Long short term memory cells

Reservoir dams play a pivotal role in water resource management. Accurate prediction of inflow to reservoirs significantly enhances operational performance. While standalone artificial intelligence methods have recently been frequently used to predict inflow, hybrid models have shown quite more satisfactory success. In this study, various deep learning models, including MLP, GRU, LSTM, CNN, CNN-MLP, CNN-GRU, CNN-LSTM, CNN-GRU-MLP, and CNN-LSTM-MLP, were utilized to predict the monthly inflow to the Aras reservoir in the Azerbaijan-Iran region. The results were compared with the Neural Basis Expansion Analysis for Time Series Forecasting (N-BEATS) model for univariate forecasting and the NBEATSx model for multivariate forecasting using a monthly inflow time series dataset. To enhance prediction accuracy, the hyperparameters of the models were optimized. Additionally, to evaluate the impact of feature selection on model performance, five different scenarios were developed as combinations of input variables for forecasting one future time step. The evaluation metrics revealed that among the scenarios, Scenario 5 (comprising lagged inflows at months 1, 11, and 12; lagged average monthly precipitation in the upstream basin at months 1 and 12; the solar month counter; and a three-month moving average of monthly inflow) yielded the best results. Among the models, the hybrid CNN-LSTM-MLP demonstrated the highest prediction accuracy. Specifically, the performance metrics for this model and the best scenario included MAE, RMSE, PBIAS, R², KGE, and NSE, which were 8.78 m³/s, 12.95 m³/s, 1.5%, 0.89, 0.91, and 0.89, respectively. Conversely, the NBEATSx model exhibited suboptimal performance, with reduced accuracy as the number of input features increased, although the N-BEATS model performed well in univariate forecasting. This study highlights the high potential of hybrid deep learning models in accurately forecasting reservoir inflows and underscores their utility in enhancing water resource and reservoir operation management.

Background Precisely predicting the water levels of rivers is critical for planning and supporting flood hazard and risk assessments and maintaining navigation, irrigation, and water withdrawal for urban areas and industry. In Hungary, the water level of rivers has been recorded since the early nineteenth century, and various water level prediction methods were developed. The Discrete Linear Cascade Model (DLCM) has been used since 1980s. However, its performance is not always reliable under the current climate-driven hydrological changes. Therefore, we aimed to test machine learning algorithms to make 7-day ahead forecasts, choose the best-performing model, and compare it with the actual DLCM. Results According to the results, the Long Short-Term Memory (LSTM) model provided the best results in all time horizons, giving more precise predictions than the Baseline model, the Linear or Multilayer Perceptron Model. Despite underestimating water levels, the validation of the LSTM model ...

Nowadays, many companies through the world wide web like YouTube, Netflix, Aliexpress and Amazon, provide personalized services as recommendations. Recommender systems use the related information about products or services to suggest the most relevant of them to particular users. The recommendation is usually made based on the prediction of the users' constraints and interests. Despite that the most of the existing recommender systems give accurate recommendation results, they do not provide explainable recommendation support. Therefore, in this paper we propose a new effective model-based trust collaborative filtering for explainable recommendations that aims not only to improve the quality of recommendation but also to provide an efficient support for explainable recommendations based on trustworthiness modeling. Our solution can both ensure how the item is recommended and why it is recommended. The proposed method is evaluated on Amazon Instant Video dataset in terms of RMSE.

Due to the stochastic nature and complexity of flow, as well as the existence of hydrological uncertainties, predicting streamflow in dam reservoirs, especially in semi-arid and arid areas, is essential for the optimal and timely use of surface water resources. In this research, daily streamflow to the Ermenek hydroelectric dam reservoir located in Turkey is simulated using deep recurrent neural network (RNN) architectures, including bidirectional long short-term memory (Bi-LSTM), gated recurrent unit (GRU), long short-term memory (LSTM), and simple recurrent neural networks (simple RNN). For this purpose, daily observational flow data are used during the period 2012–2018, and all models are coded in Python software programming language. Only delays of streamflow time series are used as the input of models. Then, based on the correlation coefficient (CC), mean absolute error (MAE), root mean square error (RMSE), and Nash–Sutcliffe efficiency coefficient (NS), results of deep-learnin...

Nowadays, many companies through the world wide web like YouTube, Netflix, Aliexpress and Amazon, provide personalized services as recommendations. Recommender systems use the related information about products or services to suggest the most relevant of them to particular users. The recommendation is usually made based on the prediction of the users' constraints and interests. Despite that the most of the existing recommender systems give accurate recommendation results, they do not provide explainable recommendation support. Therefore, in this paper we propose a new effective model-based trust collaborative filtering for explainable recommendations that aims not only to improve the quality of recommendation but also to provide an efficient support for explainable recommendations based on trustworthiness modeling. Our solution can both ensure how the item is recommended and why it is recommended. The proposed method is evaluated on Amazon Instant Video dataset in terms of RMSE.

