{"title":"Improvement of Electrical Tomographic Imaging of Moisture by Mixing Machine Learning Models","authors":"Grzegorz Kłsowski, T. Rymarczyk, K. Niderla","doi":"10.1109/IIPhDW54739.2023.10124422","DOIUrl":"https://doi.org/10.1109/IIPhDW54739.2023.10124422","url":null,"abstract":"The article proposes the optimization of the selection of machine learning algorithms used in tomographic applications. This study used electrical impedance tomography (EIT) to illustrate the distribution of moisture inside the walls of the buildings under study. The first task is to discover the ideal settings of hyperparameters used in machine learning algorithms to increase the efficiency of obtaining reliable tomographic images. The second aim of the research is to choose the optimal method of converting measurements into images. The process of turning input observations into output photos is handled by machine learning models. This is called an ill-posed problem or an inverted problem that is difficult to solve because there are not enough arguments. Ensuring the selection of the correct model hyperparameters is an essential task of machine learning. The selection of these hyperparameters has a direct impact on the quality of the reconstruction. Using the k-nearest neighbors algorithm as an example, this article shows how hyperparameter optimization can be applied to regression and classification models. This technology was created to track and visualize the distribution of moisture inside the walls of buildings and other structures. The facts revealed during the investigation showed that the proposed techniques are effective.","PeriodicalId":396821,"journal":{"name":"2023 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128195281","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":"Optimization-Based Actuator Allocation for Underwater Vehicles with Variable Buoyancy Systems","authors":"C. Rethfeldt, Sven Lack, T. Jeinsch","doi":"10.1109/IIPhDW54739.2023.10124421","DOIUrl":"https://doi.org/10.1109/IIPhDW54739.2023.10124421","url":null,"abstract":"Underwater vehicles are often equipped with variable buoyancy systems (VBS) for buoyancy variation. This also applies to the novel unmanned underwater vehicle (UUV) class MUM (Large Modifiable Underwater Mothership) which features a modular structure and variable shape, thus requiring a generalized motion control approach that adapts to the specific vehicle configuration. Regarding MUM's maneuvering devices, the control system generalization is achieved by means of actuator allocation which distributes the motion controller output to the available actuators. Consequently, this paper proposes an actuator allocation approach that treats conventional propulsion units and VBS jointly. Inspired by optimization-based solutions known from dynamically positioning ships, the selected allocation method employs a problem formulation based on model predictive control (MPC) in order to optimize usage of the actuators subject to their characteristics and physical limits. The application of the allocation algorithm to an actuator configuration with VBS is presented and results from early trials in simulation are shown.","PeriodicalId":396821,"journal":{"name":"2023 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127200170","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":"Welcome to IIPhDW'23","authors":"","doi":"10.1109/iiphdw54739.2023.10124401","DOIUrl":"https://doi.org/10.1109/iiphdw54739.2023.10124401","url":null,"abstract":"","PeriodicalId":396821,"journal":{"name":"2023 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"100 27","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131878589","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}
J. Melnikova, Aleksandra Batuchina, J. Zaščerinska, A. Ahrens
{"title":"Learning Experience Platforms in German and Lithuanian K12 Schools: Case Study Analysis","authors":"J. Melnikova, Aleksandra Batuchina, J. Zaščerinska, A. Ahrens","doi":"10.1109/IIPhDW54739.2023.10124407","DOIUrl":"https://doi.org/10.1109/IIPhDW54739.2023.10124407","url":null,"abstract":"The article is focused on the micro level of education (i.e. the teaching / learning process) and the digital learning platforms used in it. The platforms that provide the learning content and are equipped with analytical tools and are able to provide guidance to the participants in the educational process by means of artificial intelligence are referred to as Learning Experience Platforms within the framework of the research. In the educational practice of two countries learning experience platforms Bettermarks and Eduten Playground have been chosen for case study analysis. Data collection methods: analysis of open sources and interviews with users (teachers). These platforms allow learners to personalize what they are learning, how they are learning and when / where they choose to learn. Through such platforms, participants in the learning process can identify specific skills or knowledge gaps by accessing an analysis of their teaching-learning activities and use suggestions for action to improve their achievement. The article presents the empiric information on the benefits of these platforms in the teaching/learning practice as well challenges for their effective use. Research findings have pedagogical value for designing of engineering education.","PeriodicalId":396821,"journal":{"name":"2023 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132806460","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 Practical Approach to Quantum Resilient Cloud Usage Obtaining Data Privacy","authors":"Linus Töbke, Olaf Grote, A. Ahrens","doi":"10.1109/IIPhDW54739.2023.10124397","DOIUrl":"https://doi.org/10.1109/IIPhDW54739.2023.10124397","url":null,"abstract":"Cloud computing has emerged as an attractive and fastest-growing technology. The Cloud model encompasses a highly scalable infrastructure environment and guarantees the daily business processes for data-driven business cases protected by quantum vulnerable cryptography and no preserving of data privacy. This paper proposes a practical quantum-safe approach to guarantee data privacy even if a quantum computer can break classical public-key exchange algorithms. We present a quantum-safe cloud use based on post-quantum cryptographic and privacy-focused applications via homomorphic encryption and secure multiparty computation.","PeriodicalId":396821,"journal":{"name":"2023 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128822723","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":"Functional