2022 13th International Conference on Information and Communication Technology Convergence (ICTC)最新文献_第10页

Design of Neural Network Model Converting Framework based on NNEF 基于NNEF的神经网络模型转换框架设计

2022 13th International Conference on Information and Communication Technology Convergence (ICTC) Pub Date : 2022-10-19 DOI: 10.1109/ICTC55196.2022.9952413

Kyung-Hee Lee, Jaebok Park, Seon-Tae Kim, J. Kwak, Chang-Sik Cho

{"title":"Design of Neural Network Model Converting Framework based on NNEF","authors":"Kyung-Hee Lee, Jaebok Park, Seon-Tae Kim, J. Kwak, Chang-Sik Cho","doi":"10.1109/ICTC55196.2022.9952413","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952413","url":null,"abstract":"There are various engines that process artificial neural networks, such as Caffe, PyTorch, and Darknet. These engines can be operated on PCs, servers, as well as on-board devices. To cope with this kind of the diversity in these computing environments and neural network engines, compatibility among these engines is emerging as an important issue. This paper describes a neural network model converting framework to provide compatibility among these neural network engines. In this paper, we adopted a pivot model that can be used as common format among the engines. This pivot model is NNEF that was proposed by Khronos Group. With NNEF, we designed Neural Network Model Converting Framework. This framework provides user interface that configures the conversion modules between NNEF format and neural network engine's model saving formats. The framework has Manager that enables conversion and optimization of the neural network models. We also made a prototype for this framework to verify its functionalities. The prototype was tested with a neural network that recognizes hand-written numbers on Darknet and PyTorch engines.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116641830","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

Beam Size Design for LEO Satellite Networks with Doppler Shift Characteristics 具有多普勒频移特性的LEO卫星网络波束尺寸设计

2022 13th International Conference on Information and Communication Technology Convergence (ICTC) Pub Date : 2022-10-19 DOI: 10.1109/ICTC55196.2022.9952738

S. Han, W. Shin, Jae-Hyun Kim

引用次数: 0

3D occluded object visualization by using integral imaging and semantic segmentation 基于积分成像和语义分割的三维遮挡物可视化

2022 13th International Conference on Information and Communication Technology Convergence (ICTC) Pub Date : 2022-10-19 DOI: 10.1109/ICTC55196.2022.9952712

Kazuaki Honda, Jaehoon Lee, Hyun-Woo Kim, Hideaki Uchino, M. Cho, Min-Chul Lee

{"title":"3D occluded object visualization by using integral imaging and semantic segmentation","authors":"Kazuaki Honda, Jaehoon Lee, Hyun-Woo Kim, Hideaki Uchino, M. Cho, Min-Chul Lee","doi":"10.1109/ICTC55196.2022.9952712","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952712","url":null,"abstract":"In this paper, we propose the improved occluded object visualization method by using integral imaging and semantic segmentation. Integral imaging is the passive 3D visualization technique that can generate 3D information through elemental images that have different perspectives of information on 3D objects. Moreover, it can be used to remove the occlusion in the 3D scene. The elemental image's various perspective information can be utilized to remove the occlusion in the 3D scene via the 3D image reconstruction process. However, the occlusion object pixels in the elemental image can degrade the image quality of the 3D image. Therefore, it is difficult to visualize the object without occlusion, clearly. To solve this problem, we propose the occluded object visualization method that can remove the occlusion and can visualize the target 3D object by using semantic segmentation. Semantic segmentation is the machine learning technique that can recognize the labeled object in the scene. Therefore, it can generate the specific labeled object mask image. Then, our proposed method can generate accurate 3D target object information. To prove our method, we carry out the simulation experiment and evaluate image quality with a correlation metric.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124929339","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: 2

FedDDoS: An Efficient Federated Learning-based DDoS Attacks Classification in SDN-Enabled IIoT Networks FedDDoS:基于sdn的工业物联网网络中基于联邦学习的高效DDoS攻击分类

