Hyunho Mo, F. Lucca, Jonni Malacarne, Giovanni Iacca
{"title":"Multi-Head CNN-LSTM with Prediction Error Analysis for Remaining Useful Life Prediction","authors":"Hyunho Mo, F. Lucca, Jonni Malacarne, Giovanni Iacca","doi":"10.23919/fruct49677.2020.9211058","DOIUrl":"https://doi.org/10.23919/fruct49677.2020.9211058","url":null,"abstract":"Predicting accurate remaining useful life (RUL) of components plays a crucial role in making optimal decision for maintenance management. As sensor technology develops, multiple sensors are used to collect information for monitoring the condition of components. Deep learning architectures, such as convolutional neural network (CNN) and long short term memory (LSTM), can be considered as a successful end-to-end framework to predict RUL from the multivariate time series collected by those sensors. For that, we employ an architecture combining the parallel branch of CNN in series with LSTM which is referred to as multi-head CNN-LSTM. Furthermore, we propose a combination of the network with time series prediction error analysis (PEA). The prediction errors on the entire time series are estimated by recursive least squares (RLS) and single exponential smoothing (SES) respectively. We analyze each of the two sequences of prediction errors with the exponentially weighted moving average (EWMA) and combine them with the Fisher’s method. Finally, the output of the PEA is fed into the multi-head CNN-LSTM network as the additional input. We evaluate the performance of our method on the widely used C-MAPSS dataset. The experimental results suggest that using the PEA improves the performance of the deep learning-based RUL prediction model. Compared to other methods in recent literature, the proposed method achieves the state-of-the-art result on one sub-dataset and very competitive results on the others. In addition, it also shows promising results in the consecutive RUL prediction following the degradation process of components.","PeriodicalId":149674,"journal":{"name":"2020 27th Conference of Open Innovations Association (FRUCT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114345365","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}
Tommi Meskanen, Valtteri Niemi, Jarkko Kuusijäarvi
{"title":"Privacy-Preserving Peer Discovery for Group Management in p2p Networks","authors":"Tommi Meskanen, Valtteri Niemi, Jarkko Kuusijäarvi","doi":"10.23919/fruct49677.2020.9211019","DOIUrl":"https://doi.org/10.23919/fruct49677.2020.9211019","url":null,"abstract":"The necessity for peer-to-peer (p2p) communications is obvious; current centralized solutions are capturing and storing too much information from the individual people communicating with each other. Privacy concerns with a centralized solution in possession of all the users data are a difficult matter. HELIOS platform introduces a new social-media platform that is not in control of any central operator, but brings the power of possession of the data back to the users. It does not have centralized servers that store and handle receiving/sending of the messages. Instead, it relies on the current open-source solutions available in the p2p communities to propagate the messages to the wanted recipients of the data and/or messages. The p2p communications also introduce new problems in terms of privacy and tracking of the user, as the nodes part of a p2p network can see what data the other nodes provide and ask for. How the sharing of data in a p2p network can be achieved securely, taking into account the user’s privacy is a question that has not been fully answered so far. We do not claim we answer this question fully in this paper either, but we propose a set of protocols to help answer one specific problem. Especially, this paper proposes how to privately share data (end-point address or other) of the user between other users, provided that they have previously connected with each other securely, either offline or online.","PeriodicalId":149674,"journal":{"name":"2020 27th Conference of Open Innovations Association (FRUCT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129592918","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}
Robert Hupke, J. Peissig, A. Genovese, Sripathi Sridhar, A. Roginska
{"title":"Impact of Source Panning on a Global Metronome in Rhythmic Networked Music Performance","authors":"Robert Hupke, J. Peissig, A. Genovese, Sripathi Sridhar, A. Roginska","doi":"10.23919/fruct49677.2020.9211004","DOIUrl":"https://doi.org/10.23919/fruct49677.2020.9211004","url":null,"abstract":"Achieving synchronicity and tempo stability during a Network Music Performance (NMP) is not straightforward under heavy network latency conditions. Previous work on Global Metronomes has shown that it is possible to provide a universal time-reference signal to the connected nodes of an NMP. This paper illustrates the effects of using a global metronome and signal source-panning on a rhythmic performance. An experiment was conducted to evaluate the objective musical outcome and the subjective impressions of using these elements, applied to several pairs of Djembe percussion duets, under different tempo and latency conditions. The objective analysis in terms of tempo stability and synchrony, conducted from the perspective of an hypothetical audience, suggest that the use of a