Wydział Fizyki Technicznej, Informatyki i Matematyki Stosowanej / Faculty of Technical Physics, Information Technology and Applied Mathematics / W7
Stały URI zbioruhttp://hdl.handle.net/11652/7
Przeglądaj
8 wyniki
Wyniki wyszukiwania
Pozycja Increasing Skin Lesions Classification Rates using Convolutional Neural Networks with Invariant Dataset Augmentation and the Three-Point Checklist of Dermoscopy(Wydawnictwo Politechniki Łódzkiej, 2023) Milczarski, Piotr; Borowski, Norbert; Beczkowski, MichałIn the paper, we show how to tackle the problem of lack of the rotation invariance in CNN networks using the authors’ Invariant Dataset Augmentation (IDA) method. The IDA method allows to increase the classification rates taking into account as an example the classification of the skin lesions using a small image set. In order to solve the problem of the lack of rotation invariance, IDA method was used and the dataset was increased in an eightfold and invariant way. In the research, we applied the IDA methods and compared the results of VGG19, XN and Inception-ResNetv2 CNN networks in three skin lesions features classification defined by wellknown dermoscopic criterions e.g. the Three-Point Checklist of Dermoscopy or the Seven-Point Checklist. Due to Invariant Dataset Augmentation, the classification rate parameters like true positive rate by almost 20%, false positive rate as well as the F1 score and Matthews correlation coefficient have been significantly increased opposite to type II error that has significantly decreased. In the paper, the confusion matrix parameters result in: 98-100% accuracy, 98-100% true positive rate, 0.0-2.3% false positive rate, tests F1=0.95 and MCC=0.95. That general approach can provide higher results while using CNN networks in other applications.Pozycja Integrating Anomaly Detection for Enhanced Data Protection in Cloud-Based Applications(Wydawnictwo Politechniki Łódzkiej, 2023) Czerkas, Konrad; Drozd, Michał; Duraj, Agnieszka; Lichy, Krzysztof; Lipiński, Piotr; Morawski, Michał; Napieralski, Piotr; Puchała, Dariusz; Kwapisz, Marcin; Warcholiński, Adrian; Karbowańczyk, Michał; Wosiak, PiotrIn this research, anomaly detection techniques and artificial neural networks were employed to address the issue of attacks on cluster computing systems. The study investigated the detection of Distributed Denial of Service (DDoS) and Partition attacks by monitoring metrics such as network latency, data transfer rate, and number of connections. Additionally, outlier detection algorithms, namely Local Outlier Factor (LOF) and COF, as well as ARIMA and SHESD models were tested for anomaly detection. Two types of neural network architectures, multi-layer perceptron (MLP) and recursive LSTM networks, were used to detect attacks by classifying events as “attack” or “no attack”. The study underscores the importance of implementing proactive security measures to protect cluster computing systems from cyber threats.Pozycja Progress in Polish Artificial Intelligence Research 4(Wydawnictwo Politechniki Łódzkiej, 2023) Wojciechowski, Adam (Ed.); Lipiński, Piotr (Ed.)Pozycja Prediction of Natural Image Saliency for Synthetic Images(Wydawnictwo Politechniki Łódzkiej, 2021) Rudak, Ewa; Rynkiewicz, Filip; Daszuta, Marcin; Sturgulewski, Łukasz; Lazarek, JagodaNumerous 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.Pozycja A Memory Model for Emotional Decision-Making Agent in a Game(Wydawnictwo Politechniki Łódzkiej, 2018) Rogalski, Jakub; Szajerman, DominikVirtual characters are an important part of many modern computer games. This paper describes a graph-based memory system designed for artificial agents that also simulate simple emotions. The system was tested using virtual simulation environment and it showed many new and desirable AI behaviours. These behaviours include simple preferences, reactions based on bot’s opinion of a stimuli or improvement of bot’s ability to find objects to interact with.Pozycja The Use of Heuristic Algorithms: A Case Study of a Card Game(Wydawnictwo Politechniki Łódzkiej, 2018) Lichy, Krzysztof; Mazur, Marcin; Stolarek, Jan; Lipiński, PiotrIn this paper we introduce the results of an experiment consisting in the creation of artificial intelligence using the heuristic algorithm Monte Carlo Tree Search and evaluation of its effectiveness in the card game Thousand.Pozycja Affective Pathfinding in Video Games(Wydawnictwo Politechniki Łódzkiej, 2018) Daszuta, Marcin; Wróbel, Filip; Rynkiewicz, Filip; Szajerman, Dominik; Napieralski, PiotrTo allow player submerge in created environment of a video game, agents called Non-Player Characters (NPCs) should act believably. One of the most vital aspect, in case of NPCs is pathfinding. There are a few methods that allow change path finding algorithms to become more human-like. Yet, those are not considering many vital aspects of human decisions regarding path choosing. The main purpose of this paper is to present known approaches and show example of a new approach that wider considers psychological aspects of decision making in case of choosing a path.Pozycja Geometric Transformations Embedded into Convolutional Neural Networks(Wydawnictwo Politechniki Łódzkiej, 2016) Tarasiuk, Paweł; Pryczek, MichałThis paper presents a novel extension to convolutional neural networks. While CNNs are known for invariance to object translation, changes to the other parameters could make the image recognition tasks diffcult – that includes rotations and scaling. Some improvement in this area could be achieved with embedded geometric transformations used inside the CNNs. In order to provide a practical solution, which allows fast propagation and learning of the modified networks, “fast geometric transformations” are introduced.