Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896666
Di Zhao, Lan Ma, Zhixian Lin, Tailiang Guo, Shanling Lin
When taking pictures in extremely dark light, the image taken is usually very dark and noisy due to the small amount of light entering, and there is clear distortion of color. Since the method of using multi-frame or long-exposure has limitations, we use the single-frame denoising method based on residual dense network (RDN), which uses residual dense block (RDB) to makes full use of local features. Our method has achieved better results than state-of-the-art methods. In addition, we have applied the trained model without fine-tuning on photos captured by different cameras and have obtained similar end-to-end enhancements.
{"title":"End-to-End Denoising of Dark Image Using Residual Dense Network","authors":"Di Zhao, Lan Ma, Zhixian Lin, Tailiang Guo, Shanling Lin","doi":"10.1109/ISNE.2019.8896666","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896666","url":null,"abstract":"When taking pictures in extremely dark light, the image taken is usually very dark and noisy due to the small amount of light entering, and there is clear distortion of color. Since the method of using multi-frame or long-exposure has limitations, we use the single-frame denoising method based on residual dense network (RDN), which uses residual dense block (RDB) to makes full use of local features. Our method has achieved better results than state-of-the-art methods. In addition, we have applied the trained model without fine-tuning on photos captured by different cameras and have obtained similar end-to-end enhancements.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125335317","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896538
Xue-jiao Feng, Xiaoqiang Chen, Ying Wang, Jiarong Wang
The design of wireless power transfer via coupled magnetic resonances (CMR-WPT) can be used in the power transmission system of medical equipment, such as cardiac pacemaker, to solve the shortcomings of traditional energy supply. Considering the small size of implantable medical devices and the 8-shape coil, and using the finite element simulation software to analyze the effect of various relevant parameters on the output power, so as to obtain the optimal parameters of the system. The magnetic flux density distribution in the model was compared with the limits set by the International Commission on Non-ionizing Radiation Protection (ICNIRP) to evaluate the safety of electromagnetic exposure and the results show that the system can transmit wireless power safely.
{"title":"Research on the Simulation of Wireless Power Transfer Via Coupled Magnetic Resonances","authors":"Xue-jiao Feng, Xiaoqiang Chen, Ying Wang, Jiarong Wang","doi":"10.1109/ISNE.2019.8896538","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896538","url":null,"abstract":"The design of wireless power transfer via coupled magnetic resonances (CMR-WPT) can be used in the power transmission system of medical equipment, such as cardiac pacemaker, to solve the shortcomings of traditional energy supply. Considering the small size of implantable medical devices and the 8-shape coil, and using the finite element simulation software to analyze the effect of various relevant parameters on the output power, so as to obtain the optimal parameters of the system. The magnetic flux density distribution in the model was compared with the limits set by the International Commission on Non-ionizing Radiation Protection (ICNIRP) to evaluate the safety of electromagnetic exposure and the results show that the system can transmit wireless power safely.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126760512","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896458
Yuanyuan Wang, Ling Ma, Huiqin Jiang
The conductivity of the TFT-LCD circuit can be determined by counting and locating anisotropic conductive film (ACF) particles in the circuit, which is a critical step for the detection of conductivity in the TFT-LCD manufacturing process. In order to solve the aggregation and overlap problems of ACF particles, in this paper, we propose a U-shaped multi-scale convolution network(U-MultiNet). The U-Net network structure is designed adaptively, which reduces the parameter amount of the network. The multi-scale convolution blocks are introduced for extracting the multiscale spatial features. In addition, the particles detection is transformed into a segmentation task, which helps to solve the aggregation and overlap problems of particles. The experimental results show that the method achieves high precision and recall rate, which is far superior to the previous methods.
{"title":"Detecting Conductive Particles in TFT-LCD with U-MultiNet","authors":"Yuanyuan Wang, Ling Ma, Huiqin Jiang","doi":"10.1109/ISNE.2019.8896458","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896458","url":null,"abstract":"The conductivity of the TFT-LCD circuit can be determined by counting and locating anisotropic conductive film (ACF) particles in the circuit, which is a critical step for the detection of conductivity in the TFT-LCD manufacturing process. In order to solve the aggregation and overlap problems of ACF particles, in this paper, we propose a U-shaped multi-scale convolution network(U-MultiNet). The U-Net network structure is designed adaptively, which reduces the parameter amount of the network. The multi-scale convolution blocks are introduced for extracting the multiscale spatial features. In addition, the particles detection is transformed into a segmentation task, which helps to solve the aggregation and overlap problems of particles. The experimental results show that the method achieves high precision and recall rate, which is far superior to the previous methods.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115734471","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896511
Chuang Bai, Guozhou Liu, Wei Zhang
A new thyristor-based delay element for physical unclonable function (PUF) design is proposed in this paper. Thyristor-based delay element as PUF cell shows strong sensitivity to process variation and is little sensitive to supply voltage and temperature variations, which could effectively improve the uniqueness and stability of PUF design. Simulated results show that thyristor-based delay element has 12.5964 largest standard deviation of delay time over process variation, and 0.4766/1.0631 lowest standard deviation of delay time with respect to temperature variation from -$50^{circ }mathrm {C}$ to $100^{circ }mathrm {C}$, and supply voltage variation from 1.5V to 2.1V, compared with other delay elements.