metronome achieves stability improvements at medium and higher latency levels, while the use of signal panning has been effective in improving the metronome efficiency. Subjective analysis data shows that the use of the metronome becomes challenging for higher delays while it was perceptually non-intrusive for the musicians for lower and medium delays.","PeriodicalId":149674,"journal":{"name":"2020 27th Conference of Open Innovations Association (FRUCT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134185474","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":"Sensors of Mechanical Stresses and Deformations Based on Magnetic Phenomena","authors":"I. Sekirin, V. Ignakhin","doi":"10.23919/fruct49677.2020.9211074","DOIUrl":"https://doi.org/10.23919/fruct49677.2020.9211074","url":null,"abstract":"An overview of various sensors for mechanical stresses (or deformations) is provided within scope of the magnetic phenomena. The paper considers the latest achievements in the design of such sensors for the needs of smart digital devices in the area of Industrial Internet of Things applications. We specifically study the sensors based on single-domain wires, magneto-optical Kerr effect, and propagation of spin-polarized electrons.","PeriodicalId":149674,"journal":{"name":"2020 27th Conference of Open Innovations Association (FRUCT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129938625","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}
Riccardo Battello, Luca Comanducci, F. Antonacci, A. Sarti, S. Monache, Giovanni Cospito, Enrico Pietrocola, Filippo Berbenni
{"title":"An Adaptive Metronome Technique for Mitigating the Impact of Latency in Networked Music Performances","authors":"Riccardo Battello, Luca Comanducci, F. Antonacci, A. Sarti, S. Monache, Giovanni Cospito, Enrico Pietrocola, Filippo Berbenni","doi":"10.23919/fruct49677.2020.9211053","DOIUrl":"https://doi.org/10.23919/fruct49677.2020.9211053","url":null,"abstract":"The improvement of digital communication networks increased the interest towards Networked Music Performance both for entertainment and education. One of the main issues that affects the effectiveness of remote performances is the inherent network latency in the communication chain. In this paper we propose a technique that, to the best of our knowledge, is the first work that explores the use of adaptive metronomes in order to track the tempo of the musicians and help them in coping with the latency. We test our proposal with preliminary experiments in the context of chamber music.","PeriodicalId":149674,"journal":{"name":"2020 27th Conference of Open Innovations Association (FRUCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129957784","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":"Populating the Smart Musical Instruments Ontology with Data","authors":"L. Turchet, Guixia Zhu, P. Bouquet","doi":"10.23919/fruct49677.2020.9210986","DOIUrl":"https://doi.org/10.23919/fruct49677.2020.9210986","url":null,"abstract":"One of the main instances of Musical Things within the Internet of Musical Things (IoMusT) paradigm is the emerging family of Smart Musical Instruments (SMIs). This is a category of musical instruments encompassing sensors, actuators, embedded intelligence, and wireless connectivity to local networks and to the Internet. Recently, an ontology to represent this domain has been proposed, the Smart Musical Instruments Ontology. However, a database gathering SMIs instances was missing. Such a database would be useful to gather and organize information about this family of IoMusT devices which is predicted to become more widespread in the future, in both academic and industrial contexts. In this paper, we present a linked data service exposing metadata about SMIs structured according to the Smart Musical Instruments Ontology, as well as a Web application for its extension and retrieval. We first survey the existing instances of SMIs as well as the SMIs Ontology. We then outline use cases and potential applications utilizing the developed Web-based service, showing how to retrieve detailed information using metadata describing the SMIs domain.","PeriodicalId":149674,"journal":{"name":"2020 27th Conference of Open Innovations Association (FRUCT)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133291652","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}
Anastasia Moshkova, A. Samorodov, N. Voinova, A. Volkov, E. Ivanova, E. Fedotova
{"title":"Facial Emotional Expression Assessment in Parkinson’s Disease by Automated Algorithm Based on Action Units","authors":"Anastasia Moshkova, A. Samorodov, N. Voinova, A. Volkov, E. Ivanova, E. Fedotova","doi":"10.23919/fruct49677.2020.9211028","DOIUrl":"https://doi.org/10.23919/fruct49677.2020.9211028","url":null,"abstract":"This work is devoted to the study of expression and interpretation of six basic emotions: anger, disgust, fear, happiness, sadness, surprise in patients with Parkinson’s disease in comparison with the healthy control group of patients. The study involved 16 patients in each group. Each patient’s face was recorded using a 2D camera while performing 3 tasks: displaying a neutral state, displaying 6 basic emotions by researcher request, displaying 6 basic emotions depicted on the images. Action units were determined on each video frame. The