{"title":"Acoustic Classification of Cat Breed Based on Time and Frequency Domain Features","authors":"William Raccagni, S. Ntalampiras","doi":"10.23919/FRUCT53335.2021.9599975","DOIUrl":"https://doi.org/10.23919/FRUCT53335.2021.9599975","url":null,"abstract":"The emerging field of Bioacoustics has been presenting significant research activity lately, and thanks to the use of machine learning methods, several tools and methodologies have been established for identifying certain patterns and meanings in animal vocalizations. Animal sounds can vary over time in intensity and patterns produced between different breeds of the same species, both for physiological reasons and for different emotional states and needs. Pets, such as dogs and cats, are no exception, thus allowing a vocal distinction between breeds. This article studies classification of the cat breed, in particular on the Maine Coon and European Shorthair breed, based on the public audio dataset “CatMeows”. To this end, we employed features coming from time and frequency domain capturing relevant information as regard to the present audio structure. Subsequently, audio pattern recognition was carried out by means of k-means clustering, k-NN, and multilayer perceptron learning models. After extensive experiments, we obtained very promising results, with an average accuracy that runs around 98 %. In particular, time-domain features presented a strong contribution, as demonstrated by the results using k-means.","PeriodicalId":198108,"journal":{"name":"2021 30th Conference of Open Innovations Association FRUCT","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130207997","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}
Markus Hirsimäki, Paula Alavesa, Leena Arhippainen
{"title":"Between Beats: Linking Player Engagement to Advertisement Frequency and Intrusiveness","authors":"Markus Hirsimäki, Paula Alavesa, Leena Arhippainen","doi":"10.23919/FRUCT53335.2021.9599998","DOIUrl":"https://doi.org/10.23919/FRUCT53335.2021.9599998","url":null,"abstract":"Mobile phones are a popular platform for gaming in addition to being the most ubiquitous one. Monetization of free to play games with embedded and interstitial advertisements is one of the main sources of income for mobile game creators. We used a constructive approach in this study. A mobile game developed during the study, Between Beats, was used to survey the influence of interstitial advertisement on selected aspects of player experience. The study was conducted by deploying the game to Google Play and guiding the players, after gameplay, to an online survey. The survey was answered by 51 participants who were divided randomly into four groups based on how much they were subjected to interstitial or rewarded advertisements while playing. Our results show that embedding rewarded advertisements to a situation where there already is interstitial advertisements, resulted in reduction of perceived advertisement intrusiveness and increase in advertisements viewed. Player engagement remained constant in all groups. Our findings complement earlier findings on the use of rewarded advertisements in mobile games.","PeriodicalId":198108,"journal":{"name":"2021 30th Conference of Open Innovations Association FRUCT","volume":"10 1-2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131687969","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":"An Approach to Behavior Modeling Based on Elements of Theories of Planned and Organizational Behavior","authors":"N. Shilov","doi":"10.23919/FRUCT53335.2021.9599960","DOIUrl":"https://doi.org/10.23919/FRUCT53335.2021.9599960","url":null,"abstract":"The analysis of human behavior has been attracting the attention of scientists for a long time. Prediction of user intents and actions when interacting with an information system and the corresponding adaptation of the system can significantly increase the efficiency of the joint work of the pair “user - information system”. The paper proposes an approach to modeling the behavior of information system users based on the situation analysis with the aim of further behavior analysis via, for example, machine learning methods. The main idea of the approach is to capture and compare the situation described by a context before, at the moment of, and after an action made by the user. The applicability of the proposed approach is confirmed by the presented case study.","PeriodicalId":198108,"journal":{"name":"2021 30th Conference of Open Innovations Association FRUCT","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124808789","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":"Proceedings of the 30th Conference of Open Innovations Association FRUCT","authors":"","doi":"10.23919/fruct53335.2021.9599991","DOIUrl":"https://doi.org/10.23919/fruct53335.2021.9599991","url":null,"abstract":"","PeriodicalId":198108,"journal":{"name":"2021 30th Conference of Open Innovations Association FRUCT","volume":"230 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125138641","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":"Low-Energy Authentication with Selective Privacy for Heterogeneous IoT Devices in Smart-Farms","authors":"Steph Rudd, H. Cunningham","doi":"10.23919/FRUCT53335.2021.9599987","DOIUrl":"https://doi.org/10.23919/FRUCT53335.2021.9599987","url":null,"abstract":"This paper presents a payload-based security model for authenticating constrained and heterogeneous constrained devices in a smart-farm application. The domain ideally operates with optional internet and no constant power supply, using battery-powered microcontrollers for the monitoring and control of aquaponics systems. The motivation was to reduce energy consumption for extended battery life, whilst enabling a robust, decentralised security design. Results demonstrated an annual saving of up to 96 % device battery life when compared to recommended TLS implementation, whilst maintaining equally high security standards.","PeriodicalId":198108,"journal":{"name":"2021 30th Conference of Open Innovations Association FRUCT","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132711634","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}
F. Sottile, Shiva Ehsanibalajorshary, Luigi Coriasco, C. Pastrone, R. Iacoviello, Davide Zappia
