Explore the vast range of titles available.

Deep learning, a crucial technique for achieving artificial intelligence (AI), has been successfully applied in many fields. The gradual application of the latest architectures of deep learning in the field of time series forecasting (TSF), such as Transformers, has shown excellent performance and results compared to traditional statistical methods. These applications are widely present in academia and in our daily lives, covering many areas including forecasting electricity consumption in power systems, meteorological rainfall, traffic flow, quantitative trading, risk control in finance, sales operations and price predictions for commercial companies, and pandemic prediction in the medical field. Deep learning-based TSF tasks stand out as one of the most valuable AI scenarios for research, playing an important role in explaining complex real-world phenomena. However, deep learning models still face challenges: they need to deal with the challenge of large-scale data in the information age, achieve longer forecasting ranges, reduce excessively high computational complexity, etc. Therefore, novel methods and more effective solutions are essential. In this paper, we review the latest developments in deep learning for TSF. We begin by introducing the recent development trends in the field of TSF and then propose a new taxonomy from the perspective of deep neural network models, comprehensively covering articles published over the past five years. We also organize commonly used experimental evaluation metrics and datasets. Finally, we point out current issues with the existing solutions and suggest promising future directions in the field of deep learning combined with TSF. This paper is the most comprehensive review related to TSF in recent years and will provide a detailed index for researchers in this field and those who are just starting out.

Driven by real-world demands of processing massive high-frequency data and achieving longer forecasting horizons in time series forecasting scenarios, a variety of deep learning architectures designed for time series forecasting have emerged at a rapid pace. However, this rapid development actually leads to a sharp increase in parameter size, and the introduction of numerous redundant modules typically offers only limited contribution to improving prediction performance. Although prediction models have shown a trend towards simplification over a period, significantly improving prediction performance, they remain weak in capturing dynamic relationships. Moreover, the predictive accuracy depends on the quality and extent of data preprocessing, making them unsuitable for handling complex real-world data. To address these challenges, we introduced Treeformer, an innovative model that treats the traditional tree-based machine learning model as an encoder and integrates it with a Transformer-based forecasting model, while also adopting the idea of time–feature two-dimensional information extraction by channel independence and cross-channel modeling strategy. It fully utilizes the rich information across variables to improve the ability of time series forecasting. It improves the accuracy of prediction on the basis of the original deep model while maintaining a low computational cost and exhibits better applicability to real-world datasets. We conducted experiments on multiple publicly available datasets across five domains—electricity, weather, traffic, the forex market, healthcare. The results demonstrate improved accuracy, and provide a better hybrid approach for enhancing predictive performance in Long-term Sequence Forecasting (LSTF) problems.

An event camera is a novel bio-inspired sensor that effectively compensates for the shortcomings of current frame cameras, which include high latency, low dynamic range, motion blur, etc. Rather than capturing images at a fixed frame rate, an event camera produces an asynchronous signal by measuring the brightness change of each pixel. Consequently, an appropriate algorithm framework that can handle the unique data types of event-based vision is required. In this paper, we propose a dynamic object tracking framework using an event camera to achieve long-term stable tracking of event objects. One of the key novel features of our approach is to adopt an adaptive strategy that adjusts the spatiotemporal domain of event data. To achieve this, we reconstruct event images from high-speed asynchronous streaming data via online learning. Additionally, we apply the Siamese network to extract features from event data. In contrast to earlier models that only extract hand-crafted features, our method provides powerful feature description and a more flexible reconstruction strategy for event data. We assess our algorithm in three challenging scenarios: 6-DoF (six degrees of freedom), translation, and rotation. Unlike fixed cameras in traditional object tracking tasks, all three tracking scenarios involve the simultaneous violent rotation and shaking of both the camera and objects. Results from extensive experiments suggest that our proposed approach achieves superior accuracy and robustness compared to other state-of-the-art methods. Without reducing time efficiency, our novel method exhibits a 30% increase in accuracy over other recent models. Furthermore, results indicate that event cameras are capable of robust object tracking, which is a task that conventional cameras cannot adequately perform, especially for super-fast motion tracking and challenging lighting situations.

