Your search

The structure of blood vessels in the retina is a crucial factor in identifying and forecasting various eye diseases like cardiovascular diseases, diabetes, and other diseases. Therefore, detecting the structure of blood vessels from retinal fundus images is a critical field of research in healthcare. This study employed a novel deep learning model to segment vessels for different diseases, including Glaucoma, Diabetic Retinopathy (DR), and Age-related Macular Degeneration (AMD). We considered multiple transfer learning-based models and discovered that the ResNet-based U-Net architecture was the most effective for vessel segmentation, achieving the highest Dice Score above 84% for disease-agnostic, and 82%-84% for disease-specific conditions. We believe the proposed methodology will help to advance retinal vessel segmentation process and enhance the screening process of diseases based on retinal fundus images in clinical settings of Qatar Biobank as well as other biobanks across the globe. © 2023 IEEE.

Obstructive sleep apnea (OSA) is a prevalent sleep disorder that affects approximately 3–7% of males and 2–5% of females. In the United States alone, 50–70 million adults suffer from various sleep disorders. OSA is characterized by recurrent episodes of breathing cessation during sleep, thereby leading to adverse effects such as daytime sleepiness, cognitive impairment, and reduced concentration. It also contributes to an increased risk of cardiovascular conditions and adversely impacts patient overall quality of life. As a result, numerous researchers have focused on developing automated detection models to identify OSA and address these limitations effectively and accurately. This study explored the potential benefits of utilizing machine learning methods based on demographic information for diagnosing the OSA syndrome. We gathered a comprehensive dataset from the Torr Sleep Center in Corpus Christi, Texas, USA. The dataset comprises 31 features, including demographic characteristics such as race, age, sex, BMI, Epworth score, M. Friedman tongue position, snoring, and more. We devised a novel process encompassing pre-processing, data grouping, feature selection, and machine learning classification methods to achieve the research objectives. The classification methods employed in this study encompass decision tree (DT), naive Bayes (NB), k-nearest neighbor (kNN), support vector machine (SVM), linear discriminant analysis (LDA), logistic regression (LR), and subspace discriminant (Ensemble) classifiers. Through rigorous experimentation, the results indicated the superior performance of the optimized kNN and SVM classifiers for accurately classifying sleep apnea. Moreover, significant enhancements in model accuracy were observed when utilizing the selected demographic variables and employing data grouping techniques. For instance, the accuracy percentage demonstrated an approximate improvement of 4.5%, 5%, and 10% with the feature selection approach when applied to the grouped data of Caucasians, females, and individuals aged 50 or below, respectively. Furthermore, a comparison with prior studies confirmed that effective data grouping and proper feature selection yielded superior performance in OSA detection when combined with an appropriate classification method. Overall, the findings of this research highlight the importance of leveraging demographic information, employing proper feature selection techniques, and utilizing optimized classification models for accurate and efficient OSA diagnosis.

More than half a billion people worldwide are affected by diabetes, which is a prevalent non-communicable disease that can lead to critical health conditions, including vision loss. Diabetic Macular Edema (DME) is a primary cause of vision impairment and can eventually lead to blindness in diabetic patients. Early detection of DME and proper health management are crucial to controlling the disease. Retinal image-based AI-enabled diabetes diagnosis has gained significant attention as a non-invasive, fast, and reasonably accurate method for diagnosing DME. To make this technology accessible to underserved communities or areas lacking proper clinical facilities, a mobile application-based solution could have a significant impact. In this article, we describe how we transformed our previously published AI-enabled model into an Android-based mobile application, which is part of a two-phase research study. In the first phase, we developed a deep learning-based model that predicts DME grading using retinal images. In the second phase, we built a mobile application DMEgrader to make our model accessible via a mobile device. To the best of our knowledge, this is the first article to demonstrate necessary steps and code snippets to support developers in transforming deep learning models into Android based mobile applications for DME grading prediction. © 2023 IEEE.

