CNN-LSTM Models Research Articles

Short-term prediction of PV power based on fusions of power series and ramp series

Photovoltaic (PV) power generation is highly volatile and intermittent, which poses a major challenge to the prediction and intra-day scheduling of PV power. In order to effectively improve the prediction accuracy of PV power, this paper proposes a short-term prediction model through the fusion of power series and ramp series based on CNN-LSTM models. In the proposed hybrid model, both the power series prediction module and the ramp series prediction module are used to simultaneously predict the PV power, and then the results of both modules are combined by fully connected layers and corrected by a residual network to obtain the final prediction results. The prediction effects of the proposed model are illustrated by a multi-level evaluation system of prediction errors, including the evaluation of overall prediction errors, local prediction errors, and ramp point prediction errors. Case studies show that the ramp series of PV power can better characterize the fluctuation of PV power and that the proposed model has a better prediction effect than other models.

Early Diagnosis: End-to-End CNN-LSTM Models for Mass Spectrometry Data Classification.

Liquid chromatography-mass spectrometry (LC-MS) is a powerful method for cell profiling. The use of LC-MS technology is a tool of choice for cancer research since it provides molecular fingerprints of analyzed tissues. However, the ubiquitous presence of noise, the peaks shift between acquisitions, and the huge amount of information owing to the high dimensionality of the data make rapid and accurate cancer diagnosis a challenging task. Deep learning (DL) models are not only effective classifiers but are also well suited to jointly learn feature representation and classification tasks. This is particularly relevant when applied to raw LC-MS data and hence avoid the need for costly preprocessing and complicated feature selection. In this study, we propose a new end-to-end DL methodology that addresses all of the above challenges at once, while preserving the high potential of LC-MS data. Our DL model is designed to early discriminate between tumoral and normal tissues. It is a combination of a convolutional neural network (CNN) and a long short-term memory (LSTM) Network. The CNN network allows for significantly reducing the high dimensionality of the data while learning spatially relevant features. The LSTM network enables our model to capture temporal patterns. We show that our model outperforms not only benchmark models but also state-of-the-art models developed on the same data. Our framework is a promising strategy for improving early cancer detection during a diagnostic process.

Hour-by-Hour Prediction Model of Air Pollutant Concentration Based on EIDW-Informer—A Case Study of Taiyuan

Prediction of air pollutant concentrations is currently one of the most important methods for the prevention and control of urban air pollution in most countries, and accurate and timely prediction of pollutant concentrations is of great significance for urban pollution control. Using Taiyuan, China, as a case study, this study examines how to predict hourly air pollutant concentrations over longer periods of time while ensuring their accuracy. In this paper, an air pollutant concentration prediction method based on improved inverse distance interpolation and Informer model (EIDW-Informer), and hour-by-hour prediction of PM2.5, NO2, and O3 concentrations in Taiyuan, China is carried out. In this study, historical data from seven environmental monitoring stations in Taiyuan City were used to build multidimensional environmental vectors and calculate the similarity between sample points. Then, the missing values in the dataset were interpolated according to the similarity and distance weights, and the long series prediction was performed by Informer. The experimental results show that the EIDW-Informer method has advantages in hour-by-hour prediction compared to LSTM, CNN-LSTM, and Attention-LSTM models, which improves by 20%, 27%, and 43% on 1 h, 8 h, and 72 h time scales, respectively.

Soybean Futures Price Prediction Based on CNN-LSTM Model of Bayesian Optimization Algorithm

In recent years, the complex international environment and economic situation have made soybean futures prices increasingly unstable, which is not conducive to financial stability. Therefore, this paper uses a BO-CNN-LSTM model to accurately predict soybean futures prices and to manage price fluctuations for investors and governments. Firstly, LSTM network is employed to predict soybean futures prices using the local features extracted by CNN network. In addition, CNN-LSTM hyperparameters are optimally solved using Bayesian optimization algorithms. Finally, the constructed model is compared with BP neural network, LSTM model and CNN-LSTM model. This paper selects the basic daily data of the soybean futures contract No.1 of Dalian Commodity Exchange from 2014 to 2021 for research. According to the results, CNN-LSTM models based on Bayesian optimization algorithms perform best. Compared with the basic CNN-LSTM model, MAPE increased by 44.17%, RMSE increased by 24.61%, MAE increased by 41.48%, and R2 increased by 0.06%, which demonstrates Bayesian optimization's superiority.

