One of the deadly diseases in recent years is covid19 which is affecting the lives of peoples. Also leading to severe adverse problems and death. Prevention is done using early diagnosis and medication which in turn helps in early detection of the disease. The basic aim of the paper is to identify and further classify the patients using the chest x-rays. From scratch the Convolutional Neural Network is diagnosed producing a very high accurate and optimum results. In recent years, researchers found out that in the radiological images such as like x-rays, the traces of covid-19 can be found. In few areas, a good accuracy of the covid-19 detection cannot be achieved due to lack of the people who test so the artificial intelligence is combined with the radiological image. In machine learning the models used are deep learning by automatizing the actions and making it certain by swift, skillful and proficient outcome produced by the chest images provided by the patients. There are several layers like convolutional layer, max pooling layer etc. which are initiated and are used with aid of ReLU activation function. These images given as inputs are also classified accordingly. There is a sequence of neurons being given as input to the active dense layer and there is a result to the input by a sigmoidal function. There is a rise in efficiency because the models are trained and there is a decline of loss at the same time. If there is a model where fitting is done earlier to the overfitting and is restricted from implementing in the data augmentation. There is a better and efficient involvement of suggestions to models of deep learning. Further there is a classification of chest images for identifying and analyzing covid19. So, to check the Covid detection, the images are used as raw. In this paper a model is proposed to have good accuracy in the classification between Covid and normal and further it can be classified into three categories like Covid, pneumonia, normal. There is a 98.08% for the first one and 87.02% for the second one. By introducing 17 convolutional layers and using the Darknet model used for classifying you only look once (YOLO) for the live identification of the objects and multiple layers of filters are used. In the model there is an initial screening.

Covid-19 Classification and Detection Model using Deep Learning

The main objective of this research is to use machine learning algorithms to locate people stranded by an earthquake or other big disasters. Disasters are often unpredictable, they can result in significant economic loss, and the survivors may struggle with despair and other mental health issues. The time, the victim’s precise location, the possible condition of the victim, the resources and manpower on hand are the main challenges the rescue team must deal with. This article examines a model that gathers data and, using that data, predicts risk analysis and probability of finding the shortest distance to reach the person in need. Using a drone equipped with RF-pose technology and EHT sensors, it will be able to locate any individuals trapped inside a collapsed structure. To determine the dataset’s extreme points and the shortest route to the victim’s location by using the Dijkstra’s algorithms. The primary aim of this article is to discuss the idea of applying these ML (Machine Learning) algorithms and creating a model that aids in rescuing those trapped beneath collapsed buildings. Devices that are part of the Internet of Things (IoT) have grown in popularity over the past few years as a result of their capacity for data collection and transmission. Particularly in disaster management, search and rescue operations, and other related disciplines, drones have shown to be useful IoT devices. These tools are perfect for emergency response circumstances because they can be utilized to access locations that are hard to get to or too dangerous for humans. Drones with cameras and other sensors can be used in disaster management to gather data in real-time on the severity of the damage caused by earthquakes and other disasters. The afflicted area may be mapped out with their help, and they can also be used to find survivors and spot dangerous places that should be avoided. The rescue operation can then be planned and the resource allocation made more efficient using this information. Drones can be used in search and rescue operations to find and follow people who are stuck or lost. Drones can be equipped with the RF-pose sensors used in the research described in the abstract to assist in locating people who are buried under debris. Thermal camera-equipped drones can also be used to locate people in low-light or night-time conditions by detecting their body heat. The capacity of drones to offer real-time data is one of the benefits particularly disaster management.

Rescue Operation with RF Pose Enabled Drones in Earthquake Zones

The main objective of this research is to use machine learning algorithms to locate people stranded by an earthquake or other big disasters. Disasters are often unpredictable, they can result in significant economic loss, and the survivors may struggle with despair and other mental health issues. The time, the victim’s precise location, the possible condition of the victim, the resources and manpower on hand are the main challenges the rescue team must deal with. This article examines a model that gathers data and, using that data, predicts risk analysis and probability of finding the shortest distance to reach the person in need. Using a drone equipped with RF-pose technology and EHT sensors, it will be able to locate any individuals trapped inside a collapsed structure. To determine the dataset’s extreme points and the shortest route to the victim’s location by using the Dijkstra’s algorithms. The primary aim of this article is to discuss the idea of applying these ML (Machine Learning) algorithms and creating a model that aids in rescuing those trapped beneath collapsed buildings. Devices that are part of the Internet of Things (IoT) have grown in popularity over the past few years as a result of their capacity for data collection and transmission. Particularly in disaster management, search and rescue operations, and other related disciplines, drones have shown to be useful IoT devices. These tools are perfect for emergency response circumstances because they can be utilized to access locations that are hard to get to or too dangerous for humans. Drones with cameras and other sensors can be used in disaster management to gather data in real-time on the severity of the damage caused by earthquakes and other disasters. The afflicted area may be mapped out with their help, and they can also be used to find survivors and spot dangerous places that should be avoided. The rescue operation can then be planned and the resource allocation made more efficient using this information. Drones can be used in search and rescue operations to find and follow people who are stuck or lost. Drones can be equipped with the RF-pose sensors used in the research described in the abstract to assist in locating people who are buried under debris. Thermal camera-equipped drones can also be used to locate people in low-light or night-time conditions by detecting their body heat. The capacity of drones to offer real-time data is one of the benefits particularly disaster management. 

