Search Results (16)

Conventional vision-based sensors face limitations such as low update rates, restricted applicability, and insufficient robustness in dynamic environments with complex object motions. Single-pixel tracking systems offer high efficiency and minimal data redundancy by directly acquiring target positions without full-image reconstruction. This paper proposes a single-pixel detection system for adaptive multi-target tracking based on the geometric moment and the exponentially weighted moving average (EWMA). The proposed system leverages geometric moments for high-speed target localization, requiring merely $\mathit{3}\mathit{N}$ measurements to resolve centroids for $\mathit{N}$ targets. Furthermore, the output values of the system are used to continuously update the weight parameters, enabling adaptation to varying motion patterns and ensuring consistent tracking stability. Experimental validation using a digital micromirror device (DMD) operating at 17.857 kHz demonstrates a theoretical tracking update rate of 1984 Hz for three objects. Quantitative evaluations under 1920 × 1080 pixel resolution reveal a normalized root mean square error (NRMSE) of 0.00785, confirming the method’s capability for robust multi-target tracking in practical applications. Full article

A new statistical control chart denoted as CHEWMA (Cultural Heritage EWMA) is proposed for microclimate monitoring in preventive conservation. This tool is a real-time detection method inspired by the EN 15757:2010 standard, serving as an alternative to its common adaptations. The proposed control chart is intended to detect short-term fluctuations (STFs) in temperature (T) and relative humidity (RH), which would enable timely interventions to mitigate the risk of mechanical damage to collections. The CHEWMA chart integrates the Exponentially Weighted Moving Average (EWMA) control chart with a weighting mechanism that prioritizes fluctuations occurring near extreme values. The methodology was validated using RH time series recorded by seven dataloggers installed at the Alava Fine Arts Museum, and, from these, seventy simulated time series were generated to enhance the robustness of the analyses. Sensitivity analyses demonstrated that, for the studied dataset, the CHEWMA chart exhibits stronger similarity to the application of EN 15757:2010 than other commonly used real-time STF detection methods in the literature. Furthermore, it provides a flexible option for real-time applications, enabling adaptation to specific conservation needs while remaining aligned with the general framework established by the standard. To the best of our knowledge, this is the first statistical process control chart designed for the field of preventive conservation of cultural heritage. Beyond assessing CHEWMA’s performance, this study reveals that, when adapting the procedures of the European norm by developing a new real-time approach based on a simple moving average (herein termed SMA-FT), a window of approximately 14 days is more appropriate for STF detection than the commonly assumed 30-day period in the literature. Full article

High-quality processes, characterized by low defect rates, typically exhibit an exponential distribution for time-between-events (TBE) data. To effectively monitor TBE data, one-sided exponential Adaptive Exponentially Weighted Moving Average (AEWMA) schemes are introduced. However, the run length (RL) distribution varies with the magnitude of the process mean shift, rendering the median run length (MRL) a more pertinent performance metric. This paper investigates the RL properties of one-sided exponential AEWMA schemes using a Markov chain method. An optimal design procedure based on MRL is developed to enhance the one-sided exponential AEWMA scheme. Comparative analyses reveal that the one-sided exponential AEWMA scheme provides better balanced protection against both minor and major shifts in the process mean compared to EWMA-type and Shewhart schemes. Finally, two practical case studies illustrate the application of AEWMA schemes in manufacturing. Full article

The inevitability of faults arises due to prolonged exposure of photovoltaic (PV) power plants to intricate environmental conditions. Therefore, fault diagnosis of PV power plants is crucial to ensure the continuity and reliability of power generation. This paper proposes a fault diagnosis method that integrates PV power prediction and an exponentially weighted moving average (EWMA) control chart. This method predicts the PV power based on meteorological factors using the adaptive particle swarm algorithm-back propagation neural network (APSO-BPNN) model and takes its error from the actual value as a control quantity for the EWMA control chart. The EWMA control chart then monitors the error values to identify fault types. Finally, it is verified by comparison with the discrete rate (DR) analysis method. The results showed that the coefficient of determination of the prediction model of the proposed method reached 0.98. Although the DR analysis can evaluate the overall performance of the inverter and identify the faults, it often fails to point out the specific location of the faults accurately. In contrast, the EWMA control chart can monitor abnormal states such as open and short circuits and accurately locate the string where the fault occurs. Full article