Performance Prediction of Airport Traffic Using LSTM and CNN-LSTM Models

During the COVID-19 pandemic, airports faced a significant drop in passenger numbers, impacting the vital hub of the aircraft transportation industry. This study aimed to evaluate whether Long Short-Term Memory Network (LSTM) and Convolutional Neural Network - Long Short-Term Memory Network (CNN-LSTM) offer more accurate predictions for airport traffic during the COVID-19 pandemic from March to December 2020. The studies involved data filtering, applying min-max scaling, and dividing the dataset into 80% training and 20% testing sets. Parameter adjustment was performed with different optimizers such as RMSProp, Stochastic Gradient Descent (SGD), Adam, Nadam, and Adamax. Performance evaluation uses metrics that include Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and R-squared (R2). The best LSTM model achieved an impressive MAPE score of 0.0932, while the CNN-LSTM model had a slightly higher score of 0.0960. In particular, the inclusion of a balanced data set representing a percentage of the base period for each airport had a significant impact on improving prediction accuracy. This research contributes to providing stakeholders with valuable insights into the effectiveness of predicting airport traffic patterns during these unprecedented times.

Prediction of COVID-19 Using a WOA-BILSTM Model.

The COVID-19 pandemic has had a significant impact on the world, highlighting the importance of the accurate prediction of infection numbers. Given that the transmission of SARS-CoV-2 is influenced by temporal and spatial factors, numerous researchers have employed neural networks to address this issue. Accordingly, we propose a whale optimization algorithm-bidirectional long short-term memory (WOA-BILSTM) model for predicting cumulative confirmed cases. In the model, we initially input regional epidemic data, including cumulative confirmed, cured, and death cases, as well as existing cases and daily confirmed, cured, and death cases. Subsequently, we utilized the BILSTM as the base model and incorporated WOA to optimize the specific parameters. Our experiments employed epidemic data from Beijing, Guangdong, and Chongqing in China. We then compared our model with LSTM, BILSTM, GRU, CNN, CNN-LSTM, RNN-GRU, DES, ARIMA, linear, Lasso, and SVM models. The outcomes demonstrated that our model outperformed these alternatives and retained the highest accuracy in complex scenarios. In addition, we also used Bayesian and grid search algorithms to optimize the BILSTM model. The results showed that the WOA model converged fast and found the optimal solution more easily. Thus, our model can assist governments in developing more effective control measures.

Fault Diagnosis of Rolling Bearing Based on HPSO Algorithm Optimized CNN-LSTM Neural Network.

The quality of rolling bearings is vital for the working state and rotation accuracy of the shaft. Timely and accurately acquiring bearing status and early fault diagnosis can effectively prevent losses, making it highly practical. To improve the accuracy of bearing fault diagnosis, this paper proposes a CNN-LSTM bearing fault diagnosis model optimized by hybrid particle swarm optimization (HPSO). The HPSO algorithm has a strong global optimization ability and can effectively solve nonlinear and multivariate optimization problems. It is used to optimize and match the parameters of the CNN-LSTM model and dynamically find the optimal value of the parameters. This model overcomes the problem that the parameters of the CNN-LSTM model depend on empirical settings and cannot be adjusted dynamically. This model is used for bearing fault diagnosis, and the accuracy rate of fault diagnosis classification reaches 99.2%. Compared with the traditional CNN, LSTM, and CNN-LSTM models, the accuracy rates are increased by 6.6%, 9.2%, and 5%, respectively. At the same time, comparing the models with different optimization parameters shows that the model proposed in this paper has the highest accuracy. The experimental results verified the superiority of the HPSO algorithm to optimize model parameters and the feasibility and accuracy of the HPSO-CNN-LSTM model for bearing fault diagnosis.

