Evolutionary Computation for Designing Deep Recurrent Neural Networks

Utilization of the Long Short-Term Memory network for predicting streamflow in ungauged basins in Korea

In recurrent neural networks such as the long short-term memory (LSTM), the sigmoid and hyperbolic tangent functions are commonly used as activation functions in the network units. Other activation functions developed for the neural networks are not thoroughly analyzed in LSTMs. While many researchers have adopted LSTM networks for classification tasks, no comprehensive study is available on the choice of activation functions for the gates in these networks. In this paper, we compare 23 different kinds of activation functions in a basic LSTM network with a single hidden layer. Performance of different activation functions and different number of LSTM blocks in the hidden layer are analyzed for classification of records in the IMDB, Movie Review, and MNIST data sets. The quantitative results on all data sets demonstrate that the least average error is achieved with the Elliott activation function and its modifications. Specifically, this family of functions exhibits better results than the sigmoid activation function which is popular in LSTM networks.

A new approach for quantitative precipitation estimation from radar reflectivity using a gated recurrent unit network

In order to enhance the accuracy of thermal response estimation, this study proposes the utilization of a deep learning-driven method, specifically the Long Short-Term Memory (LSTM) network, for predicting temperature-induced strains and deflections in the Queensferry Crossing, UK. Initially, an examination of the temperature fields of the bridge is conducted based on monitored temperature data. Subsequently, the LSTM network is introduced as a tool to estimate thermal response utilizing temperature field information. The study proceeds to discuss the results of temperature-induced response estimation, including strains and deflections, obtained through the LSTM network, with a comparative analysis against a linear regression model. It is observed that the temperature discrepancies among steel components within the bridge are lesser in comparison to those of concrete components. The LSTM network exhibits higher estimation accuracy than the linear model, manifesting in an improvement of mean square error from 4.45 to 0.89 for strain estimation. In addition, the LSTM network can partially address time-lag effects. However, the estimation performance of the LSTM network is influenced by the structural response type and the resolution of employed sensors. Specifically, the correlation coefficient (R) associated with strain estimation is measured at 0.980 using the LSTM network, whereas R for deflection estimation stands at 0.825. Generally, local structural responses, such as strains, outperform global responses like deflections. Furthermore, sensors with higher resolutions yield enhanced estimation accuracy.

We explore the architecture of recurrent neural networks (RNNs) by studying the complexity of string sequences it is able to memorize. Symbolic sequences of different complexity are generated to simulate RNN training and study parameter configurations with a view to the network's capability of learning and inference. We compare Long Short-Term Memory (LSTM) networks and gated recurrent units (GRUs). We find that an increase in RNN depth does not necessarily result in better memorization capability when the training time is constrained. Our results also indicate that the learning rate and the number of units per layer are among the most important hyper-parameters to be tuned. Generally, GRUs outperform LSTM networks on low-complexity sequences while on high-complexity sequences LSTMs perform better.

Soft Sensor for Melt Index Prediction Based on Long Short-Term Memory Network

With the rapid increase in bridge spans, the mitigation of risk to flutter (aeroelastic instability) is of critical importance in the design of long-span bridges, especially considering the more frequent intense hurricanes under climate change. Although the strong nonlinearities of the aeroelastic (self-excited) forces in wind–bridge interactions can be well captured through either numerical simulations or experimental tests, both are expensive and time consuming. Hence, it is important to develop an efficient reduced-order model for the simulations of nonlinear aeroelastic forces on the bridge decks. This study proposes a reduced-order model based on the long short-term memory (LSTM) network to simulate the nonlinear aeroelastic forces on bridge decks with various leading edges, and thus rapidly predict the corresponding post-flutter behaviors of long-span bridges. To generate the training datasets, computational fluid dynamics (CFD) was employed to simulate the nonlinear aeroelasticities of bridge decks with a wide range of leading-edge configurations and wind speeds. Trained on the high-fidelity CFD datasets, the LSTM network takes the motion of a bridge deck, leading-edge angles and wind speeds as inputs and outputs the nonlinear aeroelastic forces on the bridge decks. A hybrid loss function utilizing the prediction errors of both aeroelastic forces simulated by the LSTM network and the bridge deck responses calculated by the Newmark-β algorithm was introduced into the training process to improve the network performance. The prediction results of the trained LSTM model were compared with the CFD simulations, which demonstrated that the nonlinear aeroelastic forces of the bridge deck with various leading edges can be accurately and efficiently acquired by the proposed LSTM model.

