Pub Date : 2019-03-14DOI: 10.1109/INFOCT.2019.8710893
Abeer Alsaiari, Ridhi Rustagi, A. Alhakamy, M. M. Thomas, A. Forbes
Animation studios render 3D scenes using a technique called path tracing which enables them to create high quality photorealistic frames. Path tracing involves shooting 1000’s of rays into a pixel randomly (Monte Carlo) which will then hit the objects in the scene and, based on the reflective property of the object, these rays reflect or refract or get absorbed. The colors returned by these rays are averaged to determine the color of the pixel. This process is repeated for all the pixels. Due to the computational complexity it might take 8–16 hours to render a single frame. We implemented a neural network-based solution to reduce the time it takes to render a frame to less than a second using a generative adversarial network (GAN), once the network is trained. The main idea behind this proposed method is to render the image using a much smaller number of samples per pixel than is normal for path tracing (e.g., 1, 4, or 8 samples instead of, say, 32,000 samples) and then pass the noisy, incompletely rendered image to our network, which is capable of generating a high-quality photorealistic image.
{"title":"Image Denoising Using A Generative Adversarial Network","authors":"Abeer Alsaiari, Ridhi Rustagi, A. Alhakamy, M. M. Thomas, A. Forbes","doi":"10.1109/INFOCT.2019.8710893","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8710893","url":null,"abstract":"Animation studios render 3D scenes using a technique called path tracing which enables them to create high quality photorealistic frames. Path tracing involves shooting 1000’s of rays into a pixel randomly (Monte Carlo) which will then hit the objects in the scene and, based on the reflective property of the object, these rays reflect or refract or get absorbed. The colors returned by these rays are averaged to determine the color of the pixel. This process is repeated for all the pixels. Due to the computational complexity it might take 8–16 hours to render a single frame. We implemented a neural network-based solution to reduce the time it takes to render a frame to less than a second using a generative adversarial network (GAN), once the network is trained. The main idea behind this proposed method is to render the image using a much smaller number of samples per pixel than is normal for path tracing (e.g., 1, 4, or 8 samples instead of, say, 32,000 samples) and then pass the noisy, incompletely rendered image to our network, which is capable of generating a high-quality photorealistic image.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132386538","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8710969
Jingren Zhang, Fang’ai Liu, Weizhi Xu
Constructing a model of online film and television commentary sentiment classification can effectively guide film and television producers to comprehensively understand the audience acceptance of film and television works, and improve it. Traditional methods based on sentiment lexicon and machine learning exist in a series of Insufficient: ignore context semantics, too single word, sparse features, etc. Based on the existing convolutional neural network model, this paper systematically optimizes its internal structure, and proposes a NCNM (New Convolutional Neural Network model) model based on multi-sliding window and new pooling method, and uses feature vectors to cluster feature words. . In this paper, the Stanford SST dataset and Cornell MRD dataset are used to verify the classification effect of the proposed model. The experimental results show that ncnnm has a certain improvement in the accuracy of the emotional classification of short text video reviews compared with the existing mainstream methods..
