into cross-device synchronization, enabling a cohesive presentation experience. To ensure optimal usability and performance, we follow established software engineering principles, resulting in a user-friendly interface and an efficiently structured codebase. This paper comprehensively guides the design, implementation, and potential of this gesture-controlled presentation software.</p> Nadia Mahmood Hussien Yasmin Makki Mohialden wurood A. jbara Copyright (c) 2024 Nadia Mahmood Hussien, Yasmin Makki Mohialden , wurood A. jbara 2024-04-01 2024-04-01 2024 56 62 10.58496/BJML/2024/005 A Short Review on Supervised Machine Learning and Deep Learning Techniques in Computer Vision <p>In last years, computer vision has shown important advances, mainly using the application of supervised machine learning (ML) and deep learning (DL) techniques. The objective of this review is to show a brief review of the current state of the field of supervised ML and DL techniques, especially on computer vision tasks. This study focuses on the main ideas, advantages, and applications of DL in computer vision and highlights their main concepts and advantages. This study showed the strengths, limitations, and effects of computer vision supervised ML and DL techniques.</p> Ahmed Adil Nafea Saeed Amer Alameri Russel R Majeed Meaad Ali Khalaf Mohammed M AL-Ani Copyright (c) 2024 Ahmed Adil Nafea, Saeed Amer Alameri , Russel R Majeed, Meaad Ali Khalaf , Mohammed M AL-Ani 2024-02-11 2024-02-11 2024 48 55 10.58496/BJML/2024/004 Green Building Techniques: Under The Umbrella of the Climate Framework Agreement <p>Various green building rating systems have been devised to assess the sustainability levels of buildings, offering a standardized approach to evaluate their environmental impact. However, adapting these existing methods to diverse regions requires addressing additional considerations, such as distinct climatic conditions and regional variations. This study delves into a comprehensive exploration of widely utilized environmental building assessment methodologies, including BREEAM, LEED, SB-Tool, CASBEE, GRIHA, and Eco-housing. A new building environmental assessment scheme tailored to the global landscape is needed due to limitations of existing assessment schemes. A framework based on principal component analysis is introduced to develop this new scheme. PCA applied to a dataset of many responses on building sustainability revealed nine key components, including site selection, environmental impact, building resources and re-use, building services and management, innovative construction techniques, environmental health and safety, mechanical systems, indoor air quality, and economic considerations. A framework for sustainable building development in world is proposed. The study provides insights for designers and developers in developing countries, offering a roadmap for achieving green development. The framework prioritizes key components for a nuanced evaluation of sustainability in building projects, contributing to the global discourse on environmentally responsible construction practices.</p> Ali Saleh Noah Saleh Obed Ali Raed Hasan Omar Ahmed Azil Alias Khalil Yassin Copyright (c) 2024 Ali Saleh, Noah Saleh, Obed Ali, Raed Hasan, Omar Ahmed , Azil Alias, Khalil Yassin 2024-01-10 2024-01-10 2024 1 14 10.58496/BJML/2024/001 Enhancing Energy Efficiency With Smart Building Energy Management System Using Machine Learning and IOT <p>The energy management system designed on the networking platform has been interfaced with controller to control the electrical device using the Wireless communication has been used as the most reliable and efficient technology in short-range communication. In this method IoT-based energy management could significantly contribute to energy conservation of home appliances device. This model analyses an IoT-based smart energy meter that automatically tracks residential energy consumption using current and voltage sensors. Input values senses unit that detects and controls the electrical devices used for daily actions. The ESP32 is used due to its built-in Wi-Fi facility, allowing data collection and exchange from electronic hardware to a cloud platform. The virtual android app displays the value of voltage, current, power, and unit consumed on a mobile screen, enhancing the efficiency of the system. The developed coding system to enhance system performance and provide more accurate results and ESP32 controller to interface non-invasive CT and voltage sensors, delivering data to a Blynk server over the internet. Model show the system accurately records voltage, current, dynamic power, and increasing power consumption and outcome accordingly, the home concerned person can turn ON/OFF the device based on such information if customer based user information.</p> M.Sahaya Sheela S. Gopalakrishnan I.Parvin Begum J. Jasmine Hephzipah M Gopianand D. Harika Copyright (c) 2024 M.Sahaya Sheela, S. Gopalakrishnan, I.Parvin Begum, J. Jasmine Hephzipah, M Gopianand, D. Harika 2024-06-11 2024-06-11 2024 80 88 10.58496/BJML/2024/008 Artificial Intelligence Predictions in Cyber Security: Analysis and Early Detection of Cyber Attacks <p>&nbsp;</p> <p>The landscape of cyber-attacks has changed due, to the upward push of digitalization and interconnected structures. This necessitates the need for revolutionary techniques to emerge as aware of and mitigate these threats at a degree. This studies delves into the correlation amongst cyber security and artificial intelligence (AI) with a focus on how AI can decorate detection of cyber-attacks via assessment, prediction and different strategies. By harnessing machine mastering, neural networks and records analytics predictive models driven with the useful resource of AI have emerged as an approach to deal with the ever evolving demanding situations posed through cyber threats. The number one goal of this observe is to look at the effectiveness of AI powered prediction fashions, in cyber security. It ambitions to evaluate how nicely those AI based systems carry out as compared to cyber security techniques emphasizing their capability to proactively locate and mitigate cyber threats as a way to minimize their effect. Additionally ability obstacles and ethical issues associated with AI based cyber security answers are also discussed. Also using AI algorithms to Analysis and Early Detection of Cyber Attacks using python programming language. The research's conclusions are extremely important for the field of cyber security since they provide information about how threat mitigation and incident response will develop in the future. This research helps to develop cutting-edge cyber security solutions by addressing the dynamic and constantly-evolving landscape of cyber threats.</p> Meaad Ali Khalaf Amani Steiti Copyright (c) 2024 Meaad Ali Khalaf, Amani Steiti 2024-05-09 2024-05-09 2024 63 68 10.58496/BJML/2024/006 Image Enhancement using Convolution Neural Networks <p>The research presents a comprehensive exploration of the topic of image enhancement using convolutional neural networks (CNN).The research goes deeper into the advanced field of image processing based on the use of neural networks to automatically and efficiently improve the quality and detail of images. The thesis shows that convolutional neural networks are one of the types of deep neural networks, which are specially designed to gain knowledge from big data and extract complex features and patterns found in images. The different layers of the grid are discussed in detail, dealing with images incrementally and extracting different attributes in each layer. The research also highlights CNN's ability to detect, learn and improve important details found in images through convolutions, filtering and data aggregation processes. The proposed CNN image enhancement model was developed and tested on both medical and normal images. The images were optimized using the proposed model and compared with other models. Various quality measures were used to evaluate the results. The results showed that the proposed model can significantly improve the quality of images.</p> Hasan Ahmed Salman Ali Kalakech Copyright (c) 2024 Hasan Ahmed Salman, Ali Kalakech 2024-01-25 2024-01-25 2024 30 47 10.58496/BJML/2024/003