Arkadiusz Rubiec, Mirosław Przybysz, M. Łopatka, Ł. Rykała, P. Krogul, K. Cieślik, R. Typiak
In the following article, the results of a study on the impact of the suspension system used in Unmanned Ground Vehicles (UGVs) on the kinematic excitation of cameras in teleoperation systems are presented. As indicated by preliminary reconnaissance studies, these excitations significantly affect the operator’s ability to perceive the environment and recognize images while driving. Currently, there is a lack of publications and guidelines in the literature regarding the design of UGV suspensions and their evaluation in terms of improving operator perception in teleoperation systems. The studies were conducted in a simulated environment using multibody systems, where various suspension structure variants were developed. The tests were carried out on the ISO 5008 rough test track. The evaluation of the tested suspension structures was carried out using a proprietary method, enabling parametric analysis and the selection of favorable solutions for improving image recognition by the UGV operator. Future research can focus on adjustment of the UGV suspension characteristics which could have significant influence on situational awareness and the operator’s ability to act effectively, especially during dynamic missions.
下文介绍了无人地面车辆（UGV）使用的悬挂系统对远程操纵系统中摄像机运动激励影响的研究结果。初步勘测研究表明，这些激励严重影响了操作员在驾驶过程中感知环境和识别图像的能力。目前，文献中缺乏有关 UGV 悬挂设计及其在改善远程操纵系统操作员感知方面的评估的出版物和指南。研究是在使用多体系统的模拟环境中进行的，其中开发了各种悬挂结构变体。测试在 ISO 5008 粗糙测试轨道上进行。使用专有方法对测试的悬挂结构进行了评估，从而能够进行参数分析，并选择有利的解决方案来提高 UGV 操作员的图像识别能力。未来的研究可侧重于调整无人潜航器的悬挂特性，这可能会对态势感知和操作员的有效行动能力产生重大影响，尤其是在执行动态任务期间。
{"title":"Study on the Influence of an UGV Suspension System on Camera Motion of the Teleoperation System","authors":"Arkadiusz Rubiec, Mirosław Przybysz, M. Łopatka, Ł. Rykała, P. Krogul, K. Cieślik, R. Typiak","doi":"10.14313/par_252/53","DOIUrl":"https://doi.org/10.14313/par_252/53","url":null,"abstract":"In the following article, the results of a study on the impact of the suspension system used in Unmanned Ground Vehicles (UGVs) on the kinematic excitation of cameras in teleoperation systems are presented. As indicated by preliminary reconnaissance studies, these excitations significantly affect the operator’s ability to perceive the environment and recognize images while driving. Currently, there is a lack of publications and guidelines in the literature regarding the design of UGV suspensions and their evaluation in terms of improving operator perception in teleoperation systems. The studies were conducted in a simulated environment using multibody systems, where various suspension structure variants were developed. The tests were carried out on the ISO 5008 rough test track. The evaluation of the tested suspension structures was carried out using a proprietary method, enabling parametric analysis and the selection of favorable solutions for improving image recognition by the UGV operator. Future research can focus on adjustment of the UGV suspension characteristics which could have significant influence on situational awareness and the operator’s ability to act effectively, especially during dynamic missions.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"48 40","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141339345","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}
This article focuses on the construction of reference surfaces with the desired spectral characteristics similar to a gray body. Using wooden plywood with a rough surface and coatings of various emissivity values, surfaces with non-selective spectral properties were created. The consistency of laboratory measurement results using a reflectance spectrometer with data obtained from a hyperspectral camera was confirmed. By utilizing multiple reference surfaces with precisely known emissivity characteristics, it will be possible to accurately determine the radiation components of the measured scene’s surroundings. Although the technology of these surfaces still requires improvement, their usefulness in remote sensing measurements is undeniable. Additionally, differences in response to solar radiation between various reference surfaces provide significant information that can be used in remote sensing and material identification. Incorporating the heating dynamics of the studied objects’ surfaces is crucial for accurate measurement modeling.
