Airport surface traffic situation prediction method based on improved CNN-LSTM

This paper presents deep learning models—specifically, Long Short-Term Memory (LSTM) networks and hybrid Convolutional Neural Network–LSTM (CNN-LSTM) with a Copula-Based Random Forest (CBRF) model to estimate Heterogeneous Treatment Effects (HTEs) in survival analysis. The proposed method is designed to capture non-linear relationships and temporal dependencies in clinical and genomic data, with a particular focus on exploring how treatment effects vary by race as a moderating factor. Using breast cancer data from the TCGA-BRCA dataset, which includes both clinical variables and gene expression profiles, we filter the data to focus on two racial groups: Black or African American and White. Dimensionality reduction is performed using Principal Component Analysis (PCA). We compare the CNN-LSTM, LSTM, and CBRF models under three weighting strategies—no weights, Horvitz–Thompson (HT) weights, and Inverse Probability of Treatment Weighting (IPTW)—for predicting treatment effects. Model performance is evaluated using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Concordance statistic (C-statistic), Average Treatment Effect (ATE), and Conditional Average Treatment Effect (CATE) by race. The CNN-LSTM model consistently outperforms the others, achieving the lowest prediction errors and highest discrimination, particularly under IPTW. Among the weighting strategies, IPTW yields the most substantial improvements in model performance and bias reduction. Importantly, race-specific treatment effects exhibit notable variation: CNN-LSTM estimates a slightly higher CATE for Black individuals under IPTW. Overall, CNN-LSTM with IPTW is recommended for robust and equitable causal inference, especially in racially stratified settings.

Air quality index forecast in Beijing based on CNN-LSTM multi-model

This research is focused on the development and comparison of time series models for short-term electrical load forecasting, utilizing several variants of Long Short-Term Memory (LSTM) networks. The specific LSTM variants employed in this study include Vanilla LSTM, Stacked LSTM, Bidirectional LSTM, and Convolutional Neural Network LSTM (CNN-LSTM). We used five years (2016-2020) of daily electricity load data from the Central Java-DIY system, provided by PT PLN (Persero). The primary objective is to ascertain the accuracy and evaluate the performance of these LSTM variants in the context of short-term load forecasting. This is achieved quantitatively through the computation of various error metrics, namely Mean Square Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-squared. The results of the study reveal that the CNN-LSTM method outperforms the other variants in terms of the calculated metrics. Specifically, the CNN-LSTM method achieved the lowest values for all metrics: an MSE of 0.007 for training and 0.0010 for testing, an MAE of 0.0050 for training and 0.0062 for testing, and an RMSE of 0.083 for training and 0.099 for testing. Among the evaluated models, CNN-LSTM demonstrates the best trade-off between predictive accuracy and training efficiency, making it the most recommended for short-term electricity load forecasting. While BiLSTM achieves higher accuracy, particularly in terms of MAE, it requires a longer training time. In contrast, Stacked LSTM converges faster with slightly lower accuracy, making it a strong alternative when computational efficiency is prioritized..

Fine particulate matter (PM2.5) is a major air pollutant affecting human survival, development and health. By predicting the spatial distribution concentration of PM2.5, pollutant sources can be better traced, allowing measures to protect human health to be implemented. Thus, the purpose of this study is to predict and analyze the PM2.5 concentration of stations based on the integrated deep learning of a convolutional neural network long short-term memory (CNN-LSTM) model. To solve the complexity and nonlinear characteristics of PM2.5 time series data problems, we adopted the CNN-LSTM deep learning model. We collected the PM2.5data of Qingdao in 2020 as well as meteorological factors such as temperature, wind speed and air pressure for pre-processing and characteristic analysis. Then, the CNN-LSTM deep learning model was integrated to capture the temporal and spatial features and trends in the data. The CNN layer was used to extract spatial features, while the LSTM layer was used to learn time dependencies. Through comparative experiments and model evaluation, we found that the CNN-LSTM model can achieve excellent PM2.5 prediction performance. The results show that the coefficient of determination (R2) is 0.91, and the root mean square error (RMSE) is 8.216µg/m3. The CNN-LSTM model achieves better prediction accuracy and generalizability compared with those of the CNN and LSTM models (R2 values of 0.85 and 0.83, respectively, and RMSE values of 11.356 and 14.367, respectively). Finally, we analyzed and explained the predicted results. We also found that some meteorological factors (such as air temperature, pressure, and wind speed) have significant effects on the PM2.5 concentration at ground stations in Qingdao. In summary, by using deep learning methods, we obtained better prediction performance and revealed the association between PM2.5 concentration and meteorological factors. These findings are of great significance for improving the quality of the atmospheric environment and protecting public health.

