2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID)最新文献_第4页

Multi Loss Function for Cross-Modality Person Re-Identification 跨模态人再识别的多重损失函数

2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2021-10-29 DOI: 10.1109/asid52932.2021.9651685

Furong Liu, Fengsui Wang, Jingang Chen, Qisheng Wang

引用次数: 0

Automatic Recognition of Fetal Heart Standard Section Based on Fast-RCNN 基于Fast-RCNN的胎儿心脏标准切片自动识别

2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2021-10-29 DOI: 10.1109/asid52932.2021.9651487

Bingzheng Wu, Huiling Wu, Yongzhao Du, Peizhong Liu

{"title":"Automatic Recognition of Fetal Heart Standard Section Based on Fast-RCNN","authors":"Bingzheng Wu, Huiling Wu, Yongzhao Du, Peizhong Liu","doi":"10.1109/asid52932.2021.9651487","DOIUrl":"https://doi.org/10.1109/asid52932.2021.9651487","url":null,"abstract":"Congenital heart defect is one of the most common fetal congenital defects. Every year, about 1% of newborns in the world suffer from this disease, and the proportion in developing countries reaches up to 4%-5%. Automatic identification of standard fetal heart sections from 2D ultrasound scanning video is an important prerequisite for examining a fetus with congenital heart disease. In China, most areas belong to rural areas. In this difficult environment, it is extremely difficult to diagnose fetuses with congenital heart disease by prenatal sonographers, which requires sonographers with rich qualifications to make the diagnosis, but few sonographers meet this qualification in rural areas. In this study, a new method based on Fast-RCNN deep learning with Mobilenet as the backbone network is proposed to automatically identify the standard section of fetal heart. This model can not only help sonographers collect fetal ultrasound images in practice, but also provide a reliable basis for later analysis of the fetal images, save more time and enhance efficiency. And this method can not only help new ultrasound physicians, but also provide high-qualified sonographers enough auxiliary diagnosis effects. All the data sets used in this method collected from the cooperative hospitals of colleges and universities, and the data volume is 1839, which can be split into training set(1479) and test set(360). In three centuries of repeated trials, the Mean Average Precision (MAP) on the validation set reaches 92.49%, and the accuracy rate reaches 90%. In the later period, some comparative experiments of different neural networks have been carried out, which proves that the method in this study is superior to other neural networks and can bring enough benefits to ultrasound physicians.","PeriodicalId":150884,"journal":{"name":"2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116089558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

A Novel SPA Countermeasure for SM2 Hardware Implementation with FPGA 一种基于FPGA的SM2硬件实现的SPA策略

2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2021-10-29 DOI: 10.1109/asid52932.2021.9651700

Jiahao Fang, Liji Wu, Xiangmin Zhang

引用次数: 1

A SAR-based Fast Automatic Frequency Tuning Circuit in a 3-th Order Active-RC Complex Filter 一种基于sar的三阶有源rc复合滤波器快速自动频率调谐电路

2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2021-10-29 DOI: 10.1109/asid52932.2021.9651714

Boyong Jin, Zhijie Chen, Xu Liu, Zhiqi Shen, Yucheng Bao, Y. Xing, Peiyuan Wan

引用次数: 0

VLSI Architecture Design for Adder Convolution Neural Network Accelerator 加法器卷积神经网络加速器的VLSI架构设计

2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2021-10-29 DOI: 10.1109/asid52932.2021.9651682

Mingyong Zhuang, Xinhui Liao, Huhong Wu, Jianyang Zhou, Zichao Guo

引用次数: 3

ASID 2021 Author Index ASID 2021作者索引

2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2021-10-29 DOI: 10.1109/asid52932.2021.9651716

引用次数: 0

A Non-Intrusive Self-Calibration Method for the Circuit Design of Inductorless Low Noise Amplifier 一种无电感低噪声放大器电路设计的非侵入式自校正方法

2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2021-10-29 DOI: 10.1109/asid52932.2021.9651692

Wenrun Xiao, Weikang Wu, Yin-Wei Chang, Jidong Diao, Yanping Qiao, Xianming Liu, Shan He, Xiaojie Liu, Donghui Guo