The imminent depletion of oil resources and increasing environmental pollution have driven the use of clean energy, particularly wind energy. However, wind turbines (WTs) face significant challenges, such as critical component failures, which can cause unexpected shutdowns and affect energy production. To address this challenge, we analyzed the Supervisory Control and Data Acquisition (SCADA) data to identify significant differences between the relationship of variables based on data reconstruction errors between actual and predicted values. This study proposes a hybrid short- and long-term memory autoencoder model with multihead self-attention (LSTM-MA-AE) for WT converter fault detection. The proposed model identifies anomalies in the data by comparing the reconstruction errors of the variables involved. However, more is needed. To address this model limitation, we developed a fault prediction system that employs an adaptive threshold with an Exponentially Weighted Moving Average (EWMA) and a fixed threshold. This system analyzes the anomalies of several variables and generates fault warnings in advance time. Thus, we propose an outlier detection method through data preprocessing and unsupervised learning, using SCADA data collected from a wind farm located in complex terrain, including real faults in the converter. The LSTM-MA-AE is shown to be able to predict the converter failure 3.3 months in advance, and with an F1 greater than 90% in the tests performed. The results provide evidence of the potential of the proposed model to improve converter fault diagnosis with SCADA data in complex environments, highlighting its ability to increase the reliability and efficiency of WTs. Full article

Timely and effective maintenance is imperative to minimize operational disruptions and ensure the reliability of marine vessels. However, given the low early warning rates and poor adaptability under complex conditions of previous data-driven fault prediction methods, this paper presents a hybrid deep learning model based on multi-layer attention mechanisms for predicting faults in a marine diesel engine. Specifically, this hybrid model first introduces a Convolutional Neural Network (CNN) and self-attention to extract local features from multi-feature input sequences. Then, we utilize Long Short-Term Memory (LSTM) and multi-head attention to capture global correlations across time steps. Finally, the hybrid deep learning model is integrated with the Exponential Weighted Moving Average (EWMA) to monitor the operational status and predict potential faults in the marine diesel engine. We conducted extensive evaluations using real datasets under three operating conditions. The experimental results indicate that the proposed method outperforms the current state-of-the-art methods. Moreover, ablation studies and visualizations highlight the importance of fusing multi-layer attention, and the results under various operating conditions and application scenarios demonstrate that this method possesses predictive accuracy and broad applicability. Hence, this approach can provide decision support for condition monitoring and predictive maintenance of marine mechanical systems. Full article

The Value-at-Risk (VaR) metric serves as a pivotal tool for quantifying market risk, offering an estimation of potential investment losses. Predominantly employed within financial sectors, it aids in adhering to regulatory mandates and in devising capital reserve strategies. Nonetheless, the predictive precision of VaR models frequently faces scrutiny, particularly during crises and heightened uncertainty phases. Phenomena like volatility clustering impinge on the accuracy of these models. To mitigate such constraints, conditional volatility models are integrated to augment the robustness and adaptability of VaR approaches. This study critically evaluates the efficacy of GARCH-type VaR models within the transportation sector amidst the Thai stock market’s volatility during the COVID-19 pandemic. The dataset encompasses daily price fluctuations in the Transportation Sector index (TRANS), the Service Industry index (SERVICE), and 17 pertinent stocks within the Stock Exchange of Thailand, spanning from 28 December 2018 to 28 December 2023, thereby encapsulating the pandemic era. The employed GARCH-type VaR models include GARCH (1,1) VaR, ARMA (1,1)—GARCH (1,1) VaR, GARCH (1,1)—M VaR, IGARCH (1,1) VaR, EWMA VaR, and csGARCH (1,1) VaR. These are juxtaposed with more traditional, less computationally intensive models like the Historical Simulation VaR and Delta Normal VaR. The backtesting methodologies encompass Kupiec’s POF test, the Independence Test, and Christoffersen’s Interval Forecast test. Intriguingly, the findings reveal that the Historical Simulation VaR model surpasses GARCH-type VaR models in failure rate accuracy. Within the GARCH-type category, the EWMA VaR model exhibited superior failure rate accuracy. The csGARCH (1,1) VaR and EWMA VaR models emerged as notably robust. These findings bear significant implications for managerial decision-making in financial risk management. Full article

The robot vision model is the basis for the robot to perceive and understand the environment and make correct decisions. However, the security and stability of robot vision models are seriously threatened by adversarial examples. In this study, we propose an adversarial attack algorithm, RMS-FGSM, for robot vision models based on root-mean-square propagation (RMSProp). RMS-FGSM uses an exponentially weighted moving average (EWMA) to reduce the weight of the historical cumulative squared gradient. Additionally, it can suppress the gradient growth based on an adaptive learning rate. By integrating with the RMSProp, RMS-FGSM is more likely to generate optimal adversarial examples, and a high attack success rate can be achieved. Experiments on two datasets (MNIST and CIFAR-100) and several models (LeNet, Alexnet, and Resnet-101) show that the attack success rate of RMS-FGSM is higher than the state-of-the-art methods. Above all, our generated adversarial examples have a smaller perturbation than those generated by existing methods under the same attack success rate. Full article

