Performance Analysis of Learner Behavior Through Online Learning Using Learning Management System

This paper discusses the performance analysis of learner behavior through online learning using Learning Management System (LMS). The analysis is performed based on the survey of lecturers and students activities. The parameters of survey consist of the problems discussion which arise in the online learning, the level of student absorption of lecture material, the level of student attendance, and the feedback on lecturer performance carried out by students. Problems that arise in the online learning include lecturers are not being able to control as much as 37%, network disturbances are as much as 22%, students having difficulty understanding lecture material are as much as 19% which are indicated by students with D score of 10%, C score of 60%, and B score of 30%. Meanwhile 17% of students use LMS and the remaining 5% have no problems with the online learning. On the other hand, students have difficulty obtaining connection for online learning of 45%, do not have a quota of 28%, and lazy of 17%. Lecturer performance feedback carried out by students based on competency parameters of pedagogic, personality, professionalism, and social shows very good score. © 2023 IEEE.

GPU libraries speed performance analysis for RCWA simulation matrix operations

Rigorous Coupled Wave Analysis (RCWA) method is highly efficient for the simulation of diffraction efficiency and field distribution patterns in periodic structures and textured optoelectronic devices. GPU has been increasingly used in complex scientific problems such as climate simulation and the latest Covid-19 spread model. In this paper, we break down the RCWA simulation problem to key computational steps (eigensystem solution, matrix inversion/multiplication) and investigate speed performance provided by optimized linear algebra GPU libraries in comparison to multithreaded Intel MKL CPU library running on IRIDIS 5 supercomputer (1 NVIDIA v100 GPU and 40 Intel Xeon Gold 6138 cores CPU). Our work shows that GPU outperforms CPU significantly for all required steps. Eigensystem solution becomes 60% faster, Matrix inversion improves with size achieving 8x faster for large matrixes. Most significantly, matrix multiplication becomes 40x faster for small and 5x faster for large matrix sizes. © 2023 SPIE.

Performance Analysis of VGG-16 Deep Learning Model for COVID-19 Detection using Chest X-Ray Images

COVID-19 is an infectious disease caused by newly discovered coronavirus. Currently, RT-PCR and Rapid Testing are used to test a person against COVID-19. These methods do not produce immediate results. Hence, we propose a solution to detect COVID-19 from chest X-ray images for immediate results. The solution is developed using a convolutional neural network architecture (VGG-16) model to extract features by transfer learning and a classification model to classify an input chest X-ray image as COVID-19 positive or negative. We introduced various parameters and computed the impact on the performance of the model to identify the parameters with high impact on the model's performance. The proposed solution is observed to provide best results compared to the existing ones. © 2023 Bharati Vidyapeeth, New Delhi.

On the Use of Conventional Neural Networks for COVID-19 Detection in CT-Scan Images: A Comparative Study and Performance Analysis

This paper presents a comprehensive study on deep learning for COVID-19 detection using CT-scan images. The proposed study investigates several Conventional Neural Networks (CNN) architectures such as AlexNet, ZFNet, VGGNet, and ResNet, and thus proposed a hybrid methodology base on merging the relevant optimized architectures considered for detecting COVID-19 from CT-scan images. The proposed methods have been assessed on real datasets, and the experimental results conducted have shown the effectiveness of the proposed methods, allowing achieving a higher accuracy up to 99%. © 2022 IEEE.

