A Comprehensive Study on Time Series Analysis in Healthcare

There has been a lot of interest in time series forecasting in recent years. Deep neural networks have shown their effectiveness and accuracy in various industries. It is currently one of the most extensively used machine-learning algorithms for dealing with massive volumes of data due to the reasons stated above. Statistical modeling includes forecasting, which is used for decision-making in various fields. Time-varying variables may be forecasted based on their past values, which is the goal of forecasting. Developing models and techniques for trustworthy forecasting is an important part of the forecasting process. As part of this study, a systematic mapping investigation and a literature review are used. Time-series researchers have relied on ARIMA approaches for decades, notably the autoregressive integrated moving average model. But the need for stationary makes this method somewhat rigid. Forecasting methods have improved and expanded with the introduction of computers, ranging from stochastic models to soft computers. Conventional approaches may not be as accurate as soft computing. In addition, the volume of data that can be analyzed and the efficiency of the process are two of the many benefits of using soft computing