{"title":"A New Thyristor-based Delay Element for PUF Design","authors":"Chuang Bai, Guozhou Liu, Wei Zhang","doi":"10.1109/ISNE.2019.8896511","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896511","url":null,"abstract":"A new thyristor-based delay element for physical unclonable function (PUF) design is proposed in this paper. Thyristor-based delay element as PUF cell shows strong sensitivity to process variation and is little sensitive to supply voltage and temperature variations, which could effectively improve the uniqueness and stability of PUF design. Simulated results show that thyristor-based delay element has 12.5964 largest standard deviation of delay time over process variation, and 0.4766/1.0631 lowest standard deviation of delay time with respect to temperature variation from -$50^{circ }mathrm {C}$ to $100^{circ }mathrm {C}$, and supply voltage variation from 1.5V to 2.1V, compared with other delay elements.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131268334","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896421
V. Sverdlov, S. Selberherr
With CMOS transistors’ scaling showing signs of saturation, an exploration of new working principles suitable for emerging microelectronic devices accelerates. The electron spin is attractive for new device applications as a complement and a possible replacement of the electron charge currently employed by CMOS. The electron spin displays the two well-defined projections on an axis and is thus suitable for digital applications. In magnetic tunnel junctions (MTJs) the free magnetic layer possesses two orientations relative to the fixed layer: parallel and antiparallel. As the parallel and antiparallel magnetization configurations are characterized by different resistances, the thereby stored information can be read. MTJs enable a spin-based type of non-volatile magnetoresistive memory. MTJs are fabricated with a CMOS-friendly process and are quite CMOS compatible. The relative magnetization configuration can be written by means of a spin-transfer torque (STT) or a spin-orbit torque (SOT) acting on the free layer. The torques are caused by spin-polarized electrical currents and not by a magnetic field. Electrically addressable non-volatile magnetoresistive memories are attractive for stand-alone and embedded applications. The state-of-the art concepts of STT and SOT memory, in particular the required modeling approaches, are reviewed, with a particular focus on a fast external magnetic field free switching in advanced SOT-MRAM.
{"title":"CMOS Technology Compatible Magnetic Memories","authors":"V. Sverdlov, S. Selberherr","doi":"10.1109/ISNE.2019.8896421","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896421","url":null,"abstract":"With CMOS transistors’ scaling showing signs of saturation, an exploration of new working principles suitable for emerging microelectronic devices accelerates. The electron spin is attractive for new device applications as a complement and a possible replacement of the electron charge currently employed by CMOS. The electron spin displays the two well-defined projections on an axis and is thus suitable for digital applications. In magnetic tunnel junctions (MTJs) the free magnetic layer possesses two orientations relative to the fixed layer: parallel and antiparallel. As the parallel and antiparallel magnetization configurations are characterized by different resistances, the thereby stored information can be read. MTJs enable a spin-based type of non-volatile magnetoresistive memory. MTJs are fabricated with a CMOS-friendly process and are quite CMOS compatible. The relative magnetization configuration can be written by means of a spin-transfer torque (STT) or a spin-orbit torque (SOT) acting on the free layer. The torques are caused by spin-polarized electrical currents and not by a magnetic field. Electrically addressable non-volatile magnetoresistive memories are attractive for stand-alone and embedded applications. The state-of-the art concepts of STT and SOT memory, in particular the required modeling approaches, are reviewed, with a particular focus on a fast external magnetic field free switching in advanced SOT-MRAM.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132701224","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896670
Zhang Taoning, Chen Enqing
The rapid detection and identification of products based on computer vision has important applications in the fields of unmanned retail and goods sorting. At present, the recognition rate of traditional product identification methods is not high, and the deep learning recognition method requires large-scale training and cannot meet real-time requirements. This paper proposes a product identification algorithm that combines traditional HOG detection with the SIFT feature-based bag of words model for the needs of product identification. Compared with the traditional product identification method for feature matching, the algorithm has the advantages of higher recognition rate and shorter time. The test results show that the real-time recognition rate can reach 98%. At the same time, the algorithm has the advantages of light weight and easy portability, and can be applied to many occasions such as unmanned retail or express picking.
