Progress in Polish Artificial Intelligence Research 4

Stały URI zbioruhttp://hdl.handle.net/11652/4774



CONTENTS

1. 3D Reconstruction of Non-Visible Surfaces of Objects from a Single Depth View – Comparative Study Staszak R., Michałek P., Chudziński J., Kopicki M., Belter D. ........................................................................................ 19
2. Challenges of Crop Classification from Satellite Imagery with Eurocrops Dataset Aszkowski P., Kraft M. ........................................................................................ 25
3. Do We Always Need AI for Image Colorization? Śluzek A. ........................................................................................ 31
4. Fault Diagnosis in a Squirrel-Cage Induction Motor Using Thermal Imaging Piechocki M., Kraft M., Pajchrowski T. ........................................................................................ 37
5. Objective Hybrid Quality Assessment of Binary Images with the Use of Shallow Neural Networks Kopytek M., Okarma K. ........................................................................................ 43
6. One-point Hough Transform with Centred Accumulator Chmielewski L. J., Bator M., Gajowniczek K. ........................................................................................ 49
7. Pedestrian Detection with High-resolution Event Camera Wzorek P., Kryjak T. ........................................................................................ 55
8. Recognition of Shoplifting Activities in CCTV Footage Using the Combined CNN-RNN Model Kirichenko L., Pichugina O., Sydorenko B., Yakovlev S. ........................................................................................ 61
9. Spotting Advertisements from Above: Billboard Detection and Segmentation in UAV Imagery Ptak B., Dominiak J., Kraft M. ........................................................................................ 67
10. Transformers Neural Networks Applications in Different Computer Vision Tasks Brodzicki A., Piekarski M., Kostuch A., Noworolnik F., Aleksandrowicz M., Wójcicka A., Jaworek-Korjakowska J. ........................................................................................ 73
11. Weak Supervision in Enemy Detection Based on Computer Game Output Video Stream Rajtar J., Szajerman D. ........................................................................................ 81
12. A Comparison of Shallow Explainable Artificial Intelligence Methods against Grammatical Evolution Approach Sepioło D., Ligęza A. ........................................................................................ 89
13. Clustering Dilemmas – A Study of the Request of Homogenicity within Clusters Versus Diversity Between Clusters Kłopotek M. A. ........................................................................................ 95
14. Contextual ES-adRNN with Attention Mechanisms for Forecasting Smyl S., Dudek G., Pełka P. ........................................................................................ 101
15. Graph-Supported Preparation of GIS Machine Learning Datasets Ernst S. ........................................................................................ 107
16. Hashtag Similarity Based on Laplacian Eigenvalue Spectrum Starosta B., Kłopotek M. A., Wierzchoń S. T. ........................................................................................ 113
17. Improvement of Attention Mechanism Explainability in Prediction of Chemical Molecules’ Properties Durys B., Tomczyk A. ........................................................................................ 119
18. On Usefulness of Dominance Relation for Selecting Counterfactuals from the Ensemble of Explainers Stępka I., Lango M., Stefanowski J. ........................................................................................ 125
19. Towards Detection of Unknown Polymorphic Patterns Using Prior Knowledge Kucharski P., Ślot K. ........................................................................................ 131
20. AI-driven Ecodriving and ETA Solutions for Truck Transport Lipiński P., Morawski M., Napieralski P., Nowok P., Zawiślak B., Hojdys L., Lazar M., Lazarek P., Zając N., Pizoń S., Jakubiec R., Sienkiewicz J., Gołąbek S., Kabocik M., Fedrizzi S., Kuliga M., Frączkiewicz M., Malarz M., Puchalski J., Danysz E., Grajcarek M. ........................................................................................ 139
21. Analysis of Surface EMG Signals to Control of a Bionic Hand Prototype Pieprzycki A., Król D., Wawryka P., Łachut K., Hamera M., Srebro B. ........................................................................................ 145
22. Brief Overview of Selected Research Directions and Applications of Process Mining in KRaKEn Research Group Kluza K., Zaremba M., Sepioło D., Wiśniewski P., Adrian W. T., Gaudio M. T., Jemioło P., Adrian M., Jobczyk K., Ślażyński M., Stachuta-Terlecka B., Ligęza A. ........................................................................................ 151
23. Carbon Footprint Reduction of a Petrochemical Process Supported by ML and Digital Twin modelling Kulikowski S., Romanowski A., Sierszeń A. ........................................................................................ 157
