Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
High-performance convolutional neural network emulation via FPGA-integrated memristive circuitry
AbstractAlthough memristors address the potential data flow and memory access bottlenecks in traditional von Neumann architectures by moving computational operations into the storage elements, thereby improving computational efficiency and reducing ...
- ArticleJuly 2024
Light-Weight SA-BNN: High-Precision Olfactory Recognition of Binary Neural Networks
AbstractWith the development of artificial intelligence, electronic nose technology, which simulates human olfaction using sensors and pattern recognition techniques, is becoming increasingly mature and widely applied in various fields. Currently, the ...
- ArticleJuly 2024
Improved Memristive Binarized Neural Networks Using Transformer_DCBNN Architecture with CBAM Attention Mechanism
AbstractAt present network compression and hardware deployment have become a hot research topic. For network compression, binary neural networks (BNNs) use binary weights and activation function parameters instead of full precision values. However, due to ...
- ArticleJuly 2024
A Visual Inertial SLAM Method for Fusing Point and Line Features
AbstractThe current SLAM methods generally have some drawbacks: such as poor stability and long time-consuming SLAM tasks; in order to solve the problem of poor positioning accuracy of SLAM tasks due to the drawbacks of these SLAM methods, the quality and ...
- ArticleJuly 2024
A Robust Visual SLAM System in Dynamic Environment
AbstractSimultaneous Localization and Mapping (SLAM) is vital for the navigation of autonomous robots in unknown environments. Current SLAM systems have made progress but still struggle to balance accuracy, robustness, and real-time processing in dynamic ...
-
- research-articleJuly 2024
A multilevel interleaved group attention-based convolutional network for gas detection via an electronic nose system
Engineering Applications of Artificial Intelligence (EAAI), Volume 133, Issue PAhttps://doi.org/10.1016/j.engappai.2024.108038AbstractIn this paper, an E-nose system for industrial exhaust detection is established and a novel deep learning model called the multilevel interleaved group attention-based convolutional network (MIGACN) is proposed for processing sensor array signals ...
- research-articleJuly 2024
Adaptive finite-time passivity and synchronization of coupled fractional-order memristive neural networks with multi-state couplings
AbstractIn this article, the adaptive finite-time passivity (FTP) and finite-time synchronization (FTS) of coupled fractional-order memristive neural networks with multi-state couplings (CFMNNMCs) are investigated. Firstly, a sufficient condition for ...
- research-articleMarch 2024
Reconfigurable Stateful Logic Circuit With Cu/CuI/Pt Memristors for In-Memory Computing
IEEE Transactions on Very Large Scale Integration (VLSI) Systems (ITVL), Volume 32, Issue 5Pages 835–847https://doi.org/10.1109/TVLSI.2024.3370176A memristive stateful logic circuit can provide a non-von Neumann computing architecture for integrating computation and storage. However, the stateful logic circuit based on memristors presents challenges in terms of computational complexity, ...
- research-articleApril 2024
Lightweight spiking neural network training based on spike timing dependent backpropagation
AbstractSpiking neural networks are energy efficient and biological interpretability, communicating through sparse, asynchronous spikes, which makes them suitable for neuromorphic hardware. However, due to the nature of binary weights and spike trains in ...
- research-articleApril 2024
Exponential synchronization of uncertain chaotic inertial neural networks by guaranteed cost intermittent control
AbstractThis paper utilizes the guaranteed cost intermittent control to achieve exponential synchronization of uncertain chaotic inertial neural networks (UCINNs). Concretely, the second-order UCINNs are first transformed into the first-order neural ...
- research-articleFebruary 2024
Design and FPGA Implementation of Grid-Scroll Hamiltonian Conservative Chaotic Flows With a Line Equilibrium
IEEE Transactions on Very Large Scale Integration (VLSI) Systems (ITVL), Volume 32, Issue 4Pages 658–668https://doi.org/10.1109/TVLSI.2024.3361889Although multiscroll attractors in dissipative chaotic systems (DCSs) have complex properties, they may be subject to reconstruction attacks in the field of information security. Conservative chaotic systems (CCSs) have no attractors and can effectively ...
