A new Apache Spark-based framework for big data streaming forecasting in IoT networks.

Analyzing time-dependent data acquired in a continuous flow is a major challenge for various fields, such as big data and machine learning. Being able to analyze a large volume of data from various sources, such as sensors, networks, and the internet, is essential for improving the efficiency of our society's production processes. Additionally, this vast amount of data is collected dynamically in a continuous stream. The goal of this research is to provide a comprehensive framework for forecasting big data streams from Internet of Things networks and serve as a guide for designing and deploying other third-party solutions. Hence, a new framework for time series forecasting in a big data streaming scenario, using data collected from Internet of Things networks, is presented. This framework comprises of five main modules: Internet of Things network design and deployment, big data streaming architecture, stream data modeling method, big data forecasting method, and a comprehensive real-world application scenario, consisting of a physical Internet of Things network feeding the big data streaming architecture, being the linear regression the algorithm used for illustrative purposes. Comparison with other frameworks reveals that this is the first framework that incorporates and integrates all the aforementioned modules.

Deep Learning for Time Series Forecasting: A Survey.

Time series forecasting has become a very intensive field of research, which is even increasing in recent years. Deep neural networks have proved to be powerful and are achieving high accuracy in many application fields. For these reasons, they are one of the most widely used methods of machine learning to solve problems dealing with big data nowadays. In this work, the time series forecasting problem is initially formulated along with its mathematical fundamentals. Then, the most common deep learning architectures that are currently being successfully applied to predict time series are described, highlighting their advantages and limitations. Particular attention is given to feed forward networks, recurrent neural networks (including Elman, long-short term memory, gated recurrent units, and bidirectional networks), and convolutional neural networks. Practical aspects, such as the setting of values for hyper-parameters and the choice of the most suitable frameworks, for the successful application of deep learning to time series are also provided and discussed. Several fruitful research fields in which the architectures analyzed have obtained a good performance are reviewed. As a result, research gaps have been identified in the literature for several domains of application, thus expecting to inspire new and better forms of knowledge.

A novel deep learning neural network approach for predicting flash flood susceptibility: A case study at a high frequency tropical storm area.

This research proposes and evaluates a new approach for flash flood susceptibility mapping based on Deep Learning Neural Network (DLNN)) algorithm, with a case study at a high-frequency tropical storm area in the northwest mountainous region of Vietnam. Accordingly, a DLNN structure with 192 neurons in 3 hidden layers was proposed to construct an inference model that predicts different levels of susceptibility to flash flood. The Rectified Linear Unit (ReLU) and the sigmoid were selected as the activate function and the transfer function, respectively, whereas the Adaptive moment estimation (Adam) was used to update and optimize the weights of the DLNN. A database for the study area, which includes factors of elevation, slope, curvature, aspect, stream density, NDVI, soil type, lithology, and rainfall, was established to train and validate the proposed model. Feature selection was carried out for these factors using the Information gain ratio. The results show that the DLNN attains a good prediction accuracy with Classification Accuracy Rate = 92.05%, Positive Predictive Value = 94.55% and Negative Predictive Value = 89.55%. Compared to benchmarks, Multilayer Perceptron Neural Network and Support Vector Machine, the DLNN performs better; therefore, it could be concluded that the proposed hybridization of GIS and deep learning can be a promising tool to assist the government authorities and involving parties in flash flood mitigation and land-use planning.

A novel imputation methodology for time series based on pattern sequence forecasting.

The Pattern Sequence Forecasting (PSF) algorithm is a previously described algorithm that identifies patterns in time series data and forecasts values using periodic characteristics of the observations. A new method for univariate time series is introduced that modifies the PSF algorithm to simultaneously forecast and backcast missing values for imputation. The imputePSF method extends PSF by characterizing repeating patterns of existing observations to provide a more precise estimate of missing values compared to more conventional methods, such as replacement with means or last observation carried forward. The imputation accuracy of imputePSF was evaluated by simulating varying amounts of missing observations with three univariate datasets. Comparisons of imputePSF with well-established methods using the same simulations demonstrated an overall reduction in error estimates. The imputePSF algorithm can produce more precise imputations on appropriate datasets, particularly those with periodic and repeating patterns.

Earthquake prediction model using support vector regressor and hybrid neural networks.

Earthquake prediction has been a challenging research area, where a future occurrence of the devastating catastrophe is predicted. In this work, sixty seismic features are computed through employing seismological concepts, such as Gutenberg-Richter law, seismic rate changes, foreshock frequency, seismic energy release, total recurrence time. Further, Maximum Relevance and Minimum Redundancy (mRMR) criteria is applied to extract the relevant features. A Support Vector Regressor (SVR) and Hybrid Neural Network (HNN) based classification system is built to obtain the earthquake predictions. HNN is a step wise combination of three different Neural Networks, supported by Enhanced Particle Swarm Optimization (EPSO), to offer weight optimization at each layer. The newly computed seismic features in combination with SVR-HNN prediction system is applied on Hindukush, Chile and Southern California regions. The obtained numerical results show improved prediction performance for all the considered regions, compared to previous prediction studies.