Cancer is one of the most fatal diseases in the world and the leading cause for most deaths worldwide. Diagnosing cancer early has become the need of the day for doctors and researchers as it allows them to categorize patients as high-risk and low-risk categories which will eventually help them in correct diagnosis and treatment. Machine learning is a subset of artificial intelligence that makes use of raw data to make predictions and insights. Using machine learning for cancer prognosis has been under study for a long time and several papers have been published regarding the same. Even though many papers have been published on the usage of statistical methods for cancer prognosis, it has been proved that machine learning models provide more accuracy when compared to conventional statistical methods of detection. These machines can be trained to detect abnormalities such as a tumour by looking at real-world examples. Models such as artificial neural networks, decision trees, clustering techniques, and K-Nearest-Neighbours (KNNs) are being used for cancer prediction, prognosis and also research purposes. The key aim of this article is to go through the popular key trends in using machine learning algorithms for cancer prognosis, types of input datasets to be fed, different types of cancers that can be studied and also the performance of these models. 

Cancer Prognosis by Using Machine Learning and Data Science: A Systematic Review

This research work has studied about the utilization of machine learning algorithms in bioinformatics. The primary purpose of studying this is to understand bioinformatics and different machine algorithms which are used to analyze the biological data present with us. This research study discusses about different machine learning approaches like supervised, unsupervised, and reinforcement which play an essential role in understanding and analyzing biological data. Machine learning is helping us to solve a wide range of bioinformatics problems by describing a wide range of genomics sequences and analyzing vast amounts of genomic data. One of the biggest real-world problems is that machine learning is helping us to identify cancer with a given gene expression, which is done using a support vector machine. In addition, this study discusses about the classification of molecular data, which will help find out minor diseases. With the advancement of machine learning in healthcare and other related applications, data collection becomes a tedious process. This article also focuses on some of the research problems in machine learning domain. The uses of machine learning algorithms in bioinformatics have been extensively studied. These objectives will help to understand bioinformatics and different machine algorithms that are used to analyze the biological data. This research study presents different machine learning approaches like supervised, unsupervised, and reinforcement, which play an important role in understanding and analyzing biological data. Machine learning helps to solve a wide range of bioinformatics related challenges by describing a wide range of genomics sequences and analyzing huge amounts of genomic data. One of the biggest real-time challenges is that the machine learning is helping to identify cancer with a given gene expression, and this is done by using a support vector machine. Finally, this research study has discussed about the classification of molecular data, which will be helpful in finding out minor diseases.

Bioinformatics Research Challenges and Opportunities in Machine Learning

In recent years, diseases and disaster have become more unpredictable. The advent of technology has not only making our lives easier but also technology-dependent. Nevertheless, the natural disasters cause great adversity by disrupting considerable human lives. Also, the disasters obstruct and affect many industries and services either directly or indirectly. Hence, it is necessary to study and observe data patterns and warning signs that lead to a natural disaster, its potential risk and its ability to resolve management strategies, which can be implemented immediately to minimize the socio-economic loss. This article reviews the state-of-the-art research works and findings through a technological perspective on data analysis, natural disaster prediction, and the utilization of technology for deploying management strategy. Also, this paper focuses on investigating the today's Industry 4.0 that utilizes cognitive computing. The primary aim of this article is to review the research ideas that leverage big data and data mining to observe and track patterns, which can impelment predictive analysis to anticipate the forthcoming disasters. Furthermore, this research work analyzed the posed predictive models by specifically using ANN (Artificial Neural Networks), sentiment model, and smart disaster prediction application (SDPA) to predict the flash flood.

N. Jayapandian

Papers

Natural Disaster Prediction by Using Image Based Deep Learning and Machine Learning