{"title":"Design of a 3D Indoor Localization System Enabling Augmented Reality TV Applications","authors":"F. Sottile, Shiva Ehsanibalajorshary, Luigi Coriasco, C. Pastrone, R. Iacoviello, Davide Zappia","doi":"10.23919/FRUCT53335.2021.9599984","DOIUrl":"https://doi.org/10.23919/FRUCT53335.2021.9599984","url":null,"abstract":"This paper focuses on the design of a robust Real Time Locating Systems (RTLS) based on the Ultra-Wide Band (UWB) technology for Augmented Reality (AR) applications in TV studios that require artists and/or a presenter to be accurately localized. According to a UWB-based measurement campaign, carried out in a TV studio environment, ranging measurements are heavily affected by the human body interference. Indeed, lots of outliers are present as the UWB receiver may synchronize to reflected paths, which result to be much stronger than the direct one. As a consequence, range errors are very large. In this context, to improve the localization performance, we increased the redundancy of the RTLS by employing more than one tag to localize the artists on the TV scene. In particular, we have applied the Extended Kalman Filter (EKF) algorithm to work with two and three tags. Moreover, an outlier detection and correction procedure have been defined and adopted for the ranging phase. The resulting localization performance, based on real range measurements, shows that the EKF with two tags outperforms by 83.5 % the one with single tag.","PeriodicalId":198108,"journal":{"name":"2021 30th Conference of Open Innovations Association FRUCT","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128574674","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":"Architecture of Cloud Telecommunication Network Monitoring Platform Based on Knowledge Graphs","authors":"K. Krinkin, I. Kulikov, A. Vodyaho, N. Zhukova","doi":"10.23919/FRUCT53335.2021.9599995","DOIUrl":"https://doi.org/10.23919/FRUCT53335.2021.9599995","url":null,"abstract":"The article is aimed to describe the architecture of a new cloud platform for telecommunications networks (TN) monitoring based on knowledge graphs (KG). The platform allows telecom operators receive modern analytics based on monitoring data for all segments of their networks, regardless of the devices generation and monitoring systems used, while requiring low expenses. The proposed architecture makes it possible to connect telecom operators TN s to the monitoring platform with low cost due to the flexible mechanism for platform ontology managing. In the case study section an example of combining operators network segments which use various monitoring systems with different domain ontologies is discussed. Also building a single report based on monitoring data in different segments is demonstrated. The directions for further functional development of the proposed platform are identified.","PeriodicalId":198108,"journal":{"name":"2021 30th Conference of Open Innovations Association FRUCT","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124607363","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":"Adaptation of Semantic Rule-Based Sentiment Analysis Approach for Russian Language","authors":"I. Paramonov, A. Poletaev","doi":"10.23919/FRUCT53335.2021.9599992","DOIUrl":"https://doi.org/10.23919/FRUCT53335.2021.9599992","url":null,"abstract":"The paper describes application of the semantic rule-based sentiment analysis approach, which was earlier developed and tested on English texts, to the Russian language. In order to take into account specificity of Russian it was adapted, particularly representation of the rules as patterns over a list of words was replaced with algorithms over the syntax tree of a sentence. The experiments on a quarter of a corpus of sentences extracted from hotel reviews allowed to perform the error analysis and refinement of the approach. The final results on the whole corpus allowed to achieve the results close to the state-of-the-art methods based on neural networks. The advantages of the approach, including simple interpretability of its results and absence of the need of learning, make it perspective for further research in sentiment analysis.","PeriodicalId":198108,"journal":{"name":"2021 30th Conference of Open Innovations Association FRUCT","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127454318","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}
Mauricio Rivas, Paul Alvarez, Alfredo Barrientos, Miguel Cuadros
{"title":"Proxemics Toolkit For F-formation Patterns Detection","authors":"Mauricio Rivas, Paul Alvarez, Alfredo Barrientos, Miguel Cuadros","doi":"10.23919/FRUCT53335.2021.9599996","DOIUrl":"https://doi.org/10.23919/FRUCT53335.2021.9599996","url":null,"abstract":"Interactions between people are of utmost magnitude for cross-device systems development. By using this kind of software, devices owned by those people end up interacting between themselves, and, therefore, making the system work. This work proposes to elaborate a toolkit that can detect and analyze those human interactions by using computer vision over videos showing them. All of these through the usage of 3D modeled test scenarios in addition to applying proxemics metrics and concepts of F -formations patterns so we can define them at various interaction types. To meet this goal, we used a previously trained human detection model in conjunction with two proposed concepts to estimate indispensable values: Distance between people, their body orientation, and relative position. To validate this tool, we tested it with a hundred test cases, each one having a set of different F -formation types so we could get the effectiveness of its detection functionality.","PeriodicalId":198108,"journal":{"name":"2021 30th Conference of Open Innovations Association FRUCT","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130904198","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}
V. Korzhik, V. Starostin, V. Yakovlev, D. Flaksman, Ivan Bukshin, B. Izotov
{"title":"Digital Watermarking System for Hard Cover Objects Against Cloning Attacks","authors":"V. Korzhik, V. Starostin, V. Yakovlev, D. Flaksman, Ivan Bukshin, B. Izotov","doi":"10.23919/FRUCT53335.2021.9599967","DOIUrl":"https://doi.org/10.23919/FRUCT53335.2021.9599967","url":null,"abstract":"We consider an application of digital watermark system technique for hard carriers (paper or plastic cover objects in addition). Algorithms of watermark embedding and extraction are proposed and the corresponding error probabilities of the extracted bits both for informed and blind decoders are presented. The spread spectrum signals used for embedding of watermark are optimized on their parameters. Similar experimental results are presented for data matrices carriers depending on paper sizes of data matrix copies. A protection against so-called “cloning” attack is elaborated where certificates are copied by attack scanner or photo camera and next printed and fixed as forges. The formulas for a missing the cloning attack and false alarm probabilities are proved. A full-scale experiment with a real scanner and printer confirms that the reliability of cloning attack detection can be provided under appropriate selection of watermark system parameters.","PeriodicalId":198108,"journal":{"name":"2021 30th Conference of Open Innovations Association FRUCT","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117228488","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}