2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI)最新文献_第3页

A system for crowdsensing vibration in public transportation 一种用于公共交通的人群感应振动系统

2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI) Pub Date : 2019-09-01 DOI: 10.1109/IC-AIAI48757.2019.00012

L. Baljak, Nataša Bojković, A. Labus, T. Naumović, Aleksandra Maksimovic

{"title":"A system for crowdsensing vibration in public transportation","authors":"L. Baljak, Nataša Bojković, A. Labus, T. Naumović, Aleksandra Maksimovic","doi":"10.1109/IC-AIAI48757.2019.00012","DOIUrl":"https://doi.org/10.1109/IC-AIAI48757.2019.00012","url":null,"abstract":"The subject of this paper is the development of a crowdsensing system for measuring vibration in traffic based on Internet of things, mobile and web technologies. The developed system should provide information about the level of comfort of the environment subjected to the measurement. Mobile crowdsensing is an emerging paradigm based on the application of sensors and crowdsourcing. The use of mobile device sensors, enabling the acquisition of local geospatial information and the provision of information / knowledge sharing with other users and the wider community creates a foundation for mobile crowdsensing. The literature overview shows that application of mobile crowdsensing approach can be found in following fields: environment, infrastructure and society. The parameters that determine the comfort of the environment, the methods for calculating them and the reference values are systematized. In the practical part described in the paper, a system for measuring vibration by a large number of participants (crowdsensing) was designed, implemented and tested using mobile phones for data collection and web technologies for displaying results and user reporting. The developed system was evaluated through a concrete experiment of measuring vibration in urban transport vehicles in Belgrade. Finally, we present the analysis of results, and a decision support system that gives support to various stakeholders.","PeriodicalId":374193,"journal":{"name":"2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115139367","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

AI for AI: What NLP Techniques Help Researchers Find the Right Articles on NLP AI for AI:什么NLP技术帮助研究人员找到关于NLP的正确文章

2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI) Pub Date : 2019-09-01 DOI: 10.1109/IC-AIAI48757.2019.00023

Sergei P. Prokhorov, Victor Safronov

{"title":"AI for AI: What NLP Techniques Help Researchers Find the Right Articles on NLP","authors":"Sergei P. Prokhorov, Victor Safronov","doi":"10.1109/IC-AIAI48757.2019.00023","DOIUrl":"https://doi.org/10.1109/IC-AIAI48757.2019.00023","url":null,"abstract":"The human progress of the coming years is largely associated with success in the field of artificial intelligence methods. The growth of knowledge in this area is in the nature of an information explosion. Researchers have to spend too much time monitoring a constantly evolving field, filtering out the flow of complex documents and texts that require a deep understanding of machine learning methods and their application in specific areas. In solving this problem, the very methods of machine learning and natural language processing are highly effective. The ability to take into account complex non-linear dependencies allows modern language models to effectively solve the problems of information retrieval, monitoring, facts extraction and further analysis. The article provides an overview of modern natural language processing methods that form the basis of modern text information retrieval systems and semi-automatic compilation of reviews and roadmaps. A review of approaches of text vectorization methods for semantic classification of documents. Known limitations of these techniques are also discussed.","PeriodicalId":374193,"journal":{"name":"2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133143141","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: 7

Topic Modelling for Extracting Behavioral Patterns from Transactions Data 从交易数据中提取行为模式的主题建模

2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI) Pub Date : 2019-09-01 DOI: 10.1109/IC-AIAI48757.2019.00015

Evgeny Egorov, Filipp Nikitin, Vasiliy Alekseev, A. Goncharov, K. Vorontsov

引用次数: 0

Detection of Big Animals on Images with Road Scenes using Deep Learning 基于深度学习的道路场景图像中大型动物的检测

2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI) Pub Date : 2019-09-01 DOI: 10.1109/IC-AIAI48757.2019.00028

D. Yudin, A. Sotnikov, A. Krishtopik

{"title":"Detection of Big Animals on Images with Road Scenes using Deep Learning","authors":"D. Yudin, A. Sotnikov, A. Krishtopik","doi":"10.1109/IC-AIAI48757.2019.00028","DOIUrl":"https://doi.org/10.1109/IC-AIAI48757.2019.00028","url":null,"abstract":"The recognition of big animals on the images with road scenes has received little attention in modern research. There are very few specialized data sets for this task. Popular open data sets contain many images of big animals, but the most part of them is not correspond to road scenes that is necessary for on-board vision systems of unmanned vehicles. The paper describes the preparation of such a specialized data set based on Google Open Images and COCO datasets. The resulting data set contains about 20000 images of big animals of 10 classes: \"Bear\", \"Fox\", \"Dog\", \"Horse\", \"Goat\", \"Sheep\", \"Cow\", \"Zebra\", \"Elephant\", \"Giraffe\". Deep learning approaches to detect these objects are researched in the paper. Authors trained and tested modern neural network architectures YOLOv3, RetinaNet R-50-FPN, Faster R-CNN R-50-FPN, Cascade R-CNN R-50-FPN. To compare the approaches the mean average precision (mAP) was determined at IoU≥50%, also their speed was calculated for input tensor sizes 640x384x3. The highest quality metrics are demonstrated by architecture YOLOv3 as for ten classes (0.78 mAP) and one joint class (0.92 mAP) detection with speed more 35 fps on NVidia Tesla V-100 32GB video card. At the same hardware, the RetinaNet R-50-FPN architecture provided recognition speed of more than 44 fps and a 13% lower mAP. The software implementation was done using the Keras and PyTorch deep learning libraries and NVidia CUDA technology. The proposed data set and neural network approach to recognizing big animals on images have shown their effectiveness and can be used in the on-board vision systems of driverless cars or in driver assistant systems.","PeriodicalId":374193,"journal":{"name":"2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132060336","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: 7

[Copyright notice] (版权)

2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI) Pub Date : 2019-09-01 DOI: 10.1109/ic-aiai48757.2019.00003

引用次数: 0

Application of Artificial Intelligence Methods in the Robocom Project 人工智能方法在Robocom项目中的应用

2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI) Pub Date : 2019-09-01 DOI: 10.1109/IC-AIAI48757.2019.00018

R. Gorbachev, N. Shvindt, M. Zaripov, D. Shishkov, A. Lazarev

引用次数: 0