Performance Analysis of GAN Approaches in the Portable Chest X-Ray Synthetic Image Generation for COVID-19 Screening

COVID-19 mainly affects lung tissues, aspect that makes chest X-ray imaging useful to visualize this damage. In the context of the global pandemic, portable devices are advantageous for the daily practice. Furthermore, Computer-aided Diagnosis systems developed with Deep Learning algorithms can support the clinicians while making decisions. However, data scarcity is an issue that hinders this process. Thus, in this work, we propose the performance analysis of 3 different state-of-the-art Generative Adversarial Networks (GAN) approaches that are used for synthetic image generation to improve the task of automatic COVID-19 screening using chest X-ray images provided by portable devices. Particularly, the results demonstrate a significant improvement in terms of accuracy, that raises 5.28% using the images generated by the best image translation model. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Performance Analysis of Machine Learning Classification Approaches for Monkey Pox Disease Prediction

After covid-19 pandemic, many countries have the possibility of getting affected by Monkey Pox Virus. Monkey pox has the same symptoms of smallpox, chicken pox, and measles virus. In this work, the computational models are construed to predict the presence or absence of monkey pox virus. Eight different Classification algorithms including Decision Tree (DT), Random Forest Classification (RF), Naïve Bayes (NB), K-Nearest Neighbor algorithms (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Ada Boosting algorithm (AB), Gradient Boosting (GB) algorithm are used for the Classification of Monkey Pox disease. Four evaluation measures are used in this work to compute the accuracy of classification. Four measures F-Score, Accuracy, Precision, and Recall are used to compare the eight different types of classification algorithms. Based on experimental analysis, it was observed that highest accuracy of 71% is achieved by Gradient Boosting algorithm when compared to other algorithms. © 2022 IEEE.

Performance Analysis of Machine Learning Algorithms for COVID-19 Detection

The Novel Coronavirus Illness 2019 (COVID-19) was found in Wuhan, Hubei, China, in December 2019 and has since spread globally. When the patient's corona sickness worsened, his life was in danger. Coronavirus assaults the lungs. Diagnostic kits today only search for viral illnesses, which deceives doctors. All patients receiving the same treatment harm patients with less infection. This publication describes non-invasive treatment for infected people. Dissecting chest X-ray pictures to examine the coronavirus helps investigate and predict COVID-19 patients. We offer a hybrid method for detecting Covid. CNN and SVM identify Covid. Because X-ray pictures are inconsistent, CNN is used for feature extraction. To construct a training dataset before CNN, we used data augmentation. Data augmentation increases the training dataset's amount and quality. SVM is used for classification since it tolerates feature differences. The main goal is to help clinical doctors determine the severity of a chest infection so they can administer life-saving treatment. Deep learning and machine learning-based techniques will determine the degree of chest infection and lead to optimal medication, avoiding expensive treatment for all patients. © 2022 IEEE.

Service Quality Analysis of a Field Hospital during COVID-19 in Thailand

The objectives of this research are to explore dimensions of service quality and evaluate service quality expectations, perceptions and satisfactions of healthcare workers in a field hospital. Data were collected from 126 medical personnel who were caring for COVID-19 patients. The questionnaire was developed from guidelines for setting up field hospitals in Thailand. Exploratory Factor Analysis (EFA) extracted 7 dimensions, Service quality was analyzed with service gap analysis, Important Performance Analysis (IPA) and Priority nonconformity index (PNCI). The Gap analysis found that overall service quality was satisfactory. Infrastructure was a most satisfied dimension. Social responsibility was a most dissatisfaction. IPA showed logistics with risk management and administrative procedure were strength. The PNCI suggested to transfer resources from infrastructure medical service, occupational health and safety to improve personnel quality and social responsibility. © 2022 ACM.

Internet of Behavior and Brain Response Identification for Cognitive Performance Analysis

Learning efficiency analysis has evolved immensely in the aftermath of the COVID-19 epidemic. Technological methods for online learning and big data in the cloud have been applied to develop various curriculums;however, an analysis of learners' performance may only be done at a similar personal background group classification level. Therefore, this study presents a machine learning model for identifying cognitive performance under the principles and characteristics of the Internet of Behavior (IoB) and human brainwaves, which is more reliable than traditional data analysis. The proposed methodology can precisely classify learners according to their current cognitive performance of the brain through simple classification and IoB analysis that can immediately enhance class manipulation. © 2022 Asia-Pacific of Signal and Information Processing Association (APSIPA).