- research-articleDecember 2023
A Hybrid Weight Quantization Strategy for Memristive Neural Networks
AbstractDue to the ability to store data and process information, the memristor-based neuromorphic system has attracted extensive attention. Its efficient parallel computing approach allows it to implement neural networks in hardware. However, due to the ...
Highlights- Obtained the pulse conductance relations from modeling the tantalum oxide memristor.
- A weight mapping rule based on the memristor array is proposed.
- Hybrid quantization schemes are proposed to improve the performance.
- research-articleFebruary 2024
SAGAN: Deep semantic-aware generative adversarial network for unsupervised image enhancement
AbstractLow-light image enhancement (LLIE) is a common pretext task for computer vision, which aims to adjust the luminance of the low-light image to obtain the normal-light image. At present, unsupervised LLIE has been developed. However, its ...
- research-articleSeptember 2023
- research-articleAugust 2023
A 6.435-nW, 26.2-ppm/°C hybrid bandgap reference with stacked ΔVGS compensation in sub-threshold region
AbstractThis paper illustrates a methodology to design an ultra-low power hybrid bandgap reference (HBR) with high accuracy to counteract the effect of temperature using single BJT and MOSFETs working in subthreshold region. Based on ...
- research-articleJuly 2023
Proportional stochastic generalized Lotka–Volterra model with an application to learning microbial community structures
Applied Mathematics and Computation (APMC), Volume 448, Issue Chttps://doi.org/10.1016/j.amc.2023.127932Highlights- A new proportional stochastic generalized Lotka–Volterra model is proposed.
- We ...
Inferring microbial community structure based on temporal metagenomics data is an important goal in microbiome studies. The deterministic generalized Lotka–Volterra (GLV) differential equations have been commonly used to model the ...
- research-articleMay 2023
An Encryption Scheme Using Multi-Scroll Memristive Chaotic System
CACML '23: Proceedings of the 2023 2nd Asia Conference on Algorithms, Computing and Machine LearningPages 553–560https://doi.org/10.1145/3590003.3590105In this paper, a novel multi-scroll memristive chaotic system is designed based on Chua's system via introducing a nonlinear memristor. The dynamics of this system is analyzed based on bifurcation diagrams, Lyapunov exponents and phase diagrams. ...
- research-articleJanuary 2023
Memristive FHN spiking neuron model and brain-inspired threshold logic computing
Neurocomputing (NEUROC), Volume 517, Issue CPages 93–105https://doi.org/10.1016/j.neucom.2022.08.056AbstractThe FitzHugh-Nagumo (FHN) spiking model has rich dynamics behaviors and can imitate the firing process of a neuron. The memristor is a nonvolatile and resistance tunable device, which gradually becomes a potential candidate for ...
- research-articleJanuary 2023
Research on the construction of enterprise human resource allocation model based on multi-objective particle swarm optimisation algorithm
International Journal of Wireless and Mobile Computing (IJWMC), Volume 24, Issue 1Pages 74–82https://doi.org/10.1504/ijwmc.2023.129090The irrationality of human resource allocation and the unfitness of talent positions make it difficult for the original human resource management model of the enterprise to give full play to its actual effect to a certain extent, which has a negative ...
- research-articleNovember 2022
Global Well-Posedness of Stochastic Nematic Liquid Crystals with Random Initial and Boundary Conditions Driven by Multiplicative Noise
Applied Mathematics and Optimization (APMO), Volume 87, Issue 1https://doi.org/10.1007/s00245-022-09909-5AbstractThe flow of nematic liquid crystals can be described by a highly nonlinear stochastic hydrodynamical model, thus is often influenced by random fluctuations, such as uncertainty in specifying initial conditions and boundary conditions. In this ...