24. Digital Twin for Training Set Generation for Unexploded Ordnance Classification Ściegienka P., Blachnik M. ........................................................................................ 163
25. Energy Dissipation Anomalies in Buildings Morawski M., Tomczyk A., Idaczyk M. ........................................................................................ 165
26. Identification of Damaged AIS Data Based on Clustering and Multi-Label Classification Szarmach M., Czarnowski I. ........................................................................................ 167
27. Integrating Anomaly Detection for Enhanced Data Protection in Cloud-Based Applications Czerkas K., Drozd M., Duraj A., Lichy K., Lipiński P., Morawski M., Napieralski P., Puchała D., Kwapisz M., Warcholiński A., Karbowańczyk M., Wosiak P. ........................................................................................ 173
28. Learning Non-Differentiable Graphs of Utility AI Świechowski M. ........................................................................................ 181
29. Lessons Learned from a Smart City Project with Citizen Engagement Ernst S., Zaworski K., Sokołowski P., Salwa G. ........................................................................................ 187
30. Machine Learning for Water Leak Detection and Localization in the WaterPrime Project Głomb P., Romaszewski M., Cholewa M., Koral W., Madej A., Skrabski M., Kołodziej K. ........................................................................................ 193
31. Performance Analysis of Machine Learning Platforms Using Cloud Native Technology on Edge Devices Cłapa K., Grudzień K., Sierszeń A. ........................................................................................ 195
32. RNN-based Phase Unwrapping for Enabling Vital Parameter Monitoring with FMCW Radars Łuczak P., Hausman S., Ślot K. ........................................................................................ 201
33. Statistical Method for Photovoltaic Power Forecasting Basing on Signal Components Decomposition Parczyk P., Burduk R. ........................................................................................ 207
34. Text-to-music Models and Their Evaluation Methods Modrzejewski M., Rokita P. ........................................................................................ 213
35. Towards Ontology-Driven Verification of Car Claims Settlement Pancerz K., Wolski J. ........................................................................................ 219
36. Using Security Games against Wild Dumping Sites Adrian M., Markiewicz J. ........................................................................................ 225
37. VideoAI – System for Synchronization of Electronic Program Guides Wasilewski J., Sochaj B., Gaca A. ........................................................................................ 231
38. Identification of Melanocytic Skin Lesions Using Deep Learning Methods Paja W., Szkoła J., Pancerz K., Sarzyński J., Żychowska M. ........................................................................................ 239
39. Loss Function Influence on Uncertainty Estimation for White Matter Lesions 3D Segmentation in a Shifted Domain Setting Kaczmarska M., Majek K. ........................................................................................ 245
40. Multi-task Learning for Classification, Segmentation, Reconstruction, and Detection on Chest CT Scans Hryniewska-Guzik W., Kędzierska M., Biecek P. ........................................................................................ 251
41. Supporting Surgical Training with the Help of Computer Vision and Machine Learning Methods Forczmański P., Ryder Y. C., Mott N. M., Gross C. L., Yu J. B., Rooney D. M., Jeffcoach D. R., Bidwell S., Anidi C., Rosenthal L., Kim G. J. ........................................................................................ 259
42. A Convolutional and Recurrent Neural Network-based Approach for Speech Emotion Recognition Duch P., Wiatrowska I., Kapusta P. ........................................................................................ 267
43. Aaron Earned an Iron Urn: Speech-to-IPA Models Improve Diagnostic of Pronunciation Olejnik F., Stachowiak R., Krysińska I., Morzy M. ........................................................................................ 273
44. Anonymizer for Polish Language Walkowiak T., Gniewkowski M., Pogoda M., Ropiak N. ........................................................................................ 281
45. A Hybrid Fuzzy-Rough Approach to Handling Missing Data in a Fall Detection System Mroczek T., Gil D., Pękala B. ........................................................................................ 285
46. Customer Churn Analytics Using Monotonic Rules Szeląg M., Słowiński R. ........................................................................................ 287
47. Application of Pawlak’s Conflict Model to Generate Coalitions of Local Tables with Similar Values on Conditional Attributes Przybyła-Kasperek M., Kusztal K. ........................................................................................ 293