To address the issues of slow convergence speed, poor dynamic adaptability, and path redundancy in the Double Deep Q Network (DDQN) within complex obstacle environments, this paper proposes an enhanced algorithm within the deep reinforcement learning framework. This algorithm, termed LPDDQN, integrates Prioritized Experience Replay (PER) and the Long Short Term Memory (LSTM) network to improve upon the DDQN algorithm. First, Prioritized Experience Replay (PER) is utilized to prioritize experience data and optimize storage and sampling operations through the SumTree structure, rather than the conventional experience queue. Second, the LSTM network is introduced to enhance the dynamic adaptability of the DDQN algorithm. Owing to the introduction of the LSTM model, the experience samples must be sliced and populated. The performance of the proposed LPDDQN algorithm is compared with five other path planning algorithms in both static and dynamic environments. Simulation analysis shows that in a static environment, LPDDQN demonstrates significant improvements over traditional DDQN in terms of convergence, number of moving steps, success rate, and number of turns, with respective improvements of 24.07%, 17.49%, 37.73%, and 61.54%. In dynamic and complex environments, the success rates of all algorithms, except TLD3 and the LPDDQN, decreased significantly. Further analysis reveals that the LPDDQN outperforms the TLD3 by 18.87%, 2.41%, and 39.02% in terms of moving steps, success rate, and number of turns, respectively.

Timely detection and identification of faults in railway track circuits are crucial for the safety and availability of railway networks. In this paper, the use of the long-short-term memory (LSTM) recurrent neural network is proposed to accomplish these tasks based on the commonly available measurement signals. By considering the signals from multiple track circuits in a geographic area, faults are diagnosed from their spatial and temporal dependences. A generative model is used to show that the LSTM network can learn these dependences directly from the data. The network correctly classifies 99.7% of the test input sequences, with no false positive fault detections. In addition, the t-Distributed Stochastic Neighbor Embedding (t-SNE) method is used to examine the resulting network, further showing that it has learned the relevant dependences in the data. Finally, we compare our LSTM network with a convolutional network trained on the same task. From this comparison, we conclude that the LSTM network architecture is better suited for the railway track circuit fault detection and identification tasks than the convolutional network.

An essential step in surface wave exploration is the inversion of dispersion curves. By inverting dispersion curves, we can effectively establish the shear-wave velocity model and obtain reliable subsurface stratigraphic information. The inversion of dispersion curves is an inversion problem with multiple parameters and multiple poles, and obtaining a high precision solution is difficult. Among the methods of inversion of dispersion curves, local search methods are prone to fall into local extremes, and global search methods such as particle swarm optimization (PSO) and genetic algorithm (GA) present the disadvantages of slow convergence speed and low precision. Deep learning models with strong nonlinear mapping capability can effectively solve nonlinear problems. Therefore, we propose a method called PSO-optimized long short-term memory (LSTM) network (PSO-LSTM) to invert the dispersion curves in order to improve the effect of inversion of dispersion curves. The method is based on the LSTM network, and PSO is used to optimize the LSTM network structure and other parameters that need to be given manually to improve the prediction of the network. Two theoretical geological models are used in the paper: Model A and Model B to test the PSO-LSTM. The tests include the noisy data test and noise-free data test. Model A was tested without noise, and Model B was tested with noise. In addition, PSO and LSTM were tested on model A to compare the performance of PSO-LSTM. In Model A, the maximum relative errors of PSO and LSTM are 20.76% and 5.85%, respectively, and the maximum standard deviations of PSO and LSTM are 57.37 and 1.97, respectively. For PSO-LSTM, the maximum relative errors of Model A and Model B in the inverse results are 2.05% and 2.09%, and the maximum standard deviations of Model A and Model B in the inverse results are 1.23 and 3.87, respectively. The test results of Model A show that the inversion performance of PSO-LSTM is better than those of LSTM and PSO, and the performance of the network can be improved after PSO is used to optimize the network parameters. The inverse results from Model B show that the PSO-LSTM is robust and can invert the dispersion curves well even after adding noise to the model. Finally, the PSO-LSTM is used to invert the actual data from Wyoming, USA, which demonstrates that the PSO-LSTM can be used for the quantitative interpretation of Rayleigh wave dispersion curves.

In this paper, long short-term memory (LSTM) networks are used in an original way to model the behavior of a viscoplastic material solicited under changing loading conditions. The material behavior is dependent on history effects of plasticity which can be visible during strain rate jumps or temperature changes. Due to their architecture and internal state (memory), the LSTM networks have the ability to remember past data to update their current state, unlike the traditional artificial neural networks (ANNs) which fail to capture history effects. Specific LSTM networks are designed and trained to reproduce the complex behavior of a viscoplastic solder alloy subjected to strain rate jumps, temperature changes or loading-unloading cycles. The training datasets are numerically generated using the constitutive viscoplastic law of Anand which is very popular for describing solder alloys. The Anand model serves also as a reference to evaluate the performances of the LSTM networks on new data. It is demonstrated that this class of networks is remarkably well suited for replicating the history plastic effects under all the tested loading conditions.