COVID 19 implementation of a partial database

The work is focused on database design and performance analysis. We chose data on COVID 19 in Slovakia. Their modification was preceded by a database design. We achieved the possibility of testing the system by subsequently creating tables and importing modified data. One of the last phases was the final analysis and design of indexes to optimize database performance. © 2022 IEEE.

Performance Analysis of the Triple Exponential Smoothing Method during the Covid19 Pandemic on Tourist Visit Data

Data forecasting methods are essential in the business world to determine the company's future steps. However, the COVID-19 pandemic has hit the tourism economy hard, resulting in a slump in income. In this study, trials were conducted to analyze the reliability of forecasting methods on data affected by the COVID-19 pandemic. The method used is the Triple Exponential Smoothing method involving two models, namely Additive and Multiplicative. In this paper, the test is carried out using actual data derived from data from a service company engaged in tourist crossing transportation. Each method's alpha, beta, and gamma values are determined based on the parameters that produce the smallest error value. The experiment results show the predictability of the Triple Exponential Smoothing method by measuring the prediction error value based on the Mean Absolute Percentage Error (MAPE) value, which was 7.56% in the Additive model and 10.32% in the Multiplicative model before the pandemic happened. However, both methods' prediction measurements during a pandemic produce poor forecasts with an error percentage above 40%. Meanwhile, during the decline in pandemic cases, the value of the Triple Exponential Smoothing Multiplicative method was closer to the actual data with a prediction error value of 33.02%. Therefore, the Triple Exponential Smoothing Multiplicative method is more resistant and suitable for implementing into a forecasting system with actual data that influences pandemic events. © 2022 IEEE.

Performance Analysis of Wiener filter in Restoration of Covid-19 Chest X-Ray Images, Ultrasound Images and Mammograms

Medical images such as X-Ray images, Mammograms and Ultrasound images are very useful diagnostic techniques used for understanding the functions of different internal organs, bones, tissues, etc. Most of the times these medical images are degraded by some noises and different kinds of blur. Image blurring and degradation leads to loss of quality of images which in hand causes difficulty in proper diagnosis. This paper emphases on the efficacy of Wiener filter in image de blurring and denoising Chest X-Ray of Covid-19 patients, ultrasound images of fetal abdominal cyst, umbilical cord cyst and Common Carotid Artery, Mammogram of both pathological and non-pathological breasts. Performance of Wiener filter is analyzed using image restoration parameters like Structural Similarity (SSIM), Histogram, Peak Signal to Noise Ratio and Mean Square Error. © 2022 IEEE.

Performance Analysis between YOLOv5s and YOLOv5m Model to Detect and Count Blood Cells: Deep Learning Approach

Blood cell identification and counting are essential nowadays for healthcare professionals and therapists treating a variety of diseases. Platelet detection and counting are commonly performed for various disorders such as COVID-19 and others. However, it is the most costly and time-consuming. Furthermore, it is not available everywhere. From that standpoint, it is necessary to develop an effective technological model for detecting and counting three fundamental kinds of blood cells: Platelets, Red Blood Cells (RBCs), and White Blood Cells (WBCs). So, a deep learning-based model is proposed in this study comparing two versions of YOLOv5 model such as YOLOv5s and YOLOv5m. It is found that the YOLOv5m model outperforms with 0.799 precision, where YOLOv5s produces 0.797 precision. The study suggests that the YOLOv5m model is highly capable of detecting and counting the blood cells individually. Doctors, physicians, and other clinicians will be capable to identify and quantify blood cells from real-time photos. It will save money and time by identifying and counting blood cells using real-time blood photos. © 2022 ACM.

