Showing papers by "University of Bridgeport published in 2020"

Stages-Based ECG Signal Analysis From Traditional Signal Processing to Machine Learning Approaches: A Survey

Abstract: Electrocardiogram (ECG) gives essential information about different cardiac conditions of the human heart. Its analysis has been the main objective among the research community to detect and prevent life threatening cardiac circumstances. Traditional signal processing methods, machine learning and its subbranches, such as deep learning, are popular techniques for analyzing and classifying the ECG signal and mainly to develop applications for early detection and treatment of cardiac conditions and arrhythmias. A detailed literature survey regarding ECG signal analysis is presented in this article. We first introduce a stages-based model for ECG signal analysis where a survey of ECG analysis related work is then presented in the form of this stage-based process model. The model describes both traditional time/frequency-domain and advanced machine learning techniques reported in the published literature at every stage of analysis, starting from ECG data acquisition to its classification for both simulations and real-time monitoring systems. We present a comprehensive literature review of real-time ECG signal acquisition, prerecorded clinical ECG data, ECG signal processing and denoising, detection of ECG fiducial points based on feature engineering and ECG signal classification along with comparative discussions among the reviewed studies. This study also presents a detailed literature review of ECG signal analysis and feature engineering for ECG-based body sensor networks in portable and wearable ECG devices for real-time cardiac status monitoring. Additionally, challenges and limitations are discussed and tools for research in this field as well as suggestions for future work are outlined.

Smartphone-Based Self-Testing of COVID-19 Using Breathing Sounds.

Abstract: Telemedicine could be a key to control the world-wide disruptive and spreading novel coronavirus disease (COVID-19) pandemic. The COVID-19 virus directly targets the lungs, leading to pneumonia-like symptoms and shortness of breath with life-threatening consequences. Despite the fact that self-quarantine and social distancing are indispensable during the pandemic, the procedure for testing COVID-19 contraction is conventionally available through nasal swabs, saliva test kits, and blood work at healthcare settings. Therefore, devising personalized self-testing kits for COVID-19 virus and other similar viruses is heavily admired. Many e-health initiatives have been made possible by the advent of smartphones with embedded software, hardware, high-performance computing, and connectivity capabilities. A careful review of breathing sounds and their implications in identifying breathing complications suggests that the breathing sounds of COVID-19 contracted users may reveal certain acoustic signal patterns, which is worth investigating. To this end, acquiring respiratory data solely from breathing sounds fed to the smartphone's microphone strikes as a very appealing resolution. The acquired breathing sounds can be analyzed using advanced signal processing and analysis in tandem with new deep/machine learning and pattern recognition techniques to separate the breathing phases, estimate the lung volume, oxygenation, and to further classify the breathing data input into healthy or unhealthy cases. The ideas presented have the potential to be deployed as self-test breathing monitoring apps for the ongoing global COVID-19 pandemic, where users can check their breathing sound pattern frequently through the app.

Trade-in-to-upgrade as a marketing strategy in disassembly-to-order systems at the edge of blockchain technology

Abstract: Growing environmental awareness and widening extended producer responsibility have heightened the need for economically, environmentally, and socially sustainable business strategies levered by dig...

Variations in Variational Autoencoders - A Comparative Evaluation

Abstract: Variational Auto-Encoders (VAEs) are deep latent space generative models which have been immensely successful in many applications such as image generation, image captioning, protein design, mutation prediction, and language models among others. The fundamental idea in VAEs is to learn the distribution of data in such a way that new meaningful data can be generated from the encoded distribution. This concept has led to tremendous research and variations in the design of VAEs in the last few years creating a field of its own, referred to as unsupervised representation learning. This paper provides a much-needed comprehensive evaluation of the variations of the VAEs based on their end goals and resulting architectures. It further provides intuition as well as mathematical formulation and quantitative results of each popular variation, presents a concise comparison of these variations, and concludes with challenges and future opportunities for research in VAEs.