{"title":"Non-selective Reference Surfaces for Hyperspectral Remote Sensing in the Long-Wave Infrared Range","authors":"A. Ligienza, M. Kastek, T. Sosnowski, K. Firmanty","doi":"10.14313/par_252/107","DOIUrl":"https://doi.org/10.14313/par_252/107","url":null,"abstract":"This article focuses on the construction of reference surfaces with the desired spectral characteristics similar to a gray body. Using wooden plywood with a rough surface and coatings of various emissivity values, surfaces with non-selective spectral properties were created. The consistency of laboratory measurement results using a reflectance spectrometer with data obtained from a hyperspectral camera was confirmed. By utilizing multiple reference surfaces with precisely known emissivity characteristics, it will be possible to accurately determine the radiation components of the measured scene’s surroundings. Although the technology of these surfaces still requires improvement, their usefulness in remote sensing measurements is undeniable. Additionally, differences in response to solar radiation between various reference surfaces provide significant information that can be used in remote sensing and material identification. Incorporating the heating dynamics of the studied objects’ surfaces is crucial for accurate measurement modeling.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"30 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141342907","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}
The article presents the Hermes route editor in the context of automating the process of creating three-dimensional terrain. The classic approach to this issue was described, the problems present in this process were defined, and then areas suitable for automation were proposed. The following sections present the steps necessary to obtain source data from external, publicly available suppliers, as well as tools for processing them in order to generate and process semi finished products (data tiles). The article discusses a number of problems encountered in the process of automatic generation of three dimensional models of buildings and areas, and also proposes and implements working software solutions. Finally, ways of synthesizing the generated and processed data into one coherent terrain model along with infrastructure elements and buildings were discussed.
{"title":"Generation of Spatial Terrain Using the Hermes Editor","authors":"Mateusz Tecław, Maciej Szłapczyński","doi":"10.14313/par_252/113","DOIUrl":"https://doi.org/10.14313/par_252/113","url":null,"abstract":"The article presents the Hermes route editor in the context of automating the process of creating three-dimensional terrain. The classic approach to this issue was described, the problems present in this process were defined, and then areas suitable for automation were proposed. The following sections present the steps necessary to obtain source data from external, publicly available suppliers, as well as tools for processing them in order to generate and process semi finished products (data tiles). The article discusses a number of problems encountered in the process of automatic generation of three dimensional models of buildings and areas, and also proposes and implements working software solutions. Finally, ways of synthesizing the generated and processed data into one coherent terrain model along with infrastructure elements and buildings were discussed.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"90 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141342097","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}
For accurate remote temperature measurement with a thermal imaging camera, it is necessary to perform radiometric calibration. This allows the radiative parameters of an object, and therefore its temperature, to be related to the response of the infrared detector observing it. The article presents the basic concepts related to radiometric calibration and various factors influencing its effectiveness. The most common calibration methods were also reviewed, and then two of them were implemented and compared on a specially constructed laboratory station, using proprietary software and equipped with a cooled infrared camera, operating in the MWIR range. The camera was calibrated in the temperature range from 20 °C to 50 ° C. The comparison of methods was carried out on the basis of a series of temperature measurements, analysis of absolute and relative errors, as well as analysis of the dispersion of the measured temperature values.
{"title":"Comparative Analysis of Selected Calibration Methods for a Thermal Imaging Camera with a Cooled Detector Operating in the MWIR Range","authors":"Karol Erd","doi":"10.14313/par_252/45","DOIUrl":"https://doi.org/10.14313/par_252/45","url":null,"abstract":"For accurate remote temperature measurement with a thermal imaging camera, it is necessary to perform radiometric calibration. This allows the radiative parameters of an object, and therefore its temperature, to be related to the response of the infrared detector observing it. The article presents the basic concepts related to radiometric calibration and various factors influencing its effectiveness. The most common calibration methods were also reviewed, and then two of them were implemented and compared on a specially constructed laboratory station, using proprietary software and equipped with a cooled infrared camera, operating in the MWIR range. The camera was calibrated in the temperature range from 20 °C to 50 ° C. The comparison of methods was carried out on the basis of a series of temperature measurements, analysis of absolute and relative errors, as well as analysis of the dispersion of the measured temperature values.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"38 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141338591","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}
Selected methods of PID settings for the heading controller in the ship’s autopilot are presented. The consistency of the design is possible due to the fact that the Nomoto model was used for the ship and thanks to the elimination of the time constant of the object by the controller, so that the closed system becomes a 2nd order system. In two cases, it was additionally assumed that the system is to have a double time constant, differing in a given ratio r from the time constant of the object. It has been shown that the heading controller designed in this way provides critical aperiodic waveforms at a step change in the setpoint value and suppresses environmental disturbances better than standardly tuned controllers.
