发布求助
文献互助 智能选刊 最新文献

2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)最新文献

筛选
英文 中文
A novel framework for reservoir computing with inertial manifolds 一种新的惯性流形油藏计算框架
2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Pub Date : 2021-04-13 DOI: 10.1109/ICAIIC51459.2021.9415194
H. Honda
{"title":"A novel framework for reservoir computing with inertial manifolds","authors":"H. Honda","doi":"10.1109/ICAIIC51459.2021.9415194","DOIUrl":"https://doi.org/10.1109/ICAIIC51459.2021.9415194","url":null,"abstract":"Reservoir computing based on machine learning has garnered significant attention in the field of research regrading time series prediction. Active discussions that were recently held on the theoretical background aided the reservoir to realize some desired properties. In this study, we propose a reservoir computing framework based on the theory of inertial manifolds. Using the theoretical results for infinite-dimensional dynamical systems, we first introduce a new formulation of the echo state network as an extension of our previous work on multivariate input.","PeriodicalId":432977,"journal":{"name":"2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127371794","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
Interference Cancellation and Proper Thresholding Using Deep Learning Method in Optical Camera Communication 光学相机通信中基于深度学习的干扰消除与阈值处理
2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Pub Date : 2021-04-13 DOI: 10.1109/ICAIIC51459.2021.9415284
Md. Faisal Ahmed, Md. Osman Ali, Md. Morshed Alam, Y. Jang
{"title":"Interference Cancellation and Proper Thresholding Using Deep Learning Method in Optical Camera Communication","authors":"Md. Faisal Ahmed, Md. Osman Ali, Md. Morshed Alam, Y. Jang","doi":"10.1109/ICAIIC51459.2021.9415284","DOIUrl":"https://doi.org/10.1109/ICAIIC51459.2021.9415284","url":null,"abstract":"During data collection from the images using rolling shutter effect in the optical camera communication, interference from the surrounding light source reduce the system performances. On the other hand, thresholding problem creates after getting the normalized intensity from the image when number of sources appear in the camera’s field of view. Therefore, we applied deep learning approach for removing the interfering light sources and use synchronous thresholding method for data correction. We also observed the performance of signal-error-rate of the system in different condition in Python environment.","PeriodicalId":432977,"journal":{"name":"2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127499135","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: 1
Object Recognition and Distance Extraction System Using Camera 基于摄像机的目标识别与距离提取系统
2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Pub Date : 2021-04-13 DOI: 10.1109/ICAIIC51459.2021.9415219
Youngjin Yoon, Dongseok Han
{"title":"Object Recognition and Distance Extraction System Using Camera","authors":"Youngjin Yoon, Dongseok Han","doi":"10.1109/ICAIIC51459.2021.9415219","DOIUrl":"https://doi.org/10.1109/ICAIIC51459.2021.9415219","url":null,"abstract":"This paper proposes a system that detects an object around a vehicle and extracts the distance of the object through vehicle sensor fusion. Unlike the camera and lidar calibration method used in the past, in this paper, the region of interest (ROI) of the frame of the image received through the camera was divided by a 2x3 ratio to perform the lidar and calibration. In addition, we propose an algorithm that detects an object through only the camera using the correction coefficient obtained through calibration of the camera and lidar and indicates the distance of the classified object.","PeriodicalId":432977,"journal":{"name":"2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123755650","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
Effects of annotation quality on model performance 标注质量对模型性能的影响
2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Pub Date : 2021-04-13 DOI: 10.1109/ICAIIC51459.2021.9415271
Khaled Alhazmi, Walaa Alsumari, Indrek Seppo, L. Podkuiko, Martin Simon
{"title":"Effects of annotation quality on model performance","authors":"Khaled Alhazmi, Walaa Alsumari, Indrek Seppo, L. Podkuiko, Martin Simon","doi":"10.1109/ICAIIC51459.2021.9415271","DOIUrl":"https://doi.org/10.1109/ICAIIC51459.2021.9415271","url":null,"abstract":"Supervised machine learning generally requires pre-labelled data. Although there are several open access and pre-annotated datasets available for training machine learning algorithms, most contain a limited number of object classes, which may not be suitable for specific tasks. As previously available pre-annotated data is not usually sufficient for custom models, most of the real world applications require collecting and preparing training data. There is an obvious trade-off between annotation quality and quantity. Time and resources can be allocated for ensuring superior data quality or for increasing the quantity of the annotated data. We test the degree of the detrimental effect caused by the annotation errors. We conclude that while the results deteriorate if annotations are erroneous; the effect – at least while using relatively homogeneous sequential video data – is limited. The benefits from the increased annotated data set size (created by using imperfect auto-annotation methods) outweighs the deterioration caused by annotated data.","PeriodicalId":432977,"journal":{"name":"2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126471539","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: 4
