Your search

Retinal Detachment (RD) is one of the major problems with retinal disorder patients. Till to date there existing no confirmatory sign or marker on retina for the early detection of RD. Therefore, patients may have sudden RD at any time of their life. Moreover, it is completely dependent upon the subjective judgement of ophthalmologist to make the final diagnostic decision on RD. To support the decision making process for the ophthalmologist, in this article we proposed RDNet, a SqueezeNet architecture based deep learning model for the early detection of RD. We used publicly available dataset of 1017 images covering rhegmatogenous RD and control group. The proposed model built on this image set achieved 97.55% sensitivity, 99.26% specificity and 98.23% accuracy in detecting RD. The proposed model outperformed the existing models for the same purpose with the highest area under the ROC curve (AUC) of 0.995. We believe our model will support the early detection of RD in clinical setup and assist the ophthalmologist in identifying RD at its early stage.

Photovoltaic systems have proven to be one of the most widely used renewable energies and the best replacement for conventional energy. Yet, their non-linear nature remains a challenge when it comes to extracting maximum power from photovoltaic modules. Therefore, in this work, a nonlinear PID controller has been used to meet the requirements of the photovoltaic system. In addition, to improve system performance and response, metaheuristic search algorithms were introduced into the tuning process of both the NPID controller and conventional PID controller parameters in order to compare them. The use of Artificial Intelligence to fine-tune the controller parameters will enable the optimum values of proportional, integral, derivative and nonlinear gains to be determined as system condition change. Finally, a comparison between the algorithms applied is conducted in terms of efficiency, rise time, settling time and overshoot as well as the overall system stability.

Stock market forecasting is an essential factor in the daily operations of many companies and individuals. However, the complex and nonlinear nature of the stock market and the unpredictable variations in factors affecting stock prices present significant challenges in accurate forecasting. To address this, we employ four model-based metaheuristic search algorithms (MHs), namely the Crow Search Algorithm (CSA), Particle Swarm Optimizer (PSO), Gray Wolf Optimizer (GWO), and Dandelion Optimizer (DO), to estimate the parameters of stock market prices models. The data utilized in our experiments are extracted from the widely recognized stock index of Standard & Poor's 500 (S&P 500), that serves as a representative benchmark for the United States stock market. Our findings demonstrate that the CSA outperforms other MHs by providing the best combination of parameters for modeling stock market prices. The optimized parameters for the CSA model yielded Variance-Account-For (VAF) values of 97.846% in the training set and 93.483% in the testing set. This suggests that CSA offers promising capabilities for enhancing the accuracy and effectiveness of stock market forecasting models. © (2024), (Research Institute of Intelligent Computer Systems). All rights reserved.

Diabetes, affecting more than 500 million individuals worldwide, is the most widespread non-communicable disease, globally. The early identification and effective management of diabetes are crucial for controlling its spread. Currently, the HbA1c test is the gold standard for the detection of diabetes with high confidence. But this is an invasive, expensive pathology test. Therefore, alternative non-invasive and inexpensive methods have been proposed in the literature for the early detection of diabetes.

Epidermolysis bullosa acquisita (EBA) represents a big challenge as a rare skin disorder, with no established markers for early detection for patients. Moreover, as a rare disease, it is extremely difficult to acquire good number of patient sample to diagnose accurately with high confidence. EBA has many biomarkers very similar to other bullosa diseases and needs specific clinical expertise to detect it using immunofluorescence microscopy. In this study, we introduce a deep learningbased method, EBAnet, that leveraged Convolutional Neural Network (CNN) based model for the detection of EBA based on Direct immunofluorescence (DIF) microscopy image. The proposed EfficientNet-based model achieved 97.3% sensitivity, 96.1% precision, and 96.7% accuracy in distinguishing EBA from other class and outperformed the existing model for the same purpose. GradCAM based class activation map also highlighted the important region of the DIF images that was focused by the proposed model leveraging the explainability of the model. We believe, EBAnet will add value in the early and accurate detection of EBA, addressing a critical need in clinical practice.

