ABSTRACT
The development of financial technology has promoted the innovation and digital transformation of commercial banks. Through digital transformation, commercial banks can improve bank efficiency and operational capabilities. Through empirical analysis, this study explored the relationship between digital bank transformation and commercial bank operating capabilities and how COVID-19, bank categories, and enterprise life cycles affect the relationship between digital bank transformation and commercial bank operating capabilities. This study selected data from China's commercial banks from 2011 to 2021 and used the regression method of fixed effects to conduct an empirical analysis. The research results show that the digital transformation of banks has improved the operational capabilities of commercial banks. Further analysis showed that the emergence of COVID-19 has negatively affected their relationship. At the same time, compared with rural commercial banks and commercial banks in the recession and phase-out periods, non-rural commercial banks and commercial banks in the growth and maturity stages play a more vital moderating role in the impact of the digital transformation of banks on the financial performance of commercial banks. The main research object of this study is Chinese commercial banks, and this study examines the results of banks' digital transformation and enriches the research on digital transformation. At the same time, this study is helpful to investors who like investment banks and has good practical significance.
ABSTRACT
With the COVID-19 pandemic, people's real-life interactions diminished, and the game-based metaverse platforms such as Minecraft and Roblox are on the rise. The main users of these platforms are teenagers, they generate content in a virtual environment, which can significantly increase the activity of the platform. However, the experience of User-Generated Content in the metaverse is not very good. So what kind of support do users need to improve the efficiency of generating content in the metaverse? To investigate teenage users' preferences and expectations of it, this paper interviewed 72 teenagers aged 12-22 who are familiar with the metaverse game, and distilled 4 suggestions that can help promote metaverse users to generate content. © 2023 IEEE.
ABSTRACT
Affective computing (AC) has been regarded as a relevant approach to identifying online learners' mental states and predicting their learning performance. Previous research mainly used one single-source data set, typically learners' facial expression, to compute learners' affection. However, a single facial expression may represent different affections in various head poses. This study proposed a dual-source data approach to solve the problem. Facial expression and head pose are two typical data sources that can be captured from online learning videos. The current study collected a dual-source data set of facial expressions and head poses from an online learning class in a middle school. A deep learning neural network using AlexNet with an attention mechanism was developed to verify the syncretic effect on affective computing of the proposed dual-source fusion strategy. The results show that the dual-source fusion approach significantly outperforms the single-source approach based on the AC recognition accuracy between the two approaches (dual-source approach using Attention-AlexNet model 80.96%;single-source approach, facial expression 76.65% and head pose 64.34%). This study contributes to the theoretical construction of the dual-source data fusion approach, and the empirical validation of the effect of the Attention-AlexNet neural network approach on affective computing in online learning contexts.
ABSTRACT
Analgesia and sedation are basic parts of the treatment in the intensive care. Nevertheless, deep sedation during mechanical ventilation has many adverse effects. In last decades the trend towards mild titrated sedation is seen. It enables early weaning from mechanical ventilation and shortening the stay in the intensive care setting and hospital. In this article pharmacology of main drugs used for analgesia/sedation nad strategy of sedation in mechanically ventilated patients are described. The last section of this article is dedicated to sedation of patients with acute respiratory distress syndrome of common"and COVID -19 etiology. These patients usually suffer from critical respiratory failure and agressive ventilatory support, prone positioning and other invasive techniques are needed. That is why deep sedation or even paralysis is sometimes necessary, but also in these patients lower sedation and weaning attempts should be tried as soon as possible.Copyright © 2022 TIGIS Spol. s.r.o.. All rights reserved.