{"title":"A Non-Intrusive Self-Calibration Method for the Circuit Design of Inductorless Low Noise Amplifier","authors":"Wenrun Xiao, Weikang Wu, Yin-Wei Chang, Jidong Diao, Yanping Qiao, Xianming Liu, Shan He, Xiaojie Liu, Donghui Guo","doi":"10.1109/asid52932.2021.9651692","DOIUrl":"https://doi.org/10.1109/asid52932.2021.9651692","url":null,"abstract":"This paper calibrates an inductorless LNA’s NF and S11 based on non-intrusive self-calibration. Since the NF and S11 of the inductorless LNA depend on transconductance and channel resistance of transistors which have a relationship with the transistors’ port voltage, we use measured dc voltage from the LNA to estimate its NF and S11. Also, we choose the LNA’s bias current and the ratio of the current mirror providing current for PMOS bias transistor as tuning knobs to adjust the LNA’s S11 and NF. To realize non-intrusive self-calibration, measured dc voltage and currents from dummy circuits are used to estimate the LNA’s S11 and NF. Different dummy sizes are used, and we find that there is a trade-off between dummy size and calibration results. The circuits are implemented in 22-nm ultra-low leakage CMOS technology and the calibration algorithm was implemented with Matlab. The simulation results show that a 15.5% yield improvement could be obtained when dc voltages are measured from the primary LNA with current from a 1/2 scaled current mirror and a yield improvement from 11% to 16.5% could be obtained when dc voltages and currents are measured from different sets of dummy circuits.","PeriodicalId":150884,"journal":{"name":"2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130376383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Low-light image enhancement based on FPGA 基于FPGA的微光图像增强

2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2021-10-29 DOI: 10.1109/asid52932.2021.9651721

Xiaohong Peng, Xuefeng Li, Shuqin Geng, Jie Wang, Fengjun Nie

引用次数: 1

An Intelligent Error Compensation Method for Height Measurement of Bump Package 凸包高度测量的智能误差补偿方法

2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2021-10-29 DOI: 10.1109/asid52932.2021.9651681

Ruiqian Ye, Peng Zheng, Yun Gao, Chun Lin, Zili Zhang, Fanchang Meng

{"title":"An Intelligent Error Compensation Method for Height Measurement of Bump Package","authors":"Ruiqian Ye, Peng Zheng, Yun Gao, Chun Lin, Zili Zhang, Fanchang Meng","doi":"10.1109/asid52932.2021.9651681","DOIUrl":"https://doi.org/10.1109/asid52932.2021.9651681","url":null,"abstract":"The coplanarity of the bump height is the guarantee of packaging quality. Optical triangulation is a widely used method to measure the bump height. However, it is not easy to accurately measure the bump height due to its small size, curved and highly reflective surface. In order to solve the problem of poor stability in triangulation measurement when using light strip center extraction, we analyzed the error reasons in a white light triangulation based bump height measurement. Then, an improved gray centroid method was applied to extract the light strip center on the base wafer and the light spot on the bump top. Next, the calibration results was combined to calculate the initial bump height. Finally, two features of the light strip and light spot were detected to train a multilayer perceptron to obtain an intelligent compensation for the bump height. It was proved that the standard deviation and the extreme difference of bump height are reduced to at least 1/2 after using our compensation method. The average standard deviation was reduced from 0.651um to 0.281um, as well as the average extreme difference was reduced from 1.790um to 0.689um. The result can meet the requirements of most of the bump package.","PeriodicalId":150884,"journal":{"name":"2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129967560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LMS Based Ultra-Fast Non Linearity Test and Calibration Method for High-speed and High-Resolution ADC 基于LMS的高速高分辨率ADC超快速非线性测试与校准方法

2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2021-10-29 DOI: 10.1109/asid52932.2021.9651698

Ting Li, Yabo Ni, Yong Zhang, Chao Chen

{"title":"LMS Based Ultra-Fast Non Linearity Test and Calibration Method for High-speed and High-Resolution ADC","authors":"Ting Li, Yabo Ni, Yong Zhang, Chao Chen","doi":"10.1109/asid52932.2021.9651698","DOIUrl":"https://doi.org/10.1109/asid52932.2021.9651698","url":null,"abstract":"This paper presents an LMS(Least Mean Square) based nonlinear error extraction and calibration algorithm for pipeline ADC(analog-to-digital converter ). In this algorithm, the nonlinear error of ADC is treated as the internal error of each stage and the gain error between stages. When testing, a known high quality signal is sent to the ADC and the error parameters are calculated using the digital output codes. Compared to traditional histogram testing, this method using much fewer samples. During calibration, the method proposed in this paper is used to eliminate the nonlinear error digitally from the digital output code of ADC. Only 4000 samples were used, the non linearity of the 14-bit high speed high resolution pipeline ADC can be extracted and removed so that the ADC can achieve less than 1.5 least significant bit (LSB) integral nonlinearity (INL) which is reduced by 78%. The measurement results illustrates the effectiveness of the method, after calibration, the ADC signal to noise and distortion ratio (SINAD) is improved from 65dBFS to 69dBFS and the spurious-free dynamic range (SFDR) is improved from 75dBFS to 92dBFS. The algorithm proposed in this paper is especially suitable for multistage ADC and can also be used for all types of ADCs.","PeriodicalId":150884,"journal":{"name":"2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130651584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1