IAES International Journal of Artificial Intelligence (IJ-AI)
Not a member yet
1769 research outputs found
Sort by
Spam social media profile detection using hybrid positive unlabelled learning
Get PDFOnline social networks (OSNs) are a communication medium of social interaction for people, where social activities, entertainment, business oriented activities, and information are exchanged. It creates an environment with worldwide connectivity where groups of individuals may discuss their interests and activities on social media platforms. Billions of people routinely interact with social content, opinion sharing, recommendations, networking, scouting, social campaigns, alerting on OSNs. The increase in popularity of OSNs creates new challenges and perspectives to the researchers of social networks, which is of interest in various fields. One of the most popular networking platforms for microblogging is X (formerly Twitter). Millions of spam accounts have inundated the X network, which could damage normal users' security and privacy. Hence, the research in this filed has become essential for enhancing real users' protection and identifying spam profiles. In this manuscript, we propose hybrid approach based on semi-supervised learning to detect the spam profiles. The proposed work is based on the positive and unlabeled (PU) learning algorithm, which learns from an unlabeled dataset and a small number of positive instances. Simulation results demonstrate that our approach outperformed existing PU learning approach by 17.39% and 17.51% improvement respectively in spam detection rate on X and Instagram datasets
Stock market liquidity: hybrid deep learning approaches for prediction
Get PDFPredicting stock market liquidity especially in emerging or frontier financial markets, such as the Casablanca stock exchange (CSE), presents significant challenges given the relative narrowness and volatility of these markets. In this paper, we conduct a comprehensive study to address the predictions accuracy gaps between five main deep learning models: convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), and two hybrid architectures, CNN-LSTM and CNN-BiLSTM. The proposed methodology focused on training and testing these models on historical data from the CSE, with precision on capturing both spatial and temporal market dynamics. The models were fine-tuned using key hyperparameters and validated on 20% of the dataset to ensure reliable results. The evaluation of performance was conducted using error metrics such as mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). The study demonstrates that the hybrid CNN-biLSTM model consistently outperformed all standalone and other hybrid models in predictive accuracy. This underscores the considerable promise of hybrid deep learning architectures for addressing the unique challenges of predicting stock market liquidity in volatile and emerging financial markets
EmoVibe: AI-driven multimodal emotion analysis for mental health via social media dashboards
Get PDFMonitoring mental health via social media often utilizes unimodal approaches, such as sentiment analysis on text or single-staged image categorization, or executes early feature fusion. However, in real-world contexts where emotions are conveyed via text, emojis, and images, unimodal approach leads to obscured decision-making pathways and overall diminished performance. To overcome these limitations, we propose EmoVibe, a hybrid multimodal AI framework for emotive analysis. EmoVibe uses attention-based late fusion strategy, where text embeddings are generated from bidirectional encoder representations from transformers (BERT) and visual features are extracted by vision transformer. Subsequently, emoticon vectors linked to avatars are processed independently. Later, these independent data features are integrated at higher levels, enhancing interpretability and performance. In contrast to early fusion methods and integrated multimodal large language models (LLMs) like CLIP, Flamingo, GPT-4V, MentaLLaMA, and domain-adapted models like EmoBERTa, EmoVibe preserves modality-specific contexts without premature fusion. This architecture saves processing cost, allowing for clearer, unambiguous rationalization and explanations. EmoVibe outperforms unimodal baselines and early fusion models, obtaining 89.7% accuracy on GoEmotions, FER, and AffectNet, compared to BERT's 87.4% and ResNet-50's 84.2%, respectively. Furthermore, a customizable, real time, privacy-aware dashboard is created, supporting physicians and end users. This technology enables scalable and proactive intervention options and fosters user self-awareness of mental health
Optimized convolution neural network with ant colony algorithm for accurate plant disease detection
Get PDFIn India, agriculture is the primary source of income for half the people. Even in situations of fast population growth, agriculture supplies nourishment for all people. To provide food for the entire population, it is advised to detect plant diseases at an early stage. Plant leaf diseases are recognized using images of the affected leaves. Deep learning (DL) research seems to offer several opportunities for increased accuracy. Ant colony optimization with convolution-neural-network (ACO-CNN), a new deep learning technique for identifying and categorizing diseases, is presented in this article. Ant colony optimization (ACO) was used to examine the efficacy of disease diagnostics in plant leaves. The convolution neural network (CNN) classifier is used to remove texture, color, and leaf arrangement geometry from the input images. The ACO-CNN model outperformed the support vector machine (SVM) and CNN models in terms of precision, recall, and accuracy. CNN's rate is 81.6% as compared to SVM's 80% accuracy level. In the “ACO-CNN” approach, the F1-score, recall, and precision have higher rates as compared to other models, and the “F1-score” has the highest rate compared with other models since the ACO-CNN model has an accuracy rate of 91.00%
Integrating machine learning and deep learning with landscape metrics for urban heat island prediction
Get PDFElevated temperatures in urban areas relative to surrounding rural areas, known as the urban heat island (UHI) effect, constitute a pressing challenge to urban sustainability, public health, and energy efficiency. With a comprehensive global dataset from NASA's Socioeconomic Data and Applications Center (SEDAC) that encompasses land surface temperature (LST) and different urban characteristics, this study investigates the UHI phenomenon. The UHI intensity was predicted using advanced machine learning models, random forest, extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), multilayer perceptron (MLP), and long short-term memory (LSTM) with attention mechanism. The LSTM with attention achieved top R2:0.9998 (day) and 0.9992 (night). Key landscape metrics include urban area size, population, and location. We analyzed spatial temporal UHI patterns to identify local factors like geometry and vegetation. These findings are critical for urban planners and policy makers to identify targeted mitigation options, including green space expansion, the use of low thermal mass, and urban climate resilience strategies. These results advance predictive modeling, supporting resilient, and sustainable cities
