Standard Long Short-term Memory Research Articles

A Novel Framework for DDoS Attacks Detection Using Hybrid LSTM Techniques

The recent development of cloud computing offers various services on demand for organization and individual users, such as storage, shared computing space, networking, etc. Although Cloud Computing provides various advantages for users, it remains vulnerable to many types of attacks that attract cyber criminals. Distributed Denial of Service (DDoS) is the most common type of attack on cloud computing. Consequently, Cloud computing professionals and security experts have focused on the growth of preventive processes towards DDoS attacks. Since DDoS attacks have become increasingly widespread, it becomes difficult for some DDoS attack methods based on individual network flow features to distinguish various types of DDoS attacks. Further, the monitoring pattern of traffic changes and accurate detection of DDoS attacks are most important and urgent. In this research work, DDoS attack detection methods based on deep belief network feature extraction and Hybrid Long Short-Term Memory (LSTM) model have been proposed with NSL-KDD dataset. In Hybrid LSTM method, the Particle Swarm Optimization (PSO) technique, which is combined to optimize the weights of the LSTM neural network, reduces the prediction error. This deep belief network method is used to extract the features of IP packets, and it identifies DDoS attacks based on PSO-LSTM model. Moreover, it accurately predicts normal network traffic and detects anomalies resulting from DDoS attacks. The proposed PSO-LSTM architecture outperforms the classification techniques including standard Support Vector Machine (SVM) and LSTM in terms of attack detection performance along with the results of the measurement of accuracy, recall, f-measure, precision.

Fake News Detection Using LSTM in TensorFlow and Deep Learning

Today's culture has seen a significant rise in fake news, especially with the emergence of social media platforms where misinformation may spread swiftly. False information may have detrimental effects, such as influencing elections, encouraging hate speech, and eroding trust in reliable news sources. Identification of false news has become a hot topic in recent years, with several solutions being proposed for the problem. The paper discusses LSTM (Long Short-Term Memory), Bidirectional LSTM (BiLSTM), and Convolution Neural Network (CNN)-based deep learning-based algorithms for identifying fake news. The "ISOT Fake News dataset," "News Dataset from TI-CNN," and "Getting Real About Fake News dataset" are among the datasets that were used. Following preprocessing methods such as stop keyword removal, stemming, and tokenization are used, these datasets are subjected to word embedding. This processed data is used to train the LSTM model, which determines whether or not news reports are fake. Performance metrics including precision, recall, accuracy, and F1-score provide as proof of the recommended model's efficacy in identifying fake news. Comparisons with other state-of-the-art models show its improved efficacy. In terms of both accuracy and F1-score, the CNN beat the standard LSTM and BiLSTM models. CNN-BiLSTM is most effective model, having superior findings as well as efficiency across the three datasets.

TA-LSTM: A Time and Attribute Aware LSTM for Deep Flight Track Clustering

The rapid development of civil aviation imposes an urgent need for efficient air traffic management. Flight track clustering is the premise and foundation of air traffic control. Flight track points compose time-series data with non-identical point- to-point intervals, and the effective latent representation of track data is key to the flight trajectory clustering. Long Short-Term Memory (LSTM) is an important and popular method to extract the features of trajectory time-series data. However, LSTM ignores the irregular time intervals between track points and fails to effectively distinguish the importance of different attributes at each track point during feature extraction. In addition, the existing methods based on LSTM either ignore the distinct impacts of different attributes at each track point or simply assume that the influences of the previous track points on the subsequent ones decrease with time. In this paper, we propose a flight trajectory feature extraction unit called TA-LSTM (Time and Attribute Aware Long Short- Term Memory) and a flight track clustering model based on TA- LSTM. The flight track clustering model consists of a feature extraction layer and a clustering layer. The feature extraction layer adopts TA-LSTM to obtain the latent representation of flight tracks, which adds a time control gate and an attribute control gate to the standard LSTM unit. The time control gate manipulates the action of each track point on subsequent points to obtain the characteristics of irregular time intervals. The attribute control gat enables LSTM to capture the impact of different attributes on the flight track features at various points. The clustering layer takes the latent representation of flight tracks as the input to obtain the clustering results. The clustering model updates the parameters of TA-LSTM and the cluster centers by minimizing the Kullback-Leibler (K-L) divergence. We conduct experiments using Automatic Dependent Surveillance-Broadcast track data provided by VariFlight. In comparison with popular and state-of-the-art methods, the proposed method obtains superior pe formance in three widely used evaluation metrics, i.e., Silhouette Coefficient, Calinski-Harabaz index and Davies-Bouldin index.

