Search Results (2,319)

“Normal” events are characterized as data patterns or behaviors that align with expected operational conditions, while “anomalies” are defined as deviations from these patterns, potentially signaling faults, errors, or unexpected system behaviors. The timely and accurate detection of anomalies plays a critical role in domains such as industrial manufacturing, financial transactions, and other related domains. In the context of Industry 4.0, the proliferation of sensors has resulted in a massive influx of time series data, making the anomaly detection of such multivariate time series data a popular research area. Long Short-Term Memory (LSTM) has been extensively recognized as an effective framework for modeling and processing time series data. Previous studies have combined Bi-directional Long Short-Term Memory (Bi-LSTM) architecture with Autoencoder (AE) for multivariate time series anomaly detection. However, due to the inherent limitations of LSTM, Bi-LSTM-AE still cannot overcome these drawbacks. Our study replaces the LSTM units within the Bi-LSTM-AE architecture of existing research with Working Memory Connections for LSTM units and demonstrates that this architecture performs better in the field of multivariate time series anomaly detection compared to using standard LSTM units. The model we proposed not only outperforms the baseline models but also demonstrates greater robustness across various scenarios. Full article

This paper presents a comparative analysis of selected deep learning methods applied to anomaly detection in data streams. The anomaly detection results obtained on the popular Yahoo! Webscope S5 dataset are used for the computational experiments. The two commonly used and recommended models in the literature, which are the basis for this analysis, are the following: the LSTM and its more complicated variant, the LSTM autoencoder. Additionally, the usefulness of an innovative LSTM-CNN approach is evaluated. The results indicate that the LSTM-CNN approach can successfully be applied for anomaly detection in data streams as its performance compares favorably with that of the two mentioned standard models. For the performance evaluation, the $F_{1score}$ is used. Full article

Face recognition (FR) is a less intrusive biometrics technology with various applications, such as security, surveillance, and access control systems. FR remains challenging, especially when there is only a single image per person as a gallery dataset and when dealing with variations like pose, illumination, and occlusion. Deep learning techniques have shown promising results in recent years using VAE and GAN, with approaches such as patch-VAE, VAE-GAN for 3D Indoor Scene Synthesis, and hybrid VAE-GAN models. However, in Single Sample Per Person Face Recognition (SSPP FR), the challenge of learning robust and discriminative features that preserve the subject’s identity persists. To address these issues, we propose a novel framework called AD-VAE, specifically for SSPP FR, using a combination of variational autoencoder (VAE) and Generative Adversarial Network (GAN) techniques. The proposed AD-VAE framework is designed to learn how to build representative identity-preserving prototypes from both controlled and wild datasets, effectively handling variations like pose, illumination, and occlusion. The method uses four networks: an encoder and decoder similar to VAE, a generator that receives the encoder output plus noise to generate an identity-preserving prototype, and a discriminator that operates as a multi-task network. AD-VAE outperforms all tested state-of-the-art face recognition techniques, demonstrating its robustness. The proposed framework achieves superior results on four controlled benchmark datasets—AR, E-YaleB, CAS-PEAL, and FERET—with recognition rates of 84.9%, 94.6%, 94.5%, and 96.0%, respectively, and achieves remarkable performance on the uncontrolled LFW dataset, with a recognition rate of 99.6%. The AD-VAE framework shows promising potential for future research and real-world applications. Full article

We propose a novel recommendation model for diversifying furniture recommendations and aligning them more closely with user preferences. Our model builds upon the Recommender Variational Autoencoder (RecVAE), known for its effectiveness and ability to overcome overfitting by linking user feedback with user representation. However, since RecVAE relies on implicit feedback data, it tends to exhibit bias towards popular items, potentially creating a recommendation filter bubble. While previous work has proposed user profiles learned from a user’s personal information and the textual data of an item, we propose user profiles generated from the image data on the item given the points of interest when selecting items in e-commerce and the ease of data acquisition. We hypothesize that to capture user preferences and provide tailored furniture recommendations accurately, it is essential to incorporate both reviewed text information and visual data on furniture pieces. To utilize user preferences well, we incorporate the Conditional Variational Autoencoder (CVAE) architecture, where both the encoder and decoder are conditioned on a user profile indicating the user’s preference information. Additionally, the user profile is trained to capture the user’s preference for a specific predefined style. We trained our models using MovieLens-20M and the Amazon Furniture Review Dataset, a new dataset dedicated to furniture recommendations. As a result, on both datasets, our model outperformed previous models, including RecVAE. These findings show the effectiveness of our user profile approach in diversifying and personalizing furniture recommendations. Full article