介绍了船舶自动驾驶仪中航向控制器 PID 设置的选定方法。由于船舶使用了 Nomoto 模型，并且控制器消除了物体的时间常数，从而使封闭系统成为二阶系统，因此设计的一致性是可能的。在两种情况下，还假设系统具有双时间常数，与物体的时间常数以给定的比率 r 不同。结果表明，以这种方式设计的航向控制器能在设定值发生阶跃变化时提供临界非周期性波形，并能比标准调谐控制器更好地抑制环境干扰。
{"title":"Tuning the Heading Controller for the Ship’s Autopilot","authors":"Zbigniew Świder","doi":"10.14313/par_252/5","DOIUrl":"https://doi.org/10.14313/par_252/5","url":null,"abstract":"Selected methods of PID settings for the heading controller in the ship’s autopilot are presented. The consistency of the design is possible due to the fact that the Nomoto model was used for the ship and thanks to the elimination of the time constant of the object by the controller, so that the closed system becomes a 2nd order system. In two cases, it was additionally assumed that the system is to have a double time constant, differing in a given ratio r from the time constant of the object. It has been shown that the heading controller designed in this way provides critical aperiodic waveforms at a step change in the setpoint value and suppresses environmental disturbances better than standardly tuned controllers.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"22 20","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141340795","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}
Systems engineering is currently playing a key role in the manufacture, implementation and maintenance of cyber-physical systems. Increasingly, it is becoming an integral tool when designing, for example, robotic systems. This paper proposes a methodology for the design of robotic systems based on two metamodels: EARL at the implementation platform-independent level and MeROS dedicated to ROS/ROS 2. The procedure is demonstrated by analysing a representative application: a heteregonous multi-robot system with a central coordinator.
{"title":"Robotic Systems Development Method Based on EARL and MeROS Metamodels","authors":"Tomasz Winiarski, Jan Kaniuka, Jakub Ostrysz","doi":"10.14313/par_252/11","DOIUrl":"https://doi.org/10.14313/par_252/11","url":null,"abstract":"Systems engineering is currently playing a key role in the manufacture, implementation and maintenance of cyber-physical systems. Increasingly, it is becoming an integral tool when designing, for example, robotic systems. This paper proposes a methodology for the design of robotic systems based on two metamodels: EARL at the implementation platform-independent level and MeROS dedicated to ROS/ROS 2. The procedure is demonstrated by analysing a representative application: a heteregonous multi-robot system with a central coordinator.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"17 24","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141342602","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}
S. Gogler, Krzysztof Sawicki, A. Ligienza, Mariusz Mścichowski
Temperature measurement of allergic skin reactions requires meeting certain criteria regarding temperature resolution between small areas. The usual criterion of temperature resolution is NETD. However, this metric does not take into account the limitations of the spatial resolution of the optical system or the detector. In this paper, a model is presented that allows for selection of camera parameters based on the required spatial thermal resolution and size of the object being imaged. The method has been implemented and compared to results obtained in commercial software and has been applied to evaluate spatial thermal resolution of a prototype objective designed for the LWIR band.
