Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 179
Filter
Add filters

Document Type
Year range
1.
14th International Conference on Information Technology and Electrical Engineering, ICITEE 2022 ; : 253-258, 2022.
Article in English | Scopus | ID: covidwho-2191881

ABSTRACT

The spread of Covid-19 virus occurs quickly, one of which is through sneezing and coughing (drops or saliva). This becomes an infectious material for dentists in carrying out dental care during the pandemic. Extra-oral suction (EOS) is a device for sucking the patient's Aerosol when performing surgery or dental treatment, but the nozzle of the suction device is still manually moved, therefore the position of the EOS nozzle is right above the patient's mouth. This allows for some aerosol particles that have not been inhaled by the device when the patient turns or changes his head position. In this paper, Visual Servoing (VS) is needed, which is an approach to guide a robot using visual information. Image processing (face and mouth detection), and controls are combined to be able to move or change the position of the nozzle automatically according to the position and direction of the patient's mouth. The human face and mouth openness pose detection can be done using the Haar-cascade method and the Adaptive Boosting (AdaBoost) algorithm. This system is expected to optimize performance in dentist operations and minimize the transmission of the Covid-19 virus. © 2022 IEEE.

2.
5th International Conference on Informatics and Computational Sciences, ICICos 2021 ; 2021-November:277-281, 2021.
Article in English | Scopus | ID: covidwho-2191860

ABSTRACT

The widening spread of an infectious disease, namely COVID-19 (corona virus disease 2019) has become a serious health problem for countries around the world. As an effort to control the confirmed case of COVID-19, WHO advice people to wear a face mask to protect themselves from the spread of the coronavirus. However, the people's awareness of wearing face masks in certain location is still low, so an automatic masked face classifier model is needed. This research performes the masked face classification into two class (masked and not-masked) by using the EfficientNet pretrained model. The experiment show that the EfficientNet is able to achieve, not only the best accuracy, but also the most efficient model, compared to the other state-of-the-art model of CNN, such as ResNet-50 and Inception. This condition is achieved when using both limited dataset and larger dataset. EfficientNet is able to achieve the 99% accuracy with about 5x lower number of network parameters and 3x faster testing time than ResNet-50. Compare to Inception, EfficientNet is better in terms of accuracy and also efficiency. © 2021 IEEE.

3.
5th International Conference on Informatics and Computational Sciences, ICICos 2021 ; 2021-November:139-143, 2021.
Article in English | Scopus | ID: covidwho-2191859

ABSTRACT

This research aims to determine the symptoms of being infected with Covid-19 using a fuzzy logic approach. Detection of Covid-19 is an important step in early identification of suspected Covid-19 patients so that further steps can be taken. Fuzzy logic is an appropriate way to map an input space into an output space. For very complex systems, the use of fuzzy logic is one solution. Research results can help the community to carry out self-diagnosis, and paramedics to carry out initial diagnoses to patients, so that it can make it easier for all parties to deal with Covid-19. From the test result with 176 individuals obtained an accuracy value of 93.7%. © 2021 IEEE.

