Rozdziały

Stały URI dla kolekcjihttp://hdl.handle.net/11652/4775

Przeglądaj

Filtry

20235

Ustawienia

Tematsearch.filters.applied.operator.equals: search.filters.subject.machine learning

collection.search.results.head

Teraz wyświetlane 1 - 5 z 5
  • Pozycja
    Supporting Surgical Training with the Help of Computer Vision and Machine Learning Methods
    (Wydawnictwo Politechniki Łódzkiej, 2023) Forczmański, Paweł; Ryder, Yoonhee C; Mott, Nicole M; Gross, Christopher L.; Yu, Joon B.; Rooney, Deborah M.; Jeffcoach, David R.; Bidwell, Serena; Anidi, Chioma; Rosenthal, Lindsay; Kim, Grace J.
    The paper presents a novel concept of laparoscopic skills evaluation based on the automated analysis of videos recorded during simulationbased training exercises via an artificial intelligence algorithm. It has been tested on data collected during the training of actual surgeons. Its performance is promising, providing an opportunity to build an automatic system used mainly in developing countries.
  • Pozycja
    Performance Analysis of Machine Learning Platforms Using Cloud Native Technology on Edge Devices
    (Wydawnictwo Politechniki Łódzkiej, 2023) Cłapa, Konrad; Grudzień, Krzysztof; Sierszeń, Artur
    This 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
    Learning Non-Differentiable Graphs of Utility AI
    (Wydawnictwo Politechniki Łódzkiej, 2023) Świechowski, Maciej
    Utility AI is an approach to modelling AI players in computer games. Its structure is a graph that computes the utility values of possible actions and chooses the one with the highest value. Currently, such graphs are created by experts manually. This paper presents the first attempts to create them automatically – through learning from data. The problem is similar to training neural networks except that the utility graphs are non-differentiable and contain various types of nodes (more complex than neurons). We present the most promising methods, preliminary experiments and results.
  • Pozycja
    Digital Twin for Training Set Generation for Unexploded Ordnance Classification
    (Wydawnictwo Politechniki Łódzkiej, 2023) Ściegienka, Piotr; Blachnik, Marcin
    The use of machine learning methods for unexploded ordnance (UXO) detection and classification is very limited. This limitation derives from the lack of representative and enough large training data. To overcome this issue we propose a construction of a digital twin where UXO and non-UXO objects are represented using mathematical models in a simulated Earth magnetic field. The use of digital twins allows for simulating and collecting a large training set which can be used for training machine learning models. In the conducted research we discuss obtained results and point out several of the detected problems.
  • Pozycja
    Carbon Footprint Reduction of a Petrochemical Process Supported by ML and Digital Twin modelling
    (Wydawnictwo Politechniki Łódzkiej, 2023) Kulikowski, Sławomir; Romanowski, Andrzej; Sierszeń, Artur
    This 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.