检索结果-内蒙古大学图书馆

Improvement of Erase Performance Using p-Type Gate in IGZO Channel-Based 3D NAND Flash

IEEE Access 2025年 13卷 32237-32247页

作者： Suh, Minkyo Jung, Youngho Kang, Daewoong Chung-Ang University School of Integrative Engineering Seoul06974 Korea Republic of Seoul National University Next Generation Semiconductor Convergence and Open Sharing System Seoul08826 Korea Republic of Daegu University Department of Electronic and Electrical Engineering Gyeongsangbuk-do Gyeongsan-si38453 Korea Republic of

A novel structure using p-doped polysilicon with a new program/erase scheme is proposed for the first time in this paper to enhance erase performance in amorphous indium gallium zinc oxide (IGZO) channel 3D-NAND Flash. In the proposed structure, the tunneling of both electrons and holes occurs simultaneously during program and erase operation. Electron tunneling is dominant at the center of the cell, while hole tunneling is dominant at the cell corners in the erase operation. By adjusting the pass voltage of adjacent cells, the programming and erasing of the cell were switched. To evaluate the program and erase performance of the proposed structure, the incremental step pulse program (ISPP) and the incremental step pulse erase (ISPE) characteristics were compared with basic IGZO channel structures and polysilicon channel structures. The proposed structure overcomes the poor erase performance of the conventional IGZO channel structure. Also, it showed better erase performance compared to the IGZO channel structure and conventional polysilicon channel structure. The program and erase performances were optimized through engineering the O/N/O layer. © 2025 The Authors.

关键词： Electron tunneling

来源：评论

学校读者我要写书评

暂无评论

Development of High Density 3D NAND Flash Memory Using New Scaling Technologies for AI semiconductor

Development of High Density 3D NAND Flash Memory Using New S...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Daewoong Kang Minkyo Suh Gwansun Choi Chaeyeon Jung Next Generation Semiconductor Convergence and Open Sharing System Seoul National University South Korea Soongsil University South Korea Chung-Ang University South Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Scaling technology of 3D NAND flash is recently required to implement large-capacity memory and high performance due to recent demand of AI semiconductors. However, it is suffering from the critical issues such as cell current, cell to cell interference and retention characteristics. In this paper, the new methods that enable for device scaling and performance were introduced.

关键词： Performance evaluation Three-dimensional displays Memory management Interference Flash memories Artificial intelligence next generation networking Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Reduce A Visual Gap Using Inpainting GAN

A Novel Approach to Reduce A Visual Gap Using Inpainting GAN

引用

2023 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2023

作者： Truong, Thanh Hien Lee, Tae-Ho Munasinghe, Viduranga Kim, Tae-Sung Kim, Jin-Sung Lee, Hyuk-Jae Seoul National University Electrical and Computer Engineering Korea Republic of Seoul National University Next-Generation Semiconductor Convergence and Open Sharing System Korea Republic of Sun Moon University Department of Electronic Engineering Korea Republic of

ISBN: (纸本)9798350344318

Image blending represents a technique employed in image composition, aimed at creating a composite image that appears as natural and realistic as possible. The objective of image blending is to ensure that the transitions between objects in the image appear seamless and without any color distortion. Recently, numerous studies investigated image blending methods adopting deep learning-based image processing algorithms and contributed to generating natural blended images. Although the previous studies show remarkable performance in many cases, they suffer from quality drop when blending incompletely cropped object. This paper introduces a novel approach that effectively reduces the unnatural edges and the color distortion in such cases. In this study, an algorithm which called edge checking (EC) is proposed to identify and manage incompletely cropped regions. To address missing or masked parts of the object image and integrate them into the image blending process, an inpainting generative adversarial model are employed. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Towards Eight-Bit Quantization for 3D U-Net Medical Image Segmentation via ROI-Based Calibration and Background-Aware Shift

Towards Eight-Bit Quantization for 3D U-Net Medical Image Se...

