Temporal Dependence Research Articles

Learning Short-Term Spatial–Temporal Dependency for UAV 2-D Trajectory Forecasting

Learning Short-Term Spatial–Temporal Dependency for UAV 2-D Trajectory Forecasting

Research on Multi-Scale Signal Processing and Efficient Model Construction Strategies in Lithium-Ion Battery State Prediction

Abstract To tackle the question of limited generalization and inefficiency in predicting state of health (SOH) and state of charge (SOC) in lithium-ion batteries across diverse sequence lengths, a novel hybrid model is developed. This model integrates multivariate variational mode decomposition (MVMD), informer, and long short-term Memory (LSTM) networks. Initially, battery health features are extracted from the charge and discharge curves, which are then validated for their relevance to SOH and SOC via correlation analysis and random forest algorithms. These features undergo multi-scale decomposition using MVMD, thereby encapsulating the intricate dynamics of battery state changes across various time scales. This decomposition enhances the model's adaptability to different sequence lengths, bolstering its generalization capability. Subsequently, the informer model is utilized to identify temporal patterns within the decomposed features. Finally, LSTM exploits its capacity to capture temporal dependencies for further refinement of the predictions. This hybrid strategy yields substantial enhancements in both efficiency and accuracy. Compared to the transformer model, the proposed hybrid model demonstrates a 30% reduction in SOH prediction error and a 22% decrease in SOC prediction error, concurrently slashing training time significantly. Spanning diverse sequence lengths and battery types, demonstrates the model's strong generalization capabilities.

Convolutional long short-term memory neural network for groundwater change prediction

Forecasting groundwater changes is a crucial step towards effective water resource planning and sustainable management. Conventional models still demonstrated insufficient performance when aquifers have high spatio-temporal heterogeneity or inadequate availability of data in simulating groundwater behavior. In this regard, a spatio-temporal groundwater deep learning model is proposed to be applied for monthly groundwater prediction over the entire Choushui River Alluvial Fan in Central Taiwan. The combination of the Convolution Neural Network (CNN) and Long Short-Term Memory (LSTM) known as Convolutional Long Short-Term Memory (CLSTM) Neural Network is proposed and investigated. Result showed that the monthly groundwater simulations from the proposed neural model were better reflective of the original observation data while producing significant improvements in comparison to only the CNN, LSTM as well as classical neural models. The study also explored the performance of the Masked CLSTM model which is designed to handle missing data by reconstructing incomplete spatio-temporal input images, enhancing groundwater forecasting through image inpainting. The findings indicated that the neural architecture can efficiently extract the relevant spatial features from the past incomplete information of hydraulic head observations under various masking scenarios while simultaneously handling the varying temporal dependencies over the entire study region. The proposed model showed strong reliability in reconstructing and simulating the spatial distribution of hydraulic heads for the following month, as evidenced by low RMSE values and high correlation coefficients when compared to observed data.

Robust Human Activity Recognition for Intelligent Transportation Systems Using Smartphone Sensors: A Position-Independent Approach

This study explores Human Activity Recognition (HAR) using smartphone sensors to address the challenges posed by position-dependent datasets. We propose a position-independent system that leverages data from accelerometers, gyroscopes, linear accelerometers, and gravity sensors collected from smartphones placed either on the chest or in the left/right leg pocket. The performance of traditional machine learning algorithms (Decision Trees (DT), K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Classifier (SVC), and XGBoost) is compared against deep learning models (Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Temporal Convolutional Networks (TCN), and Transformer models) under two sensor configurations. Our findings highlight that the Temporal Convolutional Network (TCN) model consistently outperforms other models, particularly in the four-sensor non-overlapping configuration, achieving the highest accuracy of 97.70%. Deep learning models such as LSTM, GRU, and Transformer also demonstrate strong performance, showcasing their effectiveness in capturing temporal dependencies in HAR tasks. Traditional machine learning models, including RF and XGBoost, provide reasonable performance but do not match the accuracy of deep learning models. Additionally, incorporating data from linear accelerometers and gravity sensors led to slight improvements over using accelerometer and gyroscope data alone. This research enhances the recognition of passenger behaviors for intelligent transportation systems, contributing to more efficient congestion management and emergency response strategies.