48. A Novel DNN-based Image Watermarking Algorithm Kovačević S., Pavlović K., Djurović I. ........................................................................................ 301
49. Autoregressive Label-Conditioned Autoencoder for Controllable Image-To-Video Generation Kubicki K., Ślot K. ........................................................................................ 307
50. Building Energy Use Intensity Prediction with Artificial Neural Networks Stokfiszewski K., Sztoch P., Sztoch R., Wosiak A. ........................................................................................ 313
51. Grounded HyperSymbolic Representations Learned through Gradient-Based Optimization Łuczak P., Ślot K., Kucharski J. ........................................................................................ 319
52. Increasing Skin Lesions Classification Rates using Convolutional Neural Networks with Invariant Dataset Augmentation and the Three-Point Checklist of Dermoscopy Milczarski P., Borowski N., Beczkowski M. ........................................................................................ 325
53. A Novel Learning Multi-Swarm Particle Swarm Optimization Borowska B. ........................................................................................ 337
54. Are Quantified Boolean Formulas Hard for Reason-Able Embeddings? Potoniec J. ........................................................................................ 343
55. Dynamic Mutation Control in Continuous Genetic Algorithms Wieczorek Ł., Ignaciuk P. ........................................................................................ 349
56. Local Energy Redistribution Units for Space Dimensionality Reduction in Data Classification Puchała D. ........................................................................................ 355
57. MPTCP Congestion Control Algorithms for Streaming Applications – Performance Evaluation in Public Networks Łuczak Ł. P., Ignaciuk P., Morawski M. ........................................................................................ 361
58. Optimized Mutation Operator in Evolutionary Approach to Stackelberg Security Games Żychowski A., Mańdziuk J. ........................................................................................ 367
59. Simulation of the Quantum Heat Engine in the Quantum Register Ostrowski M. ........................................................................................ 373
60. Socio-cognitive Flock-based Optimization Urbańczyk A., Czech K., Byrski A. ........................................................................................ 381
61. A New Approach to Learning of 3D Characteristic Points for Vehicle Pose Estimation Nowak T., Skrzypczyński P. ........................................................................................ 389
62. A Reinforcement Learning Framework for Motion Planning of Autonomous Vehicles Orłowski M., Skruch P. ........................................................................................ 395
63. BDOT10k-seg: A Dataset for Semantic Segmentation Kos A., Majek K. ........................................................................................ 401
64. Beacon-based Swarm Search and Rescue Ratnayake S., Figat M. ........................................................................................ 407
65. Intelligent Anticipatory Mobile Robot Networks for Autonomous Fruit Harvesting Skulimowski A. M. J., Karimi M. ........................................................................................ 411
66. Evolution of Robotic System Specification Methodology Figat M., Zieliński C. ........................................................................................ 421
67. Improving RGB-D Visual Odometry with Depth Learned from a Better Sensor’s Output Kostusiak A. ........................................................................................ 429
68. Mixing Synthetic and Real-world Datasets Strategy for Improved Generalization of the CNN Młodzikowski K., Belter D. ........................................................................................ 435
69. NeRF-based RGB-D Images Generation in Robotics – Experimental Study Kulecki B., Belter D. ........................................................................................ 443
70. Predictive User Interface for Emerging Experiences Kapusta P. Duch P. ........................................................................................ 449
71. Semantic Segmentation for Autonomous Drone Delivery SUADD’23 Challenge Mrukwa A., Majek K. ........................................................................................ 451
72. Semi-formal Methods for Security Informed Safety Assessment of Robotic Systems Kharchenko V., Abakumov A., Yakovlev S. ........................................................................................ 457
73. Using Publicly Available Building Data to Improve 3D Map Krygiel K., Majek K., Będkowski J. ........................................................................................ 459
74. AloneKnight – Enabling Affective Interaction within Mobile Video Games Jemioło P., Świder K., Storman D., Adrian W. T. ........................................................................................ 467