Predicting Output Responses of Nonlinear Dynamical Systems With Parametrized Inputs Using LSTM

Long Short-Term Memory (LSTM) has been more and more used to predict time evolution of dynamics for many problems, especially the fluid dynamics. Usually, it is applied to the latent space after dimension reduction of the full dynamical system by proper orthogonal decomposition (POD), autoencoder (AE) or convolutional autoencoder (CAE). In this work, we propose to directly apply LSTM to the data of the output without dimension reduction for output response prediction. The dimension of the output is usually small, and no dimension reduction is necessary, thus no accuracy loss is caused by dimension reduction. Based on the standard LSTM structure, we propose an LSTM network with modified activation functions which is shown to be much more robust for predicting periodic waveforms. We are especially interested in showing the efficiency of LSTM for predicting the output responses corresponding to time-vary input signals, which is rarely considered in the literature. However, such systems are of great interests in electrical engineering, mechanical engineering, and control engineering, etc. Numerical results for models from circuit simulation, neuron science and a electrochemical reaction have shown the efficiency of LSTM in predicting the dynamics of output responses.

Deep Learning with Dipper Throated Optimization Algorithm for Energy Consumption Forecasting in Smart Households

One of the relevant factors in smart energy management is the ability to predict the consumption of energy in smart households and use the resulting data for planning and operating energy generation. For the utility to save money on energy generation, it must be able to forecast electrical demands and schedule generation resources to meet the demand. In this paper, we propose an optimized deep network model for predicting future consumption of energy in smart households based on the Dipper Throated Optimization (DTO) algorithm and Long Short-Term Memory (LSTM). The proposed deep network consists of three parts, the first part contains a single layer of bidirectional LSTM, the second part contains a set of stacked unidirectional LSTM, and the third part contains a single layer of fully connected neurons. The design of the proposed deep network targets represents the temporal dependencies of energy consumption for boosting prediction accuracy. The parameters of the proposed deep network are optimized using the DTO algorithm. The proposed model is validated using the publicly available UCI household energy dataset. In comparison to the other competing machine learning models, such as Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Multi-Layer Perceptron (MLP), Sequence-to-Sequence (Seq2Seq), and standard LSTM, the performance of the proposed model shows promising effectiveness and superiority when evaluated using eight evaluation criteria including Root Mean Square Error (RMSE) and R2. Experimental results show that the proposed optimized deep model achieved an RMSE of (0.0047) and R2 of (0.998), which outperform those values achieved by the other models. In addition, a sensitivity analysis is performed to study the stability and significance of the proposed approach. The recorded results confirm the effectiveness, superiority, and stability of the proposed approach in predicting the future consumption of energy in smart households.

Aspect-based sentiment analysis for hotel reviews using an improved model of long short-term memory

Advances in information technology have given rise to online hotel reservation options. The user review feature is an important factor during the online booking of hotels. Generally, most online hotel booking service providers provide review and rating features for assessing hotels. However, not all service providers provide rating features or recap reviews for every aspect of the hotel services offered. Therefore, we propose a method to summarise reviews based on multiple aspects, including food, room, service, and location. This method uses long short-term memory (LSTM), together with hidden layers and automation of the optimal number of hidden neurons. The F1-measure value of 75.28% for the best model was based on the fact that (i) the size of the first hidden layer is 1,200 neurons with the tanh activation function, and (ii) the size of the second hidden layer is 600 neurons with the ReLU activation function. The proposed model outperforms the baseline model (also known as standard LSTM) by 10.16%. It is anticipated that the model developed through this study can be accessed by users of online hotel booking services to acquire a review recap on more specific aspects of services offered by hotels

An adaptive particle swarm optimization-based hybrid long short-term memory model for stock price time series forecasting

In this paper, we presented a long short-term memory (LSTM) network and adaptive particle swarm optimization (PSO)-based hybrid deep learning model for forecasting the stock price of three major stock indices such as Sensex, S&P 500, and Nifty 50 for short term and long term. Although the LSTM can handle uncertain, sequential, and nonlinear data, the biggest challenge in it is optimizing its weights and bias. The back-propagation through time algorithm has a drawback to overfit the data and being stuck in local minima. Thus, we proposed PSO-based hybrid deep learning model for evolving the initial weights of LSTM and fully connected layer (FCL). Furthermore, we introduced an adaptive approach for improving the inertia coefficient of PSO using the velocity of particles. The proposed method is an aggregation of adaptive PSO and Adam optimizer for training the LSTM. The adaptive PSO attempts to evolve the initial weights in different layers of the LSTM network and FCL. This research also compares the forecasting efficacy of the proposed method to the genetic algorithm (GA)-based hybrid LSTM model, the Elman neural network (ENN), and standard LSTM. Experimental findings demonstrate that the suggested model is successful in achieving the optimum initial weights and bias of the LSTM and FC layers, as well as superior forecasting accuracy.