ABSTRACT
Objectives: The aim of this study was to assess Jordanian physicians' awareness about venous thromboembolism (VTE) risk among COVID-19 patients and its treatment protocol. Method(s): This was a cross-sectional-based survey that was conducted in Jordan in 2020. During the study period, a convenience sample of physicians working in various Jordanian hospitals were invited to participate in this study. Physicians' knowledge was evaluated and physicians gained one point for each correct answer. Then, a knowledge score out of 23 was calculated for each. Key Findings: In this study, 102 physicians were recruited. Results from this study showed that most of the physicians realize that all COVID-19 patients need VTE risk assessment (n = 69, 67.6%). Regarding VTE prophylaxis, the majority of physicians (n = 91, 89.2%) agreed that low molecular weight heparin (LMWH) is the best prophylactic option for mild-moderate COVID-19 patients with high VTE risk. Regarding severe/critically ill COVID-19 patients, 75.5% of physicians (n = 77) recognized that LMWH is the correct prophylactic option in this case, while 80.4% of them (n = 82) knew that mechanical prevention is the preferred prophylactic option for severe/critically ill COVID-19 patients with high bleeding risk. Moreover, 77.5% of physicians (n = 79) knew that LMWH is the treatment of choice for COVID-19 patients diagnosed with VTE. Finally, linear regression analysis showed that consultants had an overall higher knowledge score about VTE prevention and treatment in COVID-19 patients compared with residents (P = 0.009). Conclusion(s): All physicians knew about VTE risk factors for COVID-19 patients. However, consultants showed better awareness of VTE prophylaxis and treatment compared with residents. We recommend educational workshops be conducted to enhance physicians' knowledge and awareness about VTE thromboprophylaxis and management in COVID-19 patients.Copyright © 2022 The Author(s). Published by Oxford University Press on behalf of the Royal Pharmaceutical Society. All rights reserved.
ABSTRACT
Mobile application developers rely largely on user reviews for identifying issues in mobile applications and meeting the users' expectations. User reviews are unstructured, unorganized and very informal. Identifying and classifying issues by extracting required information from reviews is difficult due to a large number of reviews. To automate the process of classifying reviews many researchers have adopted machine learning approaches. Keeping in view, the rising demand for educational applications, especially during COVID-19, this research aims to automate Android application education reviews' classification and sentiment analysis using natural language processing and machine learning techniques. A baseline corpus comprising 13,000 records has been built by collecting reviews of more than 20 educational applications. The reviews were then manually labelled with respect to sentiment and issue types mentioned in each review. User reviews are classified into eight categories and various machine learning algorithms are applied to classify users' sentiments and issues of applications. The results demonstrate that our proposed framework achieved an accuracy of 97% for sentiment identification and an accuracy of 94% in classifying the most significant issues. Moreover, the interpretability of the model is verified by using the explainable artificial intelligence technique of local interpretable model-agnostic explanations. (PsycInfo Database Record (c) 2023 APA, all rights reserved)
ABSTRACT
Artificial Intelligence is categorized into the domain of computer science focused on creating intelligent machines that function like humans. Artificial Intelligence supports institutions including Islamic Financial Services in learning, making decision, and providing useful predictive analytics. The progress and promise that artificial intelligence has made and presented in finance have so far been remarkable, allowing for cheaper, faster, closer, more accessible, more lucrative, and more efficient finance especially during the pandemic covid-19 when people are required to stay at home yet still doing a banking transaction. Despite the incredible progress and promise made possible by advances in financial artificial intelligence, it nevertheless presents some serious perils and limitations. Three categories of risks and limitations involve the rise of virtual threats and cyber conflicts in the financial system, society behavioural changes, and legal amendments that cannot respond to technological developments, especially in developing countries. The main objective of this article is to evaluate the operations of the potential risks that may arise in the use of Artificial Intelligence in Islamic finance services, especially dealing with the legal arrangement that is supposed to be in line with business development. Indonesia is a country that adheres to civil law system, in which every legal arrangement is supposed to be based on written law. The lack of this legal system is where the speed of legal changes cannot keep up with the pace of technological development, which is present as a hinder to the development of Artificial Intelligence in the financial system. This article concludes that Artificial Intelligence will have a huge impact in the future on the Islamic Finance industry, but in Indonesian context, it still needs various efforts to reduce the potential risk that eventually has a big impact on the progress of Islamic banks. © 2022, University of Muhammadiyah Malang. All rights reserved.
