A fetus is an unborn child in the basics until it is born into the world. The time when the women is pregnant, every three months is referred to as a trimester. The fetus grows and develops during this time, and frequent checks are essential. One of the primary tools for analysing the baby's health, which is typically used to measure the heartbeat, and the data collected is utilized by the doctor to analyse the health and provide his advice. The time period for the pregnancy is nine months, and during this time, there may be a variety of factors that cause impairment or mortality in the infant, which is a dire situation that must be avoided. However, there is potential for the mistake. Therefore, physicians are not dependable in analyzing the data. As a result, new machine and deep learning algorithms have been developed to analyse the data and forecast fetal's health. The statistics say a lot about the improvement or a requirement of a solution which is required for the following problem. According to it, out of every 100 fetal born, there are 9 cases of some issues with the health. In the year 2020 worldwide, there were about 7 million cases registered of unusual fetal health. Much research has been done using different classification techniques such as naive Bayes, logistic regression, random forest, etc. This paper aims to provide a study of which neural network algorithm performs better in the following case of fetal health prediction, and it turns out that artificial neural network has performed better in this case.

Students are the future of any country, as the knowledge gained by them is directly proportional to the growth and the success of the country. The students should receive all the benefits and proper attention that they deserve for their growth and development and shape them properly which would also shape their peers as it will motivate them to perform better and hence the development will be better. Machine learning and deep learning algorithms may be used to predict student performance and identify the risky factor the students face as soon as possible so that the proper steps can be taken to improve the performance. can be adopted. Many other techniques have also been carried to get the performance on the various algorithms. The main motive of the paper is to make a unique dataset and then perform the prediction of the student's performance and then measuring it on the scale of accuracy using the different tree based ensemble techniques.

We have studied that our planet Earth's surface has 71 percent covered with water and the rest 29 percent with the land. Out of that 71 percent, 97 percent water is ocean water i.e. it is too salty for drinking, for growing crops and more essential things. Since the water which is used is very less in quantity and its quality is day by day becoming poorer. The quality of the water should be maintained as it is an important life component not for the human beings but also other animals and plants. They require a proper quality maintained water to drink and use in different life activities. As a consequence, water quality evaluation and estimate are crucial for social and economic growth. Remote sensing has become a valuable tool for surface parameter monitoring as a consequence of developments. So to ensure whether the water quality we have is good or not we have collected a dataset and applied different ML models to compare the accuracies. So, the paper aims to find the prediction of water if it is in good quality or not using two neural networks, artificial neural network and deep neural network and to show which performs better.

Lethargy also a kind of feeling that occurs when you are bored doing one thing all the time and don't feel motivated due to various reasons based on the human psychology. This effect can be physical or mental based on the symptoms that may occur to the employee while he is working for the company. The work from home(WFH) culture has made everything virtual and there is no one to look at how you are working or when you are feeling fatigue. And with no change in the surrounding or no communication with the other employee, the fatigue is tend to hit the person. Many measures are taken by the company for this thing to get prevented, like organizing games in between work sessions or meditation sessions to keep everyone motivated and calm. After the WFH has peaked many machine learning and deep learning techniques have been incorporated to work for the cause. This paper aims to solve the issue of lethargy detection using deep learning method and keras to get a better accuracy than the other models.