Long-time prediction of sea wave trains by LSTM machine learning method

The present work proposes a novel way of long-time accurate prediction of sea wave trains using the Long Short-Term Memory (LSTM) method. Typical kinds of regular waves (e.g. the Stokes wave), irregular waves (produced from the PM wave spectrum by either the equal frequency method or the equal energy method) and real sea wave trains are considered. The historical data of wave elevations are used in the training process of the LSTM model, based on which future wave evolutions are predicted. To improve the accuracy of long-time estimation of irregular waves, a multi-shot prediction method is proposed. The validity of the proposed approach is proved by comparing the performance of the single-shot prediction method and the multi-shot prediction method in multiple cases of irregular waves. In the meantime, the effects of the input and output lengths are investigated. Test results demonstrate that, although the standard LSTM scheme with the single-shot method presents appealing accuracy in forecasting regular waves, the multi-shot method is an essential component in enhancing the accuracy of long-time prediction of irregular waves.

Estimating Gridded Monthly Baseflow From 1981 to 2020 for the Contiguous US Using Long Short‐Term Memory (LSTM) Networks

AbstractAccurate baseflow estimation is essential for ecological protection and water resources management. Past studies have used environmental predictors to extend baseflow from gauged basins to ungauged basins, publishing several regional or global datasets on mean annual baseflow. However, time series datasets of baseflow are still lacking due to the complexity of baseflow generation processes. Here, we developed a monthly baseflow data set using a Deep learning model called the long short‐term memory (LSTM) networks. To better train the networks across basins, we compared the standard LSTM architecture using 8 time series as inputs with four variant architectures using 16 additional static properties as inputs. Dividing the contiguous United States into nine ecoregions, we used baseflow calculated from 1,604 gauged basins as training targets to calibrate the five LSTM architectures for each ecoregion separately. Results show that three variant architectures (Joint, Front, and Entity‐Aware‐LSTM) perform better than the standard LSTM, with median Kling‐Gupta Efficiencies across basins greater than 0.85. Based on Front LSTM, the monthly baseflow data set with 0.25° spatial resolution across the contiguous United States from 1981 to 2020 was obtained. Potential applications of the data set include analyzing baseflow trends under global change and estimating large‐scale groundwater recharge.

A Comparative Study of Text Genres in English-Chinese Translation Effects Based on Deep Learning LSTM.

In recent years, neural network-based English-Chinese translation models have gradually supplanted traditional translation methods. The neural translation model primarily models the entire translation process using the “encoder-attention-decoder” structure. Simultaneously, grammar knowledge is essential for translation, as it aids in the grammatical representation of word sequences and reduces grammatical errors. The focus of this article is on two major studies on attention mechanisms and grammatical knowledge, which will be used to carry out the following two studies. Firstly, in view of the existing neural network structure to build translation model caused by long distance dependent on long-distance information lost in the delivery, leading to problems in terms of the translation effect which is not ideal, put forward a kind of embedded attention long short-term memory (LSTM) network translation model. Secondly, in view of the lack of grammatical prior knowledge in translation models, a method is proposed to integrate grammatical information into translation models as prior knowledge. Finally, the proposed model is simulated on the IWSLT2019 dataset. The results show that the proposed model has a better representation of source language context information than the existing translation model based on the standard LSTM model.

Traffic State Prediction Using One-Dimensional Convolution Neural Networks and Long Short-Term Memory

