IAES International Journal of Artificial Intelligence (IJ-AI)
Not a member yet
1769 research outputs found
Sort by
Novel preemptive intelligent artificial intelligence-model for detecting inconsistency during software testing
Get PDFThe contribution of artificial intelligence (AI)-based modelling is highly significant in automating the software testing process; thereby enhancing the cost, resources, and productivity while performing testing. Review of existing AI-models towards software testing showcases yet an open-scope for further improvement as yet the conventional AI-model suffers from various challenges especially in perspective of test case generation. Therefore, the proposed scheme presents a novel preemptive intelligent computational framework that harnesses a unique ensembled AI-model for generating and executing highly precise and optimized test-cases resulting in an outcome of adversary or inconsistencies associated with test cases. The ensembled AI-model uses both unsupervised and supervised learning approaches on publicly available outlier dataset. The benchmarked outcome exhibits supervised learning-based AI-model to offer 21% of reduced error and 1.6% of reduced processing time in contrast to unsupervised scheme while performing software testing
Enhancing e-commerce personalization with review-based adaptive feature matching: a real-time approach
Get PDFThe widespread evolution of e-commerce platforms necessitates advanced personalization techniques to enhance user experience and satisfaction. Our paper introduces the review-based adaptive feature matching (R-AFM) algorithm, an innovative approach to real-time personalization in e-commerce settings. Leveraging the rich data from user reviews and product metadata available in the Amazon product review dataset, R-AFM dynamically adapts to user preferences and behaviors through a sophisticated feature matching process. The methodology encompasses data collection, feature extraction, user preference modeling, real-time recommendation generation, and an adaptive feedback loop. By analyzing historical review data alongside real-time user interactions, R-AFM updates preference weights for product features, thereby refining the personalization mechanism. This process culminates in the generation of highly personalized product recommendations. Comparative analysis with existing personalization methods-collaborative filtering (CF), content-based filtering (CBF), hybrid recommender systems (Hybrid RS), and deep learning-based recommender systems (DL-RS)-demonstrates R-AFM's superior performance improvement varying between 2 to 8% in terms of accuracy, precision, recall, and F1-score. The algorithm's unique capability to incorporate real-time feedback significantly enhances the e-commerce personalization landscape, offering promising avenues for future research and practical application
Multilayer stacking for polycystic ovary syndrome diagnosis
Get PDFPolycystic ovary syndrome (PCOS) is a complicated hormonal condition that is experienced by women. Despite extensive research, the precise reason be hind PCOS remains unknown, and effective treatments are still lacking. Thus, early diagnosis and treatment have a significant positive impact on the health of women. Recently, there has been remarkable performance demonstrated by machine learning (ML)-based detection models for PCOS identification. They are fast and low cost compared to the traditional processes. In this work, a multi stacking PCOS detection model is proposed using K-fold cross validation. The model uses three different ML algorithms namely: na¨ıve Bayes (NB), ran dom forest (RF), and logistic regression (LR) as base classifiers and a neural network, multi-layer perception (MLP) as meta model. This approach utilizes two feature selection techniques and compares the performances on the stack ing methods. Among the two feature selection techniques, Pearson correlation approach performed better with average 98.79% accuracy, 99.17% sensitivity, 98.40% specificity, and 98.79% f1-score
The influence of sentiment analysis in enhancing early warning system model for credit risk mitigation
Get PDFOne important source of bank income is interest income from credit activities, another part of which is obtained from fee-based income. Rapid credit growth is directly proportional to an increase in potential credit risk (counterparty default). In addition to comprehensive credit assessment at the initial stage of credit initiation, banks need to monitor the condition of existing debtors. Empirically, difficulties in handling non-performing loans often occur due to delays in detection and preparation of action plans. In this case, losses due to non-performing loans can have implications for the bank's reputation and worsen its financial performance. This research aims to determine the effect of sentiment analysis (external sentiment prediction model [positive, neutral, and negative] with certain keywords) on the level of accuracy of the early warning system (EWS) model in predicting the credit quality of bank debtors in the coming months. This study found that upgrading EWS with sentiment analysis will give better accuracy levels compared to traditional EWS models. In addition, the predictive power of EWS (traditional and upgraded) is inversely proportional to the prediction period, the longer the target prediction time, and the less predictive power of the EWS model
DualVitOA: A dual vision transformer-based model for osteoarthritis grading using x-ray images
Get PDFKnee osteoarthritis (OA) is a primary factor contributing to reduced activity and physical impairment in older individuals. Early identification and treatment of knee OA can assist patients in delaying the advancement of the condition. Currently, knee OA is detected early using X-ray images and assessed based on the Kellgren-Lawrence (KL) grading system. Doctors' assessments are subjective and can vary among different doctors. The automatic knee OA grading and diagnosis can assist doctors and help doctors reduce their workload. A new novel network called dual-vision transformer (ViT) OA is proposed to automatically diagnose knee OA. The network utilizes pre-processing technologies to process the data before doing classification operations using the Dual-ViT network. The suggested network outperformed neural networks like ResNet, DenseNet, visual geometry group (VGG), inception, and ViT in terms of accuracy and mean absolute error (MAE), and achieved an accuracy of 78.4 and MAE of 0.471, demonstrating its effectiveness
Utilization of convolutional neural network in image interpretation techniques for detecting kidney disease