构建网络影视评论情感分类模型，可以有效指导影视制作方全面了解影视作品的受众接受程度，并对其进行改进。传统的基于情感词典和机器学习的方法存在着一系列不足:忽略语境语义、过于单字、特征稀疏等。本文在现有卷积神经网络模型的基础上，对其内部结构进行了系统优化，提出了一种基于多滑动窗口和新池化方法的NCNM (New convolutional neural network model)模型，并利用特征向量对特词词进行聚类。本文使用Stanford SST数据集和Cornell MRD数据集验证了所提出模型的分类效果。实验结果表明，与现有的主流方法相比，ncnnm在短文本视频评论情感分类的准确率上有一定的提高。
{"title":"The Application of An Optimized Convolutional Neural Network Model in Film Criticism","authors":"Jingren Zhang, Fang’ai Liu, Weizhi Xu","doi":"10.1109/INFOCT.2019.8710969","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8710969","url":null,"abstract":"Constructing a model of online film and television commentary sentiment classification can effectively guide film and television producers to comprehensively understand the audience acceptance of film and television works, and improve it. Traditional methods based on sentiment lexicon and machine learning exist in a series of Insufficient: ignore context semantics, too single word, sparse features, etc. Based on the existing convolutional neural network model, this paper systematically optimizes its internal structure, and proposes a NCNM (New Convolutional Neural Network model) model based on multi-sliding window and new pooling method, and uses feature vectors to cluster feature words. . In this paper, the Stanford SST dataset and Cornell MRD dataset are used to verify the classification effect of the proposed model. The experimental results show that ncnnm has a certain improvement in the accuracy of the emotional classification of short text video reviews compared with the existing mainstream methods..","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130447338","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 : 2019-03-14DOI: 10.1109/INFOCT.2019.8711434
Trevor Hillsgrove, Robert Steele
The all-condition prediction of patient mortality at the time of hospital admission has significant clinical value and broader implications for patient care and clinical decision support capabilities. In this study we have applied machine learning models to predict inpatient mortality, that is whether a patient will die during the hospital stay, as predicted from a time near to admission. We have utilized an Agency for Healthcare Research and Quality-provided large dataset of hospital discharges, to develop and evaluate a number of machine learning models. We report on the performance of the best performing of these models, with the best performing model having an AUC score of 0.802. We also evaluate the generalizability of the models via evaluating these on a separate large dataset corresponding to a different time period. We describe the results and provide an analysis and discussion of their significance.
{"title":"Utilization of Data Mining for Generalizable, All-Admission Prediction of Inpatient Mortality","authors":"Trevor Hillsgrove, Robert Steele","doi":"10.1109/INFOCT.2019.8711434","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711434","url":null,"abstract":"The all-condition prediction of patient mortality at the time of hospital admission has significant clinical value and broader implications for patient care and clinical decision support capabilities. In this study we have applied machine learning models to predict inpatient mortality, that is whether a patient will die during the hospital stay, as predicted from a time near to admission. We have utilized an Agency for Healthcare Research and Quality-provided large dataset of hospital discharges, to develop and evaluate a number of machine learning models. We report on the performance of the best performing of these models, with the best performing model having an AUC score of 0.802. We also evaluate the generalizability of the models via evaluating these on a separate large dataset corresponding to a different time period. We describe the results and provide an analysis and discussion of their significance.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115041211","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 : 2019-03-01DOI: 10.1109/INFOCT.2019.8710861
Sayyed Jaffar Ali Raza, Mingjie Lin
We present reusable policy method for modular reinforcement learning problem in continuous state space. Our method relies on two-layered learning architecture. The first layer partitions the agent’s problem space into n-folds sub-agents that are inter-connected with each other with dexterity identical to original problem. It further learns a local control policy for standalone 1-fold sub-agent. The second layer learns a global policy to reuse ‘already learnt’ standalone local policy over each n sub-agents by sampling local policy with global parameters for each sub-agent—parameterizing local policy independently to approximate non-linear interconnections between sub-agents. We demonstrate our method on simulation example of 12-DOF modular robot that learns maneuver pattern of snake-like gait. We also compare our proposed method against standard single-policy learning methods to benchmark optimality.