Timely and accurate crop yield information can ensure regional food security. In the field of predicting crop yields, deep learning techniques such as long short-term memory (LSTM) and convolutional neural networks (CNN) are frequently employed. Many studies have shown that the predictions of models combining the two are better than those of single models. Crop growth can be reflected by the vegetation index calculated using data from remote sensing. However, the use of pure remote sensing data alone ignores the spatial heterogeneity of different regions. In this paper, we tested a total of three models, CNN-LSTM, CNN and convolutional LSTM (ConvLSTM), for predicting the annual rice yield at the county level in Hubei Province, China. The model was trained by ERA5 temperature (AT) data, MODIS remote sensing data including the Enhanced Vegetation Index (EVI), Gross Primary Productivity (GPP) and Soil-Adapted Vegetation Index (SAVI), and a dummy variable representing spatial heterogeneity; rice yield data from 2000–2019 were employed as labels. Data download and processing were based on Google Earth Engine (GEE). The downloaded remote sensing images were processed into normalized histograms for the training and prediction of deep learning models. According to the experimental findings, the model that included a dummy variable to represent spatial heterogeneity had a stronger predictive ability than the model trained using just remote sensing data. The prediction performance of the CNN-LSTM model outperformed the CNN or ConvLSTM model.

The research in Human Activity Recognition (HAR) using wearable probes and pocket devices has intensified to further understand and inherently foresee human behavior and their intentions. The researchers are seeking a system to consume the least amount of allocated resources to identify the consumer’s activity being performed. In this paper, we propose a state-of-the-art deep learning-based activity recognition architecture, a Convolutional Long Short-Term Memory (ConvLSTM) network . This ConvLSTM approach significantly improves the accuracy of classification of the six activities from raw data without the use of any major aspect of feature engineering hence, reducing the complexity of the model with a very minor pre-processing procedure. Our proposed model is able to achieve a staggering 94% accuracy on the UCI HAR public dataset. During performance comparisons with earlier models, we were able to notice profitable improvements against Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) Network, Deep Neural Network (DNN) models, and also against linear and non-linear machine learning models which heavily depend upon manually manufactured featured data.KeywordsHuman Activity Recognition (HAR)Convolutional Neural Network (CNN)Long Short-Term Memory Network (LSTM)Convolutional Long Short-Term Memory (ConvLSTM)Deep learningUCI HAR datasetTime Series Classification (TSC)Neural networkMagnetometersAccelerometersGyroscopesSensorsInertial Measurement Unit (IMU)

Increasing the use of renewable energy, particularly photovoltaic (PV) systems, is essential for mitigating climate change. However, the intermittent nature of PV power generation creates challenges in accurately forecasting and managing electricity supply within grid systems. This study proposes a hybrid deep learning (DL) model combining improved harmony search (IHS) optimization, convolutional neural networks (CNNs), and long short‐term memory (LSTM) networks (IHS–CNN–LSTM) for forecasting the 15‐min power output of grid‐connected monocrystalline and polycrystalline PV systems. The model uses 14 input features obtained from numerical weather prediction (NWP) and local measurement data (LMD), with data sourced from the Public Photovoltaic Output Dataset (PVOD) covering June 2018 to June 2019 in Hebei Province, China. Comparative evaluations against genetic algorithm‐based (GA–CNN–LSTM), differential evolution‐based (DE–CNN–LSTM), and conventional CNN–LSTM models showed that the IHS–CNN–LSTM provided superior forecasting accuracy. Specifically, the proposed model achieved reductions in root mean square error (RMSE) of 3.7% for polycrystalline and 1.8% for monocrystalline PV systems, and reductions in mean absolute error (MAE) of 2.6% and 1.2%, respectively, along with high R2 values of 98% and 99%. The results confirm the effectiveness and accuracy of the proposed hybrid approach for PV power output forecasting.

A structural health monitoring (SHM) framework integrating a convolutional neural network (CNN) and a long short-term memory (LSTM) network is proposed to address the identification of nonlinear, spatiotemporally varying damage features in structures under complex service conditions. From multichannel acceleration responses of a marine high-pile frame structure, time-domain statistical features, and frequency-domain features were extracted. A CNN–LSTM architecture incorporating residual units and a global attention mechanism was constructed to enhance sensitivity to key damage indicators and improve feature-extraction effectiveness. In conjunction with the International Association for Structural Control (IASC)-American Society of Civil Engineers (ASCE) benchmark frame structure, acceleration data under impact loading were obtained via finite-element simulations and scaled physical model tests to assemble an SHM dataset. The proposed CNN–LSTM model was subsequently applied to damage identification and classification. In the conducted experiments, the CNN–LSTM network achieved 100% classification accuracy across the evaluated damage scenarios and outperformed the conventional deep-learning baselines considered, indicating strong generalization within the tested settings. These findings indicate the effectiveness and reliability of the method for SHM of complex structures within the tested settings. The study presents an end-to-end solution for automated SHM and outlines its theoretical implications and potential engineering applicability.