ABSTRACT
Objectives: COVID 19 and increasing unmet needs of health technology had accelerated an adoption of digital health globally and the major categories are mobile-health, health information technology, telemedicine. Digital health interventions have various benefit on clinical efficacy, quality of care and reducing healthcare costs. The objective of the study is to identify new reimbursement policy trend of digital health medical devices in South Korea. Method(s): Official announcements published in national bodies and supplementary secondary research were used to capture policies, frameworks and currently approved products since 2019. Result(s): With policy development, several digital health devices and AI software have been introduced as non-reimbursement by utilizing new Health Technology Assessment (nHTA) pathway including grace period of nHTA and innovative medical devices integrated assessment pathway. AI based cardiac arrest risk management software (DeepCARS) and electroceutical device for major depressive disorders (MINDD STIM) have been approved as non-reimbursement use for about 3 years. Two digital therapeutics for insomnia and AI software for diagnosis of cerebral infarction were approved as the first innovative medical devices under new integrated assessment system, and they could be treated in the market. In addition, there is remote patient monitoring (RPM) reimbursement service fee. Continuous glucose monitoring devices have been reimbursed for type 1 diabetes patients by the National Health Insurance Service (NHIS) since January 2019. Homecare RPM service for peritoneal dialysis patients with cloud platform (Sharesource) has been reimbursed since December 2019, and long-term continuous ECG monitoring service fee for wearable ECG monitoring devices (ATpatch, MEMO) became reimbursement since January 2022. Conclusion(s): Although Korean government has been developed guidelines for digital health actively, only few products had been reimbursed. To introduce new technologies for improved patient centric treatment, novel value-based assessment and new pricing guideline of digital health medical devices are quite required.Copyright © 2023
ABSTRACT
The multi-generational workforce presents challenges for organizations, as the needs and expectations of employees vary greatly between different age groups. To address this, organizations need to adapt their development and learning principles to better suit the changing workforce. The DDMT Teaching Model of Tsing Hua STEAM School, which integrates design thinking methodology, aims to address this challenge. DDMT stands for Discover, Define, Model & Modeling, and Transfer. The main aim of this study is to identify the organization development practices (OD) and gaps through interdisciplinary models such as DDMT and design thinking. In collaboration with a healthcare nursing home service provider, a proof of concept using the DDMT-DT model was conducted to understand the challenges in employment and retention of support employees between nursing homes under the healthcare organization. The paper highlights the rapid change in human experiences and mindsets in the work culture and the need for a design curriculum that is more relevant to the current and future workforce. The DDMT-DT approach can help organizations address these challenges by providing a framework for HR personnel to design training curricula that are more effective in addressing the issues of hiring and employee retention. By applying the DDMT-DT model, HR personnel can better understand the needs and motivations of the workforce and design training programs that are more relevant to their needs. The proof-of-concept research pilot project conducted with the healthcare nursing home service provider demonstrated the effectiveness of the DDMT-DT model in addressing the issues of hiring and employee retention. The project provides a valuable case study for other organizations looking to implement the DDMT-DT model in their HR practices. Overall, the paper highlights the importance of adapting HR practices to better suit the changing workforce. The DDMT-DT model provides a useful framework for organizations looking to improve their HR practices and better address the needs of their workforce.
ABSTRACT
Artificial Intelligence (AI) is contributing to the campaign against the Coronavirus Disease 2019 (COVID-19). Since 2019, more and more AI frameworks and applications in COVID-19 have been proposed, and the recent research has shown that AI is a promising technology because AI can achieve a higher degree of scalability, a more comprehensive and identification of patterns in the vast amount of unstructured and noisy data, accelerated processing power, and strategies to outperform traditional methods in many specific tasks. In this chapter, we focus on the specific AI applications in the clinical immunology/immunoinformatics for COVID-19. More precisely, on one hand, we discuss the application of deep learning in designing SARS-CoV-2 vaccines, and, on the other hand, we discuss the development of a machine learning framework for investigating the SARS-CoV-2 mutations that can help us better respond to the future mutant viruses, including designing more robust vaccines based on such AI approaches. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.
