Alessio Moreschini, Mattia Mattioni, S. Monaco, D. Normand-Cyrot
{"title":"A gradient descent algorithm built on approximate discrete gradients","authors":"Alessio Moreschini, Mattia Mattioni, S. Monaco, D. Normand-Cyrot","doi":"10.1109/ICSTCC55426.2022.9931872","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931872","url":null,"abstract":"We propose an optimization method obtained by the approximation of a novel discretization approach for gradient dynamics recently proposed by the authors. It is shown that the proposed algorithm ensures convergence for all amplitudes of the step size, contrarily to classical implementations.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122608347","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":"Search Algorithm for Optimal Synthesis of Decoder for RAMs with Error-Correcting Codes","authors":"Florin Leon, P. Cașcaval","doi":"10.1109/ICSTCC55426.2022.9931899","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931899","url":null,"abstract":"This paper addresses the issue of optimal design of the decoder in fault-tolerant RAMs with Single Error Correcting and Double Error Detecting facilities (SECDED). If for the encoding logic it is recommended to generate each control bit independently (a classic implementation), for the decoding logic the authors recommend a simpler synthesis, in order to reduce the complexity as much as possible. This is explained by the fact that the decoding logic no longer has any fault tolerance facilities. Since the decoder is implemented as a network of XOR logic gates, the problem we address is to find the simplest structure using 2-input or 3-input XOR gates as base cells. To this end, a search algorithm has been implemented to identify in the parity-check matrix common sets of bits that can be used to generate multiple error control bits. The efficiency of the solution we propose, in terms of complexity, is demonstrated by comparison with the classic one in which the error bits are generated independently.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131150096","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":"Automotive algorithm implemented in the microcontroller for adapting regenerative braking","authors":"N. Nistor, L. Baicu, B. Dumitrascu","doi":"10.1109/ICSTCC55426.2022.9931834","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931834","url":null,"abstract":"In this paper an original adaptive method for maximizing the energy transferred to the car's battery during regenerative braking is presented. The paper is based on a simulation in Proteus LabCenter, using a battery model, based on functional criteria, with the energy recovered from a reversible motor. The battery management algorithm was implemented on ATMEGA 328 microcontroller, and a MC34063 DC-to-DC converter control circuit. The voltage variations of reversible motor, recovered during braking are simulated with a variable voltage applied on the system input and the results show that the output voltage of the DC-to-DC converter must be continuously adjusted during the braking process. The efficiency lies in the fact that although the braking sequences do not take place for long periods, they are made at currents recovered from magnetic induction of considerable values.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134162360","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":"Parametrization of Airloads Using a Homogeneity-based Orthogonal Decomposition","authors":"Finn Matras, D. Reinhardt, M. D. Pedersen","doi":"10.1109/ICSTCC55426.2022.9931879","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931879","url":null,"abstract":"This work proposes a novel parametrization strategy for steady aerodynamic forces. We point out that air-loads are homogeneous and enforce this property by using a parametrization based on spherical harmonics. The parametrization enables an analogue of frequency-based truncation and a variation on the Singular Value Decomposition (SVD), constituting an orthogonal decomposition of the modeled airloads. The method's utility is showcased for model reduction and identification purposes.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131915339","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":"Object Detection in Invoices","authors":"Andrei-Stefan Bulzan, C. Cernazanu-Glavan","doi":"10.1109/ICSTCC55426.2022.9931900","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931900","url":null,"abstract":"Key field information extraction from documents is an increasingly covetable task. Previous related work has touched upon the subject through the lens of rule-based systems or through natural language processing methods. In this paper we see the task of information extraction from invoices as an object detection task. To this end, we used three different models YOLOv5, Scaled YOLOv4 and Faster R-CNN to detect key field information in invoices. Additionally, we propose a data preprocessing method that helps to better generalize the learning. All of the experiments were performed on a custom made dataset with a very high variety of invoice layouts. This decision comes in part from the lack of any suitable public dataset and from the need of finding the best procedure for annotating data pertaining to this task. The obtained results were encouraging, leading us to the conclusion that object detection is a viable method for information extraction.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"8 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132979654","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}
Omar Santander, Vidyashankar Kuppuraj, Christopher A. Harrison, M. Baldea
