{"title":"Backward chaining inference as a database stored procedure — the experiments on real-world knowledge bases","authors":"Tomasz Xieski, R. Siminski","doi":"10.1080/24751839.2018.1479931","DOIUrl":"https://doi.org/10.1080/24751839.2018.1479931","url":null,"abstract":"In this work two approaches of backward chaining inference implementation were compared. The first approach uses a classical, goal driven inference running on the client device — the algorithm implemented within the KBExpertLib library was used. Inference was performed on a rule base buffered in memory structures. The second approach involves implementing inference as a stored procedure, run in the environment of the database server — an original, previously not published algorithm was introduced. Experiments were conducted on real-world knowledge bases with a relatively large number of rules. Experiments were prepared so that one could evaluate the pessimistic complexity of the inference algorithm.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"198200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115186346","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}
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}
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}
{"title":"A novel approach for people counting and tracking from crowd video","authors":"Merve Ayyuce Kizrak Sagun, B. Bolat","doi":"10.1109/INISTA.2017.8001170","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001170","url":null,"abstract":"Crowd analysis on video recordings is an important research area currently. In this work, a combined crowd density estimation method is presented to overcome this problem. To improve the accuracy of the system two different estimators run simultaneously and a blob is marked as a person only if both estimators mark it as person. One of the main problems in crowd density estimation is occlusion. To overcome this problem we tracked the trajectories of blobs by using a Kalman filter. The method was applied to three common benchmark data which are PETS2009, UCSD and Grand Central. The results confirm the proposed method's success.","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":"2017-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116533007","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}
B. Trawinski, Zbigniew Telec, Jacek Krasnoborski, M. Piwowarczyk, Michal Talaga, T. Lasota, Edward Sawilow
{"title":"Comparison of expert algorithms with machine learning models for real estate appraisal","authors":"B. Trawinski, Zbigniew Telec, Jacek Krasnoborski, M. Piwowarczyk, Michal Talaga, T. Lasota, Edward Sawilow","doi":"10.1109/INISTA.2017.8001131","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001131","url":null,"abstract":"Machine learning models require numerous training examples to provide reliable predictions of real estate prices. Expert algorithms could be applied wherever only several training samples are available. The accuracy of two expert algorithms based on the sales comparison approach was experimentally examined using real-world data derived from a cadastral system and registry of real estate transactions. The performance of the algorithms was compared with three data driven regression models for property valuation. Statistical analysis of the obtained results was conducted.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"69 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":"126406230","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}
{"title":"Audio features dedicated to the detection of arousal and valence in music recordings","authors":"Jacek Grekow","doi":"10.1109/INISTA.2017.8001129","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001129","url":null,"abstract":"The aim of this paper was to discover what combination of audio features gives the best performance with music emotion detection. In our approach, emotion recognition was treated as a regression problem and a two-dimensional valence-arousal model was used to measure emotions in music. We used features extracted by Essentia and Marsyas, tools for audio analysis and audio-based music information retrieval. We examined the influence of different feature sets - low-level, rhythm, tonal, and their combination - on arousal and valence prediction. The use of a combination of different types of features significantly improves the results compared with using just one group of features. We found and presented features particularly dedicated to the detection of arousal and valence separately, as well as features useful in both cases.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"19 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":"133737012","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}
J. Jędrzejowicz, Jakub Neumann, Piotr Synowczyk, Magdalena Zakrzewska
{"title":"Applying Map-Reduce to imbalanced data classification","authors":"J. Jędrzejowicz, Jakub Neumann, Piotr Synowczyk, Magdalena Zakrzewska","doi":"10.1109/INISTA.2017.8001127","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001127","url":null,"abstract":"The aim of the paper was to apply MapReduce paradigm to the algorithm SplitBal which classifies imbalanced datasets and perform the evaluation of results for different parameters. Parallelization of time consuming operations allows to classify larger datasets, in perspective Big Data.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"40 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":"122429866","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}
{"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}
{"title":"Deep Convolutional Neural Networks for facial expression recognition","authors":"A. Uçar","doi":"10.1109/INISTA.2017.8001188","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001188","url":null,"abstract":"Facial expression recognition is a very active research topic due to its potential applications in the many fields such as human-robot interaction, human-machine interfaces, driving safety, and health-care. Despite of the significant improvements, facial expression recognition is still a challenging problem that wait for more and more accurate algorithms. This article presents a new model that is capable of recognizing facial expression by using deep Convolutional Neural Network (CNN). The CNN model is generated by using Caffe in Digits environment. Moreover, it is trained and tested on NVIDIA Tegra TX1 embedded development platform including a 250 Graphics Processing Unit (GPU) CUDA cores and Quadcore ARM Cortex A57 processor. The proposed model is applied to address the facial expression problem on the publicly available two expression databases, the JAFFE database and the Cohn-Kanade database.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"50 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":"121994649","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}
{"title":"Association ACDT as a tool for discovering the financial data rules","authors":"J. Kozák, Przemysław Juszczuk","doi":"10.1109/INISTA.2017.8001164","DOIUrl":"https://doi.org/10.1109/INISTA.2017.8001164","url":null,"abstract":"We present a novel approach based on the original idea of the Ant Colony Decision Tree (ACDT) algorithm used in the problem of building the decision trees. One of the crucial limitations of the canonical ACDT algorithm was its link to strict decision rules. In this paper we transform the algorithm in such way, that it is capable to manage complex association rules. Research is conducted on the various sets of financial data closely related with the swiss frank currency. Evaluation of results was possible on the basis of accuracy measure as well as the proposed fuzzy accuracy. These preliminary studies show, that the proposed algorithm is capable to maintain its effectiveness even in the problems with large number of attribute values.","PeriodicalId":314687,"journal":{"name":"2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"4 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":"127753936","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}