Ship Number Recognition Method Based on An improved CRNN Model

Wenqi Xu,Yuesheng Liu,Ziyang Zhong,Yang Chen,Jinfeng Xia,Yunjie Chen 한국인터넷정보학회 2023 KSII Transactions on Internet and Information Syst Vol.17 No.3

Text recognition in natural scene images is a challenging problem in computer vision. The accurate identification of ship number characters can effectively improve the level of ship traffic management. However, due to the blurring caused by motion and text occlusion, the accuracy of ship number recognition is difficult to meet the actual requirements. To solve these problems, this paper proposes a dual-branch network based on the CRNN identification network. The network couples image restoration and character recognition. The CycleGAN module is used for blur restoration branch, and the Pix2pix module is used for character occlusion branch. The two are coupled to reduce the impact of image blur and occlusion. Input the recovered image into the text recognition branch to improve the recognition accuracy. After a lot of experiments, the model is robust and easy to train. Experiments on CTW datasets and real ship maps illustrate that our method can get more accurate results.

Enhanced Solo-Based Instance Segmentation Algorithm for Efficient Plant Growth Assessment: A Radish Case Study

Wenqi Zhang,L. Minh Dang,Yanfen Li,Hanxiang Wang,Sujin Lee,Hyeonjoon Moon 한국방송·미디어공학회 2023 한국방송공학회 학술발표대회 논문집 Vol.2023 No.6

The dimensions of plants, including their length and width, as well as the size of their leaves, serve as crucial indicators for assessing their growth status. These factors provide essential data for studying plant conditions. This article introduces an algorithm for instance segmentation based on Solo, with the addition of a residual block module to enhance segmentation performance. The original rectified linear unit (ReLU) activation function is replaced with a functional ReLU (PReLU), and an open turnip segmentation dataset is proposed. Experimental results demonstrate that, in comparison to the original model, the average accuracy of the modified model reaches 87.6%, an improvement of approximately 2.0%. The improved algorithm accurately segments turnips and their leaves, exhibiting superior accuracy in measuring both turnip and leaf dimensions. Compared to manual measurements, the average accuracy for turnip length is 97.38%, turnip width is 95.46%, turnip leaf length is 97.79%, and turnip leaf width is 96.13%.

Observer-based Adaptive Neural Network Output-feedback Control for Nonlinear Strict-feedback Discrete-time Systems

Wenqi Xu,Xiaoping Liu,Huanqing Wang,Yucheng Zhou 제어·로봇·시스템학회 2021 International Journal of Control, Automation, and Vol.19 No.1

This paper focuses on an observer-based output-feedback controller design for a nonlinear discrete-timesystem. The major characteristics of this system is that all of the subsystems are in strict-feedback form and all thestates of the system are not measurable. An output tracking control problem is firstly considered in this paper. NNsare utilized to approximate unknown functions, while a state observer is designed to approximatethe unvailablestates. An adaptive controller is designed on the basis of the backstepping technique. On the basis of the Lyapunovanalysis approach, the boundedness of all the signals is provided. The feasibility of the proposed scheme is verifiedthrough a simulation example.

High-sensitivity detection for cantharidin by ratiometric fluorescent sensor based on molecularly imprinted nanoparticles of quantum dots

Jiang Ling,Wenqi Zhang,Zijia Cheng,Yanjun Ding 한국공업화학회 2022 Journal of Industrial and Engineering Chemistry Vol.112 No.-

Cantharidin (CTD), an effective component of Chinese herbal medicine with unique efficacy, caused poisoningor death constantly for incorrect use. Therefore, there is an intense need for a reliable, selective,sensitive and low-costing analytical method for monitoring the concentration of CTD in biological samples. In this work, a ratiometric fluorescent sensor (CdTe@MIPs/CDs@NIPs) was successfully constructedfor selective determination of CTD by simply integrated the non-imprinted polymers coated CDs(CDs@NIPs) with cadmium telluride quantum dots coated with molecular imprinted polymers(CdTe@MIPs). CDs@NIPs were directly used as reference signal without addition of CTD templates andthe as-prepared CdTe@MIPs were response signal. With the CTD addition, the fluorescence intensity ofCdTe@MIPs decreased, while the fluorescence of CDs@NIPs remained approximately unchanged, resultinga detection limit as low as 0.15 nM. By spiked human blood samples, the ratiometric sensor was successfullyapplied to CTD detection with good recoveries of 96.12–107.40% and relative standard deviation(RSD) of 2.87–3.96%. Moreover, after centrifuging and re-eluting, the developed sensor could be effectivelyrecycled and reused five times. Significantly, the proposed platform with low-cost and highsensitivityopens a door towards the practical applications of ratiometric sensor and shows immensepotential in pursuing the sensitive, reliable and low-cost determination of poisons in forensic toxicologyanalysis.

