Neural Processing Letters

In this paper, the finite-time (FNT) cluster synchronization of complex dynamic networks (CDNs) is discussed on the basis of encoding and decoding communication protocol involved in network attacks. Compared with general CDNs, the proposed ...

The human gait sequence contains both spatial and temporal information, and the spatial and temporal information are restricted to different degrees under different views and walking conditions. In this paper, we propose a method based on spatio-...

Single image super-resolution based on deep neural network has been a hot topic in recent years. In this paper, we propose a gated residual and gated convolution network (GRGCN) to deal with super-resolution reconstruction. Gated residual (GR) and ...

Multi-object tracking (MOT) is mainly used for detecting and tracking the object on multi-cameras, which is widely applied in intelligent video surveillance and intelligent security. The process of MOT generally involves three import parts: ...

Deep-learning based methods have achieved great success in the field of Single Image Super-Resolution (SISR) by progressively exploring contextual and deep semantic features. However, existing methods do not make full use of scale-space features, ...

Amidst of all the tumors, breast tumor is the main source for a high incidence mortality rate among women. In the past decades, this mortality rate has tremendously reduced by early detection and diagnosis of the tumors using different modalities. ...${}^{\mathrm{}}$

The current investigation aims at the adaptive consensus issue for a class of nonlinear multiagent systems with time delays and unknown disturbances under a directed graph topology. A novel designed disturbance observer eliminates the impact on ...

The receptive field of convolutional neural networks (CNNs) is focused on the local context, while the transformer receptive field is concerned with the global context. Transformers are the new backbone of computer vision due to their powerful ...

Current visual question answering (VQA) has become a research hotspot in the computer vision and natural language processing field. A core solution of VQA is how to fuse multi-modal features from images and questions. This paper proposes a ...

The aim of this research is to enhance the quality of prenatal ultrasound images by addressing common artifacts such as missing or damaged areas, speckle noise, and other types of distortions that can impede accurate diagnosis. The proposed ...

Colonic polyps are highly correlated with colorectal cancer. Prevention of colorectal cancer is the detection and removal of polyps in the early stages of the disease. But the detection process relies on the physician’s experience and is prone to ...

Traversability analysis is essential for ground robot operations because it allows the incorporation of knowledge about traversable and non-traversable terrains into the robot’s path planning algorithm. It is possible to use aerial data to compute ...

Retinex decomposition is a prevalent solution to low-light image enhancement. It is usually considered as a constrained optimization problem. To improve enhancement performance, the Retinex model is incorporated with various prior constraints, ...

Weakly supervised semantic segmentation (WSSS) can obtain pseudo-semantic masks through a weaker level of supervised labels, reducing the need for costly pixel-level annotations. However, the general class activation map (CAM)-based pseudo-mask ...

A 32-bit floating-point format is often used for the development and training of deep neural networks. Training and inference in deep learning-optimized codecs can result in enormous performance and energy efficiency advantages. However, training ...

Data envelopment analysis (DEA) is one of the non-parametric approaches for evaluating efficiency. The present paper investigates a novel recurrent neural network (RNN) model for solving DEA problems. To the best of our knowledge, there is no ...

Artificial neural networks are widely used for solving engineering design problems of various disciplines due to its simplicity, efficiency, and adaptability. It predicts promising and accurate results. Artificial neural network solves these ...

Due to the complexity of natural language, the current relation extraction methods can no longer meet people’s requirements. Dependency trees have been proved to be able to capture the long-distance relation between the target entity pairs, this ...

At present, there are few studies on the delayed kernel function of hyper-strong kernel. This paper attempts to analyze the stability and bifurcation of neural networks with distributed delayed hyper-strong kernels. Firstly, considering the ...

With the development of data-centric artificial intelligence, more and more people pay attention to the importance of image information quality. Based on the core idea that images in datasets have different intra-class information richness and ...

In this paper, we aim to improve the imaging quality of super-resolution (SR) without increasing the inference time to address the difficulty of trading off between quality and inference time in many existing methods and design a deployment-...

In this paper, the passivity-based state estimation problem is investigated for Markov jump singularly perturbed neural networks, in which the partially known transition rate matrix and the nonlinear characteristics of sensors are considered ...

The ${\mathcal{H}}_{\mathit{\infty }}$ state feedback control problem of Takagi–Sugneo (T–S) fuzzy system with dynamic quantization and event-triggered mechanism is studied in this paper. Based on T–S fuzzy model, a new quantization scheme is proposed to solve the problem of ...${\mathcal{}}_{\mathit{}}$

Unsupervised domain adaptation addresses the problem that model trained on labeled source domains can be transferred to unlabeled target domains, which crucially involves aligning the data distributions in the source and target domains by learning ...

The finite-time synchronization (FTS) is investigated in this paper for delayed fractional-order quaternion-valued Cohen-Grossberg neural networks (FQVCGNNs). First, a fractional-order finite-time stability theorem is established by using the ...

Federated learning is a machine learning paradigm in which decentralized client devices collaboratively train shared model under the coordinating of a central server without sharing local data. Data heterogeneity is one of the major challenges ...

The precise segmentation of lesions can assist doctors to complete efficient disease diagnosis. Unet is widely used in the field of medical image segmentation due to its excellent feature fusion ability. However, the deep network based on Unet has ...

In order to address the issues of slow convergence and susceptibility to falling into the local optimum trap of the original sparrow search algorithm, a novel multi-strategy improved sparrow search algorithm (MSSSA) is proposed. Firstly, an ...

In recent years, multivariate time series prediction has attracted extensive research interests. However, the dynamic changes of the spatial topology and the temporal evolution of multivariate variables bring great challenges to the spatio-...

Extreme learning machine (ELM) is a machine learning technique with simple structure, fast learning speed, and excellent generalization ability, which has received a lot of attention since it was proposed. In order to further improve the sparsity ...