VVC intra prediction decoder: Feature improvement and performance analysis

Nowadays, streaming applications have been in great demand, especially due to covid-19 (teleworking, online teaching, virtual reality, etc.). In addition, artificial intelligence has become widely used especially in video processing domains, so a video with high quality improves the accuracy rate of this application. To meet these needs, the Versatile Video Coding standard (VVC) has appeared to give a high compression efficiency compared to high-efficiency video coding. This norm consists of a high complexity algorithm that offers an improvement in processing time and decreases the bit rate by 50 % thanks to several new compression techniques. In this context, we propose the implementation of an intra prediction decoding chain of this standard on a system on chip. In this work, we highlight the VVC feature enhancements, we present the suitable method for VVC intra-prediction decoder implementation on the PYNQ-Z2, and we provide profiling in terms of decoding time and power consumption. As a future work, this study is helpful to distinguish the block that will be a candidate for a Hardware acceleration. © 2022 IEEE.

Performance Analysis of KNN Algorithm to Improve the Process of Hemodialysis on Post-Covid-19 Patients

A recent study shows that covid-19 infected patients are having more probability of developing acute kidney injury that may leads to loss of kidney functionality. Hemodialysis is a process of removing the waste and excess fluids from the blood. Nowadays, because of covid-19, people prefer for home dialysis rather than taking dialysis in the hospitals. Generally, in the patients starting dialysis, almost, 23 percent of patients died in first month due to improper monitoring during the process of dialysis. Here, we have proposed an approach for real-time monitoring and health prediction. Our aim is to predict the probability of success, by analyzing the data using the popular classification techniques of machine learning which gives the maximum rate of accuracy to predict the outcome of dialysis. The system designed will collect the patient’s parameters such as temperature, blood pressure, and pulse rate during home dialysis. The stored data are then processed to check for any air bubbles or blood leakage occurrences. In such occurrences, the patient’s family is immediately alerted through an SMS to take the patient to hospital. This system helps to reduce the mortality rate after the dialysis treatment. Results prove that the KNN algorithm shows improvement in prediction accuracy of about 14%, 8%, and 5% when compared with logistic regression, SVM, and Naïve Bayes algorithms. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Performance Analysis of VGG-19 Deep Learning Model for COVID-19 Detection

Various clinical studies and researchers have established that chest CT scans provide an accurate clinical diagnosis on the detection of COVID-19. The traditional gold standard RT-PCR testing methodology might give false positive and false negative results than the desired rates. AI has proven to be the driving force in developing various COVID-19 management tools. Provided with the situation of lack of datasets, we applied a transfer learning approach to detect COVID-19 from chest CT images. The previous work observed that the VGG-19 has better performance with medical image data compared to other deep learning models such as VGG-16, InceptionV3, DenseNet121, which showed overfitting in the initial epochs. This study determined the best performing parameters for the VGG-19 transfer learning model to classify COVID-19 cases and healthy cases. We experimented with the model against three parameters: activation function, loss function, and training batch size. After the analysis, we found that the VGG-19 model with SoftMax activation function, Categorical cross-entropy loss function, and training batch size as 32 has the highest accuracy of 93%. © 2022 Bharati Vidyapeeth, New Delhi.

Hardware-accelerated Simulation-based Inference of Stochastic Epidemiology Models for COVID-19

Epidemiology models are central to understanding and controlling large-scale pandemics. Several epidemiology models require simulation-based inference such as Approximate Bayesian Computation (ABC) to fit their parameters to observations. ABC inference is highly amenable to efficient hardware acceleration. In this work, we develop parallel ABC inference of a stochastic epidemiology model for COVID-19. The statistical inference framework is implemented and compared on Intel's Xeon CPU, NVIDIA's Tesla V100 GPU, Google's V2 Tensor Processing Unit (TPU), and the Graphcore's Mk1 Intelligence Processing Unit (IPU), and the results are discussed in the context of their computational architectures. Results show that TPUs are 3×, GPUs are 4×, and IPUs are 30× faster than Xeon CPUs. Extensive performance analysis indicates that the difference between IPU and GPU can be attributed to higher communication bandwidth, closeness of memory to compute, and higher compute power in the IPU. The proposed framework scales across 16 IPUs, with scaling overhead not exceeding 8% for the experiments performed. We present an example of our framework in practice, performing inference on the epidemiology model across three countries and giving a brief overview of the results. © 2022 Association for Computing Machinery.

