Class Of Time Series Models Research Articles

Multi-Task Diffusion Learning for Time Series Classification

Current deep learning models for time series often face challenges with generalizability in scenarios characterized by limited samples or inadequately labeled data. By tapping into the robust generative capabilities of diffusion models, which have shown success in computer vision and natural language processing, we see potential for improving the adaptability of deep learning models. However, the specific application of diffusion models in generating samples for time series classification tasks remains underexplored. To bridge this gap, we introduce the MDGPS model, which incorporates multi-task diffusion learning and gradient-free patch search (MDGPS). Our methodology aims to bolster the generalizability of time series classification models confronted with restricted labeled samples. The multi-task diffusion learning module integrates frequency-domain classification with random masked patches diffusion learning, leveraging frequency-domain feature representations and patch observation distributions to improve the discriminative properties of generated samples. Furthermore, a gradient-free patch search module, utilizing the particle swarm optimization algorithm, refines time series for specific samples through a pre-trained multi-task diffusion model. This process aims to reduce classification errors caused by random patch masking. The experimental results on four time series datasets show that the proposed MDGPS model consistently surpasses other methods, achieving the highest classification accuracy and F1-score across all datasets: 95.81%, 87.64%, 82.31%, and 100% in accuracy; and 95.21%, 82.32%, 78.57%, and 100% in F1-Score for Epilepsy, FD-B, Gesture, and EMG, respectively. In addition, evaluations in a reinforcement learning scenario confirm MDGPS’s superior performance. Ablation and visualization experiments further validate the effectiveness of its individual components.

Extraction of Features for Time Series Classification Using Noise Injection

Time series data often display complex, time-varying patterns, which pose significant challenges for effective classification due to data variability, noise, and imbalance. Traditional time series classification techniques frequently fall short in addressing these issues, leading to reduced generalization performance. Therefore, there is a need for innovative methodologies to enhance data diversity and quality. In this paper, we introduce a method for the extraction of features for time series classification using noise injection to address these challenges. By employing noise injection techniques for data augmentation, we enhance the diversity of the training data. Utilizing digital signal processing (DSP), we extract key frequency features from time series data through sampling, quantization, and Fourier transformation. This process enhances the quality of the training data, thereby maximizing the model’s generalization performance. We demonstrate the superiority of our proposed method by comparing it with existing time series classification models. Additionally, we validate the effectiveness of our approach through various experimental results, confirming that data augmentation and DSP techniques are potent tools in time series data classification. Ultimately, this research presents a robust methodology for time series data analysis and classification, with potential applications across a broad spectrum of data analysis problems.

Economical hybrid novelty detection leveraging global aleatoric semantic uncertainty for enhanced MRI-based ACL tear diagnosis

This study presents an innovative hybrid deep learning (DL) framework that reformulates the sagittal MRI-based anterior cruciate ligament (ACL) tear classification task as a novelty detection problem to tackle class imbalance. We introduce a highly discriminative novelty score, which leverages the aleatoric semantic uncertainty as this is modeled in the class scores outputted by the YOLOv5-nano object detection (OD) model. To account for tissue continuity, we propose using the global scores (probability vector) when the model is applied to the entire sagittal sequence. The second module of the proposed pipeline constitutes the MINIROCKET timeseries classification model for determining whether a knee has an ACL tear. To better evaluate the generalization capabilities of our approach, we also carry out cross-database testing involving two public databases (KneeMRI and MRNet) and a validation-only database from University General Hospital of Larissa, Greece. Our method consistently outperformed (p-value<0.05) the state-of-the-art (SOTA) approaches on the KneeMRI dataset and achieved better accuracy and sensitivity on the MRNet dataset. It also generalized remarkably good, especially when the model had been trained on KneeMRI. The presented framework generated at least 2.1 times less carbon emissions and consumed at least 2.6 times less energy, when compared with SOTA. The integration of aleatoric semantic uncertainty-based scores into a novelty detection framework, when combined with the use of lightweight OD and timeseries classification models, have the potential to revolutionize the MRI-based injury detection by setting a new precedent in diagnostic precision, speed and environmental sustainability. Our resource-efficient framework offers potential for widespread application.

