International Journal of Advances in Artificial Intelligence and Machine Learning
The International Journal of Advances in Artificial Intelligence and Machine Learning (IJAAIML) is a prominent academic journal dedicated to publishing cutting-edge research and developments in the fields of Artificial Intelligence (AI) and Machine Learning (ML). It serves as an essential platform for researchers, practitioners, and professionals worldwide to share innovative ideas, technologies, and empirical studies that contribute to advancing AI and ML. The journal emphasizes both theoretical advancements and practical applications, showcasing how these technologies are shaping various industries, including healthcare, finance, education, robotics, and autonomous systems. IJAAIML covers a wide range of topics within AI and ML, such as deep learning, neural networks, natural language processing (NLP), computer vision, robotics, data mining, reinforcement learning, and AI ethics. The journal is open to diverse types of scholarly contributions, including original research articles, review papers, case studies, technical notes, and surveys. It encourages submissions that introduce novel algorithms, methodologies, and systems, as well as those addressing challenges and proposing new approaches in AI and ML. This broad scope allows the journal to remain at the forefront of technological innovation, providing valuable insights into the latest trends and developments in the field. The journal maintains high academic standards through a rigorous peer-review process, ensuring that each published article is of exceptional quality and originality. Submissions are evaluated by experts in relevant fields based on their significance, innovation, methodology, and clarity. This commitment to quality makes IJAAIML a trusted source of information for a diverse audience, including academic researchers, industry professionals, AI practitioners, and students who seek to stay informed about the latest advances in AI and ML. IJAAIML is committed to global knowledge dissemination, making its publications accessible to researchers and professionals worldwide through its online platform. This approach fosters knowledge exchange and collaboration across borders, enabling the journal to reach a broad international audience. By highlighting state-of-the-art research that addresses real-world problems using AI and ML technologies, IJAAIML plays a significant role in advancing the understanding and application of these technologies. Additionally, the journal explores the ethical, societal, and economic impacts of AI and ML, promoting discussions on responsible AI practices and future directions. By contributing to these conversations, IJAAIML not only advances technological innovation but also encourages the development of AI and ML in a manner that considers broader implications for society. Overall, the International Journal of Advances in Artificial Intelligence and Machine Learning stands as a crucial resource for anyone involved in AI and ML, driving forward the frontiers of these dynamic fields through high-quality, peer-reviewed research.
Articles
21 Documents
<![CDATA[AI-Enhanced Gross Pollutant Traps: A Smart Approach to River Health and Pollution Control ]]>
<![CDATA[Ying, Chang Shi]]>;
<![CDATA[May , Bong Peak]]>;
<![CDATA[Fang , Soo Ting]]>;
<![CDATA[Yi, Lee Wai]]>;
<![CDATA[Misinem, Misinem]]>
<![CDATA[ International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 1 No. 1 (2024): International Journal of Advances in Artificial Intelligence and Machine Learni ]]>
Publisher : <![CDATA[CV Media Inti Teknologi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58723/ijaaiml.v1i1.285
<![CDATA[Flooding and river pollution pose significant challenges in Malaysia, exacerbated by the inefficiencies of Gross Pollutant Traps (GPTs), which rely on manual monthly cleaning processes. These conventional methods are inadequate for addressing the dynamic influx of pollutants, particularly during adverse weather conditions. This research proposes an innovative AI-powered framework that integrates logistic regression for weather prediction and Convolutional Neural Networks (CNNs) for real-time garbage classification. By predicting weather patterns and classifying pollutants, this system optimizes GPT maintenance, enhancing its effectiveness and efficiency. The proposed system leverages real-time data from sensors, cameras, and weather forecasts, enabling authorities to implement proactive maintenance strategies based on accurate weather predictions and pollutant types. Logistic regression models forecast adverse weather conditions, while CNNs accurately classify garbage types, allowing targeted GPT cleaning during periods of increased pollutant buildup. The logistic regression model achieved an accuracy of 86.41%, and the CNN model attained a classification accuracy of 79.37%, showcasing strong performance in predicting weather conditions and categorizing pollutants. The integration of AI technologies in GPT maintenance significantly enhances environmental planning, mitigates flooding risks, and improves the accuracy of pollution monitoring. This solution provides valuable insights for decision-makers, helping them allocate resources effectively and maintain sustainable water management practices. In conclusion, the AI-driven system offers a robust and efficient approach to optimizing GPT operations, contributing to better environmental protection and urban sustainability.]]>
