IAES International Journal of Artificial Intelligence (IJ-AI)
Not a member yet
1769 research outputs found
Sort by
Intravenous drug administration application for pediatric patients via augmented reality
Get PDFThis research presents the development of the intravenous drug administration application for pediatric patients using augmented reality (AR) technology, with a primary focus on aiding nursing students in administering medications accurately to reduce the risk of errors. The system architecture encompasses two core components: the creation of medication preparation videos and detailed drug information, and the design of a mobile application featuring medication list display, drug dosage calculation, user satisfaction assessment, and intravenous drug information addition. The system classifies users into administrators and nursing students, allowing administrators to manage user information in the member database. the application seamlessly integrates Visual Studio Code, flutter, dart programming language, firebase database, and AR.js Studio for QR code-linked videos. Operating in four main parts, namely users, mobile application, member database, and results display, the IDA application enables users to log in, access detailed drug information, calculate dosages, and view AR-based medication preparation videos. Tested with 111 nursing students, the system demonstrated functionality, completeness, and accuracy. The Likert scale-based evaluation revealed high satisfaction levels in content, design, functionality, and benefits received, affirming the intravenous drug administration application's effectiveness in pediatric intravenous drug management through AR, offering an innovative solution for nursing education and error reduction
Early detection and classification of bone marrow changes in lumbar vertebrae using machine learning techniques
Get PDFBone marrow changes in lumbar vertebrae (BMCLVB) have emerged as a significant correlation of chronic low back pain (CLBP) severity, especially in patients with comorbid conditions like HIV, osteoporosis, and cancer. Identifying these correlations not only aids governments and health insurance providers but also facilitates early treatment for those at risk. However, challenges lurk due to the unavailability and quality of healthcare data. The collaboration between data science and artificial intelligence, particularly machine learning (ML), has propelled biomedical research forward. So far, accessing and processing hospital and clinical data remains a hurdle. In doing so it aims to provide an opportunity for early intervention and treatment. In addition, the goal of the current study was to overcome data shortcomings using advanced ML techniques to unlock complex magnetic resonance imaging (MRI) features. We believe that extending the dataset with that obtained from an Iraqi hospital will not only assist in diagnosing BMCLVB but also fill the gap between data science and healthcare. Above all, the upgrade is intended to empower biomedical research and increase the chances of successful patient treatment
Advancements in abstractive text summarization: a deep learning approach
Get PDFWith the rapid growth of data, text summarization has become vital for extracting key information efficiently. While extractive text summarization models are widely available, they often produce redundant outputs with limited capability of generating human-like summaries. Abstractive summarization, which generates new phrases and rephrases content, remains underexplored due to its complexity. This paper addresses this gap by developing an abstractive deep learning model using an encoder-decoder architecture supported with an attention mechanism. Trained on the dataset of Amazon Food Reviews, the model generates contextually rich and semantically accurate summaries. The model’s evaluation using BLEU and ROUGE metrics demonstrated promising results, with a score of 0.641 for BLEU, 0.520 for ROUGE-1, 0.345 for ROUGE-2, 0.461 for ROUGE-L and 0.428 for ROUGE-W, indicating coherence and structural integrity. This research highlights the potential of deep learning in addressing the limitations of classical methods and suggests opportunities for future advancements, such as scaling the model with larger datasets and integrating transformer-based techniques for improved summarization across diverse applications
Rooftops detection with YOLOv8 from aerial imagery and a brief review on rooftop photovoltaic potential assessment
Get PDFRecent years have seen significant advancements in the switch from fossil fuel-based energy systems to renewable energy. Decentralized solar photovoltaic (PV) is one of the most promising energy sources since there is a lot of rooftop space, it is easy to install, and the cost of the PV panels is low. The determination of rooftop locations for PV installation is crucial for energy planning. With this context, this study aimed to detect the suitable rooftops of different shapes. The dataset of 5,076 building roofs used in this study was gathered by us utilizing a drone. This study identified ten distinct roof shapes accurately, including triangle, square, penta, hexa, hepta, octa, nona, deca, gabled roof, and hipped roof, using the most recent version of you only live once (YOLO), known as YOLOv8. Recent research revealed, YOLOv8 is more accurate than earlier YOLO models which is the reason of utilizing YOLOv8. Accuracy of this work of rooftops detection is 93.6%. Also, the precision, recall, and F1-score confidence curve showed good performances too. Finally, a brief review of the most recent studies on the evaluation of rooftop PV potential was conducted to provide insight into the use of solar energy
Bridging biosciences and deep learning for revolutionary discoveries: a comprehensive review
Get PDFDeep learning (DL), a pivotal artificial intelligence (AI) innovation, has dramatically transformed biosciences, aligning with the surge in complex data volumes to foster notable progress across disciplines such as genomics, genetics, and drug discovery. DL's precision and efficiency outmatch conventional methods, propelling advancements in biomedical imaging and disease marker identification. Despite its success, DL's integration into broader bioscience areas encounters hurdles including data scarcity, interpretability challenges, computational demands, and the necessity for ethical and regulatory considerations. Overcoming these obstacles is vital for DL to achieve its transformative potential fully. This review explores into DL's expanding role in biosciences, critically examining areas ripe for DL application and highlighting underexplored opportunities. It provides an insightful analysis of the algorithms that form the backbone of DL in biosciences, offering a thorough understanding of their capabilities. Ultimately, this paper aims to equip biotechnologists and researchers with the knowledge to leverage DL effectively, thereby enhancing the analysis of complex bioscience data and contributing to the field's future advancements