SPB-YOLO: An Efficient Real-Time Detector For Unmanned Aerial Vehicle Images SPB-YOLO:一种高效的无人机图像实时检测器
2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Pub Date : 2021-04-13 DOI: 10.1109/ICAIIC51459.2021.9415214
Xinran Wang, Weihong Li, Wei Guo, Kun Cao
{"title":"SPB-YOLO: An Efficient Real-Time Detector For Unmanned Aerial Vehicle Images","authors":"Xinran Wang, Weihong Li, Wei Guo, Kun Cao","doi":"10.1109/ICAIIC51459.2021.9415214","DOIUrl":"https://doi.org/10.1109/ICAIIC51459.2021.9415214","url":null,"abstract":"Recently, using unmanned Aerial Vehicle(UAV) to capture images has become a popular application. However, the large scale variation and dense object distribution characteristic of UAV images brings challenges to object detection. Hence, we propose an efficient end-to-end detector named SPB-YOLO for UAV images. In this paper, firstly we design a Strip Bottleneck (SPB) module to better understand the width-height dependency by using an attention mechanism for improving the detection sensitivity of different scales’ objects in the UAV image. Secondly, we propose an upsample strategy based on Path Aggregation Network(PANet) for the feature map and add another one detection head compared to YOLOv5, which specially deal with the detection task of dense objects distribution. Finally, we execute some experiments on two public datasets, and the results show that the proposed SPBYOLO outperforms other latest UAV image detectors and makes a good trade-off between detection accuracy and speed.","PeriodicalId":432977,"journal":{"name":"2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128363206","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: 15
An Energy Efficient Sensor Duty Cycling for Smart Home Networks 智能家庭网络的节能传感器占空比
2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Pub Date : 2021-04-13 DOI: 10.1109/ICAIIC51459.2021.9415223
Murad Khan, Junho Seo, Dongkyun Kim
{"title":"An Energy Efficient Sensor Duty Cycling for Smart Home Networks","authors":"Murad Khan, Junho Seo, Dongkyun Kim","doi":"10.1109/ICAIIC51459.2021.9415223","DOIUrl":"https://doi.org/10.1109/ICAIIC51459.2021.9415223","url":null,"abstract":"Wireless Sensor Networks (WSN) applications are envisioned in various smart environments such as smart homes, smart cities, e-health, etc. Similarly, in future smart homes, an extensive sensor deployment would be required to control various home resident activities. However, deploying many sensors and operate them continuously requires a high amount of electrical energy. Therefore, in this paper, we presented a solution to prolong the sensors’ battery life by assigning the pre-detected slots to the sensors using Bayesian Network (BN). Among the rest of the Idle Sensors (IS), a Watch Sensor (WS) is selected to detect the upcoming activities and activate the rest of the closely related sensors to the WS. The similarities between IS sensors are modeled using the Earth Mover’s Distance (EMD) approach. Finally, an extensive set of simulations is performed in a smart home scenario to test the proposed scheme’s performance. The simulation results show that the proposed approach significantly enhances the sensors’ battery lifetime by scheduling the sensors’ operational time to detect smart home resident activities.","PeriodicalId":432977,"journal":{"name":"2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129979916","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
Ego Network-based Virtual Network Embedding Scheme for Revenue Maximization 基于自我网络的收益最大化虚拟网络嵌入方案
2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Pub Date : 2021-04-13 DOI: 10.1109/ICAIIC51459.2021.9415185
Ihsan Ullah, Hyun-kyo Lim, Youn-Hee Han
{"title":"Ego Network-based Virtual Network Embedding Scheme for Revenue Maximization","authors":"Ihsan Ullah, Hyun-kyo Lim, Youn-Hee Han","doi":"10.1109/ICAIIC51459.2021.9415185","DOIUrl":"https://doi.org/10.1109/ICAIIC51459.2021.9415185","url":null,"abstract":"Network Virtualization (NV) technology allows multiple virtual network requests to share resources on the same subtract network. In network virtualization, Virtual Network Embedding (VNE) is one of the main techniques used to map a virtual network to the substrate network. The effectiveness and efficiency of the virtual network are determined by the performance of the embedding algorithm. Hence, an efficient embedding algorithm is required to reduce the rejection rate and embed the maximum number of virtual networks which best fit the subtract network. In this article, we propose Ego Network-based Virtual Network Embedding (EN-ViNE) algorithm which aims to improve the performance of the embedding to accept more VNRs and increase the long-term revenue. We utilize the ego-network technique to search the nearest subtract nodes for embedding virtual nodes and found the shortest path between them for link embedding. The proposed scheme attempts to minimize the rejection of virtual network requests (VNRs) that are intended to maximize the long-term revenue for the substrate network provider. Extensive computer simulation reveals that the proposed scheme considerably outperforms the existing algorithms, topology-aware, and baseline for the long-term average revenue, acceptance ratio, and revenue/cost ratio.","PeriodicalId":432977,"journal":{"name":"2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132498713","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: 4