Traffic prediction is a vitally important keystone of an intelligent transportation system (ITS). It aims to improve travel route selection, reduce overall carbon emissions, mitigate congestion, and enhance safety. However, efficiently modelling traffic flow is challenging due to its dynamic and non-linear behaviour. With the availability of a vast number of data samples, deep neural network-based models are best suited to solve these challenges. However, conventional network-based models lack robustness and accuracy because of their incapability to capture traffic’s spatial and temporal correlations. Besides, they usually require data from adjacent roads to achieve accurate predictions. Hence, this article presents a one-dimensional (1D) convolution neural network (CNN) and long short-term memory (LSTM)-based traffic state prediction model, which was evaluated using the Zenodo and PeMS datasets. The model used three stacked layers of 1D CNN, and LSTM with a logarithmic hyperbolic cosine loss function. The 1D CNN layers extract the features from the data, and the goodness of the LSTM is used to remember the past events to leverage them for the learnt features for traffic state prediction. A comparative performance analysis of the proposed model against support vector regression, standard LSTM, gated recurrent units (GRUs), and CNN and GRU-based models under the same conditions is also presented. The results demonstrate very encouraging performance of the proposed model, improving the mean absolute error, root mean squared error, mean percentage absolute error, and coefficient of determination scores by a mean of 16.97%, 52.1%, 54.15%, and 7.87%, respectively, relative to the baselines under comparison.

Predicting High Flow Nasal Cannula Failure in an Intensive Care Unit Using a Recurrent Neural Network With Transfer Learning and Input Data Perseveration: Retrospective Analysis.

BackgroundHigh flow nasal cannula (HFNC) provides noninvasive respiratory support for children who are critically ill who may tolerate it more readily than other noninvasive ventilation (NIV) techniques such as bilevel positive airway pressure and continuous positive airway pressure. Moreover, HFNC may preclude the need for mechanical ventilation (intubation). Nevertheless, NIV or intubation may ultimately be necessary for certain patients. Timely prediction of HFNC failure can provide an indication for increasing respiratory support.ObjectiveThe aim of this study is to develop and compare machine learning (ML) models to predict HFNC failure.MethodsA retrospective study was conducted using the Virtual Pediatric Intensive Care Unit database of electronic medical records of patients admitted to a tertiary pediatric intensive care unit between January 2010 and February 2020. Patients aged <19 years, without apnea, and receiving HFNC treatment were included. A long short-term memory (LSTM) model using 517 variables (vital signs, laboratory data, and other clinical parameters) was trained to generate a continuous prediction of HFNC failure, defined as escalation to NIV or intubation within 24 hours of HFNC initiation. For comparison, 7 other models were trained: a logistic regression (LR) using the same 517 variables, another LR using only 14 variables, and 5 additional LSTM-based models using the same 517 variables as the first LSTM model and incorporating additional ML techniques (transfer learning, input perseveration, and ensembling). Performance was assessed using the area under the receiver operating characteristic (AUROC) curve at various times following HFNC initiation. The sensitivity, specificity, and positive and negative predictive values of predictions at 2 hours after HFNC initiation were also evaluated. These metrics were also computed for a cohort with primarily respiratory diagnoses.ResultsA total of 834 HFNC trials (455 [54.6%] training, 173 [20.7%] validation, and 206 [24.7%] test) met the inclusion criteria, of which 175 (21%; training: 103/455, 22.6%; validation: 30/173, 17.3%; test: 42/206, 20.4%) escalated to NIV or intubation. The LSTM models trained with transfer learning generally performed better than the LR models, with the best LSTM model achieving an AUROC of 0.78 versus 0.66 for the 14-variable LR and 0.71 for the 517-variable LR 2 hours after initiation. All models except for the 14-variable LR achieved higher AUROCs in the respiratory cohort than in the general intensive care unit population.ConclusionsML models trained using electronic medical record data were able to identify children at risk of HFNC failure within 24 hours of initiation. LSTM models that incorporated transfer learning, input data perseveration, and ensembling showed improved performance compared with the LR and standard LSTM models.

A Data Organization Method for LSTM and Transformer When Predicting Chinese Banking Stock Prices

The accurate prediction of stock prices is not an easy task. The long short-term memory (LSTM) neural network and the transformer are good machine learning models for times series forecasting. In this paper, we use LSTM and transformer to predict prices of banking stocks in China’s A-share market. It is shown that organizing the input data can help get accurate outcomes of the models. In this paper, we first introduce some basic knowledge about LSTM and present prediction results using a standard LSTM model. Then, we show how to organize the input data during the training period and give the comparison results for not only LSTM but also the transformer model. The numerical results show that the prediction results of LSTM and transformer can be improved after the input data are organized when training.