<![CDATA[AI-Powered Face Mask Detection Utilizing MobileNetV2 for Health Monitoring ]]>
<![CDATA[Misinem, Misinem]]>;
<![CDATA[Agustini , Eka Puji]]>;
<![CDATA[Ulfa, Maria]]>
<![CDATA[ International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 1 No. 1 (2024): International Journal of Advances in Artificial Intelligence and Machine Learni ]]>
Publisher : <![CDATA[CV Media Inti Teknologi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58723/ijaaiml.v1i1.286
<![CDATA[The COVID-19 pandemic has highlighted the critical need for face masks to prevent virus transmission. Ensuring consistent mask usage in crowded public spaces remains a challenge, especially with manual monitoring methods that are inefficient and prone to error. To address this, this research introduces a real-time face mask detection system leveraging MobileNet-V2, a lightweight and efficient deep learning model known for its high performance in image classification tasks. The system utilizes a dataset from Kaggle comprising 11,792 images, divided into training (10,000), validation (800), and testing (992) sets. MobileNet-V2 was fine-tuned for this task, using its inverted residual layers to extract features and enhance performance effectively. Data augmentation techniques were applied to improve the model’s ability to generalize across diverse scenarios. The MobileNet-V2 model achieved an impressive 98.69% accuracy on the testing dataset, demonstrating exceptional reliability in identifying individuals wearing masks versus those without. Standard evaluation metrics, including precision, recall, and a confusion matrix, confirmed its robustness. This system’s ability to operate in real-time makes it ideal for public health surveillance in environments such as airports, shopping malls, and public transport. The proposed face mask detection system is both accurate and scalable, offering an efficient solution for enforcing mask-wearing protocols in public spaces. The system’s integration of advanced deep learning techniques ensures its reliability in real-time monitoring, contributing to better public health management. Future work will focus on further optimizing the model and expanding its application to other health-related monitoring tasks, enhancing its value for public health surveillance.]]>
<![CDATA[Real-Time Outlier Detection in Fast-Moving Data Streams ]]>
<![CDATA[Eka, Eka Puji Agustini]]>;
<![CDATA[Zakaria, Mohd Zaki]]>
<![CDATA[ International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 1 No. 1 (2024): International Journal of Advances in Artificial Intelligence and Machine Learni ]]>
Publisher : <![CDATA[CV Media Inti Teknologi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58723/ijaaiml.v1i1.287
<![CDATA[Anomaly detection is a critical task in various fields such as finance, healthcare, network monitoring, and sensor data analysis, where identifying unusual patterns or outliers in data streams is essential for timely decision-making. Two commonly used techniques for anomaly detection are the Moving Average (MA) and Exponential Moving Average (EMA) methods. Despite their widespread use, selecting the appropriate method depends on the nature of the data and the requirements of the system. This paper presents a comparative analysis of MA and EMA for anomaly detection, focusing on critical factors such as speed of detection, stability, precision and recall, false positive rate, and computational efficiency. This research addresses the problem of determining which method, MA or EMA, is better suited for specific types of data, particularly in streaming environments with varying trends and anomalies. The results of our comparison indicate that EMA performs better in dynamic environments where rapid identification of anomalies is critical, such as financial markets or network traffic analysis. It quickly detects sudden deviations but may flag minor fluctuations as false positives due to its sensitivity. MA, on the other hand, is more stable and computationally efficient, with a lower false positive rate, making it more suitable for applications where long-term trend monitoring is required, and stability is prioritized over speed. This research highlights the strengths and weaknesses of both methods, demonstrating that the choice between MA and EMA should be based on the specific needs of the anomaly detection system. For real-time, high-speed environments, EMA offers a more responsive solution, while MA provides better stability and efficiency in long-term monitoring. A hybrid approach combining both methods could offer a more robust solution, adapting to different types of data and detection requirements.]]>