Survey sampling commonly faces the challenge of missing information, prompting the development of various imputation-based mean estimation methods to address this concern. Among these, ratio-type regression estimators have been devised to compute population parameters using only current sample data. However, recent pioneering research has revolutionized this approach by integrating both past and current sample information through the application of exponentially weighted moving averages (EWMA). This groundbreaking methodology has given rise to the creation of memory-type estimators tailored for surveys conducted over time. In this paper, we present novel imputation-based memory-type mean estimators that leverage EWMA and quantile regression to handle missing observations. For the performance assessment between traditional, adapted and proposed estimators, real-life time-scaled datasets related to the stock market and humidity are considered. Furthermore, we conduct a simulation study using an asymmetric dataset to further validate the effectiveness of the introduced estimators. The humidity data results show that the proposed estimators ($T_{p_{q_{\left(0.25\right)}}}$, $T_{p_{q_{\left(0.45\right)}}}$, $T_{p_{q_{\left(0.25\right)}}}^{{}^{\prime }}$, $T_{p_{q_{\left(0.45\right)}}}^{{}^{\prime }}$, $T_{p_{q_{\left(0.25\right)}}}^{{}^{″}}$, $T_{p_{q_{\left(0.45\right)}}}^{{}^{″}}$) have the minimum MSE. The stock market data results show that the proposed estimators ($T_{p_{q_{\left(0.85\right)}}}$, $T_{p_{q_{\left(0.85\right)}}}^{{}^{\prime }}$, $T_{p_{q_{\left(0.85\right)}}}^{{}^{″}}$) also have the minimum MSE. Additionally, the simulation results demonstrate that the proposed estimators ($T_{p_{q_{\left(0.45\right)}}}$, $T_{p_{q_{\left(0.45\right)}}}^{{}^{\prime }}$, $T_{p_{q_{\left(0.45\right)}}}^{{}^{″}}$) have the minimum MSE when compared to traditional and adapted estimators. Therefore, in conclusion, the use of the proposed estimators is recommended over traditional and adapted ones. Full article

Exponentially weighted moving average (EWMA) and Shewhart control charts are commonly utilized to detect the small to moderate and large shifts in the process mean, respectively. This article introduces a novel Bayesian AEWMA control chart that employs various loss functions (LFs), including square error loss function (SELF) and LINEX loss function (LLF). The control chart incorporates an informative prior for posterior and posterior predictive distributions. Additionally, the control chart utilizes various paired ranked set sampling (PRSS) schemes to improve its accuracy and effectiveness. The average run length (ARL) and standard deviation of run length (SDRL) are used to evaluate the performance of the suggested control chart. Monte Carlo simulations are conducted to compare the performance of the proposed approach to other control charts. The results show that the proposed method outperforms in identifying out-of-control signals, particularly under PRSS schemes compared to simple random sampling (SRS). The proposed CCs effectiveness was validated using a real-life semiconductor manufacturing application, utilizing different PRSS schemes. The performance of the Bayesian AEWMA CC was evaluated, demonstrating its superiority in detecting out-of-control signs compared to existing CCs. This study introduces an innovative method incorporating various LFs and PRSS schemes, providing an enhanced and efficient approach for identifying shifts in the process mean. Full article

Gearbox fault deterioration can significantly impact the safety, reliability, and efficiency of wind turbines, resulting in substantial economic losses for wind farms. However, current condition monitoring methods face challenges in effectively mining the hidden spatio-temporal features within SCADA data and establishing reasonable weight allocations for model input variables. To tackle these issues, we proposed a novel condition monitoring method for wind turbine gearboxes called HBCE, which integrated a feature-time hybrid attention mechanism (HA), the bidirectional convolutional long short-term memory networks (BiConvLSTM), and an improved exponentially weighted moving-average (iEWMA). Specifically, utilizing historical health SCADA data acquired through the modified Thompson tau data-cleaning algorithm, a normal behavior model (HA-BiConvLSTM) of gearbox was constructed to effectively extract the spatio-temporal features and learn normal behavior patterns. An iEWMA-based outlier detection approach was employed to set dynamic adaptive thresholds, and real-time monitor the prediction residuals of HA-BiConvLSTM to identify the early faults of gearbox. The proposed HBCE method was validated through actual gearbox faults and compared with conventional spatio-temporal models (i.e., CNN-LSTM and CNN&LSTM). The results illustrated that the constructed HA-BiConvLSTM model achieved superior prediction precision in terms of RMSE, MAE, MAPE, and R², and the proposed method HBCE can effectively and reliably identify early anomalies of a wind turbine gearbox in advance. Full article

