Application of SIFT Algorithm based on the Gabor Features in Multi-source Information Image Monitoring

Shuwen Wang,Huiqi Cao,Yao Liu 대한전자공학회 2023 IEIE Transactions on Smart Processing & Computing Vol.12 No.2

Under the background of today’s intelligence, the application of intelligent images is becoming popularized, and the detection of multi-source information images is a valuable research topic. Current image detection methods are insensitive and inaccurate. Therefore, the research combines the SIFT (scale-invariant feature transform) algorithm with the Gabor features and CNN (convolutional neural network (Ed note. Acronyms only need to be defined once.)) to form an improved new algorithm. The algorithm divides the features of the image into several different categories. In each category, the features will be fully identified and extracted, and different levels of feature matching will be performed. The properties of the SIFT algorithm are used to form an operational stacking pyramid and combine the Gabor features and CNN with it. The Gabor filter is formed into a filter bank to obtain parameters, including frequency, scale, and direction in various dimensions. The results are fused to obtain a fusion Gabor descriptor. The high sensitivity of CNN to images, particularly colors, is applied to the algorithm to make monitoring the algorithm more accurate. The experimental results show that the average precision rate, average recall rate, and average precision rate of the improved algorithm are 92.35%, 74.79%, and 82.55%, respectively, which are significantly higher than the other two algorithms used for comparison. The improved algorithm shows better performance and has remarkable advantages that can be applied to the image monitoring of image information.

Particle Size Control in Iminodiacetic Acid Modified Magnetic Nanoparticle and Its Adsorption Capacity Evaluation

Shuwen Wang,Woo-Seok Choe 한국생물공학회 2007 한국생물공학회 학술대회 Vol.2007 No.10

Genome wide association study on feed conversion ratio using imputed sequence data in chickens

Jiaying Wang,Xiaolong Yuan,Shaopan Ye,Shuwen Huang,Yingting He,Hao Zhang,Jiaqi Li,Xiquan Zhang,Zhe Zhang 아세아·태평양축산학회 2019 Animal Bioscience Vol.32 No.4

Objective: Feed consumption contributes a large percentage for total production costs in the poultry industry. Detecting genes associated with feeding traits will be of benefit to improve our understanding of the molecular determinants for feed efficiency. The objective of this study was to identify candidate genes associated with feed conversion ratio (FCR) via genome-wide association study (GWAS) using sequence data imputed from single nucleotide polymorphism (SNP) panel in a Chinese indigenous chicken population. Methods: A total of 435 Chinese indigenous chickens were phenotyped for FCR and were genotyped using a 600K SNP genotyping array. Twenty-four birds were selected for sequencing, and the 600K SNP panel data were imputed to whole sequence data with the 24 birds as the reference. The GWAS were performed with GEMMA software. Results: After quality control, 8,626,020 SNPs were used for sequence based GWAS, in which ten significant genomic regions were detected to be associated with FCR. Ten candidate genes, ubiquitin specific peptidase 44, leukotriene A4 hydrolase, ETS transcription factor, R-spondin 2, inhibitor of apoptosis protein 3, sosondowah ankyrin repeat domain family member D, calmodulin regulated spectrin associated protein family member 2, zinc finger and BTB domain containing 41, potassium sodium-activated channel subfamily T member 2, and member of RAS oncogene family were annotated. Several of them were within or near the reported FCR quantitative trait loci, and others were newly reported. Conclusion: Results from this study provide valuable prior information on chicken genomic breeding programs, and potentially improve our understanding of the molecular mechanism for feeding traits.

UKF Estimation Method of Centroid Slip Angle for Vehicle Stability Control

Pan Wang,Xiaobin Fan,Xinbo Chen,Juean Yi,Shuwen He 제어·로봇·시스템학회 2023 International Journal of Control, Automation, and Vol.21 No.7

Vehicle center of sideslip angle is an essential parameter in vehicle stability control system. In view of the current problems is taken as the research object including low estimation accuracy and poor real-time performance of the current centroid sideslip angle, the four-wheel motor driven electric vehicle. The estimation problem of the sideslip angle is studied in-depth when the vehicle is in a nonlinear state. In addition, an Unscented Kalman Filter (UKF) estimation method is proposed to reduce observation error and improve the practicability of the estimation system. First of all, the research starts with building a 7-degree-of-freedom vehicle model which is based on the Dugoff tire model. Then, after measuring the state parameters, the UKF algorithm is used to estimate the sideslip angle. By comparing with the Extended Kalman Filter (EKF) algorithm, it is confirmed that the estimation method can not only better estimate the center of sideslip angle in real time, but also greater improve the handling stability of the vehicle in the driving state. Besides, the effectiveness of the algorithm is further verified by the real vehicle road test.