Due to the growing quantity of information available on the Web, recommender systems have become crucial component for the success of online shopping stores. However, most of the existing recommender systems were only designed to improve the recommendation results and ignore the explainable recommendation aspect. Therefore, in this paper we propose a long short-term memory deep learning framework for explainable recommendation, that is able to generate an efficient explanation for any rating made by users for a recommended item. Such a framework would help users to choose a product with confident after reading the automatically generated explanation by our framework. The generated explanation is a concise sentence that shows the reason behind a recommendation, i.e., why a user should select that product. Extensive experiments on a real-world dataset from Amazon are conducted with the goal to evaluate the effectiveness of the proposed method in terms of loss and accuracy metrics. The experimental results demonstrate the effectiveness of our method according to the diversity in generating explainable recommendation.

Stock market Indices prediction is one of the most important issues in the financial field. Although many prediction models have been developed during the last decade, they suffer a poor performance because indices movement is highly non stationary and volati le dynamic process. Artificial Neural Network (ANN) is a technique that is heavily researched and widely used in stock market prediction [1][6]. However, there is no formal method to determine the optimal neural network for prediction purpose in the literature. This paper describes various Neural Network models for stock prediction. The prediction was done by, Modular Neural Network, ARIMA-based Neural Networks, Genetic Algorithm, Recurrent Network, Back propagation Network, Radial Basis Function, Branch Network, Functional Link Artificial Neural Network, Feed Forward Neural Network, Fuzzy Neural Network etc [8]. Analysis of all these Neural Network models is performed in this paper, as well as the future work.

Definition of Artificial Neural Networks (ANNs) is made by computer scientists, artificial intelligence experts and mathematicians in various dimensions. Many of the definitions explain ANN by referring to graphics instead of giving well explained mathematical definitions; therefore, misleading weighted graphs (as in minimum cost flow problem networks) fit the definition of ANN. This study aims to give a clear definition that will differentiate ANN and graphical networks by referring to biological neural networks. The proposed definition of ANN is a mathematical definition, from the point of graph theory which defines ANN as a directed graph. Then differences between ANNs and other networks will be explained by examples using proposed definition.

COVID-19 is a global pandemic that has been reported first in Wuhan, China in December 2019. According to the World Health Organization (WHO), around 1 out of every 5 people who get COVID-19 get seriously ill and develop difficulty breathing. The virus is spreading from one person to others causing fear and a big struggle in the world. Building accurate learning models for forecasting positive new cases would help to better manage the crisis situation thereby helping to fight COVID-19 and save lives. For this purpose, we use LSTM (Long Short Time Memory) model in Morocco's case and evaluate its performance according to six architectures. The results demonstrate that the architecture with three cells outperforms the other models and shows the best fitting.

The long short-term memory neural network (LSTM) is a type of recurrent neural network (RNN). During the training of RNN architecture, sequential information is used and travels through the neural network from input vector to the output neurons, while the error is calculated and propagated back through the network to update the network parameters. Information in these networks incorporates loops into the hidden layer. Loops allow information to flow multi-directionally so that the hidden state signifies past information held at a given time step. Consequently, the output is dependent on the previous predictions which are already known. However, RNNs have limited capacity to bridge more than a certain number of steps. Mainly this is due to the vanishing of gradients which causes the predictions to capture the short-term dependencies as information from earlier steps decays. As more layers in RNN containing activation functions are added, the gradient of the loss function approaches z...

Statistical methods were traditionally primarily used for time series forecasting. However, new hybrid methods demonstrate competitive accuracy, leading to increased machine-learning-based methodologies in the financial sector. However, very little development has been seen in explainable AI (XAI) for financial time series prediction, with a growing mandate for explainable systems. This study aims to determine if the existing XAI methodology is transferable to the context of financial time series prediction. Four popular methods, namely, ablation, permutation, added noise, and integrated gradients, were applied to a recurrent neural network (RNN), long short-term memory (LSTM), and a gated recurrent unit (GRU) network trained on S&P 500 stocks data to determine the importance of features, individual data points, and specific cells in each architecture. The explainability analysis revealed that GRU displayed the most significant ability to retain long-term information, while the LSTM...