percentages of emotional expressions in each video were determined, and the intensity of the recognized expressions for each task using the emotion recognition algorithm based on action units. The difference between emotional expressions and the neutral state was calculated as Euclidian distance between vectors of action units to quantify the changes in facial expression between the Parkinson’s disease and healthy control groups. To analyze the differences between the groups, the non-parametric Mann– Whitney U-test was used. The obtained results show changes in the emotional expressions in the Parkinson’s disease group in comparison with the healthy control group, Parkinson’s disease patients show a decrease in the expressiveness of face and the intensity of the emotional expression.","PeriodicalId":149674,"journal":{"name":"2020 27th Conference of Open Innovations Association (FRUCT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116212483","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":"Solution Management for Current Temporal Aspect Using Tuple Versions","authors":"Michal Kvet","doi":"10.23919/fruct49677.2020.9211017","DOIUrl":"https://doi.org/10.23919/fruct49677.2020.9211017","url":null,"abstract":"The current temporal paradigm is based on the validity, which delimits each data tuple by the time frame. The uni-temporal solution extends the object identifier with the validity interval inside the primary key. It can be used on various granularities (object, attribute, and group), however, it cannot store individual versions for existing data corrections. This paper references temporal architectures highlights current challenges for dealing with data versions and proposes own solution replacing transaction time frame forming transaction reliability concept. It deals with the referential integrity in the temporal environment and proposes a model for covering references and ensuring the integrity of the processed data using signature hash values, two-level indexes formed by the object and individual states with corrections.","PeriodicalId":149674,"journal":{"name":"2020 27th Conference of Open Innovations Association (FRUCT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128771610","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}
O. Makhnytkina, A. Matveev, Aleksei Svischev, Polina Korobova, Dmitrii A. Zubok, Nikita Mamaev, Artem Tchirkovskii
{"title":"Conversational Question Generation in Russian","authors":"O. Makhnytkina, A. Matveev, Aleksei Svischev, Polina Korobova, Dmitrii A. Zubok, Nikita Mamaev, Artem Tchirkovskii","doi":"10.23919/fruct49677.2020.9211056","DOIUrl":"https://doi.org/10.23919/fruct49677.2020.9211056","url":null,"abstract":"In this paper, we discuss possibilities of automatic generation of conversational questions in Russian. We are exploring the possibility of using “A Conversational Question Answering Challenge” (CoQA) dataset translated into Russian for training an encoder-decoder model. We review several techniques for improving the quality of questions generated in the Russian language. The results are evaluated manually. Combining a neural network-based approach with a rules-based approach, we develop a system for automatic examination of university students.","PeriodicalId":149674,"journal":{"name":"2020 27th Conference of Open Innovations Association (FRUCT)","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114752933","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}
Tychonas Michailidis, G. Meadow, C. Barlow, E. Rajabally
{"title":"Implementing Remote Audio as a Diagnostics Tool for Maritime Autonomous Surface Ships","authors":"Tychonas Michailidis, G. Meadow, C. Barlow, E. Rajabally","doi":"10.23919/fruct49677.2020.9211029","DOIUrl":"https://doi.org/10.23919/fruct49677.2020.9211029","url":null,"abstract":"The role of marine engineers is to maintain the operational state of all systems in the engine room such as to diagnose and rectify problems arising, and to understand what maintenance will be required to keep the vessel appropriately operational and safe. Through training and experience, the engineering crew can read and interpret engine room instrumentation, and employ their intuitive feel for normal operation in-situ. In order to examine the possibilities of future remote and autonomous uncrewed vessels, we developed a virtual reality simulated engine room based on a real vessel. Even though the end product is effectively a virtual simulation, the original audio from the engine room was recorded and used, thus providing a more accurate and immersive experience to the users. This paper examines the use and application of a remote server to feed audio and other data in the simulated virtual engine and to create hypothetical failures scenarios for testing and training. Experience engineers carried out different failure scenarios as they usually do onboard and provided valuable feedback. User testing suggests that upcoming paradigms of the Internet of Audio Things can become a vital element in future operations of Maritime Autonomous Surface Ships.","PeriodicalId":149674,"journal":{"name":"2020 27th Conference of Open Innovations Association (FRUCT)","volume":"369 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116519944","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}