Artificial intelligence (AI) is a distinct area of computer science that enables machines to handle and interpret complex data effectively. In recent years, there has been a dramatic uptick in studies devoted to AI, with many focusing on healthcare and medical research. This article delves deep into the potential of AI in several areas of healthcare, including the diagnosis and treatment of diseases. In recent years, Machine learning (ML) and deep learning (DL) have emerged as the most widely used artificial intelligence technologies in the healthcare industry. Moreover, this research demonstrates the crucial significance of progressing AI technologies, namely generative AI and large language models (LLMs), highlighting their revolutionary influence on healthcare. Finally, we highlight upcoming innovations and offer profound insights into the significant ethical, medical, and technological challenges associated with AI in healthcare. © 2025 Nova Science Publishers, Inc. All rights reserved.

Obstructive Sleep Apnea (OSA) is a prevalent health issue affecting 10-25% of adults in the United States (US) and is associated with significant economic consequences. Machine learning methods have shown promise in improving the efficiency and accessibility of OSA diagnoses, thus reducing the need for expensive and challenging tests. A comparative analysis of Logistic Regression (LR), Support Vector Machine (SVM), Gradient Boosting (GB), Gaussian Naive Bayes (GNB), Random Forest (RF), and K-Nearest Neighbors (KNN) algorithms was conducted to predict Obstructive Sleep Apnea (OSA). To improve the predictive accuracy of these models, Random Oversampling was applied to address the imbalance in the dataset, ensuring a more equitable representation of the minority class. Patient demographics, including age, sex, height, weight, BMI, neck circumference, and gender, were employed as predictive features in the models. The RFC provided outstanding training and testing accuracies of 87% and 65%, respectively, and a Receiver Operating Characteristic (ROC) score of 87%. The GBC and SVM classifiers also demonstrated good performance on the test dataset. The results of this study show that machine learning techniques may be effectively used to diagnose OSA, with the Random Forest Classifier demonstrating the best results.

Background: In the United States, chronic obstructive pulmonary disease (COPD) is a significant cause of mortality. As far as we know, it is a chronic, inflammatory lung condition that cuts off airflow to the lungs. Many symptoms have been reported for such a disease: breathing problems, coughing, wheezing, and mucus production. Patients with COPD might be at risk, since they are more susceptible to heart disease and lung cancer. Methods: This study reviews COPD diagnosis utilizing various machine learning (ML) classifiers, such as Logistic Regression (LR), Gradient Boosting Classifier (GBC), Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), Random Forest Classifier (RFC), K-Nearest Neighbors Classifier (KNC), Decision Tree (DT), and Artificial Neural Network (ANN). These models were applied to a dataset comprising 1603 patients after being referred for a pulmonary function test. Results: The RFC has achieved superior accuracy, reaching up to 82.06% in training and 70.47% in testing. Furthermore, it achieved a maximum F score in training and testing with an ROC value of 0.0.82. Conclusions: The results obtained with the utilized ML models align with previous work in the field, with accuracies ranging from 67.81% to 82.06% in training and from 66.73% to 71.46% in testing.

Meta-heuristic optimization algorithms have become widely used due to their outstanding features, such as gradient-free mechanisms, high flexibility, and great potential for avoiding local optimal solutions. This research explored the grey wolf optimizer (GWO) to find the ideal configuration for a six-element Yagi–Uda antenna. The GWO algorithm adjusted the lengths of the antenna wires and the spacings between them. The goal was to maximize the antenna’s ability to transmit signals (throughput gain). Optimal antenna selection relies on various parameters, including gain, bandwidth, impedance matching, frequency, side-lobe levels, etc. The optimization of a six-element Yagi–Uda antenna presents a challenging engineering design problem due to its multimodal and nonlinear nature. Achieving optimal performance hinges on the intricate interplay between the lengths of the constituent elements and the spacing configurations. To this end, a multiobjective function was adopted to design this antenna. The performance of several meta-heuristic algorithms, including genetic algorithms, biogeography-based optimization, simulated annealing, and grey wolf optimizer, was compared. The GWO-based approach has performed better than its competitors. This optimized antenna design based on GWO reported a gain of 14.21 decibel. Therefore, the GWO-based method optimizes antennas that can be further investigated for other antenna design problems.