CNN-LSTM Hybrid Model for Enhanced Malware Analysis and Detection

Electromyogram (EMG) signals cannot be forged and have the advantage of being able to change the registered data as they are characterized by the waveform, which varies depending on the gesture. In this paper, a two-step biometrics method was proposed using EMG signals based on a convolutional neural network–long short-term memory (CNN-LSTM) network. After preprocessing of the EMG signals, the time domain features and LSTM network were used to examine whether the gesture matched, and single biometrics was performed if the gesture matched. In single biometrics, EMG signals were converted into a two-dimensional spectrogram, and training and classification were performed through the CNN-LSTM network. Data fusion of the gesture recognition and single biometrics was performed in the form of an AND. The experiment used Ninapro EMG signal data as the proposed two-step biometrics method, and the results showed 83.91% gesture recognition performance and 99.17% single biometrics performance. In addition, the false acceptance rate (FAR) was observed to have been reduced by 64.7% through data fusion.

Water quality monitoring is an important component of water resources management. In order to predict two water quality variables, namely dissolved oxygen (DO; mg/L) and chlorophyll-a (Chl-a; µg/L) in the Small Prespa Lake in Greece, two standalone deep learning (DL) models, the long short-term memory (LSTM) and convolutional neural network (CNN) models, along with their hybrid, the CNN–LSTM model, were developed. The main novelty of this study was to build a coupled CNN–LSTM model to predict water quality variables. Two traditional machine learning models, support-vector regression (SVR) and decision tree (DT), were also developed to compare with the DL models. Time series of the physicochemical water quality variables, specifically pH, oxidation–reduction potential (ORP; mV), water temperature (°C), electrical conductivity (EC; µS/cm), DO and Chl-a, were obtained using a sensor at 15-min intervals from June 1, 2012 to May 31, 2013 for model development. Lag times of up to one (t − 1) and two (t − 2) for input variables pH, ORP, water temperature, and EC were used to predict DO and Chl-a concentrations, respectively. Each model’s performance in both training and testing phases was assessed using statistical metrics including the correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE), their normalized equivalents (RRMSE, RMAE; %), percentage of bias (PBIAS), Nash–Sutcliffe coefficient ($$E_{NS}$$), Willmott’s Index, and graphical plots (Taylor diagram, box plot and spider diagram). Results showed that LSTM outperformed the CNN model for DO prediction, but the standalone DL models yielded similar performances for Chl-a prediction. Generally, the hybrid CNN–LSTM models outperformed the standalone models (LSTM, CNN, SVR and DT models) in predicting both DO and Chl-a. By integrating the LSTM and CNN models, the hybrid model successfully captured both the low and high levels of the water quality variables, particularly for the DO concentrations.

This paper proposes a method based on the clustering algorithm, deep learning, and transfer learning (TL) for short‐term traffic prediction with limited data. To address the challenges posed by limited data and the complex and diverse traffic patterns observed in traffic networks, we propose a profile model based on few‐shot learning to extract each detector's unique profiles. These profiles are then used to cluster detectors with similar patterns into distinct clusters, facilitating effective learning with limited data. A Convolutional Neural Network ‐ Long Short‐Term Memory (CNN‐LSTM)‐based predictive model is proposed to learn and predict traffic volumes for each detector within a cluster. The proposed method demonstrates resilience to detector failures and has been validated using the Performance Measurement System dataset. In scenarios with less than 2 months of training data and 10% failed detectors, the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) for station‐level traffic volume prediction increase from 12.7 vehs/5 min, 20.9 vehs/5 min, and 10.5% to 13.9 vehs/5 min, 24.2 vehs/5 min, and 11.7%, respectively. For lane‐level traffic volume prediction, the average MAE, RMSE, and MAPE increase from 4.7 vehs/5 min, 7.7 vehs/5 min, and 15% to 5.6 vehs/5 min, 9.6 vehs/5 min, and 16.8%. Furthermore, the proposed method extends its applicability to traffic speed and occupancy prediction tasks. TL is integrated to improve speed/occupancy prediction accuracy by leveraging knowledge obtained from traffic volume, considering the correlation between traffic flow, speed, and occupancy. When less than 1 month of traffic speed/occupancy data is available for learning, the proposed method achieves an MAE, RMSE, and MAPE of 0.7 km/h, 1.3 km/h, and 1.3% for station‐level traffic speed prediction and 0.5%, 1.1%, and 11% for station‐level traffic occupancy.

