Using independently recurrent networks for reinforcement learning based unsupervised video summarization

Prediction of dissolved oxygen in a fishery pond based on gated recurrent unit (GRU)

To quantitatively evaluate the performance of two types of recurrent neural networks (RNNs), long short-term memory (LSTM) and gated recurrent units (GRU), using Monte Carlo dropout (MCD) to predict pharmacokinetic (PK) parameters from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data. DCE-MRI data for simulation studies were synthesized using the extended Tofts model and a population-averaged arterial input function (AIF). The ranges of PK parameters for training the RNNs were determined from data of patients with brain tumors. The effects of the number of training samples, number of hidden units, dropout rate (DR), and bolus arrival time delay and dispersion in AIF on the accuracy of the PK parameters were investigated, and the uncertainties for different DRs and peak signal-to-noise ratios (PSNRs) were quantified. For comparison, PK parameters were estimated using the nonlinear least-squares method. In the clinical studies, the PK parameter and uncertainty images were generated by applying the trained RNNs to DCE-MRI data. Compared with GRU, the computational cost for training the LSTM was significantly higher. The prediction accuracy of GRU decreased with decreasing numbers of training samples and hidden units, whereas the performance of LSTM remained stable. Despite an increased computational cost, MCD reduced the prediction error at low PSNR and improved the quality of PK parameter images. The simulation results recommended using a DR of 0.25-0.5 at low PSNR and ≤ 0.25 for other PSNRs. The clinical studies recommended using a DR of 0.25 and 0.5 for LSTM and GRU, respectively. MCD is effective in quantifying uncertainty in PK parameter prediction from DCE-MRI data and improves their performance, particularly at low PSNR; however, at the expense of increased computational cost. This study helps deepen our understanding of RNNs with MCD and select suitable hyperparameters for creating an RNN architecture for DCE-MRI studies.

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.

In this study, different kinds of hybrid Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) algorithms with forecasting models including Random Forest (RF), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) neural networks, are developed to estimate the mean daily wind speed at the height of 2 m in Ağrı city (WS st12 ), Turkey. In these hybrid models, different layer networks of single and integrated LSTM and GRU models include general single LSTM, general single GRU, simple coupled LSTM-GRU, and novel coupled LSTM with GRU through Addition layer (i.e., LSTM + GRU model) structures are applied. The most effective parameters on the WS st12 , from a list of on-site potential meteorological parameters and wind speed values in its adjacent cities of Ağrı province from Jan 2015–Dec 2019 through the Pearson correlation coefficient method, are determined. In the hybrid CEEMDAN and DNNs-based models, State activation functions (SAF), numbers of hidden neurons (NHN), dropout rates (P-rate), and network structural architect (NSA) as the meta-parameters are tuned for lessening the impact of overfitting/underfitting dilemmas and improving modeling performance. According to the comparison plots, performance evaluation measures, and total learnable parameter (TLP), the novel developed hybrid CEEMDAN-RF-(LSTM + GRU) model is confirmed as the best approach with an R 2 of 0.86 while, in the optimal scenario using the RF model, R 2 was 0.47. Graphical Abstract Based on the graphical snapshot, this study focuses on estimating daily mean wind speed at a 2-meter height in Ağrı, Turkey, using hybrid data-driven models. The research integrates the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) algorithm with advanced forecasting techniques, including Random Forest (RF), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) neural networks. The modeling framework explores various configurations, such as standalone LSTM and GRU, coupled LSTM-GRU structures, and a novel LSTM + GRU model using an Addition layer to enhance predictive accuracy.

In recent years, machine learning and Deep Learning have increased and gathered epic success in traditional application domains and new areas of Artificial Intelligence. The performance using Deep Learning has dominated experimental results compared to conventional machine learning algorithms. This paper presents an overview of the progress that has occurred in Deep Learning (DL) concerning some application domains like Autonomous Driving, Healthcare, Voice Recognition, Image Recognition, Advertising, Predicting Natural Calamities, National Stock Exchange and many more. Additionally, deeper insights into several Deep Learning techniques, their working principles, and experimental results are scrutinized. The survey covers Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), including Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), Auto-Encoder (AE), Deep Belief Network (DBN), Generative Adversarial Network (GAN), and Deep Reinforcement Learning (DRL).

With the exponential growth of video data, video summarization techniques are urgently needed for reducing people’s efforts in the videos' content exploration by generating succinct but informative summaries from original lengthy videos. Though supervised video summarization approaches have demonstrated the state-of-the-art performance, unsupervised methods are still highly demanded due to resourcefully expensive human annotations and the subjectiveness of video summarization tasks. In this paper, a novel unsupervised-based Deep Self-attention Recurrent summarization network with Reinforcement Learning (DSR-RL) for video summarization is proposed. The model can learn the input video sequence and suggest the key-shot summary without additional human annotations by integrating self-attention, BRNN, and reinforcement learning mechanisms. The DSR-RL improves not only importance score through the attention map vector of self-attention network but also the diversity of summaries via the reward function of reinforcement learning. Our method outperforms the state-of-the-art unsupervised video summarization methods on both SumMe and TVSum datasets. The source code is available at https://github.com/phaphuang/DSR-RL.

