{"title":"Ensemble noisy label detection on MNIST","authors":"I. Fazekas, Attila Barta, László Fórián","doi":"10.33039/AMI.2021.03.015","DOIUrl":"https://doi.org/10.33039/AMI.2021.03.015","url":null,"abstract":"In this paper machine learning methods are studied for classification data containing some misleading items. We use ensembles of known noise correction methods for preprocessing the training set. Preprocessing can be either relabeling or deleting items detected to have noisy labels. After preprocessing, usual convolutional networks are applied to the data. With preprocessing, the performance of very accurate convolutional networks can be further improved.","PeriodicalId":8040,"journal":{"name":"Applied Medical Informaticvs","volume":"1 1","pages":"125-137"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77290428","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":"Exploiting the structure of communication in actor systems","authors":"K. Schäffer, C. Sidló","doi":"10.33039/AMI.2021.03.006","DOIUrl":"https://doi.org/10.33039/AMI.2021.03.006","url":null,"abstract":"We propose a novel algorithm for minimizing communication costs of multi-threaded and distributed actor systems, to gain performance advantage by dynamically adapting to the structure of actor communication. We provide an implementation in Circo, an open source actor system, and show promising experimental results.","PeriodicalId":8040,"journal":{"name":"Applied Medical Informaticvs","volume":"54 1","pages":"271-282"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88438217","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":"Motor imagery EEG classification using feedforward neural network","authors":"T. Majoros, S. Oniga, Yu Xie","doi":"10.33039/AMI.2021.04.007","DOIUrl":"https://doi.org/10.33039/AMI.2021.04.007","url":null,"abstract":"Electroencephalography (EEG) is a complex voltage signal of the brain and its correct interpretation requires years of training. Modern machine- learning methods help us to extract information from EEG recordings and therefore several brain-computer interface (BCI) systems use them in clinical applications. By processing the publicly available PhysioNet EEG dataset, we extracted information that could be used for training feedforward neural network to classify three types of activities performed by 109 volunteers. While volunteers were performing different activities, a BCI2000 system was recording their EEG signals from 64 electrodes. We used motor imagery runs where a target appeared on either the top or the bottom of a screen. The subject was instructed to imagine opening and closing either both his/her fists (if the target is on top) or both his/her feet (if the target is on the bottom) until the target disappears from the screen. We used the EEGLAB Matlab toolbox for EEG signal processing and applied several feature extraction techniques. Then we evaluated the classification performance of feedforward, multilayer perceptron (MLP) networks with different structures (number of layers, number of neurons). Achieved accuracy score for test data was 71.5%.","PeriodicalId":8040,"journal":{"name":"Applied Medical Informaticvs","volume":"18 1","pages":"235-244"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86313172","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 contribution to scheduling jobs submitted by finite-sources in computational clusters","authors":"A. Kuki, T. Bérczes, Á. Tóth, J. Sztrik","doi":"10.33039/AMI.2021.03.008","DOIUrl":"https://doi.org/10.33039/AMI.2021.03.008","url":null,"abstract":"Data science and data processing are very popular topics nowadays. Un- like a few years ago, everything is connected to data now and we have to handle these kinds of large data well. Therefore the distributed heterogeneous resources of networks e.g. the computational grid, have attracted great interest. It has become a challenge to schedule jobs in order to utilize the available resources effectively. The allocation of arriving jobs has a great impact on the efficiency and the energy consumption of the system. A generalized finite source model is presented in this paper. Our main goal is to build up models for the performance evaluation of scheduling computeintensive jobs with unknown service times in a computational cluster that consists of servers of different types. For this purpose we determine various performance measures for all combinations of three scheduling policies (two of them are the novelty of this paper: the MRT and the MRTHP policies) which can be used for assigning jobs to servers with three schemes for buffering arriving jobs. Furthermore, we investigate the effect of switching off idle servers on the energy consumption of the system under these combinations of scheduling policies and buffering schemes. Computational results