A Performance Evaluation of Classic Convolutional Neural Networks for 2D and 3D Palmprint and Palm Vein Recognition

Palmprint recognition and palm vein recognition are two emerging biometrics technologies. In the past two decades, many traditional methods have been proposed for palmprint recognition and palm vein recognition, and have achieved impressive results. However, the research on deep learning-based palmprint recognition and palm vein recognition is still very preliminary. In this paper, in order to investigate the problem of deep learning based 2D and 3D palmprint recognition and palm vein recognition in-depth, we conduct performance evaluation of seventeen representative and classic convolutional neural networks (CNNs) on one 3D palmprint database, five 2D palmprint databases and two palm vein databases. A lot of experiments have been carried out in the conditions of different network structures, different learning rates, and different numbers of network layers. We have also conducted experiments on both separate data mode and mixed data mode. Experimental results show that these classic CNNs can achieve promising recognition results, and the recognition performance of recently proposed CNNs is better. Particularly, among classic CNNs, one of the recently proposed classic CNNs, i.e., EfficientNet achieves the best recognition accuracy. However, the recognition performance of classic CNNs is still slightly worse than that of some traditional recognition methods.

     

Research on Action Strategies and Simulations of DRL and MCTS-based Intelligent Round Game

International Journal of Control, Automation and Systems - The reinforcement learning problem of complex action control in multiplayer online battlefield games has brought considerable interest in...     

Modeling and Control of Hybrid-driven Gliding Motion for an Underwater Gliding Snake-like Robot

International Journal of Control, Automation and Systems - An underwater gliding snake-like robot (UGSR) combines the advantages of an underwater glider (UG) and an underwater snake-like robot...     

Actuator and Sensor Fault Detection and Isolation for Uncertain Switched Nonlinear System Based on Sliding Mode Observers

International Journal of Control, Automation and Systems - In this paper, we discuss actuator fault and sensor fault detection and isolation (FDI) problems for a class of switched nonlinear systems...     

A brief review on α-zirconium phosphate intercalation compounds and nano-composites

The layer structured zirconium phosphate(Zr P) can be intercalated with atoms, molecules, small organic groups and even polymers. The structures and properties of the Zr P intercalation compounds can be deliberately tuned, leading to promising potential applications in many fields. This article provides a brief review on the experimental results of the Zr P intercalation compounds, with the focus on the polymer/a-zirconium phosphate (α-Zr P) nano-composites. The computer simulations of the Zr P intercalation compounds at the atomic level play a significant role in designing and understanding the properties of Zr P, and in the promotion of the applications of compounds.     

Influence of Cryomilling on the Morphology and Composition of the Oxide Scales Formed on HVOF CoNiCrAlY Coatings

Commercially available, gas-atomized CoNiCrAlY powder was cryomilled to produce powder with nanocrystalline grains. The cryomilled powder and conventional gas-atomized powder were thermally sprayed using the HVOF process to prepare two coatings with fine-grain (～15 nm) and coarse-grain (～1 μm) microstructure, respectively. The two coatings were isothermally oxidized in air at 1000° C for up to 330 hr. The morphology and composition of the oxide scales formed on the two coatings were compared with each other. The results indicate that, while a fine-grain microstructure can promote the formation of a pure alumina layer on the coating by increasing the Al diffusion rate toward the surface, it can also accelerate the Al depletion by increasing the Al diffusion rate toward the substrate, which results in the formation of non-alumina oxides after long-term oxidation. The mechanisms governing the oxide formation are discussed in terms of atomic diffusion and thermodynamic stability.     

Microstructural Investigation of Protective and Non-Protective Oxides on 11% Chromium Steel

FIB, SEM and STEM/EDX were used to investigate X20 stainless-steel samples exposed to dry O₂, or O₂ containing 40% H₂O, with a flow velocity of 0.5 cm/s or 5 cm/s, for 168 hr or 336 hr at 600°C. Thin protective Cr-rich (Cr,Fe)₂O₃ was maintained on the samples exposed to dry O₂, even after 336 hr, and on the sample exposed to O₂/H₂O mixture with the low-flow velocity (0.5 cm/s) for 168 hr. The oxide scale formed in the latter environment contained less Cr, due to Cr loss through CrO₂(OH)₂ evaporation. Breakaway oxidation occurred on the samples exposed in high-gas-flow velocity for shorter time (168 hr) or in low-gas-flow velocity (0.5 cm/s) for longer time (336 hr). The breakaway scales featured a two-layered structure: an outward-growing oxide “island” consisting of almost pure hematite (α-Fe₂O₃), and an inward-growing oxide “crater” consisting of (Cr,Fe)₃O₄. The transition from a thin protective (Cr,Fe)₂O₃ scale to a non-protective thick scale on this martensitic/ferritic steel originated locally and was followed by rapid oxide growth, resulting in a thick scale that covered the whole sample surface.     

保温条件下过共晶Al-Si合金半固态浆料的组织演变

研究了保温时间和保温温度对电磁搅拌ZL117合金半固态浆料稳定性的影响.试验结果表明：半固态浆料中初生Si的颗粒直径随着保温时间的延长而逐渐增大,但在前15 min内增长速度比较缓慢,15 min后增长较快;随着保温温度的升高而缓慢增大;初生Si的形状系数随着保温时间的延长而变得越来越大,但也在前15 min内变化较为缓慢,15 min后变大速度突然加快;初生Si的形状系数在620 ℃下保温时最小,在610～620 ℃之间随着保温温度的升高而缓慢变小;在620～650 ℃之间随着保温温度的升高而逐渐增加.     

A modular designed bolt tightening shaft based on adaptive fuzzy backstepping control

This paper presents a modular designed autonomous bolt tightening shaft system with an adaptive fuzzy backstepping control approach developed for it. The bolt tightening shaft is designed for the autonomous bolt tightening operation, which has huge potential for industry application. Due to the inherent nonlinear and uncertain properties, the bolt tightening shaft and the bolt tightening process are mathematically modeled as an uncertain strict feedback system. With the adaptive backstepping and approximation property of fuzzy logic system, the controller is recursively designed. Based on the Lyapunov stability theorem, all signals in the closed-loop system are proved to be uniformly ultimately bounded and the torque tracking error exponentially converges to a small residue. And the effectiveness and performance of the proposed autonomous system are verified by the simulation and experiment results on the bolt tightening shaft system.