Search

Time series data complexity presents new challenges in clustering analysis across fields such as electricity, energy, industry, and finance. Despite advances in representation learning and clustering with Variational Autoencoders (VAE) based deep learning techniques, issues like the absence of discriminative power in feature representation, the disconnect between instance reconstruction and clustering objectives, and scalability challenges with large datasets persist. This paper introduces a novel deep time series clustering approach integrating VAE with metric learning. It leverages a VAE based on Gated Recurrent Units for temporal feature extraction, incorporates metric learning for joint optimization of latent space representation, and employs the sum of log likelihoods as the clustering merging criterion, markedly improving clustering accuracy and interpretability. Experimental findings demonstrate a 27.16% improvement in average clustering accuracy and a 47.15% increase in speed on industrial load data. This study offers novel insights and tools for the thorough analysis and application of time series data, with further exploration of VAE's potential in time series clustering anticipated in future research. [ABSTRACT FROM AUTHOR]

The identification research of hydrogenation catalyst information has always been one of the most important businesses in the chemical industry. In order to aid researchers in efficiently screening high-performance catalyst carriers and tackle the pressing challenge at hand, it is imperative to find a solution for the intelligent recognition of hydrogenation catalyst images. To address the issue of low recognition accuracy caused by adhesion and stacking of hydrogenation catalysts, An image recognition algorithm of hydrogenation catalyst based on FPNC Net was proposed in this paper. In the present study, Resnet50 backbone network was used to extract the features, and spatially-separable convolution kernel was used to extract the multi-scale features of catalyst fringe. In addition, to effectively segment the adhesive regions of stripes, FPN (Feature Pyramid Network) is added to the backbone network for deep and shallow feature fusion. Introducing an attention module to adaptively adjust weights can effectively highlight the target features of the catalyst. The experimental results showed that the FPNC Net model achieved an accuracy of 94.2% and an AP value improvement of 19.37% compared to the original CenterNet model. The improved model demonstrates a significant enhancement in detection accuracy, indicating a high capability for detecting hydrogenation catalyst targets [ABSTRACT FROM AUTHOR]

To overcome the problem of the high initial position of the point cloud required by the traditional Iterative Closest Point (ICP) algorithm, in this paper, we propose a point cloud registration method based on normal vector and directional histogram features (SHOT). Firstly, a hybrid filtering method based on the voxel idea is proposed and verified using the measured point cloud data, and the noise removal rates of 97.5%, 97.8%, and 93.8% are obtained. Secondly, in terms of feature point extraction, the original algorithm is optimized, and the optimized algorithm can better extract the missing part of the point cloud. Finally, a fine alignment method based on normal vector and directional histogram features (SHOT) is proposed, and the improved algorithm is compared with the existing algorithm. Taking the Stanford University point cloud data and the self-measured point cloud data as examples, the plotted iteration-error plots can be concluded that the improved method can reduce the number of iterations by 40.23% and 37.62%, respectively. [ABSTRACT FROM AUTHOR]

Real-time and accurate detection of ships plays a vital role in ensuring navigation safety and ship supervision. Aiming at the problems of large parameters, large computation quantity, poor real-time performance, and high requirements for memory and computing power of the current ship detection model, this paper proposes a ship target detection algorithm MC-YOLOv5s based on YOLOv5s. First, the MobileNetV3-Small lightweight network is used to replace the original feature extraction backbone network of YOLOv5s to improve the detection speed of the algorithm. And then, a more efficient CNeB is designed based on the ConvNeXt-Block module of the ConvNeXt network to replace the original feature fusion module of YOLOv5s, which improves the spatial interaction ability of feature information and further reduces the complexity of the model. The experimental results obtained from the training and verification of the MC-YOLOv5s algorithm show that, compared with the original YOLOv5s algorithm, MC-YOLOv5s reduces the number of parameters by 6.98 MB and increases the mAP by about 3.4%. Even compared with other lightweight detection models, the improved model proposed in this paper still has better detection performance. The MC-YOLOv5s has been verified in the ship visual inspection and has great application potential. The code and models are publicly available at https://github.com/sakura994479727/datas. [ABSTRACT FROM AUTHOR]

Simultaneous Localization and Mapping (SLAM) technology is crucial for achieving spatial localization and autonomous navigation. Finding image features that are representative presents a key challenge in visual SLAM systems. The widely used ORB (Oriented FAST and Rotating BRIEF) algorithm achieves rapid image feature extraction. However, traditional ORB algorithms face issues such as dense, overlapping feature points, and imbalanced distribution, resulting in mismatches and redundancies. This paper introduces an image feature extraction algorithm called Adaptive Threshold and Local Gray Difference-ORB(ALGD-ORB) to address these limitations. Specifically, an adaptive threshold is employed to enhance feature point detection, and an improved quadtree method is used to homogenize feature point distribution. This method combines feature descriptors generated from both gray size and gray difference to enhance feature descriptor distinctiveness. By fusing these descriptors, their effectiveness is improved. Experimental results demonstrate that the ALGD-ORB algorithm significantly enhances the uniformity of feature point distribution compared to other algorithms, while maintaining accuracy and real-time performance. [ABSTRACT FROM AUTHOR]

Recommendation algorithms save a lot of valuable time for people to get the information they are interested in. However, the feature calculation and extraction process of each machine learning or deep learning recommendation algorithm are different, so how to obtain various features with different dimensions, i.e., how to integrate the advantages of each model and improve the model inference efficiency, becomes the focus of this paper. In this paper, a better deep learning model is obtained by integrating several cutting-edge deep learning models. Meanwhile, to make the integrated learning model converge better and faster, the parameters of the integrated module are initialized, constraints are imposed, and a new activation function is designed for better integration of the sub-models. Finally, the integrated large model is distilled for knowledge distillation, which greatly reduces the number of model parameters and improves the model inference efficiency. [ABSTRACT FROM AUTHOR]

Multi-scale image decomposition is crucial for image fusion, extracting prominent feature textures from infrared and visible light images to obtain clear fused images with more textures. This paper proposes a fusion method of infrared and visible light images based on spatial domain and image features to obtain high-resolution and texture-rich images. First, an efficient hierarchical image clustering algorithm based on superpixel fast pixel clustering directly performs multi-scale decomposition of each source image in the spatial domain and obtains high-frequency, medium-frequency, and low-frequency layers to extract the maximum and minimum values of each source image combined images. Then, using the attribute parameters of each layer as fusion weights, high-definition fusion images are through adaptive feature fusion. Besides, the proposed algorithm performs multi-scale decomposition of the image in the spatial frequency domain to solve the information loss problem caused by the conversion process between the spatial frequency and frequency domains in the traditional extraction of image features in the frequency domain. Eight image quality indicators are compared with other fusion algorithms. Experimental results show that this method outperforms other comparative methods in both subjective and objective measures. Furthermore, the algorithm has high definition and rich textures. [ABSTRACT FROM AUTHOR]