4.
Critical Care Medicine ; 51(1 Supplement):594, 2023.
Article in English | EMBASE | ID: covidwho-2190679

ABSTRACT

INTRODUCTION: Transcriptome-derived sepsis subphenotypes, termed 'adaptive', 'inflammopathic' and 'coagulopathic', have been reliably identified in sepsis cohorts, however plasma proteomics in these groups have not been well characterized. We hypothesized that inflammatory and vascular injury markers would be elevated in the inflammopathic and coagulopathic groups compared to the adaptive group. METHOD(S): We prospectively enrolled and obtained blood from 130 inpatients with COVID19-related sepsis. Severity was classified by NIH ordinal scale. Gene expression analysis was performed by Nanostring nCounter (Inflammatix). Inflammatory proteins interleukin (IL)-6, IL8, IL10, IL1RA, IL1RL1, and IFNg and vascular markers ANGPT2, sICAM, vWF, ADAMTS13, and protein C were measured with OLINK proximity extension assay. Clinical variables were compared by chi-square and protein levels were compared using ANOVA with Bonferroni adjustment. RESULT(S): The transcriptomic classifier identified 32% (41) inflammopathic, 50% (65) adaptive and 18% (24) coagulopathic subjects. The inflammopathic group had more patients requiring mechanical ventilation (39% vs 9% vs 21%;p < 0.001) and higher 90-day mortality (32% vs 8% vs 13%, p = 0.016). Inflammatory cytokines IL8 and IL10 were significantly higher in inflammopathic compared to adaptive (p=0.038 and p=0.017 respectively), but not compared to coagulopathic (p>0.99 and p=0.24, respectively). Both the inflammopathic and coagulopathic groups expressed higher IL1RL1 and interferon-gamma compared to adaptive (IL1RL1;p< 0.001, p=0.002, IFNg;p=0.007, p=0.001). Plasma IL6 and IL1RA did not differ between groups, nor did many vascular proteins. The inflammopathic group expressed higher sICAM (p=0.049 vs adaptive) and lower ADAMTS13 compared to the adaptive group, and the coagulopathic group did not differ in its vascular protein expression. CONCLUSION(S): Transcriptomic subphenotypes are present in COVID-19 sepsis at similar proportions to non-COVID-19 sepsis. Inflammopathic subjects manifested higher severity of illness at admission, higher expression of inflammatory proteins and higher mortality. Markers of vascular injury did not distinguish the coagulopathic group. Integrating RNA and protein expression may offer new insights to host immune dysregulation during COVID sepsis.

5.
Indian Heart Journal ; 74(Supplement 1):S7, 2022.
Article in English | EMBASE | ID: covidwho-2179318

ABSTRACT

Background: Coronary re-interventions after CABG are generally preferably percutaneous, and may be related to progression of atherosclerosis due to pre-existing risk factors and may be influenced by operator experience, type of surgery-(off pump or on-pump), and conduits used. We analysed the demographics, patient and operative characteristics, clinical features of patients undergoing early re-interventions - arbitrarily defined as within 2 years of index "primary" CABG for this study (i.e. no prior percutaneous coronary interventions) to determine predictors of the same. Method(s): We collected data on 1367 patients who underwent primary CABG over a decade from Jan 1,2010 to Jan 1 2020( pre-COVID).Demographic and clinical risk factors for CAD, angiographic characteristics, pattern of CAD, electrocardiographic (ECG) changes, and prevalent LV function were evaluated at baseline, immediate post-op and on follow ups till the need of the next intervention. Patients who underwent re-intervention in the said period were compared with an age- and gender- matched population who did not undergo re interventions to determine predictors for re-intervention by both Logistic regression and Machine learning analysis using SVM, KNN and Naive Bayes Classifier Results: 160 patients ( 11.7%) patients underwent re-intervention within 2 years of the primary CABG. Multivariate backward logistic regression analysis and Machine learning analysis with three models revealed that re-intervention was performed significantly more frequent in patients with : Index admission with uncontrolled diabetes mellitus (strongest risk factor), patient age < 50 years, emergency CABG -Both as primary CABG or bail-out for PCI complications, Use of saphenous vein graft v/s total arterial revascularisation ( except RIMA usage), those undergoing off- pump CABG, failure of DAPT to continue beyond three months, CABG following recent acute coronary syndrome, CABG in Multivessel disease with Syntax score> 27 need of mechanical support following CABG ( IABP), higher ventilation requirement with delayed sternal course, patients with post-op renal insufficiency with /without undergoing assisted renal replacement, statin intolerance/ lower doses, and CABG with more than 4 grafts(all p < 0.001). Patients with carotid disease and peripheral disease were also higher in number in the re-intervened arm. Re-interventions were more common in patients with LVEF > 50% at time of need of re-intervention, but this may be attributed to selection bias due to preference for conservative management if the LVEF was too low on follow up. Conclusion(s): Predictors for early re-intervention after CABG are a pointer towards more aggressive "malignant" form of atherosclerosis. There is actually higher graft loss in younger age especially in emergency CABG, patients with uncontrolled DM, renal insufficiency and high SS, and inadequate statin usage- all of which may contribute to( or indicate towards) an inflammatory process of atherosclerosis. Knowledge of these risk factors may guide the surgeon in counselling the patient for possible graft loss as well as suitably plan the surgical course in reducing re-intervention. Copyright © 2022

