Tibetan language processing is crucial for preserving its rich cultural heritage and reducing communication barriers between different languages. However, as a low-resource language, the development of Tibetan natural language processing has lagged ...

We proposed a novel underwater acoustic ranging scheme based on a single smartphone. To achieve this goal, we analyzed the complexity of the underwater environment. In addressing the underwater sound speed issue, we selected an appropriate signal ranging ...

Recent innovations have revealed the potential of backscatter to enable simultaneous analog computation and wireless communication directly on RF signals. However, conventional backscatter structures rely on switches and impedance circuits and have ...

Fully Homomorphic Encryption (FHE) is a key technology enabling privacy-preserving computing. However, the fundamental challenge of FHE is its inefficiency, due primarily to the underlying polynomial computations with high computation complexity and ...

The classification of Synthetic Aperture Radar (SAR) ships is a challenging task due to the small inter-class differences and large intra-class variance. Previous methods have used multiscale feature fusion to solve this problem, but most of them ...

Hierarchical fine-grained visual classification assigns multi-granularity labels to each object, forming a tree hierarchy. However, how to minimize the impact of coarse-grained classification errors on fine-grained classification and achieve high ...

Filter pruning (FP) is an effective method for reducing the computational costs of convolutional neural networks, and herein, the most critical task involves evaluating the significance of each convolutional filter and eliminating the less ...

• Filter pruning considers both the magnitude and correlation information.
• Cross-filter-independence-based metric increases efficiency and lowers costs.
• Asymptotic pruning ratio progressively concentrates training information.

In this paper, the Lagrange stability and passivity of a class of discrete-time stochastic Markovian switching neural networks with mixed delays are studied. The mixed delays include time-varying transmission and distribution delays. Global ...

• Lagrange stability and passivity of discrete-time SM-SNNs with mixed delays are studied.
• The time-varying transmission and distribution delays are involved.
• Global exponential Lagrange stability criterion and passivity criterion in ...

Cross-silo federated learning (FL) adopts various cryptographic operations to preserve data privacy, which introduces significant performance overhead. In this paper, we identify nine widely-used cryptographic operations and design an efficient hardware ...

In this paper, a GPU-based explicit Runge-Kutta flow solver is extended with Message Passing Interface (MPI) parallelization. The data at MPI boundaries are first packed on the Graphics Processing Unit (GPU) memory and then transferred to the Central ...

• The utilization of machine learning approach.
• Compressive strength and sensitivity analysis of fly ash composite foam concrete.
• Development of eight machine learning models for estimating measured compressive strength.
• SVM ...

This study aims to propose a reliable machine learning model for predicting the compressive strength of fly ash composite foam concrete (FFC), improving the waste of work time, cost and resources due to over-testing. Firstly, 320 groups of FFC ...

Display Omitted

Coronavirus disease 2019 (COVID-19) is an acute disease, which can rapidly become severe. Hence, it is of great significance to realize the automatic diagnosis of COVID-19. However, existing models are often inapplicable for fusing patients’ ...

With the rapid development of the global renewable energy source field, the importance of dynamic index processing technology in distributed energy systems has become more and more obvious. To better improve the real‐time dynamic interaction ...

This paper is devoted to the multistability problem for complex-valued recurrent neural networks (CVRNNs) with a specific class of piecewise nonlinear activation functions. Firstly, a general class of piecewise nonlinear activation functions is ...

Evaluation is a systematic approach to assessing how well a system achieves its intended purpose. Federated learning (FL) is a novel paradigm for privacy-preserving machine learning that allows multiple parties to collaboratively train models without ...

In order to solve the two-player Stackelberg game for the continuous-time nonlinear stochastic system, using the Takagi&#x2013;Sugeno (T-S) fuzzy stochastic model, this paper defines the novel <inline-formula><tex-math notation="LaTeX">$Q$</tex-math></...

Session-based recommendation predicts users' future interests from previous interactions in a session. Despite the memorizing of historical samples, the request of unlearning, i.e., to remove the effect of certain training samples, also occurs for ...

Excessive stress generally leads to degraded driving performance, which increases the risk of road accidents. Therefore, real-time driver stress detection is of great significance to improve road safety. To this end, this paper proposes a deep ...

Cloud manufacturing is a rapidly growing trend in modern manufacturing, which has transformed the traditional operations and value chain structure of enterprises. It is crucial to develop a rational and effective trading mechanism of cloud ...