Z. Geler, V. Kurbalija, M. Ivanović, Miloš Radovanović, Weihui Dai
{"title":"Dynamic Time Warping: Itakura vs Sakoe-Chiba","authors":"Z. Geler, V. Kurbalija, M. Ivanović, Miloš Radovanović, Weihui Dai","doi":"10.1109/INISTA.2019.8778300","DOIUrl":"https://doi.org/10.1109/INISTA.2019.8778300","url":null,"abstract":"In the domain of time-series classification, one simple but persistently successful method is the 1-nearest neighbour (1NN) classifier coupled with an elastic distance measure such as Dynamic Time Warping (DTW). In this paper we evaluate the performance of DTW when constrained using the Itakura parallelogram, and compare it with the more commonly used Sakoe-Chiba band, as well as with the unconstrained DTW. Results show that although the Itakura parallelogram is generally inferior to the Sakoe-Chiba band, it is still superior to unconstrained DTW. Furthermore, on individual data sets the Itakura parallelogram can produce superior results, warranting further investigation into the merits of its use with DTW and other elastic distance measures for time-series classification.","PeriodicalId":262143,"journal":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129306905","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":"Technological innovation and its enhancement of cultural heritage","authors":"V. Cantoni, M. Mosconi, Alessandra Setti","doi":"10.1109/INISTA.2019.8778378","DOIUrl":"https://doi.org/10.1109/INISTA.2019.8778378","url":null,"abstract":"The technological revolution which has completely transformed social relations and which has enabled communication and sharing of multimedia formats is also rapidly transforming the field of art and cultural heritage management. This contribution focuses on the innovative use of interactive digital technologies in digital humanities practices. In the last recent years, we experienced different approaches exploiting advanced technological innovation in the field of cultural heritage promotion and conservation. In 2015, for the exhibition “1525-2015. Pavia, the Battle, the Future. Nothing was the same again”, we applied multimodal interaction modalities. Visitors could look at and examine seven ancient tapestries through 3D reconstructions, virtual simulations, eye interaction and gesture navigation. Moreover, a transposition of the tapestries into tactile images enabled exploration by partially sighted and blind people. Motivated by this successful exhibition, in 2018, a more ambitious project, the 3D reconstruction of Pavia in the Renaissance, was undertaken. Advanced techniques and innovative applications have led to a resource useful for the promotion of the history of the city and its architectural richness through videos offering virtual tours of the city. Later, in 2019, a “Digital Anastylosis of Frescoes challeNgE (DAFNE)” has been proposed, to provide virtual solutions that ultimately add to the fresco restorer's toolkit, with digital re-composition of ‘puzzles’ formed by the artwork fragments, often mixed with spurious elements.","PeriodicalId":262143,"journal":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130367560","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 Semiautomated Human Resource Management System","authors":"Mihaela Ilie, S. Ilie, Ionuţ Murareţu","doi":"10.1109/INISTA.2019.8778252","DOIUrl":"https://doi.org/10.1109/INISTA.2019.8778252","url":null,"abstract":"This paper is an extension of our previous work where we have introduced a skill-based mathematical model of resource allocation. This paper expands our skill based approach by introducing adaptive skill sets for employees and a history-based initial evaluation strategy. For this purpose, the mathematical model is adjusted in order to modify skill vectors after a task allocation. In turn this enables estimations of the time to task completion based on employee history. We experimentally evaluate the impact of the skill adjustment on the project duration and cost in an agent-based simulation environment. The conclusion of the experiment is that taking into account the implicit skill gain of employees during their daily activity decreases projected costs and execution time significantly, which is this papers contribution to the state of the art. This approach is a good way to keep the teams skill sets automatically updated. The experiment is designed as an agent society simulation and through their interactions raw data is collected in order to calculate the performance measures. A scalability experiment is also presented showing slight (1%) decrease in project duration when tasks double while costs decrease between 7–32 %.","PeriodicalId":262143,"journal":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"16 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113974583","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 Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders","authors":"Aniekan Essien, C. Giannetti","doi":"10.1109/INISTA.2019.8778417","DOIUrl":"https://doi.org/10.1109/INISTA.2019.8778417","url":null,"abstract":"This paper proposes a deep learning framework where wavelet transforms (WT), 2-dimensional Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) stacked autoencoders (SAE) are combined towards single-step time series prediction. Within the framework, the input dataset is denoised using wavelet decomposition, before learning in an unsupervised manner using SAEs comprising bidirectional Convolutional LSTM (ConvLSTM) layers to predict a single-step ahead value. To evaluate our proposed framework, we compared its performance to two (2) state-of-the-art deep learning predictive models using three open-source univariate time series datasets. The experimental results support the value of the approach when applied to univariate time series prediction.","PeriodicalId":262143,"journal":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126266044","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":"[Copyright notice]","authors":"","doi":"10.1109/inista.2019.8778309","DOIUrl":"https://doi.org/10.1109/inista.2019.8778309","url":null,"abstract":"","PeriodicalId":262143,"journal":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124255071","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":"Inter-Criteria Analysis Based on Belief Functions for GPS Surveying Problems","authors":"S. Fidanova, J. Dezert, A. Tchamova","doi":"10.1109/INISTA.2019.8778423","DOIUrl":"https://doi.org/10.1109/INISTA.2019.8778423","url":null,"abstract":"In this paper we present an application of a new Belief Function-based Inter-Criteria Analysis (BF-ICrA) approach for Global Positioning System (GPS) Surveying Problems (GSP). GPS surveying is an NP-hard problem. For designing Global Positioning System surveying network, a given set of earth points must be observed consecutively. The survey cost is the sum of the distances to go from one point to another one. This kind of problems is hard to be solved with traditional numerical methods. In this paper we use BF-ICrA to analyze an Ant Colony Optimization (ACO) algorithm developed to provide near-optimal solutions for Global Positioning System surveying problem.","PeriodicalId":262143,"journal":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129979298","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}