Across three online studies, we examined the relationship between the Fear of Missing Out (FoMO) and moral cognition and behavior. Study 1 (N = 283) examined whether FoMO influenced moral awareness, judgments, and recalled and predicted behavior of first-person moral violations in either higher or lower social settings. Study 2 (N = 821) examined these relationships in third-person judgments with varying agent identities in relation to the participant (agent = stranger, friend, or someone disliked). Study 3 (N = 604) examined the influence of recalling activities either engaged in or missed out on these relationships. Using the Rubin Causal Model, we created hypothetical randomized experiments from our real-world randomized experimental data with treatment conditions for lower or higher FoMO (median split), matched for relevant covariates, and compared differences in FoMO groups on moral awareness, judgments, and several other behavioral outcomes. Using a randomization-based approach, we examined these relationships with Fisher Tests and computed 95% Fisherian intervals for constant treatment effects consistent with the matched data and the hypothetical FoMO intervention. All three studies provide evidence that FoMO is robustly related to giving less severe judgments of moral violations. Moreover, those with higher FoMO were found to report a greater likelihood of committing moral violations in the past, knowing people who have committed moral violations in the past, being more likely to commit them in the future, and knowing people who are likely to commit moral violations in the future.

Establishing an optimal datacenter selection policy within the cloud environment is paramount to maximize the performance of the cloud services. Service broker policy governs the selection of datacenters for user requests. In our research, we introduce an innovative approach incorporating the genetic algorithm with service broker policy to assist cloud services in identifying the most suitable datacenters for specific userbases. The effectiveness of our proposed genetic algorithm was rigorously evaluated through experiments conducted on CloudAnalyst platform. The results clearly indicate that our proposed algorithm surpasses existing service broker policies and previous research works done in this field in terms of reducing response time and data processing time. The results analysis validates its efficacy and potential for enhancing cloud service performance and reducing the cost of overall cloud infrastructure.

This study developed a framework for predicting usability factors through an understanding of how cognitive traits relate to human interaction with a computer system. Specifically, this study examined the relationship of field-independence, spatial visualization, logical reasoning, and integrative reasoning to interaction process and outcome. The research hypothesis was tested through correlation to determine the relationships among variables. As a post hoc analysis, multiple regression analysis was used to examine the predictive power of four cognitive variables on interaction outcome. The results of the study emphasize the importance of considering cognitive variables as important predictors to human interaction process and outcome. © 2024 IEEE.

Scheduling periodic real-time tasks on multiple periodic resources is an emerging research issue in the real-time scheduling community and has drawn increased attention over the last few years. This paper studies a sub-category of the scheduling problem which focuses on scheduling a periodic task on multiple periodic resources where none of these resources have sufficient capacity to support the task. Instead of splitting the task into sub-tasks, which is not always practical in real systems, we integrate resources together to jointly support the task. First, we develop a method to integrate two fixed but arbitrary pattern periodic resources into an equivalent periodic resource. Second, for two periodic resources with unknown but fixed resource occurrence patterns, we give the lower and upper bounds of the available time provided by an integrated periodic resource within a period. Third, we present theoretical and empirical analysis on the schedulability of a non-splittable periodic task on two periodic resources and their integrated periodic resource.

