Fingerprint Classification Using Deep Convolutional Neural Network
Issue:
Volume 9, Issue 5, October 2021
Pages:
147-152
Received:
5 August 2021
Accepted:
16 August 2021
Published:
6 September 2021
Abstract: Fingerprint classification is a method of reducing the number of candidates needed by fingerprint recognition systems to determine if a fingerprint picture matches one in the database. Deep learning has gained a lot of attraction in the recent decade including natural language processing, digital image processing, speech recognition, handwritten digit recognition, medical picture assessments, and so on. The subject of this paper is to explore the factors affecting fingerprint classification using a convolutional neural network and to train and test a deep CNN model, The CNN model includes two serial stages, a preprocessing phase which is used to enhance the fingerprint images qualities, and post-processing phase which used to train the classification model. This has been accomplished by designing a new deep convolutional neural network model for this work. The Convolutional neural network model achieved outstanding classification accuracy on the fingerprint. This experiment used the NIST DB4 dataset which contains 4,000 fingerprints images with five labels. Separately, each label of this database comprises almost 800 fingerprint samples with dimension of 512 x 512. To lower the training time required we reduced the fingerprint images up to 200 x 200 dimension. the study achieves 99.2% of classification accuracy with a zero-rejection rate.
Abstract: Fingerprint classification is a method of reducing the number of candidates needed by fingerprint recognition systems to determine if a fingerprint picture matches one in the database. Deep learning has gained a lot of attraction in the recent decade including natural language processing, digital image processing, speech recognition, handwritten di...
Show More
Hierarchical Microchannel Carbons Derived from Biological Phloem Tissues as High-Performance Anode for Lithium-Ion Batteries
Yunlong Liao,
Jiahua Hu,
Zhuang Sun,
Wei Zhang,
Xiaomeng Zhou,
Haijun Zhang
Issue:
Volume 9, Issue 5, October 2021
Pages:
153-160
Received:
29 June 2021
Accepted:
15 July 2021
Published:
15 September 2021
Abstract: With the upgrading of consumption, the existing carbon-based anode materials are facing the major challenges of high preparation cost and low initial Coulomb efficiency. The fast-growing and developed sieve tube network is an inspiration to transform cattail phloem tissue (CPT) into a high-performance carbon-based anode for lithium-ion battery. In this study, porous carbon materials from CPT with abundant microchannel and nanochannel were prepared by a top-down strategy combined with an indispensable passivation process. The sidewall and end of the sieve tube are fully covered by a large number of pore structures and various supporting cells, thus ensuring the stiffness and tensile strength of phloem tissue. And benefiting from the neoteric hierarchical porous structure without Li+ trapping sites, the cells with CPT anode showed high electrochemical performance. For the passivated CPT electrode, the reversible capacity increased to 321.6 mAh/g, and the initial Coulomb efficiency was 1.47 times higher than that of the passivated CPT electrode. The CPT exhibits excellent rate performance under high current, which indicates that the abundant pore structure on the surface of the sieve tube is an effective measure to improve ion diffusion. Besides, the generation mechanism of high-performance CPT is analyzed through microstructure characterization. The improvement of electrochemical performance of CPT in this work has provided a clear strategy for the application of resource-rich natural biomass to electrochemical products.
Abstract: With the upgrading of consumption, the existing carbon-based anode materials are facing the major challenges of high preparation cost and low initial Coulomb efficiency. The fast-growing and developed sieve tube network is an inspiration to transform cattail phloem tissue (CPT) into a high-performance carbon-based anode for lithium-ion battery. In ...
Show More
Generalized Weighted Adaptive Time Delay Estimation Algorithm Based on Minimum Average P Norm
Issue:
Volume 9, Issue 5, October 2021
Pages:
161-169
Received:
22 September 2021
Accepted:
13 October 2021
Published:
16 October 2021
Abstract: The time delay estimation algorithm is one of the important factors of sound source localization. The generalized weighted adaptive time delay estimation algorithm is limited by the environmental conditions of signal and noise, and has great limitations in non-Gaussian environments. In order to make the algorithm suitable for non-Gaussian environments, and to retain the advantages of the algorithm in effectively suppressing harmonics, this paper combines the minimum average P norm (LMP) with the generalized weighting function, and proposes a method based on the minimum average P norm. The generalized weighted adaptive time delay estimation algorithm of the number can make the algorithm suitable for non-Gaussian environments, and for the shortcomings of slow iteration speed and large calculation amount for the minimum average P norm, the Sigmoid function is introduced to further improve the parameter selection in the algorithm. MATLAB simulation experiments show that the algorithm in this paper can effectively suppress the existence of harmonics in a non-Gaussian environment, and has strong convergence, high accuracy of time delay estimation, and fast iteration speed. It can be based on time delay estimation in a non-Gaussian environment. The positioning plays a certain role.
Abstract: The time delay estimation algorithm is one of the important factors of sound source localization. The generalized weighted adaptive time delay estimation algorithm is limited by the environmental conditions of signal and noise, and has great limitations in non-Gaussian environments. In order to make the algorithm suitable for non-Gaussian environme...
Show More
An Integrated Management System for Quality, Health and Safety, and Environment: A Case Study
Rui Ding,
Jintao Xu,
Yang Sui
Issue:
Volume 9, Issue 5, October 2021
Pages:
170-179
Received:
10 September 2021
Accepted:
18 October 2021
Published:
30 October 2021
Abstract: The nuclear power plant (NPP) project (NPPP) usually faces with the complex quality, health and safety, and environment (QHSE) risks, so that it is vital to establish the QMS, OHSMS, and EMS, as is called QHSEMSs, according to ISO 9001, ISO 45001, and ISO 14001 standards, as is called the three ISO standards, respectively. Meanwhile, the QHSEMSs need to be supplemented and improved according to IAEA safety standards due to its industry particularity, and the special QHSEMSs need to be established and then implemented. However, during establishing and implementing the special QHSEMSs for NPPP, problems including huge numbers of documents, complex organizational structures, cumbersome management processes, lower management efficiency, and higher management cost are encountered. In order to solve these problems, a generic model for integrating the special QHSEMSs into an integrated management system (IMS) for QHSE (QHSEIMS) for NPPP in China was proposed according to the three ISO standards and IAEA safety standards through PDCA, process, and system approaches, as is called the three integration approaches. The proposed model was applied to establish and implement the QHSEIMS in a typical case, and the application results indicated that the proposed model was of great help to streamline the documentation, organizational structure, and management process for QHSE, and to effectively and efficiently manage the QHSE for the NPPP.
Abstract: The nuclear power plant (NPP) project (NPPP) usually faces with the complex quality, health and safety, and environment (QHSE) risks, so that it is vital to establish the QMS, OHSMS, and EMS, as is called QHSEMSs, according to ISO 9001, ISO 45001, and ISO 14001 standards, as is called the three ISO standards, respectively. Meanwhile, the QHSEMSs ne...
Show More
