Search Results (9)

Early detection of diabetic retinopathy is critical for preserving vision in diabetic patients. The classification of lesions in Retinal fundus images, particularly macular edema, is an essential diagnostic tool, yet it presents a significant learning curve for both novice and experienced ophthalmologists. To address this challenge, a novel Convolutional Deep Belief Network (CDBN) is proposed to classify image patches into three distinct categories: two types of macular edema—microhemorrhages and hard exudates—and a healthy category. The method leverages high-level feature extraction to mitigate issues arising from the high similarity of low-level features in noisy images. Additionally, a Real-Coded Genetic Algorithm optimizes the parameters of Gabor filters and the network, ensuring optimal feature extraction and classification performance. Experimental results demonstrate that the proposed CDBN outperforms comparative models, achieving an F1 score of 0.9258. These results indicate that the architecture effectively overcomes the challenges of lesion classification in retinal images, offering a robust tool for clinical application and paving the way for advanced clinical decision support systems in diabetic retinopathy management. Full article

Anomaly detection (AD) is crucial in various domains such as industrial inspection, medical diagnosis, and video surveillance. Previous advancements in unsupervised AD often necessitated training separate models for different objects, which can be inefficient when dealing with diverse categories in real-world scenarios. This paper addresses the recently proposed task of multi-class unsupervised anomaly detection (MUAD), which is more practical and challenging. We begin by reviewing the first MUAD framework, UniAD, and analyzing the characteristics of end-to-end feature reconstruction networks that can adapt to various backbone architectures. Building on these insights, we introduce a novel MUAD framework called DualAD. Our approach is based on the innovative design of a Coupled Dual-Branch Network (CDBN), which integrates a Wide–Shallow Network (WSN) with a Narrow–Deep Network (NDN), leveraging the strengths of both to achieve superior performance. We explore a fully transformer-based homogeneous design for the CDBN and introduce a more lightweight heterogeneous CDBN design that integrates a transformer with a Memory-Augmented Multi-Layer Perceptron (MMLP). Experimental results on the MVTec AD and VisA datasets demonstrate that DualAD outperforms the recent state-of-the-art methods and exhibits robust performance across various pre-trained backbone architectures. Full article

Epilepsy is a group of neurological disorders characterized by epileptic seizures, and it affects tens of millions of people worldwide. Currently, the most effective diagnostic method employs the monitoring of brain activity through electroencephalogram (EEG). However, it is critical to predict epileptic seizures in patients prior to their onset, allowing for the administration of preventive medications before the seizure occurs. As a pivotal application of artificial intelligence in medical treatment, learning the features of EEGs for epilepsy prediction and detection remains a challenging problem, primarily due to the presence of intra-class and inter-class variations in EEG signals. In this study, we propose the spatio-temporal EEGNet, which integrates contractive slab and spike convolutional deep belief network (CssCDBN) with a self-attention architecture, augmented by dual-task learning to address this issue. Initially, our model was designed to extract high-order and deep representations from EEG spectrum images, enabling the simultaneous capture of spatial and temporal information. Furthermore, EEG-based verification aids in reducing intra-class variation by considering the time correlation of the EEG during the fine-tuning stage, resulting in easier inference and training. The results demonstrate the notable efficacy of our proposed method. Our method achieved a sensitivity of 98.5%, a false-positive rate (FPR) of 0.041, a prediction time of 50.92 min during the epilepsy prediction task, and an accuracy of 94.1% during the epilepsy detection task, demonstrating significant improvements over current state-of-the-art methods. Full article

Printed Circuit Boards (PCBs), as integral components of electronic products, play a crucial role in modern industrial production. However, due to the precision and complexity of PCBs, existing PCB defect detection methods exhibit some issues such as low detection accuracy and limited usability. In order to address these problems, a PCB defect detection method based on D-DenseNet (PCBDD-DDNet) has been proposed. This method capitalizes on the advantages of two deep learning networks, CDBN (Convolutional Deep Belief Networks) and DenseNet (Densely Connected Convolutional Networks), to construct the D-DenseNet (Combination of CDBN and DenseNet) network. Within this network, CDBN focuses on extracting low-level features, while DenseNet is responsible for high-level feature extraction. The outputs from both networks are integrated using a weighted averaging approach. Additionally, the D-DenseNet employs a multi-scale module to extract features from different levels. This is achieved by incorporating filters of sizes 3 × 3, 5 × 5, and 7 × 7 along the three paths of the CDBN network, multi-scale feature extraction network, and DenseNet network, effectively capturing information at various scales. To prevent overfitting and enhance network performance, the Adafactor optimization function and L2 regularization are introduced. Finally, online hard example mining mechanism (OHEM) is incorporated to improve the network’s handling of challenging samples and enhance the accuracy of the PCB defect detection network. The effectiveness of this PCBDD-DDNet method is demonstrated through experiments conducted on publicly available PCB datasets. And the method achieves a mAP (mean Average Precision) of 93.24%, with an accuracy higher than other classical networks. The results affirm the method’s efficacy in PCB defect detection. Full article

