Książki, monografie, podręczniki, rozdziały (WEEIiA)
Stały URI dla kolekcjihttp://hdl.handle.net/11652/171
Przeglądaj
8 wyniki
collection.search.results.head
Pozycja Performance Analysis of Machine Learning Platforms Using Cloud Native Technology on Edge Devices(Wydawnictwo Politechniki Łódzkiej, 2023) Cłapa, Konrad; Grudzień, Krzysztof; Sierszeń, ArturThis article presents the results of an experiment performed on a machine learning edge computing platform composed of a virtualized environment with a K3s cluster and Kubeflow software. The study aimed to analyze the effectiveness of executing Kubeflow pipelines for simulated parallel executions. A benchmarking environment was developed for the experiment to allow system performance measurements based on parameters, including the number of pipelines and nodes. The results demonstrate the impact of the number of cluster nodes on computational time, revealing insights that could inform future decisions regarding increasing the effectiveness of running machine learning pipelines on edge devices.Pozycja Carbon Footprint Reduction of a Petrochemical Process Supported by ML and Digital Twin modelling(Wydawnictwo Politechniki Łódzkiej, 2023) Kulikowski, Sławomir; Romanowski, Andrzej; Sierszeń, ArturThis article aims to present a concept of an Artificial Intelligence application in the form of pre-trained Machine Learning modules to reduce the carbon footprint of a chemical recycling process. Chemical recycling of plastic is energy-consuming as it requires relatively high temperatures and calibration cycles based on a constantly changing structure of raw materials. Due to that fact, complex process parameters must be tuned to allow the production of the required fraction of gasoline. In general, the designed IoT system enables a massive collection of technology and environmental data and the processing of parameters to feed the Digital Twin of a petrochemical plant. The scientific part of the project consists of Digital Twin modelling, experiments, simulations, and training of machine learning modules to predict the optimal set of production line parameters based on the specific structure of raw materials to reduce the number of calibrations and lower energy consumption indirectly which will lead to carbon footprint reduction. There is an here is an estimate that that deployed solution will allow reduction of energy consumption on a monthly level of 10-15% which could generate direct savings on a cost of energy but also savings in a field of carbon emission and related credits. The project also includes the evaluation of predictions supported by machine learning modules, training techniques and comparison to expert settings to assess the quality of the application.Pozycja Generating and modelling network traffic(Wydawnictwo Politechniki Łódzkiej, 2015) Zarzycki, Maciej; Romanowski, Andrzej; Sierszeń, Artur; Sturgulewski, Łukasz[...] This chapter presents a flexible and scalable approach to automated network adapter testing. It defines a model that can be used to develop complete testing scenarios that reflect the usage patterns seen in todays networks. The work also implements a tool capable of understanding the model and conducting the test scenario. This application is written with performance and ease of extending in mind so it should evolve to meet the the ever changing requirements.[...]Pozycja Generating and modelling network traffic(Wydawnictwo Politechniki Łódzkiej, 2014) Zarzycki, Maciej; Romanowski, Andrzej; Sierszeń, Artur; Sturgulewski, Łukasz[...] This chapter presents a flexible and scalable approach to automated network adapter testing. It defines a model that can be used to develop complete testing scenarios that reflect the usage patterns seen in todays networks. The work also implements a tool capable of understanding the model and conducting the test scenario. This application is written with performance and ease of extending in mind so it should evolve to meet the the ever changing requirements.[...]Pozycja Accelerometer enhancement for mobile positioning application(Wydawnictwo Politechniki Łódzkiej, 2016) Ciążyński, Karol; Sierszeń, ArturIn recent years, a majority of mobile devices are equipped with a number of sensors such as accelerometers, gyroscopes, GPS receivers, microphones and cameras. What is more all such devices use embedded Bluetooth and wireless network cards for mobile communication. However GPS is one of the most significant development of the twentieth century, it has some limitations. GPS could not determine the accurate position inside the buildings, because of the loss of signal froni the satellites. Recently, due to the existence of ubiquities mobile devices the interest in location based services has significantly increased. The application of Bluetooth and wireless network was employed for mobile positioning systems. However, those systems significantly increase the accuracy for indoor localization, still the results are not satisfactory. Thus, the combination. of various signals measured by mobile devices could provide an enhancement for mobile positioning systems. This chapter presents the performance of accelerometer embedded in mobile phones. The experiments have been performed in order to present the possibility of distance calculation with the usage of accelerometer.Pozycja Improvement for mobile positioning systems applying a gyroscope(Wydawnictwo Politechniki Łódzkiej, 2016) Ciążyński, Karol; Sierszeń, ArturNowadays, a huge amount of mobile devices are equipped with a number of inertial sensors such as magnetometer, accelerometer and gyroscopes. Today's positioning systems such as GPS or GLONASS are not able to determine the precise position inside the buildings, because of the lack of signal from the satellites. In recent years, the interest in context awareness of mobile devices has increased significantly. Several positioning techniques for indoor navigation have been proposed with the usage of Bluetooth or WLAN. Due to the fact that those systems are very prone to any environmental changes the necessity for enhancement arises. This chapter presents the performance of gyroscope embedded in smartphones. The experiments have been performed in-order to present the possibility of distance calculation with the usage of gyroscope. The gathered results show that gyroscope could be a great enhancement for indoor positioning systems.Pozycja Real-time GPS tracking and product security system(Wydawnictwo Politechniki Łódzkiej, 2016) Sierszeń, Artur; Sturgulewski, Łukasz; Waktola, SelamThe goal of this study was to provide a system which uses Global Positioning System (GPS) to track mobile devices in real-time and secures properties using bar-code technology. Even though, there are similar solutions in the current market, they are most frequently operated by large third-party companies with an expensive service fees. Considering the high demand for using such systems and the exaggerated service fees; the proposed system of this study provides a free service using ordinary devices and technologies: The new system focused on specific user groups ( such as production, logistics and transport companies) for providing very rich functionalities with a proper security. Users of the new solution of this study are able to track their trucks ( or any mobile property) at real time, retrieving tracked history, planning routes and searching for any location throughout the world. Additionally it allows them to secure products while on transport using bar-code technology.Pozycja GNS3 environment in the aspect of testing software for management and monitoring of computer networks(Oficyna Wydawnicza Politechniki Wrocławskiej, 2009) Sierszeń, Artur; Sturgulewski, Łukasz; Janicka, JoannaThe GNS3 environment is a Graphical Network Simulator designed for emulating complex highquality networks that consist of Cisco networking equipment. Devices emulated in GNS3 employ real Cisco Internetwork Operating System (abbreviated as IOS). It allows to examine properties of the Cisco IOS and to verify configurations that need to be implemented later on the Cisco devices. The emulation process takes places in a virtual environment on a personal computer without the need of an actual physical Cisco hardware. The GNS3 is mainly used to visualize the design process of complex network topologies. Therefore, it uses the Scalable Vector Graphics to provide high-quality symbols of Cisco networking equipment. There is a great amount of software for monitoring and managing networks. This kind of applications should be tested before they are purchased. It is usually impossible in a typical network environment; it poses too many risks to the security and functionality ofa network. The Graphical Network Simulator 3 environment is a good solution for testing software and learning how software should be used.