Uneven illumination phenomenon and the cloud are common factors in lower quality aerial images, which will lead to the ground cover image, tonal change, distribution of color and brightness in RS images. This paper presents a technique to eliminate the cloud of the RS images, which uses filter dodging and information compensation to the processed images, in order to achieve a clear representation of the ground cover information.
{"title":"A Technique to Eliminate Cloud of RS Images","authors":"Youwei Zhang, Xiaoqing Zhu, Fangli Ge, Yafei Liu, Bing Xue, Xuekai Sun","doi":"10.1109/ISNE.2019.8896673","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896673","url":null,"abstract":"Uneven illumination phenomenon and the cloud are common factors in lower quality aerial images, which will lead to the ground cover image, tonal change, distribution of color and brightness in RS images. This paper presents a technique to eliminate the cloud of the RS images, which uses filter dodging and information compensation to the processed images, in order to achieve a clear representation of the ground cover information.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"70 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":"130010266","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.2019.8896576
Yan Ma, Ya Li, Jianning Yao, Bing Chen, Jicai Deng, Xiaonan Yang
Colorectal cancer is one of the most common cancers in China. The occurrence of most colorectal cancer is closely related to colorectal polyps. Colonoscopy is the gold standard for the diagnosis of intestinal lesions. Usually, existing colonoscopy is performed by physicians to determine the location of polyps by observing the results of detection with the naked eye. The detection rate of polyps is also affected by the doctor’s experience, fatigue, detection rate, and other factors, so there is a certain degree of polyp missed detection. Therefore, to improve diagnostic accuracy and reduce the rate of missed diagnosis, the paper proposes an improved_ssd model based on deep learning. The model is extended from the ssd_inception_v2 model, and the inception_v2 basic framework is used to extract features from multiple dimensions and fuse them, which improve the accuracy of polyp location. The test results show that the AP of this method is 94.92%, the accuracy is 96.04%, the sensitivity is 93.67%, and the specificity is 98.36%. This method realizes the accurate localization of polyps in colonoscopy and provides a reference for doctors' diagnosis.
{"title":"Polyp Location in Colonoscopy Based on Deep Learning","authors":"Yan Ma, Ya Li, Jianning Yao, Bing Chen, Jicai Deng, Xiaonan Yang","doi":"10.1109/ISNE.2019.8896576","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896576","url":null,"abstract":"Colorectal cancer is one of the most common cancers in China. The occurrence of most colorectal cancer is closely related to colorectal polyps. Colonoscopy is the gold standard for the diagnosis of intestinal lesions. Usually, existing colonoscopy is performed by physicians to determine the location of polyps by observing the results of detection with the naked eye. The detection rate of polyps is also affected by the doctor’s experience, fatigue, detection rate, and other factors, so there is a certain degree of polyp missed detection. Therefore, to improve diagnostic accuracy and reduce the rate of missed diagnosis, the paper proposes an improved_ssd model based on deep learning. The model is extended from the ssd_inception_v2 model, and the inception_v2 basic framework is used to extract features from multiple dimensions and fuse them, which improve the accuracy of polyp location. The test results show that the AP of this method is 94.92%, the accuracy is 96.04%, the sensitivity is 93.67%, and the specificity is 98.36%. This method realizes the accurate localization of polyps in colonoscopy and provides a reference for doctors' diagnosis.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"42 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":"124945632","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.2019.8896449
N. Prabhu, Desmond Loy Jia Jun, P. Dananjaya, E. Toh, W. Lew, N. Raghavan
In this work, the quantitative impact of variability in the low and high resistance state distributions of Hafnium oxide based RRAM on the prediction accuracy of deep learning neural networks is explored over a wide range of current compliance ranging from 2 to 500micro Ampere. The device power versus prediction accuracy trade-off trend is examined for such a wide range of compliance for the first time. The weights of one of the layers of the convolutional neural network (CNN) are represented by the floating point binary representation where the binary bits are configured using the RRAM resistance distribution data on an AlexNet platform.
