The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well and past multiple driving (exogenous) series, has been studied for decades. Despite fact that various NARX models have developed, few them can capture long-term temporal dependencies appropriately select relevant to make predictions. In this paper, we propose dual-stage attention-based recurrent neural network (DA-RNN) address these two issues. first...

In this paper, we introduce Cellular Automata-a dynamic evolution model to intuitively detect the salient object. First, construct a background-based map using color and space contrast with clustered boundary seeds. Then, novel propagation mechanism dependent on Automata is proposed exploit intrinsic relevance of similar regions through interactions neighbors. Impact factor matrix coherence are constructed balance influential power towards each cell's next state. The saliency values all...

The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well and past multiple driving (exogenous) series, has been studied for decades. Despite fact that various NARX models have developed, few them can capture long-term temporal dependencies appropriately select relevant to make predictions. In this paper, we propose dual-stage attention-based recurrent neural network (DA-RNN) address these two issues. first...

Efficient detection of targets immersed in a complex background with low signal-to-clutter ratio (SCR) is very important infrared search and tracking (IRST) applications. In this paper, we address the target problem terms local image segmentation propose novel small algorithm derived from facet kernel random walker (RW) which includes four main stages. First, since RW suitable for images less noises, order-statistic mean filtering are applied to remove pixel-sized noises high brightness...

Identifying feature correspondences between multimodal images is facing enormous challenges because of the significant differences both in radiation and geometry. To address these problems, we propose a novel matching method (named R <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> FD ) that robust to rotation differences, which consists repeatable detector rotation-invariant descriptor. In first stage, called Multi-channel...

Image matching is a key preprocessing step for the integrated application of synthetic aperture radar (SAR) and optical images. Due to significant nonlinear intensity differences between such images, automatic them still quite challenging. Recently, structure features have been effectively applied SAR-to-optical image because their robustness differences. However, designed by handcraft are limited achieve further improvement. Accordingly, this letter employs deep learning technique refine...

For remote sensing object detection, fusing the optimal feature information automatically and overcoming sensitivity to adapt multi-scale objects remains a significant challenge for existing convolutional neural networks. Given this, we develop network model with an adaptive attention fusion mechanism (AAFM). The is proposed based on backbone of EfficientDet. Firstly, according characteristics distribution in datasets, stitcher applied make one image containing various scales. Such process...

To date, although numerous methods of Change detection (CD) in remote sensing images have been proposed, accurately identifying changes is still a great challenge, due to the difficulties effectively modeling features from ground objects with different patterns. In this paper, novel CD method based on graph convolutional network (GCN) and multiscale object-based technique proposed for both homogeneous heterogeneous images. First, object-wise high level are obtained through pre-trained U-net...

Prompt engineering is a technique that involves augmenting large pre-trained model with task-specific hints, known as prompts, to adapt the new tasks. Prompts can be created manually natural language instructions or generated automatically either vector representations. enables ability perform predictions based solely on prompts without updating parameters, and easier application of models in real-world In past years, has been well-studied processing. Recently, it also intensively studied...

Deep learning-based change detection (CD) using remote sensing images has received increasing attention in recent years. However, how to effectively extract and fuse the deep features of bi-temporal for improving accuracy CD is still a challenge. To address that, novel adjacent-level feature fusion network with 3D convolution (named AFCF3D-Net) proposed this article. First, through inner property convolution, we design new way that can simultaneously information from images. Then, alleviate...

NLP models are shown to suffer from robustness issues, i.e., a model’s prediction can be easily changed under small perturbations the input. In this work, we present Controlled Adversarial Text Generation (CAT-Gen) model that, given an input text, generates adversarial texts through controllable attributes that known invariant task labels. For example, in order attack for sentiment classification over product reviews, use categories as attribute which would not change of reviews. Experiments...

We study the problem of object detection in remote sensing images. As a simple but effective feature extractor, Feature Pyramid Network (FPN) has been widely used several generic vision tasks. However, it still faces some challenges when for detection, as objects images usually exhibit variable shapes, orientations, and sizes. To this end, we propose dedicated detector based on FPN architecture to achieve accurate Specifically, considering shapes orientations objects, first replace original...

In this letter, a novel object detection method based on feature pyramid network (FPN) is proposed to improve the performance of remote sensing objects. First, since information in background regions may interfere with detection, multi-scale deformable attention module (MSDAM) designed and added top backbone FPN make suppress features while highlight target features. The MSDAM generates maps from receptive fields, thus can fit objects various shapes sizes better predict more precise for...

Abstract Remaining useful life (RUL) prediction of rolling bearing plays an important role in maintaining the safety equipment. However, data collected from industrial scene often contains noises, which affects RUL precision bearing. To overcome above problem, a data-driven scheme for is proposed based on convolutional denoising autoencoder (CDAE) and bidirectional long short-term memory network (Bi-LSTM). In method, vibration signal directly used as input prognostics model. Then, model CDAE...

Abstract Glutamic acid decarboxylase, the enzyme required for GABA synthesis, exists as distinct isoforms, which have recently been found to be encoded by different genes. The relative expression of messenger RNAs encoding two isoforms glutamic decarboxylase (M r 67,000 and M 65,000) was measured at single‐cell level in neurons rat basal ganglia with situ hybridization histochemistry. Both were expressed striatum, pallidum, substantia nigra pars reticulata, but marked differences labelling...

Deep subspace clustering network has shown its effectiveness in hyperspectral image (HSI) clustering. However, there are two major challenges that need to be addressed: 1) lack of effective supervision for feature learning; and 2) negative effect caused by the high redundancy global dictionary atoms. In this article, we propose an end-to-end trainable HSI Specifically, ensure extracted features well-suited subsequent clustering, cluster assignments with confidence employed as pseudo-labels...

Quantization plays a crucial role in deploying neural network models on resource-limited hardware. However, current quantization methods have issues like large accuracy loss and poor generalization for complex tasks. These pose obstacles to the practical application of deep learning language smart systems. The main problem is our limited understanding quantization&amp;#039;s effect accuracy, there also need more effective approaches evaluate performance quantized models. To address these...

Quantization plays a crucial role in deploying neural network models on resource-limited hardware. However, current quantization methods have issues like the large accuracy loss and poor generalization for complex tasks. These pose obstacles to practical application of deep learning language smart systems. The main problem is our limited understanding quantization’s effect accuracy, there also need more effective approaches evaluate performance quantized models. To address these concerns, we...

This paper presents a deep neural network (DNN)-embedded mixed-integer linear programming (MILP) model for fault prediction and production optimization in tablet pressing machines. The DNN predicts the probability of failures during process by analyzing key operational parameters such as pressure, temperature, humidity, speed, vibration, number maintenance cycles. MILP optimizes temperature humidity settings, schedules, planning to maximize total profit while minimizing penalties pressing,...

A refined YOLOv8A-SD model is introduced to address pig detection challenges in aerial surveillance of farms. The incorporates the ADown attention mechanism and a dual-task strategy combining segmentation tasks. Testing was conducted using top-view footage from large-scale farm Sichuan, with 924 images for training, 216 validation, 2985 1512 validation. achieved 96.1% Precision 96.3% mAP50 tasks while maintaining strong performance (IoU: 83.1%). key finding reveals that training original...