6.
Expert Systems with Applications ; : 119549, 2023.
Article in English | ScienceDirect | ID: covidwho-2178608

ABSTRACT

The sudden outbreak of COVID-19 has dramatically altered the state of the global economy, and the stock market has become more volatile and even fallen sharply as a result of its negative impact, heightening investors' apprehension regarding the correlation between unexpected events and stock market volatility. Additionally, internal and external characteristics coexist in the stock market. Existing research has struggled to extract more effective stock market features during the COVID-19 outbreak using a single time-series neural network model. This paper presents a framework for multitasking learning-based stock market forecasting (COVID-19-MLSF), which can extract the internal and external features of the stock market and their relationships effectively during COVID-19.The innovation comprises three components: designing a new market sentiment index (NMSI) and COVID-19 index to represent the external characteristics of the stock market during the COVID-19 pandemic. Besides,it introduces a multi-task learning framework to extract global and local features of the stock market.Moreover, a temporal convolutional neural network with a multi-scale attention mechanism is designed (MA-TCN) alongside a Multi-View Convolutional-Bidirectional Recurrent Neural Network with Temporal Attention (MVCNN-BiLSTM-Att), adjusting the model to account for the changing status of COVID-19 and its impact on the stock market. Experiments indicate that our model achieves superior performance both in terms of predicting the accuracy of the China CSI 300 Index during the COVID-19 period and in terms of sing market trading.

7.
Virtual Meeting of the Mexican Statistical Association, AME 2020 and 34FNE meeting, 2021 ; 397:65-80, 2022.
Article in English | Scopus | ID: covidwho-2173617

ABSTRACT

The potential need of hospitalization for patients with acute respiratory COVID-19 infection caused by the SARS-CoV2 virus is a critical decision, as it has a direct effect on the potential response. In addition, it leads to an allocation of resources (bed, care, and medical personnel) that, given the pandemic, are limited. According to official information reported since March 1, 2020 and updated to June 30, 2021, an ensemble of classifiers weighted by the cross-entropy information measure is proposed. We considered data based on the knowledge of a set of features before a wide availability of vaccines or identified variants of the virus were present. The aim is to contribute toward the enhancement of a better-informed assessment of risk by the general population when exposed to the disease in the aforementioned period. The results show an improvement in the detection of cases susceptible to hospitalization, with an accuracy of 91.46%, and in a restrictive scenario, there is a preventive alert to patients, even though under the established criteria should not be admitted, to remain under monitoring to anticipate the evolution of the disease to a severe stage. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

8.
Internetworking Indonesia ; 13(2):29-34, 2021.
Article in English | Web of Science | ID: covidwho-2169210

ABSTRACT

The The COVID-19 pandemic is a problem that worries the wider community. To stop the spread of COVID-19, the mandatory health protocol to use masks is enforced. Many people do not comply with these health protocols. Based on these problems, a technology was developed to monitor the face that uses a mask or not used. This technology uses the Viola-Jones algorithm. In carrying out its detection function, this algorithm requires a classifier which is the result of training on some positive and negative image data sets. In this study, two positive image data sets were used: facial data using masks and facial data not using masks. The classifier obtained from the training process is a cascade file in XML format that will be used in the detection program. In this study, several training processes were carried out to obtain a good comparison value between positive and negative dataset samples in forming a cascade. The cascade test with the highest accuracy value was obtained from the classifier using 1000 positive samples and 2000 negative samples, namely 98.70% for face detection without a mask and 92.63% for face detection using a mask.

