Network sparsification serves as an effective technique to accelerate Deep Neural Network (DNN) inference. However, existing sparsification techniques often rely on structured sparsity, which yields limited benefits. This is primarily due to the ...

Let f ( x , y ) > 0 be a real symmetric function. For a connected graph G, the weight of edge v i v j is equal to the value f ( d i , d j ), where d i is the degree of vertex v i. The degree-based weighted adjacency matrix is defined as A f ( G ),...

Recommendation models based on deep learning are fragile when facing adversarial examples (AE). Adversarial training (AT) is the existing mainstream method to promote the adversarial robustness of recommendation models. However, these AT methods often ...

Reconstructing the 3D shape of objects using limited information from a single image is a complex and necessary task. The existing methods for reconstructing point clouds from a single image haven't effectively addressed the issue of background ...

Display Omitted

• Proposed reconstruct point clouds from single images using spatial and channel attention, and symmetric point cloud encoder.

This article has been retracted: please see Elsevier Policy on Article Withdrawal ().

This article has been retracted at the request of the authors, after they reported methodological errors that compromise ...

Considering the existence of time delay and interval uncertainty, a set‐membership state estimation problem based on zonotopes is studied for discrete‐time switched systems subject to unknown but bounded noises. To conform the actual situation, a ...

Personalized fairness in recommendations has been attracting increasing attention from researchers. The existing works often treat a fairness requirement, represented as a collection of sensitive attributes, as a hyper-parameter, and pursue extreme ...

LiDAR simultaneous localization and mapping (SLAM) system plays a vital role in numerous applications, such as robots and autonomous vehicles. Since the measurement characteristics of the LiDAR sensor, the information obtained in the vertical ...

Spiking neural networks (SNNs) are emerging as energy-efficient alternatives to traditional artificial neural networks (ANNs). Their event-driven information processing significantly reduces computational demands while maintaining competitive ...

Deep Neural Network (DNN) inference consumes significant computing resources and development efforts due to the growing model size. Quantization is a promising technique to reduce the computation and memory cost of DNNs. Most existing quantization ...

Event-driven spiking neural networks (SNNs) have demonstrated significant potential for achieving high energy and area efficiency. However, existing SNN accelerators suffer from issues such as high latency and energy consumption due to serial accumulation-...

In the domain of physical education pedagogy, the orchestration of curricula commonly presents intricate optimization conundrums, the crux of which lies in the efficacious and rational employment of limited resources and temporal allotments. The ...

Accurate and automated segmentation of lesions in brain MRI scans is crucial in diagnostics and treatment planning. Despite the significant achievements of existing approaches, they often require substantial computational resources and fail to fully ...

This paper discusses the event-triggered set-membership state estimation problem for discrete delayed linear systems over sensor networks, where noises are unknown but bounded. For the purpose of saving limited communication resources between ...

• Screening features that passed the hypothesis test were established with reference to the 2019 ESC guidelines for diagnosis and management of acute pulmonary embolism. The data set of the study on pulmonary embolism was established by ...

Pulmonary embolism (PE) is a complex disease with high mortality and morbidity rate, leading to increasing society burden. However, current diagnosis is solely based on symptoms and laboratory data despite its complex ...

The traditional motion recognition method can not accurately recognize the shot beater's motion in the complex environment background in real time, so a basketball shot beater's motion recognition method based on machine vision is designed. An octree ...

Spiking neural networks (SNNs) are energy-efficient alternatives to commonly used deep artificial neural networks (ANNs). However, their sequential computation pattern over multiple time steps makes processing latency a significant hindrance to ...

Hyper-Dimensional Computing (HDC) is a brain-inspired learning framework that is particularly suited to resource-limited edge devices. HDC operates in a high-parallel manner, encoding raw data into hyper-dimensional space, thus enabling efficient ...

Developing early and transferable Network Intrusion Detection Systems (NIDSs) is essential for robust network security. Early detection prevents further damage, while transferable NIDSs enables reuse across diverse networks. For Machine Learning (ML) and ...

Adversarial attacks, widely recognized as significant threats to machine learning (ML) models in computer vision and natural language processing, can have more severe consequences when targeting ML-based Network Intrusion Detection Systems (NIDS). These ...