Applying Human Factors to Modify and Design Healthcare Workspaces and Processes in Response to COVID-19

The COVID-19 pandemic continues to present unique challenges to healthcare organizations around the world. Members of a provincial Human Factors team supported several workspace design projects prompted by the pandemic. This article highlights some of the challenges identified in a selection of these projects. It also presents the human factors methods and recommendations that were used to improve workspace designs, processes, and patient safety in healthcare environments. © 2023 by Human Factors and Ergonomics Society.

Artificial Intelligence Applications in Quality Management Systems of Philippine Higher Education Institutions

To ensure quality assurance, Higher Education Institutions (HEIs) implement a Quality Management System (QMS) anchored on international benchmarks like ISO 9001:2015 Standards. With the COVID-19 pandemic, quality audits have become more challenging. Also, to address the lapses due to human error and lack of technical knowledge in clause identification during audit processes, an artificial intelligence (AI)-enabled QMS is presented. This study successfully demonstrated how AI-enabled QMS can match audit findings in accreditation compliance reports and internal quality audit reports with the clauses of ISO 9001:2015. Audit findings corpus data gathered are within the span of the last five years, which serve as the dataset to be employed. After data pre-processing, a long short-term memory (LSTM) deep neural network was created and trained using MATLAB. The AI model achieved a combined classification accuracy (CA) of 82.15% and predicted 70% of the examined audit findings in actual implementation. Further analyses illustrate how AI can be maximized in generating useful and precise and useful audit reports for HEIs to develop and implement globally competitive educational policies, programs, and standards. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Evaluation of human error in workers of an Iranian copper mine during the COVID-19 pandemic using the CREAM.

BACKGROUND: The outbreak of COVID-19 has adversely affected both global economy and public health around the world. These effects have also been observed in many workplaces, including mines. OBJECTIVE: This study aimed to examine the human error of copper miners during the pandemic. METHOD: This descriptive-analytical, cross-sectional study was performed on 192 workers of a copper mine in Iran.. For this, occupation tasks were firstly analyzed using the Hierarchical Task Analysis (HTA), and then the human error in different subunits was assessed using the basic Cognitive Reliability and Error Analysis Method (CREAM). The prevalence of COVID-19 among miners was determined by assessing positive PCR test records. RESULTS: The probability of human error in the operational subunits including mining, crushing, processing, and support subunits was estimated to be 0.0056, 0.056, 0.0315, and 0.0177, respectively. All three operational units were found to be in the scrambling control mode. The support unit was determined to be in the tactical control mode. Approximately 50% of all workers had been infected with COVID-19, with the highest prevalence in support units. CONCLUSION: The results suggest that during the COVID-19 pandemic, copper miners are at higher risk of human error induced by poor working conditions. Therefore, it is recommended to employ some management strategies such as promotion of safety, health monitoring, and adopting supportive measures to control occupational stresses and therefore the probability of human error in the mine's operational units.

Securing Remote User Authentication in Industrial Internet of Things

The Industrial Internet of Things (IIoT) enhances the benefit of the Internet of Things (IoT) to a higher level, especially in industries where human error can lead to catastrophic effects. However, security is a major concern in IIoT as hackers can gain access to connected systems, thus potentially subjecting operations to a shutdown. Besides, the outbreak of the COVID-19 pandemic changed the operations style of organizations into a remote work model. Consequently, there has been a significant increase in cyber-attacks leveraging vulnerabilities of IoT devices connected to the Internet. Considering the above factors, we propose a method of remote user authentication combining Photo Response Non-Uniformity (PRNU) with fingerprint bio-metric, which can prevent attacks. PRNU uniquely identifies the scanner, thereby authenticates the device of the user. To prove the effectiveness of PRNU, we collect fingerprint images from various scanners prototyped using Raspberry Pi and evaluate the performance. Our performance evaluation with a set of 10 fingerprint scanners shows promising results. Moreover, our analysis shows that the proposed scheme achieves a classification accuracy of 99%. © 2022 IEEE.