{"title":"Deep learning economic model predictive control for refinery operation: A fluid catalytic cracker - fractionator case study","authors":"Omar Santander, Vidyashankar Kuppuraj, Christopher A. Harrison, M. Baldea","doi":"10.1109/ICSTCC55426.2022.9931761","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931761","url":null,"abstract":"An integrated deep learning - economic model predictive control (EMPC) framework for large scale processes is presented. The framework is successfully implemented to a realistic fluid catalytic cracker (FCC) - fractionator process. Scenarios under the effect of no disturbances (nominal) and with disturbances are simulated demonstrating fast computation (potentially allowing industrial implementation) and improved performance (taking into account process nonlinear behavior, enhancing the process operating profit).","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116841139","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}
Andrei-Daniel Andreiana, C. Bǎdicǎ, Eugenia Ganea, B. Andreiana
{"title":"A Review of the Impact of Convolutional Neural Networks in the Process of Renal Cancer Diagnosis","authors":"Andrei-Daniel Andreiana, C. Bǎdicǎ, Eugenia Ganea, B. Andreiana","doi":"10.1109/ICSTCC55426.2022.9931820","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931820","url":null,"abstract":"Accurate diagnosis using histopathology images re-quires experienced pathologists, a large amount of work and time. Recent studies show that AI could be a solution to help pathologist by offering a fast and reliable help for setting a diagnosis. This paper offers a review of the latest advancements in renal cancer diagnosis using advanced AI methods, especially Convolutional Neural Networks. It includes both Computer Aided Diagnosis solutions and algorithms or frameworks that use histopathology images as input. It provides extensive data about the input databases, preprocessing methods, feature extraction, classifier architectures and results quantification. Further, it elaborates on the type of classification each algorithm offers, ranging from segmentation to benign-malignant classification and up to renal cancer subtypes differentiation or Fuhrman grade determination.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"29 3-4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128828816","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":"Improving the Performance of Distributed Model Predictive Control by Applying Graph Partitioning Methods","authors":"Daniel Burk, Andreas Völz, K. Graichen","doi":"10.1109/ICSTCC55426.2022.9931785","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931785","url":null,"abstract":"The major part of the execution time of distributed algorithms is required for the communication between agents. This paper approaches a reduction of the communication effort by reducing the number of edges in the considered graph. This is achieved by partitioning the graph and formulating a super graph. At first, the computational and communication effort is evaluated on an abstract level independent of the distributed algorithm, before the Alternating Direction Method of Multipliers (ADMM) is applied to a system of coupled water tanks. This allows to outline the trade-off between computation and communication time and to evaluate an optimal number of partitions that minimizes the execution time. The influence of the partitioning on the convergence behavior of the distributed algorithm is studied and compared with the concept of neighbor approximation.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129976292","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 Multi-Layer Feed Forward Neural Network for Breast Cancer Diagnosis from Ultrasound Images","authors":"M. Miron, S. Moldovanu, Anisia Culea-Florescu","doi":"10.1109/ICSTCC55426.2022.9931772","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931772","url":null,"abstract":"Diagnosis of breast cancer from ultrasound images (USIs) and images processing are two main stages of medical computing field. In this paper, we propose a Multi-Layer Feed Forward Neural Network (MLFNN) for classification of benign and malignant breast tumors by using a Python based implementation. The neural model is trained using the preprocessed regions of interests (ROIs) from USIs that belong to the Breast Ultrasound Dataset (BUSI dataset). The preprocessing procedure includes extracting the ROIs, resizing, normalizing, and flattening. The ROIs are obtained with our own algorithm that overlaps the original image with its corresponding ground truth image. More images and tumor shapes employed in the training stage of the neural network can lead to better prediction performances. In this study, the binary classification of tumors into benignancy or malignancy gives 99% training accuracy, 86% validation accuracy and 71.43% test accuracy.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130871490","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":"Model-free Control Under Passivity Constraint Applied to BLDC control","authors":"Razvan Mocanu, A. Onea","doi":"10.1109/ICSTCC55426.2022.9931864","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931864","url":null,"abstract":"The objective of this work is to derive the requirements for passivity for a model-free control strategy. We describe a method for model-free control of passive systems that can be applied to the speed control of a DC synchronous machine. The approach is intended for systems that are internally passive. We establish the conditions for the interconnected system's passivity. We use the strategy to control the angular velocity of a brushless DC machine (BLDC). Theoretical results are supported by simulation and experimental results, which demonstrate the effectiveness of the algorithm.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130293328","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}