Graphene Quantum Dot Oxidation Governs Noncovalent Biopolymer Adsorption

Abstract: Graphene quantum dots (GQDs) are an allotrope of carbon with a planar surface amenable to functionalization and nanoscale dimensions that confer photoluminescence. Collectively, these properties render GQDs an advantageous platform for nanobiotechnology applications, including optical biosensing and delivery. Towards this end, noncovalent functionalization offers a route to reversibly modify and preserve the pristine GQD substrate, however, a clear paradigm has yet to be realized. Herein, we demonstrate the feasibility of noncovalent polymer adsorption to GQD surfaces, with a specific focus on single-stranded DNA (ssDNA). We study how GQD oxidation level affects the propensity for polymer adsorption by synthesizing and characterizing four types of GQD substrates ranging ~60-fold in oxidation level, then investigating noncovalent polymer association to these substrates. Adsorption of ssDNA quenches intrinsic GQD fluorescence by 31.5% for low-oxidation GQDs and enables aqueous dispersion of otherwise insoluble no-oxidation GQDs. ssDNA-GQD complexation is confirmed by atomic force microscopy, by inducing ssDNA desorption, and with molecular dynamics simulations. ssDNA is determined to adsorb strongly to no-oxidation GQDs, weakly to low-oxidation GQDs, and not at all for heavily oxidized GQDs. Finally, we reveal the generality of the adsorption platform and assess how the GQD system is tunable by modifying polymer sequence and type.

An Intelligent Multiattribute Group Decision-Making Approach With Preference Elicitation for Performance Evaluation

Abstract: The concept of efficiency has always been and will continue to be important for competitive business environments where limited resources exist. Owing to the growing complexity of organizations and economy in general, this trend is expected to continue to remain a high priority for organizations. Continuous performance evaluations that utilize both qualitative and quantitative information play a significant role in sustaining efficient and effective business processes. Therefore, the literature offers a wide range of performance evaluation methodologies to assess the operational efficiency in various industries. Majority of these models, however, focus solely on quantitative criteria, avoiding the interrelations and dependencies between qualitative and quantitative measurements. Furthermore, these methodologies tend to utilize discrete and contemporary information eliminating historical performance data. With these motivations, this paper proposes an integrated approach combining fuzzy decision-making trial and evaluation laboratory (DEMATEL), analytic network process (ANP), and artificial neural network (ANN) methodologies for performance evaluation. In the proposed model, DEMATEL and ANP methodologies are utilized in a group decision-making concept to obtain priorities of the evaluation criteria. Following this, an ANN model is designed and trained with historical performance data collected from the organization and the results of the fuzzy DEMATEL-ANP model. The outcomes include the relational data among the criteria and alternatives used in the model in addition to their relative rankings. A food industry case study is presented to demonstrate the steps of the proposed model.

GNSS-Based Attitude Determination Techniques—A Comprehensive Literature Survey

Abstract: GNSS-based Attitude Determination (AD) of a mobile object using the readings of the Global Navigation Satellite Systems (GNSS) is an active area of research. Numerous attitude determination methods have been developed lately by making use of various sensors. However, the last two decades have witnessed an accelerated growth in research related to GNSS-based navigational equipment as a reliable and competitive device for determining the attitude of any outdoor moving object using data demodulated from GNSS signals. Because of constantly increasing number of GNSS-based AD methods, algorithms, and techniques, introduced in scientific papers worldwide, the problem of choosing an appropriate approach, that is optimal for the given application, operational environment, and limited financial funding becomes quite a challenging task. The work presents an extensive literature survey of the methods mentioned above which are classified in many different categories. The main aim of this survey is to help researchers and developers in the field of GNSS applications to understand pros and cons of the current state of the art methods and their computational efficiency, the scope of use and accuracy of the angular determination.