Oops,We Did it Again: Reducing Human Error-Induced Truck Unloading Events

Human error is a leading contributing factor to several well-known reactive chemistry and loss-of-containment events that involve unloading trucks to storage tanks or processing equipment. Driving,connecting hoses,and initiating (and ending) chemical transfers requires worker actions that must be completed correctly in spite of these activities being done in an ever-changing work environment. Workers are faced with doing their jobs correctly in spite of personnel turnover,budget constraints,changes in technology,and organizational changes that sometimes add third parties (drivers,loaders,and operators) who may not understand the chemical,physical,or fire hazards of the job. Recent challenges brought by COVID-19 have added stressors and changes to the workplace that make it even more difficult toget it right the first time.For decades,industry has been trying to reduce human error and unlock the mystery of why good employees make poor decisions that can create high-consequence events. Neuroscience research is identifying methods to implement human factor controls that reduce risk,and this information can be applied from the boardroom to the shop floor to improve the reliability of our operations. Critical organizational elements - including work environments,technological interfaces,operating procedures,training,work schedules and leadership actions - are often not aligned with how our brains work. Copyright © American Institute of Chemical Engineers. All rights reserved.

An Extended Deep Learning based Solution for Screening COVID-19 CT-Scans

Due to immense pressure on the medical sector, there is a huge chance of human error in diagnosing the report of COVID-19 patients. For the detection of COVID-19, many Artificial Intelligence-based methodologies have been proposed. This work offers an ideal approach by a fusion of deep learning classifiers and medical images to provide a speedy and accurate identification of the COVID-19 virus by analyzing the user's CT-Scan images of the lungs. In this work, an adjusted rendition of ResNet101V2 that is improved by a Feature Pyramid Network for classifying the CT scan images into the categories: normal or COVID-19 positive, has been implemented. An accuracy of marginally significant has been obtained by ResNet101V2 with Feature Pyramid Network. The proposed FPN, using the deep learning technique, assured a satisfactory performance in terms of detecting COVID-19 in CT scan and gives a testing accuracy of 97.79%. The predicted results on test-cases are highly accurate using FPN and can assist the medical professionals in making a proper judgment. © 2022 Bharati Vidyapeeth, New Delhi.

IoT based Attendance Management System (AMS) with Smartwatches Compatibility

The technological evolution and recent advances in machine learning have transformed how ordinary tasks are performed. Due to many technological, cultural and health related changes (such as Covid 19 pandemic), the means for managing attendance has been transformed with Internet of Things (IoT) based technologies. Attendance management system (AMS) is a system that documents and keeps track of employee and student hours and stores them on local repository or in the cloud. Manual approach to recording and keeping track of attendance is prone to human errors and time consuming. Although many studies have proposed new IoT biometric based solutions to enhance this process, achieving accuracy, efficiency and expense affordability can be a challenging task. The most used biometric approach recently is face recognition IoT solutions. Face recognition can be challenging during the Covid 19 pandemic because of face masks. Taking these issues into consideration, we propose a GPS-enabled Iris-based biometric approach for the attendance management system with smartwatches' compatibility feature. The system performs two main tasks: identification and real time localization. The identification is achieved with iris-based identification while localization is using GPS technology and smart watches. The proposed system addresses many fundamental issues such as the expense factors of manufacturing dedicated tracking wearable devices. It also provides an efficient means of identification using iris-based biometric identification which provides many advantages such as accuracy and enhanced friendly experience without relying on face recognition. The proposed IoT Attendance management systems will be designed to provide better automation for managing attendance and reduce many human errors resulting from manual approaches. © 2021 ACM.

AI-Driven Medical Imaging Analysis for COVID-19 Detection

As of January 2019, there have been fears worldwide over COVID-19. In order to detect a person is affected by the virus is not, Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests, Chest X-Ray Images, Computerized Tomography (CT) scans are used. The patients who test positive for COVID-19 require early treatment and diagnosis. Manually analyzing the medical images of Chest radiographs and CT scans takes more time and are more susceptible to human error. So, to overcome this problem, Artificial Intelligence (AI) and Deep Learning-based tools are used to analyze medical images. This study focuses primarily on comparing deep learning models and finding the best one to detect COVID-19 in CT scans and X-rays of the chest. For X-Rays of the chest, COVID-19 Radiography Database is used, and SARS COV 2 Ct Scan Dataset is used for CT scans. © 2022 IEEE.

