IAES International Journal of Artificial Intelligence (IJ-AI)
IAES International Journal of Artificial Intelligence (IJ-AI) publishes articles in the field of artificial intelligence (AI). The scope covers all artificial intelligence area and its application in the following topics: neural networks; fuzzy logic; simulated biological evolution algorithms (like genetic algorithm, ant colony optimization, etc); reasoning and evolution; intelligence applications; computer vision and speech understanding; multimedia and cognitive informatics, data mining and machine learning tools, heuristic and AI planning strategies and tools, computational theories of learning; technology and computing (like particle swarm optimization); intelligent system architectures; knowledge representation; bioinformatics; natural language processing; multiagent systems; etc.
Articles
85 Documents
Search results for
, issue
"Vol 15, No 2: April 2026"
:
85 Documents
clear
<![CDATA[Machine learning-based solar power prediction for major Indian metro cities ]]>
<![CDATA[Napa, Komal Kumar]]>;
<![CDATA[Govindarajan, Rajkumar]]>;
<![CDATA[Senthil Murugan, J.]]>;
<![CDATA[Manindhar, Billa]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v15.i2.pp1362-1370
<![CDATA[The growing reliance on renewable energy has intensified the need for accurate solar power forecasting to support efficient grid operation and energy planning. However, reliable prediction remains challenging due to the strong dependence of solar power output on dynamic meteorological conditions. This study proposes a data-driven machine learning (ML) framework for high-precision solar power prediction across several major Indian metro cities. Using hourly weather and power generation data for the year 2023, a random forest regressor was developed to model complex non linear relationships between environmental variables and solar energy output. The proposed model achieved exceptional predictive performance, with an R² score of 0.9999 and a mean absolute error (MAE) of 0.15 kW, significantly outperforming conventional regression approaches. Feature contribution analysis revealed solar radiation as the dominant factor influencing power generation, while cloud cover and elevated temperatures exhibited negative effects. The key contribution of this work lies in demonstrating the robustness and generalizability of ensemble learning for urban-scale solar forecasting under diverse climatic conditions. The findings provide actionable insights for policymakers, grid operators, and energy planners to optimize solar integration and resource management.]]>
<![CDATA[Climate change and pollinator dynamics: integrating social media insights and ecological data for conservation strategies ]]>
<![CDATA[Hadimane, Pooja]]>;
<![CDATA[Kukkuvada, Ashoka]]>;
<![CDATA[Hediyalad, Gangamma]]>;
<![CDATA[Hegade Kota, Govardhan]]>;
<![CDATA[Kisan, Rajeswari]]>;
<![CDATA[Patil, Shivanand]]>;
<![CDATA[Myala, Arjun]]>;
<![CDATA[Anekonda Subhash, Basavaraja]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v15.i2.pp1680-1690
<![CDATA[Pollination is an essential ecosystem service intricately linked to biodiversity, ecosystem health, and agricultural systems. The need to understand the effect of climate change on pollination processes has never been greater, given that a significant portion of global crop production is dependent on biotic pollination. This survey paper examines the multifaceted challenges that climate change poses to pollination dynamics across various ecosystems. By synthesizing existing literature to highlight how alterations in temperature and precipitation patterns have led to a phenological mismatch between pollinators and plants, potentially disrupting established trophic relationships and ecosystem functions. Our review reveals that insect-pollinated plants, particularly those that bloom early in the season, exhibit a heightened sensitivity to climate-induced phenological shifts. Moreover, exploring how the altered life cycles of pollinators, struggling to synchronize with the new flowering schedules, may precipitate declines in pollination services. Our findings underscore the critical need for conservation strategies that address climate adaptation for pollinators, focusing on enhancing landscape connectivity and heterogeneity. By bridging diverse studies ranging from the application of social media data in ecological research to advanced predictive models for pollination services, the main aim is to foster a deeper understanding of the consequences of climate change on pollination.]]>
<![CDATA[Multi-dimensional performance-optimized array design framework for efficient mmWave energy harvesting ]]>
<![CDATA[Mirle Gajendra, Shalini]]>;
<![CDATA[Kalenahalli Bhoganna, Naveen]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v15.i2.pp1143-1154
<![CDATA[The proliferation of next-generation wireless networks and autonomous devices has intensified the need for efficient and compact energy harvesting solutions at millimeter-wave (mmWave) frequencies. This paper presents a multi-dimensional performance-optimized array design framework for mmWave energy harvesting (MAPLE-H), which enables the systematic development of advanced antenna arrays that fulfill the simultaneous demands of wide operational bandwidth, high efficiency, polarization diversity, and miniaturization. The proposed framework integrates simulation-driven array modeling with integrated analog–digital beamforming and adaptive entity partitioning, accommodating real-world energy harvesting array non-idealities. Furthermore, an energy–information optimization factor is introduced to dynamically balance the trade-off between energy harvesting and data communication performance. Intelligent energy–information resource optimization algorithms jointly tune design parameters to maximize harvested power and signal integrity across diverse deployment scenarios. Comprehensive simulation results and comparative benchmarking demonstrate that the proposed framework consistently outperforms state-of-the-art designs in terms of gain, bandwidth, robustness, and flexibility, positioning it as an enabling technology for future energy autonomous wireless systems.]]>
