Search

Cardinality estimation is critical for database management systems (DBMSs) to execute query optimization tasks, which can guide the query optimizer in choosing the best execution plan. However, traditional cardinality estimation methods cannot provide accurate estimates because they cannot accurately capture the correlation between multiple tables. Several recent studies have revealed that learning-based cardinality estimation methods can address the shortcomings of traditional methods and provide more accurate estimates. However, the learning-based cardinality estimation methods still have large errors when an SQL query involves multiple tables or is very complex. To address this problem, we propose a sampling-based tree long short-term memory (TreeLSTM) neural network to model queries. The proposed model addresses the weakness of traditional methods when no sampled tuples match the predicates and considers the join relationship between multiple tables and the conjunction and disjunction operations between predicates. We construct subexpressions as trees using operator types between predicates and improve the performance and accuracy of cardinality estimation by capturing the join-crossing correlations between tables and the order dependencies between predicates. In addition, we construct a new loss function to overcome the drawback that Q-error cannot distinguish between large and small cardinalities. Extensive experimental results from real-world datasets show that our proposed model improves the estimation quality and outperforms traditional cardinality estimation methods and the other compared deep learning methods in three evaluation metrics: Q-error, MAE, and SMAPE.

Remote sensing image object detection holds significant research value in resources and the environment. Nevertheless, complex background information and considerable size differences between objects in remote sensing images make it challenging. This paper proposes an efficient remote sensing image object detection model (MSA-YOLO) to improve detection performance. First, we propose a Multi-Scale Strip Convolution Attention Mechanism (MSCAM), which can reduce the introduction of background noise and fuse multi-scale features to enhance the focus of the model on foreground objects of various sizes. Second, we introduce the lightweight convolution module GSConv and propose an improved feature fusion layer, which makes the model more lightweight while improving detection accuracy. Finally, we propose the Wise-Focal CIoU loss function, which can reweight different samples to balance the contribution of different samples to the loss function, thereby improving the regression effect. Experimental results show that on the remote sensing image public datasets DIOR and HRRSD, the performance of our proposed MSA-YOLO model is significantly better than other existing methods.

The most significant technical challenges of current aerial image object-detection tasks are the extremely low accuracy for detecting small objects that are densely distributed within a scene and the lack of semantic information. Moreover, existing detectors with large parameter scales are unsuitable for aerial image object-detection scenarios oriented toward low-end GPUs. To address this technical challenge, we propose efficient-lightweight You Only Look Once (EL-YOLO), an innovative model that overcomes the limitations of existing detectors and low-end GPU orientation. EL-YOLO surpasses the baseline models in three key areas. Firstly, we design and scrutinize three model architectures to intensify the model’s focus on small objects and identify the most effective network structure. Secondly, we design efficient spatial pyramid pooling (ESPP) to augment the representation of small-object features in aerial images. Lastly, we introduce the alpha-complete intersection over union (α-CIoU) loss function to tackle the imbalance between positive and negative samples in aerial images. Our proposed EL-YOLO method demonstrates a strong generalization and robustness for the small-object detection problem in aerial images. The experimental results show that, with the model parameters maintained below 10 M while the input image size was unified at 640 × 640 pixels, the APS of the EL-YOLOv5 reached 10.8% and 10.7% and enhanced the APs by 1.9% and 2.2% compared to YOLOv5 on two challenging aerial image datasets, DIOR and VisDrone, respectively.

Sequential recommendation uses contrastive learning to randomly augment user sequences and alleviate the data sparsity problem. However, there is no guarantee that the augmented positive or negative views remain semantically similar. To address this issue, we propose graph neural network-guided contrastive learning for sequential recommendation (GC4SRec). The guided process employs graph neural networks to obtain user embeddings, an encoder to determine the importance score of each item, and various data augmentation methods to construct a contrast view based on the importance score. Experimental validation is conducted on three publicly available datasets, and the experimental results demonstrate that GC4SRec improves the hit rate and normalized discounted cumulative gain metrics by 1.4% and 1.7%, respectively. The model can enhance recommendation performance and mitigate the data sparsity problem.

The convolution module in Conformer is capable of providing translationally invariant convolution in time and space. This is often used in Mandarin recognition tasks to address the diversity of speech signals by treating the time-frequency maps of speech signals as images. However, convolutional networks are more effective in local feature modeling, while dialect recognition tasks require the extraction of a long sequence of contextual information features; therefore, the SE-Conformer-TCN is proposed in this paper. By embedding the squeeze-excitation block into the Conformer, the interdependence between the features of channels can be explicitly modeled to enhance the model’s ability to select interrelated channels, thus increasing the weight of effective speech spectrogram features and decreasing the weight of ineffective or less effective feature maps. The multi-head self-attention and temporal convolutional network is built in parallel, in which the dilated causal convolutions module can cover the input time series by increasing the expansion factor and convolutional kernel to capture the location information implied between the sequences and enhance the model’s access to location information. Experiments on four public datasets demonstrate that the proposed model has a higher performance for the recognition of Mandarin with an accent, and the sentence error rate is reduced by 2.1% compared to the Conformer, with only 4.9% character error rate.

You Only Look Once (YOLO) series detectors are suitable for aerial image object detection because of their excellent real-time ability and performance. Their high performance depends heavily on the anchor generated by clustering the training set. However, the effectiveness of the general Anchor Generation algorithm is limited by the unique data distribution of the aerial image dataset. The divergence in the distribution of the number of objects with different sizes can cause the anchors to overfit some objects or be assigned to suboptimal layers because anchors of each layer are generated uniformly and affected by the overall data distribution. In this paper, we are inspired by experiments under different anchors settings and proposed the Layered Anchor Generation (LAG) algorithm. In the LAG, objects are layered by their diagonals, and then anchors of each layer are generated by analyzing the diagonals and aspect ratio of objects of the corresponding layer. In this way, anchors of each layer can better match the detection range of each layer. Experiment results showed that our algorithm is of good generality that significantly uprises the performance of You Only Look Once version 3 (YOLOv3), You Only Look Once version 5 (YOLOv5), You Only Learn One Representation (YOLOR), and Cascade Regions with CNN features (Cascade R-CNN) on the Vision Meets Drone (VisDrone) dataset and the object DetectIon in Optical Remote sensing images (DIOR) dataset, and these improvements are cost-free.