obtained by simulation show that the choice of the scheduling policy and the buffering scheme plays an important role in ensuring the quality of service parameters such as the waiting time and the response time experienced in the case of arriving jobs. However, the energy consumption is only affected by the scheduling policy and the energy saving mode, while the buffering scheme does not have a significant impact.","PeriodicalId":8040,"journal":{"name":"Applied Medical Informaticvs","volume":"25 1","pages":"201-218"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81230073","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":"SimBPDD: Simulating differential distributions in Beta-Poisson models, in particular for single-cell RNA sequencing data","authors":"Roman Schefzik","doi":"10.33039/AMI.2021.03.003","DOIUrl":"https://doi.org/10.33039/AMI.2021.03.003","url":null,"abstract":"Beta-Poisson (BP) models employ Poisson distributions, where the corresponding rate parameter itself is a Beta-distributed random variable. They have been shown to appropriately mimic gene expression distributions in the context of single-cell ribonucleic acid sequencing (scRNA-seq), a breakthrough technology allowing to sequence information from individual biological cells and facilitating fundamental insights into numerous fields of biology. A prominent scRNA-seq data analysis task is to identify differences in gene expression distributions across two conditions. To validate new statistical approaches in this context, one typically has to rely on accurate simulations, as usually no ground truth for an assessment is available. We introduce several simulation procedures that allow to generate differential distributions (DDs) based on BP models. In particular, we describe how to create different types of DDs, mirroring various sources or origins of a difference, and different degrees of DDs, from a weak to a strong difference. The soundness of the simulation procedures is shown in a validation study in which theoretically expected model properties of the DD simulations are confirmed. The findings are in principle not restricted to the scRNA-seq context and may be generally applicable also to other application areas. The simulation approaches are implemented in the publicly available R package SimBPDD.","PeriodicalId":8040,"journal":{"name":"Applied Medical Informaticvs","volume":"3 1","pages":"283-298"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78960745","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}
Norbert Bátfai, Renátó Besenczi, P. Jeszenszky, M. Szabó, M. Ispány
{"title":"Markov modeling of traffic flow in Smart Cities","authors":"Norbert Bátfai, Renátó Besenczi, P. Jeszenszky, M. Szabó, M. Ispány","doi":"10.33039/AMI.2021.04.008","DOIUrl":"https://doi.org/10.33039/AMI.2021.04.008","url":null,"abstract":"Modeling and simulating the traffic flow in large urban road networks are important tasks. A mathematically rigorous stochastic model proposed in [8] is based on the synthesis of the graph and Markov chain theories. In this model, the transition probability matrix describes the traffic dynamics and its unique stationary distribution approximates the proportion of the vehicles at the segments of the road network. In this paper various Markov models are studied and a simulation method is presented for generating random traffic trajectories on a road network based on the two-dimensional stationary distribution of the models. In a case study we apply our method to the central region of the city of Debrecen by using the road network data from the OpenStreetMap project which is available publicly.","PeriodicalId":8040,"journal":{"name":"Applied Medical Informaticvs","volume":"1 1","pages":"21-44"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91183761","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":"Post-processing methods for calibrating the wind speed forecasts in central regions of Chile","authors":"Mailiu Díaz, O. Nicolis, J. Marín, S. Baran","doi":"10.33039/AMI.2021.03.012","DOIUrl":"https://doi.org/10.33039/AMI.2021.03.012","url":null,"abstract":"In this paper we propose some parametric and non-parametric post-processing methods for calibrating wind speed forecasts of nine Weather Research and Forecasting (WRF) models for locations around the cities of Valparaíso and Santiago de Chile (Chile). The WRF outputs are generated with different planetary boundary layers and land-surface model parametrizations and they are calibrated using observations from 37 monitoring stations. Statistical calibration is performed with the help of ensemble model output statistics and quantile regression forest (QRF) methods both with regional and semi-local approaches. The best performance is obtained by the QRF using a semilocal approach and considering some specific weather