Predictive analysis of electronic waste for reverse logistics operations: a comparison of improved univariate grey models

Abstract: Growing rates of innovation and consumer demand resulted in rapid accumulation of waste of electrical and electronic equipment or electronic waste (e-waste). In order to build and sustain green cities, efficient management of e-waste rises as a viable response to this accumulation. Accurate e-waste predictions that municipalities can utilize to build appropriate reverse logistics infrastructures gain significance as collecting, recycling and disposing the e-waste become more complex and unpredictable. In line with its significance, the related literature presents several methodologies focusing on e-waste generation forecasting. Among these methodologies, grey modeling approach has aroused interest due to its ability to present meaningful results with small-sized or limited data. In order to improve the overall success rate of the approach, several grey modeling-based forecasting techniques have been proposed throughout the past years. The performance of these models, however, profoundly leans on the parameters used with no established consensus regarding the suitable criteria for better accuracy. To address this issue and to provide a guideline for academicians and practitioners, this paper presents a comparative analysis of most utilized grey modeling methods in the literature improved by particle swarm optimization. A case study employing e-waste data from Washington State is provided to demonstrate the comparative analysis proposed in the study.

Transforming Digital Employee Experience with Artificial Intelligence

Abstract: Employee expectations are changing significantly due to the increased digitalization and remote work in the last couple of years. This study emphasizes the growing role of Artificial Intelligence (AI) in Human Resources (HR) to design enhanced digital employee experience. A set of popular AI applications such as chatbots and virtual assistants in recruitment, career development, and employee engagement are provided along with their definitions. Considerations regarding their organizational implementation, including related concerns and potential benefits, are listed.

Correlates of sleep quality and excessive daytime sleepiness in people with opioid use disorder receiving methadone treatment.

Abstract: The aim of this study was to evaluate the prevalence and clinical correlates of impaired sleep quality and excessive daytime sleepiness among patients receiving methadone for opioid use disorder (OUD) Patients receiving methadone (n = 164) completed surveys assessing sleep quality (Pittsburgh Sleep Quality Index [PSQI]), daytime sleepiness (Epworth Sleepiness Scale [ESS]), and related comorbidities We used bivariate and multivariable linear regression models to evaluate correlates of sleep quality and daytime sleepiness Ninety percent of patients had poor sleep quality (PSQI >5), and the mean PSQI was high (110 ±4) Forty-six percent reported excessive daytime sleepiness (ESS > 10) In multivariable analyses, higher PSQI (worse sleep quality) was significantly associated with pain interference (coefficient = 040; 95% CI = 018–062; β = 031), somatization (coefficient = 22; 95% CI = 075–36; β = 026), and negatively associated with employment (coefficient = − 26; 95% CI = − 49 to − 019; β = − 017) Greater sleepiness was significantly associated with body mass index (coefficient = 032; 95% CI = 018–046; β = 033), and there was a non-significant association between sleepiness and current chronic pain (coefficient = 16; 95% CI = 026–35; β = 013; p value = 009) Poor sleep quality and excessive daytime sleepiness are common in patients receiving methadone for OUD Chronic pain, somatization, employment status, and obesity are potentially modifiable risk factors for sleep problems for individuals maintained on methadone People with OUD receiving methadone should be routinely and promptly evaluated and treated for sleep disorders

Sustainable smartphone-based healthcare systems: A systems engineering approach to assess the efficacy of respiratory monitoring apps

Abstract: Recent technological developments along with advances in smart healthcare have been rapidly changing the healthcare industry and improving outcomes for patients. To ensure reliable smartphone-based healthcare interfaces with high levels of efficacy, a system dynamics model with sustainability indicators is proposed. The focus of this paper is smartphone-based breathing monitoring systems that could possibly use breathing sounds as the data acquisition input. This can especially be useful for the self-testing procedure of the ongoing global COVID-19 crisis in which the lungs are attacked and breathing is affected. The method of investigation is based on a systems engineering approach using system dynamics modeling. In this paper, first, a causal model for a smartphone-based respiratory function monitoring is introduced. Then, a systems thinking approach is applied to propose a system dynamics model of the smartphone-based respiratory function monitoring system. The system dynamics model investigates the level of efficacy and sustainability of the system by studying the behavior of various factors of the system including patient wellbeing and care, cost, convenience, user friendliness, in addition to other embedded software and hardware breathing monitoring system design and performance metrics (e.g., accuracy, real-time response, etc.). The sustainability level is also studied through introducing various indicators that directly relate to the three pillars of sustainability. Various scenarios have been applied and tested on the proposed model. The results depict the dynamics of the model for the efficacy and sustainability of smartphone-based breathing monitoring systems. The proposed ideas provide a clear insight to envision sustainable and effective smartphone-based healthcare monitoring systems.