Steam traps are essential for industrial systems, ensuring steam quality and energy efficiency by removing condensate and preventing steam leakage. However, their failure results in energy loss, operational disruptions, and increased greenhouse gas emissions. This paper proposes a novel predictive maintenance system for steam traps that integrates statistical time series features and transformer encoder–decoder models for fault diagnosis and visualization. The proposed system combines IoT sensor data, operational parameters, open data (e.g., weather information and public holiday calendars), machine learning, and two-dimensional diagnostic projection to improve reliability and interpretability. Experiments were conducted in two industrial plants: an aluminum processing plant and a food manufacturing plant, and the system achieved superior defect detection accuracy and diagnostic reliability compared to existing methods. The transformer-based model outperformed traditional methods, including random forest, gradient boosting, and variational autoencoder, in classification and clustering. The system also demonstrated an average 6.92% reduction in thermal energy across both sites, highlighting its potential to improve energy efficiency and reduce carbon emissions. This research highlights the transformative impact of AI-based predictive maintenance technologies in industrial operations and provides a framework for sustainable manufacturing practices. Full article

This paper investigates the use of machine learning techniques on hyperspectral images of pistachios to detect and classify different levels of aflatoxin contamination. Aflatoxins are toxic compounds produced by moulds, posing health risks to consumers. Current detection methods are invasive and contribute to food waste. This paper explores the feasibility of a non-invasive method using hyperspectral imaging and machine learning to classify aflatoxin levels accurately, potentially reducing waste and enhancing food safety. Hyperspectral imaging with machine learning has shown promise in food quality control. The paper evaluates models including Dimensionality Reduction with K-Means Clustering, Residual Networks (ResNets), Variational Autoencoders (VAEs), and Deep Convolutional Generative Adversarial Networks (DCGANs). Using a dataset from Leeds Beckett University with 300 hyperspectral images, covering three aflatoxin levels (<8 ppn, >160 ppn, and >300 ppn), key wavelengths were identified to indicate contamination presence. Dimensionality Reduction with K-Means achieved 84.38% accuracy, while a ResNet model using the 866.21 nm wavelength reached 96.67%. VAE and DCGAN models, though promising, were constrained by dataset size. The findings highlight the potential for machine learning-based hyperspectral imaging in pistachio quality control, and future research should focus on expanding datasets and refining models for industry application. Full article

To achieve intelligent manufacturing and improve the machining quality of machine tools, this paper proposes an interpretable machining size prediction model combining eXtreme Gradient Boosting (XGBoost), autoencoder (AE), and Shapley additive explanation (SHAP) analysis. In this study, XGBoost was used to establish an evaluation system for the actual machining size of computer numerical control (CNC) machine tools. The XGBoost model was combined with SHAP approximation to effectively capture local and global features in the data using autoencoders and transform the preprocessed data into more representative feature vectors. Grey correlation analysis (GRA) and principal component analysis (PCA) were used to reduce the dimensions of the original data features, and the synthetic minority overstimulation technique of the Gaussian noise regression (SMOGN) method was used to deal with the problem of data imbalance. Taking the actual size of the machine tool as the response parameter, based on the size parameters in the milling process of the CNC machine tool, the effectiveness of the model is verified. The experimental results show that the proposed AE-XGBoost model is superior to the traditional XGBoost method, and the prediction accuracy of the model is 7.11% higher than that of the traditional method. The subsequent SHAP analysis reveals the importance and interrelationship of features and provides a reliable decision support system for machine tool processing personnel, helping to improve processing quality and achieve intelligent manufacturing. Full article

Structural health monitoring (SHM) in fiber-reinforced polymer (FRP) composites is essential to ensure safety and reliability during service, particularly in critical industries such as aerospace and wind energy. Traditional methods of analyzing Acoustic Emission (AE) signals in the time domain often fail to accurately detect subtle or early-stage damage, limiting their effectiveness. The present study introduces a novel approach that integrates frequency-domain analysis using the fast Fourier transform (FFT) with deep learning techniques for more accurate and proactive damage detection. AE signals are first transformed into the frequency domain, where significant frequency components are extracted and used as inputs to an autoencoder network. The autoencoder model reduces the dimensionality of the data while preserving essential features, enabling unsupervised clustering to identify distinct damage states. Temporal damage evolution is modeled using Markov chain analysis to provide insights into how damage progresses over time. The proposed method achieves a reconstruction error of 0.0017 and a high R-squared value of 0.95, indicating the autoencoder’s effectiveness in learning compact representations while minimizing information loss. Clustering results, with a silhouette score of 0.37, demonstrate well-separated clusters that correspond to different damage stages. Markov chain analysis captures the transitions between damage states, providing a predictive framework for assessing damage progression. These findings highlight the potential of the proposed approach for early damage detection and predictive maintenance, which significantly improves the effectiveness of AE-based SHM systems in reducing downtime and extending component lifespan. Full article