Fuzzy C-Means Clustering-Based mMIMO-NOMA Downlink Communication for 6G Ultra-Massive Interconnectivity 基于模糊c均值聚类的6G超大规模互联mimo - noma下行通信
2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Pub Date : 2021-04-13 DOI: 10.1109/ICAIIC51459.2021.9415222
M. Shahjalal, Md. Faisal Ahmed, Md. Morshed Alam, Md. Habibur Rahman, Y. Jang
{"title":"Fuzzy C-Means Clustering-Based mMIMO-NOMA Downlink Communication for 6G Ultra-Massive Interconnectivity","authors":"M. Shahjalal, Md. Faisal Ahmed, Md. Morshed Alam, Md. Habibur Rahman, Y. Jang","doi":"10.1109/ICAIIC51459.2021.9415222","DOIUrl":"https://doi.org/10.1109/ICAIIC51459.2021.9415222","url":null,"abstract":"Cooperation between massive multiple input multiple output (mMIMO) and non-orthogonal multiple access (NOMA) can significantly boost the future sixth-generation (6G) network capacity supporting ultra-massive interconnectivity. Co-operative mMIMO-NOMA has been recently considered in 6G high frequency spectrum such as Millimeter Wave and Terahertz because of its enhanced spectral efficiency property. Moreover, hybrid precoding is used importantly in such communications to reduce the overhead of high power consumption and increase the hardware cost performance. In this paper, we present a sub-array mMIMO-NOMA based downlink network architecture for 6G ultra-massive interconnectivity. A fully-connected hybrid precoding scheme is also considered incorporating with the system which supports equal performance with reduced number of RF chain than a fully-connected digital precoder. In addition, fuzzy c-means clustering algorithm is proposed for huddling the users of the mMIMO-NOMA based communication networks. The algorithm is performed on the received signal strength indicator data set, and the resulting clusters can be used to maximize the power and energy efficiency of the network.","PeriodicalId":432977,"journal":{"name":"2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128540369","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
Classification of Metastatic Breast Cancer Cell using Deep Learning Approach 利用深度学习方法对转移性乳腺癌细胞进行分类
2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Pub Date : 2021-04-13 DOI: 10.1109/ICAIIC51459.2021.9415245
Seohyun Lee, Hyuno Kim, H. Higuchi, M. Ishikawa
{"title":"Classification of Metastatic Breast Cancer Cell using Deep Learning Approach","authors":"Seohyun Lee, Hyuno Kim, H. Higuchi, M. Ishikawa","doi":"10.1109/ICAIIC51459.2021.9415245","DOIUrl":"https://doi.org/10.1109/ICAIIC51459.2021.9415245","url":null,"abstract":"Metastasis of cancer cells is one of the major reasons for cancer mortality, as an indicator of the stage of cancer. Since the degree of metastasis is often dependent upon the cancer cell mobility which is closely related to the shape of the cell, analyzing the cell shape is an essential factor to determine whether a cellular sample develops into a malignant tumor. In this paper, we attempted to classify two types of breast cancer cells based on their cell shapes, using a deep-learning approach.","PeriodicalId":432977,"journal":{"name":"2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134215008","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: 5
Reinforcement Learning for Random Access in Multi-cell Networks 多单元网络随机访问的强化学习
2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Pub Date : 2021-04-13 DOI: 10.1109/ICAIIC51459.2021.9415281
Dongwook Lee, Yu Zhao, Joohyung Lee
{"title":"Reinforcement Learning for Random Access in Multi-cell Networks","authors":"Dongwook Lee, Yu Zhao, Joohyung Lee","doi":"10.1109/ICAIIC51459.2021.9415281","DOIUrl":"https://doi.org/10.1109/ICAIIC51459.2021.9415281","url":null,"abstract":"In this paper, our goal is to maximize the system throughput in a time-slotted uplink multi-cell random access communication system. To this end, we propose a two-stage reinforcement learning (RL)-based algorithm based on the exponential-weight algorithm for exploration and exploitation (EXP3). In each macro-time slot that consists of multiple time slots, users run the RL-based algorithm to choose the associated access point (AP). Then, a transmission policy determines the sub-time slot that user will transmit data in each time slot. Another RL-based learning algorithm is used to obtain an optimal transmission policy. To show that our method is efficient, we compare our proposed algorithm with the $epsilon$-greedy algorithm in two different scenarios. The simulation results show that the average system throughput of our algorithm outperforms that of $epsilon$-greedy exploration.","PeriodicalId":432977,"journal":{"name":"2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134072356","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信