Enhanced and broadband absorber with surface pattern design for X-Band

Chenguang Wu,Shuwen Chen,Xisheng Gu,Renchao Hu,Shuomin Zhong,Guoguo Tan,Qikui Man,Chuntao Chang,Xinmin Wang,Run-Wei Li 한국물리학회 2018 Current Applied Physics Vol.18 No.1

A broadband and thin-layer microwave absorber is designed based on surface pattern design made by carbonyl iron and rubber composite. The bandwidth with reflection less than 10 dB covers the full Xband owing to two absorption peaks appeared simultaneously in both the simulation results and experimental results. In this work, the power loss and power flow diagram were present by CST simulation, which clearly explain the broadband absorption caused by double l/4 matching absorption and interfacial scattering synergistic effect. A facile splicing method was provided to extend the absorption bandwidth for the magnetic absorbing materials.

Detection of Starch Content in Potato Based on Hyperspectral Imaging Technique

Wei Jiang,Junlong Fang,Shuwen Wang,Yongcun Fan 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.12

Detection of starch content in potato is studied applying hyperspectral imaging technique in the paper. The original and preprocessing spectra were processed with partial least square(PLS) method to build prediction model of starch content. The original spectra between 400 and 1000nm was preprocessed with smoothing, second derivation, and multiplicative scatter correction (MSC). Prediction model was built with preprocessing spectra by applying principal component analysis (PCA). Known from the result, the model based on the preprocessing spectra preprocessed with smoothing and PCA is the best of all prediction models built in research. The determination coefficient (R2)of calibration set and prediction set was 0.8234 and 0.9031 respectively. The root mean square error of calibration set (RMSEC) and root mean square error of validation set(RMSEV) was 0.5633 and 0.5025,respectively.It indicated that this method could be applied in detection of starch content in potato. The study could offer theoretical and practical reference for further study in the future.

Hyperspectral Determination of Reducing Sugar in Potatoes Based on CARS

Wei Jiang,Junlong Fang,Shuwen Wang,Runtao Wang 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.9

It usually contains a large amount of redundant information to use the hyperspectral information to create a model, which will increase the difficulty of the model analysis. Therefore, it’s so important to select the characteristic wavelength in an effective and quick way. This study is proposed by using the competitive adaptive reweighed sampling (CARS) to select the characteristic wavelength for detecting the reducing sugar content in the potatoes. In that experiment a total of 238 samples are prepared. Among them, 190 samples are selected as the calibration set and 48 samples as the validation set. The performance of CARS is compared with full spectrum and classical variable extraction methods such as Monte Carlo uninformative variable elimination (MC-UVE), genetic algorithm (GA) and moving window partial least squares (MWPLS). Experimental results show that the band screened by algorithm CARS has the best effect, compared to full spectrum modeling, the wavelength of the model reduces from 203 to 33, the model validation set coefficient R2 increases from 0.8464 to 0.8965, and the root mean square error prediction (RMSEP) decreases from 0.0758 to 0.0416. The results demonstrate that it is feasible to detect the reducing sugar content of potatoes by using CARS combined with hyperspectral imaging.

Analysis of size-dependent protein adsorption behavior of Fe₃O₄ nanoparticles

Seon-hwa SEO,Min-seon SONG,Shuwen WANG,Woo-seok CHOE 한국생물공학회 2009 한국생물공학회 학술대회 Vol.2009 No.10

Evidence of the genetic diversity and clonal population structure of Oenococcus oeni strains isolated from different wine-making regions of China

Dongliang Yu,Kan Shi,Xiangyuan Wen,Fangshu Xie,Tao Wang,Shuwen Liu,Ling He 한국미생물학회 2018 The journal of microbiology Vol.56 No.8

Studies of the genetic diversity and population structure of Oenococcus oeni (O. oeni) strains from China are lacking compared to other countries and regions. In this study, amplified fragment length polymorphism (AFLP) and multilocus sequence typing (MLST) methods were used to investigate the genetic diversity and regional evolutionary patterns of 38 O. oeni strains isolated from different wine-making regions in China. The results indicated that AFLP was markedly more efficient than MLST for typing O. oeni strains. AFLP distinguished 37 DNA patterns compared to 7 sequence types identified using MLST, corresponding to discriminatory indices of 0.999 and 0.602, respectively. The AFLP results revealed a high level of genetic diversity among the O. oeni strains from different regions of China, since two subpopulations and an intraspecific homology higher than 60% were observed. Phylogenetic analysis of the O. oeni strains using the MLST method also identified two major phylogroups, which were differentiated into two distinct clonal complexes by minimum spanning tree analysis. Neither intragenic nor intergenic recombination verified the existence of the clonal population structure of the O. oeni strains.