High-precision prediction of microalgae biofuel production efficiency: employing ELG ensemble method

Microalgae biofuels are considered a significant source of future renewable energy due to their efficient photosynthesis and rapid growth rates. However, practical applications face numerous challenges such as variations in environmental conditions, high cultivation costs, and energy losses during production. In this study, we propose an ensemble model called ELG, integrating Empirical Mode Decomposition (EMD), Long Short-Term Memory (LSTM), and Gradient Boosting Machine (GBM), to enhance prediction accuracy. The model is tested on two primary datasets: the EIA (U.S. Energy Information Administration) dataset and the NREL (National Renewable Energy Laboratory) dataset, both of which provide extensive data on biofuel production and environmental conditions. Experimental results demonstrate the superior performance of the ELG model, achieving an RMSE of 0.089 and MAPE of 2.02% on the EIA dataset, and an RMSE of 0.1 and MAPE of 2.21% on the NREL dataset. These metrics indicate that the ELG model outperforms existing models in predicting the efficiency of microalgae biofuel production. The integration of EMD for preprocessing, LSTM for capturing temporal dependencies, and GBM for optimizing prediction outputs significantly improves the model’s predictive accuracy and robustness. This research, through high-precision prediction of microalgae biofuel production efficiency, optimizes resource allocation and enhances economic feasibility. It advances technological capabilities and scientific understanding in the field of microalgae biofuels and provides a robust framework for other renewable energy applications.

Reconstructing Richtmyer–Meshkov instabilities from noisy radiographs using low dimensional features and attention-based neural networks

We develop an ML-based approach for density reconstruction based on transformer neural networks. This approach is demonstrated in the setting of ICF-like double shell hydrodynamic simulations wherein the parameters related to material properties and initial conditions are varied. The new method can robustly recover the complex topologies given by the Richtmyer-Meshkoff instability (RMI) from a sequence of hydrodynamic features derived from radiographic images corrupted with blur, scatter, and noise. A noise model is developed to characterize errors in extracting features from synthetic radiographs of the simulated density field. The key component of the network is a transformer encoder that acts on a sequence of features extracted from noisy radiographs. This encoder includes numerous self-attention layers that act to learn temporal dependencies in the input sequences and increase the expressiveness of the model. This approach is shown to exhibit an excellent ability to accurately recover the RMI growth rates, despite the gas-metal interface being greatly obscured by radiographic noise. Our approach can be applied in a broad array of fields involving shock physics and material science.

Deep learning-based spectrum sensing and modulation categorization for efficient data transmission in cognitive radio

Abstract One prominent feature of cognitive radio (CR) involves spectrum sensing (SS), which allows licensed primary users to remain unaffected by secondary users’ ability to discover and exploit unoccupied frequency bands. Spectrum sensing enhances the use of spectrum in CR devices, increasing their adaptability and efficiency in wireless communication systems. The rise of wireless equipment and the advent of IoT technologies compound this need for flexibility. Over time, the fixed allocation of frequencies has led to inefficiencies and underutilization as bandwidth needs increase. Deep learning and artificial intelligence have improved spectrum sensing by increasing detection probability of primary users’ presence under noisy environments, enabling cognitive radio systems to respond intelligently to fluctuations in RF environments. This article is concerned with deep learning techniques for spectrum sensing and modulation categorization with CBRT structure, which combines convolutional neural networks (CNNs), bidirectional recurrent neural networks (BRNNs), and transformer networks (TNs) to improve spectrum sensing. CNNs are responsible for performing spectrum feature extraction; BRNNs are used to capture temporal dependencies; and TNs are good at long range dependencies. Better performance for this model is aimed by integrating the three architectures described. In the proposed work, six digital modulation schemes were considered, for spectrum sensing. The sensing of spectrum in this model is performed using the RadioML2016.10B open-source dataset and performance metrics like the Jaccard Index (JI), Fowlkes’s Mallows Index, and F1 Score. Modulation classification has been performed using MIGOU-MOD open-source dataset. The proposed model exhibits good detection probability and low sensing error, unlike other methods at lower SNR.