A Novel Temporal Feature Selection Based LSTM Model for Electrical Short-Term Load Forecasting

An accurate electrical Short-term Load Forecasting (STLF) is an eminent factor in the power generation, electrical load dispatching and energy planning for the power supply companies, specifically in developing countries. This paper proposes a novel temporal feature selection-based Long Short-term Memory (LSTM) model developed by the combination of standard Artificial Neural Network (ANN) layer and LSTM for electrical short term load forecasting. The LSTM model has excellent capability of predicting the stochastic nature of an hour ahead electrical loads. The standard ANN layer consisting 11 neurons is used as an input to LSTM cells. Such a combination of ANN layer with LSTM was never proposed before. The proposed model accommodates variations in weather as well as temporal inputs like humidity, holidays, and date-time features in the hourly load data of the power supply company situated in Johor, Malaysia. This paper gives the insights of hyper parameter tuning to capture the more generalized electrical load patterns in the dataset without compromising the time complexity of the proposed model. The proposed approach was compared with five existing approaches, namely: ANN, LSTM model 1, LSTM model 2, LSTM model 3 and Convolutional Neural Network-LSTM (CNN-LSTM) using hourly load dataset of Johor. The experimental results demonstrate that the proposed approach outperformed the existing approaches in terms of root mean square error, mean absolute percentage error and Diebold-Mariano statistical inference test within 95% confidence interval.

Financial Time Series Forecasting Based on LSTM Neural Network optimized by Wavelet Denoising and Whale Optimization Algorithm

In order to further explore the application of deep learning in predicting financial market time series data and improve the accuracy of the prediction, this paper adopts a financial time series prediction method based on wavelet denoising, whale optimization algorithm and long-short term memory (LSTM) neural network. This article chooses 10 common evaluation indexes in the financial market as the input, the financial time series data are denoised by wavelet analysis. Then the optimal LSTM neural network parameters are obtained by whale optimization algorithm (WOA). Finally, the LSTM neural network algorithm is used for stock prediction to output the predicted closing price. To verify the effectiveness of WP-WOA-LSTM model, three other neural networks are used to compare with the forecasting result. By comparing the prediction accuracy of different methods, it is obvious that the mean absolute error (MAE) of LSTM neural network under whale optimization algorithm can be reduced by 22 % compared with the standard LSTM neural network. Therefore, the results show that WOA-LSTM model has significantly improved the prediction accuracy.

A Hybrid LSTM-CPS Approach for Long-Term Prediction of Train Delays in Multivariate Time Series

In many big cities, train delays are among the most complained-about events by the public. Although various models have been proposed for train delay prediction, prior studies on both primary and secondary train delay prediction are limited in number. Recent advances in deep learning approaches and increasing availability of various data sources has created new opportunities for more efficient and accurate train delay prediction. In this study, we propose a hybrid deep learning solution by integrating long short-term memory (LSTM) and Critical Point Search (CPS). LSTM deals with long-term prediction tasks of trains’ running time and dwell time, while CPS uses predicted values with a nominal timetable to identify primary and secondary delays based on the delay causes, run-time delay, and dwell time delay. To validate the model and analyse its performance, we compare the standard LSTM with the proposed hybrid model. The results demonstrate that new variants outperform the standard LSTM, based on predicting time steps of dwell time feature. The experiment results also showed many irregularities of historical trends, which draws attention for further research.

Short-Term Forecasting of Wind Energy: A Comparison of Deep Learning Frameworks

Wind energy has been recognized as the most promising and economical renewable energy source, attracting increasing attention in recent years. However, considering the variability and uncertainty of wind energy, accurate forecasting is crucial to propel high levels of wind energy penetration within electricity markets. In this paper, a comparative framework is proposed where a suite of long short-term memory (LSTM) recurrent neural networks (RNN) models, inclusive of standard, bidirectional, stacked, convolutional, and autoencoder architectures, are implemented to address the existing gaps and limitations of reported wind power forecasting methodologies. These integrated networks are implemented through an iterative process of varying hyperparameters to better assess their effect, and the overall performance of each architecture, when tackling one-hour to three-hours ahead wind power forecasting. The corresponding validation is carried out through hourly wind power data from the Spanish electricity market, collected between 2014 and 2020. The proposed comparative error analysis shows that, overall, the models tend to showcase low error variability and better performance when the networks are able to learn in weekly sequences. The model with the best performance in forecasting one-hour ahead wind power is the stacked LSTM, implemented with weekly learning input sequences, with an average MAPE improvement of roughly 6, 7, and 49%, when compared to standard, bidirectional, and convolutional LSTM models, respectively. In the case of two to three-hours ahead forecasting, the model with the best overall performance is the bidirectional LSTM implemented with weekly learning input sequences, showcasing an average improved MAPE performance from 2 to 23% when compared to the other LSTM architectures implemented.