ABSTRACT
Objectives: The coronavirus disease 2019 (COVID-19) pandemic has imposed significant burden on Brazil's health system. The present study aims to describe patients' demographic and clinical characteristics, vaccine uptake and assess healthcare resource utilization (HCRU) and costs associated with acute COVID-19 in Brazil during the Omicron predominant period. Method(s): A population-based retrospective study was conducted using the National Health Data Network (RNDS), National Vaccination Campaign against COVID-19 data and surveillance data in public setting. Individuals with positive COVID-19 test results between January-April 2022 were identified. Patients' demographics, comorbidities, vaccination status, HCRU for those who were admitted to hospitals and their associated costs were described by age groups. Result(s): A total of 8,160,715 COVID-19 cases were identified and 2.7% were aged <5 years, 11.6% were 5-19 years, 76.9% were 20-64 years and 8.7% were >= 65 years. The presence of comorbidity was 23.1% with a higher prevalence of comorbidities in the elderly (61.8% for 65-74 years and 71.2% for >=75 years). Regarding COVID -19 vaccination uptake, among those aged <=19 years, 20-64 years and >=65 years, 40.6%, 86.5% and 92.2% had primary series, respectively. Among adults, the booster uptake was 47.3% and 75.8% for those aged 20-64 years and >= 65 years, respectively. Among those with confirmed COVID-19, regardless of vaccination status, 87% were being symptomatic and 1.7% were hospitalized (3.8% in aged <5 years, 4.2% in 5-19 years, 34.3% in 20-64 years and 57.6% in >= 65 years). Among hospitalized patients, 32,6% were admitted to ICU and 80% required mechanical ventilation support. The average cost per day in normal wards and ICU without ventilation was R$291,89 and R$923,90, respectively. Conclusion(s): Our results quantify the public health and economic burden of COVID-19 in Brazil, suggesting substantial healthcare resources required to manage the COVID-19 pandemic.Copyright © 2023
ABSTRACT
Objectives: The COVID pandemic has imposed significant direct medical cost and resource use burden on healthcare systems. This study described the patient demographic and clinical characteristics, healthcare resource utilization and costs associated with acute COVID in adults in England. Method(s): This population-based retrospective study used linked primary care (Clinical Practice Research Datalink, CPRD, Aurum) and secondary care (Hospital Episode Statistics) data to identify: 1) hospitalized (admitted within 12 weeks of a positive COVID-19 PCR test between August 2020 and March 2021) and 2) non-hospitalized patients (positive test between August 2020 and January 2022 and managed in the community). Hospitalization and primary care costs, 12 weeks after COVID diagnosis, were calculated using 2021 UK healthcare reference costs. Result(s): We identified 1,706,368 adult COVID cases. For hospitalized (n=13,105) and non-hospitalized (n=1,693,263) cohorts, 84% and 41% considered high risk for severe COVID using PANORAMIC criteria and 41% and 13% using the UKHSA's Green Book for prioritized immunization groups, respectively. Among hospitalized cases, median (IQR) length of stay was 5 (2-7), 6 (4-10), 8 (5-14) days for 18-49 years, 50-64 years and >= 65 years, respectively;6% required mechanical ventilation support, and median (IQR) healthcare costs (critical care cost excluded) per-finished consultant episode due to COVID increased with age (18-49 years: 4364 (1362-4471), 50-64 years: 4379 (4364-5800), 65-74 years: 4395 (4364-5800), 75-84 years: 4473 (4364-5800) and 85+ years: 5800 (4370-5807). Among non-hospitalized cases, older adults were more likely to seek GP consultations (13% of persons age 85+, 9% age 75-84, 7% age 65-74, 5% age 50-64, 3% age 18-49). Of those with at least 1 GP visit, the median primary care consultation total cost in the non-hospitalized cohort was 16 (IQR 16-31). Conclusion(s): Our results quantify the substantial economic burden required to manage adult patients in the acute phase of COVID in England.Copyright © 2023
ABSTRACT
Diabetes mellitus is prevalent worldwide and affects 1 in 10 adults. Despite the successful development of glucose-lowering drugs, such as glucagon-like peptide-1 (GLP-1) receptor agonists and sodium-glucose cotransporter-2 inhibitors recently, the proportion of patients achieving satisfactory glucose control has not risen as expected. The heterogeneity of diabetes determines that a one-size-fits-all strategy is not suitable for people with diabetes. Diabetes is undoubtedly more heterogeneous than the conventional subclassification, such as type 1, type 2, monogenic and gestational diabetes. The recent progress in genetics and epigenetics of diabetes has gradually unveiled the mechanisms underlying the heterogeneity of diabetes, and cluster analysis has shown promising results in the substratification of type 2 diabetes, which accounts for 95% of diabetic patients. More recently, the rapid development of sophisticated glucose monitoring and artificial intelligence technologies further enabled comprehensive consideration of the complex individual genetic and clinical information and might ultimately realize a precision diagnosis and treatment in diabetics.
