发布求助
文献互助 智能选刊 最新文献

2023 Zooming Innovation in Consumer Technologies Conference (ZINC)最新文献

筛选
英文 中文
Ambient Connectivity: what it is, how to realize it and what do to with it 环境连接:它是什么，如何实现它，以及如何使用它
2023 Zooming Innovation in Consumer Technologies Conference (ZINC) Pub Date : 2023-05-29 DOI: 10.1109/zinc58345.2023.10174070
B. Frankston, S. K. Datta
{"title":"Ambient Connectivity: what it is, how to realize it and what do to with it","authors":"B. Frankston, S. K. Datta","doi":"10.1109/zinc58345.2023.10174070","DOIUrl":"https://doi.org/10.1109/zinc58345.2023.10174070","url":null,"abstract":"","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125783582","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
MRI Brain Tumor Classification based on Federated Deep Learning 基于联邦深度学习的MRI脑肿瘤分类
2023 Zooming Innovation in Consumer Technologies Conference (ZINC) Pub Date : 2023-05-29 DOI: 10.1109/ZINC58345.2023.10174015
Khanh Le Dinh Viet, Khiem Le Ha, Trung Nguyen Quoc, Vinh Truong Hoang
{"title":"MRI Brain Tumor Classification based on Federated Deep Learning","authors":"Khanh Le Dinh Viet, Khiem Le Ha, Trung Nguyen Quoc, Vinh Truong Hoang","doi":"10.1109/ZINC58345.2023.10174015","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174015","url":null,"abstract":"The proliferation of artificial intelligence (AI) has the potential to revolutionize many industries, but its application is hindered by the shortage of large-scale data. Data in various domains often exist in isolated silos, necessitating privacy and security. In the meantime, the lack of access to medical privacy prevented the development of trustworthy systems for diagnosing deadly malignancies like brain tumors. In this study, we apply a federated learning algorithm known as Federated Averaging (FedAvg) to train a brain tumor classification system using decentralized data without requesting the exchange of sensitive data. The proposed framework’s hyperparameters are adjusted to enhance its effectiveness on both independently and identically (IID) and non-independently and identically distributed data (Non-IID). Additionally, we leverage four cutting-edge deep learning models, namely, VGG16, ResNet50, ConvNext, and MaxViT, to optimize classification accuracy. The proposed framework achieves a classification accuracy of 98.69% on IID data and over 93% on Non-IID data.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126717843","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
Improving text detection by generating images with curved text instances 通过生成具有弯曲文本实例的图像来改进文本检测
2023 Zooming Innovation in Consumer Technologies Conference (ZINC) Pub Date : 2023-05-29 DOI: 10.1109/ZINC58345.2023.10174175
Leon Landeka, R. Grbić, Matteo Brisinello, M. Herceg
{"title":"Improving text detection by generating images with curved text instances","authors":"Leon Landeka, R. Grbić, Matteo Brisinello, M. Herceg","doi":"10.1109/ZINC58345.2023.10174175","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174175","url":null,"abstract":"Modern text detection algorithms rely on deep neural networks, which are trained on labeled datasets to achieve high performance. Despite the increasing popularity of text detection, accurate detection of text in natural images remains a challenging problem due to variations in text size, shape, color, and font. In particular, curved text instances present a unique challenge for detection algorithms, yet they are seldom found in existing text detection datasets. In this paper, we present an approach to improve curved text detection performance by generating synthetic images with curved text instances and polygon bounding regions as annotations. We train a deep neural network-based text detector on these synthetic images and evaluate its performance on test sets. Our findings highlight the importance of utilizing diverse and realistic datasets for training robust text detection systems.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129616785","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
Artificial Intelligence and Deep Learning 101: A Friend or Foe? 人工智能与深度学习101:是敌是友?
2023 Zooming Innovation in Consumer Technologies Conference (ZINC) Pub Date : 2023-05-29 DOI: 10.1109/zinc58345.2023.10174252
Jelena Kocic
{"title":"Artificial Intelligence and Deep Learning 101: A Friend or Foe?","authors":"Jelena Kocic","doi":"10.1109/zinc58345.2023.10174252","DOIUrl":"https://doi.org/10.1109/zinc58345.2023.10174252","url":null,"abstract":"","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"416 6883 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117313115","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
Lifetime estimation of p-channel power VDMOSFETs applied in automotive applications 汽车用p沟道功率vdmosfet寿命估计
2023 Zooming Innovation in Consumer Technologies Conference (ZINC) Pub Date : 2023-05-29 DOI: 10.1109/ZINC58345.2023.10174162
N. Mitrović, S. Veljković, Z. Prijić, D. Danković
{"title":"Lifetime estimation of p-channel power VDMOSFETs applied in automotive applications","authors":"N. Mitrović, S. Veljković, Z. Prijić, D. Danković","doi":"10.1109/ZINC58345.2023.10174162","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174162","url":null,"abstract":"This paper presents research on the lifetime estimation of p-channel power VDMOSFETs, widely available in automotive and consumer applications. Lifetime and period of reliable work of these devices that present parts of the system also constraints the reliable operation mode of the system as a whole. Operation of these devices, especially operation under harsh conditions as in automotive applications, degrade VDMOSFET characteristics through time. Degradation of parameters leads to parametric failure of devices so that device no longer operates reliable, which is a problem for a consumer. Parameter of the VDMOSFETs that strongly impacts the lifetime is threshold voltage. Lifetime of devices used with different types of controlling signals is estimated using declared algorithms. Appropriate experiments have been carried out with the goal to obtain experimental data that can be used for the algorithms implementations. Experimental setup as well as estimation algorithms are discussed in detail in the paper. Usage of the signals is compared and further analyzed from the developers, as well as from the consumer’s standpoint.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127027909","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