75. AMUseBot: Towards Making the Most out of a Task-oriented Dialogue System Christop I., Dudzic K., Krzymiński M. ........................................................................................ 473
76. Hierarchical Distributed Cluster-based Method for Robotic Swarms Mastej B., Figat M. ........................................................................................ 479
77. Lung Xray Images Analysis for COVID-19 Diagnosis Kloska A., Tarczewska M., Giełczyk A., Marciniak B. ........................................................................................ 485
78. On Parameters of Migration in PEA Computing Biełaszek S., Byrski A. ........................................................................................ 491
79. On the Importance of the RGB-D Sensor Model in the CNN-based Robotic Perception Zieliński M., Belter D. ........................................................................................ 495
80. On the Selection of a Machine Learning model in TinyML Devices – Preliminary Study Puślecki T., Walkowiak K. ........................................................................................ 501
81. Valuing Passes in Actions Leading to the Third Zone on the Pitch with Machine Learning Methods Tylka M., Wałęsa S., Girejko K., Kaczmarek J., Grzelak B., Piłka T. ........................................................................................ 507

Przeglądaj

Wyniki wyszukiwania

Teraz wyświetlane 1 - 4 z 4
  • Pozycja
    On the Importance of the RGB-D Sensor Model in the CNN-based Robotic Perception
    (Wydawnictwo Politechniki Łódzkiej, 2023) Zieliński, Mikołaj; Belter, Dominik
    Mobile and manipulation robots operating indoors use RGB-D cameras as the environment perception sensors. To process data from RGB and depth cameras neural networks are applied. These neural-based systems are trained using synthetic datasets due to the difficulties of obtaining ground truth data on real robots. As a result, the neural model used on the real robot does not produce satisfactory performance due to the differences between the images used during training and the inference. In this paper, we show the importance of depth sensor modeling while training the neural network on a synthetic dataset. We show that the obtained neural model can be used on the real robot and process the data from the real RGB-D camera.
  • Pozycja
    NeRF-based RGB-D Images Generation in Robotics – Experimental Study
    (Wydawnictwo Politechniki Łódzkiej, 2023) Kulecki, Bartłomiej; Belter, Dominik
    Multiple learning-based algorithms in robotics require collecting RGB-D images of the scene from various viewpoints. These procedures are time-consuming, so many methods are trained using synthetic images. Recently, a Neural Radiance Fields (NeRF) model of the scene was proposed. Moreover, recent methods show that this model can be trained in minutes. This opens the possible applications in robotics for training the systems to reconstruct scenes, grasp objects or estimate their 3D poses using RGB-D images generated from a small number of input images. In this paper, we verify the quality of RGB-D images generated by the Instant Neural Graphics Primitives implementation of NeRF. We compare the obtained results from the Instant NeRF with the ground-truth RGB-D images obtained from the Kinect Azure and images generated from the point cloud model of the scene. The results show that the difference between generated RGB-D images and ground truth images is small, especially near the object.
  • Pozycja
    Mixing Synthetic and Real-world Datasets Strategy for Improved Generalization of the CNN
    (Wydawnictwo Politechniki Łódzkiej, 2023) Młodzikowski, Kamil; Belter, Dominik
    In this paper, we deal with the problem of supervised training neural networks with an insufficient number of real-world training examples. We propose a method that at the beginning trains the neural network using a relatively simple synthetic dataset. In the following epochs, we add more challenging and real-life images to the training dataset. We compare the proposed strategy with other methods of using artificial and real-world datasets for training the neural network. The obtained results show that the proposed strategy allows for obtaining the neural network with higher generalization capabilities than competitive methods.
  • Pozycja
    3D Reconstruction of Non-Visible Surfaces of Objects from a Single Depth View – Comparative Study
    (Wydawnictwo Politechniki Łódzkiej, 2023) Staszak, Rafał; Michałek, Piotr; Chudziński, Jakub; Kopicki, Marek; Belter, Dominik
    Scene and object reconstruction is an important problem in robotics, in particular in planning collision-free trajectories or in object manipulation. This paper compares two strategies for the reconstruction of nonvisible parts of the object surface from a single RGB-D camera view. The first method, named DeepSDF predicts the Signed Distance Transform to the object surface for a given point in 3D space. The second method, named MirrorNet reconstructs the occluded objects’ parts by generating images from the other side of the observed object. Experiments performed with objects from the ShapeNet dataset, show that the view-dependent MirrorNet is faster and has smaller reconstruction errors in most categories.