This study presents a comparative analysis of three AutoEncoder (AE) models—Variational AutoEncoder (VAE), Sparse AutoEncoder (SAE), and Convolutional AutoEncoder (CAE)—to detect and quantify structural anomalies in railway vehicle wheels, such as polygonization. Vertical acceleration data from a virtual wayside monitoring system serve as input for training the AE models, which are coupled with Hotelling’s T² Control Charts to differentiate normal and abnormal railway component behaviors. The results indicate that the SAE-T² model outperforms its counterparts, achieving 16.67% higher accuracy than the CAE-T² model in identifying distinct structural conditions, although with a 35.78% higher computational cost. Conversely, the VAE-T² model is outperformed in 100% of the analyzed scenarios when compared to SAE-T² in identifying distinct structural conditions while also exhibiting a 21.97% higher average computational cost. Across all scenarios, the SAE-T² methodology consistently provided better classifications of wheel damage, showing its capability to extract relevant features from dynamic signals for Structural Health Monitoring (SHM) applications. These findings highlight SAE’s potential as an interesting tool for predictive maintenance, offering improved efficiency and safety in railway operations. Full article

In contrast to conventional localization methods, connectivity-based localization is a promising approach that leverages wireless links among network nodes. Here, the Euclidean distance matrix (EDM) plays a pivotal role in implementing the multidimensional scaling technique for the localization of wireless nodes based on pairwise distance measurements. This is based on the representation of complex datasets in lower-dimensional spaces, resulting from the mathematical property of an EDM being a low-rank matrix. However, EDM data are inevitably susceptible to contamination due to errors such as measurement imperfections, channel dynamics, and clock asynchronization. Motivated by the low-rank property of the EDM, we introduce a new pre-processor for connectivity-based localization, namely denoising-autoencoder-aided EDM reconstruction (DAE-EDMR). The proposed method is based on optimizing the neural network by inputting and outputting vectors of the eigenvalues of the noisy EDM and the original EDM, respectively. The optimized NN denoises the contaminated EDM, leading to an exceptional performance in connectivity-based localization. Additionally, we introduce a relaxed version of DAE-EDMR, i.e., truncated DAE-EDMR (T-DAE-EDMR), which remains operational regardless of variations in the number of nodes between the training and test phases in NN operations. The proposed algorithms show a superior performance in both EDM denoising and localization accuracy. Moreover, the method of T-DAE-EDMR notably requires a minimal number of training datasets compared to that in conventional approaches such as deep learning algorithms. Overall, our proposed algorithms reduce the required training dataset’s size by approximately one-tenth while achieving more than twice the effectiveness in EDM denoising, as demonstrated through our experiments. Full article

Advancements in music emotion prediction are driving AI-driven algorithmic composition, enabling the generation of complex melodies. However, bridging neural and auditory domains remains challenging due to the semantic gap between brain-derived low-level features and high-level musical concepts, making alignment computationally demanding. This study proposes a deep learning framework for generating MIDI sequences aligned with labeled emotion predictions through supervised feature extraction from neural and auditory domains. EEGNet is employed to process neural data, while an autoencoder-based piano algorithm handles auditory data. To address modality heterogeneity, Centered Kernel Alignment is incorporated to enhance the separation of emotional states. Furthermore, regression between feature domains is applied to reduce intra-subject variability in extracted Electroencephalography (EEG) patterns, followed by the clustering of latent auditory representations into denser partitions to improve MIDI reconstruction quality. Using musical metrics, evaluation on real-world data shows that the proposed approach improves emotion classification (namely, between arousal and valence) and the system’s ability to produce MIDI sequences that better preserve temporal alignment, tonal consistency, and structural integrity. Subject-specific analysis reveals that subjects with stronger imagery paradigms produced higher-quality MIDI outputs, as their neural patterns aligned more closely with the training data. In contrast, subjects with weaker performance exhibited auditory data that were less consistent. Full article