<![CDATA[Deep Learning Innovations in Fingerprint Recognition: A Comparative Study of Model Efficiencies ]]>
<![CDATA[Efrizoni, Lusiana]]>;
<![CDATA[Armoogum , Sheeba]]>;
<![CDATA[Zakaria , Mohd Zaki]]>
<![CDATA[ International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 1 No. 1 (2024): International Journal of Advances in Artificial Intelligence and Machine Learni ]]>
Publisher : <![CDATA[CV Media Inti Teknologi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58723/ijaaiml.v1i1.294
<![CDATA[Fingerprint recognition technology is integral to biometric security systems, providing secure and reliable identification through unique human fingerprint patterns. However, challenges such as low contrast, high intra-class variability, and partial fingerprints often compromise the efficiency and accuracy of traditional recognition systems. This research addresses these challenges by employing advanced deep learning techniques, specifically Convolutional Neural Networks (CNNs), to enhance fingerprint recognition performance. We propose a methodological approach that leverages state-of-the-art CNN architectures tailored to capture intricate fingerprint details. The study utilizes the Sokoto Coventry Fingerprint Dataset (SOCOFing), which includes diverse fingerprint types and synthetic alterations to evaluate model performance under realistic conditions. Through a comparative analysis of various CNN configurations, we assessed the models based on efficiency and accuracy, using metrics such as accuracy, precision, recall, and F1-score. Our experimental results demonstrate significant improvements in fingerprint recognition capabilities. The optimized CNN model achieved an accuracy of 98.61%, a precision of 97.12%, a recall of 97.46%, and an F1-score of 97.29%. These results validate the effectiveness of CNNs in handling complex biometric data and underscore their potential to enhance the reliability and security of fingerprint recognition systems. The study concludes that deep learning, through the use of CNNs, offers a powerful solution to the limitations of traditional fingerprint recognition techniques. This will pave the way for more sophisticated and accurate biometric security systems in practical applications. The research findings contribute to ongoing advancements in neural network architectures, enhancing their applicability in increasingly automated and data-driven security environments.]]>
<![CDATA[Scalability and Efficiency: A Comparative Study of Face Recognition Technologies ]]>
<![CDATA[Zakaria, Zaki]]>;
<![CDATA[Misinem, Misinem]]>;
<![CDATA[Sopiah , Nyimas]]>;
<![CDATA[Efrizoni , Lusiana]]>
<![CDATA[ International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 1 No. 1 (2024): International Journal of Advances in Artificial Intelligence and Machine Learni ]]>
Publisher : <![CDATA[CV Media Inti Teknologi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58723/ijaaiml.v1i1.296
<![CDATA[This article addresses the challenge of selecting the most effective machine learning algorithm for face recognition tasks, a common problem in academic research and practical applications. To tackle this issue, we conducted a comparative analysis of five widely used algorithms: Linear Discriminant Analysis (LDA), Logistic Regression, Naive Bayes, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The study involved implementing each algorithm on a standardized dataset, followed by a rigorous evaluation of their performance based on accuracy metrics. The results revealed that LDA, Logistic Regression, and SVM significantly outperformed the other models, each achieving an impressive accuracy of 97%. This high accuracy indicates that these algorithms are well-suited for handling datasets with linearly separable classes. Naive Bayes also showed a strong performance with 90% accuracy, proving effective under the feature independence assumption. However, KNN lagged, with an accuracy of 70%, highlighting its sensitivity to data scale and local structure, which affects its applicability in larger datasets or real-time scenarios. The findings suggest that while LDA, Logistic Regression, and SVM are optimal for datasets with clear class distinctions, the choice of an algorithm should still be guided by specific data characteristics and computational constraints. This study underscores the necessity for carefully considering each algorithm’s strengths and limitations, ensuring that the selected model aligns with the unique demands of the application. Future work could explore ensemble methods and advanced parameter tuning further to enhance the performance and robustness of these models.]]>