引用

2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Kim, Soosung Cha, Mincheol Yi, Chaehag Nguyen, Xuan Truong Chungang University Department of Electrical and Computer Engineering Seoul Korea Republic of Seoul National University Department of Electrical and Computer Engineering Seoul Korea Republic of Seoul National University Department of Next Generation Semiconductor Convergence and Open Sharing System Seoul Korea Republic of

ISBN: (纸本)9798331530839

3D U-Net medical image segmentation is essential for precise diagnosis and treatment planning but comes with massive bandwidth requirements and considerable computational costs. Eight-bit fixed-point quantization is crucial for efficient 3D U-Net inference on modern deep learning accelerators. However, quantizing a 3D U-Net model is non-trivial and frequently leads to unfavorable accuracy degradation. We empirically observed that large range imbalances between tumor/non-tumor voxels and foreground/background areas are the main contributing factors. Based on these findings, we propose an eight-bit quantization method with a simple yet effective ROI-based calibration and a background shift that captures outliers in tumor areas to avoid accuracy degradation. Moreover, our method incorporates instance normalization folding, which eliminates computation-intensive operations during inference. Experimental results on the KITS19 dataset show that the proposed method with integer-only arithmetic achieves a negligible accuracy drop, i.e., 0.4%p in the dice score, compared to the FP32 model. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

CNN-based Hand Gesture Recognition for Contactless Elevator Button Control

CNN-based Hand Gesture Recognition for Contactless Elevator ...

引用

2023 International Conference on Electronics, Information, and Communication, ICEIC 2023

作者： Taeho-Lee Munasinghe, Viduranga Li, Yan-Mei Sung Kim, Tae Lee, Hyuk-Jae Seoul National University Next-Generation Semiconductor Convergence and Open Sharing System Seoul08826 Korea Republic of Seoul National University Department of Electrical and Computer Engineering Seoul08826 Korea Republic of Sun Moon University Department of Electronic Engineering Asan31460 Korea Republic of

ISBN: (纸本)9798350320213

Recently, with the outbreak of the COVID-19 pandemic, various quarantine measures have been implemented to reduce the spread of the virus. As a part of efforts, the preference for touchless technology has been emerging. In this paper, we propose a touchless elevator control system using CNN-based hand gesture recognition. Experimental results show that the hand recognition AP and FPS on the Jetson TX2 board are 81.87% and 11.8FPS, respectively. We demonstrate that an elevator model could be controlled by virtual elevator buttons utilizing CNN-based hand gesture recognition. The proposed method can be applied to commercial elevators as an approach to prevent the spread of viruses from elevator buttons. © 2023 IEEE.

关键词： contactless elevator control Convolutional neural networks deep learning hand gesture recognition Jetson GPU board

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Reduce A Visual Gap Using Inpainting GAN

A Novel Approach to Reduce A Visual Gap Using Inpainting GAN

引用

IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)

作者： Thanh Hien Truong Tae-Ho Lee Viduranga Munasinghe Tae-Sung Kim Jin-Sung Kim Hyuk-Jae Lee Electrical and Computer Engineering Seoul National University Next-Generation Semiconductor Convergence and Open Sharing System Seoul National University Department of Electronic Engineering Sun Moon University

关键词：

来源：评论

学校读者我要写书评

暂无评论

CNN-based Hand Gesture Recognition for Contactless Elevator Button Control

CNN-based Hand Gesture Recognition for Contactless Elevator ...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Taeho-Lee Viduranga Munasinghe Yan-Mei Li Tae Sung Kim Hyuk-Jae Lee Next-Generation Semiconductor Convergence and Open Sharing System Seoul National University Seoul Korea Department of Electrical and Computer Engineering Seoul National University Seoul Korea Department of Electronic Engineering Sun Moon University Asan Korea

关键词： COVID-19 Deep learning Computer viruses Pandemics Graphics processing units Gesture recognition Control systems

来源：评论

学校读者我要写书评

暂无评论

Towards Eight-Bit Quantization for 3D U-Net Medical Image Segmentation via ROI-Based Calibration and Background-Aware Shift

Towards Eight-Bit Quantization for 3D U-Net Medical Image Se...

引用

IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)

作者： Soosung Kim Mincheol Cha Chaehag Yi Xuan Truong Nguyen Department of Electrical and Computer Engineering Chungang University Seoul Korea Department of Electrical and Computer Engineering Seoul National University Seoul Korea Department of Next Generation Semiconductor Convergence and Open Sharing System Seoul National University Seoul Korea

ISBN: (数字)9798331530839

ISBN: (纸本)9798331530846

关键词： Degradation Image segmentation Solid modeling Three-dimensional displays Quantization (signal) Accuracy Computational modeling Calibration Medical diagnostic imaging Tumors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：