2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)最新文献

Backward chaining inference as a database stored procedure — the experiments on real-world knowledge bases 作为数据库存储过程的倒链推理——在真实知识库上的实验

2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) Pub Date : 2018-06-18 DOI: 10.1080/24751839.2018.1479931

Tomasz Xieski, R. Siminski

引用次数: 0

Operational data augmentation in classifying single aerial images of animals 航拍动物单幅图像分类的操作数据增强

2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) Pub Date : 2017-07-05 DOI: 10.1109/INISTA.2017.8001185

Emmanuel Okafor, Rik Smit, Lambert Schomaker, M. Wiering

{"title":"Operational data augmentation in classifying single aerial images of animals","authors":"Emmanuel Okafor, Rik Smit, Lambert Schomaker, M. Wiering","doi":"10.1109/INISTA.2017.8001185","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001185","url":null,"abstract":"In deep learning, data augmentation is important to increase the amount of training images to obtain higher classification accuracies. Most data-augmentation methods adopt the use of the following techniques: cropping, mirroring, color casting, scaling and rotation for creating additional training images. In this paper, we propose a novel data-augmentation method that transforms an image into a new image containing multiple rotated copies of the original image in the operational classification stage. The proposed method creates a grid of n×n cells, in which each cell contains a different randomly rotated image and introduces a natural background in the newly created image. This algorithm is used for creating new training and testing images, and enhances the amount of information in an image. For the experiments, we created a novel dataset with aerial images of cows and natural scene backgrounds using an unmanned aerial vehicle, resulting in a binary classification problem. To classify the images, we used a convolutional neural network (CNN) architecture and compared two loss functions (Hinge loss and cross-entropy loss). Additionally, we compare the CNN to classical feature-based techniques combined with a k-nearest neighbor classifier or a support vector machine. The results show that the pre-trained CNN with our proposed data-augmentation technique yields significantly higher accuracies than all other approaches.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131620354","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: 30

Source-target mapping model of streaming data flow for machine translation 机器翻译流数据流的源-目标映射模型

2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) Pub Date : 2017-07-03 DOI: 10.1109/INISTA.2017.8001209

Jolanta Mizera-Pietraszko, G. Kolaczek, Ricardo Rodriguez Jorge

{"title":"Source-target mapping model of streaming data flow for machine translation","authors":"Jolanta Mizera-Pietraszko, G. Kolaczek, Ricardo Rodriguez Jorge","doi":"10.1109/INISTA.2017.8001209","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001209","url":null,"abstract":"Streaming information flow allows identification of linguistic similarities between language pairs in real time as it relies on pattern recognition of grammar rules, semantics and pronunciation especially when analyzing so called international terms, syntax of the language family as well as tenses transitivity between the languages. Overall, it provides a backbone translation knowledge for building automatic translation system that facilitates processing any of various abstract entities which combine to specify underlying phonological, morphological, semantic and syntactic properties of linguistic forms and that act as the targets of linguistic rules and operations in a source language following professional human translator. Streaming data flow is a process of mining source data into target language transformation during which any inference impedes the system effectiveness by producing incorrect translation. We address a research problem of exploring streaming data from source-target parallels for detection of linguistic similarities between languages originated from different groups.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115449977","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 novel approach for people counting and tracking from crowd video 一种从人群视频中计数和跟踪人群的新方法

2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) Pub Date : 2017-07-03 DOI: 10.1109/INISTA.2017.8001170

Merve Ayyuce Kizrak Sagun, B. Bolat

引用次数: 7

Comparison of expert algorithms with machine learning models for real estate appraisal 房地产评估中专家算法与机器学习模型的比较

2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) Pub Date : 2017-07-03 DOI: 10.1109/INISTA.2017.8001131

B. Trawinski, Zbigniew Telec, Jacek Krasnoborski, M. Piwowarczyk, Michal Talaga, T. Lasota, Edward Sawilow

引用次数: 24

Audio features dedicated to the detection of arousal and valence in music recordings 专门用于检测音乐录音中的唤醒和价的音频功能

2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) Pub Date : 2017-07-03 DOI: 10.1109/INISTA.2017.8001129

Jacek Grekow

引用次数: 22

Applying Map-Reduce to imbalanced data classification Map-Reduce在不平衡数据分类中的应用

2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) Pub Date : 2017-07-03 DOI: 10.1109/INISTA.2017.8001127

J. Jędrzejowicz, Jakub Neumann, Piotr Synowczyk, Magdalena Zakrzewska

引用次数: 1

Real-time ground filtration method for a loader crane environment monitoring system using sparse LIDAR data 基于稀疏激光雷达数据的装载机起重机环境监测系统实时地面滤波方法

2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) Pub Date : 2017-07-03 DOI: 10.1109/INISTA.2017.8001158

K. Miądlicki, M. Pajor, M. Saków

{"title":"Real-time ground filtration method for a loader crane environment monitoring system using sparse LIDAR data","authors":"K. Miądlicki, M. Pajor, M. Saków","doi":"10.1109/INISTA.2017.8001158","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001158","url":null,"abstract":"The segmentation and analysis of the environment using three-dimensional (3D) data (point clouds) is a dynamically developing area. This article presents a real-time ground filtration method for the loader crane environment monitoring system. The falling prices of depth sensors based on light detection and ranging (LIDAR), time of flight (ToF), radio detection and ranging (RADAR) technologies, and growth-computing power led us to use the Velodyne VLP-16 sensor in the developed system. In the presented filtering solution, we use characteristic scan pattern properties, the dot product of vectors, and interpolation using the RANSAC method. Algorithm performance was evaluated based on real data acquired under different conditions, and the results were compared to known filtration methods. The described algorithm is developed for real-time operation; therefore, the computation time is critical. Furthermore, in this article, we discuss other methods used to extract ground points from the entire point cloud in real time, describe Velodyne VLP-16 scanner and data acquisition methods.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133871811","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: 19

Deep Convolutional Neural Networks for facial expression recognition 用于面部表情识别的深度卷积神经网络

2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) Pub Date : 2017-07-03 DOI: 10.1109/INISTA.2017.8001188

A. Uçar

引用次数: 18

Association ACDT as a tool for discovering the financial data rules 关联ACDT作为发现财务数据规则的工具

2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) Pub Date : 2017-07-03 DOI: 10.1109/INISTA.2017.8001164

J. Kozák, Przemysław Juszczuk

引用次数: 6