Purpose Maize/soybean intercropping is a commonly employed agricultural technique with significant implications for enhancing crop productivity. However, the mechanisms by which rhizosphere soil microbial communities modulate genetic-level phosphorus (P) availability in maize/soybean intercropping systems in Northwest China remain unexplored. Methods The effects of maize/soybean intercropping on rhizosphere soil P availability and P cycling-related genes were evaluated using the biologically based P fractionation method and metagenomics. Results Soil organic carbon, total P, available P, and P activation coefficient improved in the maize/soybean intercropping. Further, the content of soil P fractions followed the order HCl-P > citrate-P > enzyme-P > CaCl 2 -P. The dominant soil microbial phyla were Proteobacteria, Actinobacteria, Acidobacteria, Chloroflexi, and Planctomycetes. The results of principal component analysis and nonmetric multidimensional scaling indicate that soil microbial composition differed among systems. The genes phoD , ppa , ppx , and pstC up-regulated in the intercropping, the results of random forest analysis indicate that these genes have the highest explanation for available P, suggesting that the improved P availability in the intercropping might be due to the up-regulation of these gene expressions. Redundant analysis indicated that pH and microbial biomass P significantly correlated with P fractions, suggesting they are essential factors in influencing P availability. Inorganic P solubilization, regulatory, and transporter genes were found to be associated with soil pH, total P, and alkaline phosphatase, suggesting they are the key factors that affect the expression of genes related to soil P cycling. Conclusion Maize/soybean intercropping can increase rhizosphere soil P availability. While there are associations between available P and microbial genes, it is important to note that soil properties play a more pivotal role than genes in determining soil P availability.

Occlusion in facial photos poses a significant challenge for machine detection and recognition. Consequently, occluded face recognition for camera-captured images has emerged as a prominent and widely discussed topic in computer vision. The present standard face recognition methods have achieved remarkable performance in unoccluded face recognition but performed poorly when directly applied to occluded face datasets. The main reason lies in the absence of identity cues caused by occlusions. Therefore, a direct idea of recovering the occluded areas through an inpainting model has been proposed. However, existing inpainting models based on an encoder-decoder structure are limited in preserving inherent identity information. To solve the problem, we propose ID-Inpainter, an identity-guided face inpainting model, which preserves the identity information to the greatest extent through a more accurate identity sampling strategy and a GAN-like fusing network. We conduct recognition experiments on the occluded face photographs from the LFW, CFP-FP, and AgeDB-30 datasets, and the results indicate that our method achieves state-of-the-art performance in identity-preserving inpainting, and dramatically improves the accuracy of normal recognizers in occluded face recognition.

Traditional object detectors require extensive instance-level annotations for training. Conversely, few-shot object detectors, which are generally fine-tuned using limited data from unknown classes, tend to show biases toward base categories and are susceptible to variations within these unknown samples. To mitigate these challenges, we introduce a Two-Stage Fine-Tuning Approach (TFA) named Extreme R-CNN, designed to operate effectively with extremely limited original samples through the integration of sample synthesis and knowledge distillation. Our approach involves synthesizing new training examples via instance clipping and employing various data-augmentation techniques. We enhance the Faster R-CNN architecture by decoupling the regression and classification components of the Region of Interest (RoI), allowing synthetic samples to train the classification head independently of the object-localization process. Comprehensive evaluations on the Microsoft COCO and PASCAL VOC datasets demonstrate significant improvements over baseline methods. Specifically, on the PASCAL VOC dataset, the average precision for novel categories is enhanced by up to 15 percent, while on the more complex Microsoft COCO benchmark it is enhanced by up to 6.1 percent. Remarkably, in the 1-shot scenario, the AP50 of our model exceeds that of the baseline model in the 10-shot setting within the PASCAL VOC dataset, confirming the efficacy of our proposed method.

