Watermarking Techniques Performance Analysis in Medical Images for Secure Communication

Over the past few years, most medical diagnostics and treatments have shifted to digital content. COVID-19 is a viral disease first identified in Wuhan, China 2019. Its pandemic caused a dramatic loss in human health, work, and food systems worldwide. WHO recommended social distancing as a preventive measure to protect ourselves from corona viral infections. Hence, now many avail hospitals facilities are online. It enables telemedicine where patients, doctors, and medical research units can easily share their digital medical information through various communication channels. At the receiver's end, the patient's record must not be lost or altered during transmission. As medical imaging contains many fine features, even small changes cause confusion among medical staff for diagnosis. One of the best techniques for image authentication is digital image watermarking. When developing an effective watermark method, it's necessary to have a balanced trade-off among imperceptibility, capacity, and robustness. The work gives a comprehensive survey of cryptography, biometrics, and blockchain-based on various watermarking schemes in medical images that gives new ideas to improve the already existing techniques. © 2022 IEEE.

COVID-19 Classification Using Medical Image Synthesis by Generative Adversarial Networks

The outbreak of novel coronavirus disease 2019, also called COVID-19, in Wuhan, China, began in December 2019. Since its outbreak, infectious disease has rapidly spread across the globe. The testing methods adopted by the medical practitioners gave false negatives, which is a big challenge. Medical imaging using deep learning can be adopted to speed up the testing process and avoid false negatives. This work proposes a novel approach, COVID-19 GAN, to perform coronavirus disease classification using medical image synthesis by a generative adversarial network. Detecting coronavirus infections from the chest X-ray images is very crucial for its early diagnosis and effective treatment. To boost the performance of the deep learning model and improve the accuracy of classification, synthetic data augmentation is performed using generative adversarial networks. Here, the available COVID-19 positive chest X-ray images are fed into the styleGAN2 model. The styleGAN model is trained, and the data necessary for training the deep learning model for coronavirus classification is generated. The generated COVID-19 positive chest X-ray images and the normal chest X-ray images are fed into the deep learning model for training. An accuracy of 99.78% is achieved in classifying chest X-ray images using CNN binary classifier model.

Comparative Study Based on Analysis of Coronavirus Disease (COVID-19) Detection and Prediction Using Machine Learning Models.

As the number of COVID-19 cases increases day by day, the situation and livelihood of people throughout the world deteriorates. The goal of this study is to use machine learning models to identify disease and forecast whether or not a person is infected with the virus or another common illness. More articles about COVID-19 will be released starting in 2020, but we still do not have a reliable prediction mechanism to diagnose the disease with 100% accuracy. This comparison is done to see which model is the most effective in detecting and predicting disease. Despite the fact that we have immunizations, we require a best-prediction strategy to assist all humans in surviving. Researchers claimed that the supervised learning method predicts more accurately than the unsupervised learning method in the majority of studies. Supervised learning is the process of mapping inputs to derived outputs using a set of variables and created functions. This will also help us to optimize performance criteria using experience. It is further divided into two categories: classification and regression. According to recent studies, classification models are more accurate than other models.

Assessment of academic performance with the e-mental health interventions in virtual learning environment using machine learning techniques: A hybrid approach

Background: The act of virtual learning is defined through learning and practicing in an environment using digital/electronic content for self-paced through online teaching and mentoring. It explicitly deals with the interaction in an asynchronous mode of learning. The quality of teaching-learning depends on the utilization of digital technologies with the advancement in educational technology. There is a need and evaluation for the assessment and estimation of the impact of e-mental health interventions with the students learning through the virtual learning environment. Purpose/Hypothesis: This research evaluates the psychotherapeutic support for the students to overcome the psychological distress during this COVID-19 pandemic by using machine learning techniques. This mechanism evaluates the efficacy of the academic performance made by the students during the pandemic situation. This analysis involves a hybrid approach for the assessment in machine learning using a genetic algorithm with an artificial neural network upon statistical evaluation. The psychological factors are determined with a keen focus on behaviourism, cognitivism, and social constructivism. The metrics have been evaluated based on digital technologies (ICT) in remote access, individual learning process, flexible learning, cost-effectiveness, time complexity and scalability. Design/Method: The design process involves the 775 student responses with 27 attributes with differentiation of labels corresponding to behaviourism, cognitivism, and social constructivism. The preprocessed data is fed to genetic algorithm with processing parameters focusing crossover and mutation probability and then classified using artificial neural network. The estimation of academic performance is made using the techniques followed in virtual learning environment such as: 1. Online quiz (Quizizz platform) - Individual assessment 2. Flipped classroom activity - Individual assessment 3. MOOCs online courses - Individual assessment 4. Prototype design - Team activity 5. Research proposal - Team activity From the assessment process the each of the student performance is evaluated with regard to the course outcome of individual student in the learning environment. The variation has also been observed with the applicability of ALS and traditional practice methods. Results: The hybrid approach found to be good in the assessment and evaluation of academic performance and health interventions in terms of accuracy (88.18%), precision (94.69%), recall (92.24%), RMS error (0.202) and correlation (0.844) respectively. The statistical analysis and evaluation have been made using Fisher’s F-Statistical test, and the P-value is found significantly to be P<0.001. From the experiments, the factors that contribute towards web-based learning, blended learning, and online learning has been differentiated with the psychotherapeutic factors. A total of 775 samples have been used for analysis with the applicability of ICT tools and the pedagogical practices for the course. The factors contributing towards Behaviorism with a focus on interaction and response towards the learning environment plays a significant role in varying the academic performance of the student of about 20% in total learning rate varied significantly. Step-by-step analysis in virtual learning provides a good initiative for the student’s community to have a variation in the learning process. Virtual learning is one of the good practices if the ICT in education, process and its principles adhere more efficiently. © 2021, Rajarambapu Institute Of Technology. All rights reserved.