Nowadays, deep learning (DL)-based video surveillance services are widely used in smart cities because of their ability to accurately identify and track objects, such as vehicles and pedestrians, in real time. This allows a more efficient traffic management and improved public safety. However, DL-based video surveillance services that require object movement and motion tracking (e.g., for detecting abnormal object behaviors) can consume a substantial amount of computing and memory capacity, such as (i) GPU computing resources for model inference and (ii) GPU memory resources for model loading. This paper presents a novel cognitive video surveillance management with long short-term memory (LSTM) model, denoted as the CogVSM framework. We consider DL-based video surveillance services in a hierarchical edge computing system. The proposed CogVSM forecasts object appearance patterns and smooths out the forecast results needed for an adaptive model release. Here, we aim to reduce standby GPU memory by model release while avoiding unnecessary model reloads for a sudden object appearance. CogVSM hinges on an LSTM-based deep learning architecture explicitly designed for future object appearance pattern prediction by training previous time-series patterns to achieve these objectives. By referring to the result of the LSTM-based prediction, the proposed framework controls the threshold time value in a dynamic manner by using an exponential weighted moving average (EWMA) technique. Comparative evaluations on both simulated and real-world measurement data on the commercial edge devices prove that the LSTM-based model in the CogVSM can achieve a high predictive accuracy, i.e., a root-mean-square error metric of 0.795. In addition, the suggested framework utilizes up to 32.1% less GPU memory than the baseline and 8.9% less than previous work. Full article

The presence of asymmetric data in production processes or service operations has prompted the development of new monitoring schemes. In this article, an adapted version of the exponentially weighted moving averages (EWMA) control chart with dynamic limits is proposed to monitor the mean of samples from the skew-normal distribution. The detection ability of the proposed control chart in online monitoring was investigated by simulating the average run length (ARL) performance for different out-of-control scenarios. The results of the simulation study suggest that the proposed scheme overcomes the main drawback of the recently developed Shewhart-type control scheme. As shown in this article, the existing Shewhart-type procedure exhibits the undesirable property of taking longer to detect changes in the mean value of skewed normal observations due to increases in the shape parameter of the basic distribution than in stable conditions. The proposed control chart was shown to work fairly acceptably in all considered out-of-control scenarios. Full article

The special causes of variations, which is also known as a shift, can occur in a single or more than one related process characteristics. Statistical process control tools such as control charts are useful to monitor shifts in the process parameters (location and/or dispersion). In real-life situation, the shift is emerging in different sizes, and it is hard to identify it with classical control charts. Moreover, more than one process of characteristics required special attention because they must monitor jointly due to the association among them. This study offers two adaptive control charts to monitor the different sizes of a shift in the process mean vector. The novelty behind this study is to use dimensionally reduction techniques such as principal component analysis (PCA) and an adaptive method such as Huber and Bi-square functions. In brief, the multivariate cumulative sum control chart based on PCA is designed, and its plotting statistic is utilized as an input in the classical exponentially weighted moving average (EWMA) control chart. The run length (RL) properties of the proposed and other control charts are obtained by designing algorithms in MATLAB through a Monte Carlo simulation. For a single shift, the performance of the control charts is assessed through an average of RL, standard deviation of RL, and standard error of RL. Likewise, overall performance measures such as extra quadratic loss, relative ARL, and the performance comparison index are also used. The comparison reveals the superiority over other control charts. Furthermore, to emphasize the application process and benefits of the proposed control charts, a real-life example of the wind turbine process is included. Full article

Key performance indicator (KPI) anomaly detection is the underlying core technology in Artificial Intelligence for IT operations (AIOps). It has an important impact on subsequent anomaly location and root cause analysis. Variational auto-encoder (VAE) is a symmetry network structure composed of encoder and decoder, which has attracted extensive attention because of its ability to capture complex KPI data features and better detection results. However, VAE is not well applied to the modeling of KPI time series data and it is often necessary to set the threshold to obtain more accurate results. In response to these problems, this paper proposes a novel hybrid method for KPI anomaly detection based on VAE and support vector data description (SVDD). This method consists of two modules: a VAE reconstructor and SVDD anomaly detector. In the VAE reconstruction module, firstly, bi-directional long short-term memory (BiLSTM) is used to replace the traditional feedforward neural network in VAE to capture the time correlation of sequences; then, batch normalization is used at the output of the encoder to prevent the disappearance of KL (Kullback–Leibler) divergence, which prevents ignoring latent variables to reconstruct data directly. Finally, exponentially weighted moving average (EWMA) is used to smooth the reconstruction error, which reduces false positives and false negatives during the detection process. In the SVDD anomaly detection module, smoothed reconstruction errors are introduced into the SVDD for training to determine the threshold of adaptively anomaly detection. Experimental results on the public dataset show that this method has a better detection effect than baseline methods. Full article