Abnormal pattern recognition for online inspection in manufacturing process based on multi-scale time series classification

The collection of large volumes of temporal data during the production process is streamlined in a cyber manufacturing environment. The ineluctable abnormal patterns in these time series often serve as indicators of potential manufacturing faults. Consequently, the presence of effective analytical methods becomes essential for monitoring and recognizing these abnormal manufacturing patterns. However, the extensive process data may contain various minor abnormal patterns, typically reflecting changes in production status influenced by multiple anomalous causes. This study introduces an approach for recognizing abnormal manufacturing patterns through multi-scale time series classification (TSC). Long-term process signals undergo slicing using dynamically sized observation windows and subsequent classification at multiple scales employing our proposed TSC model, the distance mode profile-multi-branch dilated convolution network (DMP-MDNet). DMP-MDNet comprises two key modules aimed at bypassing complicated feature engineering and enhancing generalization capability. The first module, DMP, uses similarity measurement to encode scale- and magnitude-invariant temporal properties. Subsequently, the MDNet, equipped with multi-receptive field sizes, effectively leverages multi-granularity data for accurate classification. The effectiveness of our method is demonstrated through the analysis of a real-world body-in-white production dataset and various widely used public TSC datasets, showing promising applicability in actual manufacturing processes.

Discord-based counterfactual explanations for time series classification

The opacity inherent in machine learning models presents a significant hindrance to their widespread incorporation into decision-making processes. To address this challenge and foster trust among stakeholders while ensuring decision fairness, the data mining community has been actively advancing the explainable artificial intelligence paradigm. This paper contributes to the evolving field by focusing on counterfactual generation for time series classification models, a domain where research is relatively scarce. We develop, a post-hoc, model agnostic counterfactual explanation algorithm that leverages the Matrix Profile to map time series discords to their nearest neighbors in a target sequence and use this mapping to generate new counterfactual instances. To our knowledge, this is the first effort towards the use of time series discords for counterfactual explanations. We evaluate our algorithm on the University of California Riverside and University of East Anglia archives and compare it to three state-of-the-art univariate and multivariate methods.

POCKET: Pruning random convolution kernels for time series classification from a feature selection perspective

In recent years, two competitive time series classification models, namely, ROCKET and MINIROCKET, have garnered considerable attention due to their low training cost and high accuracy. However, they rely on a large number of random 1-D convolutional kernels to comprehensively capture features, which is incompatible with resource-constrained devices. Despite the development of heuristic algorithms designed to recognize and prune redundant kernels, the inherent time-consuming nature of evolutionary algorithms hinders efficient evaluation. To efficiently prune models, this paper eliminates feature groups contributing minimally to the classifier, thereby discarding the associated random kernels without direct evaluation. To this end, we incorporate both group-level (l2,1-norm) and element-level (l2-norm) regularizations to the classifier, formulating the pruning challenge as a group elastic net classification problem. An ADMM-based algorithm is initially introduced to solve the problem, but it is computationally intensive. Building on the ADMM-based algorithm, we then propose our core algorithm, POCKET, which significantly speeds up the process by dividing the task into two sequential stages. In Stage 1, POCKET utilizes dynamically varying penalties to efficiently achieve group sparsity within the classifier, removing features associated with zero weights and their corresponding kernels. In Stage 2, the remaining kernels and features are used to refit a l2-regularized classifier for enhanced performance. Experimental results on diverse time series datasets show that POCKET prunes up to 60% of kernels without a significant reduction in accuracy and performs 11× faster than its counterparts. Our code is publicly available at https://github.com/ShaowuChen/POCKET.

Anomaly detection in wind turbine blades based on PCA and convolutional kernel transform models: employing multivariate SCADA time series analysis

With the widespread application of wind power technology, the detection of abnormalities in wind turbine blades has become a key research area. The use of data from monitoring and data acquisition (SCADA) systems for data-driven fault detection research presents new challenges. This study utilizes short-term SCADA data from wind turbine generators to classify the blade abnormal and normal operational states, thereby introducing a new method called PCABSMMR. This strategy integrates principal component analysis (PCA) and borderline-synthetic minority over-sampling technique (Borderline-SMOTE) for data processing and utilizes an improved multi-dimensional time series classification (MTSC) model. It combines one-dimensional convolution from deep learning with shallow learning’s rigid classifiers. PCA is used for dimensionality reduction, while Borderline-SMOTE expands the samples of minority class fault instances. Comparative analysis with various methods shows that the proposed method has an average F1-score of 0.98, outperforming many state-of-the-art MTSC models across various evaluation metrics.