<![CDATA[Assessing student perspectives on ChatGPT in higher education: a quantitative analysis ]]>
<![CDATA[Amin, Muhammad]]>;
<![CDATA[Mustaqim, Bimaa]]>;
<![CDATA[Pratama, Wegig]]>;
<![CDATA[Sibuea, Abdul Muin]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v15.i2.pp1062-1070
<![CDATA[The rapid advancement of artificial intelligence (AI) has transformed higher education, with ChatGPT increasingly used as an academic support tool. This study examines university students’ perceptions of ChatGPT in Indonesian higher education through a quantitative survey involving 56 undergraduate, master’s, and doctoral students at Universitas Negeri Medan. The survey assessed perceived ease of use, quality of responses, learning support, and ethical concerns related to ChatGPT usage. The results indicate that most students perceive ChatGPT as easy to use and helpful for understanding academic materials and improving learning efficiency. However, concerns regarding academic integrity, overreliance, and potential reductions in problem-solving skills were also identified. Significant differences in perceptions emerged across academic levels, with undergraduate students expressing higher enthusiasm, while postgraduate and doctoral students demonstrated greater caution toward ethical and pedagogical implications. These findings highlight both the opportunities and challenges of integrating generative AI into higher education. This study provides the first quantitative empirical evidence on ChatGPT perceptions in Indonesian higher education and underscores the importance of embedding AI literacy, ethical guidelines, and critical thinking strategies into university curricula to ensure responsible and effective AI adoption.]]>
<![CDATA[Attribute optimization to improve breast cancer prediction using machine learning techniques ]]>
<![CDATA[Srinivasaiah, Raghavendra]]>;
<![CDATA[Kumar Jankatti, Santosh]]>;
<![CDATA[Shravanabelagola Jinachandra, Niranjana]]>;
<![CDATA[Ramanna Lamani, Manjunath]]>;
<![CDATA[Vijaya Lakshmi, Bellam]]>;
<![CDATA[Bhelwa, Rishita]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v15.i2.pp1327-1338
<![CDATA[Breast cancer (BC) arises when cells grow out of control. It affects women more than men. Seeking cancer treatment can be both costly and time consuming, with test results spanning from a few hours to several weeks. The duration of these tests depends on the number of attributes within the dataset. This research paper endeavors to optimize the dataset attributes and find the accuracy of the optimized dataset. The primary goal is to reduce features using recursive feature elimination to minimize the time taken for the test result. This work discusses the machine learning technique and the random forest (RF) algorithm, which helps determine the parameter accuracy on the Wisconsin BC diagnostic dataset. The method achieves an accuracy of 96.49% with only eighteen attributes. It has aided the healthcare industry in finding BC in less time and improving the treatment.]]>
<![CDATA[Multimodal facial expression recognition using residual mogrifier long short-term memory ]]>
<![CDATA[Rajanna, Mamatha Kariyappa]]>;
<![CDATA[Shankar, Thejaswini]]>;
<![CDATA[Narasimhamurthy, Rashmi]]>;
<![CDATA[Annivedu Lakshmanan, Nandhini]]>;
<![CDATA[S. Ananthapadmanabharao, Hariprasad]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v15.i2.pp1566-1577
<![CDATA[Multimodal facial expression recognition aims to improve emotion analysis by integrating visual, audio, and textual cues to achieve accuracy and robustness. However, effectively recognizing facial expressions across video, text, and audio presents challenges due to inconsistencies in how emotions are expressed among these modalities. To overcome this issue, this research proposes a residual mogrifier long short-term memory (RMLSTM) model to enhance robustness in multimodal facial expression recognition. By integrating residual connections into the long short-term memory (LSTM), the model improves its ability to capture complex dependencies among various modalities, including video, text, and audio. The residual connection overcomes the vanishing gradient problem and ensures stable training with better gradient flow in deeper networks. The mogrifier mechanism refines the input features dynamically, enhancing feature interaction and alignment across modalities. The RMLSTM achieves 99.57% and 97.83% accuracy on the SAVEE and YouTube datasets, respectively, outperforming both the mel-frequency cepstral coefficients time-domain feature with iterative dilated convolutional neural network (MFCCT-1DCNN) and attention-based multi-modal popularity prediction model of short-form videos (AMPS).]]>
<![CDATA[The effects of data imbalance on fraud detection model accuracy ]]>
<![CDATA[Ruslan, Rusma Anieza]]>;
<![CDATA[Arbaiy, Nureize]]>;
