Time series analysis and forecasting future values has been a major research focus since years ago. Time series analysis and forecasting in time series data finds it significance in many applications such as business, stock market and exchange, weather, electricity demand, cost and usage of products such as fuels, electricity, etc. and in any kind of place that has specific seasonal or trendy changes with time. The forecasting of time series data provides the organization with useful information that is necessary for making important decisions. In this paper, a detailed survey of the various techniques applied for forecasting different types of time series dataset is provided. This survey covers the overall forecasting models, the algorithms used within the model and other optimization techniques used for better performance and accuracy. The various performance evaluation parameters used for evaluating the forecasting models are also discussed in this paper. This study gives the reader an idea about the various researches that take place within forecasting using the time series data.

Background: In recent times, digitization is gaining importance in different domains of knowledge such as agriculture, medicine, recommendation platforms, the Internet of Things (IoT), and weather forecasting. In agriculture, crop yield estimation is essential for improving productivity and decision-making processes such as financial market forecasting, and addressing food security issues. The main objective of the article is to predict and improve the accuracy of crop yield forecasting using hybrid machine learning (ML) algorithms. Methods: This article proposes hybrid ML algorithms that use specialized ensembling methods such as stacked generalization, gradient boosting, random forest, and least absolute shrinkage and selection operator (LASSO) regression. Stacked generalization is a new model which learns how to best combine the predictions from two or more models trained on the dataset. To demonstrate the applications of the proposed algorithm, aerial-intel datasets from the github data science repository are used. Results: Based on the experimental results done on the agricultural data, the following observations have been made. The performance of the individual algorithm and hybrid ML algorithms are compared using cross-validation to identify the most promising performers for the agricultural dataset. The accuracy of random forest regressor, gradient boosted tree regression, and stacked generalization ensemble methods are 87.71%, 86.98%, and 88.89% respectively. Conclusions: The proposed stacked generalization ML algorithm statistically outperforms with an accuracy of 88.89% and hence demonstrates that the proposed approach is an effective algorithm for predicting crop yield. The system also gives fast and accurate responses to the farmers.

Data preprocessing plays an important and critical role in the data mining process. Data preprocessing is required in order to improve the efficiency of an algorithm. This paper focuses on missing value estimation and prediction of time series data based on the historical values. A number of algorithms have been developed to solve this problem, but they have several limitations. Most existing algorithms like KNNimpute (K-Nearest Neighbours imputation), BPCA (Bayesian Principal Component Analysis) and SVDimpute (Singular Value Decomposition imputation) are not able to deal with the situation where a particular time point (column) of the data is missing entirely. This paper focuses on autoregressive-model-based missing value estimation method (ARLSimpute) which is effective for the situation where a particular time point contains many missing values or where the entire time point is missing. Data preprocessing output is given to the input of the prediction techniques namely linear prediction and quadratic prediction. These techniques are used to predict the future values based on the historical values. The performance of the algorithm is measured by performance metrics like precision and recall. Experimental results on real-life datasets demonstrate that the proposed algorithm is effective and efficient to reveal future time series data.

In the current engross world, traffic overflow is a common problem for the metropolises. In spite of increasing the size of transportation systems and prompting the public transportation may increase the traffic overflow. This kind of traffic overflow problem cannot be solved manually. Today the traffic data has been entered and erupted the time of huge transportation of the data. Hence it is important to predict the traffic information on the accurate and timeline based, for forming the successful Intelligent Transportation System (ITS). In the existing system, the forecasting of traffic flow is depend on the short term of spectral analysis [3] with the small amount of data. This paper focuses on predicting the traffic flow of taxes traveling from multiple sources to the destination on basis of Nearest Neighbor (NN) approach on a Hadoop platform. The performance of the proposed algorithm is measured using metrics like MAPE, RMSE, MAE, and ME. The result shows that the proposed algorithm gives the better accuracy than the existing approach on a Hadoop platform.