The accurate and timely estimation of river discharge plays an important role in hydrological modeling, especially for avoiding the consequences of flood events. The majority of existing work on hydrologic prediction focuses on modeling the inherent physical process for specific river basins, while the geographic-connections between rivers are largely ignored. Geographically connected rivers provide rich spatial information that can be used to predict discharge amounts. In this paper, we study a novel problem of exploiting both temporal patterns and spatial connections for hydrological prediction. We construct three relationship graphs for hydrological gauges in the study area: the hydraulic distance graph, the Euclidean distance graph and the correlation graph. We fuse these graphs into one hydrological network graph, and propose a novel framework ST-Hydro which exploits Graph Convolutional Networks (GCN) for learning the spatial feature representations, and Recurrent Neural Networks with carefully designed activation functions for capturing temporal features simultaneously for hydrological prediction. Experimental results on real world data set demonstrate that the proposed framework can predict the river discharge effectively and at an early stage.

Predictive Maintenance (PM) is a proactive maintenance strategy that tries to minimize a system’s downtime by predicting failures before they happen. It uses data from sensors to measure the component’s state of health and make forecasts about its future degradation. However, existing PM methods typically focus on individual measurements. While it is natural to assume that a history of measurements carries more information than a single one. This paper aims at incorporating such information into PM models. In practice, especially in the automotive domain, diagnostic models have low performance, due to a large amount of noise in the data and limited sensing capability. To address this issue, this paper proposes to use a specific type of ensemble learning known as Stacked Ensemble. The idea is to aggregate predictions of multiple models—consisting of Long Short-Term Memory (LSTM) and Convolutional-LSTM—via a meta model, in order to boost performance. Stacked Ensemble model performs we...

Floods are a complex phenomenon that are difficult to predict because of their non-linear and dynamic nature. Therefore, flood prediction has been a key research topic in the field of hydrology. Various researchers have approached this problem using different techniques ranging from physical models to image processing, but the accuracy and time steps are not sufficient for all applications. This study explores deep learning techniques for predicting gauge height and evaluating the associated uncertainty. Gauge height data for the Meramec River in Valley Park, Missouri was used to develop and validate the model. It was found that the deep learning model was more accurate than the physical and statistical models currently in use while providing information in 15 minute increments rather than six hour increments. It was also found that the use of data sub-selection for regularization in deep learning is preferred to dropout. These results make it possible to provide more accurate and t...

Investing in stock markets is a decisive role for every investor. Speculation in the market makes an investor distressed about his investment. Hence predicting the exact stock market price at high accuracy helps investors to invest wisely to yield more returns. Most of the literature has been carried in predicting the stock market prices using various Logistic regression, ARIMA and machine learning techniques. This paper aims at predicting the stock indices of developed markets and emerging markets using deep learning neural network techniques i.e., Artificial Neural Networks (ANN) and Recurrent Neural Network (RNN). The data consists of daily prices open, close, high, and low, volume of NIFTY 50, S&P 500, New York Stock Index, Korean Stock Index and Dow Jones Index Jan 2014 to July 2019. The open price of the index is fed as input to the models. This study predicts the next day index and gives a comparative analysis between the two models based on the accuracy of prediction. Based on the performance of the models, the best model would be suggested to the investors for the investors.

Due to the growing quantity of information available on the Web, recommender systems have become crucial component for the success of online shopping stores. However, most of the existing recommender systems were only designed to improve the recommendation results and ignore the explainable recommendation aspect. Therefore, in this paper we propose a long short-term memory deep learning framework for explainable recommendation, that is able to generate an efficient explanation for any rating made by users for a recommended item. Such a framework would help users to choose a product with confident after reading the automatically generated explanation by our framework. The generated explanation is a concise sentence that shows the reason behind a recommendation, i.e., why a user should select that product. Extensive experiments on a real-world dataset from Amazon are conducted with the goal to evaluate the effectiveness of the proposed method in terms of loss and accuracy metrics. The experimental results demonstrate the effectiveness of our method according to the diversity in generating explainable recommendation.

Stock Market act as a mechanism for organizations to mean their capitals by introducing their organization shares to market and furthermore ends up being a helpful stage for investors to procure past the edge of interest rates of offered by banks. Main objective of Stock Market Prediction (SMP) is to forecast expected values of companies financial stocks. Recently SMP utilizes machine learning (ML) for prediction in light of estimations of current stock market for that they train their previous values. ML present numerous models for making prediction easier and authenticated. This paper reviews on different available SMP techniques mainly utilizing Regression and LSTM based ML for making prediction of stock values. Main aspects well thought-out for prediction are close, open, high, low and volume.

The stock market is considered to be one of the most highly complex financial systems which consist of various components or stocks, the price of which fluctuates greatly with respect to time. Stock market forecasting involves uncovering the market trends with respect to time. All the stock market investors aim to maximize the returns over their investments and minimize the risks associated. There are time series methods such as AR, MA, SARIMAX developed to predict the stock price but neural network methods such as CNN, LSTM also used to predict the stock price. This research paper describes the prediction of stock market using neural network alogorithms and also few time series methods.