A Survey on COVID-19 Detection from X-ray Images using Deep Learning

Currently, the detection of coronavirus is one of the main challenges in the world. Recent statistics have shown that the total number of cases are increasing exponentially. Existing high-precision diagnostic technologies such as RT-PCRs are expensive and complex. In order to obtain a quick and precise medical diagnosis, X-ray images are commonly used. Detecting positive cases of COVID-19 from x-ray images is really difficult, challenging and susceptible to human error. Various deep learning networks have been used in recent studies for X-ray image classification and have generated competitive results, because stages like feature selection, feature extraction and classification are performed spontaneously in deep learning techniques. This article presents a detailed study of some of recent works for detecting coronavirus from X-ray images with the help of deep learning, a comparative analysis of the methodologies used by them, a comparison of available datasets, and scope of future exploration in this field. © 2021 IEEE.

Detecting Anomalies in Daily COVID-19 Cases Data From Brazil Capitals Using GSP Theory

The COVID-19 pandemic has created an urgency for studies to understand the spread of the virus, in particular, to predict the number of daily cases. This type of investigation depends heavily on the data collected and made available manually. Therefore, data are susceptible to human errors which can cause anomalies in the dataset. Understanding and correcting anomalies in real-world application data is an important task to ensure the reliability of the data analysis and prediction tools. This paper presents a spectral anomaly detection and correction strategy that uses concepts from the graph signal processing (GSP) theory. The main advantage of the introduced strategy is to analyze the variation in the daily number of cases with the proximity relation between the investigated locations. Experiments were carried out with real meteorological and mobility data for predicting the number of COVID-19 cases by the classic prediction model known as autoregressive integrated moving average exogenous (ARIMAX). Then, the anomaly detection method was applied to determine the relationship between the prediction errors and the anomalous variations identified by the tool. The results show a strong relationship between the anomalous variations and the errors made by the model and attest to the increase in the accuracy of the prediction model after the normalization of the anomalies. © 2021 IEEE

Voting Booth Helper System Using Machine Learning

Elections are the fundamental defining characteristics of any democracy that is being governed by the people, where in people express their choices or articulate opinions through voting. The existing voting system uses EVM system at polling booths for voting and its main drawback is the manual validation of the voter. In the polling booths, the voting process is organized by few organizers having a count from 5 to 10 or even above. These people are assigned to perform certain tasks, one of such tasks is to validate the voter. With the raising population this consumes a lot of time, which in turn increases the man power and the human error. This project aims to provide an efficient solution to overcome the drawbacks of the existing voting system. We have developed a module using face recognition algorithm, to validate the voter accurately and efficiently within no time. It even reduces the man power, as it alone, performs all the tasks performed by the several organizers at the voting booths. The algorithm made use of, is the Multi-Task Cascaded Convolutional Neural Networks which is known for its accuracy and speed. The reduction of man power helps to control the rapid increase of covid cases, which is the most prevailing problem and helps the voters to vote with ease. © 2021 IEEE.

Building an AI Model on ECG Data for Identifying Burnout/Stressed Healthcare Workers Involved in Covid-19 Management

An electrocardiogram (ECG) is used to monitor electrical activity of the heart. ECG data with 12 leads can help in detecting various cardiac (heart) problems. One of the significant factors that contribute to various cardiac diseases is work/personal stress. Use of various machine and deep learning approaches to analyse ECG data has yielded promising results in the field of predictive and diagnostic healthcare with less human error or bias. In our study, 10sec of 500Hz, 12-lead ECG samples were collected from the healthcare workers, who were involved directly or indirectly in taking care of COVID-19 patients. The present study was designed to determine whether Healthcare workers were stressed by using only ECG as input to a deep learning model. To the best of our knowledge, no earlier ECG based study has been carried out to identify stressed persons among the healthcare workers who are giving support to COVID-19 patients. In this study, ECG data of healthcare workers giving services to COVID-19 patients is utilized. This data was collected from four tertiary academic care centres of India. A modified version of AlexNet is utilized on this data that is able to identify a stressed healthcare worker with 99.397% accuracy and 99.411% AUC score. Successful deployment of such systems can help governments and hospital administrations make appropriate policy decisions during pandemics. © 2021 IEEE.