Analyzing the Sentiments by Classifying the Tweets Based on COVID-19 Using Machine Learning Classifiers

In the current scenario, almost all the countries face one of the biggest disasters in COVID-19. This paper has to analyze the tweets related to COVID 19 and discuss the various machine learning algorithms and their performance analysis on the tweets associated with COVID-19. The implemented classification algorithms are applied to classify the sentiments to predict whether they relate to COVID-19 or non-COVID-19. Ten most popular classification algorithms implemented. The Linear Support Vector Machine (LSVM) achieved the highest test accuracy in these algorithms with 90.3%. Logistic regression has performed better in recall with 96.06%, F1 score of 90.46%, ROC_AUC with 90.48%. Random forest classifier has achieved the better specificity and precision of 99.16% and 96.3%, respectively. Out of all, stochastic gradient descent (SGD) has attained better results in all the computational parameters. © 2021 IEEE.

CRaaS: Cyber Range as a Service

The Internet and networking have evolved substantially into new forms and types. These technologies are used by everyone in the 21st century. After the COVID pandemic, everything has become more virtual, and most transactions, including studies, were accomplished online. With the growth in technology and services, the risk of them being exploited increases. Cybersecurity is a collection of technologies, procedures, and practices aimed at preventing attacks, damage, and illegal access to networks, devices, programs, and data. Overcoming the cybersecurity challenges is even more complicated due to the lack of training and unavailable cybersecurity environments. Cybersecurity experiments must be run in a realistic and controllable environment. In this work, we have set up a virtual environment to provide the required resources for the user to learn cybersecurity skills. We have demonstrated eight cyber attacks. Each attack is provided with a demo video and an automated version of the attack. The user is provided with steps to practice how the attack works and instructions to mitigate these attacks. These resources are made available on-demand to the user through a web portal. The performance analysis has been done for every attack. The launch time of the automated attacks is also recorded and analyzed. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Development Wells Optimum Management Technique Coping with Production Curtailment for Stacked Oilfields Consisting of Multiple Complex Reservoirs

Affected by the Covid-19 pandemic and low oil prices, OPEC members were forced to curtail production. The H oilfield in Iraq commenced production curtailment in early March 2020 and then oil production gradually decreased. By the end of 2020, production was less than one-third of the rate before curtailment. There are multiple sets of oil-bearing formations in the H Oilfield vertically. The developed oil reservoirs have a total of more than three hundreds development wells. The reservoir types are diverse, the relationship among multiphase fluids is complex, and the development methods are different. The reduction of the daily production will inevitably require a comprehensive strategy adjustment to cope with the new situation. Any intentional or unintentional shut-in has a price. Therefore, the key is how to reasonably control the production in many oil reservoirs and re-adjust the oil reservoir development plan at the minimum cost while meeting the overall changing production restriction target for each oil reservoir. In this study, the author established a simple and fast process for judging open and closed wells through years of experience in reservoir dynamic analysis and field management. Step 1: Wells are classified according to production characteristics. For pre-selected wells, some wells with unique functions that need to be opened and those that need to be closed for objective reasons should be excluded. Step 2: Conduct single well cost analysis with reference to production status. Respectively evaluate the performance of the production well under the state of opening and closing. Step 3: Establish the model with economic indicators as the objective function. According to different goals, the model established is slightly different. Step 4: Optimize the best solution based on actual needs. Solve the optimal solution under the target and optimize the number of reasonably configured wells in each reservoir. Through this process, combined with historical and current actual production conditions, different types of oil wells in all reservoirs are classified. Their priorities of reopening are evaluated to meet the needs of other production restriction targets and ensure the smooth transition of oilfield development. © Copyright 2021, Society of Petroleum Engineers