ABSTRACT
It is important to evaluate medical imaging artificial intelligence (AI) models for possible implicit discrimination (ability to distinguish between subgroups not related to the specific clinical task of the AI model) and disparate impact (difference in outcome rate between subgroups). We studied potential implicit discrimination and disparate impact of a published deep learning/AI model for the prediction of ICU admission for COVID-19 within 24 hours of imaging. The IRB-approved, HIPAA-compliant dataset contained 8,357 chest radiography exams from February 2020-January 2022 (12% ICU admission within 24 hours) and was separated by patient into training, validation, and test sets (64%, 16%, 20% split). The AI output was evaluated in two demographic categories: sex assigned at birth (subgroups male and female) and self-reported race (subgroups Black/African-American and White). We failed to show statistical evidence that the model could implicitly discriminate between members of subgroups categorized by race based on prediction scores (area under the receiver operating characteristic curve, AUC: median [95% confidence interval, CI]: 0.53 [0.48, 0.57]) but there was some marginal evidence of implicit discrimination between members of subgroups categorized by sex (AUC: 0.54 [0.51, 0.57]). No statistical evidence for disparate impact (DI) was observed between the race subgroups (i.e. the 95% CI of the ratio of the favorable outcome rate between two subgroups included one) for the example operating point of the maximized Youden index but some evidence of disparate impact to the male subgroup based on sex was observed. These results help develop evaluation of implicit discrimination and disparate impact of AI models in the context of decision thresholds © COPYRIGHT SPIE. Downloading of the is permitted for personal use only.
ABSTRACT
Submission content Introduction: At the end of a particularly hectic night shift on the intensive care unit (ICU) I found myself sitting in the relatives' room with the mother and aunt of a young patient, listening to their stories of her hopes and aspirations as she grew up. She had been diagnosed with lymphoma aged 14 and received a bone marrow transplant from her younger sister. Fighting through treatment cycles interposed with school studies, she eventually achieved remission and a portfolio of A-levels. Acceptance into university marked the start of a new era, away from her cancer label, where she studied forensic science and took up netball. Halfway through her first year she relapsed. Main body: When I met this bright, ambitious 20-year-old, none of this history was conveyed. She had been admitted to ICU overnight and rapidly intubated for type-1 respiratory failure. The notes contained a clinical list of her various diagnoses and treatments, with dates but no sense of the context. Rules regarding visitation meant her family were not allowed onto the unit, with next-of-kin updates carried out by designated non-ICU consultants to reduce pressures on ICU staff. No photos or personal items surrounded her bedside, nothing to signify a life outside of hospital. She remained in a medically-induced coma from admission onwards, while various organ systems faltered and failed in turn. Sitting in that relatives' room I had the uncomfortable realisation that I barely saw this girl as a person. Having looked after her for some weeks, I could list the positive microbiology samples and antibiotic choices, the trends in noradrenaline requirements and ventilatory settings. I had recognised the appropriate point in her clinical decline to call the family in before it was too late, without recognising anything about the person they knew and loved. She died hours later, with her mother singing 'Somewhere Over the Rainbow' at her bedside. Poignant as this was, the concept of this patient as more than her unfortunate diagnosis and level of organ failure had not entered my consciousness. Perhaps a coping mechanism, but dehumanisation none-the-less. Conclusion(s): Striking a balance between emotional investment and detachment is of course vital when working in a clinical environment like the ICU, where trauma is commonplace and worst-case-scenarios have a habit of playing out. At the start of my medical career, I assumed I would need to consciously take a step back, that I would struggle to switch off from the emotional aspects of Medicine. However, forgetting the person behind the patient became all too easy during the peaks of Covid-19, where relatives were barred and communication out-sourced. While this level of detachment may be understandable and necessary to an extent, the potential for this attitude to contribute to the already dehumanising experience of ICU patients should not be ignored. I always thought I was more interested in people and their stories than I was in medical science;this experience reminded me of that, and of the richness you lose out on when those stories are forgotten.