Fraud Detection for Online Interbank Transaction Using Deep Learning

The World Banking with its various financial services is an easy target for fraudsters to carry out their actions. Various kinds of fraud that occurred such as credit card fraud, online payment fraud, debit card fraud, online transaction fraud, e-commerce fraud and other services including interbank online transactions. Fast and reliable fraud detection is important because many financial losses have occurred due to fraud. The objective of this study is obtaining a more effective deep learning model for fraud detection in the interbank online transaction system compared to similar models. This study using CNN, LSTM and hybrid model CNN-LSTM models are used to build an interbank online transaction system. The proposed model CNN consist of three convolution layer, one maxpooling layer, one dropout layer and one fully connected layer. The proposed model LSTM built by double layer LSTM with each layer consist 32 cell LSTM, dropout layer and one fully connected layer. The proposed model CNN-LSTM built by combination three convolution layer, 1 maxpooling layer, dropout layer, 1 LSTM layer with 64 LSTM cell and one fully connected layer. The Dataset taken from an interbank online transaction in March 2021 from one of the switching company in Indonesia. SMOTE is use to overcome the imbalance Dataset in training and validation Dataset. The Dataset contains 279513 transactions with 2374 transactions categorized as fraud. The results showed that the CNN model scored an F1-score value at 93,09%, followed by the LSTM model at 86,25% and the CNN-LSTM hybrid model at 69,22%. Based on these results, the proposed CNN model can be accurate for fraud detection in interbank online transaction systems compared to similar models.

Arabic Sentiment Analysis Based on Word Embeddings and Deep Learning

Social media networks have grown exponentially over the last two decades, providing the opportunity for users of the internet to communicate and exchange ideas on a variety of topics. The outcome is that opinion mining plays a crucial role in analyzing user opinions and applying these to guide choices, making it one of the most popular areas of research in the field of natural language processing. Despite the fact that several languages, including English, have been the subjects of several studies, not much has been conducted in the area of the Arabic language. The morphological complexities and various dialects of the language make semantic analysis particularly challenging. Moreover, the lack of accurate pre-processing tools and limited resources are constraining factors. This novel study was motivated by the accomplishments of deep learning algorithms and word embeddings in the field of English sentiment analysis. Extensive experiments were conducted based on supervised machine learning in which word embeddings were exploited to determine the sentiment of Arabic reviews. Three deep learning algorithms, convolutional neural networks (CNNs), long short-term memory (LSTM), and a hybrid CNN-LSTM, were introduced. The models used features learned by word embeddings such as Word2Vec and fastText rather than hand-crafted features. The models were tested using two benchmark Arabic datasets: Hotel Arabic Reviews Dataset (HARD) for hotel reviews and Large-Scale Arabic Book Reviews (LARB) for book reviews, with different setups. Comparative experiments utilized the three models with two-word embeddings and different setups of the datasets. The main novelty of this study is to explore the effectiveness of using various word embeddings and different setups of benchmark datasets relating to balance, imbalance, and binary and multi-classification aspects. Findings showed that the best results were obtained in most cases when applying the fastText word embedding using the HARD 2-imbalance dataset for all three proposed models: CNN, LSTM, and CNN-LSTM. Further, the proposed CNN model outperformed the LSTM and CNN-LSTM models for the benchmark HARD dataset by achieving 94.69%, 94.63%, and 94.54% accuracy with fastText, respectively. Although the worst results were obtained for the LABR 3-imbalance dataset using both Word2Vec and FastText, they still outperformed other researchers’ state-of-the-art outcomes applying the same dataset.

A Power Load Prediction by LSTM Model Based on the Double Attention Mechanism for Hospital Building

This work proposed a LSTM (long short-term memory) model based on the double attention mechanism for power load prediction, to further improve the energy-saving potential and accurately control the distribution of power load into each department of the hospital. Firstly, the key influencing factors of the power loads were screened based on the grey relational degree analysis. Secondly, in view of the characteristics of the power loads affected by various factors and time series changes, the feature attention mechanism and sequential attention mechanism were introduced on the basis of LSTM network. The former was used to analyze the relationship between the historical information and input variables autonomously to extract important features, and the latter was used to select the historical information at critical moments of LSTM network to improve the stability of long-term prediction effects. In the end, the experimental results from the power loads of Shanxi Eye Hospital show that the LSTM model based on the double attention mechanism has the higher forecasting accuracy and stability than the conventional LSTM, CNN-LSTM and attention-LSTM models.

Real-World Driver Stress Recognition and Diagnosis Based on Multimodal Deep Learning and Fuzzy EDAS Approaches.