{"title":"Exploring the Power – Prediction Accuracy Trade-Off in a Deep Learning Neural Network using Wide Compliance RRAM Device","authors":"N. Prabhu, Desmond Loy Jia Jun, P. Dananjaya, E. Toh, W. Lew, N. Raghavan","doi":"10.1109/ISNE.2019.8896449","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896449","url":null,"abstract":"In this work, the quantitative impact of variability in the low and high resistance state distributions of Hafnium oxide based RRAM on the prediction accuracy of deep learning neural networks is explored over a wide range of current compliance ranging from 2 to 500micro Ampere. The device power versus prediction accuracy trade-off trend is examined for such a wide range of compliance for the first time. The weights of one of the layers of the convolutional neural network (CNN) are represented by the floating point binary representation where the binary bits are configured using the RRAM resistance distribution data on an AlexNet platform.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"75 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":"134068298","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.2019.8896388
Benqing Guo, Jun Chen, Yao Wang
A CMOS fully differential current-mode frontend for SAW-less receivers is proposed. The noise-cancelling LNTA has a main path of the common-gate (CG) stage and an auxiliary path of the inverter stage. A current mirror is used to combine the signals from the main and auxiliary paths in current-mode domain. The stacked nMOS/pMOS configurations improve their power efficiency. Traditional stacked tri-state inverter as D-latch replaced by the discrete inverter and transmission gate enables a reduced supply voltage of divider core. LO generator based on the improved divider provides quarter LO signals to drive the proposed LNTA-shared receiver front-end. Simulation results in 180 nm CMOS indicate that the integrated receiver front-end provides a NF of 2.4 dB, and a maximum gain of 45 dB from 0.2 to 3.3 GHz. The inband and out-of-band IIP3 of 2.5 dBm and 4 dBm, are obtained, respectively.
{"title":"A 0.2-3.3 GHz 2.4 dB NF 45 dB Gain Current-Mode Front-End for SAW-less Receivers in 180 nm CMOS","authors":"Benqing Guo, Jun Chen, Yao Wang","doi":"10.1109/ISNE.2019.8896388","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896388","url":null,"abstract":"A CMOS fully differential current-mode frontend for SAW-less receivers is proposed. The noise-cancelling LNTA has a main path of the common-gate (CG) stage and an auxiliary path of the inverter stage. A current mirror is used to combine the signals from the main and auxiliary paths in current-mode domain. The stacked nMOS/pMOS configurations improve their power efficiency. Traditional stacked tri-state inverter as D-latch replaced by the discrete inverter and transmission gate enables a reduced supply voltage of divider core. LO generator based on the improved divider provides quarter LO signals to drive the proposed LNTA-shared receiver front-end. Simulation results in 180 nm CMOS indicate that the integrated receiver front-end provides a NF of 2.4 dB, and a maximum gain of 45 dB from 0.2 to 3.3 GHz. The inband and out-of-band IIP3 of 2.5 dBm and 4 dBm, are obtained, respectively.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"15 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":"134329439","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.2019.8896438
Mingyao Zheng, Y. Tie, L. Qi, Shengnan Jiang
Gesture recognition is applied in various intelligent scenes. In this paper, we propose the multi-modality fusion temporal segment networks (MMFTSN) model to solve dynamic gestures recognition. Three gesture modalities: RGB, Depth and Optical flow (OF) video data are equally segmented and randomly sampled. Then, the sampling frames are classified using convolutional neural network. Finally, fusing three kinds of modality classification results. MMFTSN is used to obtain the recognition accuracy of 60.2% on the gesture database Chalearn LAP IsoGD, which is better than the result of related algorithms. The results show that the improved performance of our MMFTSN model.