The advancement in neural network and deep learning is enabling the use of these technologies in several art and other fields, and produces outcome which are similar to humans. This paper proposes a method to generate music, different than the music samples it uses as the dataset using bidirectional recurrent neural networks (RNN) with Long Short Term Memory (LSTM) cells, efficiently, by understanding the complex relation between the different notes, pitches, timbre values, that constitutes music. Experiments with the Pokémon midi files showed that we can achieve a high performance in music generation using bidirectional recurrent neural networks with Long Short Term Memory (LSTM) cells. Further, the performance of the model with the variation in the number of epochs used is analyzed

Due to the stochastic nature and complexity of flow, as well as the existence of hydrological uncertainties, predicting streamflow in dam reservoirs, especially in semi-arid and arid areas, is essential for the optimal and timely use of surface water resources. In this research, daily streamflow to the Ermenek hydroelectric dam reservoir located in Turkey is simulated using deep recurrent neural network (RNN) architectures, including bidirectional long short-term memory (Bi-LSTM), gated recurrent unit (GRU), long short-term memory (LSTM), and simple recurrent neural networks (simple RNN). For this purpose, daily observational flow data are used during the period 2012-2018, and all models are coded in Python software programming language. Only delays of streamflow time series are used as the input of models. Then, based on the correlation coefficient (CC), mean absolute error (MAE), root mean square error (RMSE), and Nash-Sutcliffe efficiency coefficient (NS), results of deep-learning architectures are compared with one another and with an artificial neural network (ANN) with two hidden layers. Results indicate that the accuracy of deep-learning RNN methods are better and more accurate than ANN. Among methods used in deep learning, the LSTM method has the best accuracy, namely, the simulated streamflow to the dam reservoir with 90% accuracy in the training stage and 87% accuracy in the testing stage. However, the accuracies of ANN in training and testing stages are 86% and 85%, respectively. Considering that the Ermenek Dam is used for hydroelectric purposes and energy production, modeling inflow in the most realistic way may lead to an increase in energy production and income by optimizing water management. Hence, multi-percentage improvements can be extremely useful. According to results, deep-learning methods of RNNs can be used for estimating streamflow to the Ermenek Dam reservoir due to their accuracy.

The performance of financial market prediction systems depends heavily on the quality of features it is using. While researchers have used various techniques for enhancing the stock specific features, less attention has been paid to extracting features that represent general mechanism of financial markets. In this paper, we investigate the importance of extracting such general features in stock market prediction domain and show how it can improve the performance of financial market prediction. We present a framework called U-CNNpred, that uses a CNN-based structure. A base model is trained in a specially designed layer-wise training procedure over a pool of historical data from many financial markets, in order to extract the common patterns from different markets. Our experiments, in which we have used hundreds of stocks in S\&P 500 as well as 14 famous indices around the world, show that this model can outperform baseline algorithms when predicting the directional movement of the markets for which it has been trained for. We also show that the base model can be fine-tuned for predicting new markets and achieve a better performance compared to the state of the art baseline algorithms that focus on constructing market-specific models from scratch.

Stock Market has started to attract more people from academics and business point of view which has increased. So this paper is mostly based on the approach of predicting the share price using Long Short Term Memory (LSTM) and Recurrent Neural Networks (RNN) to predict the stock price on NSE data using various factors such as current market price, price-earning ratio, base value and some miscellaneous events. We use a numerical data and recommended data for a company selected from collaborative and content based recommendation system. So this paper is all about selecting the company based on the recommendation system using collaborative and content based on selecting a company for the machine learning model based on the LSTM and RNN method. The performance of the model is displayed by comparing the company data and the predicted data using a RNN graph.

The trust which has grown in the power of deep learning models has made the finance industry very eager and with dynamical attitude to apply them in practice as it has been for the past few years. There are a variety of methods and techniques used which have remained very separate from each other in their approach. During the course of this survey, we intend to study the various techniques currently being used to predict or analyze the market and attempt to make a hybrid model so that a wider domain is covered in order to make better predictions.

Definition of Artificial Neural Networks (ANNs) is made by computer scientists, artificial intelligence experts and mathematicians in various dimensions. Many of the definitions explain ANN by referring to graphics instead of giving well
explained mathematical definitions; therefore, misleading weighted graphs (as in minimum cost flow problem networks) fit the definition of ANN. This study aims to give a clear definition that will differentiate ANN and graphical networks by referring to
biological neural networks. The proposed definition of ANN is a mathematical definition, from the point of graph theory which
defines ANN as a directed graph. Then differences between ANNs and other networks will be explained by examples using
proposed definition.