IAES International Journal of Artificial Intelligence (IJ-AI)
Not a member yet
1769 research outputs found
Sort by
Unmanned aircraft vehicles/unmanned aerial systems digital twinning: Data-driven lift and drag prediction for airfoil design
Get PDFThis study investigates the innovative application of neural networks algorithms in the aviation industry's mechanical design process, motivated by the pursuit of creating a more accurate and efficient method for performance prediction. Traditional approaches, such as computational fluid dynamics (CFD) simulations based on solving Navier-Stokes’s equations, demand substantial computational power and often exhibit limited accuracy, particularly when compared with complex geometries. The state-of-the-art review unveils a growing research trend advocating for data-driven methodologies to revolutionize design practices, addressing the limitations of conventional techniques. The primary objective of this study is to explore how neural network algorithms can overcome the drawbacks of CFD simulations, offering a more effective alternative for predicting the performance of airfoils. To achieve this objective, we conducted a performance analysis of airfoils using neural network algorithms. The results presented a promising avenue for a more accurate and efficient performance prediction method through digital twinning. The study highlights the advantageous features of neural network methods in unmanned aircraft vehicles (UAV) component mechanical design, showcasing their potential to outperform traditional methods and offering practical recommendations for integration into the design process
CycleGAN for day-to-night image translation: a comparative study
Get PDFComputer vision tasks often fail when applied to night images, because the models are usually trained using clear daytime images only. This creates the need to augment the data with more nighttime image for training to increase robustness. In this study, we consider day-to-night image translation using both traditional image processing approaches and deep learning models. This study employs a hybrid framework of traditional image processing followed by a CycleGANbased deep learning model for day-to-night image translation. We then conduct a comparative study on various generator architectures in our CycleGAN model. This research compares four different CycleGAN models; i.e., the orginal CycleGAN, feature pyramid network (FPN) based CycleGAN, the original U-Net vision transformer based UVCGAN, plus a modified UVCGAN with additional edge loss. The experimental results show that the orginal UVCGAN obtains an Frechet inception distance (FID) score of 16.68 and structural similarity index ´ measure (SSIM) of 0.42, leading in terms of FID. Meanwhile, FPN-CycleGAN obtains an FID score of 104.46 and SSIM score of 0.44, leading in terms of SSIM. Considering FPN-CycleGAN’s bad FID score and visual observation, we conclude that UVCGAN is more effective in generating synthetic nighttime images
User acceptance of the gender and development mobile app with a rating checklist using a modified technology acceptance model
Get PDFResource centers of gender and development (GAD) in local government use the traditional method of disseminating information about GAD awareness, such as distributing printed campaign materials and conducting gender sensitivity training (GST) on faculty and staff, students, and selected barangay communities in the Philippines. Some recipients of campaign materials are text-heavy and unappealing to read, which makes them less interested. However, faculty and students conducting research are not aware if their study is gender-responsive or if GAD is invisible. Hence, this study examines the user acceptance of the GAD app mobile application using the modified technology acceptance model (TAM) with a machine learning (ML) algorithm applied. The results of statistics and analyses from the intended users (N=100) were presented including data-driven modeling using a support vector machine (SVM) to show precise findings for the research on how this technology was used and accepted. The study’s findings show widespread acceptance among experts and users of the mobile application employing external factors like self-efficacy (SE) and specific anxiety (SA) and moderating variables such as age, sex, highest educational attainment (HEA), and knowledge in GAD implementation, which are crucial for predicting and understanding the consequences of the research made clear
Review on class imbalance techniques to strengthen model prediction
Get PDFData is a fundamental component in various fields, including science, business, health care, and technology. It is often processed, stored, and analyzed using computer systems and software applications. The importance of data lies in its ability to provide valuable insights, drive innovation, and improve decision-making processes. However, it’s essential to handle and manage data responsibly to address privacy and ethical considerations. Data mining (DM) involves discovering patterns, trends, correlations, or useful information from large datasets. Data dredging or DM and machine learning (ML) are closely related fields that both involve the analysis of data to discover patterns and make predictions. DM focuses on extracting knowledge from data; ML emphasizes the development of algorithms that can do analysis. The two fields are interconnected, and the techniques from one state of art integrated into the processes of the other. In ML the class imbalance problem occurs due to the class distribution in the training data is not equal. Imbalanced classification refers to a condition where a particular class (minority class) is under represented parallelled to another class (majority class) in a dataset. This paper furthermore emphasizes on the synthetic minority oversampling technique (SMOTE) variants employed by the researchers, and highlights the limitations the work
Depression and post traumatic stress disorder analysis with multi-modal data
Get PDFWith an increasing global population and more people living to the age when major depressive disorder (MDD) or post traumatic stress disorder (PTSD) commonly occurs, the number of those who suffer from such disorders is rising. Studies have also shown a high likelihood of comorbidity between these 2 disorders. This comorbidity can worsen symptoms, increase the risk of chronicity, and complicate treatment, significantly impacting patients’ emotional wellbeing and social and occupational functioning. There is a need to enable faster and reliable diagnosis methods, while taking into account the subjectivity of individuals and the role of behavioural cues. The proposed approach analyses the combination of audio, video and text input features (multi-modal data) of the subject to determine the severity class of MDD and PTSD. The DistilBERT transformer is used for learning and building a model with the textual modality and random forest classifiers for the audio and video modalities. An ensemble of these 3 models from 3 modalities performs better in the final classification of MDD and PTSD when compared to individual models. This work also covers a comparison of the models with different splits on the dataset. This ensembled system shows an improved accuracy of 2% to 7% for the MDD and PTSD multi class classification over the models tested on individual modalities