9.
NeuroQuantology ; 20(20):1379-1393, 2022.
Article in English | EMBASE | ID: covidwho-2206898

ABSTRACT

Covid-19 is a highly contagious disease that can easily spread from infected person through mouth or nose when they breathe, sneeze, speak etc. Because of its highly contagious nature, it makes large number of people sick at a pace that can destroy any country's health system. Although most of the young and fit people have seen mild impact of Covid-19, it has proven to be severe to highly severe in people with comorbidities. Covid19 has changed the way we live and work and is making huge impact in economic, social, political environments. Diagnosis of coronavirus can be done through different tests and tools. This paper includes the role of machine learning in diagnosis of coronavirus from chest X-rays. Three commonly used classifiers were used i.e., Logistic Regression, XGBoost, and Random Forest and final model is created using all these algorithms. The main focus is achieve high accuracy. To fasten the learning process, Principal Component Analysis (PCA) is also integrated and also high discriminate features are used in order to achieve better accuracy. We have used dataset containing Chest X-Ray images for this study. Our proposed work of PCA with Ensemble Learning algorithms have shown promising signs with better results for identification of positive cases. Copyright © 2022, Anka Publishers. All rights reserved.

10.
Journal of Pharmaceutical Negative Results ; 13:5392-5403, 2022.
Article in English | EMBASE | ID: covidwho-2206794

ABSTRACT

Corona Virus Disease (Covid-19) is a label species of the Corona virus family. It can cause a variety of illnesses, from the ordinary cold to advanced respiratory syndromes like Middle-East Respiratory Syndrome (MERS) and Severe Acute Respiratory Syndrome (SARS). This virus is highly contagious and spreads due to the droplets produced by coughing and sneezing. Though there are several ways to prevent the transmission of Covid-19, one of the most important and effective way is using a face mask or a face shield. In this paper, we constructed face mask detection framework using Viola-Jones algorithm in order to recognize whether an individual is wearing a mask or not. This algorithm includes the selection of Haar features of a face, integral image creation, adaptive boost training and cascading. An extensive study is carried out in order to analyze the performance of the proposed approach;we use a large facial image dataset from the publicly available MAFA dataset. The results indicate the proposed method can accurately identify face mask wearing images with a classifier accuracy of 98.26%, suggesting it might be useful in Covid-19 prevention. Copyright © 2022 Wolters Kluwer Medknow Publications. All rights reserved.

11.
2022 International Symposium on Information Technology and Digital Innovation, ISITDI 2022 ; : 16-21, 2022.
Article in English | Scopus | ID: covidwho-2161434

ABSTRACT

Covid-19 is a new virus that appeared in the city of Wuhan in 2019. This virus spreads very quickly even to Indonesia. One effort that can be done to detect the presence of this virus is the PCR and antigen test. Increasing this case resulted in a medical team having difficulty detecting suspects exposed to viruses. This research was conducted to find the best classification algorithm in predicting and classifying status on the suspected Covid-19 both exposed or not exposed. The method used in this study is Naïve Bayes, C4.5 and K-Nearest Neighbor which have very high accuracy using secondary data from the Dumai City Health Agency. From this study it was found that the algorithm C4.5 as the best algorithm in predicting the status of COVID-19 patients, especially in the city of Dumai with an accuracy of 86.54%, recall 71.51%and precision 85.14%. This study has implications for further researchers in choosing an algorithm to predict the COVID-19 case. © 2022 IEEE.