Incentivized BiLSTM with Triplet Attention for Predecting Congestion in Network Traffic

In the world of online live video streaming, network traffic congestion poses a serious risk to user experience and service quality. Several factors contributing to the congestion include insufficient bandwidth, an increase in user demand, as well as ineffective data routing. The incapacity of the prediction algorithms to Adjust to modifications in network circumstances and challenges in detecting long-range relationships may restrict their ability to effectively estimate congestion in dynamic contexts when it comes to online streaming video. In order to overcome these constraints, this study created an Incentivized-RF-Triplet ASTM (“Incentivized learning-based triplet attention enabled rat fierce hunting optimized Bidirectional Long Short-Term Memory) for network traffic congestion prediction in online streaming video. A reward” scheme built into the Incentivized learning mechanism pushes the algorithm to prioritize online live video streaming congestion prediction. The sequential structure of network traffic data is handled by the BiLSTM architecture, that is well-known for capturing temporal dependencies. By utilizing the triplet Attention method, the model is better able to identify relevant regions within the input data as well as identify congestion patterns more successfully. The RFSO method incorporates social behavior with selection and searching qualities to further improve the classifier's parameters. Therefore, the characteristics of the model can be tuned more effectively and robustly, improving its effectiveness in congestion detection. The outcomes of the experiment show how well the Incentivized-RF-Triplet ASTM technique works to precisely estimate traffic congestion for the Darpa99week1 dataset. 95.97% accuracy, 96.08% specificity, and 0.22 mean square error are reported.

SAM-Net: Spatio-Temporal Sequence Typhoon Cloud Image Prediction Net with Self-Attention Memory

Cloud image prediction is a spatio-temporal sequence prediction task, similar to video prediction. Spatio-temporal sequence prediction involves learning from historical data and using the learned features to generate future images. In this process, the changes in time and space are crucial for spatio-temporal sequence prediction models. However, most models now rely on stacking convolutional layers to obtain local spatial features. In response to the complex changes in cloud position and shape in cloud images, the prediction module of the model needs to be able to extract both global and local spatial features from the cloud images. In addition, for irregular cloud motion, more attention should be paid to the spatio-temporal sequence features between input cloud image frames in the temporal sequence prediction module, considering the extraction of temporal features with long temporal dependencies, so that the spatio-temporal sequence prediction network can learn cloud motion trends more accurately. To address these issues, we have introduced an innovative model called SAM-Net. The self-attention module of this model aims to extract an inner image frame’s spatial features of global and local dependencies. In addition, a memory mechanism has been added to the self-attention module to extract interframe features with long temporal and spatial dependencies. Our method shows better performance than the PredRNN-v2 model on publicly available datasets such as MovingMNIST and KTH. We achieved the best performance in both the 4-time-step and 10-time-step typhoon cloud image predictions. On a cloud dataset consisting of 10 time steps, we observed a decrease in MSE of 180.58, a decrease in LPIPS of 0.064, an increase in SSIM of 0.351, and a significant improvement in PSNR of 5.56 compared to PredRNN-v2.

MSDG: Multi-Scale Dynamic Graph Neural Network for Industrial Time Series Anomaly Detection

A large number of sensors are typically installed in industrial plants to collect real-time operational data. These sensors monitor data with time series correlation and spatial correlation over time. In previous studies, GNN has built many successful models to deal with time series data, but most of these models have fixed perspectives and struggle to capture the dynamic correlations in time and space simultaneously. Therefore, this paper constructs a multi-scale dynamic graph neural network (MSDG) for anomaly detection in industrial sensor data. First, a multi-scale sliding window mechanism is proposed to input different scale sensor data into the corresponding network. Then, a dynamic graph neural network is constructed to capture the spatial–temporal dependencies of multivariate sensor data. Finally, the model comprehensively considers the extracted features for sequence reconstruction and utilizes the reconstruction errors for anomaly detection. Experiments have been conducted on three real public datasets, and the results show that the proposed method outperforms the mainstream methods.

Milling Machine Fault Diagnosis Using Acoustic Emission and Hybrid Deep Learning with Feature Optimization

This paper presents a fault diagnosis technique for milling machines based on acoustic emission (AE) signals and a hybrid deep learning model optimized with a genetic algorithm. Mechanical failures in milling machines, particularly in critical components like cutting tools, gears, and bearings, account for a significant portion of operational breakdowns, leading to unplanned downtime and financial losses. To address this issue, the proposed method first acquires AE signals from the milling machine. AE signals, capturing the dynamic responses of machine components, are transformed into continuous wavelet transform (CWT) scalograms for further analysis. Gaussian filtering is applied to enhance the clarity of these scalograms, effectively reducing noise while maintaining essential features. A convolutional neural network (CNN) based on the VGG16 architecture is utilized for spatial feature extraction, followed by a bidirectional long short-term memory (BiLSTM) network to capture the temporal dependencies of the scalograms. The genetic algorithm (GA) is used to optimize feature selection and ensure the selection of the most relevant features to further improve the model’s performance. The optimized features are finally fed into a fully connected (FC) layer of the proposed hybrid model for fault classification. The proposed method achieves an accuracy of 99.6%, significantly outperforming traditional approaches. This method offers a highly accurate and efficient solution for fault detection in milling machines, allowing for more reliable predictive maintenance and operational efficiency in industrial settings.