In this paper, we focus on improving the age estimation accuracy on smartphones. Estimating a smartphone user’s age has several applications such as protecting our children online by filtering age-inappropriate contents, providing a customized e-commerce experience, etc. However, accuracy of the the state-of-the-art age estimation techniques that use touch behavior on smartphones is still limited because of the lack of sufficient amount of training data. We perform rigorous experiments using zoom gestures on smartphones and demonstrate that increasing the amount of training data can significantly improve the age estimation accuracy. Based on the findings in this study, we recommend creating a large touch dynamics-based age estimation data set so that more accurate age estimation models can be built and in turn, can be used more confidently.

Over recent decades, research in Artificial Intelligence (AI) has developed a broad range of approaches and methods that can be utilized or adapted to address complex optimization problems. As real-world problems get increasingly complicated, this requires an effective optimization method. Various meta-heuristic algorithms have been developed and applied in the optimization domain. This paper used and ameliorated a promising meta-heuristic approach named Crow Search Algorithm (CSA) to address numerical optimization problems. Although CSA can efficiently optimize many problems, it needs more searchability and early convergence. Its positioning updating process was improved by supporting two adaptive parameters: flight length (fl) and awareness probability (AP) to tackle these curbs. This is to manage the exploration and exploitation conducts of CSA in the search space. This process takes advantage of the randomization of crows in CSA and the adoption of well-known growth functions. These functions were recognized as exponential, power, and S-shaped functions to develop three different improved versions of CSA, referred to as Exponential CSA (ECSA), Power CSA (PCSA), and S-shaped CSA (SCSA). In each of these variants, two different functions were used to amend the values of fl and AP. A new dominant parameter was added to the positioning updating process of these algorithms to enhance exploration and exploitation behaviors further. The reliability of the proposed algorithms was evaluated on 67 benchmark functions, and their performance was quantified using relevant assessment criteria. The functionality of these algorithms was illustrated by tackling four engineering design problems. A comparative study was made to explore the efficacy of the proposed algorithms over the standard one and other methods. Overall results showed that ECSA, PCSA, and SCSA have convincing merits with superior performance compared to the others.

This paper introduces an enhanced version of the Capuchin Search Algorithm (CapSA) called ECapSA. CapSA draws inspiration from the collective intelligence of Capuchin monkeys and has shown success in solving real-world problems. However, it may encounter challenges handling complex optimization tasks, such as premature convergence or being trapped in local optima. ECapSA employs a local escaping mechanism operating the abandonment limit concept to exploit potential solutions and introduce diversification trends. Additionally, the ECapSA algorithm is improved by integrating the principles of the cooperative island model, resulting in the iECapSA. This modification enables better management of population diversity and a more optimal balance between exploration and exploitation. The efficiency of iECapSA is validated through a series of experiments, including the IEEE-CEC2014 benchmark functions and training the feedforward neural network (FNN) on seven biomedical datasets. The performance of iECapSA is compared to other metaheuristic techniques, namely differential evolution (DE), sine cosine algorithm (SCA), and whale optimization algorithm (WOA). The results of the comparative study demonstrate that iECapSA is a strong contender and surpasses other training algorithms in most datasets, particularly in terms of its ability to avoid local optima and its improved convergence speed.

In this study, we conducted experiments to model the temperature of two manufacturing processes using various metaheuristic search algorithms. The two processes adopted were the P05 horny steel tool and the AISI304 stainless steel castings machines. Our approach involves building a data-driven model, as traditional search methods for modeling manufac-turing problems often need help finding the global optimum when faced with a complex objective function and numerous decision variables. Bio-inspired metaheuristic search algorithms have shown promising performance in handling multi-model optimization functions, and efficiently exploring the search space to attain more global results. We applied several metaheuristic search algorithms to find the optimal tuning parameters of a temperature-based model. The results from the case studies demonstrate that Particle Swarm Optimization (PSO) provided the best performance in tuning model parameters, resulting in minimum modeling error.