<![CDATA[The Fight Against Fiction: Leveraging AI for Fake News Detection ]]>
<![CDATA[Misinem, Misinem]]>;
<![CDATA[Komalasari, Dinny]]>;
<![CDATA[Adha Oktarini Saputri, Nurul]]>
<![CDATA[ International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 2 No. 1 (2025): International Journal of Advances in Artificial Intelligence and Machine Learni ]]>
Publisher : <![CDATA[CV Media Inti Teknologi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58723/ijaaiml.v2i1.367
<![CDATA[This study aims to evaluate the performance of three machine learning algorithms namely Logistic Regression, Naïve Bayes, and Random Forest in classifying fake news. The research methods include data collection from various news sources, text preprocessing to improve data quality, and context-based feature engineering that considers temporal, linguistic, and named entity aspects. Furthermore, the model is developed using a machine learning approach that integrates ensemble techniques to improve prediction accuracy. Evaluation was conducted using accuracy, precision, accuracy, and F1 score metrics. The experimental results showed that Random Forest performed best with an accuracy of 93.00%, superior to Naïve Bayes (89.96%) and Logistic Regression (91.00%). This analysis confirms that algorithm selection should be tailored to the specific needs of the project, with Random Forest being a more reliable choice for scenarios that require high accuracy and robustness to data complexity. The findings are expected to contribute to the development of fake news detection systems that are more effective and adaptive to the dynamics of information in the digital world.]]>
<![CDATA[A Comparative Evaluation of Predictive Models for Lung Cancer: Insights from Logistic Regression, Naive Bayes, and Random Forest ]]>
<![CDATA[Hafiz Kurniawan, Muhammad]]>;
<![CDATA[Misinem, Misinem]]>
<![CDATA[ International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 2 No. 1 (2025): International Journal of Advances in Artificial Intelligence and Machine Learni ]]>
Publisher : <![CDATA[CV Media Inti Teknologi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58723/ijaaiml.v2i1.378
<![CDATA[This study aims to evaluate the performance of three machine learning models-Logistic Regression, Naive Bayes, and Random Forest-in predicting lung cancer using a publicly available dataset from Kaggle. The data used included demographic information, risk factors, and diagnostic imaging features, with significant class imbalance between benign and malignant cases. To address this imbalance, the Synthetic Minority Sampling Technique (SMOTE) was applied. In addition, Principal Component Analysis (PCA) and Recursive Feature Elimination (RFE) were used for dimensionality reduction and feature selection to improve model performance. The results showed that Random Forest, especially when combined with PCA, outperformed the other models with the highest accuracy of 96.77% and a balanced F1 score of 0.50 for the minority class. Although Logistic Regression achieved high accuracy, it was less effective in predicting minority classes, especially when combined with RFE. Meanwhile, Naive Bayes showed moderate performance but was limited by the assumption of feature independence. The application of SMOTE significantly improved the model's ability to handle class imbalance, while PCA proved more effective than RFE in improving model performance. This study highlights the importance of selecting appropriate machine learning models and preprocessing techniques for lung cancer prediction. Random Forest, with its ability to model complex relationships and handle imbalanced data, emerged as the most effective model for this task. These findings underscore the potential of machine learning in medical diagnostics and provide valuable insights for future research.]]>
<![CDATA[The Eye's Signature: Innovative Approaches to Iris Detection ]]>
<![CDATA[pambudi, dhidhi]]>;
<![CDATA[Fadly, Fadly]]>;
<![CDATA[Kurniawan, Muhammad Hafiz]]>;
<![CDATA[Haryanto, Haryanto]]>
<![CDATA[ International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 2 No. 1 (2025): International Journal of Advances in Artificial Intelligence and Machine Learni ]]>
Publisher : <![CDATA[CV Media Inti Teknologi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58723/ijaaiml.v2i1.379
