The objective of the paper is to provide a model capable of serving as a basis for retraining a convolutional neural network that can be used to detect COVID-19 cases through spectrograms of coughing, sneezing and other respiratory sounds from infected people. To address this challenge, the methodology was focused on Deep Learning technics worked with a dataset of sounds of sick and non-sick people, and using ImageNet's Xception architecture to train the model to be presented through Fine-Tuning. The results obtained were a precision of 0.75 to 0.80, this being drastically affected by the quality of the dataset at our availability, however, when getting relatively high results for the conditions of the data used, we can conclude that the model can present much better results if it is working with a dataset specifically of respiratory sounds of COVID-19 cases with high quality.
This research paper was developed to implement an intelligent solution for This research paper was developed to implement an intelligent solution for the control of the capacity of commercial establishments in times of COVID-19 using Yolo, which is a Convolutional Neural Network and a Deep Learning algorithm. For the application of this solution, a COCO dataset was used that is used in the implementation of Yolov4. A computer module was developed for the analysis of the flow of people, using Python 3.7, which mainly consists of an algorithm that determines the path and direction (movement) of a person, and this is evaluated in a limit o threshold that acts as the entrance and exit door of the main establishment; that is, it determines whether a person leaves or enters according to their route and direction. The results indicate that it is possible to implement this solution as an additional monitoring module for use as capacity control and with this offer a complete alternative to the owners of commercial establishments. In this way, it seeks to control the maximum capacity allowed due to the pandemic generated by the Sars-Cov.2 virus. The tests were conducted using an AMD Ryzen 7 3750H processor and an NVIDIA GTX 1660 TI video card. The possibility of determining whether the number of people who entered less than the number of people who left exceeds the maximum allowed by the pandemic on 50% of the real capacity.
The advancement in network technology has led to an exponential rise in the number of internet users across the globe. The increase in internet usage has resulted in an increase in both the number of malicious websites and cybercrimes reported over the years. Therefore, it has become critical to devise an intelligent solution that can detect malicious websites and be used in real-time systems. In our paper, we perform a comparative analysis of various feature selection techniques to build a time-efficient and accurate predictive model. To build our predictive model, a set of features are selected by feature selection methods. The selected features consist of at least 70% of the categorical features in all feature selection techniques examined in this paper. Keeping the end goal of real-time deployment of models in context the cost of processing or storing these features is far cheaper when compared to text or image-based features. We started out with a class imbalance in our data which was later dealt with using Synthetic Minority Oversampling Technique. Our proposed model also bested the existing work in the literature when compared over various evaluation metrics. The result indicated that Embedded feature selection was the best technique considering the accuracy of the model. The Filter-based technique may also be used in the context of developing a low latency system at the cost of the accuracy of the model.
BackgroundVarious infections can mimick inflammatory arthropathies and misdiagnosed as rheumatoid arthritis, Spondyloarthritis or lupus. Occasionally, rare infections prevalent in a specific geographical region may present with arthritis as their first and only symptom which may confuse the clinician leading to incorrect diagnosis and management. Many a times, such patients land up in a rheumatology clinic prior to the diagnosis. Hence, Rheumatologists practicing worldwide should be aware of such manifestations of infectious diseases.ObjectivesMain objective of this multi-centric study was to appraise the clinical features and demographics of various rare infectious diseases (newly or previously diagnosed) that presented with arthritis.MethodsThis retrospective study (January 2022- December 2022) was carried out at 3 tertiary care centres, two in central India (city Indore and Bilaspur) and 1 in northern India (city Saharangpur). Patients who were previously diagnosed with an infectious disease and presented with arthritis were included. Patients with arthritis who were diagnosed as infectious disease were also included. Their details regarding demographics and clinical presentations were collected. Pearson chi-square test was applied and cases were studied according to their Age, Sex, distribution of joints, rheumatoid arthritis (RA) factor and anti cyclic citrullinated peptide (anti-ccp) antibodies positivity,presence of myalgias, rashes, extra-articular manifestations and cutaneous manifestations.ResultsSeventy- nine patients (39 male) were identified. Out of these,34 (43%) patients had chikungunya arthritis, 12 (15.2%) leprosy, 11 (13.9%) Covid-19, 10 (12.9%) Dengue, 4 (5.1%),Hepatitis C, 4 (5.1%) HIV, 3 (3.8%) HCV and 1 (1.3%) Poncet’s disease. No significant association was seen among rheumatoid factor (p=0.494) or anti-ccp antibodies positivity (p=0.987) with these diseases. Patients with chikungunya had oligoarthritis (14.7%) or polyarthritis (85.3%). Patients with Covid-19 had oligoarthritis (18.2%), polyarthralgia (27.3%) and polyarthritis (54.5%). Patients with dengue, HCV and Poncet’s disease had only polyarthritis. Majority of the patients with hepatitis C and leprosy had polyarthritis. Patients with HIV showed enthesitis (25%), oligoarthritis (25%) and polyarthritis (50%).There was a statistically significant association between presence/ absence of myalgia and infectious diseases (P=0.001). It was absent in patients with hepatitis C. Only about one-third of the patients with leprosy had myalgia; while most of the patients with other infectious diseases had myalgia. 20% of the dengue patients and 41.7% of the leprosy patients had rashes, while rashes were absent in patients with other infectious diseases. Erythema nodosum was seen in only 25% patients with leprosy; while it was absent in the patients with other infectious diseases. Extra-articular manifestations were seen in 35.3% patients with chikungunya, 9.1% with Covid-19, 20% with dengue, 25% with hepatitis C, 33.3% with leprosy and 100% patients with Poncet’s disease; while extra-articular manifestations were not seen in patients with HCV and HIV infection. 9.1% patients with Covid-19, 25% with hepatitis C, 25% with HIV, 83.3% with leprosy had cutaneous manifestations, while cutaneous manifestations were not seen in patients with chikungunya arthritis, dengue, HCV and Poncet’s disease.ConclusionRheumatological manifestations of various infections can mimic various inflammatory arthritis and can be a diagnostic challenge. Apart from the joint involvement, these infections can also have various extraarticular manifestations as well. One should be aware of such manifestations as increased awareness can prevent diagnostic delay and complications.Reference[1]Sharma V, Sharma A. Infectious mimics of rheumatoid arthritis. Best Pract Res Clin Rheumatol. 2022 Mar;36(1):101736. doi: 10.1016/j.berh.2021.101736. Epub 2021 Dec 31. PMID: 34974970.Acknowledgements:NIL.Disclosure of InterestsNone Declared.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.