Deep Learning‐Based Anomaly Diagnosis Method for Capacitive Voltage Transformer Measurement Error in PIoT

ABSTRACTIn the era of power Internet of Things (PIoT), the accuracy of capacitive voltage transformers (CVTs) is crucial for maintaining the reliability of voltage measurement and protection systems in smart grids, thereby contributing to overall grid stability and efficiency. Accurate and timely detection of anomalies in CVT measurement errors is essential for preventing equipment failures, reducing maintenance costs, and improving overall system reliability. However, existing anomaly diagnosis methods often rely on statistical analysis and rule‐based approaches, which have limitations in capturing complex patterns and adapting to evolving anomaly types. This paper proposes a novel deep learning‐based anomaly diagnosis method for CVT measurement error in PIoT, called LSTM‐CVT. The proposed method leverages a long short‐term memory (LSTM) neural network architecture with three key strategies: bidirectional temporal dependency capture, hierarchical feature learning, and joint anomaly diagnosis and error estimation. The experimental results demonstrate the superior performance of LSTM‐CVT compared to state‐of‐the‐art baseline methods.

Spatio-temporal attention based collaborative local–global learning for traffic flow prediction

Traffic flow prediction is crucial for intelligent transportation systems (ITS), providing valuable insights for traffic control, route planning, and operation management. Existing work often separately models the spatial and temporal dependencies and primarily relies on predefined graphs to represent spatio-temporal dependencies, neglecting the traffic dynamics caused by unexpected events and the global relationships among road segments. Unlike previous models that primarily focus on local feature extraction, we propose a novel collaborative local–global learning model (LOGO) that employs spatio-temporal attention (STA) and graph convolutional networks (GCN). Specifically, LOGO simultaneously extracts hidden traffic features from both local and global perspectives. In local feature extraction, a novel STA is devised to directly attend to spatio-temporal coupling interdependencies instead of separately modeling temporal and spatial dependencies, and to capture in-depth spatio-temporal traffic context with an adaptive graph focusing on the dynamics in traffic flow. In global feature extraction, a global correlation matrix is constructed and GCNs are utilized to propagate messages on the obtained matrix to achieve interactions between both adjacent and similar road segments. Finally, the obtained local and global features are concatenated and fed into a gated aggregation to forecast future traffic flow. Extensive experiments on four real-world traffic datasets sourced from the Caltrans Performance Measurement System (PEMS03, PEMS04, PEMS07, and PEMS08) demonstrate the effectiveness of our proposed model. LOGO achieves the best performance over 18 state-of-the-art baselines and the best prediction performance with the highest improvement of 6.06% on the PEMS07 dataset. Additionally, two real-world case studies further substantiate the robustness and interpretability of LOGO.

Comparative Study of Time Series Analysis Algorithms Suitable for Short-Term Forecasting in Implementing Demand Response Based on AMI

This paper compares four time series forecasting algorithms—ARIMA, SARIMA, LSTM, and SVM—suitable for short-term load forecasting using Advanced Metering Infrastructure (AMI) data. The primary focus is on evaluating the applicability and performance of these forecasting models in predicting electricity consumption patterns, which is a critical component for implementing effective demand response (DR) strategies. The study provides a comprehensive analysis of the predictive accuracy, computational efficiency, and scalability of each algorithm using a dataset of real-time electricity consumption collected from AMI systems over a designated period. Through extensive experiments, we demonstrate that each algorithm has distinct strengths and weaknesses depending on the characteristics of the dataset. Specifically, SVM exhibited superior performance in handling nonlinear patterns and high volatility, while SARIMA effectively captured seasonal trends. LSTM showed potential in modeling complex temporal dependencies but was sensitive to hyperparameter settings and required a substantial amount of training data. This research offers practical guidelines for selecting the optimal forecasting model based on data characteristics and application needs, contributing to the development of more efficient and dynamic energy management strategies. The findings highlight the importance of integrating advanced forecasting techniques into smart grid systems to enhance the reliability and responsiveness of DR programs. This study lays a solid foundation for future research on integrating these forecasting models into real-world AMI applications to support effective demand response and grid stability.