<![CDATA[This research aims to develop and evaluate a deep learning-based iris detection system using a specialized Convolutional Neural Network (CNN) architecture. The research methodology includes data set preprocessing, CNN model design, training using Adam optimization, as well as evaluation using accuracy, precision, recall, and F1 score metrics. The dataset used was obtained from Kaggle and preprocessed before being divided into training, validation, and testing sets. The CNN model consists of three convolutional layers with increasing filter sizes (32, 64, and 128), ReLU activation, batch normalization, and MaxPooling layers for efficient feature extraction, as well as dropout regularization to reduce overfitting. Experimental results show that the proposed model achieves a high classification accuracy of 97.33%, with robust performance against variations and noise in iris images. Comparative analysis with traditional iris recognition methods confirms the superiority of deep learning in handling challenges such as lighting changes and occlusions. Although the results are promising, challenges such as data bias and computational demands are still a concern. Future research will explore more advanced architectures as well as additional pre-processing techniques to improve the generalizability and effectiveness of the system in real-world applications.]]>
<![CDATA[AI-Driven Approaches to Power Grid Management: Achieving Efficiency and Reliability ]]>
<![CDATA[Sasilatha, T.]]>;
<![CDATA[Suprianto, Adolf Asih]]>;
<![CDATA[Hamdani, Hamdani]]>
<![CDATA[ International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 2 No. 1 (2025): International Journal of Advances in Artificial Intelligence and Machine Learni ]]>
Publisher : <![CDATA[CV Media Inti Teknologi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58723/ijaaiml.v2i1.380
<![CDATA[The main objective of this research is to improve the efficiency, reliability, and security of the power grid through the integration of artificial intelligence (AI) techniques. The research method involves developing an integrated AI-SGMS framework, including: (1) AI-based Load Forecasting using LSTM and transformer models; (2) Reinforcement Learning for Network Optimization with deep reinforcement learning (DRL) agents; (3) AI-enabled Fault Detection using CNN and autoencoder; (4) AI-driven Intrusion Detection System (IDS) for cybersecurity; and (5) Edge Computing for Decentralized Decision Making. The results show that AI-SGMS is able to optimize energy distribution, improve predictive maintenance, strengthen cybersecurity, and enhance network resilience. The system reduces waste, prevents congestion, detects potential failures, and mitigates cyber threats. Decentralized decision-making ensures rapid response and network resilience. The conclusion of this research is that the application of AI in power grid management, such as AI-SGMS, has the potential to revolutionize energy distribution, reduce operational costs, and support the transition to a sustainable, resilient, and efficient power grid. This research provides a foundation for broader development of AI solutions in power grid management.]]>
<![CDATA[AI and the Optimization of Product Placement: Enhancing Sales through Strategic Positioning ]]>
<![CDATA[kasim, Shahreen]]>;
<![CDATA[Zakaria, Mohd Zaki]]>;
<![CDATA[Efrizoni, Lusiana]]>;
<![CDATA[Fadly, Fadly]]>
<![CDATA[ International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 2 No. 1 (2025): International Journal of Advances in Artificial Intelligence and Machine Learni ]]>
Publisher : <![CDATA[CV Media Inti Teknologi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58723/ijaaiml.v2i1.381
<![CDATA[This study aims to analyze the impact of strategic product placement and promotion strategies using the Customer's Purchase Behavior Dataset. The study utilized a controlled experimental design, wherein trial stores were matched with control stores based on pre-trial performance metrics, including total sales and customer demographics. A detailed exploratory data analysis (EDA) was conducted to segment customers based on life-stage and purchasing behaviour. Additionally, a t-Test was performed to determine whether price sensitivity and purchasing patterns differed significantly between mainstream, budget, and premium customer segments. The results indicate that trial stores implementing strategic initiatives experienced a measurable uplift in sales compared to their control counterparts. Young and mid-age singles and couples in the mainstream category were found to be more willing to pay a premium for chips, whereas families tended to purchase in bulk. The t-test confirmed statistically significant differences in purchasing behaviour across customer segments. The findings suggest that a data-driven, segment-specific marketing approach can optimise retail performance by aligning promotions and pricing with the behavioural tendencies of different consumer groups. This study demonstrates that well-targeted strategic retail initiatives can significantly improve sales performance. The insights derived from this research provide retailers with actionable strategies for tailoring product placement and promotions to maximise customer engagement. Future work should incorporate machine learning techniques to refine predictive models for real-time decision-making in retail marketing.]]>