{"title":"Policy Reuse in Reinforcement Learning for Modular Agents","authors":"Sayyed Jaffar Ali Raza, Mingjie Lin","doi":"10.1109/INFOCT.2019.8710861","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8710861","url":null,"abstract":"We present reusable policy method for modular reinforcement learning problem in continuous state space. Our method relies on two-layered learning architecture. The first layer partitions the agent’s problem space into n-folds sub-agents that are inter-connected with each other with dexterity identical to original problem. It further learns a local control policy for standalone 1-fold sub-agent. The second layer learns a global policy to reuse ‘already learnt’ standalone local policy over each n sub-agents by sampling local policy with global parameters for each sub-agent—parameterizing local policy independently to approximate non-linear interconnections between sub-agents. We demonstrate our method on simulation example of 12-DOF modular robot that learns maneuver pattern of snake-like gait. We also compare our proposed method against standard single-policy learning methods to benchmark optimality.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117142966","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 : 2019-03-01DOI: 10.1109/infoct.2019.8711159
{"title":"ICICT 2019 Message from the Program Chair","authors":"","doi":"10.1109/infoct.2019.8711159","DOIUrl":"https://doi.org/10.1109/infoct.2019.8711159","url":null,"abstract":"","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125133032","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 : 2019-03-01DOI: 10.1109/INFOCT.2019.8710982
A. Alhakamy, M. Tuceryan
Current augmented and mixed reality systems suffer a lack of correct illumination modeling where the virtual objects render the same lighting condition as the real environment. While we are experiencing astonishing results from the entertainment industry in multiple media forms, the procedure is mostly accomplished offline. The illumination information extracted from the physical scene is used to interactively render the virtual objects which results in a more realistic output in real-time. In this paper, we present a method that detects the physical illumination with dynamic scene, then uses the extracted illumination to render the virtual objects added to the scene. The method has three steps that are assumed to be working concurrently in real-time. The first is the estimation of the direct illumination (incident light) from the physical scene using computer vision techniques through a 360° live-feed camera connected to AR device. The second is the simulation of indirect illumination (reflected light) from the real-world surfaces to virtual objects rendering using region capture of 2D texture from the AR camera view. The third is defining the virtual objects with proper lighting and shadowing characteristics using shader language through multiple passes. Finally, we tested our work with multiple lighting conditions to evaluate the accuracy of results based on the shadow falling from the virtual objects which should be consistent with the shadow falling from the real objects with a reduced performance cost.
{"title":"AR360: Dynamic Illumination for Augmented Reality with Real-Time Interaction","authors":"A. Alhakamy, M. Tuceryan","doi":"10.1109/INFOCT.2019.8710982","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8710982","url":null,"abstract":"Current augmented and mixed reality systems suffer a lack of correct illumination modeling where the virtual objects render the same lighting condition as the real environment. While we are experiencing astonishing results from the entertainment industry in multiple media forms, the procedure is mostly accomplished offline. The illumination information extracted from the physical scene is used to interactively render the virtual objects which results in a more realistic output in real-time. In this paper, we present a method that detects the physical illumination with dynamic scene, then uses the extracted illumination to render the virtual objects added to the scene. The method has three steps that are assumed to be working concurrently in real-time. The first is the estimation of the direct illumination (incident light) from the physical scene using computer vision techniques through a 360° live-feed camera connected to AR device. The second is the simulation of indirect illumination (reflected light) from the real-world surfaces to virtual objects rendering using region capture of 2D texture from the AR camera view. The third is defining the virtual objects with proper lighting and shadowing characteristics using shader language through multiple passes. Finally, we tested our work with multiple lighting conditions to evaluate the accuracy of results based on the shadow falling from the virtual objects which should be consistent with the shadow falling from the real objects with a reduced performance cost.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130284795","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 : 2019-03-01DOI: 10.1109/INFOCT.2019.8711056
Y. Shaev, E. Samoylova
The information and computer technologies are developing very fast. Every year information and computer systems are becoming more complicated. Such new systems are gradually improving human/nonhuman interactions. Artificial intelligence also becomes smarter and smarter. Modern robots can solve not only the problems in the production of goods and services, transport and infrastructure issues, but they becoming an integral part of everyday human practices in the areas of life, communication, entertainment and leisure. An important feature of modern robots is their „human-like factor„, which is focusing not only on functionality, but also on humanoid characteristics of appearance, functions, senses, voice etc. Humanoid robots or androids need to „to be like a real human„, so they need to copy human activity. Androids are oriented to the reproduction or retranslation of archetypal images, rooted in culture and remaining relevant even in the modern world of high technologies. In this case, the most important issue is to understand the role of androids in the structures of everyday practice. Moreover, we need to rethink the phenomenology of their „physicality„, which is focused on patterns of human interactions and „communications„, to the possibilities of embedding into the structures of social interaction with reproduction of human behavior patterns. Some examples of rethinking of this, we can find in popular culture and computer games. These cultural phenomena help us to understand the transformation of the being of a modern human, his physicality and projection of his „I„ on technical devices and artificial intelligence.