Crowd Flow Prediction: An Integrated Approach Using Dynamic Spatial–Temporal Adaptive Modeling for Pattern Flow Relationships

ABSTRACTPredicting crowd flows in smart cities poses a significant challenge for the intelligent transportation system (ITS). Traffic management and behavioral analysis are crucial and have garnered considerable attention from researchers. However, accurately and timely predicting crowd flow is difficult due to various complex factors, including dependencies on recent crowd flow and neighboring regions. Existing studies often focus on spatial–temporal dependencies but neglect to model the relationship between crowd flow in distant areas. In our study, we observe that the daily flow of each region remains relatively consistent, and certain regions, despite being far apart, exhibit similar flow patterns, indicating a strong correlation between them. In this paper, we proposed a novel Multiscale Adaptive Graph‐Gated Network (MSAGGN) model. The main components of MSAGGN can be divided into three major parts: (1) To capture the parallel periodic learning architecture through a layer‐wise gated mechanism, a layer‐wise functional approach is employed to modify gated mechanism, establishing parallel skip periodic connections to effectively manage temporal and external factor information at each time interval; (2) a graph convolutional‐based adaptive mechanism that effectively captures crowd flow traffic data by considering dynamic spatial–temporal correlations; and (3) we proposed a novel intelligent channel encoder (ICE). The task of this block is to capture citywide spatial–temporal correlation along external factors to preserve correlation for distant regions with external elements. To integrate spatio‐temporal flexibility, we introduce the adaptive transformation module. We assessed our model's performance by comparing it with previous state‐of‐the‐art models and conducting experiments using two real‐world datasets for evaluation.

Audio-visual event localization with dual temporal-aware scene understanding and image-text knowledge bridging

Audio-visual event localization (AVEL) task aims to judge and classify an audible and visible event. Existing methods devote to this goal by transferring pre-trained knowledge as well as understanding temporal dependencies and cross-modal correlations of the audio-visual scene. However, most works comprehend the audio-visual scene from an entangled temporal-aware perspective, ignoring the learning of temporal dependency and cross-modal correlation in both forward and backward temporal-aware views. Recently, transferring the pre-trained knowledge from Contrastive Language-Image Pre-training model (CLIP) has shown remarkable results across various tasks. Nevertheless, since audio-visual knowledge of the AVEL task and image-text alignment knowledge of the CLIP exist heterogeneous gap, how to transfer the image-text alignment knowledge of CLIP into AVEL field has barely been investigated. To address these challenges, a novel Dual Temporal-aware scene understanding and image-text Knowledge Bridging (DTKB) model is proposed in this paper. DTKB consists of forward and backward temporal-aware scene understanding streams, in which temporal dependencies and cross-modal correlations are explicitly captured from dual temporal-aware perspectives. Consequently, DTKB can achieve fine-grained scene understanding for event localization. Additionally, a knowledge bridging (KB) module is proposed to simultaneously transfer the image-text representation and alignment knowledge of CLIP to AVEL task. This module regulates the ratio between audio-visual fusion features and CLIP’s visual features, thereby bridging the image-text alignment knowledge of CLIP and the audio-visual new knowledge for event category prediction. Besides, the KB module is compatible with previous models. Extensive experimental results demonstrate that DTKB significantly outperforms the state-of-the-arts models.