Enhanced object tracking with artificial bee colony, motion modeling, and deep learning
Get PDFAs a fundamental aspect of computer vision, visual object tracking supports a wide array of applications, notably in transport infrastructure and advanced industrial automation. Although correlation filter-based trackers demonstrate robust performance, they face persistent limitations including scale changes, object occlusion, boundary artifacts, and complex background interference. To address these issues, we have introduced an approach that combines artificial bee colony (ABC) optimization, deep neural architectures, and Kalman filtering techniques. Our methodology begins with reliability assessment of the tracking pipeline, proceeding to compute target confidence measures at the predicted position, followed by an adaptive update mechanism. The proposed system leverages ABC optimization for dynamic scale adaptation while employing Kalman filtering to model inter-frame target motion dynamics. Comprehensive evaluation across multiple benchmark datasets demonstrates our method's efficacy, precision, and resilience, achieving enhanced performance relative to existing state-of-the art approaches
Enhancing learning outcomes in smart education: a supervised machine learning predictive analytics model for course completion
Get PDFPredictive analytics have become increasingly capable of delivering actionable and accessible feedback to enhance teacher performance to enhance student outcomes in higher education. This study introduces a supervised machine learning predictive model designed to forecast the duration required to complete a course in a video learning environment using a dataset of 8,665 statements from 490 students from National Higher School of Art and Design at Hassan II University in Casablanca over six academic years (2019-24). This paper analyzes decision trees (DT), random forest (RF), support vector machines (SVM), gradient boosting (GB), and linear regression (LR) techniques. The CMI-5 standard and JSON format are used to automatically transfer learning activity data from the learning management system (LMS) to the learning record store (LRS). The results indicate that DT, RF, and GB achieved 100 percent predictor accuracy
Evaluation of midwifery educated mobile applications for labor guidance and a roadmap for future developers
Get PDFThe objective of the study was to review the midwifery guided mobile apps for labor advice, assessing features, functions, and content relevance. In February to March 2024, midwifery labor-guided applications were reviewed in mobile platforms such as the Google Play Store and Apple iTunes Store. We used multimodal evaluation tools, such as the mobile app rating scale (MARS), specific statements, and IQVIA ratings, to assess the quality of these applications. The study evaluated midwifery-guided applications, resulting in an average objective quality score of 3.96±0.96 out of 5. 'Safe delivery' scored the highest rating of 4.94, followed by 'Pregnancy mentor' (4.89), 'Hypno-birthing' (4.61), 'Obstetrics 6th edition' (4.68), and 'MSD manual guide to obstetrics' (4.56). Functionality received the highest score (4.16±0.865), followed by information (3.99±0.97), engagement (3.88±1.07), and aesthetics (3.82±0.28) areas. Subjective quality score was 3.6±1.18 out of 5 for an overall MARS score of 3.76±1.02. Most applications received favorable reviews, indicating good quality, and it is recommended that future app developers design applications that include comprehensive information on labor management
Multi-class stock market forecasting with deep learning models: an explainable artificial intelligence
Get PDFIn this research, we investigated the influence of different deep learning techniques on time series stock market data, especially for all Nifty50 companies in the Indian stock market. Our proposed method of stock market prediction focused on multi-class classification with explainable artificial intelligence (XAI). Our proposed model incorporates convolutional neural network (CNN) for operational feature extraction and long short-term memory (LSTM) to capture time-based dependencies. Predicted value is classified with multiclass classes-very bullish, bullish, neutral, bearish, very bearish signals for all Nifty50 stocks. The model integrates essential technical indicators to find patterns from basic price data. XAI techniques are also used to find feature contributions to model prediction. It improves the clarity of the model’s administrative procedure by figuring out how technical indicators influence stock estimates. The outcomes highlight the model’s ability to generate actionable trading signals, reinforced by performance progress metrics, contributing to more well-informed and planned venture decisions. The proposed model reveals greater performance, reaching an average accuracy of 96%, beating LightGBM at 89%, random forest at 85%, and support vector machine at 60%
Efficiency search: application of nature-inspired algorithms in artificial intelligence forecasting models
Get PDFThis study reviews how nature-inspired optimization algorithms (NIOAs) have been applied to artificial intelligence-based demand forecasting, using preferred reporting items for systematic reviews and meta-analyses (PRISMA) and clustering analysis to examine 36 selected articles. The findings reveal that NIOAs, particularly genetic algorithms and swarm intelligence methods, including their hybrids, have been frequently applied to long short-term memory (LSTM) and other backpropagation neural network models (BPNN). A key insight is the differentiated application of NIOAs depending on network depth: In shallow networks, they have been effectively used to optimize trainable parameters, whereas in deep networks, their role has focused primarily on hyperparameter optimization due to the prohibitive dimensionality of trainable weights. In all studies, NIOA-optimized models consistently outperform conventional baselines based on backpropagation. However, persistent challenges such as excessive execution times and slow convergence have led to the development of more efficient hybrid strategies and adaptive mechanisms for automated exploration-exploitation control. By mapping explored and unexplored pathways, summarizing key outcomes and techniques, and identifying promising methodologies, this review offers a practical foundation to guide future experiments and implementations involving NIOA-based optimization strategies in neural network models. As a conceptual contribution, it also proposes an innovative use of multispace optimization to address one of the most critical challenges identified: the optimization of trainable parameters in deep neural networks