{"title":"Phenomenology of Androids: Between Human and Non-human","authors":"Y. Shaev, E. Samoylova","doi":"10.1109/INFOCT.2019.8711056","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711056","url":null,"abstract":"The information and computer technologies are developing very fast. Every year information and computer systems are becoming more complicated. Such new systems are gradually improving human/nonhuman interactions. Artificial intelligence also becomes smarter and smarter. Modern robots can solve not only the problems in the production of goods and services, transport and infrastructure issues, but they becoming an integral part of everyday human practices in the areas of life, communication, entertainment and leisure. An important feature of modern robots is their „human-like factor„, which is focusing not only on functionality, but also on humanoid characteristics of appearance, functions, senses, voice etc. Humanoid robots or androids need to „to be like a real human„, so they need to copy human activity. Androids are oriented to the reproduction or retranslation of archetypal images, rooted in culture and remaining relevant even in the modern world of high technologies. In this case, the most important issue is to understand the role of androids in the structures of everyday practice. Moreover, we need to rethink the phenomenology of their „physicality„, which is focused on patterns of human interactions and „communications„, to the possibilities of embedding into the structures of social interaction with reproduction of human behavior patterns. Some examples of rethinking of this, we can find in popular culture and computer games. These cultural phenomena help us to understand the transformation of the being of a modern human, his physicality and projection of his „I„ on technical devices and artificial intelligence.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124507923","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 : 2019-03-01DOI: 10.1109/INFOCT.2019.8711021
Xuefeng Li, Xiaochuan Wu, Xin Pei, Zhuojun Yao
Token represents the right to do some operations in software. In blockchain, there are two types of tokens: utility token and security token. They endow the items of token more value in blockchain world. In order to achieve asset tokenization, we propose a new kind of token in this paper, the asset-backed token, which is used for the proposed blockchain based Open Asset Protocol (OAP). Using OAP, we show to how to convert both of the real and virtual objects to asset-backed tokens on blockchain. Then we discussed a new method for data utilization and privacy-preserving based on OAP and compare with our previous scheme, the Secure Multi-Party Computation (SMPC). Additionally, we introduce the Policy-Backed Token(PBT), which is an instance implementing OAP in insurance industry. We have applied PBT in the airline travel insurance product E-life of an insurance company.
{"title":"Tokenization: Open Asset Protocol on Blockchain","authors":"Xuefeng Li, Xiaochuan Wu, Xin Pei, Zhuojun Yao","doi":"10.1109/INFOCT.2019.8711021","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711021","url":null,"abstract":"Token represents the right to do some operations in software. In blockchain, there are two types of tokens: utility token and security token. They endow the items of token more value in blockchain world. In order to achieve asset tokenization, we propose a new kind of token in this paper, the asset-backed token, which is used for the proposed blockchain based Open Asset Protocol (OAP). Using OAP, we show to how to convert both of the real and virtual objects to asset-backed tokens on blockchain. Then we discussed a new method for data utilization and privacy-preserving based on OAP and compare with our previous scheme, the Secure Multi-Party Computation (SMPC). Additionally, we introduce the Policy-Backed Token(PBT), which is an instance implementing OAP in insurance industry. We have applied PBT in the airline travel insurance product E-life of an insurance company.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117032714","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 : 2019-03-01DOI: 10.1109/INFOCT.2019.8711436
Baoling Qin, Xiaowei Lin, Sina Li, Qiao Luo, F. Zheng, Jiejian Cai, Yunshi Luo
Fog computing based on big data is a hot topic in the research of computing technology at home and abroad. With the wide application and popularity of IoT (Internet of Things), the big data generated by edge devices is exploding, and cloud computing models are becoming increasingly inadequate to meet the needs of big data processing and communication, which is mainly manifested as follows. Slow data processing, insufficient storage space, prolonged communication and many other issues. Fog computing, of which the advantage is distributed computing, namely the „de-centralized„ mode calculation, is the suitable solution to solve these problems. In the IoT system, fog computing model based on big data is constructed to distribute the big data computing, storage and communication in the system to the edge device. The purpose is to make the system structure simpler, more modular and intelligent, duce network congestion, exploit advantages of edge devices and improve high quality intelligence of IoT applications, and moreover, to reduce the deployment of IoT hardware and operating costs. Taking the cloud robotics as an example, it is proposed to embed the fog computing technology in the cloud robotics system, which greatly improves the computing function of the cloud robotics system. In short, it provides theoretical support and scientific experimental basis for the informationization and intelligence of all walks of life, and its research has certain value and significance.