Recurrent Neural Networks (RNNs), which are a powerful scheme for modeling temporal and sequential data need to capture long-term dependencies on datasets and represent them in hidden layers with a powerful model to capture more information from inputs. For modeling long-term dependencies in a dataset, the gating mechanism concept can help RNNs remember and forget previous information. Representing the hidden layers of an RNN with more expressive operations (i.e., tensor products) helps it learn a more complex relationship between the current input and the previous hidden layer information. These ideas can generally improve RNN performances. In this paper, we proposed a novel RNN architecture that combine the concepts of gating mechanism and the tensor product into a single model. By combining these two concepts into a single RNN, our proposed models learn long-term dependencies by modeling with gating units and obtain more expressive and direct interaction between input and hidden layers using a tensor product on 3-dimensional array (tensor) weight parameters. We use Long Short Term Memory (LSTM) RNN and Gated Recurrent Unit (GRU) RNN and combine them with a tensor product inside their formulations. Our proposed RNNs, which are called a Long-Short Term Memory Recurrent Neural Tensor Network (LSTMRNTN) and Gated Recurrent Unit Recurrent Neural Tensor Network (GRURNTN), are made by combining the LSTM and GRU RNN models with the tensor product. We conducted experiments with our proposed models on word-level and character-level language modeling tasks and revealed that our proposed models significantly improved their performance compared to our baseline models.

This paper proposes a hybrid deep reinforcement learning framework for locomotive axle temperature by combining the wavelet packet decomposition (WPD), long short-term memory (LSTM), gated recurrent unit (GRU) reinforcement learning and generalized autoregressive conditional heteroskedasticity (GARCH) algorithms. The WPD is utilized to decompose the raw nonlinear series into subseries. Then the deep learning predictors LSTM and GRU are established to predict the future axle temperatures in each subseries. The Q-learning could generate optimal ensemble weights to integrate the predictors to finish the deterministic forecasting and GARCH is used to conduct the deterministic forecasting based on the deterministic forecasting residual. These parts of the hybrid ensemble structure contributed to optimal modelling accuracy and provided effective support in the real-time monitoring and fault diagnosis of transportation.

Recurrent neural networks (RNN) have been very successful in handling sequence data. However, understanding RNN and finding the best practices for RNN learning is a difficult task, partly because there are many competing and complex hidden units, such as the long short-term memory (LSTM) and the gated recurrent unit (GRU). We propose a gated unit for RNN, named as minimal gated unit (MGU), since it only contains one gate, which is a minimal design among all gated hidden units. The design of MGU benefits from evaluation results on LSTM and GRU in the literature. Experiments on various sequence data show that MGU has comparable accuracy with GRU, but has a simpler structure, fewer parameters, and faster training. Hence, MGU is suitable in RNN's applications. Its simple architecture also means that it is easier to evaluate and tune, and in principle it is easier to study MGU's properties theoretically and empirically.

Recently different Deep Learning (DL) models have been emerging to predict the disease amelioration. Generally deep learning is the state of art for learning the multiple representation of neuron. Discriminant DL model includes different architecture and initial architecture is Recurrent Neural Network (RNN) which learn the data labeled in the form of sequence and it has long term dependency and vanishing gradient problem. Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) is an improved version of RNN which deal with problems in RNN. Deep care LSTM is one of the model in LSTM developed by [Trang Pham et.al] for predicting diabetes disease and compared the results with markovian and support vector machine model. In deep LSTM model some problems are reported like short term trajectories, less accuracy. To overcome the problem Deep Care GRU has been proposed to identify the diabetes disease amelioration.

As a new type of currency introduced in the new millennium, cryptocurrency has established its ecosystems and attracts many people to use and invest in it. However, cryptocurrencies are highly dynamic and volatile, making it challenging to predict their future values. In this research, we use a multivariate prediction approach and three different recurrent neural networks (RNNs), namely the long short-term memory (LSTM), the bidirectional LSTM (Bi-LSTM), and the gated recurrent unit (GRU). We also propose simple three layers deep networks architecture for the regression task in this study. From the experimental results on five major cryptocurrencies, i.e., Bitcoin (BTC), Ethereum (ETH), Cardano (ADA), Tether (USDT), and Binance Coin (BNB), we find that both Bi-LSTM and GRU have similar performance results in terms of accuracy. However, in terms of the execution time, both LSTM and GRU have similar results, where GRU is slightly better and has lower variation results on average.

