Wydział Elektrotechniki, Elektroniki, Informatyki i Automatyki / Faculty of Electrical, Electronic, Computer and Control Engineering / W2

Stały URI zbioruhttp://hdl.handle.net/11652/2

Przeglądaj

Filtry

2021 - 20235

Ustawienia

Data rozpoczęcia: 2009Tematsearch.filters.applied.operator.equals: search.filters.subject.artificial intelligence

Wyniki wyszukiwania

Teraz wyświetlane 1 - 5 z 5
  • Pozycja
    Predictive User Interface for Emerging Experiences
    (Wydawnictwo Politechniki Łódzkiej, 2023) Kapusta, Paweł; Duch, Piotr
    This research paper focuses on the use of predictive techniques to improve interaction with user interfaces in emerging experiences such as Virtual Reality, Augmented Reality, Metaverse, and touchless kiosks and dashboards. We propose the concept of intelligent snapping, which uses gaze tracking, head-pose tracking, hand tracking, as well as gesture recognition and hand posture recognition to catch the intent of the person rather than the actual input.
  • Pozycja
    Grounded HyperSymbolic Representations Learned through Gradient-Based Optimization
    (Wydawnictwo Politechniki Łódzkiej, 2023) Łuczak, Piotr; Ślot, Krzysztof; Kucharski, Jacek
    Hyperdimensional computing is a novel paradigm, capable of processing complex data structures with simple operations. Its main limitations lie in the conversion of real world data onto hyperdimensional space, which due to lack of a universal translation scheme, oftentimes requires application-specific methods. This work presents a novel method for unsupervised hyperdimensional conversion of arbitrary image data. Additionally, this method is augmented by the ability of creating HyperSymbols, or class prototypes, provided that such class labels are available. The proposed method achieves promising performance on MNIST dataset, both in translating individual samples as well as producing HyperSymbols for downstream classification task.
  • Pozycja
    A Convolutional and Recurrent Neural Network-based Approach for Speech Emotion Recognition
    (Wydawnictwo Politechniki Łódzkiej, 2023) Duch, Piotr; Wiatrowska, Izabela; Kapusta, Paweł
    Speech emotion recognition (SER) is a crucial aspect of humancomputer interaction. In this article, we propose a deep learning approach, using CNN and RNN architectures, for SER using both convolutional and recurrent neural networks. We evaluated the approach on four audio datasets, including CREMA-D, RAVDESS, TESS, and EMOVO. Our experiments tested various feature sets and extraction settings to determine optimal features for SER. Our results demonstrate that the proposed approach achieves high accuracy rates and outperforms state-of-the-art algorithms.
  • 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
    Prediction of Natural Image Saliency for Synthetic Images
    (Wydawnictwo Politechniki Łódzkiej, 2021) Rudak, Ewa; Rynkiewicz, Filip; Daszuta, Marcin; Sturgulewski, Łukasz; Lazarek, Jagoda
    Numerous saliency models are being developed with the use ofneural networks and are capable of combining various features and predicting the saliency values with great results. In fact, it might be difficult to replace the possibilities of artificial intelligence applied to algorithms responsible for predicting saliency. However, the low-level features are still important and should not be removed completely from new saliency models. This work shows that carefully chosen and integrated features, including a deep learning based one, can be used for saliency prediction. The integration is obtained by using Multiple Kernel Learning. This solution is quite effective, as compared to a few other models tested on the same dataset.