Enhanced Grey Risk Assessment Model for Support of Cloud Service Provider

Abstract: The cloud computing environment provides easy-to-access service for private and confidential data. However, there are many threats to the leakage of private data. This paper focuses on investigating the vulnerabilities of cloud service providers (CSPs) from three risk aspects: management risks, law risks, and technology risks. Additionally, this paper presents a risk assessment model that is based on grey system theory (GST), defines indicators for assessment, and fully utilizes the analytic hierarchy process (AHP). Furthermore, we use the GST to predict the risk values by using the MATLAB platform. The GST determines the bottom evaluation sequence, while the AHP calculates the index weights. Based on the GST and the AHP, layer-based assessment values are determined for the bottom evaluation sequence and the index weights. The combination of AHP and GST aims to obtain systematic and structured well-defined procedures that are based on step-by-step processes. The AHP and GST methods are applied successfully to handle any risk assessment problem of the CSP. Furthermore, substantial challenges are encountered in determining the CSP's response time and identifying the most suitable solution out of a specified series of solutions. This issue has been handled using two additive features: the response time and the grey incidence. The final risk values are calculated and can be used for prediction by utilizing the enhanced grey model (EGM) (1,1), which reduces the prediction error by providing direct forecast to avoid the iterative prediction shortcoming of standard GM (1,1). Thus, EGM (1,1) helps maintain the reliability on a larger scale despite utilizing more prediction periods. Based on the experimental results, we evaluate the validity, accuracy, and response time of the proposed approach. The simulation experiments were conducted to validate the suitability of the proposed model. The simulation results demonstrate that our risk assessment model contributes to reducing deviation to support CSPs with the three adopted models.

Progress in the Mechanism and Clinical Application of Cilostazol

Abstract: Cilostazol is a unique platelet inhibitor that has been used clinically for more than 20 years. As a phosphodiesterase type III inhibitor, cilostazol is capable of reversible inhibition of platelet aggregation and vasodilation, has antiproliferative effects, and is widely used in the treatment of peripheral arterial disease, cerebrovascular disease, percutaneous coronary intervention, etc. This article briefly reviews the pharmacological mechanisms and clinical application of cilostazol.

Partial Observer Decision Process Model for Crane-Robot Action

Abstract: The most common use of robots is to effectively decrease the human’s effort with desirable output. In the human-robot interaction, it is essential for both parties to predict subsequent actions bas...

Smart Parking for Disabled Parking Improvement Using RFID and Database Authentication

Abstract: In many populous cities across the world, parking tends to be at the forefront of traffic concerns. Many cities have seen rises in urban population as people move to the cities for job opportunities. The increase in population also means more cars in the city making parking spaces valuable commodities. In many of these cities, parking spaces near venues and other services are reserved for disabled parking. In the United States, federal law sets the requirements for the number of spaces that must be made available along with the size of each area. Requirements for authorization to park in these spaces are also set by federal offices and the authorized person is given a placard designating their legal right to park in these designated parking spaces for the disabled. Our proposed method, which adds RFID and database authentication to the use of ultrasonic sensors, LED, and cloud technology methods, will assist with ensuring that the limited disabled-parking spaces are used by those authorized to do so, and will alert the parking authority when a space is occupied by an unauthenticated person. Our goal is to explain how some of the currently researched smart parking methods can be used for disabled parking management and improved with the addition of authenticating disabled parking authorization.

