Neural Processing Letters

Semantic segmentation of large unstructured 3D point clouds is important problem for 3D object recognition which in turn is essential to solving more complex tasks such as scene understanding. The problem is highly challenging owing to large scale ...

This paper aims to restore a clear image at high resolution from a low-resolution and motion-blurred image. To this end, we propose an end-to-end neural network named P²GAN containing deblurring and super-resolution modules with pixel-level and ...

This paper is concerned with the problem of extended dissipativity performance for a class of delayed discrete-time neural networks (DNNs) subject to state-feedback observer-based control design. To achieve this, a new improved summation based ...

The success of these meta-learning methods in few-shot bearing fault diagnosis depends strictly on the assumption that the meta-training set and the meta-testing set share the same distribution, which inevitably leads to undesirable performance ...

When used for small-scale datasets classification tasks, deep neural networks are difficult to train, which results in the network not extracting useful features and the low accuracy of network. This paper proposes a method called Enhanced ...

Alzheimer’s disease (AD) is the most common cause of dementia and threatens the health of millions of people. Early stage diagnosis of AD is critical for improving clinical outcomes and longitudinal magnetic resonance imaging (MRI) data collection ...

The feature-based transfer learning method has become popular for transferred daily activity recognition in heterogeneous smart home environment since the feature-based transfer learning can reduce the difference between the source smart home ...

Siamese network has been proven to achieve excellent results for visual object tracking where the SiamFC(Fully-Convolutional)is among the most well-known seminar work. Recently, with the successful application of the Region Proposal Network (RPN) ...

A simple yet effective architectural design of radial basis function neural networks (RBFNN) makes them amongst the most popular conventional neural networks. The current generation of radial basis function neural network is equipped with multiple ...

Channel pruning is one of the main methods of model compression for the deep neural network. Some of the existing pruning methods manually set parameters based on experience, which is very time-consuming, and pruning channels by greedy algorithms ...

Classification in hyperspectral remote sensing images (HRSIs) is a challenging process in image analysis and one of the most popular topics. In recent years, many methods have been proposed to solve the HRSIs classification problem. Compared to ...

In this paper, a novel robust $L_1$-norm based twin bounded support vector machine with pinball loss- having regularization term, scatter loss and misclassification loss- is proposed to enhance robustness in the presence of feature noise and ...${}_{\mathrm{}}$

To deal with the insufficient feedbacks and dynamics of individual arrival and item popularity in online recommender, collaborative multi-armed bandit (MAB) schemes intentionally utilize the explicitly known or implicitly inferred social ...

This paper proposes a learning-based algorithm to imitate the head-on obstacle avoidance behavior of humans by the mobile robot. Head-on collision avoidance is the most complex behavior where someone comes directly towards the robot and the robot ...

Named entity recognition aims to identify and mark entities with specific meanings in text. It is a key technology to further extract entity relationships and mine other potential information in natural language processing. At present, the methods ...

Due to the excellent performance of deep learning, more and more image denoising methods based on convolutional neural networks (CNN) are proposed, including dilated convolution method and multi-scale convolution method. A fundamental issue is how ...

Solar PhotoVoltaic is one among the majority of key techniques for moving away from fossil fuels and toward renewable energy. Solar prediction is an efficient approach for improving the process of an electrical method for combining a huge number ...

Neuromorphic computation processes sensors output in the spiking domain, which presents constraints in many cases when converting information to spikes, loosing, as example, temporal accuracy. This paper presents a spike-based system to adapt ...$$

Multi-label text classification task is one of the research hotspots in the field of natural language processing. However, most of the existing multi-label text classification models are only suitable for scenarios with a small number of labels ...

Quality assessment of real, user-generated content videos lacking reference videos is a challenging problem. For such scenarios, we propose an objective quality assessment method for no-reference video from the spatio-temporal perception ...

To maximize the accuracy of the news headline generation model, increase the attention ratio of the model to significant information, and avoid duplication of generated headlines and problems unrelated to feature semantics, we proposed a topic ...

In this paper, the exponential stabilization problem is investigated for delayed neural networks (DNNs) via aperiodically intermittent control. First, a suitable time-dependent functional is constructed in view of the features of intermittent ...

Multivariate time series classification is a critical problem in data mining with broad applications. It requires harnessing the inter-relationship of multiple variables and various ranges of temporal dependencies to assign the correct ...

Class labels in multi-label datasets are only associated with a very small fraction of the data instances leading to a class imbalance problem. There exist multi-label learning algorithms that handle the datasets’ class imbalance issue by ...

Person re-identification (re-id) expects to find a picture according to a few clues that refer to the same pedestrian from an image database caught from different locations. Previous studies show that the exploration of local features may help for ...

As an important part of intelligent surveillance systems, person re-identification (re-ID) has a wide range of application prospects in smart cities. However, due to occlusion, viewpoint variation, and background shift, the misalignment problem ...$$

Vision Transformer (ViT) has attracted tremendous attention and achieved remarkable success on high-level visual tasks. However, ViT relies on costly pre-training on large external datasets and is strict in data and calculations, making it an ...

The Real-time wearable Electrocardiogram (ECG) monitoring device is a perfect choice for assisting in detecting cardiovascular disease. A novel ECG beat classification algorithm is presented for continuous heart monitoring on low-processing-...$\mathrm{}\mathrm{}\mathrm{}$

Gated Recurrent Neural Networks (RNNs) such as LSTM and GRU have been highly effective in handling sequential time series data in recent years. Although Gated RNNs have an inherent ability to learn complex temporal dynamics, there is potential for ...

Object tracking has made remarkable progress in the past few years. But most advanced trackers are becoming more expensive, which limits their deployment in mobile devices with limited resources. In addition, the current popular tracker realizes ...