LSTGCN: Inductive Spatial Temporal Imputation Using Long Short-Term Dependencies

Spatial temporal forecasting of urban sensors is essentially important for many urban systems, such as intelligent transportation and smart cities. However, due to the problem of hardware failure or network failure, there are some missing values or missing monitoring sensors that need to be interpolated. Recent research on deep learning has made substantial progress on imputation problem, especially temporal aspect (i.e., time series imputation), while little attention has been paid to spatial aspect (both dynamic and static) and long-term temporal dependencies. In this article, we proposed a spatial temporal imputation model, named Long Short-Term Graph Convolution Networks (LSTGCN), which includes gated temporal extraction (GTE) module, multi-head attention-based temporal capture (MHAT) module, long-term periodic temporal encoding (LPTE) module, and bidirectional spatial graph convolution (BSGC) module. The GTE adopts a gated mechanism to filter short-term temporal information, while the MHAT utilizes position encoding to enhance the difference of each timestamps, then use multi-head attention to capture short-term temporal dependency. The BSGC is adopted to handle with spatial relationships between sensor nodes. And we design a periodic encoding technique to process long-term temporal dependencies. The BSGC handles spatial relationships between sensor nodes, and a periodic encoding technique is used to process long-term temporal dependencies. Our experimental analysis includes completion and forecasting tasks, as well as transfer and ablation analyses. The results show that our proposed model outperforms state-of-the-art baselines on real-world datasets.

Research on prediction and evaluation algorithm of sports athletes performance based on neural network.

The Ultimate Fighting Championship (UFC) stands as a prominent global platform for professional mixed martial arts, captivating audiences worldwide. With its continuous growth and globalization efforts, UFC events have garnered significant attention and achieved commendable results. However, as the scale of development expands, the operational demands on UFC events intensify. At its core, UFC thrives on the exceptional performances of its athletes, which serve as the primary allure for audiences. This study aims to enhance the allure of UFC matches and cultivate exceptional athletes by predicting athlete performance on the field. To achieve this, a recurrent neural network prediction model based on Bidirectional Long Short-Term Memory (BiLSTM) is proposed. The model seeks to leverage athlete portraits and characteristics for performance prediction. The proposed methodology involves constructing athlete portraits and analyzing athlete characteristics to develop the prediction model. The BiLSTM-based recurrent neural network is utilized for its ability to capture temporal dependencies in sequential data. The model's performance is assessed through experimental analysis. Experimental results demonstrate that the athlete performance prediction model achieved an overall accuracy of 0.7524. Comparative analysis reveals that the proposed BiLSTM model outperforms traditional methods such as Linear Regression and Multilayer Perceptron (MLP), showcasing superior prediction accuracy. This study introduces a novel approach to predicting athlete performance in UFC matches using a BiLSTM-based recurrent neural network. By leveraging athlete portraits and characteristics, the proposed model offers improved accuracy compared to classical methods. Enhancing the predictive capabilities in UFC not only enriches the viewing experience but also contributes to the development of exceptional athletes in the sport.

Classification of hand movements from EEG using a FusionNet based LSTM network.


Accurate classification of electroencephalogram (EEG) signals is crucial for advancing brain-computer interface (BCI) technology. However, current methods face significant challenges in classifying hand movement EEG signals, including effective spatial feature extraction, capturing temporal dependencies, and representing underlying signal dynamics.
Approach.
This paper introduces a novel multi-model fusion approach, FusionNet-LSTM, designed to address these issues. Specifically, it integrates Convolutional Neural Networks (CNN) for spatial feature extraction, Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) networks for capturing temporal dependencies, and Autoregressive (AR) models for representing signal dynamics.
Main results.
Compared to single models and state-of-the-art methods, this fusion approach demonstrates substantial improvements in classification accuracy. Experimental results show that the proposed model achieves an accuracy of 87.1% in cross-subject data classification and 99.1% in within-subject data classification. Additionally, Gradient Boosting Trees were employed to evaluate the significance of various EEG features to the model.
Significance.
This study highlights the advantages of integrating multiple models and introduces a superior classification model, which is pivotal for the advancement of BCI systems.

Boosting Financial Market Prediction Accuracy With Deep Learning and Big Data

The accuracy of financial market trend prediction directly impacts investors' decisions and financial institutions' risk management, making it a focal point of research in the financial domain. While traditional statistical methods lay the foundation for market forecasting, they still face limitations in handling complex, nonlinear, and non-stationary financial time series data with accuracy and adaptability. Time series analysis plays a pivotal role in financial market prediction, revealing historical patterns and future trends within the data. Addressing the limitations of existing methods, this study proposes a deep learning-based CEEMDAN-CNN-LSTM model. Leveraging the CEEMDAN decomposition method to capture the multi-frequency components of time series, CNN extracts spatial features, and LSTM learns temporal dependencies. Experimental results demonstrate that the performance of the CEEMDAN-CNN-LSTM model surpasses traditional models on standardized evaluation metrics such as RMSE, MAE, and MAPE across four major financial datasets.