Enhanced Deep Learning Architectures for Face Liveness Detection for Static and Video Sequences

Abstract: Face liveness detection is a critical preprocessing step in face recognition for avoiding face spoofing attacks, where an impostor can impersonate a valid user for authentication. While considerable research has been recently done in improving the accuracy of face liveness detection, the best current approaches use a two-step process of first applying non-linear anisotropic diffusion to the incoming image and then using a deep network for final liveness decision. Such an approach is not viable for real-time face liveness detection. We develop two end-to-end real-time solutions where nonlinear anisotropic diffusion based on an additive operator splitting scheme is first applied to an incoming static image, which enhances the edges and surface texture, and preserves the boundary locations in the real image. The diffused image is then forwarded to a pre-trained Specialized Convolutional Neural Network (SCNN) and the Inception network version 4, which identify the complex and deep features for face liveness classification. We evaluate the performance of our integrated approach using the SCNN and Inception v4 on the Replay-Attack dataset and Replay-Mobile dataset. The entire architecture is created in such a manner that, once trained, the face liveness detection can be accomplished in real-time. We achieve promising results of 96.03% and 96.21% face liveness detection accuracy with the SCNN, and 94.77% and 95.53% accuracy with the Inception v4, on the Replay-Attack, and Replay-Mobile datasets, respectively. We also develop a novel deep architecture for face liveness detection on video frames that uses the diffusion of images followed by a deep Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) to classify the video sequence as real or fake. Even though the use of CNN followed by LSTM is not new, combining it with diffusion (that has proven to be the best approach for single image liveness detection) is novel. Performance evaluation of our architecture on the REPLAY-ATTACK dataset gave 98.71% test accuracy and 2.77% Half Total Error Rate (HTER), and on the REPLAY-MOBILE dataset gave 95.41% accuracy and 5.28% HTER.

Predicting Emerging Trends on Social Media by Modeling it as Temporal Bipartite Networks

Abstract: The behavior of peoples’ request for a post on online social media is a stochastic process that makes post’s ranking highly skewed in nature. We mean peoples interest for a post can grow/decay exponentially or linearly. Considering this nature of the evolutionary peoples’ interest, this paper presents a Growth-based Popularity Predictor (GPP) model for predicting and ranking the web-contents. Three different kinds of web-based real datasets namely Movielens, Facebook-wall-post and Digg are used to evaluate the performance of the proposed model. This performance is measured based on four information-retrieval metrics Area Under receiving operating Characteristic (AUC), Novelty, Precision, and Kendal’s Tau. The obtained results show that the prediction performance can be further improved if the score is mapped onto a cumulative predicted item’s ranking.

Families in Transition: The Lived Experience of Parenting a Transgender Child:

Abstract: Research exploring the parents' experience of their child undergoing gender transition is almost nonexistent. However, as the number of individuals who identify as transgender increases, gender identity will continue to evolve; therefore, supporting families of these individuals is paramount. Parents of transgender children were interviewed and yielded five themes: (a) It Rocks Your World; (b) Dancing Around in a Way that Doesn't Distance; (c) Your Child Is Still Your Child; (d) Worrying About the Future; and (e) Transformational: Finally an Answer. These themes begin to identify the complex nature and struggles parents face as they encounter the emotional and physical aspects of their child's gender transition. The findings raise awareness of the parents' perspective, provide a better understanding of the complex family issues that occur, and provide nursing suggestions on how to continue to work to facilitate "healthy families" and promote cultural sensitivity.