BITCOIN PRICE PREDICTION BY USING ARIMA

Cryptocurrency markets have emerged as a dynamic and intriguing domain, with Bitcoin at the forefront, captivating the attention of investors, researchers, and enthusiasts alike. The volatile nature of Bitcoin prices presents both opportunities and challenges for market participants seeking to understand and anticipate its movements. In this study, we delve into the realm of time series analysis to explore the feasibility of predicting The research journey begins with meticulous data preprocessing steps to ensure the quality and integrity of the input data. Leveraging Python libraries such as pandas and NumPy, we cleanse and format the historical Bitcoin price data, laying the foundation for subsequent analysis. Key preprocessing tasks include handling missing values, normalization, and addressing any anomalies or outliers that may distort the underlying patterns. With the data prepared, our attention turns to assessing the stationarity of the Bitcoin price time series—a fundamental prerequisite for applying classical time series models. Through visual inspection and statistical tests such as the Augmented Dickey-Fuller (ADF) test, we ascertain the presence of trends or seasonality that could influence the modelling process. To mitigate such effects, we employ techniques such as differencing and transformations, including the Box-Cox transformation, to stabilize the variance of the data. Armed with a stationary time series, we embark on the core of our analysis: modelling Bitcoin prices using Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX) models. These models, renowned for their versatility and effectiveness in capturing temporal dependencies, offer a sophisticated framework for forecasting time series data. Guided by the principles of parsimony and model selection criteria such as the Akaike Information Criterion (AIC), we systematically explore the parameter space to identify the optimal specifications for our models. The efficacy of the chosen models is rigorously evaluated through diagnostic checks, encompassing residual analysis, model fit statistics, and out-of-sample validation. Insights gleaned from these assessments inform our confidence in the models' predictive capabilities and guide our interpretation of the forecasted outcomes. Finally, armed with a validated model, we turn our gaze to the future, employing it to generate forecasts of Bitcoin prices for forthcoming periods. Visualizations juxtaposing predicted prices against observed values provide a compelling narrative of the model's performance and offer stakeholders valuable insights into potential market trends and dynamics. In summary, this research contributes to the burgeoning field of cryptocurrency analytics by showcasing the application of time-tested statistical methodologies to forecast Bitcoin prices. By leveraging the power of ARIMA and SARIMAX models, we illuminate the intricate patterns underlying Bitcoin's price dynamics, empowering market participants with actionable intelligence for informed decision-making in an ever-evolving landscape. Keywords Cryptocurrency Markets, Bitcoin Price Prediction, Time Series Analysis, Python Programming, Data Preprocessing, Pandas, NumPy, Stationarity Testing, Augmented Dickey-Fuller (ADF) Test, Box-Cox Transformation, ARIMA Model, SARIMAX Model, Model Selection, Akaike Information Criterion (AIC), Diagnostic Checks, Residual Analysis, Out-of-Sample Validation, Forecasting, Visualization, Market Trends, Decision-Making, Cryptocurrency Analytics

Local perturbation-based black-box federated learning attack for time series classification

The widespread adoption of intelligent machines and sensors has generated vast amounts of time series data, leading to the increasing use of neural networks in time series classification. Federated learning has emerged as a promising machine learning paradigm that reduces the risk of user privacy leakage. However, federated learning is vulnerable to backdoor attacks, which pose significant security threats. Furthermore, existing unrealistic white-box methods for attacking time series result in insufficient adaptation and inferior stealthiness. To overcome these limitations, this paper proposes a gradient-free black-box method called local perturbation-based backdoor Federated Learning Attack for Time Series classification (FLATS). The attack is formulated as a constrained optimization problem and is solved using a differential evolution algorithm, without requiring any knowledge of the internal architecture of the target model. In addition, the proposed method considers the time series shapelet interval as a local perturbation range and adopts a soft target poisoning approach to minimize the difference between the attacker model and the benign model. Experimental results demonstrate that our proposed method can effectively attack federated learning time series classification models with potential security issues while generating imperceptible poisoned samples that can evade various defence methods.