Sleep apnea is a sleeping disorder affecting more than 20 % of all American adults, associated with intermittent air passageway obstruction during sleep. This results in intermittent hypoxia, sympathetic activation, and an interruption of sleep with various health consequences. The diagnosis of sleep apnea traditionally involves the performance of overnight polysomnography, where oxygen, heart rate, and breathing, among other physiologic variables, are continuously monitored during sleep at a sleep center. However, these sleep studies are expensive and impose access issues, given the number of patients who need to be diagnosed. There is hence utility in having an effective triage system to screen for OSA to utilize polysomnography better. In this study, we plan to explore using several machine learning algorithms to utilize pre-screening symptoms to diagnose obstructive sleep apnea (OSA). Per our experimental results, it was found that Decision Tree Classifier (DTC) and Random Forest (RF) provided the highest classification accuracies compared to other algorithms such as Logistic Regression (LR), Support Vector Machines (SVM), Gradient Boosting Classifier (GBC), Gaussian Naive Bayes (GNB), K Neighbors Classifier (KNC), and Artificial Neural Networks (ANN).

Winning football matches is the major goal of all football clubs in the world. Football being the most popular game in the world, many studies have been conducted to analyze and predict match winners based on players’ physical and technical performance. In this study, we analyzed the matches from the professional football league of Qatar Stars League (QSL) covering the matches held in the last ten seasons. We incorporated the highest number of professional matches from the last ten seasons covering from 2011 up to 2022 and proposed SoccerNet, a Gated Recurrent Unit (GRU)-based deep learning-based model to predict match winners with over 80% accuracy. We considered match- and player-related information captured by STATS platform in a time slot of 15 minutes. Then we analyzed players’ performance at different positions on the field at different stages of the match. Our results indicated that in QSL, the defenders’ role in matches is more dominant than midfielders and forwarders. Moreover, our analysis suggests that the last 15–30 minutes of match segments of the matches from QSL have a more significant impact on the match result than other match segments. To the best of our knowledge, the proposed model is the first DL-based model in predicting match winners from any professional football leagues in the Middle East and North Africa (MENA) region. We believe the results will support the coaching staff and team management for QSL in designing game strategies and improve the overall quality of performance of the players.

In modern-day computing, cloud services are widely used in every aspect of life. So, user satisfaction depends on the effectiveness and efficiency of cloud services. Service broker policy of the cloud maintains the effectiveness and efficiency of cloud services. Service broker policy provides the rules and norms based on which a data center is selected for a userbase request. This paper proposes a genetic algorithm-based service broker policy that provides the optimal sequence of data centers for different userbases based on their requirements. This research aims to find an optimal data center for userbases that can achieve user satisfaction by minimizing the cloud service's response time and data processing time. We have experimented with our proposed genetic algorithm-based service broker policy in the CloudAnalyst platform based on different real-world scenarios. Simulation results indicate that our proposed genetic algorithm outperforms existing traditional algorithms. © 2023 IEEE.

Monitoring of electrical distribution grids requires the joint processing of electrical measurements from different grid locations. Such type of processing is influenced by inaccuracies in measurement data originating from measurement errors, non-ideal clocks in measurement devices, and from time averaging of measurands as part of the data collection process. This paper introduces an approach to assess the impact of these three different measurement artifacts in realistic measurement scenarios of electrical distribution grids. A case study of power loss calculation in a real-life medium-voltage grid is presented, covering both technical loss obtained from current measurement and total loss obtained from power measurements. The results show that total loss in general is more robust to aggregation of power measurements over longer measurement intervals, while it is more sensitive to measurement errors and clock offsets. The results of the study are important for quantifying the trustworthiness of the obtained loss values and for the future enhancement of the measurement data collection process. © 2023 ACM.

The optical disc in the human retina can reveal important information about a person's health and well-being. We propose a deep learning-based approach to automatically identify the region in human retinal images that corresponds to the optical disc. We formulated the task as an image segmentation problem that leverages multiple public-domain datasets of human retinal fundus images. Using an attention-based residual U-Net, we showed that the optical disc in a human retina image can be detected with more than 99% pixel-level accuracy and around 95% in Matthew's Correlation Coefficient. A comparison with variants of UNet with different encoder CNN architectures ascertains the superiority of the proposed approach across multiple metrics.