Mental stress is known as a prime factor in road crashes. The devastation of these crashes often results in damage to humans, vehicles, and infrastructure. Likewise, persistent mental stress could lead to the development of mental, cardiovascular, and abdominal disorders. Preceding research in this domain mostly focuses on feature engineering and conventional machine learning approaches. These approaches recognize different levels of stress based on handcrafted features extracted from various modalities including physiological, physical, and contextual data. Acquiring good quality features from these modalities using feature engineering is often a difficult job. Recent developments in the form of deep learning (DL) algorithms have relieved feature engineering by automatically extracting and learning resilient features. This paper proposes different CNN and CNN-LSTSM-based fusion models using physiological signals (SRAD dataset) and multimodal data (AffectiveROAD dataset) for the driver's two and three stress levels. The fuzzy EDAS (evaluation based on distance from average solution) approach is used to evaluate the performance of the proposed models based on different classification metrics (accuracy, recall, precision, F-score, and specificity). Fuzzy EDAS performance estimation shows that the proposed CNN and hybrid CNN-LSTM models achieved the first ranks based on the fusion of BH, E4-Left (E4-L), and E4-Right (E4-R). Results showed the significance of multimodal data for designing an accurate and trustworthy stress recognition diagnosing model for real-world driving conditions. The proposed model can also be used for the diagnosis of the stress level of a subject during other daily life activities.

Short-term Bus Passenger Flow Forecast Based on CNN-BiLSTM

Effective prediction of urban bus passenger flow is critical for improving urban bus operation efficiency and optimizing the bus network. However, there are some issues with predicting urban bus passenger flow at the moment, such as lack of single eigenvalue consideration and insufficient research depth. In order to improve the short-term prediction accuracy of urban bus passenger flow, this paper proposed a deep learning prediction model that is based on CNN-BiLSTM. Based on historical data of urban bus passenger flow, this paper analyzes the dependence of bus credit card data, clusters the travel feature of different groups of people, and analyzes the dependence of bus passengers. Simultaneously, external factors of passenger flow, such as rainfall, weather condition, traffic flow state, and date, are introduced to build the bus passenger flow prediction feature matrix, and the correlation analysis of the characteristic matrix structure is performed to optimize the matrix structure. Finally, the optimized passenger flow characteristic matrix is fed into the CNN-BiLSTM deep learning model for prediction, and the results are compared to the LSTM, CNN and CNN-LSTM models. The results shown that the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) of the the CNN-BiLSTM deep learning model are lower than those of other models, and the prediction accuracy is the highest. Meanwhile, this method has a good generalization effect and can improve deep learning prediction accuracy.

Research on Stock Prediction Based on Bidirectional Long Short Term Memory Neural Network Model Based on Attention Mechanism Optimization

The complexity and volatility of financial markets place higher demands on the accuracy of stock forecasts. This paper uses Ping An Daily Market Data as the source of experimental data for empirical analysis, and innovatively combines BiLSTM with attention mechanism for stock price prediction in the experimental process. Introduce an attention mechanism, AM, to reinforce important features by reassigning the weight of each data; Bidirectional LSTM can learn sequential and reverse time series data information to ensure adequate data utilization. After establishing BP (backpropagation), LSTM and CNN-LSTM models for comparison, it is found that the proposed AM-BiLSTM model has high accuracy, good feasibility and versatility.

Blockchain Transaction Fee Forecasting: A Comparison of Machine Learning Methods

Gas is the transaction-fee metering system of the Ethereum network. Users of the network are required to select a gas price for submission with their transaction, creating a risk of overpaying or delayed/unprocessed transactions involved in this selection. In this work, we investigate data in the aftermath of the London Hard Fork and shed insight into the transaction dynamics of the network after this major fork. As such, this paper provides an update on work previous to 2019 on the link between EthUSD/BitUSD and gas price. For forecasting, we compare a novel combination of machine learning methods such as Direct-Recursive Hybrid LSTM, CNN-LSTM, and Attention-LSTM. These are combined with wavelet threshold denoising and matrix profile data processing toward the forecasting of block minimum gas price, on a 5-min timescale, over multiple lookaheads. As the first application of the matrix profile being applied to gas price data and forecasting that we are aware of, this study demonstrates that matrix profile data can enhance attention-based models; however, given the hardware constraints, hybrid models outperformed attention and CNN-LSTM models. The wavelet coherence of inputs demonstrates correlation in multiple variables on a 1-day timescale, which is a deviation of base free from gas price. A Direct-Recursive Hybrid LSTM strategy is found to outperform other models, with an average RMSE of 26.08 and R2 of 0.54 over a 50-min lookahead window compared to an RMSE of 26.78 and R2 of 0.452 in the best-performing attention model. Hybrid models are shown to have favorable performance up to a 20-min lookahead with performance being comparable to attention models when forecasting 25–50-min ahead. Forecasts over a range of lookaheads allow users to make an informed decision on gas price selection and the optimal window to submit their transaction in without fear of their transaction being rejected. This, in turn, gives more detailed insight into gas price dynamics than existing recommenders, oracles and forecasting approaches, which provide simple heuristics or limited lookahead horizons.