12.
2021 IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2021 ; : 14-17, 2021.
Article in English | Scopus | ID: covidwho-2152513

ABSTRACT

Importance of online education can be seen especially during the ongoing Covid-19 when going to schools or colleges is not possible. So validity of online exams should also be maintained with respect to traditional pen-paper examinations. However, absence of invigilator makes it easy for the examinees to cheat during the exam. Though there are already many systems for online proctoring, not all educational institutes can afford them as the systems are very expensive. In this paper, we have used eye gaze and head pose estimation as the main features to design our online proctoring system. Therefore, the purpose of this paper is to use these features to create an online proctoring system using computer vision and machine learning and stop cheating attempts in exams. © 2021 IEEE.

13.
2022 International Conference on Edge Computing and Applications, ICECAA 2022 ; : 1559-1564, 2022.
Article in English | Scopus | ID: covidwho-2152470

ABSTRACT

Worldwide, the (COVID-19) pandemic had also affected people's daily routines. In general also during lockdown periods, people around the world use social media to express their thoughts and feelings about the epidemic which has interrupted their daily lives. There has been a huge spike in tweets about coronavirus on Twitter in a short period of time, including both positive and negative messages. As a result of the wide range of content in the tweets, the researchers have turned to sentiment analysis in order to gauge how the general public feels about COVID-19. According to the findings of this study, the best way to examine COVID-19 is to look athow people use Twitter to share theirthoughts and opinions. Sentiment categorization can be accomplished by utilising a variety of feature sets as well as classifiers in combination with the suggested approach. Tweets collected from people with COVID-19 perceptions can be used to better understand and manage the epidemic. Positive, negative, as well as neutral emotion classifications are being usedto classify tweets. In this study, Tweets containing specific information about the Coronavirus epidemic are used as sentiment analysis packages. Bidirectional Encoder Representations from Transformers (BERT) are used to identify sentiment categories, whereas the TF-IDF (term frequency-inverse document frequency) prototype is used to summarise the topics of postings. Trend analysis and qualitative methods are being used to identify negative sentiment traits. In general, when it comes to sentiment classification, the fine-tuned BERT is very accurate. In addition, the COVID-19related post features of TF-IDF themes are accurately conveyed. Coronavirus tweet sentiments are analysedusing a BERT and TF-IDF hybrid classifier. Single-sentence classification is transformedinto pair-sentence classification, which solves BERT's performance issue in text classification problems. Our evaluation measures (accuracy= 0.70;precision= 0.67;recall= 0.64;and F1-score= 0.65) are used to evaluate the effectiveness of the classifier. © 2022 IEEE.

14.
Journal of Pharmaceutical Negative Results ; 13:713-722, 2022.
Article in English | EMBASE | ID: covidwho-2164814

ABSTRACT

Aim: The primary aim of this research is to increase the intensity percentage of personage traits detection to reveal the impact of coronavirus on Twitter users by utilizing machine learning classifier algorithms by comparing Novel Naive Bayes Classifier algorithm and Logistic Regression algorithm. Material(s) and Method(s): Naive Bayes Classifier algorithm with test size=10 and Logistic Regression algorithm with test size=10 was estimated several times to envision the efficiency percentage with confidence interval of 95% and G-power (value=0.8). Naive Bayes classifier compares whether a specific feature in a class is unrelated to another feature. A logistic regression model predicts the probability of an item belonging to one group or another. Results and Discussion: Naive Bayes algorithm has greater efficiency (86%) when compared to Logistic Regression efficiency (60%). The results achieved with significance value p=0.169 (p>0.05) shows that two groups are statistically insignificant. Conclusion(s): Naive Bayes Algorithm executes remarkably greater than the Logistic Regression algorithm. Copyright © 2022 Wolters Kluwer Medknow Publications. All rights reserved.