基于大数据的雾计算是国内外计算技术研究的热点。随着IoT (Internet of Things)的广泛应用和普及，边缘设备产生的大数据呈爆炸式增长，云计算模型越来越不能满足大数据处理和通信的需求，主要表现在以下几个方面。数据处理速度慢，存储空间不足，通信时间长等诸多问题。雾计算的优势在于分布式计算，即“去中心化”模式的计算，是解决这些问题的合适方案。在物联网系统中，构建基于大数据的雾计算模型，将系统中的大数据计算、存储、通信等工作分配给边缘设备。目的是使系统结构更简单、模块化和智能化，减少网络拥塞，发挥边缘设备的优势，提高物联网应用的高质量智能化，同时降低物联网硬件的部署和运营成本。以云机器人为例，提出在云机器人系统中嵌入雾计算技术，大大提高了云机器人系统的计算功能。总之，它为各行各业的信息化、智能化提供了理论支撑和科学实验依据，其研究具有一定的价值和意义。
{"title":"Design and Application of Fog Computing Model Based on Big Data","authors":"Baoling Qin, Xiaowei Lin, Sina Li, Qiao Luo, F. Zheng, Jiejian Cai, Yunshi Luo","doi":"10.1109/INFOCT.2019.8711436","DOIUrl":"https://doi.org/10.1109/INFOCT.2019.8711436","url":null,"abstract":"Fog computing based on big data is a hot topic in the research of computing technology at home and abroad. With the wide application and popularity of IoT (Internet of Things), the big data generated by edge devices is exploding, and cloud computing models are becoming increasingly inadequate to meet the needs of big data processing and communication, which is mainly manifested as follows. Slow data processing, insufficient storage space, prolonged communication and many other issues. Fog computing, of which the advantage is distributed computing, namely the „de-centralized„ mode calculation, is the suitable solution to solve these problems. In the IoT system, fog computing model based on big data is constructed to distribute the big data computing, storage and communication in the system to the edge device. The purpose is to make the system structure simpler, more modular and intelligent, duce network congestion, exploit advantages of edge devices and improve high quality intelligence of IoT applications, and moreover, to reduce the deployment of IoT hardware and operating costs. Taking the cloud robotics as an example, it is proposed to embed the fog computing technology in the cloud robotics system, which greatly improves the computing function of the cloud robotics system. In short, it provides theoretical support and scientific experimental basis for the informationization and intelligence of all walks of life, and its research has certain value and significance.","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116290295","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 : 2019-03-01DOI: 10.1109/infoct.2019.8711384
{"title":"ICICT 2019 Copyright Page","authors":"","doi":"10.1109/infoct.2019.8711384","DOIUrl":"https://doi.org/10.1109/infoct.2019.8711384","url":null,"abstract":"","PeriodicalId":369231,"journal":{"name":"2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117121308","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：