{"title":"A Method of Measurement of Minimum Resolvable Temperature Difference as a Function of Magnification and Defocusing of a Thermal Camera","authors":"S. Gogler, Krzysztof Sawicki, A. Ligienza, Mariusz Mścichowski","doi":"10.14313/par_252/99","DOIUrl":"https://doi.org/10.14313/par_252/99","url":null,"abstract":"Temperature measurement of allergic skin reactions requires meeting certain criteria regarding temperature resolution between small areas. The usual criterion of temperature resolution is NETD. However, this metric does not take into account the limitations of the spatial resolution of the optical system or the detector. In this paper, a model is presented that allows for selection of camera parameters based on the required spatial thermal resolution and size of the object being imaged. The method has been implemented and compared to results obtained in commercial software and has been applied to evaluate spatial thermal resolution of a prototype objective designed for the LWIR band.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"24 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141338933","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}
The article presents data analysis for predicting energy production in photovoltaic (PV) power plant systems. The purpose of long-term forecasts is to determine the effectiveness of preventive actions and manage the power system effectively. Climate variables affecting the production of electricity in photovoltaic systems were analyzed. Forecasting methods using machine learning techniques such as Multi-Layer Perceptron (MLP) neural networks and Support Vector Machine (SVM) were compared. In addition, metrics were selected to determine the quality of forecasts. Determining the quality of forecasts was based on the actual varying conditions, not on the weather forecast data. The way of data preparation to create forecasting models were presented and the models with the best metrics were selected. For this purpose, the Scikit-learn library was used to create scripts in Python. The best results were obtained for regression models: MLPRegressor, CatBoostRegressor and Support Vector Regression. Actual measurement data from a system of optimally-positioned panels with a power of 3.0 kWp were used. For the MLPRegressor model, the highest coefficient of determination 0.605 was achieved with the smallest root-mean-square error of 1.79 KWh.
{"title":"The Use of Machine Learning Algorithms to Forecast Energy Production in a Small PV System","authors":"Adam Idźkowski, Mateusz Sumorek","doi":"10.14313/par_252/37","DOIUrl":"https://doi.org/10.14313/par_252/37","url":null,"abstract":"The article presents data analysis for predicting energy production in photovoltaic (PV) power plant systems. The purpose of long-term forecasts is to determine the effectiveness of preventive actions and manage the power system effectively. Climate variables affecting the production of electricity in photovoltaic systems were analyzed. Forecasting methods using machine learning techniques such as Multi-Layer Perceptron (MLP) neural networks and Support Vector Machine (SVM) were compared. In addition, metrics were selected to determine the quality of forecasts. Determining the quality of forecasts was based on the actual varying conditions, not on the weather forecast data. The way of data preparation to create forecasting models were presented and the models with the best metrics were selected. For this purpose, the Scikit-learn library was used to create scripts in Python. The best results were obtained for regression models: MLPRegressor, CatBoostRegressor and Support Vector Regression. Actual measurement data from a system of optimally-positioned panels with a power of 3.0 kWp were used. For the MLPRegressor model, the highest coefficient of determination 0.605 was achieved with the smallest root-mean-square error of 1.79 KWh.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"5 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141343745","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}
Ela Zawidzka, Jacek Szklarski, J. Kobaka, M. Zawidzki
Arm-Z is a conceptual hyperredundant robotic manipulator composed on linearly joined number of identical modules. Each of them has one-degree-of-freedom (1-DOF) – the relative twist. Since modules are congruent, Arm-Z presents potential economical advantages and enhanced robustness. The modules can be mass produced and easily replaceable. The control of Arm-Z, however, is difficult and not intuitive. Therefore it most often requires the use of computational intelligence techniques. This article presents selected concepts for kinetic street furniture based on Arm-Z: a helical column of adjustable height, a sun tracking shade or solar energy harvesting device, bio-mimicing sculpture, sprinkler or fountain. All these ideas are based on low-tech approach. For this purpose, the initial unit in the chain is fixed to the solid foundation. For simplicity, the drive is applied directly to the first unit and transferred by the means of internal gears to the following modules. All of them are equipped with a set of cylindrical and bevel gears with straight teeth with involute profile (for connecting the modules).