In this paper, we address the resource and virtual machine instance hour minimization problem for directed-acyclic-graph based deadline constrained applications deployed on computer clouds. The allocated resources and instance hours on computer clouds must: (1) guarantee the satisfaction of a deadline constrained application's end-to-end deadline; (2) ensure that the number of virtual machine (VM) instances allocated to the application is minimized; (3) under the allocated number of VM instances, determine application execution schedule that minimizes the application's makespan; and (4) under the decided application execution schedule, determine a VM operation schedule, i.e., when a VM should be turned on or off, that minimizes total VM instance hours needed to execute the application. We first give lower and upper bounds for the number of VM instances needed to guarantee the satisfaction of a deadline constrained application's end-to-end deadline. Based on the bounds, we develop a heuristic algorithm called minimal slack time and minimal distance (MSMD) algorithm that finds the minimum number of VM instances needed to guarantee the application's deadline and schedules tasks on the allocated VM instances so that the application's makespan is minimized. Once the application execution schedule and the number of VM instances needed are determined, the proposed VM instance hour minimization (IHM) algorithm is applied to further reduce the instance hours needed by VMs to complete the application's execution. Our experimental results show that the MSMD algorithm can guarantee applications' end-to-end deadlines with less resources than the HEFT [32], MOHEFT [16], DBUS [9], QoS-base [40] and Auto-Scaling [25] heuristic scheduling algorithms in the literature. Furthermore, under allocated resources, the MSMD algorithm can, on average, reduce an application's makespan by 3.4 percent of its deadline. In addition, with the IHM algorithm we can effectively reduce the application's execution instance hours compared with when IHM is not applied.

The periodic task set assignment problem in the context of multiple processors has been studied for decades. Different heuristic approaches have been proposed, such as the Best-Fit (BF), the First-Fit (FF), and the Worst-Fit (WF) task assignment algorithms. However, when processors are not dedicated but only periodically available to the task set, whether existing approaches still provide good performance or if there is a better task assignment approach in the new context are research problems which, to our best knowledge, have not been studied by the real-time research community. In this paper, we present the Best-Harmonically-Fit (BHF) task assignment algorithm to assign periodic tasks on multiple periodic resources. By periodic resource we mean that for every fixed time interval, i.e., the period, the resource always provides the same amount of processing capacity to a given task set. Our formal analysis indicates that if a harmonic task set is also harmonic with a resource's period, the resource capacity can be fully utilized by the task set. Based on this analysis, we present the Best-Harmonically-Fit task assignment algorithm. The experimental results show that, on average, the BHF algorithm results in 53.26 , 42.54 , and 27.79 percent higher resource utilization rate than the Best-Fit Decreasing (BFD), the First-Fit Decreasing (FFD), and the Worst-Fit Decreasing (WFD) task assignment algorithms, respectively; but comparing to the optimal resource utilization rate found by exhaustive search, it is about 11.63 percent lower.

Cloud bursting is one of the key research topics in the cloud computing communities. A well designed cloud bursting module enables private clouds to automatically launch virtual machines (VMs) to public clouds when more resources are needed. One of the main challenges in developing a cloud bursting module is to decide when and where to launch a VM so that all resources are most effectively and efficiently utilized and the system performance is optimized. However, based on system operational data obtained from FermiCloud, a private cloud developed by the Fermi National Accelerator Laboratory for scientific workflows, the VM launching overhead is not a constant. It varies with physical resource utilization, such as CPU and I/O device utilizations, at the time when a VM is launched. Hence, to make judicious decisions as to when and where a VM should be launched, a VM launching overhead reference model is needed. In this paper, we first develop a VM launching overhead reference model based on operational data we have obtained on FermiCloud. Second, we apply the developed reference model on FermiCloud and compare calculated VM launching overhead values based on the model with measured overhead values on FermiCloud. Our empirical results on FermiCloud indicate that the developed reference model is accurate. We believe, with the guidance of the developed reference model, efficient resource allocation algorithms can be developed for cloud bursting process to minimize the operational cost and resource waste.

In this age of technology, building quality software is essential to competing in the business market. One of the major principles required for any quality and business software product for value fulfillment is reliability. Estimating software reliability early during the software development life cycle saves time and money as it prevents spending larger sums fixing a defective software product after deployment. The Software Reliability Growth Model (SRGM) can be used to predict the number of failures that may be encountered during the software testing process. In this paper we explore the advantages of the Grey Wolf Optimization (GWO) algorithm in estimating the SRGM’s parameters with the objective of minimizing the difference between the estimated and the actual number of failures of the software system. We evaluated three different software reliability growth models: the Exponential Model (EXPM), the Power Model (POWM) and the Delayed S-Shaped Model (DSSM). In addition, we used three different datasets to conduct an experimental study in order to show the effectiveness of our approach.