Innovative framework for effective service parts management in the automotive industry

Effective service parts management and demand forecasting are crucial for optimizing operations in the automotive industry. However, existing literature lacks a comprehensive framework tailored to the specific context of the Thai automotive sector. This study addresses this gap by proposing a strategic approach to service parts management and demand forecasting in the Thai automotive industry. Drawing on a diverse set of methodologies, including classical time series models and advanced machine learning techniques, various forecasting models were assessed to identify the most effective approach for predicting service parts demand. Categorization of service parts based on demand criteria was conducted, and decision rules were developed to guide stocking strategies, balancing the need to minimize service disruptions with cost optimization. This analysis reveals substantial cost savings potential through strategic stocking guided by the developed decision rules. Furthermore, evaluation of the performance of different forecasting models recommends the adoption of Support Vector Regressor (SVR) as the most accurate model for forecasting service parts demand in this context. This research contributes to the automotive service industry by providing a nuanced framework for service parts management and demand forecasting, leading to cost-effective operations and enhanced service quality. The findings offer valuable insights for practitioners and policymakers seeking to improve efficiency and sustainability in the Thai automotive sector.

Machine learning to predict grains futures prices

AbstractAccurate commodity price forecasts are crucial for stakeholders in agricultural supply chains. They support informed marketing decisions, risk management, and investment strategies. Machine learning methods have significant potential to provide accurate forecasts by maximizing out‐of‐sample accuracy. However, their inherent complexity makes it challenging to understand the appropriate data pre‐processing steps to ensure proper functionality. This study compares the forecasting performance of Long Short‐Term Memory Recurrent Neural Networks (LSTM‐RNNs) with classical econometric time series models for corn futures prices. The study considers various combinations of data pre‐processing techniques, variable clusters, and forecast horizons. Our results indicate that LSTM‐RNNs consistently outperform classical methods, particularly for longer forecast horizons. In particular, our findings demonstrate that LSTM‐RNNs are capable of automatically handling structural breaks, resulting in more accurate forecasts when trained on datasets that include such shocks. However, in our setting, LSTM‐RNNs struggle to deal with seasonality and trend components, necessitating specific data pre‐processing procedures for their removal.

Deep Latent Factor Model for Spatio-Temporal Forecasting

Latent factor models can perform spatio-temporal forecasting (i.e., predicting future responses at unmeasured as well as measured locations) by modeling temporal dependence using latent factors and considering spatial dependence using a spatial prior on factor loadings. However, they may fail to capture complex spatio-temporal dependence because the latent factors are typically assumed to follow a classical linear time series model, such as a vector autoregressive model. In this article, we propose a deep latent factor model for spatio-temporal forecasting that can model complex spatio-temporal dependence more flexibly by leveraging the high expressive power of a deep neural network. Specifically, the latent factors are modeled using a recurrent neural network and the factor loadings are modeled using a distance-based Gaussian process. The proposed model allows the number of latent factors to be inferred from the data using a beta-Bernoulli process, which enables computationally more efficient implementation compared to previous methods. We derive a stochastic variational inference algorithm for scalable inference of the proposed model and validate the model using simulated and real data examples.