variables from WRF simulations. ∗This research was partially supported by the Interdisciplinary Center of Atmospheric and Astro-Statistical Studies, University of Valparaíso, Chile. Annales Mathematicae et Informaticae 53 (2021) pp. 93–108 doi: https://doi.org/10.33039/ami.2021.03.012 url: https://ami.uni-eszterhazy.hu","PeriodicalId":8040,"journal":{"name":"Applied Medical Informaticvs","volume":"13 1","pages":"93-108"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82559469","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":"Resistance determination of joints of plastic components, made by additive technologies, to effect of negative temperatures","authors":"I. S. Nefyolov, Moscow Automobile, N. Baurova","doi":"10.31044/1994-6260-2021-0-1-23-27","DOIUrl":"https://doi.org/10.31044/1994-6260-2021-0-1-23-27","url":null,"abstract":"The effect of negative temperatures on strength characteristics of plastic component joints (hot gas welding, gluing, 3D-welding) made with the use of additive technologies has been examined. It has been found out that 3D-wlding allows one to produce joints with the highest strength properties. It was shown that low temperature values (–30 °С) did not have the negative influence on strength properties of ABS-plastic joints but even increased them as compared with analogues samples tested at the room temperature.","PeriodicalId":8040,"journal":{"name":"Applied Medical Informaticvs","volume":"21 1","pages":"23-27"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88540976","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":"TEE-based protection of cryptographic keys on embedded IoT devices","authors":"Dorottya Papp, Máté Zombor, L. Buttyán","doi":"10.33039/AMI.2021.02.002","DOIUrl":"https://doi.org/10.33039/AMI.2021.02.002","url":null,"abstract":"The Internet of Things (IoT) consists of billions of embedded devices connected to the Internet. Secure remote management of many of these devices requires them to store and use long-term cryptographic keys. In this work we propose to protect cryptographic keys in embedded IoT devices using a Trusted Execution Environment (TEE) which is supported on many embedded platforms. Our approach provides similar protection as secure co-processors, but does not actually require an additional secure hardware element.","PeriodicalId":8040,"journal":{"name":"Applied Medical Informaticvs","volume":"8 5 1","pages":"245-256"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86675986","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":"Dakwah Perempuan: Pemberdayaan Perempuan Muhammadiyah Sulawesi Tenggara","authors":"M. Yusuf","doi":"10.31332/AM.V13I2.2127","DOIUrl":"https://doi.org/10.31332/AM.V13I2.2127","url":null,"abstract":"Penelitian ini berjudul “Pemberdayaan Perempuan Muhammadiyah Sultra di Kota Kendari. Penelitian ini diangkat berdasarkan observasi awal sebelumnya bahwa belum ada profil tentang Profil Pemberdayaan Perempuan Muhammadiyah di Sulawesi Tenggara. Tujuan penelitian ini adalah Untuk menemukan Pemberdayaan perempuan Muhammadiyah di Sulawesi Tenggara. Metode yang digunakan dalam penelitian ini adalah metode penelitian kualitatif dengan pendekatan historis. Hasil penelitian ini adalah dimulai dari priode ibu Tawaningsih yaitu beliau belum membentuk PDA sama sekali karena masih sibuk melaksanakan pengkaderan dan program kerja yang lainnya, walaupun pada priodenya sempat dibentuk TK ABA yang diletakkan di perumahan Pindayani Lepo-lepo karena alasan kesibukan sehingga TK ABA tersebut tidak ditindak lanjuti. Pada periode ibu Fahima banyak mengalami pemberdayaan diantaranya terbentuklah Pimpinan Daerah diantaranya PD Raha, PD Kota Kendarai, dan PD Kolaka. Selain membentuk PD beliau juga mendirikan amal usaha diantaranya TK ABA I lorong Jati dan TK ABA II di Andounohu. Pada pengurusan ibu Nurseha Gazali beliau juga banyak memberdayakan PWA terutama dipriode kedua beliau yang berhasil membentuk PD yaitu PD Konawe Selatan, PD Bombana, dan PD Bau-Bau. Serta di priode kedua beliu juga sempat mendirikan TK ABA III di Baruga diatas tanah waqaf beliau sendiri. Pada periode, selanjutnya yaitu pada tahun 2010–2015 terpilihlah ibu Marlina Gazali menggantikan Nurseha Gazali dan dilanjutkan pada periode selanjutnya pada tahun 2015 – 2020. Pada kepemimpinan Marlina Gazali PWA kembali mengalami kemajuan diantaranya membangun Gedung Serba Guna yang dijadikan sebagai pusat kegiatan Aisyiyah, selain itu beliau membentuk kembali Pimpinan Daerah yaitu PD Kolaka Timur, Muna Barat, dan Kolaka Utara. Kemudian PWA juga membangun TK ABA IV Baruga.","PeriodicalId":8040,"journal":{"name":"Applied Medical Informaticvs","volume":"74 1","pages":"231-252"},"PeriodicalIF":0.0,"publicationDate":"2020-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77539999","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}