Slow motion video sequences database for freezing artifact detection 用于冻结伪影检测的慢动作视频序列数据库
2023 Zooming Innovation in Consumer Technologies Conference (ZINC) Pub Date : 2023-05-29 DOI: 10.1109/ZINC58345.2023.10174092
Ela Vrtar, M. Herceg, M. Vranješ, Danijel Babic
{"title":"Slow motion video sequences database for freezing artifact detection","authors":"Ela Vrtar, M. Herceg, M. Vranješ, Danijel Babic","doi":"10.1109/ZINC58345.2023.10174092","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174092","url":null,"abstract":"In this paper, a new video sequence database, called Slow Motion Video Sequences (SMVS), is developed. The developed SMVS database consists of 30 video sequences with very low temporal activities, where every sequence contains a freezing artifact. The performance of two freezing detection algorithms, the Histogram-Based Freezing Artifacts Detection Algorithm (HBFDA) and the Real-Time no-reference Freezing Detection Algorithm (RTFDA) are tested on the developed database. The testing results show the poor performance of the tested algorithms.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126547707","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
One solution of providing ADAS data to the IVI domain via the Android Java service 通过Android Java服务向IVI域提供ADAS数据的一种解决方案
2023 Zooming Innovation in Consumer Technologies Conference (ZINC) Pub Date : 2023-05-29 DOI: 10.1109/ZINC58345.2023.10174158
Dusan Stanisic, Marija Antic, Dusan Kenjic, L. Bilac
{"title":"One solution of providing ADAS data to the IVI domain via the Android Java service","authors":"Dusan Stanisic, Marija Antic, Dusan Kenjic, L. Bilac","doi":"10.1109/ZINC58345.2023.10174158","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174158","url":null,"abstract":"In recent years, manufacturers are working parallel in developing and integrating two in-vehicle systems, an Advanced Driver Assistance System (ADAS) and In-Vehicle Infotainment (IVI). ADAS’s purpose is to increase safety and aid the driver while the vehicle is in motion, by using various sensors to perceive the vehicle surrounding or the driver’s errors and respond accordingly. Consumer applications in the IVI domain would significantly benefit from accessing such vehicle-specific data. Unfortunately, due to active vehicle system architecture requirements, the IVI domain cannot achieve communication with the ADAS by following traditional signal-oriented mechanisms. In addition, Android paved its way into the IVI domain as the most common Operating System because of its high flexibility and customization, but without being adapted for communication with ADAS. This paper offers a solution for enabling Android applications to access ADAS data via Java services. Data is procured over GENIVI company’s SOME/IP-based communication middleware, integrated within the services. Communication performance is measured, evaluated, and limitations are identified.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122460579","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
ZINC 2023 Organizing Team 锌2023组织团队
2023 Zooming Innovation in Consumer Technologies Conference (ZINC) Pub Date : 2023-05-29 DOI: 10.1109/zinc58345.2023.10174022
{"title":"ZINC 2023 Organizing Team","authors":"","doi":"10.1109/zinc58345.2023.10174022","DOIUrl":"https://doi.org/10.1109/zinc58345.2023.10174022","url":null,"abstract":"","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115340606","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
An ensemble-based framework for biomedical classification problems 生物医学分类问题的集成框架
2023 Zooming Innovation in Consumer Technologies Conference (ZINC) Pub Date : 2023-05-29 DOI: 10.1109/ZINC58345.2023.10174224
Mario Dudjak, Bruno Zoric, Drazen Bajer
{"title":"An ensemble-based framework for biomedical classification problems","authors":"Mario Dudjak, Bruno Zoric, Drazen Bajer","doi":"10.1109/ZINC58345.2023.10174224","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174224","url":null,"abstract":"Model selection is an essential step when applying machine learning to classification problems. It is typically carried out by the practitioner who strives to identify the most suitable classifier for a given problem. Given the variety of classifiers available and the difficulty in predicting which one will yield the best performance depending on the characteristics of the problem, this is by no means a simple task. Biomedical problems pose a significant challenge in this regard due to their numerous data intrinsic characteristics that are known to impair classification performance. Given that different classifiers perform well for different biomedical problems, combining them into an ensemble would seem practical. However, the practitioner still needs to determine how to combine them. This paper presents an ensemble-based framework that automates the training and combination of different classifiers in order to relieve practitioners of this burden whilst obtaining highly competitive performance. The effectiveness of the proposed framework was evaluated on several biomedical problems from the literature.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131487191","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
A Simple Python Testbed for Federated Learning Algorithms 联邦学习算法的简单Python测试平台
2023 Zooming Innovation in Consumer Technologies Conference (ZINC) Pub Date : 2023-05-29 DOI: 10.1109/ZINC58345.2023.10173859
M. Popovic, M. Popovic, I. Kastelan, Miodrag Djukic, S. Ghilezan
{"title":"A Simple Python Testbed for Federated Learning Algorithms","authors":"M. Popovic, M. Popovic, I. Kastelan, Miodrag Djukic, S. Ghilezan","doi":"10.1109/ZINC58345.2023.10173859","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10173859","url":null,"abstract":"Nowadays many researchers are developing various distributed and decentralized frameworks for federated learning algorithms. However, development of such a framework targeting smart Internet of Things in edge systems is still an open challenge. In this paper, we present our solution to that challenge called Python Testbed for Federated Learning Algorithms. The solution is written in pure Python, and it supports both centralized and decentralized algorithms. The usage of the presented solution is both validated and illustrated by three simple algorithm examples.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117216876","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
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：481959085
Book学术官方微信