手势识别应用于各种智能场景中。本文提出了多模态融合时间段网络(MMFTSN)模型来解决动态手势识别问题。三种手势模式:RGB，深度和光流(OF)视频数据等分割和随机采样。然后，利用卷积神经网络对采样帧进行分类。最后，将三种情态分类结果进行融合。利用MMFTSN在手势数据库Chalearn LAP IsoGD上获得60.2%的识别准确率，优于相关算法的识别结果。结果表明，我们的MMFTSN模型的性能得到了改善。
{"title":"Dynamic Gesture Recognition Based on the Multimodality Fusion Temporal Segment Networks","authors":"Mingyao Zheng, Y. Tie, L. Qi, Shengnan Jiang","doi":"10.1109/ISNE.2019.8896438","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896438","url":null,"abstract":"Gesture recognition is applied in various intelligent scenes. In this paper, we propose the multi-modality fusion temporal segment networks (MMFTSN) model to solve dynamic gestures recognition. Three gesture modalities: RGB, Depth and Optical flow (OF) video data are equally segmented and randomly sampled. Then, the sampling frames are classified using convolutional neural network. Finally, fusing three kinds of modality classification results. MMFTSN is used to obtain the recognition accuracy of 60.2% on the gesture database Chalearn LAP IsoGD, which is better than the result of related algorithms. The results show that the improved performance of our MMFTSN model.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"527 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":"133437493","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.2019.8896662
{"title":"ISNE 2019 TOC","authors":"","doi":"10.1109/isne.2019.8896662","DOIUrl":"https://doi.org/10.1109/isne.2019.8896662","url":null,"abstract":"","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"83 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":"127636101","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.2019.8896425
Sakib Islam, Ibrahim M Abdel Motaleb
Although 3D IC technology can provide very high integration density, they suffer from having hotspots that may reach 1000’s of degrees. To manage this heat, it is necessary to study the dynamics of cooling and thermal behavior of the ICs. In this study, we report on the dynamics of microchannel liquid cooling using water, R22, and liquid nitrogen. The study shows that using diamond cooling blocks ensures normal operating temperature of 60 ˚C or less, using any of the above coolants. Using SiO2 blocks, only liquid nitrogen can provide acceptable operating temperatures. The study shows also that liquid latent energy and inlet velocity play a major role in the cooling dynamics.
{"title":"Investigation of the Dynamics of Liquid Cooling of 3D ICs","authors":"Sakib Islam, Ibrahim M Abdel Motaleb","doi":"10.1109/ISNE.2019.8896425","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896425","url":null,"abstract":"Although 3D IC technology can provide very high integration density, they suffer from having hotspots that may reach 1000’s of degrees. To manage this heat, it is necessary to study the dynamics of cooling and thermal behavior of the ICs. In this study, we report on the dynamics of microchannel liquid cooling using water, R22, and liquid nitrogen. The study shows that using diamond cooling blocks ensures normal operating temperature of 60 ˚C or less, using any of the above coolants. Using SiO2 blocks, only liquid nitrogen can provide acceptable operating temperatures. The study shows also that liquid latent energy and inlet velocity play a major role in the cooling dynamics.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"31 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":"122778364","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.2019.8896415
Chuang Ding, Y. Tie, L. Qi
Multi-modal methods play an important role on action recognition. Each modal can extract different features to analyze the same motion classification. But numbers of researches always separate the one task from the others, which cause the unreasonable utilization of complementary information in the multi-modality data. Skeleton is robust to the variation of illumination, backgrounds and viewpoints, while RGB has better performance in some circumstances when there are other objects that have great effect on recognition of action, such as drinking water and eating snacks. In this paper, we propose a novel Multi-information Complementarity Neural Network (MiCNN) for human action recognition to address this problem. The proposed MiCNN can learn the features from both skeleton and RGB data to ensure the abundance of information. Besides, we design a weighted fusion block to distribute the weights reasonably, which can make each modal draw on their respective strengths. The experiments on NTU RGB-D datasets demonstrate the excellent performance of our scheme, which are superior to other methods that we have ever known.