Landslide displacement prediction based on the ICEEMDAN, ApEn and the CNN-LSTM models

Landslide displacement prediction based on the ICEEMDAN, ApEn and the CNN-LSTM models

Prediction of atmospheric pollutants in urban environment based on coupled deep learning model and sensitivity analysis

Accurate and efficient predictions of pollutants in the atmosphere provide a reliable basis for the scientific management of atmospheric pollution. This study develops a model that combines an attention mechanism, convolutional neural network (CNN), and long short-term memory (LSTM) unit to predict the O3 and PM2.5 levels in the atmosphere, as well as an air quality index (AQI). The prediction results given by the proposed model are compared with those from CNN-LSTM and LSTM models as well as random forest and support vector regression models. The proposed model achieves a correlation coefficient between the predicted and observed values of more than 0.90, outperforming the other four models. The model errors are also consistently lower when using the proposed approach. Sobol-based sensitivity analysis is applied to identify the variables that make the greatest contribution to the model prediction results. Taking the COVID-19 outbreak as the time boundary, we find some homology in the interactions among the pollutants and meteorological factors in the atmosphere during different periods. Solar irradiance is the most important factor for O3, CO is the most important factor for PM2.5, and particulate matter has the most significant effect on AQI. The key influencing factors are the same over the whole phase and before the COVID-19 outbreak, indicating that the impact of COVID-19 restrictions on AQI gradually stabilized. Removing variables that contribute the least to the prediction results without affecting the model prediction performance improves the modeling efficiency and reduces the computational costs.

Prediction of road dust concentration in open-pit coal mines based on multivariate mixed model.

The problem of dust pollution in the open-pit coal mine significantly impacts the health of staff, the regular operation of mining work, and the surrounding environment. At the same time, the open-pit road is the largest dust source. Therefore, it analyzes the influencing factors of road dust concentration in the open-pit coal mine. It is of practical significance to establish a prediction model for scientific and effective prediction of road dust concentration in the open pit coal mine. The prediction model helps reduce dust hazards. This paper uses the hourly air quality and meteorological data of an open-pit coal mine in Tongliao City, Inner Mongolia Autonomous Region, from January 1, 2020, to December 31, 2021. Create a CNN-BiLSTM-Attention multivariate hybrid model consisting of a Convolutional Neural Network (CNN), a bidirectional long short-term memory neural network (BiLSTM), and an attention mechanism, Prediction of PM2.5 concentration in the next 24h. Establish prediction models of parallel and serial structures, and carry out many experiments according to the change period of the data to determine the optimal configuration and the input and output size. Then, a comparison of the proposed model and Lasso regression, SVR, XGBoost, LSTM, BiLSTM, CNN-LSTM, and CNN-BiLSTM models for short-term prediction (24h) and long-term prediction (48h, 72h, 96h, and 120h). The results show that the CNN-BiLSTM-Attention multivariate mixed model proposed in this paper has the best prediction performance. The mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2) of the short-term forecast (24h) are 6.957, 8.985, and 0.914, respectively. Evaluation indicators of long-term forecasts (48h, 72h, 96h, and 120h) are also superior to contrast models. Finally, we used field-measured data to verify, and the obtained evaluation indexes MAE, RMSE, and R2 are 3.127, 3.989, and 0.951, respectively. The model-fitting effect was good.