Architecture for Solution Independent Realizations of Digital Continuity in System Development","authors":"M. Manoury","doi":"10.1109/IIPhDW54739.2023.10124410","DOIUrl":"https://doi.org/10.1109/IIPhDW54739.2023.10124410","url":null,"abstract":"Product and service creation requires the interdisciplinary collaboration of different stakeholders. In virtual product and service creation these stakeholders generate models and data to describe the product or service over their entire life cycle. For a reliant product creation and optimization, these models and data need to be consistent through all disciplines and life cycle phases. In this publication, a solution-independent functional architecture to foster the digital continuity across the involved disciplines and life cycle phases is described. To achieve it, existing approaches in literature are evaluated and requirements and desired capabilities extracted. An reduced form of the Architecture Analysis & Design Integrated Approach (ARCADIA) is used to describe a functional architecture. Consecutively, existing solutions are mapped to the architecture and evaluated for compliance.","PeriodicalId":396821,"journal":{"name":"2023 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114487944","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}
Jasmeet Singh, A. Ahrens, S. Lochmann, C. B. Peces
{"title":"SVD-Assisted Joint Pre- and Post-Equalization in Optical MIMO System","authors":"Jasmeet Singh, A. Ahrens, S. Lochmann, C. B. Peces","doi":"10.1109/IIPhDW54739.2023.10124406","DOIUrl":"https://doi.org/10.1109/IIPhDW54739.2023.10124406","url":null,"abstract":"In recent years, the surge in capacity demands and cost-effectiveness have been beyond the ability of single-mode fiber (SMF) operating optical networks. In this work, the capacity crunch is dealt with by utilizing an optical multiple-input and multiple-output (MIMO) technology integrated with higher-order modulations (HOMs) as they lead to higher spectral efficiency. The low cost is achieved using intensity modulation / direct detection (IM/DD) system with a multi-mode fiber (MMF) transmission link. Contrary to an SMF channel, a highly dispersion-impaired MMF is equalized using a jointly designed pre- and post-equalization (PPE) filter, which consists of just two-taps pre-equalizer. A numerical optimization is defined to optimize the pre-and post-equalizer coefficients within the provided power and cost budgets. This work is the first investigation of a singular value decomposition (SVD) based joint-PPE scheme with a 1km long MMF link. The obtained results reveal that the signal-to-noise-ratio (SNR) gains of 5.48 dB and 10.57 dB at 10–4 bit-error rate (BER) for PAM-2 and PAM-4 compared to post-equalization only (PE-only) respectively. From the results, the SVD-assisted joint-PPE yields benefit in the presence of an MMF channel.","PeriodicalId":396821,"journal":{"name":"2023 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126505309","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}
Bartłomiej Baran, Bartosz Przysucha, T. Rymarczyk, D. Wójcik
{"title":"Effect of Measurement Noise on Reconstruction using Machine Learning with Electrical Tomography in the Case of the Abdominal Cavity","authors":"Bartłomiej Baran, Bartosz Przysucha, T. Rymarczyk, D. Wójcik","doi":"10.1109/IIPhDW54739.2023.10124426","DOIUrl":"https://doi.org/10.1109/IIPhDW54739.2023.10124426","url":null,"abstract":"In this paper, we compare the reconstruction efficiency obtained by the least angle regression (LARS) and Elastic Net algorithms using electrical impedance tomography (EIT). Furthermore, we investigate the impact of measurement noise on the quality of reconstruction obtained by the more efficient algorithm. We reveal the relationship between the quality of reconstruction and the magnitude of information loss in a data frame. This study was conducted on a dataset representing EIT measurements for a cross-section of the abdomen at the bladder level. The simulated dataset contains 10,000 different measurement examples for a different number of inclusions.","PeriodicalId":396821,"journal":{"name":"2023 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"388 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117314496","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":"Image Reconstruction Using Radio Tomography and Artificial Intelligence in Tracking and Navigation Systems for Indoor Applications","authors":"M. Styła, Bartłomiej Kiczek, P. Adamkiewicz","doi":"10.1109/IIPhDW54739.2023.10124404","DOIUrl":"https://doi.org/10.1109/IIPhDW54739.2023.10124404","url":null,"abstract":"This thesis focuses on the technology for acquiring and processing localization data within the radio tomographic imaging technique supported by neural networks. The scope of work included both proprietary hardware solutions and computational algorithms. The result was a fully functional and self-contained system detecting living agents in confined spaces. Doing so does not require any signal source device located at the user.","PeriodicalId":396821,"journal":{"name":"2023 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127989518","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}
Bartosz Przysucha, D. Wójcik, T. Rymarczyk, Bartłomiej Baran, K. Król
{"title":"Sensitivity Matrix Reconstruction in Ultrasound Transmission Tomography Using Singular Value Decomposition","authors":"Bartosz Przysucha, D. Wójcik, T. Rymarczyk, Bartłomiej Baran, K. Król","doi":"10.1109/IIPhDW54739.2023.10124408","DOIUrl":"https://doi.org/10.1109/IIPhDW54739.2023.10124408","url":null,"abstract":"The main purpose of this paper is to present a method for determining the approximation of the sensitivity matrix in a computed tomography problem. A method based on multiply regression and singular value decomposition was proposed. The study was carried out on 5000 simulated cases for ultrasound tomography. The authors first checked the reconstruction quality obtained by the proposed method. Then these results were compared with reconstructions obtained using the elastic net method. The reconstruction times obtained by the different methods were also examined. The analyses conducted in the paper showed that the proposed method is much faster than the Elastic net method, while the reconstruction quality is comparable.","PeriodicalId":396821,"journal":{"name":"2023 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133463171","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}