A smart grid improves power grid efficiency by using modern information and communication technologies. However, at the same time, due to the dependence on information technology and the deep integration of electrical components and computing information in cyber space, the system might become increasingly vulnerable to cyber-attacks. Among various emerging security problems, a false data injection attack (FDIA) is a new type of attack against the state estimation. In this article, a deep learning-based identification scheme is developed to detect and mitigate information corruption. The scheme implements a conditional deep belief network (CDBN) to analyze time-series input data and leverages captured features to detect the FDIA. The performance of our detection mechanism is validated by using the IEEE 14-bus test system for simulation. Different attack scenarios and parameters are set to demonstrate the feasibility and effectiveness of the developed scheme. Compared with the artificial neural network (ANN) and the support vector machine (SVM), the experimental analyses indicate that the results of our detection mechanism are better than those of the other two in terms of FDIA detection accuracy and robustness. Full article

Mechanical equipment fault detection is critical in industrial applications. Based on vibration signal processing and analysis, the traditional fault diagnosis method relies on rich professional knowledge and artificial experience. Achieving accurate feature extraction and fault diagnosis is difficult using such an approach. To learn the characteristics of features from data automatically, a deep learning method is used. A qualitative and quantitative method for rolling bearing faults diagnosis based on an improved convolutional deep belief network (CDBN) is proposed in this study. First, the original vibration signal is converted to the frequency signal with the fast Fourier transform to improve shallow inputs. Second, the Adam optimizer is introduced to accelerate model training and convergence speed. Finally, the model structure is optimized. A multi-layer feature fusion learning structure is put forward wherein the characterization capabilities of each layer can be fully used to improve the generalization ability of the model. In the experimental verification, a laboratory self-made bearing vibration signal dataset was used. The dataset included healthy bearings, nine single faults of different types and sizes, and three different types of composite fault signals. The results of load 0 kN and 1 kN both indicate that the proposed model has better diagnostic accuracy, with an average of 98.15% and 96.15%, compared with the traditional stacked autoencoder, artificial neural network, deep belief network, and standard CDBN. With improved diagnostic accuracy, the proposed model realizes reliable and effective qualitative and quantitative diagnosis of bearing faults. Full article

Effective and accurate water demand prediction is an important part of the optimal scheduling of a city water supply system. A novel deep architecture model called the continuous deep belief echo state network (CDBESN) is proposed in this study for the prediction of hourly urban water demand. The CDBESN model uses a continuous deep belief network (CDBN) as the feature extraction algorithm and an echo state network (ESN) as the regression algorithm. The new architecture can model actual water demand data with fast convergence and global optimization ability. The prediction capacity of the CDBESN model is tested using historical hourly water demand data obtained from an urban waterworks in Zhuzhou, China. The performance of the proposed model is compared with those of ESN, continuous deep belief neural network, and support vector regression models. The correlation coefficient (r²), normalized root-mean-square error (NRMSE), and mean absolute percentage error (MAPE) are adopted as assessment criteria. Forecasting results obtained in the testing stage indicate that the CDBESN model has the largest r² value of 0.995912 and the smallest NRMSE and MAPE values of 0.027163 and 2.469419, respectively. The prediction accuracy of the proposed model clearly outperforms those of the models it is compared with due to the good feature extraction ability of CDBN and the excellent feature learning ability of ESN. Full article

Hyperspectral images (HSIs) provide unique capabilities for urban impervious surfaces (UIS) extraction. This paper proposes a multi-feature extraction model (MFEM) for UIS detection from HSIs. The model is based on a nonlinear dimensionality reduction technique, t-distributed stochastic neighbor embedding (t-SNE), and the deep learning method convolutional deep belief networks (CDBNs). We improved the two methods to create a novel MFEM consisting of improved t-SNE, deep compression CDBNs (d-CDBNs), and a logistic regression classifier. The improved t-SNE method provides dimensionality reduction and spectral feature extraction from the original HSIs and the d-CDBNs algorithm extracts spatial feature and edges using the reduced dimensional datasets. Finally, the extracted features are combined into multi-feature for the impervious surface detection using the logistic regression classifier. After comparing with the commonly used methods, the current experimental results demonstrate that the proposed MFEM model provides better performance for UIS extraction and detection from HSIs. Full article

The domestic cat (Feliscatus) is one of the most attractive pets in the world, and it generates mysterious kinds of sound according to its mood and situation. In this paper, we deal with the automatic classification of cat sounds using machine learning. Machine learning approach for the classification requires class labeled data, so our work starts with building a small dataset named CatSound across 10 categories. Along with the original dataset, we increase the amount of data with various audio data augmentation methods to help our classification task. In this study, we use two types of learned features from deep neural networks; one from a pre-trained convolutional neural net (CNN) on music data by transfer learning and the other from unsupervised convolutional deep belief network that is (CDBN) solely trained on a collected set of cat sounds. In addition to conventional GAP, we propose an effective pooling method called FDAP to explore a number of meaningful features. In FDAP, the frequency dimension is roughly divided and then the average pooling is applied in each division. For the classification, we exploited five different machine learning algorithms and an ensemble of them. We compare the classification performances with respect following factors: the amount of data increased by augmentation, the learned features from pre-trained CNN or unsupervised CDBN, conventional GAP or FDAP, and the machine learning algorithms used for the classification. As expected, the proposed FDAP features with larger amount of data increased by augmentation combined with the ensemble approach have produced the best accuracy. Moreover, both learned features from pre-trained CNN and unsupervised CDBN produce good results in the experiment. Therefore, with the combination of all those positive factors, we obtained the best result of 91.13% in accuracy, 0.91 in f1-score, and 0.995 in area under the curve (AUC) score. Full article