ABSTRACT
Past research has discovered that the shape design and interaction process design of AI robots, as well as the users' constant features, are the major factors that affect users' willingness to interact with AI robots. Currently, AI robots that play a vital part in the daily activities of our society are becoming increasingly prevalent, thus things about AI robots have gone from mythic to prosaic. But when and where people are more likely to adopt AI robots remains an important research topic. With the development of online technology and the long-term impact of COVID-19, there has been a recent trend in the lower frequency of socializing. To investigate whether a state of low socializing frequency is a robotic moment and whether it affects people's willingness to interact with AI robots, we conducted two-wave questionnaire surveys to collect data from 300 participants from 23 provinces in China. The results showed that the frequency of socializing had a significant negative correlation with the willingness to interact with the AI robots via the mediation role of social compensation. Furthermore, the relationship between social compensation and willingness to interact with the AI robots was demonstrated to be stronger, when participants had a lower anthropomorphic tendency. These findings have theoretical implications for the human-computer interaction literature and managerial implications for the robotics industry. (PsycInfo Database Record (c) 2023 APA, all rights reserved)
ABSTRACT
Remote healthcare is a well-accepted telemedicine service that renders efficient and reliable healthcare to patients suffering from chronic diseases, neurological disorders, diabetes, osteoporosis, sensory organs, and other ailments. Artificial intelligence, wireless communication, sensors, organic polymers, and wearables enable affordable, non-invasive healthcare to patients in all age groups. Telehealth services and telemedicine are beneficial to people residing in remote locations or patients with limited mobility, rehabilitation treatment, and post-operative recovery. Remote healthcare applications and services proved to be significant during the COVID-19 pandemic for both patients and doctors. This study presents a detailed study of the use of artificial intelligence and the internet of things in applications of remote healthcare in many domains of health, along with recent patents. This research also presents network diagrams of documents from the Scopus database using the tool VOSViewer. The paper highlights gap which can be undertaken by future researchers. © 2023 IEEE.
ABSTRACT
Introduction: The use of protective mechanical ventilation and prone position was recommended for the management of moderate to severe acute respiratory distress syndrome (ARDS) due to COVID-19, as a result of its reported utility on oxygenation and mortality. Our objective is to describe gasometric and mechanical behavior in subjects with ARDS due to COVID-19 managed with protective mechanical ventilation and prone position in a high complexity hospital. Method: Observational study. Subjects ≥18 years of age with ARDS due to COVID-19 were included. Protective mechanical ventilation was started from the first connection to invasive ventilation, while the prone position started with PaO2/FIO2 150. Follow-up was performed during and after the prone position. A descriptive analysis of baseline characteristics and comparison of means between groups was performed using the Dunn and Friedman test. Statistical significance corresponds to p 0.05 in all analyses. Results: 74 subjects were studied, 58% correspond to men with a mean age of 60 years. There is evidence of a significant increase in arterial oxygenation assessed by PaO2 (76 to 98 mmHg, p 0.05) and PaO2/FIO2 (100 to 161, p 0.05) during the first hour of treatment, with stability of values beyond 48 hours after supination. Pulmonary mechanics values remain constant within the established protection range (p = 0,18). Conclusion: The strategy of protective mechanical ventilation and prone position for 48 or more hours, in subjects with moderate to severe ARDS due to COVID-19, improves and maintains arterial oxygenation up to 48 hours after supination. © 2023
ABSTRACT
The Intensive Care Unit (ICU) is a paradigmatic example of the potential reach of data-centred knowledge discovery. This is because the contemporary ICU heavily depends on medical devices for patient monitoring through electronic data acquisition. This poses a unique opportunity for multivariate data analysis to support evidence-based medicine (EBM), particularly in the form of Artificial Intelligence (AI) approaches. The COVID-19 pandemic has tested the limits of critical care management, often overwhelming ICUs. In this brief chapter, we sketch the role of AI, especially in the form of Machine Learning (ML), at the ICU and discuss what can it offer to address COVID-19 disruption in this environment. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.
ABSTRACT
This paper presents a control system for indoor safety measures using a Faster R-CNN (Region-based Convolutional Neural Network) architecture. The proposed system aims to ensure the safety of occupants in indoor environments by detecting and recognizing potential safety hazards in real time, such as capacity control, social distancing, or mask use. Using deep learning techniques, the system detects these situations to be controlled, notifying the person in charge of the company if any of these are violated. The proposed system was tested in a real teaching environment at Rey Juan Carlos University, using Raspberry Pi 4 as a hardware platform together with an Intel Neural Stick board and a pair of PiCamera RGB (Red Green Blue) cameras to capture images of the environment and a Faster R-CNN architecture to detect and classify objects within the images. To evaluate the performance of the system, a dataset of indoor images was collected and annotated for object detection and classification. The system was trained using this dataset, and its performance was evaluated based on precision, recall, and F1 score. The results show that the proposed system achieved a high level of accuracy in detecting and classifying potential safety hazards in indoor environments. The proposed system includes an efficiently implemented software infrastructure to be launched on a low-cost hardware platform, which is affordable for any company, regardless of size or revenue, and it has the potential to be integrated into existing safety systems in indoor environments such as hospitals, warehouses, and factories, to provide real-time monitoring and alerts for safety hazards. Future work will focus on enhancing the system's robustness and scalability to larger indoor environments with more complex safety hazards.