Leaf nitrogen content is a critical quantitative indicator for the growth of rubber trees, and accurately determining this content holds significant value for agricultural management and precision fertilization. This study introduces a novel feature extraction framework—SFS-CAE—that integrates the Sequential Feature Selection (SFS) method with Convolutional Autoencoder (CAE) technology to enhance the accuracy of nitrogen content estimation. Initially, the SFS algorithm was employed to select spectral bands from hyperspectral data collected from rubber tree leaves, thereby extracting feature information pertinent to nitrogen content. Subsequently, a CAE was utilized to further explore deep features within the dataset. Ultimately, the selected feature subset was concatenated with deep features to create a comprehensive input feature set, which was then analyzed using partial least squares regression (PLSR) for nitrogen content regression estimation. To validate the effectiveness of the proposed methodology, comparisons were made against commonly used competitive adaptive reweighted sampling (CARS), successive projection algorithm (SPA), and uninformative variable elimination (UVE) feature selection algorithms. The results indicate that SFS-CAE outperforms traditional SFS methods on the test set; notably, CARS-CAE achieved optimal performance with a coefficient of determination (R²) of 0.9064 and a root mean square error (RMSE) of 0.1405. This approach not only effectively integrates deep features derived from hyperspectral data but also optimizes both band selection and feature extraction processes, offering an innovative solution for the efficient estimation of nitrogen content in rubber tree leaves. Full article

The advent of Industry 4.0 has significantly transformed the manufacturing sector, bringing advancements in quality control efficiency, environmental sustainability, and production development. These changes have led to the development of intelligent technologies such as artificial intelligence (AI). However, implementing AI solutions in manufacturing processes still presents challenges in many aspects, particularly in handling irregular datasets influenced by diverse manufacturing settings. In the field of injection molding, quality inspection often occurs at the batch level rather than at the individual level, providing only the overall defect ratio of batch production instead of labeling each individual product. These issues limit the general application of AI and data-driven decision-making. To address these limitations and enhance product efficiency, this study proposes a novel anomaly detection framework for a specific manufacturing process. In Recipe-Based Learning, we first apply K-Means clustering to account for the flexible manufacturing process, which relies on diverse settings. The injection molding data are classified into setting-specific recipes to ensure data normality and uniqueness. The Kruskal-Wallis test is conducted to provide statistical evidence of differences in data based on varying settings, further justifying the necessity of Recipe-Based Learning. Then, Autoencoders for anomaly detection are trained with normal data from each recipe. With this data-driven AI approach, 61 defective products are predicted, compared to the existing 41 defects. Meanwhile, the integrated model, which does not consider variations in settings, only predicted 2 defects, indicating poor and distorted quality inspection. For Adaptable Learning, which focuses on new inputs with unseen settings, we apply KL-Divergence to identify the closest trained recipe data and its corresponding model. This approach outperformed both the integrated and additionally trained models in predictive power. As a result, continuous prediction is achieved without the need for further training, successfully enhancing process optimization. In the context of smart factories in the injection molding industry, such improvements in process management can significantly enhance overall productivity and decision-making, primarily through a data-driven AI approach. Full article

Arrhythmia is an irregularity in the rhythm of the heartbeat, and it is the primary method for detecting cardiac abnormalities. The electrocardiogram (ECG) identifies arrhythmias and is one of the methods used to diagnose cardiac issues. Traditional arrhythmia detection methods are time-consuming, error-prone, and often subjective, making it difficult for doctors to discern between distinct patterns of arrhythmia. To understand ECG signals, this study presents a multi-class classifier and an autoencoder with long short-term memory (LSTM) network layers for extracting signal properties on a dataset from the Massachusetts Institute of Technology and Boston’s Beth Israel Hospital (MIT-BIH). The suggested model had an accuracy rate of 98.57% on the arrhythmia dataset and 97.59% on the supraventricular dataset. In contrast to other deep learning models, the proposed model eliminates the problem of the gradient disappearing in classification tasks. Full article

Deep learning has emerged as a prevalent approach for hyperspectral unmixing. However, most existing unmixing methods employ a single network, resulting in moderate estimation errors and less meaningful endmembers and abundances. To address this imitation, this paper proposes a novel double autoencoders-based unmixing method, consisting of an endmember extraction network and an abundance estimation network. In the endmember network, to improve the spectral discrimination, a logarithm spectral angle distance (SAD), integrated with anomaly-guided weight, is developed as the loss function. Specifically, the logarithm function is used to boost the reliability of a pixel based on its high SAD similarity to other pixels. Moreover, the anomaly-guided weight mitigates the influence of outliers. As for the abundance network, a spectral convolutional autoencoder combined with the channel attention module is employed to exploit the spectral features. Additionally, the decoder weight is shared between the two networks to reduce computational complexity. Extensive comparative experiments with state-of-the-art unmixing methods demonstrate that the proposed method achieves superior performance in both endmember extraction and abundance estimation. Full article