Synthesizing strategies and innovations in combating land degradation: a global perspective on sustainability and resilience
Get PDFThis paper presents a comprehensive examination of land degradation, a critical environmental challenge with far-reaching implications for agricultural productivity, ecosystem sustainability, and socio-economic stability worldwide. With the backdrop of escalating human population pressures and the exacerbating impact of climate change. It delves into the causes and consequences of soil erosion, desertification, salinization, and biodiversity loss, highlighting the interplay between natural processes and anthropogenic activities. Through a detailed review of literature spanning various remediation technologies, conservation practices, and policy frameworks, the paper critically assesses the effectiveness of current land management approaches, including the utilization of biosurfactants, remote sensing technologies, and agroforestry systems. Furthermore, it identifies significant research gaps and future directions, emphasizing the need for quantitative assessments, exploration of socio-economic impacts, and evaluation of restoration techniques. By offering evidence-based recommendations for policymakers and practitioners, this paper contributes to the global dialogue on sustainable land management and aims to catalyze action towards halting the advance of land degradation, ensuring food security, and preserving biodiversity for future generations. This work not only advances our understanding of land degradation challenges but also outlines a path forward for research, policy, and practice in the pursuit of environmental sustainability and resilience
An automatic social engagement measurement during human-robot interaction
Get PDFSocial engagement refers the expressions of existing interpersonal relationships during the interaction which represents the actual interesting of human in the interaction. However, social engagement measurement is a significant concern in social human-robot interaction (HRI) because of its role in understanding the interaction’s trend and adapt robot’s behavior accordingly. Hence, we achieved the two main objectives of this study. Firstly, enrichment the theoretical literature and related concepts. Secondly, proposed a robust neural network model which is multilayer perceptron (MLP) classifier to measure social engagement state during interaction. PInSoRo dataset was used for training and testing purpose. In particular, the parameters of MLP model were meticulously crafted to recognize the social engagement accurately. We evaluated the model’s performance by several metrics and the result showed an interesting accuracy reached 94.85%. Given that, it supports the robot to has adaptive and responsive behavior in real time applications which is improving HRI eventually
Voting classifier in pain points identification
Get PDFA successful app understands and addresses the needs of its users. Pain points-specific difficulties and frustrations that users experience while using an application-are crucial for understanding user expectations and improving user experience. Google Play Store reviews can be a valuable source for identifying these pain points, but this raw data requires processing to be useful for developers. This study develops a model to automatically classify reviews as either containing pain points or not. We chose the voting classifier as our primary algorithm because of its proven ability to produce models with high accuracy through combining the strengths of multiple classifiers. After evaluating 5 different classifier methods, our research shows that the optimal model combines XGradient boosting, multinomial naïve Bayes, and logistic regression-with each contributing unique strengths in text classification. This combination achieves 90% accuracy and a 90% F1-Score, outperforming previous studies that used neural networks (which achieved 80% accuracy). The model successfully identifies user frustrations from app reviews, providing developers with actionable insights to improve their applications.
Facial paralysis image analysis for stroke detection using deep ensemble transfer learning and optimization
Get PDFFacial paralysis (FP) weakens facial muscles, leading to asymmetric facial actions and complicating stroke diagnosis. Machine learning (ML) and deep learning (DL) systems have been explored for diagnosing FP, but the effectiveness of these methods is hindered by the limited size and diversity of available datasets. This study proposes a novel deep ensemble transfer learning method for accurate stroke diagnosis using facial paralysis imaging (DETLM-ASDFPI). The method leverages pre-trained models to reduce computation costs on edge devices. The framework includes data acquisition, preparation, and pre-processing, with image rescaling to standardize input dimensions. Feature extraction is performed using a deep capsule network (DCapsNet) to capture complex features. For stroke detection, an ensemble transfer learning model integrates three classifiers: gated recurrent unit (GRU), deep convolutional neural network (DCNN), and stacked sparse auto-encoder (SSAE). The hippopotamus optimization algorithm (HOA) is applied to fine-tune model parameters. The method was validated using two benchmark datasets, Massachusetts eye and ear infirmary (MEEI) and YouTube facial palsy (YFP), achieving an accuracy of 97.06%, outperforming recent approaches. This research demonstrates the effectiveness of the DETLM-ASDFPI method in accurately diagnosing strokes from FP images while addressing challenges related to dataset limitations and computational efficiency
Detection of chronic kidney disease based on ensemble approach with optimal feature selection using machine learning
Get PDFChronic kidney disease (CKD) poses a significant health risk globally, necessitating early and accurate detection to ensure timely intervention and effective treatment. This study presents an advanced ensemble machine learning (ML) approach combined with optimal feature selection to enhance the detection of CKD. Using five baseline ML classifiers like gradient boosting (GB), random forest (RF), K-nearest neighbors (KNN), support vector machine (SVM), and decision tree (DT), and utilizing grid search for hyperparameter tuning, the proposed ensemble model capitalizes on the strengths of each algorithm. Our approach was tested on a public benchmark CKD dataset from Kaggle. The experimental results demonstrate that the ensemble model consistently outperforms individual classifiers and existing methods, achieving 97.5% accuracy, precision, recall, and an F1-score of 97.4%. This superior performance underscores the ensemble model's potential as a reliable early CKD detection tool. Integrating ML into CKD diagnostics enhances accuracy. It facilitates the development of automated, scalable diagnostic tools, aiding healthcare professionals in making informed decisions and ultimately improving patient outcomes