Comparative Performance Analysis of Deep Learning, Classical, and Hybrid Time Series Models in Ecological Footprint Forecasting

In a globalized world, factors such as increasing population, rising production rates, changing consumption habits, and continuous economic growth contribute significantly to climate change. Therefore, successfully forecasting the Ecological Footprint (EF) effectively indicates global sustainable development. Despite the significant role of the EF as one of the indicators of sustainable development, there is a gap in the literature regarding time series methods and forward-looking predictions. To address this gap, Ecological Footprint (EF) forecasting was performed using deep learning methods such as LSTMs, classical time series methods like ARIMA and Holt–Winters, and the developed hybrid ARIMA-SVR model. In the scope of the study, first, a spreadsheet was created using the total Ecological Footprint (EF) worldwide between 1961 and 2022, obtained from the Global Footprint Network database. Second, the forecasting performances of the ARIMA, Holt–Winters, LSTM, and the hybrid ARIMA-SVR models were compared using MAPE and RMSE metrics. Finally, the forecasting performances of the time series models were statistically validated through Wilcoxon Signed-Rank and Friedman tests. The study findings indicate that the proposed ARIMA (1,1,0) model demonstrated better performance with an average MAPE of 2.12%, compared to Holt–Winters (MAPE of 2.27%), LSTM (MAPE of 3.19%), and ARIMA-SVR (MAPE of 2.68%) methods in the test dataset. Additionally, it was observed that the ARIMA model forecasted the EF, which experienced a sudden decrease due to the COVID-19 lockdown, with a lower error compared to other models. These findings highlight the adaptability of the ARIMA model to variable and uncertain conditions.

Hand Movement Recognition and Salient Tremor Feature Extraction With Wearable Devices in Parkinson’s Patients

Tremor is one of the earliest signs of Parkinson’s disease (PD), which seriously disrupts patients’ daily lives. It is important to study upper limb tremors quantitatively to control PD progression. In this study, surface electromyography (sEMG) signals from wearable devices are used to recognize rest, posture, and kinetic tremor action from 6 upper-limb clinical actions and to quantify features of tremors. A multivariable time series classification model (MTSCM) based on fully convolutional networks and a long short-term memory network is proposed to recognize tremor actions. MTSCM achieves a high degree of accuracy both on the left-hand and right-hand data sets for tremor actions. An improved Hilbert-Huang transform (HHT) method is proposed to decompose the inertial signals of tremor actions to obtain tremor components. Using the improved HHT, tremor and motion components can be decomposed effectively. In addition, 53 features are extracted from inertial and sEMG signals, and a canonical correlation analysis is used to determine the correlation between features and MDS-UPDRS scores. Several of the relevant characteristics are related to MDS-UPDRS scores, notably the dominant frequency and amplitude of the tremor component are significantly correlated (p < 0.01) with tremor scores. Detecting upper-limb clinical tremors in PD patients using wearable sensors is feasible according to our findings.

Dynamic Graph Convolutional Network-Based Prediction of the Urban Grid-Level Taxi Demand–Supply Imbalance Using GPS Trajectories

The objective imbalance between the taxi supply and demand exists in various areas of the city. Accurately predicting this imbalance helps taxi companies with dispatching, thereby increasing their profits and meeting the travel needs of residents. The application of Graph Convolutional Networks (GCNs) in traffic forecasting has inspired the development of a spatial–temporal model for grid-level prediction of the taxi demand–supply imbalance. However, spatial–temporal GCN prediction models conventionally capture only static inter-grid correlation features. This research aims to address the dynamic influences caused by taxi mobility and the variations of other transportation modes on the demand–supply dynamics between grids. To achieve this, we employ taxi trajectory data and develop a model that incorporates dynamic GCN and Gated Recurrent Units (GRUs) to predict grid-level imbalances. This model captures the dynamic inter-grid influences between neighboring grids in the spatial dimension. It also identifies trends and periodic changes in the temporal dimension. The validation of this model, using taxi trajectory data from Shenzhen city, indicates superior performance compared to classical time-series models and spatial–temporal GCN models. An ablation study is conducted to analyze the impact of various factors on the predictive accuracy. This study demonstrates the precision and applicability of the proposed model.

Interpretable synthetic signals for explainable one-class time-series classification

This research paper introduces an innovative approach for explainable one-class time-series classification (XOCTSC). The proposed method involves generating pseudounseen synthetic signals by altering the amplitude and cycle of the original signals. Subsequently, a classification process is performed to distinguish between the original and synthetic signals, and the resulting model is applied to testing data. Instances classified as synthetic classes are treated as unseen classes, and the dissimilarity with the training data can be elucidated through an explanation of the synthetic class creation process. This approach aims to enhance the interpretability of one-class time-series classification models by providing insights into the reasoning behind their decisions. The proposed method is demonstrated with a ballistocardiogram (BCG) signal for the breathing dataset and an electroencephalogram (EEG) signal for the epilepsy dataset. The proposed method recognizes BCG amplitude reduction during breath holding. Moreover, EEG cycle changes during epileptic seizures are observed across multiple channels. These observations align with actual epilepsy symptoms and breathing behaviors.