Energy efficiency, scalability, and reliability are increasingly important for sustainable data centers. In this paper, we focus on forecasting real-world resource usage using neural network time series models, specifically utilizing convolutional recurrent long short-term Memory (LSTM) and gated recurrent unit (GRU) architectures. In our analysis, we compare LSTM and GRU in terms of forecasting accuracy and computational complexity during model training. We demonstrate that recurrent neural networks are more accurate and robust compared to the traditional autoregressive integrated moving average (ARIMA) time series model in this complex forecasting problem. GRU achieved a 9% reduction and LSTM a 5% reduction in forecasting mean squared error (MSE) compared to ARIMA. Furthermore, the GRU architecture with a 1D convolution layer outperforms LSTM architecture in both forecast accuracy and training time. The proposed model can be effectively applied to load forecasting as part of a data center computing cluster. In this application, the proposed GRU architecture has 25% fewer trainable parameters in the recurrent layer than the commonly used LSTM.

Highly accurate cryptocurrency price predictions are of paramount interest to investors and researchers. However, owing to the nonlinearity of the cryptocurrency market, it is difficult to assess the distinct nature of time-series data, resulting in challenges in generating appropriate price predictions. Numerous studies have been conducted on cryptocurrency price prediction using different Deep Learning (DL) based algorithms. This study proposes three types of Recurrent Neural Networks (RNNs): namely, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bi-Directional LSTM (Bi-LSTM) for exchange rate predictions of three major cryptocurrencies in the world, as measured by their market capitalization—Bitcoin (BTC), Ethereum (ETH), and Litecoin (LTC). The experimental results on the three major cryptocurrencies using both Root Mean Squared Error (RMSE) and the Mean Absolute Percentage Error (MAPE) show that the Bi-LSTM performed better in prediction than LSTM and GRU. Therefore, it can be considered the best algorithm. Bi-LSTM presented the most accurate prediction compared to GRU and LSTM, with MAPE values of 0.036, 0.041, and 0.124 for BTC, LTC, and ETH, respectively. The paper suggests that the prediction models presented in it are accurate in predicting cryptocurrency prices and can be beneficial for investors and traders. Additionally, future research should focus on exploring other factors that may influence cryptocurrency prices, such as social media and trading volumes.

This study investigates the application of advanced deep learning models to forecast fossil energy prices, a critical factor influencing global economic stability. Unlike previous research, this study conducts a comparative analysis of Gated Recurrent Unit (GRU), Recurrent Neural Network (RNN), Bidirectional Long Short-Term Memory (Bi-LSTM), Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Deep Neural Network (DNN) models. The evaluation metrics employed include Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results reveal that recurrent architectures, particularly GRU, LSTM, and Bi-LSTM, consistently outperform feedforward and convolutional models, demonstrating superior ability to capture temporal dependencies and nonlinear dynamics in energy markets. In contrast, the RNN and DNN show relatively weaker generalization capabilities. Additionally, visualizations of actual versus predicted prices for each model further emphasize superior forecasting accuracy of recurrent models. The results highlight the potential of deep learning in enhancing investment and policy decisions. Additionally, the results provide significant implications for policymakers and investors by emphasizing the value of accurate energy price forecasting in mitigating market volatility, improving portfolio management, and supporting evidence-based energy policies.

Real-time tracking of a target volume is a promising solution for reducing the planning margins and both dosimetric and geometric uncertainties in the treatment of thoracic and upper-abdomen cancers. Respiratory motion prediction is an integral part of real-time tracking to compensate for the latency of tracking systems. The purpose of this work was to develop a novel method for accurate respiratory motion prediction using dual deep recurrent neural networks (RNNs). The respiratory motion data of 111 patients were used to train and evaluate the method. For each patient, two models (Network1 and Network2) were trained on 80% of the respiratory wave, and the remaining 20% was used for evaluation. The first network (Network 1) is a ‘coarse resolution’ prediction of future points and second network (Network 2) provides a ‘fine resolution’ prediction to interpolate between the future predictions. The performance of the method was tested using two types of RNN algorithms : Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The accuracy of each model was evaluated using the root mean square error (RMSE) and mean absolute error (MAE). Overall, the RNN model with GRU- function had better accuracy than the RNN model with LSTM-function (RMSE (mm): 0.4 ± 0.2 versus 0.6 ± 0.3; MAE (mm): 0.4 ± 0.2 versus 0.6 ± 0.2). The GRU was able to predict the respiratory motion accurately (<1 mm) up to the latency period of 440 ms, and LSTM’s accuracy was acceptable only up to 240 ms. The proposed method using GRU function can be used for respiratory-motion prediction up to a latency period of 440 ms.