Medical image segmentation is crucial for disease diagnosis, as precise results aid clinicians in locating lesion regions. However, lesions often have blurred boundaries and complex shapes, challenging traditional methods in capturing clear edges and impacting accurate localization and complete excision. Small lesions are also critical but prone to detail loss during downsampling, reducing segmentation accuracy. To address these issues, we propose a novel adaptive scale thresholding network (AdSTNet) that acts as a post-processing lightweight network for enhancing sensitivity to lesion edges and cores through a dual-threshold adaptive mechanism. The dual-threshold adaptive mechanism is a key architectural component that includes a main threshold map for core localization and an edge threshold map for more precise boundary detection. AdSTNet is compatible with any segmentation network and introduces only a small computational and parameter cost. Additionally, Spatial Attention and Channel Attention (SACA), the Laplacian operator, and the Fusion Enhancement module are introduced to improve feature processing. SACA enhances spatial and channel attention for core localization; the Laplacian operator retains edge details without added complexity; and the Fusion Enhancement module adapts concatenation operation and Convolutional Gated Linear Unit (ConvGLU) to improve feature intensities to improve edge and small lesion segmentation. Experiments show that AdSTNet achieves notable performance gains on ISIC 2018, BUSI, and Kvasir-SEG datasets. Compared with the original U-Net, our method attains mIoU/mDice of 83.40%/90.24% on ISIC, 71.66%/80.32% on BUSI, and 73.08%/81.91% on Kvasir-SEG. Moreover, similar improvements are observed in the rest of the networks.

Object detection, an important task in computer vision, has achieved a conspicuous improvement. Among the methods for object detection, the one-stage detector is a simple, end-to-end, anchor-free, and straightforward deep learning pipeline. Many one-stage detectors locate the bounding box using regression, and the regression loss is the maximum among all errors. Hence, locating the bounding box accurately is one of the keys for improving the average precision (AP) for a detector. In this paper, we suggest a simple and precise locator named the bounding convolutional network (BoundConvNet) to draw “bounding features” from heatmaps to refine the object locations and apply a category-aware collaborative intersection over union (Co-IoU) loss function to optimize the bounding box regression for dealing with a problem of different class center point overlap. BoundConvNet is a head network for bounding box regression, which contains several depthwise separable dilated convolutional layers to decouple the classification task from the regression task. Extensive experiments demonstrate that BoundConvNet improves the AP of the one-stage detector CenterNet and helps the CenterNet mark the bounding box of objects more accurately. For small object detection, the AP of CenterNet is improved by 13.8% relative on MS COCO dataset with ResNet-18 as backbone.

Background Post-stroke dementia (PSD), a common complication, diminishes rehabilitation efficacy and affects disease prognosis in stroke patients. Many factors may be related to PSD, including demographic, comorbidities, and examination characteristics. However, most existing methods are qualitative evaluations of independent factors, which ignore the interaction amongst various factors. Therefore, the purpose of this study is to explore the applicability of machine learning (ML) methods for predicting PSD. Methods 9 acceptable features were screened out by the Spearman correlation analysis and Boruta algorithm. We developed and evaluated 8 ML models: logistic regression, elastic net, k-nearest neighbors, decision tree, extreme gradient boosting, support vector machine, random forest, and multilayer perceptron. Results A total of 539 stroke patients were included in this study. Among the 8 models used to predict PSD, extreme gradient boosting and random forest showed the highest area under the curve (AUC) of the receiver operating characteristic curve (ROC), with values of 0.7287 and 0.7285, respectively. The most important features for predicting PSD included age, high sensitivity C-reactive protein, stroke side and location, and the occurrence of cerebral hemorrhage. Conclusion Our findings suggest that ML models, especially extreme gradient boosting, can best predict the risk of PSD.

Discovering meaningful face morphing is critical for applications in image synthesis. Traditional unsupervised methods rely on global or layer‐wise representations, neglecting finer local details and thus limiting the control over specific facial attributes. In this work, we introduce an improved unsupervised approach that leverages contrastive learning and K‐means clustering to learn both layer‐wise and local features (LLF) in the latent space of StyleGAN. Our method segments latent representations into multiple local components across different layers, enabling fine‐grained control over attributes such as hair, eyes, and mouth. Experimental results demonstrate that LLF outperforms existing methods by providing more interpretable facial transformations while preserving high image realism, offering a promising solution for enhanced unsupervised face morphing applications. The code is available at https://github.com/disanda/LLF .