{"title":"Examples of Urban Furniture Based on Arm-Z System","authors":"Ela Zawidzka, Jacek Szklarski, J. Kobaka, M. Zawidzki","doi":"10.14313/par_252/73","DOIUrl":"https://doi.org/10.14313/par_252/73","url":null,"abstract":"Arm-Z is a conceptual hyperredundant robotic manipulator composed on linearly joined number of identical modules. Each of them has one-degree-of-freedom (1-DOF) – the relative twist. Since modules are congruent, Arm-Z presents potential economical advantages and enhanced robustness. The modules can be mass produced and easily replaceable. The control of Arm-Z, however, is difficult and not intuitive. Therefore it most often requires the use of computational intelligence techniques. This article presents selected concepts for kinetic street furniture based on Arm-Z: a helical column of adjustable height, a sun tracking shade or solar energy harvesting device, bio-mimicing sculpture, sprinkler or fountain. All these ideas are based on low-tech approach. For this purpose, the initial unit in the chain is fixed to the solid foundation. For simplicity, the drive is applied directly to the first unit and transferred by the means of internal gears to the following modules. All of them are equipped with a set of cylindrical and bevel gears with straight teeth with involute profile (for connecting the modules).","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141343126","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}
S. Śmigiel, Tomasz Topoliński, D. Ledziński, Tomasz Andrysiak
An electrocardiogram (ECG) is the first step in diagnosing heart disease. Heart rhythm abnormalities are among the early signs of heart disease, which can contribute to a patient’s heart attack, stroke, or sudden death. The importance of the ECGs has increased with the development of technologies based on machine learning and remote monitoring of vital signs. In particular, early detection of arrhythmias is of great importance when it comes to diagnosing a patient with heart disease. This is made possible through recognizing and classifying pathological patterns in the ECG signal. This paper presents a system for mobile monitoring of ECG signals enriched with the results of the study of the application of machine learning models from the group of Tree-based ML techniques and Neural Networks in the context of heart disease classification. The research was carried out through the use of the publicly available PTB-XL database of the ECG signals. The results were analyzed in the context of classification accuracy for 2, 5 and 15 classes of heart disease. Moreover, a novelty in the work is the proposal of machine learning techniques and architectures neural networks, which, have been selected to be applicable to IoT devices. It has been proven that the proposed solution can run in real time on IoT devices.
心电图（ECG）是诊断心脏病的第一步。心律异常是心脏病的早期征兆之一，可导致患者心脏病发作、中风或猝死。随着基于机器学习和远程生命体征监测技术的发展，心电图的重要性日益凸显。特别是，在诊断心脏病患者时，早期发现心律失常非常重要。这可以通过识别心电图信号中的病理模式并对其进行分类来实现。本文介绍了一种心电信号移动监测系统，该系统采用了基于树的 ML 技术和神经网络的机器学习模型在心脏病分类方面的应用研究成果。研究是通过使用公开的 PTB-XL 心电信号数据库进行的。研究结果根据 2、5 和 15 类心脏病的分类准确率进行了分析。此外，这项工作的新颖之处在于提出了适用于物联网设备的机器学习技术和神经网络架构。事实证明，所提出的解决方案可以在物联网设备上实时运行。
{"title":"The ECG Signal Monitoring System Using Machine Learning Methods and LoRa Technology","authors":"S. Śmigiel, Tomasz Topoliński, D. Ledziński, Tomasz Andrysiak","doi":"10.14313/par_252/21","DOIUrl":"https://doi.org/10.14313/par_252/21","url":null,"abstract":"An electrocardiogram (ECG) is the first step in diagnosing heart disease. Heart rhythm abnormalities are among the early signs of heart disease, which can contribute to a patient’s heart attack, stroke, or sudden death. The importance of the ECGs has increased with the development of technologies based on machine learning and remote monitoring of vital signs. In particular, early detection of arrhythmias is of great importance when it comes to diagnosing a patient with heart disease. This is made possible through recognizing and classifying pathological patterns in the ECG signal. This paper presents a system for mobile monitoring of ECG signals enriched with the results of the study of the application of machine learning models from the group of Tree-based ML techniques and Neural Networks in the context of heart disease classification. The research was carried out through the use of the publicly available PTB-XL database of the ECG signals. The results were analyzed in the context of classification accuracy for 2, 5 and 15 classes of heart disease. Moreover, a novelty in the work is the proposal of machine learning techniques and architectures neural networks, which, have been selected to be applicable to IoT devices. It has been proven that the proposed solution can run in real time on IoT devices.","PeriodicalId":383231,"journal":{"name":"Pomiary Automatyka Robotyka","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141343985","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：