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.

Being healthy is a very important aspect of one's life and should not be taken very lightly. Physical and mental health are both incredibly vital. Physical health can be maintained by exercise and if there is any problem with it, it can be resolved in a short span of time. But if one's mental health gets disturbed, it takes a lot amount of time and patience to get cured. Mental health can be affected anywhere there's not a certain place for mental health to deteriorate, but stress at the workplace plays a huge role in making its condition worse. Curing mental health takes a lot of time, medicines and effort which starts to impact one's physical health too which causes harm to the most crucial aspects of one's life i.e. being healthy. Many machine learning and deep learning techniques such as the machine learning classification techniques and the deep learning's neural network techniques are used to predict the mental health of one. The main aim of the paper is to show which neural network technique works best to solve this problem in the terms of accuracy mental health at work, deep learning, comparative analysis, artificial neural network, convolutional neural network

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.

Stroke is one of the heart diseases and is very dangerous to very much people in the world as it is the world’s third-largest disease which is causing death to the people in this world. This is a very big health issue in the world and is addressed by the World Health Organization (WHO) and can be seen from the statistics that have been provided by the organization and is very much approved by the other organizations too. The symptoms that are shown by the patients who are suffering from the stroke disease or which are very much prone to the stroke disease and may suffer from a very chronic stroke disease show heart disease, declination of metabolism and problems in the artilleries. The main issue due to which this problem is occurring is due to the flow of the blood, which is not able to reach the part of the heart through which the cleaning of the blood takes place or in other words the carbon dioxide is taken out of the blood and the oxygen is given which purifies the blood and is sent to the other body parts. In this medical industry, there are many machine learning and deep learning methods that are incorporated by the research community and different novelties have been researched by the community. By the method proposed, we could mitigate the strokes occurring by approximately 96

It is not possible to handle and huge amounts of data using present software programmes and personal computers owing to a lack of appropriate computing power. Manufacturing organisations must either employ Cloud computing technology or engage in more current techniques including Edge Computing technology if they are to compete in the global market. The SEM model is used to examine the Smart Grid Information Processes in this article. Furthermore, it is proposed that the research contributes to the expansion of experience in the discipline of smart meters and Internet of Things acceptability, despite the fact that this is a very rare topic.

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.

NLP is a computer-based software technology that used primarily to translate the natural human language into machine understandable format efficiently. The inputs for the machine could be text, audio, video, image, and speech. NLP is emerging globally and is being used in many applications. One popular application of NLP is Siri introduced in Apple Inc. This created a greater impact on iPhone community. Machines being trained with respect to voice search will facilitate the future generation in performing day-to-day activities. Machine learning (ML) algorithms have contributed extensively for building this popular framework. The paper aims to provide an NLP solution to a text classification problem and solve it using NLP and machine learning to get the best results and the best accuracy.