<![CDATA[Lin, Pei-Chun]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v15.i2.pp1402-1408
<![CDATA[Machine learning (ML) model performance is often assessed by accuracy, but the quality and balance of data also play crucial roles. Imbalanced datasets, where the minority class has fewer samples than the majority class, can lead to biased predictions favoring the majority class. This study addresses the issue of class imbalance through resampling techniques, including random undersampling (RUS) and random oversampling (ROS), specifically applied to a fraud detection dataset. We classify the resampled datasets using random forest (RF) and gradient boosting (GB) models. Our findings indicate that the RF model, when combined with ROS, achieves an accuracy of 97.4%, surpassing the 96.1% accuracy of the GB model with RUS. This approach demonstrates the importance of addressing class imbalance to improve prediction accuracy in ML.]]>
<![CDATA[Hybrid recommender for computer aided design software ]]>
<![CDATA[Zidani, Younes]]>;
<![CDATA[Zahrou, Younes]]>;
<![CDATA[Nissabouri, Salah]]>;
<![CDATA[El Houssine Ech-Chhibat, Moulay]]>;
<![CDATA[Mansouri, Khalifa]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v15.i2.pp1931-1946
<![CDATA[Choosing the right computer-aided design (CAD) software is a complex task due to the wide variety of available options. Using user opinions and reviews may not be sufficient, which highlighting the need for a decision support system. In this paper, we develop and evaluate a hybrid recommendation program (HRP) for CAD software written in the Python programming language, combining collaborative filtering (CF) and content-based filtering (CBF) using k-nearest neighbors (KNN). CF uses user ratings to identify similar users, while CBF compares software characteristics to find similar options. In our hybrid approach, we integrate both filtering techniques with KNN to generate personalized recommendations. It will improve the relevance of software options, help users make choices (students, educators, and professionals), and encourage the adoption of tools most appropriate for every profile. We used the analytic hierarchy process (AHP) method to choose the criteria for our recommendation program. We tested the HRP on a simulated CAD dataset and found that it made recommendations much more accurately than using CF and CBF separately. Evaluation metrics like precision (0.81), recall (0.95), and F1-score (0.87) show that this hybrid approach works, making it a more reliable tool for helping people choose CAD software.]]>
<![CDATA[Structured data collection and deep learning for retinal OCT image-to-text translation: a comprehensive framework ]]>
<![CDATA[Mande, Uday]]>;
<![CDATA[Pathan, Shafi]]>;
<![CDATA[Chandre, Pankaj]]>;
<![CDATA[Mande, Sharvari]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v15.i2.pp1050-1061
<![CDATA[This paper presents a comprehensive framework for structured data collection and deep learning (DL)-based translation of retinal optical coherence tomography (OCT) images into diagnostic text. The suggested approach guarantees high-quality OCT data for model training through the use of sophisticated image processing methods like edge detection, noise suppression, and contrast improvement. The study utilizes 84,484 retinal images from the OCT dataset available on Kaggle. The research utilizes various preprocessing techniques, such as median and Gaussian filtering, along with data augmentation strategies like translation, rotation, and scaling, to mitigate class imbalances and improve model performance. The system automatically identifies and categorizes retinal diseases such as drusen, diabetic macular edema (DME), and choroidal neovascularization (CNV) by integrating feature extraction and selection with DL techniques. The research highlights the importance of effective data handling and model scalability to address the increasing need for automated diagnostic tools in ophthalmology. This framework aims to support ophthalmologists in managing the increasing incidence of diabetic retinopathy (DR) and other retinal conditions by enhancing the efficiency of retinal image analysis, thereby improving patient results through early detection and treatment.]]>
<![CDATA[YOLOv8-TMS: spatiotemporal attention networks for real-time occlusion-resilient urban traffic monitoring ]]>
<![CDATA[Kandasamy, Vidhya]]>;
<![CDATA[Taurshi, Antony]]>;
<![CDATA[M. Thiyagu, Thavittupalayam]]>;
<![CDATA[Joy RusselRaj, Catherine]]>;
<![CDATA[Archpaul, Jenefa]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v15.i2.pp1709-1718
<![CDATA[Traffic monitoring from roadside cameras benefits from fast object detection, yet real street scenes remain difficult because occlusions, small targets, and adverse weather conditions reduce visual reliability. This study presents YOLOv8 for traffic management system (TMS), which enhances YOLOv8 using hybrid attention refinement, temporal coherence modeling, and adaptive occlusion handling to improve stability in crowded frames. Experiments on the traffic management enhanced dataset from the Roboflow universe street view project use 5,805 training images and 279 testing images across five road-user categories. The model achieves 95.2% mAP@0.50 in sunny scenes and 90.0% mAP@0.50inrainyscenes, whilesustaining 50msinference time and30frames per second throughput with 8 GB graphics processing unit memory. The results support reliable deployment for near real-time traffic analytics under varying conditions.]]>