2022 13th International Conference on Information and Communication Technology Convergence (ICTC) Pub Date : 2022-10-19 DOI: 10.1109/ICTC55196.2022.9952610

Ahmad Zainudin, Rubina Akter, Dong‐Seong Kim, Jae-Min Lee

引用次数: 2

A Machine Learning based Scalable Blockchain architecture for a secure Healthcare system 用于安全医疗保健系统的基于机器学习的可扩展区块链架构

2022 13th International Conference on Information and Communication Technology Convergence (ICTC) Pub Date : 2022-10-19 DOI: 10.1109/ICTC55196.2022.9952962

Mikail Mohammed Salim, Laihyuk Park, Jong Hyuk Park

{"title":"A Machine Learning based Scalable Blockchain architecture for a secure Healthcare system","authors":"Mikail Mohammed Salim, Laihyuk Park, Jong Hyuk Park","doi":"10.1109/ICTC55196.2022.9952962","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952962","url":null,"abstract":"The evolution of the Industrial revolution from 3.0 to 4.0 has transformed the Healthcare environment. Patient Electronic Health Records (EHR) are shared with medical research institutes for clinical research and to manage national disease outbreaks. Healthcare systems implementing centralized machine learning models risk cyberattacks exposing private patient data. Blockchain-based data storage systems enable data security of EHR. However, the low transactions/minute of decentralized systems limit the performance of Healthcare systems and increase network bottleneck concerns. In this paper, we propose a Machine Learning based Blockchain architecture for secure Healthcare systems to preserve patient data privacy using Federated Learning and address Blockchain bottleneck issues by adding sidechains for processing growing transaction requests. A local model using machine learning trains data locally in hospitals and uploads it via Smart Contracts to the Public Healthcare System for global model training. Sidechains enable increased processing speed of Smart Contracts reducing congestions in the network and increasing the transactions per second in the mainchain.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121337922","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: 2

Evaluation of Hydrogen Safety Leakage Risk using Pseudo Hydrogen Leakage(%) 用伪氢气泄漏量(%)评价氢气安全泄漏风险

2022 13th International Conference on Information and Communication Technology Convergence (ICTC) Pub Date : 2022-10-19 DOI: 10.1109/ICTC55196.2022.9952932

Hyunmi Lee, Jeong-Ah Jang, Yongju Yi, Si-Woo Kim

引用次数: 0

Generating and Modifying High Resolution Fashion Model Image using StyleGAN 生成和修改高分辨率时尚模型图像使用StyleGAN

2022 13th International Conference on Information and Communication Technology Convergence (ICTC) Pub Date : 2022-10-19 DOI: 10.1109/ICTC55196.2022.9952574

I. Choi, Soonchan Park, Jiyoung Park

引用次数: 3

Topic Modelling Supreme Court Case Decisions using Latent Dirichlet Allocation 题目用潜在狄利克雷分配模拟最高法院案件判决

2022 13th International Conference on Information and Communication Technology Convergence (ICTC) Pub Date : 2022-10-19 DOI: 10.1109/ICTC55196.2022.9952945

Bermylle John U. Razon, Geoffrey A. Solano, Lorenz Timothy B. Ranera

引用次数: 0

UAV arming Authorization using DIM and Flight Authorization Code 无人机武装授权使用DIM和飞行授权代码

2022 13th International Conference on Information and Communication Technology Convergence (ICTC) Pub Date : 2022-10-19 DOI: 10.1109/ICTC55196.2022.9952583

Ju-Han Kim, Yousung Kang

引用次数: 0

Lazy Net: Lazy Entry Neural Networks for Accelerated and Efficient Inference 懒网:用于加速和高效推理的懒入口神经网络

2022 13th International Conference on Information and Communication Technology Convergence (ICTC) Pub Date : 2022-10-19 DOI: 10.1109/ICTC55196.2022.9953031

Junyong Park, Dae-Young Kim, Yong-Hyuk Moon

引用次数: 0