Improved adaptive multi-threshold method for automatic identification of rhinosinusitis in paranasal sinus images
Get PDFRhinosinusitis, characterized by inflammation of the mucosa or mucous membrane within the paranasal sinuses, anatomical cavities situated in the facial bones, is the focus of this investigation. This study employs computed tomography (CT)-scan images comprising sagittal slices of the paranasal sinuses, acquired through a CT device featuring a Philips Ingenuity CT model MRC880 tube type, identified by tube serial number 163889, with a pixel value resolution of 0.24 mm. The primary objective of this research is to automatically identify and delineate rhizosinusitis-affected areas. This involves the application of multi-threshold values during the segmentation process, utilizing the improved adaptive multi-threshold (IAMT) segmentation method. The research dataset encompasses 380 slices of CTscans derived from 10 patients displaying indications of rhinosinusitis. Analysis of the test results reveals that the smallest observed rhinosinusitis size in this study is 0.05 cm2 on the right side, while the largest size measures 1.81 cm2 , yielding an accuracy rate of 96.66%. The magnitude of rhinosinusitis sizes serves as an indicative measure of the extent of inflammation within the paranasal sinus region, thereby suggesting a potential need for more intensive treatment interventions for the affected patients
Event detection in soccer matches through audio classification using transfer learning
Get PDFAddressing the complexities of generating sports summaries through machine learning, our research aims to bridge the gap in audio-based event detection, particularly in soccer games. We introduce an extended ResNet-50 deep learning approach for soccer audio, emphasizing key moments from large soccer content archives through the use of transfer learning. The proposed model accurately classifies soccer audio segments into two categories: i) events, representing crucial in-game occurrences and ii) no events, denoting less impactful moments. The model involves complete audio preprocessing, the implementation of proposed model using transfer learning and the classification of events. The model’s reliability is validated using the dataset soccer action dataset compilation (SADC), involves dataset creation by football fans. Comparative analysis with pre-trained models such as VGG19, DesNet121, and EfficientNetB7 demonstrates the superior performance of the extended ResNet-50 based approach. Results across different epochs reveal consistently high accuracy, precision, recall, and F1-score, emphasizing the proposed model's effectiveness in event detection through audio classification. The paper concludes that the proposed model offers a robust solution for detecting an event from audio of soccer sports providing valuable insights for fans, analysts, and content creators to identify interested moments from soccer game with low failure
Hybrid horned lizard optimization algorithm-aquila optimizer for DC motor
Get PDFThis research presents a modification of the horned lizard optimization (HLO) algorithm to optimize proportional integral derivative (PID) parameters in direct current (DC) motor control. This hybrid method is called horned lizard optimization algorithm-aquila optimizer (HLAO). The HLO algorithm models various escape tactics, including blood spraying, skin lightening or darkening, crypsis, and cellular defense systems, using mathematical techniques. HLO enhancement by modifying additional functions of aquila optimizer improves HLO performance. This research validates the performance of HLAO using performance tests on the CEC2017 benchmark function and DC motors. From the CEC2017 benchmark function simulation, it is known that HLAO's performance has promising capabilities. By simulating using 3 types of benchmark functions, HLOA has the best value. Tests on DC motors showed that the HLAO-PID method had the best integrated of time-weighted squared error (ITSE) value. The ITSE value of HLOA is 89.25 and 5.7143% better than PID and HLO-PID
Exploring the dynamics of providing cognition using a computational model of cognitive insomnia
Get PDFInsomnia is a common sleep-related neuropsychological disorder that can lead to a range of problems, including cognitive deficits, emotional distress, negative thoughts, and a sense of insufficient sleep. This study proposes a providing computational dynamic cognitive model (PCDCM) insight into providing cognitive mechanisms of insomnia and consequent cognitive deficits. Since the support providing is significantly dynamic and it includes substantial changes as demanding condition happen. From this perspective the underlying model covers integrating of both coping strategies, provision preferences and adaptation concepts. The model was found to produce realistic behavior that could clarify conditions for providing support to handle insomnia individuals, which was done by employing simulation experiments under various negative events, personality resources, altruistic attitude and personality attributes. Simulation results show that, a person with bonadaptation and either problem focused or emotion focused coping can provide different social support based on his personality resources, personality attributes, and knowledge level, whereas a person with maladaptation regardless the coping strategies cannot provide any type of social support. Moreover, person with close tie tends to provide instrumental, emotional, and companionship support than from weak tie. Finally, a mathematical analysis was used to examine the possible equilibria of the model.
Per capita expenditure prediction using model stacking based on satellite imagery
Get PDFOne of the indicators for measuring poverty is per capita expenditure. However, collecting timely and reliable per capita expenditure data is quite challenging and expensive, as it requires collecting detailed household data directly. One way to deal with this issue is to use satellite image data processed by machine learning methods. This research proposes a method to predict the per capita expenditure of regencies or cities in Indonesia based on satellite imagery using machine learning techniques, such as k-nearest neighbors (KNN), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM). The predictions are stacked to predict per capita expenditure using least absolute shrinkage and selection operator (LASSO) regression as the meta-learner. The model is trained on Google-Earth-based satellite imagery of Java Island, Indonesia, which provides more update field conditions compared to data collected from Statistics Indonesia (BPS). The research found that the stacked model outperforms the individual methods. However, the R2 criterion of the stacked method is comparable to that of RF, which is slightly higher than the others