Dragana Suvara, Kristina Vajda, Miroslav Katanić, M. Kisić, M. Damnjanović, K. Babković
{"title":"3D Printed Capacitive Displacement/Force Sensor with Different Patterns of Dielectric Layer","authors":"Dragana Suvara, Kristina Vajda, Miroslav Katanić, M. Kisić, M. Damnjanović, K. Babković","doi":"10.1109/TELFOR56187.2022.9983791","DOIUrl":"https://doi.org/10.1109/TELFOR56187.2022.9983791","url":null,"abstract":"In this paper a simple capacitive sensor for displacement/force measuring is presented. Additive 3D printing technology was used to make the sensor housing and electrodes, while silicone rubber was used for the dielectric layer to ensure good sensitivity to the applied force. Three different patterns of dielectric layers were investigated. During experimental measurements, a change in capacitance was observed depending on the performed displacement in the range of 0.5 mm with 0.1 mm increments. The measured capacitance values and characteristics for all three types of sensors were compared.","PeriodicalId":277553,"journal":{"name":"2022 30th Telecommunications Forum (TELFOR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129753314","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 New Clutter Removal Method Based on Direct Robust Matrix Factorization for Buried Target Detection","authors":"D. Kumlu, I. Erer","doi":"10.1109/TELFOR56187.2022.9983731","DOIUrl":"https://doi.org/10.1109/TELFOR56187.2022.9983731","url":null,"abstract":"Clutter decreases severely the performance of target detection algorithms in ground-penetrating radar (GPR) imaging systems. Low rank and sparse decomposition (LRSD) methods divide the data into its clutter and target components by rank minimization with sparsity constraint. This paper proposes a direct solution for LRSD decomposition of the GPR data unlike robust principal component analysis (RPCA) which uses a nuclear norm relaxation. The non convex optimization problem is solved by successive partial singular value decompositions (SVD)s and soft thresholding operations and does not require any parameter computation. The visual and numerical comparisons for both simulated and real data show the superiority of the direct robust matrix factorization (DRMF) over the relaxation solution RPCA as well as over the traditional low rank methods SVD and PCA.","PeriodicalId":277553,"journal":{"name":"2022 30th Telecommunications Forum (TELFOR)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124912179","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}
Slobodan Djukanovic, Nikola Bulatovic, Ivana Cavor
{"title":"A dataset for audio-video based vehicle speed estimation","authors":"Slobodan Djukanovic, Nikola Bulatovic, Ivana Cavor","doi":"10.1109/TELFOR56187.2022.9983773","DOIUrl":"https://doi.org/10.1109/TELFOR56187.2022.9983773","url":null,"abstract":"Accurate speed estimation of road vehicles is important for several reasons. One is speed limit enforcement, which represents a crucial tool in decreasing traffic accidents and fatalities. Compared with other research areas and domains, the number of available datasets for vehicle speed estimation is still very limited. We present a dataset of on-road audio-video recordings of single vehicles passing by a camera at known speeds, maintained stable by the on-board cruise control. The dataset contains thirteen vehicles, selected to be as diverse as possible in terms of manufacturer, production year, engine type, power and transmission, resulting in a total of 400 annotated audio-video recordings. The dataset is fully available and intended as a public benchmark to facilitate research in audio-video vehicle speed estimation. In addition to the dataset, we propose a cross-validation strategy which can be used in a machine learning model for vehicle speed estimation. Two approaches to training-validation split of the dataset are proposed.","PeriodicalId":277553,"journal":{"name":"2022 30th Telecommunications Forum (TELFOR)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130263003","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}
Miloš Kotlar, Marija Punt, Z. Radivojević, M. Cvetanović
{"title":"Meta features for anomaly detection in AutoML","authors":"Miloš Kotlar, Marija Punt, Z. Radivojević, M. Cvetanović","doi":"10.1109/TELFOR56187.2022.9983735","DOIUrl":"https://doi.org/10.1109/TELFOR56187.2022.9983735","url":null,"abstract":"This abstract paper sheds light on automated machine learning systems used for anomaly detection. Such systems can propose optimal model for a given tasks by using meta learning as a core component. Systems presented in this paper are based on domain-specific meta features for choosing an optimal unsupervised model for anomaly detection. It also proposes further improvements by using multi-dimensional dense vectors to limit the dimensions of meta features.","PeriodicalId":277553,"journal":{"name":"2022 30th Telecommunications Forum (TELFOR)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130388401","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":"Technique for Testing Optical Fibers by Using Electronic Microscopy","authors":"M. Popescu, A. Náaji, Monica Ciobanu, D. Lacrama","doi":"10.1109/TELFOR56187.2022.9983734","DOIUrl":"https://doi.org/10.1109/TELFOR56187.2022.9983734","url":null,"abstract":"Optical fibers have several advantages over traditional communication lines, such as: support higher bandwidth, less susceptibility to interference, stronger data security, they are much thinner and lighter, etc. The paper proposes a technique that characterizes, describes and defines a guided environment imported into the European Union (EU), which complies with the recommendations of the International Telecommunication Union (ITU-T) G.652.D and G.657.A2. Using this technique, a product (optical fiber) can be framed either under the European Union Integrated Tariff (TARIC) code 85447000 00, for which customs duties have a level, or under the TARIC commodity code 90011090 90, for which the value of custom duties would be calculated on the basis of a certain percent. In comparison to other techniques used in practice, the technique proposed by us requires, in addition, a multitude of new tests, which can fit the optical fiber in one of the fields of applicability, respectively, telecommunications, IT communications, various industrial or medical applications for the purpose of classification under a TARIC commodity code.","PeriodicalId":277553,"journal":{"name":"2022 30th Telecommunications Forum (TELFOR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128769930","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}
