Neurocomputing

Recently, infrared object detection (IOD) has been extensively studied due to the rapid growth of deep neural networks (DNNs). An adversarial attack using imperceptible perturbation can dramatically deteriorate the performance of DNNs. ...

In recent times, deep learning models have achieved state-of-the-art performances in image classification. However, the classification and generalization ability of most achievements have highly relied on the availability of large-...

Differentiable search methods can be used to find effective network architectures fast. However, these approaches are accompanied by low accuracy when evaluating a searched architecture, especially evaluating a searched architecture ...

• We propose a causal inference framework for stochastic intervention estimation (SIE).

Causal inference methods are widely applied in various decision-making domains such as precision medicine, optimal policy and economics. The main focus of causal inference is the treatment effect estimation of intervention strategies, ...

The attention mechanism of computer vision represented by a non-local network improves the performance of numerous vision tasks while bringing computational burden for deployment Wang et al. (2018). In this work, we explore to release ...

Recent research that applies Transformer-based architectures to image captioning has resulted in state-of-the-art image captioning performance, capitalising on the success of Transformers on natural language tasks. Unfortunately, ...

This dissertation investigates the H ∞ state estimation for static neural networks with time-varying delays. In order to fully utilize delay information, a innovative Lyapunov–Krasovskii (L-K) functional is developed, which includes ...

Segmentation of Peripherally Inserted Central Catheter (PICC) from chest X-rays (CXR) is the first step towards automatic PICC position confirmation. PICC is a relatively small and thin tube that occupies only a small proportion on the ...

Pedestrian detection has achieved significant progress in recent years. Though promising results have been obtained on standard pedestrians, it remains challenging to detect pedestrians in various occlusion situations. In this paper, ...

Recently, face hallucination, also termed face super-resolution (SR), has been widely studied and achieved significant progress. The algorithm based on manifold learning is one of the primary methods for SR. However, when recovering ...

The architecture of AND/OR fuzzy neural networks exhibits outstanding learning abilities and significant interpretation capabilities. However, AND/OR networks suffer from structure-related problems namely low efficiency and slow ...

In recent years, classical fuzzy clustering-based neural networks (FCNNs) have been successfully applied to regression tasks. The determination of the parameters such as cluster centers of the existing hard c-means (HCM) or fuzzy c-...

This paper presents a novel framework of self-supervised learning for video representation. Inspired by Contrastive Predictive Coding and Self-attention, we make the following contributions: First, we propose the Contrastive Predictive ...

Implementations of machine learning models in resource-limited embedded systems are becoming highly desired. This has led to a need for resource-efficient building blocks for computing the mathematical operations required for neural ...

Display Omitted

• Investigates a novel EEG fading data classification problem.
• Proposes a novel ...

In electroencephalogram (EEG) signal analysis, data fading problem exists from signal production to collection by brain-computer interface (BCI) device, which can be raised by BCI device deficiency, dynamic network limitation and ...

• Forming less complex and small-size ensembles via considering instance selection and ensemble selection of classifiers.

Classifier ensembles are characterized by the high quality of classification, thanks to their generalizing ability. Most existing ensemble algorithms use all learning samples to learn the base classifiers that may negatively impact the ...

To address the problem of efficient task for the fully-actuated aerial manipulation system, the flight platform control scheme based on neural networks embedding is proposed. We embed the neural networks controllers (NNC) into some ...

• A CFD model optimization procedure is proposed.
• The surrogate assisted ...

As restrictions on NOx (nitrogen oxides) emission become increasingly stringent, many efforts have been put into the development of NOx control strategies. The burner structures of the heating furnace can affect NOx formation by the ...

• A novel dual-spectral semantic segmentation network with channel-coordinate attention feature-fusion module is proposed for semantic segmentation of ...

Dual-spectral (RGB-thermal) semantic segmentation is a fundamental task for visual perception of autonomous driving in harsh imaging environments (such as darkness, rain, and fog). In recent years, the encoder-decoder dual-spectral ...

• Heterogeneous networks with both heterogeneous coefficients and heterogeneous nonlinear functions are investigated.

The target of this paper is studying the problem of quasi-synchronization of heterogeneous Lur’e networks with uncertain parameters and impulsive effect. Considering the heterogeneity of Lur’e networks, quasi-synchronization instead of ...

Box localization that aims at localizing the position of the box plays a significant role in the application of bin picking. Accurate box localization is still a challenging problem. The boxes are stacked tightly with all kinds of ...

Display Omitted

• A distributed algorithm is proposed for the generalized Nash equilibrium seeking.

In this paper, a distributed optimization algorithm is proposed for aggregative game with coupled constraints. Based on the singular perturbation system, the generalized Nash equilibrium is sought by a group of agents. By employing the ...

In this paper, a double sparse low-rank decomposition method is proposed to defect detection for complex irregular printed fabrics. Firstly, a low rank decomposition model with double sparsity is established by taking the sparse ...

One of the elements of the modern trade and services market is a business chain solution (chain store/retail chain). An example of a business chain is, e.g., a restaurant chain, where each restaurant in the chain has the same decor, ...