15.
Endocrine ; 2022 Nov 29.
Article in English | MEDLINE | ID: covidwho-2129150

ABSTRACT

PURPOSE: To assess the prognostic value of serum TSH in Greek patients with COVID-19 and compare it with that of commonly used prognostic biomarkers. METHODS: Retrospective study of 128 COVID-19 in patients with no history of thyroid disease. Serum TSH, albumin, CRP, ferritin, and D-dimers were measured at admission. Outcomes were classified as "favorable" (discharge from hospital) and "adverse" (intubation or in-hospital death of any cause). The prognostic performance of TSH and other indices was assessed using binary logistic regression, machine learning classifiers, and ROC curve analysis. RESULTS: Patients with adverse outcomes had significantly lower TSH compared to those with favorable outcomes (0.61 versus 1.09 mIU/L, p < 0.001). Binary logistic regression with sex, age, TSH, albumin, CRP, ferritin, and D-dimers as covariates showed that only albumin (p < 0.001) and TSH (p = 0.006) were significantly predictive of the outcome. Serum TSH below the optimal cut-off value of 0.5 mIU/L was associated with an odds ratio of 4.13 (95% C.I.: 1.41-12.05) for adverse outcome. Artificial neural network analysis showed that the prognostic importance of TSH was second only to that of albumin. However, the prognostic accuracy of low TSH was limited, with an AUC of 69.5%, compared to albumin's 86.9%. A Naïve Bayes classifier based on the combination of serum albumin and TSH levels achieved high prognostic accuracy (AUC 99.2%). CONCLUSION: Low serum TSH is independently associated with adverse outcome in hospitalized Greek patients with COVID-19 but its prognostic utility is limited. The integration of serum TSH into machine learning classifiers in combination with other biomarkers enables outcome prediction with high accuracy.

16.
NeuroQuantology ; 20(13):1984-1990, 2022.
Article in English | EMBASE | ID: covidwho-2145492

ABSTRACT

Web of Things (IoT) with profound learning (DL) is definitely developing and assumes a critical part in numerous applications, including clinical and medical care frameworks. It can assist clients in this field with getting a benefit as far as upgraded touchless verification, particularly in spreading irresistible illnesses like Covid sickness 2019 (Coronavirus). Despite the fact that there is various accessible security frameworks, they experience the ill effects of at least one of issues, like character extortion, loss of keys and passwords, or spreading sicknesses through touch confirmation instruments. To beat these issues, IoT-based keen control clinical validation frameworks utilizing DL models are proposed to improve the security element of clinical and medical services puts actually. This work applies IoT with DL models to perceive human appearances for verification in savvy control clinical frameworks. We use Raspberry Pi (RPi) on the grounds that it has minimal expense and goes about as the principal regulator in this framework. The establishment of a brilliant control framework utilizing broadly useful info/yield (GPIO) pins of RPi likewise upgraded the antitheft for savvy locks, and the RPi is associated with shrewd entryways. For client validation, a camera module is utilized to catch the face picture and contrast them and information base pictures for gaining admittance. The proposed approach performs face location utilizing the Haar overflow procedures, while for face acknowledgment, the framework involves the accompanying advances. The initial step is the facial component extraction step, which is finished utilizing the pretrained CNN models (ResNet-50 and VGG-16) alongside direct twofold example histogram (LBPH) calculation. The subsequent step is the characterization step which should be possible utilizing a help vector machine (SVM) classifier. Just ordered face as veritable prompts open the entryway;in any case, the entryway is locked, and the framework sends a notice email to the home/clinical spot with identified face pictures and stores the recognized individual name and time data on the SQL data set. The near investigation of this work shows that the methodology accomplished 99.56% precision contrasted and a few different related techniques. Copyright © 2022, Anka Publishers. All rights reserved.