The Effect of Green Transformation on the Operating Efficiency of Green M&A Enterprises: Evidence from China

Lingling ZHOU,Wenqi LI,Brian Sheng-Xian TEO,Siti Khalidah Md YUSOFF 한국유통과학회 2022 The Journal of Asian Finance, Economics and Busine Vol.9 No.1

Environmental protection has been infused into the development of numerous fields by the Chinese government. The government’s implementation of green development has also shifted its focus to green transformation and governance of highpolluting companies. In the context of green and sustainable development, this study employs DEA data envelopment analysis to compare the operating efficiency of listed firms that implemented Green Mergers and Acquisitions (M&A) in China in 2018. The conclusions of this study are as follows: First, China’s green M&A enterprises are unevenly dispersed among the country’s east, middle, and western regions. Second, compared to before the implementation of Green M&A, operational efficiency has improved in most industries. Third, the difference in Green M&A across industries is generally favorable, showing that most organizations have improved their operational performance as a result of Green M&A implementation. In 2018, however, the gap in operating efficiency is more negative. Fourth, whereas the eastern and western areas’ operational efficiency has improved as a result of Green M&A, the central region’s has not. Based on this conclusion, this study makes recommendations for China’s future sustainable development of heavily polluted firms.

Customer Voice at Starbucks: An SVM-based Sentiment Analysis Perspective

( Yuhang Wu ),( Wenqi Li ) 한국감성과학회 2023 한국감성과학회 국제학술대회(ICES) Vol.2023 No.-

This study presents a comprehensive sentiment analysis of customer reviews pertaining to Starbucks, employing the Support Vector Machine (SVM) model. Our findings underscore the model's notable proficiency in discerning negative feedback, thus functioning as a vital tool for enterprises to comprehend customer sentiments in real-time. The insights gleaned from our research extend beyond Starbucks, offering valuable insights for diverse businesses aiming to leverage customer feedback for service enhancement and strategic decision-making. Looking ahead, the potential integration of deep learning techniques holds promising prospects for further enhancing sentiment analysis capabilities.

Analysis of Energy Rebound Effect Measurement of Liaoning Province

Qing Liu,Wenqi Cui,Chen Sun,Baoxin Bai 경성대학교 산업개발연구소 2015 산업혁신연구 Vol.31 No.4

The rebound effect explains the effect of the implementation of government’s energy policy. In response to the situation that research about Liaoning province’s energy rebound effect is less, the research uses Solow residual method and DEA-Malmquist index method to build measurement models which aim at calculating the energy rebound effect of Liaoning Province from 1986 to 2012. The results show that rebound effect of Liaoning Province is obvious and the trend is upward. The result means that it can’t merely pay attention to improve energy efficiency but ignore rebound effect, so technological progress should combine with industrial structure adjustment, energy price reform and market regulation to achieve the goal of energy saving and emission reduction.

Histone lysine demethylases in mammalian embryonic development

Hongjie Shen,Wenqi Xu,Fei Lan 생화학분자생물학회 2017 Experimental and molecular medicine Vol.49 No.-

Post-translational modifications, such as methylation, acetylation and phosphorylation, of histone proteins play important roles in regulating dynamic chromatin structure. Histone demethylation has become one of the most active research areas of epigenetics in the past decade. To date, with the exception of histone H3 lysine 79 methylation, the demethylases for all major lysine methylation sites have been discovered. These enzymes have been shown to be involved in various biological processes, with embryonic development being an exciting emerging area. This review will primarily discuss the involvement of these demethylases in the regulation of mammalian embryonic development, including their roles in embryonic stem cell pluripotency, primordial germ cell (PGC) formation and maternal-to-zygotic transition.

Benchtop fabrication of three-dimensional reconfigurable microfluidic devices from paper-polymer composite.

Han, Yu Long,Wang, Wenqi,Hu, Jie,Huang, Guoyou,Wang, Shuqi,Lee, Won Gu,Lu, Tian Jian,Xu, Feng Royal Society of Chemistry 2013 Lab on a chip Vol.13 No.24

<P>We presented a benchtop technique that can fabricate reconfigurable, three-dimensional (3D) microfluidic devices made from a soft paper-polymer composite. This fabrication approach can produce microchannels at a minimal width of 100 μm and can be used to prototype 3D microfluidic devices by simple bending and stretching. The entire fabrication process can be finished in 2 hours on a laboratory bench without the need for special equipment involved in lithography. Various functional microfluidic devices (e.g., droplet generator and reconfigurable electronic circuit) were prepared using this paper-polymer hybrid microfluidic system. The developed method can be applied in a wide range of standard applications and emerging technologies such as liquid-phase electronics.</P>

Investigation of the Deformation Characteristics and Bearing Capacity of a Segment Structure of a Shield Tunnel with Cracks

Chuankun Liu,Shimin Wang,Wenqi Guo,Fan Chen,Junbo Zhang,Chuan He 대한토목학회 2022 KSCE Journal of Civil Engineering Vol.26 No.1

In this paper, the displacement data of a segment lining structure in a similar model test were analyzed in depth based on a field investigation and the analysis of a cracked segment in a metro project. In doing so, we proved the displacement characteristics and bearing capacity of shield tunnel segments with different cracks numbers, lengths, and locations. The results showed that the presence of a crack decreases the overall stiffness of the structure relative to an undamaged segment ring and causes the deformation increases with the same load to increase. One-third of the width of a segment is the demarcation point at which the length of the crack begins to affect the mechanical properties of structure of the lining of the segment. When the length of the crack is larger than one-third the width of the segment, the instability of the structure tends to result in sudden failure. Although an increase in the number of cracks does not reduces the ultimate bearing capacity of the structure further, the deformation of the structure of the lining of the segment increases significantly as the number of cracks increases. compared to a crack at the vault and at the arch waist, the ultimate bearing capacity of the segment is the same when the crack is at the bottom of the arch, but the effects of cracks located at the arch bottom in the structural deformation are the most significant.