Analysis of Gradient Vanishing of RNNs and Performance Comparison

A recurrent neural network (RNN) combines variable-length input data with a hidden state that depends on previous time steps to generate output data. RNNs have been widely used in time-series data analysis, and various RNN algorithms have been proposed, such as the standard RNN, long short-term memory (LSTM), and gated recurrent units (GRUs). In particular, it has been experimentally proven that LSTM and GRU have higher validation accuracy and prediction accuracy than the standard RNN. The learning ability is a measure of the effectiveness of gradient of error information that would be backpropagated. This study provided a theoretical and experimental basis for the result that LSTM and GRU have more efficient gradient descent than the standard RNN by analyzing and experimenting the gradient vanishing of the standard RNN, LSTM, and GRU. As a result, LSTM and GRU are robust to the degradation of gradient descent even when LSTM and GRU learn long-range input data, which means that the learning ability of LSTM and GRU is greater than standard RNN when learning long-range input data. Therefore, LSTM and GRU have higher validation accuracy and prediction accuracy than the standard RNN. In addition, it was verified whether the experimental results of river-level prediction models, solar power generation prediction models, and speech signal models using the standard RNN, LSTM, and GRUs are consistent with the analysis results of gradient vanishing.

Prediction of biogas production in anaerobic co-digestion of organic wastes using deep learning models

Interest in anaerobic co-digestion (AcoD) has increased significantly in recent decades owing to enhanced biogas productivity due to the utilization of different organic wastes, such as food waste and sewage sludge. In this study, a robust AcoD model for biogas prediction is developed using deep learning (DL). We propose a hybrid DL architecture, i.e., DA–LSTM–VSN, wherein a dual-stage-attention (DA)-based long short-term memory (LSTM) network is integrated with variable selection networks (VSNs). To enhance the model predictability, we perform hyperparameter optimization. The model accuracy is validated using long-term AcoD monitoring data measured over two years of municipal wastewater treatment plant operation and then compared with those of two other DL-based models (i.e., DA–LSTM and the standard LSTM). In addition, the feature importance (FI) is analyzed to investigate the relative contribution of input variables to biogas production prediction. Finally, we demonstrate the successful application of the validated DL model to the AcoD process optimization. Results show that the model accuracy improved significantly by incorporating DA into LSTM, i.e., the coefficient of determination (R2) increased from 0.38 to 0.68; however, the R2 can be further increased to 0.76 by combining DA–LSTM with a VSN. For the biogas prediction of the AcoD model, the VSN contributes significantly by employing the discontinuous time series of measurement data on biodegradable organic-associated variables during AcoD. In addition, the VSN allows the AcoD model to be interpretable via FI analysis using its weighted input features. The FI results show that the relative importance is vital to variables associated with food waste leachate, whereas it is marginal for those associated with the primary and chemically assisted sedimentation sludges. In conclusion, the AcoD model proposed herein can be utilized in practical applications as a robust tool because it can provide the optimal sludge conditions to improve biogas production. This is because it facilitates the time-series biogas prediction at the full scale using unprocessed datasets with either missing value imputation or outlier removal.

Constructing Long Short-Term Memory Networks to Predict Ulcerative Colitis Progression from Longitudinal Gut Microbiome Profiles

Introduction &amp; Objective: Ulcerative colitis is an intestinal disorder with an erratic progression in which the patients suffer from capricious remissions and changeful severities. Lacking prognosis to the UC progression can lead to irrational treatments that adversely affect the patients’ quality of life. Existing studies have stated a connection between gut microbiomes and UC progression. We aim to construct Long Short-Term Memory (LSTM) networks to predict UC progression (remission &amp; severity) from longitudinal gut microbiome data.&#x0D; Methods: Using one-step and two-step modelling strategies, we develop a standard LSTM network, an encoder-decoder LSTM network, a convolutional LSTM network, and several benchmarking classifiers such as random forests. For high-dimensional data, we also implement auto-encoder to select variables in addition to baseline procedures like principal component analysis. We train each model using a longitudinal microbiome data, and validate them via a 10-round set splitting approach.&#x0D; Results: Each proposed model shows the potential to predict UC progression, but they do not reach an optimal level for medical utilizations. The encoder-decoder LSTM demonstrates superiority over the other classifiers while the auto-encoder outperformed the baseline variable selectors.&#x0D; Conclusion: We support the capacity of Long Short-Term Memory (LSTM) networks to predict UC progression from longitudinal microbiome data, and verify the strength of autoencoder networks in selecting features from high dimensional data.