Cluster assignment of large and complex datasets is a crucial but challenging task in pattern recognition and computer vision. In this study, we explore the possibility of employing fuzzy clustering in a deep neural network framework. Thus, we present a novel evolutionary unsupervised learning representation model with iterative optimization. It implements the deep adaptive fuzzy clustering (DAFC) strategy that learns a convolutional neural network classifier from given only unlabeled data samples. DAFC consists of a deep feature quality-verifying model and a fuzzy clustering model, where deep feature representation learning loss function and embedded fuzzy clustering with the weighted adaptive entropy is implemented. We joint fuzzy clustering to the deep reconstruction model, in which fuzzy membership is utilized to represent a clear structure of deep cluster assignments and jointly optimize for the deep representation learning and clustering. Also, the joint model evaluates current clustering performance by inspecting whether the resampled data from estimated bottleneck space have consistent clustering properties to improve the deep clustering model progressively. Experiments on various datasets show that the proposed method obtains a substantially better performance for both reconstruction and clustering quality compared to the other state-of-the-art deep clustering methods, as demonstrated with the in-depth analysis in the extensive experiments.

In this article, a source–grid–load-collabora tion-based control framework is proposed to improve the power quality of active distribution networks (ADNs) with high penetration of low-carbon energy. First, hybrid dynamics of ADNs are characterized by addressing the voltage regulation and operation economics in each operation mode, and the mode switching control is designed in line with the operation principle of the on-load tap changer, where voltage security events are used to build the event-triggered functions. Second, multiobjective optimization is formulated with consideration of the system-wide operation cost and distribution circuit loss of the ADN in a relatively slow time scale, while in the fast time scale, all the inverter-based distributed generators, energy storages, and static var compensator devices are coordinated at the source–load side, through which multiple voltage issues, including voltage profile issue and voltage increment issue, can be addressed in a fully distributed manner. Finally, simulation results validate the effectiveness and robustness of the proposed method based on the modified IEEE 33-bus system.

Recent methods often introduce attention mechanisms into the skip connections of U-shaped networks to capture features. However, these methods usually overlook spatial information extraction in skip connections and exhibit inefficiency in capturing spatial and channel information. This issue prompts us to reevaluate the design of the skip-connection mechanism and propose a new deep-learning network called the Fusing Spatial and Channel Attention Network, abbreviated as FSCA-Net. FSCA-Net is a novel U-shaped network architecture that utilizes the Parallel Attention Transformer (PAT) to enhance the extraction of spatial and channel features in the skip-connection mechanism, further compensating for downsampling losses. We design the Cross-Attention Bridge Layer (CAB) to mitigate excessive feature and resolution loss when downsampling to the lowest level, ensuring meaningful information fusion during upsampling at the lowest level. Finally, we construct the Dual-Path Channel Attention (DPCA) module to guide channel and spatial information filtering for Transformer features, eliminating ambiguities with decoder features and better concatenating features with semantic inconsistencies between the Transformer and the U-Net decoder. FSCA-Net is designed explicitly for fine-grained segmentation tasks of multiple organs and regions. Our approach achieves over 48% reduction in FLOPs and over 32% reduction in parameters compared to the state-of-the-art method. Moreover, FSCA-Net outperforms existing segmentation methods on seven public datasets, demonstrating exceptional performance. The code has been made available on GitHub: https://github.com/Henry991115/FSCA-Net .

Accurate segmentation of human tissue structure from medical images is one of the critical links in medical image diagnosis. However, due to the medical image scale of different tissues varying significantly and being structurally complex, the low contrast between tissues and background in some medical imaging makes it challenging to identify. The existing models are difficult to extract representative multi-scale features of medical images that cannot accurately segment the organizational structure from the background in low-contrast medical images. To solve these problems, this study presents a scale and context information fusion network structure based on multi-type medical image segmentation (SCIF-Net), which contains three modules: feature pyramid encoder (FPE), multi-scale feature dynamic aggregation (MFDA), and adaptive spatial information fusion (ASIF). We build the FPE module to further enhance the representational ability of the network encoder output feature map at each stage. The MFDA module is used to effectively extract multi-scale information from the encoder output feature map and aggregate multi-scale features. The constructed ASIF module enables the network to selectively concentrate on the vital spatial information in the encoder feature map and merge the decoder feature map semantic information, minimizing background noise influence. Extensive experiments on the retinal segmentation task, gland segmentation task, and femur segmentation task, show that the SCIF-Net network outperforms other advanced methods.

This study presents a new target detection method which is named as circular targets feature detection framework based on a deep convolutional neural network (DCNN). The central proposition of this method uses the optimized DCNN architecture to detect the target and locate the position of the circle accurately in the image field of view. In this study, a Hough transform based on threshold processing (HTP) is embedded into the optimized DCNN architecture, which calculates the center positions and radius of all circles by training the circular samples for each detected rectangular frame. It can efficiently identify small circular target materials in the industry and screen out unqualified particles. The experimental results show that the circular boundary information can be obtained from the complex noise background images, thereby accurately determining the location of the circle. It has some advantages over only using a specific circular recognition algorithm. We proposed the new study on HTP-DCNN, which has extremely high accuracy in the field of machine vision positioning with circles for industrial applications.

Inferential modeling has been of significance for modern manufacturing in estimating the quality-related process variables. As an effective inferential model, probabilistic slow feature analysis (PSFA) has gained attention in regression tasks to interpret dynamic properties with a slowness preference. However, PSFA is often challenged by the nonlinear sequential data due to its linear state-space structure. In this article, a new nonlinear extension of PSFA is proposed under the deep learning framework to enhance the dynamic feature extraction with limited labels, incorporating variational inference and Monte Carlo inference to derive the objective function. The proposed model considers the relevance of inputs with outputs as the input weights to upgrade prediction performance. The proposed model is verified through an industrial hydrocracking process to predict diesel yield with missing labels ranged from 0% to 50%, and the root mean squared error is reduced by at least 8.78% compared to PSFA.