{"title":"Product Recognition Algorithm Based on HOG and Bag of Words Model","authors":"Zhang Taoning, Chen Enqing","doi":"10.1109/ISNE.2019.8896670","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896670","url":null,"abstract":"The rapid detection and identification of products based on computer vision has important applications in the fields of unmanned retail and goods sorting. At present, the recognition rate of traditional product identification methods is not high, and the deep learning recognition method requires large-scale training and cannot meet real-time requirements. This paper proposes a product identification algorithm that combines traditional HOG detection with the SIFT feature-based bag of words model for the needs of product identification. Compared with the traditional product identification method for feature matching, the algorithm has the advantages of higher recognition rate and shorter time. The test results show that the real-time recognition rate can reach 98%. At the same time, the algorithm has the advantages of light weight and easy portability, and can be applied to many occasions such as unmanned retail or express picking.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"128 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131811049","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896684
Hanmo Wang, Yang Zhao, S. Tan
Along with the deregulation of electric power market as well as aggregation of renewable resources, a sufficiently accurate, robust and fast short-term load forecasting (STLF) is necessary for the day-to-day reliable operation of the grid. To obtain parameter values that provide better performances with faster speed, this paper uses a temporal convolutional network (TCN), which constituted by the one-dimensional convolutional neural network, for short-term load forecasting. It’s commonly thought that recurrent neural networks (RNNs) is the king of short-term load forecasting areas, but the TCN model has faster speed and less memory requirement because of the convolutional neural network structure. The simulation studies are carried out using an hourly power consumption dataset collected from Toronto. Compared with support vector regression machine (SVRM) model and long short-term memory (LSTM) model, the TCN model has the best performance in predicting the short-term electrical load.
{"title":"Short-term load forecasting of power system based on time convolutional network","authors":"Hanmo Wang, Yang Zhao, S. Tan","doi":"10.1109/ISNE.2019.8896684","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896684","url":null,"abstract":"Along with the deregulation of electric power market as well as aggregation of renewable resources, a sufficiently accurate, robust and fast short-term load forecasting (STLF) is necessary for the day-to-day reliable operation of the grid. To obtain parameter values that provide better performances with faster speed, this paper uses a temporal convolutional network (TCN), which constituted by the one-dimensional convolutional neural network, for short-term load forecasting. It’s commonly thought that recurrent neural networks (RNNs) is the king of short-term load forecasting areas, but the TCN model has faster speed and less memory requirement because of the convolutional neural network structure. The simulation studies are carried out using an hourly power consumption dataset collected from Toronto. Compared with support vector regression machine (SVRM) model and long short-term memory (LSTM) model, the TCN model has the best performance in predicting the short-term electrical load.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133737807","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896650
Tiantian Xie, Runchuan Li, Xingjin Zhang, Bing Zhou, Zongmin Wang
Premature ventricular contraction (PVC) is a widespread condition of arrhythmia that can be life-threatening at any time. Fast and accurate use of computers to diagnose PVC is critical for both doctors and patients. In this paper, we propose a new method for PVC detection based on abnormal eigenvalues and decision tree. We choose composite areas, amplitudes and intervals as feature parameters to identify heartbeat types. The method was tested in the published MITBIH arrhythmia database with accuracy, sensitivity and specificity of 99.6%, 97.3% and 99.5%, respectively. The effectiveness of the proposed method is proved by comparison with other methods.
{"title":"Research on Heartbeat Classification Algorithm Based on CART Decision Tree","authors":"Tiantian Xie, Runchuan Li, Xingjin Zhang, Bing Zhou, Zongmin Wang","doi":"10.1109/ISNE.2019.8896650","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896650","url":null,"abstract":"Premature ventricular contraction (PVC) is a widespread condition of arrhythmia that can be life-threatening at any time. Fast and accurate use of computers to diagnose PVC is critical for both doctors and patients. In this paper, we propose a new method for PVC detection based on abnormal eigenvalues and decision tree. We choose composite areas, amplitudes and intervals as feature parameters to identify heartbeat types. The method was tested in the published MITBIH arrhythmia database with accuracy, sensitivity and specificity of 99.6%, 97.3% and 99.5%, respectively. The effectiveness of the proposed method is proved by comparison with other methods.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116216476","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}
Pub Date : 2019-10-01DOI: 10.1109/isne.2019.8896512
{"title":"ISNE 2019 Copyright Page","authors":"","doi":"10.1109/isne.2019.8896512","DOIUrl":"https://doi.org/10.1109/isne.2019.8896512","url":null,"abstract":"","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116472655","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896534
Yan Wang, Zhiwei Liu, Jizhi Liu
In this paper, a novel RC-triggered bidirectional ESD protection circuit in SOI technology is proposed and demonstrated. In the proposed circuit, the improved bridge rectifier circuit is formed by diode rectifier circuit paralleling MOSFET rectifier circuit. The circuit can convert the input voltage in I/O pin ranging between negative and positive values into a single polarity input voltage to the RC-triggered circuit. From the simulation results, the novel circuit can provide efficient bidirectional ESD protection for the I/O pin.
{"title":"A Novel RC-Triggered Bidirectional ESD Protection Circuit in SOI Technology","authors":"Yan Wang, Zhiwei Liu, Jizhi Liu","doi":"10.1109/ISNE.2019.8896534","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896534","url":null,"abstract":"In this paper, a novel RC-triggered bidirectional ESD protection circuit in SOI technology is proposed and demonstrated. In the proposed circuit, the improved bridge rectifier circuit is formed by diode rectifier circuit paralleling MOSFET rectifier circuit. The circuit can convert the input voltage in I/O pin ranging between negative and positive values into a single polarity input voltage to the RC-triggered circuit. From the simulation results, the novel circuit can provide efficient bidirectional ESD protection for the I/O pin.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121791252","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：