In this work, we propose a multi-task learning-based approach towards the localization of optic disc and fovea from human retinal fundus images using a deep learning-based approach. Formulating the task as an image-based regression problem, we propose a Densenet121-based architecture through an extensive set of experiments with a variety of CNN architectures. Our proposed approach achieved an average mean absolute error of only 13pixels (0.04%), mean squared error of 11 pixels (0.005%), and a root mean square error of only 0.02 (13%) on the IDRiD dataset.

Fingerprinting-based indoor positioning systems require a significant amount of time to set up due to the need for prior, offline signal map creation. We propose a mobile phone-based indoor positioning system that can be set up in a short amount of time in any environment with existing Wi-Fi infrastructure. We introduce interpolation into a fingerprinting-based system to reduce the number of reference points needed, leading to a reduction in signal map creation time. The proposed interpolation method is used in conjunction with a particle filter algorithm to provide an accuracy level comparable to the state-of-the-art. We created signal maps at three separate locations using a 100%, 50%, 20%, and 10% scan coverage in order to evaluate the effectiveness of our interpolation on the localization error on a lower scan percentage. We evaluated our signal maps before and after interpolation using 16 tests which included both motion and stationary tests, as well as tests taken 2 and 3 weeks after the initial data gathering. We show that our interpolation method is able to reduce the effects of a dimensional mismatch between signal map reference point vectors and a test sample vector, as well as reduce the effects of signal map aging. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

The earth’s population is growing at a rapid rate, while the availability of water resources remains limited. Water is required for various purposes, including drinking, agriculture, industry, recreation, and development. Accurate forecasting of river flows can have a significant economic impact, particularly in agricultural water management and planning during water resource scarcity. Developing precise river flow forecasting models can greatly improve the management of water resources in many countries. In this study, we propose a two-phase model for predicting the flow of the Blackwater river located in the South Central United States. In the first phase, we use Multigene Symbolic Regression Genetic Programming (MG-GP) to develop a mathematical model. In the second phase, Particle Swarm Optimization (PSO) is employed to fine-tune the model parameters. Fine-tuning the MG-GP parameters improves the prediction accuracy of the model. The newly fine-tuned model exhibits 96% and 94% accuracy in training and testing cases, respectively © 2023, International Journal of Advanced Computer Science and Applications.All Rights Reserved.

The spread of COVID-19 has thrown the world into a panic. We are constantly learning more about the virus every day, from how it spreads to who is more susceptible to becoming infected by different variants. Those with underlying respiratory conditions and other immunocompromised individuals need to be extra cautious regarding the virus. Many researchers have created COVID-19 trackers to detect the spread of COVID-19 around the world and show hot spots where COVID-19 cases are more prevalent. Previous work lacks the consideration of comorbidity as a factor of death rate. This work aims to create an agent-based model to predict comorbidity death rate caused by a health condition in addition to COVID-19. The model is evaluated using the symmetric mean absolute percentage error metric and proved to be very efficient.

High-Throughput DNA and RNA sequencing are revolutionizing precision oncology, enabling personalized therapies such as cancer vaccines designed to target tumor-specific neoepitopes generated by somatic mutations expressed in cancer cells. Identification of these neoepitopes from next-generation sequencing data of clinical samples remains challenging and requires the use of complex bioinformatics pipelines. In this paper, we present GeNeo, a bioinformatics toolbox for genomics-guided neoepitope prediction. GeNeo includes a comprehensive set of tools for somatic variant calling and filtering, variant validation, and neoepitope prediction and filtering. For ease of use, GeNeo tools can be accessed via web-based interfaces deployed on a Galaxy portal publicly accessible at https://neo.engr.uconn.edu/. A virtual machine image for running GeNeo locally is also available to academic users upon request. © Copyright 2023, Mary Ann Liebert, Inc., publishers 2023.

Subcellular localization of messenger RNA (mRNAs) plays a pivotal role in the regulation of gene expression, cell migration as well as in cellular adaptation. Experiment techniques for pinpointing the subcellular localization of mRNAs are laborious, time-consuming and expensive. Therefore, in silico approaches for this purpose are attaining great attention in the RNA community.