D. Brdjanin, G. Banjac, Nebojša Babić, Nenad Golubovic
{"title":"Towards the Speech-driven Database Design","authors":"D. Brdjanin, G. Banjac, Nebojša Babić, Nenad Golubovic","doi":"10.1109/TELFOR56187.2022.9983727","DOIUrl":"https://doi.org/10.1109/TELFOR56187.2022.9983727","url":null,"abstract":"The paper presents an early prototype of an online tool named SpeeD, which is aimed at conversion of a recorded speech into the corresponding conceptual database model. SpeeD is the first tool that provides such functionality. The tool is currently able to process English speech and generate the model represented by the corresponding UML class diagram.","PeriodicalId":277553,"journal":{"name":"2022 30th Telecommunications Forum (TELFOR)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128024490","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}
Luka Jovanovic, Nemanja Milutinovic, Masa Gajevic, Jelena O. Krstovic, Tarik A. Rashid, A. Petrovic
{"title":"Sine Cosine Algorithm for Simple recurrent neural network Tuning for Stock Market Prediction","authors":"Luka Jovanovic, Nemanja Milutinovic, Masa Gajevic, Jelena O. Krstovic, Tarik A. Rashid, A. Petrovic","doi":"10.1109/TELFOR56187.2022.9983694","DOIUrl":"https://doi.org/10.1109/TELFOR56187.2022.9983694","url":null,"abstract":"Deep artificial neural networks have recently gained popularity in the time series forecasting literature. Recurrent neural networks’ higher suitability for this type of problem is the reason why this type of network has been chosen over other deep neural network approaches. Due to the number of parameters used the simplicity of these networks is considerable. This characteristic makes deep recurrent neural networks highly suitable for the problems of forecasting. Unfortunately, finding recurrent neural architecture for each specific task is NP-hard, therefore employment of metaheuristics is appropriate. Accordingly, the research proposed in this paper tackles tuning simple recurrent neural networks by sine cosine algorithm for stock market prediction. The proposed method’s performance was compared with other metaheuristics and validated against the Nikkei stock exchange.","PeriodicalId":277553,"journal":{"name":"2022 30th Telecommunications Forum (TELFOR)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123418711","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}
M. Barjaktarović, M. Faralli, M. Bertamini, L. Bruzzone
{"title":"A multispectral acquisition system for potential detection of Flavescence dorée","authors":"M. Barjaktarović, M. Faralli, M. Bertamini, L. Bruzzone","doi":"10.1109/TELFOR56187.2022.9983685","DOIUrl":"https://doi.org/10.1109/TELFOR56187.2022.9983685","url":null,"abstract":"Agriculture is under constant pressure to increase the production rate and to provide more food or resources for other industries. Without precision agriculture it is not possible to fulfil these requirements. Medium and large-size farms already adopted this technology, but small farms are far from precision agriculture due to the high initial costs. In this paper we present a bespoke and affordable multispectral camera for precision farming and illustrate its application in the detection of Flavescence dorée. This is a grapevine disease that makes a great concern to grapevine producers in the whole Mediterranean region. Flavescence dorée is the only quarantine disease in the European region. The related mandatory control procedures include uprooting every infected plant, with the obligation to uproot the vineyard when the infection exceed the 20% of threshold infection, hence resulting in a high economical loss. Thus, it is highly important to detect even a single infected plant over an entire vineyard plot, preventing the spreading of Flavescence dorée at earliest stages. We used the in-house developed multispectral camera together with a hyperspectral camera to acquire data from two vineyards near Riva del Garda, Trentino, Italy, during the summer of 2022. These data are the starting point for selecting the optimal spectral bands for the detection of Flavescence dorée using affordable multispectral approaches and developing an appropriate classification algorithm.","PeriodicalId":277553,"journal":{"name":"2022 30th Telecommunications Forum (TELFOR)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114074249","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}
Stefana Bogojević, M. Banovic, J. Crnjanski, M. Krstić, D. Gvozdić
{"title":"Performance Analysis of Optical Reservoir Computer with Two Delayed Inputs","authors":"Stefana Bogojević, M. Banovic, J. Crnjanski, M. Krstić, D. Gvozdić","doi":"10.1109/TELFOR56187.2022.9983772","DOIUrl":"https://doi.org/10.1109/TELFOR56187.2022.9983772","url":null,"abstract":"In this paper, a novel reservoir computing architecture based on the single nonlinear node with two delayed inputs is presented. Its performance is investigated on time-series forecasting tasks, for two different profiles of activation functions implemented in the optical domain. Simulation results show reduced NRMSE value to around 3% for Mackey-Glass time series prediction 11 steps in advance, when sine squared optical activation function based on Mach-Zehnder modulator is used.","PeriodicalId":277553,"journal":{"name":"2022 30th Telecommunications Forum (TELFOR)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114544379","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":"Secrecy Performance of RIS-enabled Linear Interference Alignment Multi-User MIMO Network","authors":"Hakan Alakoca, L. Durak-Ata","doi":"10.1109/TELFOR56187.2022.9983711","DOIUrl":"https://doi.org/10.1109/TELFOR56187.2022.9983711","url":null,"abstract":"In this study, an reconfigurable intelligent surface (RIS)-enabled linear interference alignment (IA) is examined for multi-user multiple-input multiple-output (MU-MIMO) in a presence of an eavesdropper. Modified precoder and postcoder matrix designs are introduced to minimize interference for legitimate users which is used as ensuring secure communications. According to our findings, the secrecy sum rate of the IA-based RIS-enabled MU-MIMO outperforms that without IA case due to the intensive interference of the communication environment.","PeriodicalId":277553,"journal":{"name":"2022 30th Telecommunications Forum (TELFOR)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121857996","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}