With the increasing urbanization in China, monitoring and predicting the deformation of deep excavations has become increasingly critical. Concurrently, as neural network models find application and development in deep excavation displacement prediction, traditional models face challenges such as insufficient accuracy and weak generalization capabilities, failing to meet the high-precision warning demands of practical engineering. Therefore, research into hybrid models is necessary. This study proposes a combined neural network model integrating a Convolutional Neural Network, Long Short-Term Memory network, and Self-Attention Mechanism (CNN–LSTM–SAM), which utilizes time-series monitoring data as input. The CNN–LSTM–SAM model merges the data feature extraction capabilities of CNN, the long-term memory function of LSTM, and the information weighting capacity of the self-attention mechanism, synthesizing the advantages of various deep excavation displacement prediction models to enhance prediction accuracy and provide more effective support for construction practice. Furthermore, given the limited application of the CNN–LSTM–SAM model in deep excavation displacement analysis, this research contributes to addressing gaps in this field. Applied to an internally braced deep excavation project in the Donggang Business District of Dalian, displacement data acquired through Distributed Fiber Optic Sensing (DFOS) technology were used as training data. The CNN–LSTM–SAM model was employed to predict the horizontal displacement at the pile top. The resulting deformation predictions were compared and analyzed against those from Back Propagation (BP) neural network, Long Short-Term Memory (LSTM) network, and a combined Convolutional Neural Network-Long Short-Term Memory (CNN–LSTM) model. Results indicate that at monitoring point S5, the coefficient of determination (R2) for the CNN–LSTM–SAM model’s predictions increased by 12.42%, 10.85%, and 5.63% compared to the BP, LSTM, and CNN–LSTM models, respectively, demonstrating higher accuracy than the other three models. Similar patterns were observed when training and predicting using data from other monitoring points, proving the applicability and robustness of the CNN–LSTM–SAM model. The findings of this study offer valuable references for the design and construction of similar deep excavation projects.

Electrical conductivity (EC) is widely recognized as one of the most essential water quality metrics for predicting salinity and mineralization. In the current research, the EC of two Australian rivers (Albert River and Barratta Creek) was forecasted for up to 10 days using a novel deep learning algorithm (Convolutional Neural Network combined with Long Short-Term Memory Model, CNN-LSTM). The Boruta-XGBoost feature selection method was used to determine the significant inputs (time series lagged data) to the model. To compare the performance of Boruta-XGB-CNN-LSTM models, three machine learning approaches—multi-layer perceptron neural network (MLP), K-nearest neighbour (KNN), and extreme gradient boosting (XGBoost) were used. Different statistical metrics, such as correlation coefficient (R), root mean square error (RMSE), and mean absolute percentage error, were used to assess the models' performance. From 10 years of data in both rivers, 7 years (2012–2018) were used as a training set, and 3 years (2019–2021) were used for testing the models. Application of the Boruta-XGB-CNN-LSTM model in forecasting one day ahead of EC showed that in both stations, Boruta-XGB-CNN-LSTM can forecast the EC parameter better than other machine learning models for the test dataset (R = 0.9429, RMSE = 45.6896, MAPE = 5.9749 for Albert River, and R = 0.9215, RMSE = 43.8315, MAPE = 7.6029 for Barratta Creek). Considering the better performance of the Boruta-XGB-CNN-LSTM model in both rivers, this model was used to forecast 3–10 days ahead of EC. The results showed that the Boruta-XGB-CNN-LSTM model is very capable of forecasting the EC for the next 10 days. The results showed that by increasing the forecasting horizon from 3 to 10 days, the performance of the Boruta-XGB-CNN-LSTM model slightly decreased. The results of this study show that the Boruta-XGB-CNN-LSTM model can be used as a good soft computing method for accurately predicting how the EC will change in rivers.

This paper proposes the prediction model of wind speed and direction using convolutional neural network - long short-term memory (CNN-LSTM). The proposed prediction model combines CNN, LSTM, and fully connected neural networks (FCNN) which are useful for getting high prediction accuracy of wind speed and direction for wind power. Performances of the prediction models are evaluated by using root mean square error (RMSE) between actual measurement data and predicted data. To verify the effectiveness of the proposed prediction model in comparison with that using FCNN, CNN, or LSTM model. The usefulness of the proposed prediction model is evaluated from the improvement of prediction accuracy for each season. The proposed prediction model using CNN-LSTM can improve 27.95 - 42.16% for wind speed and 28.71 - 35.15% for wind direction depending on the season in comparison with using the FCNN that is a higher accuracy than CNN and LSTM models, and also it indicates the strongest prediction model.