A global model-agnostic rule-based XAI method based on Parameterized Event Primitives for time series classifiers.

Time series classification is a challenging research area where machine learning and deep learning techniques have shown remarkable performance. However, often, these are seen as black boxes due to their minimal interpretability. On the one hand, there is a plethora of eXplainable AI (XAI) methods designed to elucidate the functioning of models trained on image and tabular data. On the other hand, adapting these methods to explain deep learning-based time series classifiers may not be straightforward due to the temporal nature of time series data. This research proposes a novel global post-hoc explainable method for unearthing the key time steps behind the inferences made by deep learning-based time series classifiers. This novel approach generates a decision tree graph, a specific set of rules, that can be seen as explanations, potentially enhancing interpretability. The methodology involves two major phases: (1) training and evaluating deep-learning-based time series classification models, and (2) extracting parameterized primitive events, such as increasing, decreasing, local max and local min, from each instance of the evaluation set and clustering such events to extract prototypical ones. These prototypical primitive events are then used as input to a decision-tree classifier trained to fit the model predictions of the test set rather than the ground truth data. Experiments were conducted on diverse real-world datasets sourced from the UCR archive, employing metrics such as accuracy, fidelity, robustness, number of nodes, and depth of the extracted rules. The findings indicate that this global post-hoc method can improve the global interpretability of complex time series classification models.

Deep Learning based Time Series Classification Model for Monitoring Land Cover Changes in Tropical High Forests

Deep Learning based Time Series Classification Model for Monitoring Land Cover Changes in Tropical High Forests

The Integration and Development of Ideological and Political Education and Student Management in Universities Based on Data Fusion Models under the Background of Three Comprehensive Education

Abstract Mental health management of college students is a crucial aspect of college student management. To this end, this paper extracts the characteristic sequences of consumption behaviors, including the number of consumption per week, the number of times of use breakfast, the number of times of deviating from the normal time of using breakfast and the number of times fetching water from the daily consumption records of students. Then, the best model MLSTM-FCN is selected from the different existing time series classification models. Aiming at the problem that the FCN branch has a small sensory field and can only run in one direction in the network structure of the MLSTM-FCN two-branch splicing, it is proposed to use a Transformer to replace the FCN branch so as to put forward a Trans-LSTM students’ psychological abnormality early warning model based on the classification of time series. Model. According to the model comparison, the Trans-LSTM fusion model F1 has the highest mean value. The value is 0.8245. Finally, in the psychological intervention based on ideology and politics for students with psychological problems identified by the early warning model, the results show that the individual’s pressure t=8.163, df=6, p&lt;0.001, and the social environment pressure t=9.872, df=6, p&lt;0.001, indicating that the subject’s mental anomalies can be classified based on the time series. 0.001, indicating a significant difference between before and after the intervention for the subjects.

Time series classification models based on nonlinear spiking neural P systems

Reservoir computing (RC) is a novel class of recurrent neural networks (RNN) models. Nonlinear spiking neural P (NSNP) systems are neural-like computing models with nonlinear spiking mechanisms. By introducing NSNP systems as the reservoir, we propose a new RC model for time series classification task, termed TSC-NSNP model. However, due to the high-dimensional nature of the reservoir state space, the TSC-NSNP model, like existing RC models, will encounter some challenges. To address the challenges. we utilize the reservoir model space representation and dimensionality reduction method to propose two improved models, termed TSC-DR-NSNP model and TSC-RMS-NSNP model. The three RC models can be easily realized and learnt in the RC framework. The proposed three RC models are evaluated on 21 benchmark time series classification data sets, and are compared with 20 classification models. The comparisons demonstrate the effectiveness of the presented three RC models for time series classification tasks.