17.
NeuroQuantology ; 20(9):6610-6615, 2022.
Article in English | EMBASE | ID: covidwho-2145472

ABSTRACT

Pandemic was present for the entire world from 2019 to 20. Due to this reason the workload for doctors and other healthcare professionals were increased. This workload will be eased by machine learning and the development of computer-aided analytical systems. The goal of the proposed methodology is towards the prevalence of COVID-19 to cost/benefit predictions on real-life dataset. Our proposed methodology is given for weka classification for the accuracy measurement ratios by applying 1R machine learning classifiers Considering the development of clustering with positive and negative occurrences ratios in terms of cost-benefit analysis's initial care projections. In this study 1R Supervised Machine Learning Algorithm have been applied to Covid 19 dataset provided by healthcare organization. The best classification accuracy is obtained from the algorithm of 1R with 75.54%. In this paper visualization Cost/Benefit Analysis and also analysed. Copyright © 2022, Anka Publishers. All rights reserved.

18.
10th IEEE Region 10 Humanitarian Technology Conference, R10-HTC 2022 ; 2022-September:288-293, 2022.
Article in English | Scopus | ID: covidwho-2136456

ABSTRACT

Internet adoption has increased rapidly during the worldwide COVID-19 pandemic. Nowadays people not only prefer to shop using various e-commerce platforms, but also like to provide feedback and express their opinions and experiences using the online platforms. Since new customers try to understand the products' utility and acceptability from other consumers' reviews, it has become crucial to analyze the customers' sentiments and opinions on each product. In this paper, we have presented a sentiment analysis technique on the basis of product reviews written in Bangla language to better understand the combined consumer perspective. Our work aims to compare existing classifiers' performance and find the best algorithm for our dataset. We collected reviews from the leading Bangla bookselling e-commerce site 'Rokomari.com' for this work. We implemented ML and DL classifier models and compared their overall performance on this dataset. The experimental studies show that the best accuracy is achieved from LSTM and SGD over the other implemented ML and DL based classifier models. © 2022 IEEE.

19.
4th IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2022 ; 2022.
Article in English | Scopus | ID: covidwho-2136362

ABSTRACT

COVID-19 was first identified in Wuhan (China) and swiftly spread over the world, resulting in a global pandemic emergency. It has had a profound effect on everyday living, general well-being, and international finance. Rapid diagnosis of susceptible people is critical. There is no precise testing for COVID-19 except for RT-PCR, which is expensive and time-consuming. Recent studies conducted using radiological imaging techniques suggest that such pictures include characteristics of the COVID-19 infection. The implication of machine learning algorithms in conjunction with chest imaging may aid in the accurate detection of this illness and help to overcome the shortage of specialized physicians. This work aims to construct a model for the automated recognition of COVID-19 infection using chest CT scans. To extract features from patient's chest CT scans, a convolutional neural network was used, and Principle Component Analysis was used to decrease computing cost. The proposed model (an ensemble of machine learning classifiers) was created to offer accurate diagnostics by incorporating the five categories (Normal, Mycoplasma pneumonia, Bacterial pneumonia, Viral pneumonia, and COVID-19). The proposed model reached an accuracy of 99.3%, positive predictive value (ppv) of 99.3%, and sensitivity of 99.2 %. © 2022 IEEE.

20.
7th International Conference on Information Management and Technology, ICIMTech 2022 ; : 57-61, 2022.
Article in English | Scopus | ID: covidwho-2136277

ABSTRACT

Right now, the world is busy with the COVID-19 pandemic. Coronavirus disease (COVID-19) itself is an infectious caused by a new variant of the newly discovered coronavirus. One way to deal with the virus is to get vaccinated against COVID-19. The government through the Indonesian Ministry of Health is also promoting the procurement of this COVID-19 vaccine by bringing various types of this COVID-19 vaccine. This research was conducted to know the sentiment and perception of the Indonesian people about the COVID-19 vaccination program. To find out, this research uses the Text Mining technique using Twitter as a data source. Data processing and analysis in this research used the Naive Bayes Classifier method using Python software. The results of this study show that the sentiment and perception of the Indonesian people to vaccination against COVID-19 is positive, as evidenced by the Confession Matrix value leaning towards True Positive. © 2022 IEEE.

SELECTION OF CITATIONS
SEARCH DETAIL