Can you detect covid-19 using machine learning?

 



Technology advancements have a rapid effect on every field of life, be it medical field or any other field. Artificial intelligence has shown the promising results in health care through its decision making by analyzing the data. COVID-19 has affected more than 100 countries in a matter of no time. This will affect people all across the planet in the future.

The development of a control system that can detect the coronavirus is critical. The detection of disease with the use of various AI tools could be one option to control the current chaos. Using classical and ensemble machine learning techniques, we categorized textual clinical reports into four types in this research.

Feature engineering was performed using techniques like Term frequency/inverse document frequency (TF/IDF), Bag of words (BOW) and report length. Traditional and ensemble machine learning classifiers were given these features. Logistic regression and Multinomial Naïve Bayes showed better results than other ML algorithms by having 96.2% testing accuracy. In future recurrent neural network can be used for better accuracy.

Variants of Covid-19:

Country/region

Scientific name

WHO name

Kent, UK

B.1.1.7

Alpha

South Africa

B.1.351

Beta

Brazil

P.1

Gamma

India

B.1.617.2

Delta

Comments

Post a Comment

Popular posts from this blog

EXPLAIN HOW DEEP LEARNING WORKS?

Image
  Deep learning networks gain knowledge by identifying complex patterns in the data they process. The networks can develop several degrees of abstraction to describe the data by constructing computational models that are made up of many processing layers. For instance, a convolutional neural network, a type of deep learning model, can be trained using a lot (like, millions) of photos, such as ones with cats. This kind of neural network often picks up information from the pixels in the photographs it collects. It has the ability to categorise sets of pixels that are typical of cat traits, with sets like claws, ears, and eyes indicating the presence of a cat in a picture. The fundamental building block of the brain is a brain cell, often known as a neuron. An artificial neuron or perceptron was created after being inspired by a neuron. Dendrites are employed by biological neurons to receive inputs. A perceptron operates similarly, taking in a variety of inputs, applying a variety of tr
Read more

What is the difference between Strong AI and Weak AI?

Image
The word " Artificial Intelligence " is sometimes misinterpreted, yet the technology is more beneficial than harmful. Although past developments in the field of AI may no longer be relevant, the method has evolved significantly over time. Despite the fact that AI is one of the newest branches of intellectual inquiry its roots may be traced back thousands of years. Strong AI is a speculative form of machine intelligence that argues that machines can develop human consciousness on par with humans. Strong AI refers to computers or programs that have their own mind and can think and complete complicated tasks without the need for human intervention. Strong AI uses complicated algorithms to assist systems operate in a variety of scenarios and strong AI-powered robots can make judgments without the need for human intervention. Artificial intelligence with restricted capability is known as weak AI or narrow AI. Weak AI is the application of advanced algorithms to specific probl
Read more

What distinguishes supervised from unsupervised machine learning?

Image
  What is supervised learning? The use of labelled datasets distinguishes the machine learning strategy known as supervised learning. These datasets are intended to "supervise" or "train" algorithms to correctly classify data or forecast outcomes. Labelled inputs and outputs allow the model to monitor its precision and improve over time. Supervised learning can be separated into two types of problems when data mining: classification and regression: Using an algorithm, classification issues correctly categories test data into distinct groups, such as distinguishing apples from oranges. Alternately, supervised learning algorithms can be applied in the real world to categories spam in a distinct folder from your email. Common classification techniques include decision trees, support vector machines, random forests, and linear classifiers. Another supervised learning technique that employs an algorithm to comprehend the link between dependent and independent varia
Read more