Adaptive Cruise Control (ACC) is an important part of automotive autonomy. To have a robust Adaptive Cruise Control system, a well-defined sensor fusion system is required. This paper focuses on feature-level sensor fusion system where three fusion techniques are explored: independent Kalman filtering, interacting multiple model (IMM) filtering, and a novel hybrid technique using a combination of both an IMM Filter and deep neural network (DNN). Kalman Filtering is a popular approach for automotive sensor fusion, but heavily relies on the given kinematic models to make state estimations. We explore the IMM filter to capture multi-model motion as well as a DNN approach to build a data-driven model of the system. Our IMM filter is built with several Kalman Filters featuring different kinematic models. The proposed DNN used is a Long Short-Term Memory (LSTM) network trained on radar and camera data to forecast a vehicle's state. To overcome the weaknesses in both IMM filtering and LSTM networks, we propose a hybrid technique of consisting of both the IMM filter and the LSTM network. The proposed hybrid system uses a single filter for each sensor. The filtered sensor data is synchronized and used as the input for a trained LSTM network. Our LSTM network was trained on over 100 simulated highway driving scenarios that might occur in an ACC application. Simulations and code were developed using MATLAB and the Autonomous Driving Toolbox. Our hybrid IMM-LSTM system outperformed the independent Kalman Filtering approach in longitudinal and lateral tracking accuracy (RMSE) by 23 percent and had promising results compared to the IMM filter where the tracking error was decreased by nearly 50 percent in certain driving scenarios.

Flash floods occur frequently and distribute widely in mountainous areas because of complex geographic and geomorphic conditions and various climate types. Effective flash flood forecasting with useful lead times remains a challenge due to its high burstiness and short response time. Recently, machine learning has led to substantial changes across many areas of study. In hydrology, the advent of novel machine learning methods has started to encourage novel applications or substantially improve old ones. This study aims to establish a discharge forecasting model based on Long Short-Term Memory (LSTM) networks for flash flood forecasting in mountainous catchments. The proposed LSTM flood forecasting (LSTM-FF) model is composed of T multivariate single-step LSTM networks and takes spatial and temporal dynamics information of observed and forecast rainfall and early discharge as inputs. The case study in Anhe revealed that the proposed models can effectively predict flash floods, especially the qualified rates (the ratio of the number of qualified events to the total number of flood events) of large flood events are above 94.7% at 1–5 h lead time and range from 84.2% to 89.5% at 6–10 h lead-time. For the large flood simulation, the small flood events can help the LSTM-FF model to explore a better rainfall-runoff relationship. The impact analysis of weights in the LSTM network structures shows that the discharge input plays a more obvious role in the 1-h LSTM network and the effect decreases with the lead-time. Meanwhile, in the adjacent lead-time, the LSTM networks explored a similar relationship between input and output. The study provides a new approach for flash flood forecasting and the highly accurate forecast contributes to prepare for and mitigate disasters.

Modern decision-making in fixed income asset management benefits from intelligent systems, which involve the use of state-of-the-art machine learning models and appropriate methodologies. We conduct the first study of bond yield forecasting using long short-term memory (LSTM) networks, validating its potential and identifying its memory advantage. Specifically, we model the 10-year bond yield using univariate LSTMs with three input sequences and five forecasting horizons. We compare those with multilayer perceptrons (MLP), univariate and with the most relevant features. To demystify the notion of black box associated with LSTMs, we conduct the first internal study of the model. To this end, we calculate the LSTM signals through time, at selected locations in the memory cell, using sequence-to-sequence architectures, uni and multivariate. We then proceed to explain the states’ signals using exogenous information, for what we develop the LSTM-LagLasso methodology. The results show that the univariate LSTM model with additional memory is capable of achieving similar results as the multivariate MLP using macroeconomic and market information. Furthermore, shorter forecasting horizons require smaller input sequences and vice-versa. The most remarkable property found consistently in the LSTM signals, is the activation/deactivation of units through time, and the specialisation of units by yield range or feature. Those signals are complex but can be explained by exogenous variables. Additionally, some of the relevant features identified via LSTM-LagLasso are not commonly used in forecasting models. In conclusion, our work validates the potential of LSTMs and methodologies for bonds, providing additional tools for financial practitioners.

Due to unconscious consumption of natural water resources and climate change, a water crisis is expected in the upcoming years. At this point, it is necessary to know the water levels in the dams and develop strategies for water-saving applications in the coming periods. This study aimed to propose the artificial neural network models for forecasting the water in the dams that provide usable water for the future. For this reason, long short-term memory (LSTM) networks that are a type of recurrent neural networks are employed to make future forecasts. The daily dam occupancy rate data between 2005 and 2021 for İstanbul is used to train the LSTM network. Then, the developed models are used to forecast over the next 30 days. The data are used in ARIMA to model the daily dam occupancy time series, for a fair comparison. The forecast values gained by the proposed LSTM network are compared with the traditional methods using RMSE and MAPE for all the forecast horizons. The results show that the LSTM-based forecast model always has a better accuracy rate than the ARIMA.
 
 Keywords: ANNs, dam, forecasting, occupancy, LSTM, RNNs;