Get PDFThis research is conducted with deep learning for kidney stone disease detection including cysts, stones, normal, and tumors using axial computerized tomography (CT) scan images. The author uses augmentation, generative adversarial networks (GANs), original, and synthetic minority over-sampling technique (SMOTE) to classify kidney disease (cyst, stone, normal, and tumor). This study uses the public dataset nazmul0087 and primary data/data from the hospital, using convolutional neural network (CNN) models, namely augmentation, GANs, original, and SMOTE by training and testing. The results of the accuracy value of the training model (dataset nazmul0087) in the detection of kidney cysts, stones, tumors, and normal. The results of augmentation value are 99.93%, GANs 100%, original 100%, and SMOTE 99.93%. In the results of the training model, a very high accuracy value is obtained, with perfect results. The testing model's accuracy value in detecting kidney cysts, stones, tumors, and normal kidney tissue in the original dataset and hospital data. The results of augmentation value are 11.48%, GANs 17.96%, original 21.76%, and SMOTE 20.41%. In the results of the training model, the highest accuracy value is obtained in the original model. For the testing model to automatically diagnose kidney illness and obtain a high accuracy value, which can enhance patient outcomes and save health care costs, we advise using it in conjunction with the original model
Prediction of metabolic syndrome in mexicans using machine learning
Get PDFMetabolic syndrome (MetS) is a compelling public health issue in Mexico, with high prevalence rates of overweight, obesity, arterial hypertension, diabetes, high triglycerides, low high-density lipoprotein cholesterol, and high total cholesterol. Despite this, predictive models tailored for under-researched professional groups with sedentary habits are scarce. This study introduces a novel predictive model for MetS using data from the National Center for Health Statistics and a unique dataset of higher education staff. By employing and comparing machine learning algorithms such as decision trees, random forest, artificial neural networks, and adaptive boosting, the research provides new insights into gender and race-specific aspects of MetS. The data was labeled using standards from the International Diabetes Federation and the National Cholesterol Education Program Adult Treatment Panel III to create classification models, which were tested on the higher education staff dataset. Model predictions were assessed using F1-score, accuracy and area under the curve - receiver operating characteristic (AUC-ROC), with random forest, decision tree, and adaptive boosting performing best. The key predictive features identified for MetS prediction include triglycerides, glucose, high-density lipoprotein cholesterol, waist-to-height ratio, and body mass index.
Improving the performance of the fuzzy-internet of things joint system by using an efficient service deployment algorithm
Get PDFThe aim of this paper to present research proposes a quality of service (QoS)-fog service placement algorithm, which is in the context of providing better performance when there are requests for high-priority (delay-sensitive) services. Our proposed algorithm attempts to maintain the implementation of delay-sensitive services within a fog environment. Its performance was evaluated by comparing it with two placement strategies (cloud only, edge-ward), using the MobFogSim simulator. The results showed that the proposal achieved better performance than the two mentioned strategies, from two perspectives (according to the scenarios). The first is at the service level, where the algorithm was able to achieve a lower average response time and the other is at the system level, as it was able to reduce the total energy consumption by adopting a mechanism to save energy when there is a low network load
Depression detection through transformers-based emotion recognition in multivariate time series facial data
Get PDFGlobally, the prevalence of mental health disorders, particularly depression, has become a pressing issue. Early detection and intervention are vital to mitigate the profound impact of depression on individuals and society. Leveraging transformer models, renowned for their excellence in natural language processing and time series tasks, we explore their application in depression detection using multivariate time series (MTS) data from facial expressions. Transformer models excel in sequential data processing but remain relatively unexplored in facial expression analysis. This study aims to compare transformer models applied to first-order time derivative data with traditional methods. We use the distress analysis interview corpus wizard of oz (DAIC-WOZ) dataset and evaluate models with mean absolute error (MAE) and root mean squared error (RMSE) metrics. Results show that transformer models on first derivatives outperform others with an MAE of 4.42 and RMSE of 5.42. While transformer models on raw data surpass XGBoost in RMSE, they fall short of LSTM+transformer with an MAE of 5.41 and RMSE of 6.02. Preprocessing through differentiation enhances transformer models' ability to capture temporal patterns, promising improved depression detection accuracy
Spectral efficient network and resource selection model in 5G networks
Get PDFThis work addresses the challenges in modern communication networks, emphasizing the need for improved efficiency, higher data transfer rates, and reduced delays. In 5G networks, advanced resource optimization, network selection, and relaying techniques are crucial for expanding multi-cellular coverage and enhancing network performance. However, implementing these techniques in mobile environments with high interference levels increases computational demands for radio resource management (RRM). Machine learning (ML) and deep learning (DL) are proposed as solutions to enhance consumer applications, reduce communication overhead, and improve RRM. Current ML/DL methods, however, struggle with identifying key features for network selection and balancing system throughput with spectral efficiency. This paper introduces the spectral efficient network and resource selection (SENRS) model for 5G multiple input multiple output-orthogonal frequency division multiplexing (MIMO-OFDM) networks. Tested using the Stanford University Interim (SUI) channel fading model in a highway scenario, the SENRS model demonstrates superior performance compared to existing network and resource selection systems