Root-Cause Problem Solving in an Industry 4.0 Context

Abstract: Root cause analysis (RCA) is a highly effective methodology for product design teams and manufacturing managers to engage in creative problem solving by utilizing the tools of the Fourth Industrial Revolution—Industry 4.0. This article outlines the RCA problem-solving process as it is applied to detect and resolve problems in a consumer product manufacturing setting. This article presents a case study of collaborative design, testing, and implementation of a product-specific solution to resolve quality control issues caused by a flawed component specification. The provided case study details company's application of RCA. Once the problem is identified, we describe how the design and production teams collaborated to verify and validate the revised product design via three-dimensional product simulations. Having identified a solution, the company's manufacturing managers and supervisory staff incorporate this change into their standard operating procedures, conduct staff training, and share the solution across the organization. This problem-solving approach, implemented as part of a wider continuous improvement effort, also includes the utilization of digital applications and smart devices to share data across the company in real time.

On the Chermak–Delgado lattice of a finite group

Abstract: By imposing conditions upon the index of a self-centralizing subgroup of a group, and upon the index of the center of the group, we are able to classify the Chermak-Delgado lattice of the g...

Correlates of Homelessness Among Patients in Methadone Maintenance Treatment.

Abstract: BACKGROUND Although homelessness and opioid use disorder (OUD) are important public health issues, few studies have examined their cooccurrence. OBJECTIVES The aim of this study was to evaluate the correlates of homelessness among patients enrolled in low-barrier-to-treatment-access methadone maintenance treatment (MMT) programs for OUD. METHODS Demographic, diagnosis-related, and treatment-related correlates were assessed by self-report for 164 patients in MMT. Correlates of past-month homelessness were investigated with logistic regression. RESULTS Twenty-four percent of patients reported homelessness in the past month. Bivariate analyses initially identified 7 statistically significant (P<0.05) correlates of homelessness: gender; Latinx ethnicity; symptoms of depression, anxiety, and somatization; self-criticism; and duration of MMT. In the final logistic regression model, which included significant independent variables from the bivariate logistic regressions, patients in MMT who were homeless (vs. domiciled) were more likely to be male (odds ratio 2.54; confidence interval, 1.01-6.36) and report higher symptoms of depression (odds ratio 1.07; confidence interval, 1.01-1.15). CONCLUSIONS Low-barrier-to-treatment-access programs can attract people who are homeless with OUD into MMT. These programs also have an important public health role in addressing both depression and OUD among people who are homeless.

A Smooth Angle Velocity Active Return-to-Centre Control Based on Single Neuron PID Control for Electric Power Steering System

Abstract: The active return of the steering wheel is playing a significant role in Electric Power Steering(EPS) system. In order to have a safe driving experience and comfortable maneuverability when cornering, a smooth angle velocity active return-to-center(RTC) control strategy based on single neuron adaptive PID control is proposed in the paper. In the newly-designed RTC controller, the return angular velocity is designed to change as the steering wheel angle changes, making the steering wheel return to the center position accurately and smoothly. In addition, the proposed control strategy based on single neuron adaptive PID control can cope with the control parameter uncertainty in the process of RTC control. The experimental results demonstrate that the corrected active RTC control method compared with uncorrected one effectively reduces the residual angle of the steering wheel at low vehicle speed as well as improves the RTC performance of the vehicle which does not affect the basic assist characteristics.

DRNN-based shift decision for automatic transmission:

Abstract: In research on intelligent shift for automatic transmission, the neural network selected has no feedback and lacks an associative memory function. Thus, its adaptability needs to be improved. To ac...

Influential factors in design and implementation of virtual reality technology

Abstract: Virtual Reality (VR) is a computer-generated environment that creates a simulated experience for users. VR technology is used as an effective training tool, especially for teaching potentially dangerous and/or difficult-to-create scenarios in real-life. Despite the vast literature that shows the positive impact of VR training on the learners’ performance and experience, studies that investigate the criteria for the selection of appropriate VR technology are quite limited. This paper proposes key decision criteria in selecting and investing in the right VR technology to create the best possible learning outcome based on the feedback from VR developers and engineers in the US. Ease of installation and creating an immersive user experience are identified as the most influential factors affecting the successful implementation of VR technology. We envision that this study will help companies that plan to invest in VR technologies better understand the critical factors affecting the successful design and implementation of the technology and hence will aid in decision making.