Streamflow Simulation with High-Resolution WRF Input Variables Based on the CNN-LSTM Hybrid Model and Gamma Test

Streamflow modelling is one of the most important elements for the management of water resources and flood control in the context of future climate change. With the advancement of numerical weather prediction and modern detection technologies, more and more high-resolution hydro-meteorological data can be obtained, while traditional physical hydrological models cannot make full use of them. In this study, a hybrid deep learning approach is proposed for the simulation of daily streamflow in two mountainous catchments of the Daqing River Basin, northern China. Two-dimensional high-resolution (1 km) output data from a WRF model were used as the model input, a convolutional neural network (CNN) model was used to extract the physical and meteorological characteristics of the catchment at a certain time, and the long short-term memory (LSTM) model was applied to simulate the streamflow using the time-series data extracted by the CNN model. To reduce model input noise and avoid overfitting, the Gamma test method was adopted and the correlations between the input variables were checked to select the optimal combination of input variables. The performance of the CNN-LSTM models was acceptable without using the Gamma test (i.e., with all WRF input variables included), with NSE and RMSE values of 0.9298 and 9.0047 m3/s, respectively, in the Fuping catchment, and 0.8330 and 1.1806 m3/s, respectively, in the Zijingguan catchment. However, it was found that the performance of the model could be significantly improved by the use of the Gamma test. Using the best combination of input variables selected by the Gamma test, the NSE of the Fuping catchment increased to 0.9618 and the RMSE decreased to 6.6366 m3/s, and the NSE of the Zijingguan catchment increased to 0.9515 and the RMSE decreased to 0.6366 m3/s. These results demonstrate the feasibility of the CNN-LSTM approach for flood streamflow simulation using WRF-downscaled high-resolution data. By using this approach to assess the potential impacts of climate change on streamflow with the abundant high-resolution meteorological data generated by different climate scenarios, water managers can develop more effective strategies for managing water resources and reducing the risks associated with droughts and floods.

Improving LSTM hydrological modeling with spatiotemporal deep learning and multi-task learning: A case study of three mountainous areas on the Tibetan Plateau

Long short-term memory (LSTM) networks have demonstrated their excellent capability in processing long-length temporal dynamics and have proven to be effective in precipitation-runoff modeling. However, the current LSTM hydrological models lack the incorporation of multi-task learning and spatial information, which limits their ability to make full use of meteorological and hydrological data. To address this issue, this study proposes a spatiotemporal deep-learning (DL)-based hydrological model that couples the 2-Dimension convolutional neural network (CNN) and LSTM and introduces actual evaporation (Ea) as an additional training target. The proposed CNN-LSTM model is tested on three large mountainous basins on the Tibetan Plateau, and the results are compared to those obtained from the LSTM-only model. Additionally, a probe method is used to decipher the internal embedding layers of the proposed DL models. The results indicate that both LSTM and CNN-LSTM hydrological models perform well in simulating runoff (Q) and Ea, with Nash-Sutcliffe efficiency coefficients (NSEs) higher than 0.82 and 0.95, respectively. The higher NSEs suggest that introducing spatial information into LSTM-only models can improve the overall and peak model performance. Moreover, multi-task simulation with LSTM-only models shows better accuracy in the estimation of Q volume and performance, with NSEs increasing by approximately 0.02. The probe method also reveals that CNN can capture the basin-averaged meteorological values in CNN-LSTM models, while LSTM Q (Ea) models contain the information about the known Ea (Q) process. Overall, this study demonstrates the value of spatial information and multi-task learning in LSTM hydrological modeling and provides a perspective for interpreting the internal embedding layers of DL models.

A CNN-LSTM model for six human ankle movements classification on different loads.

This study aims to address three problems in current studies in decoding the ankle movement intention for robot-assisted bilateral rehabilitation using surface electromyogram (sEMG) signals: (1) only up to four ankle movements could be identified while six ankle movements should be classified to provide better training; (2) feeding the raw sEMG signals directly into the neural network leads to high computational cost; and (3) load variation has large influence on classification accuracy. To achieve this, a convolutional neural network (CNN)-long short-term memory (LSTM) model, a time-domain feature selection method of the sEMG, and a two-step method are proposed. For the first time, the Boruta algorithm is used to select time-domain features of sEMG. The selected features, rather than raw sEMG signals are fed into the CNN-LSTM model. Hence, the number of model's parameters is reduced from 331,938 to 155,042, by half. Experiments are conducted to validate the proposed method. The results show that our method could classify six ankle movements with relatively good accuracy (95.73%). The accuracy of CNN-LSTM, CNN, and LSTM models with sEMG features as input are all higher than that of corresponding models with raw sEMG as input. The overall accuracy is improved from 73.23% to 93.50% using our two-step method for identifying the ankle movements with different loads. Our proposed CNN-LSTM model have the highest accuracy for ankle movements classification compared with CNN, LSTM, and Support Vector Machine (SVM).