T. Vafeiadis, Alexandros Nizamis, K. Apostolou, V. Charisi, I. Metaxa, Theofilos D. Mastos, D. Ioannidis, Angelos Papadopoulos, D. Tzovaras
{"title":"Intelligent Information Management System for Decision Support: Application in a Lift Manufacturer's Shop Floor","authors":"T. Vafeiadis, Alexandros Nizamis, K. Apostolou, V. Charisi, I. Metaxa, Theofilos D. Mastos, D. Ioannidis, Angelos Papadopoulos, D. Tzovaras","doi":"10.1109/INISTA.2019.8778290","DOIUrl":"https://doi.org/10.1109/INISTA.2019.8778290","url":null,"abstract":"Intelligent systems and applications on manufacturing domain aim to improve decision-making capabilities, ease complex decision problems, offer predictions related to maintenance activities and provide cost savings to companies. In order to support the aforementioned functionalities, the intelligent prediction and decision support systems are based on machine learning and signal processing techniques, AI algorithms, IoT devices, data mining and modeling techniques, rules and fuzzy logic systems, and advance visualizations. In this paper, we introduce an intelligent information management system that aims to provide predictive maintenance and enhance decision support in a leading lift manufacturer. The proposed solution is a decision support system equipped with analytic tools, IoT sensors and visualizations. The system supports the full cycle of polishing procedures of the lift manufacturer, as it starts from predictive maintenance during the polishing machines' operation and ends in the scrap metals' removal after the operation. Both the intelligent information system and the scenario of its usage in the lift manufacturer's shop floor are presented in this work.","PeriodicalId":262143,"journal":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131152525","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":"Finding Musical Pieces with a Similar Emotional Distribution throughout the Same Composition","authors":"Jacek Grekow","doi":"10.1109/INISTA.2019.8778296","DOIUrl":"https://doi.org/10.1109/INISTA.2019.8778296","url":null,"abstract":"The aim of this work was to build a system that would enable to automatically compare various interpretations of the same composition in terms of the emotions, and to discover which of them are more and less similar. The stages of building such a computer system include such issues as annotating music data, building regressors, aligning different renditions, detecting and visualizing emotions over time, and result analysis. Analyzing the obtained results for Prelude No. 18 by Frédéric Chopin, the author found which performances of the same composition were more similar to each other and which were quite dissimilar in terms of the shaping of emotions over time.","PeriodicalId":262143,"journal":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130189963","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}
A. Bădică, C. Bǎdicǎ, Ion Buligiu, L. Ciora, M. Ganzha, M. Ivanović, M. Paprzycki
{"title":"Optimizing Nash Social Welfare in Semi-Competitive Intermediation Networks","authors":"A. Bădică, C. Bǎdicǎ, Ion Buligiu, L. Ciora, M. Ganzha, M. Ivanović, M. Paprzycki","doi":"10.1109/INISTA.2019.8778270","DOIUrl":"https://doi.org/10.1109/INISTA.2019.8778270","url":null,"abstract":"We have recently proposed a mathematical model of collective profitability, in semi-competitive intermediation networks. In this work, we are interested in determining optimal pricing strategies of network participants. The optimization criterion is defined using the Nash social welfare function. We provide theoretical results of existence of such strategies, as well as computational experimental results, based on nonlinear convex mathematical optimization.","PeriodicalId":262143,"journal":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122784289","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":"Comparison of Ensemble-Based Multiple Instance Learning Approaches","authors":"Pelin Yildirim Taser, K. Birant, Derya Birant","doi":"10.1109/INISTA.2019.8778273","DOIUrl":"https://doi.org/10.1109/INISTA.2019.8778273","url":null,"abstract":"Multiple instance learning (MIL) is concerned with learning from training set of bags including multiple feature vectors. This paradigm has various algorithms as a solution for multiple instance problem. Recently, ensemble learning has become one of the most preferred machine learning technique because its high classification ability. The main goal of ensemble learning is combining multiple learning models and obtaining a decision from all outputs of these models. Considering this motivation, the study presented in this paper proposes an ensemble-based multiple instance learning approach which merges standard algorithms (MIWrapper and SimpleMI) with ensemble learning methods (Bagging and AdaBoost) to improve classification ability. The proposed approach includes ensemble of combination of MIWrapper and SimpleMI learners with Naive Bayes, Support Vector Machines (SVM), Neural Networks (Multilayer Perceptron (MLP)), and Decision Tree (C4.5) as base classifiers. In the experimental studies, the proposed ensemble-based approach was compared with individual MIWrapper and SimpleMI algorithms in terms of accuracy. The obtained results indicate that the ensemble-based approach shows higher classification ability than the conventional solutions.","PeriodicalId":262143,"journal":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132682086","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}