{"title":"Multi-information Complementarity Neural Networks for Multi-Modal Action Recognition","authors":"Chuang Ding, Y. Tie, L. Qi","doi":"10.1109/ISNE.2019.8896415","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896415","url":null,"abstract":"Multi-modal methods play an important role on action recognition. Each modal can extract different features to analyze the same motion classification. But numbers of researches always separate the one task from the others, which cause the unreasonable utilization of complementary information in the multi-modality data. Skeleton is robust to the variation of illumination, backgrounds and viewpoints, while RGB has better performance in some circumstances when there are other objects that have great effect on recognition of action, such as drinking water and eating snacks. In this paper, we propose a novel Multi-information Complementarity Neural Network (MiCNN) for human action recognition to address this problem. The proposed MiCNN can learn the features from both skeleton and RGB data to ensure the abundance of information. Besides, we design a weighted fusion block to distribute the weights reasonably, which can make each modal draw on their respective strengths. The experiments on NTU RGB-D datasets demonstrate the excellent performance of our scheme, which are superior to other methods that we have ever known.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"351 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":"124446573","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.2019.8896379
Guancong Liu, Xia Xiao, Haiyang Qi, Hang Song, Shuming Zhao, Derong Cao
In the new green Eco-toilet, the temperature of the reaction chamber plays a crucial role in the effective decomposition and utilization of human excreta. In this paper, an FPGA-based reaction chamber thermal control system is proposed. The system combines with explosion-proof temperature sensor and DC water pump, which can control and keep the temperature of reaction chamber in a proper range. The experimental results show the efficacy of the system, demonstrating that the proposed system can promote the development of new green Eco-toilet.
{"title":"FPGA-based Thermal Control System of Reaction Chamber of Photovolatic powerd Eco-toilet","authors":"Guancong Liu, Xia Xiao, Haiyang Qi, Hang Song, Shuming Zhao, Derong Cao","doi":"10.1109/ISNE.2019.8896379","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896379","url":null,"abstract":"In the new green Eco-toilet, the temperature of the reaction chamber plays a crucial role in the effective decomposition and utilization of human excreta. In this paper, an FPGA-based reaction chamber thermal control system is proposed. The system combines with explosion-proof temperature sensor and DC water pump, which can control and keep the temperature of reaction chamber in a proper range. The experimental results show the efficacy of the system, demonstrating that the proposed system can promote the development of new green Eco-toilet.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"38 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":"124747650","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.2019.8896442
Yongquan Xia, Xiwang Xie, Xinwen Wu, Jun Zhi, Sihai Qiao
Liver region extraction in abdominal CT images is a very important research field, a method of liver segmentation based on region growing for automatic selection of seed points is proposed in this paper. Firstly, the original image is binarized, and the initial area of the liver is extracted by the maximum area measurement method; After that, the improved region growth algorithm was used to segment the liver, and the location of seed points was automatically obtained by finding the center of the maximum inscribed circle locked in the initial liver area, which was used as the basis for the selection of seed points; Finally, the segmented liver region is treated by morphological methods. The experimental results show that the approach effectively solves the problem of manually selecting seed points for regional growth, and can improve the efficiency and accuracy of seed point selection, which avoids the selection of seed points at the wrong positions such as edges or noise due to subjective factors.
{"title":"An Approach of Automatically Selecting Seed Point Based on Region Growing for Liver Segmentation","authors":"Yongquan Xia, Xiwang Xie, Xinwen Wu, Jun Zhi, Sihai Qiao","doi":"10.1109/ISNE.2019.8896442","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896442","url":null,"abstract":"Liver region extraction in abdominal CT images is a very important research field, a method of liver segmentation based on region growing for automatic selection of seed points is proposed in this paper. Firstly, the original image is binarized, and the initial area of the liver is extracted by the maximum area measurement method; After that, the improved region growth algorithm was used to segment the liver, and the location of seed points was automatically obtained by finding the center of the maximum inscribed circle locked in the initial liver area, which was used as the basis for the selection of seed points; Finally, the segmented liver region is treated by morphological methods. The experimental results show that the approach effectively solves the problem of manually selecting seed points for regional growth, and can improve the efficiency and accuracy of seed point selection, which avoids the selection of seed points at the wrong positions such as edges or noise due to subjective factors.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":"9 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":"124793761","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：