This research introduces the application of an innovative bio-inspired metaheuristic technique, termed the Crow Search Algorithm (CSA), to model a crucial industrial process - hot rolling manufacturing. Inspired by the foraging patterns of crows, the CSA algorithm has demonstrated its prowess in solving diverse optimization challenges. In the context of this study, the CSA algorithm is harnessed to fine-tune the parameters of a simulation model focused on predicting the force exerted during a hot rolling procedure. The proposed model takes into consideration a range of influential factors, including the initial temperature (Ti), width (Ws), carbon equivalent (Ce), gauge (hi), draft (i), and roll diameter (R). The findings underscore the CSA's capability to deliver an exceptional modeling performance characterized by swift convergence and high solution quality. By getting along very well with the proposed model with the CSA algorithm, a robust and efficient avenue to optimize the hot rolling process emerges, with the potential for expansion into other manufacturing domains. The computational and simulation results demonstrated that the proposed approach-based CSA outperformed different meta-heuristic search algorithms, such as the Salp Swarm Algorithm (SSA), Dandelion Optimizer (DO), Particle Swarm Optimization (PSO), Gray Wolf Optimizer (GWO), and Moth-Flame Optimization (MFO), in all test cases. The CSA has achieved the highest coefficient of determination (R2), equal to 0.97244, and the lowest mean squared error (MSE), equal to 1904.97, compared to its opponent algorithms. © 2024 IEEE.

Urban air pollution, a combination of industry, traffic, forest burning, and agriculture pollutants, significantly impacts human health, plants, and economic growth. Ozone exposure can lead to mortality, heart attacks, and lung damage, necessitating the creation of complex environmental safety regulations by forecasting ozone concentrations and associated pollutants. This study proposes a hybrid method, RFNN-GOA, combining recurrent fuzzy neural network (RFNN) and grasshopper optimization algorithm (GOA) to estimate and forecast the daily ozone (O3) in specific urban areas, specifically Kopački Rit and Osijek city in Croatia, aiming to improve air quality, human health, and ecosystems. Due to the intricate structure of atmospheric particles, modeling of O3 likely poses the biggest challenge in air pollution today. The dataset used by the proposed RFNN-GOA model for the prediction of O3 concentrations in each explored area consists of the following air pollutants, NO, NO2, CO, SO2, O3, PM10, and PM2.5; and five meteorological elements, including temperature, relative humidity, wind direction, speed, and pressure. The RFNN-GOA method optimizes membership functions’ parameters and the rule premise, demonstrating robustness and reliability compared to other identifiers and indicating its superiority over competing methods. The RFNN-GOA method demonstrated superior accuracy in Osijek city and Kopački Rit area, with variance-accounted for (VAF) values of 91.135%, 83.676%, 87.807%, 79.673% compared to the RFNN method’s corresponding values of 85.682%, 80.687%, 80.808%, 74.202% in both training and testing phases, respectively. This reveals that RFNN-GOA increased the average VAF in Osijek city and Kopački Rit area by over 5% and 8%, respectively. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

Barcode-less fruit recognition technology has revolutionized the checkout process by eliminating manual barcode scanning. This technology automatically identifies and adds fruit items to the purchase list, significantly reducing waiting times at the cash register. Faster checkouts enhance customer convenience and optimize operational efficiency for retailers. Adding barcode to fruits require using adhesives on the fruit surface that may cause health hazards. Leveraging deep learning techniques for barcode-less fruit recognition brings valuable advantages to industries, including advanced automation, enhanced accuracy, and increased efficiency. These benefits translate into improved productivity, cost reduction, and superior quality control. This study introduces a Convolutional Neural Network (CNN) designed explicitly for automatic fruit recognition, even in challenging real-world scenarios. The proposed method assists fruit sellers in accurately identifying and distinguishing between different types of fruit that may exhibit similarities. A dataset that includes 44,406 images of different fruit types is used to train and test our technique. Employing a CNN, the developed model achieves an impressive classification accuracy of 97.4% during the training phase and 88.6% during the testing phase respectively, showcasing its effectiveness in precise fruit recognition.