Numer czasopisma
Computer Science
Ładuję...
ISSN: 1508-2806
e-ISSN:
Data wydania
2023
Rocznik
Vol. 24
Numer
No. 4
Prawa dostępu
Dostęp: otwarty dostęp
Uwagi:
Prawa: CC BY 4.0 
Uznanie autorstwa 4.0 Międzynarodowe (CC BY 4.0)
Strony
Opis
Rocznik czasopisma (rel.)
Rocznik czasopisma
Computer Science
Vol. 24 (2023)
Artykuły numeru (rel.)
Artykuł
Otwarty dostęp
Hybrid implementation of the fastica algorithm for high-density eeg using the capabilities of the intel architecture and cuda programming
(Wydawnictwa AGH, 2023) Gajos-Balińska, Anna; Wójcik, Grzegorz M.; Stpiczyński, Przemysław
High-density electroencephalographic (EEG) systems are utilized in the study of the human brain and its underlying behaviours. However, working with the EEG data requires a well-cleaned signal, which is often obtained using independent component analysis (ICA) methods. The longer the calculation time for these types of algorithms is, the more data is obtained. This paper presents a hybrid implementation of the fastICA algorithm that uses parallel programming techniques (libraries and extensions of the Intel processors and CUDA programming), which results in a significant acceleration of execution time on selected architectures.
Artykuł
Otwarty dostęp
Mesh compression algorithm for geometrical coordinates in computational meshes
(Wydawnictwa AGH, 2023) Michalik, Kazimierz; Rauch, Łukasz
Application of advanced mesh based methods, including adaptive finite element method, is impossible without theoretical elaboration and practical realization of a model for organization and functionality of computational mesh. One of the most basic mesh functionality is storing and providing geometrical coordinates for vertices and other mesh entities. New algorithm for this task based on onthe- fly recreation of coordinates was developed. Conducted tests are proving that, for selected cases, it can be orders of magnitude faster than naive approach or other similar algorithms.
Artykuł
Otwarty dostęp
Parkinson’s disease classification based on stacked denoising autoencoder
(Wydawnictwa AGH, 2023) Sukanya, P.; Srinivasa Rao, B.
One of the most common neurological conditions caused by gradual brain degeneration is Parkinson’s disease (PD). Although this neurological condition has no known treatment, early detection and therapy can help patients improve their quality of life. An essential patient’s health record is made of medical images used to control, manage, and treat diseases. However, in computerbased diagnostics, disease classification is a difficult task because of the time consumption and high rate of false positive marks. To overcome this problem, this paper introduces a stacked denoising autoencoder (SDA) for Parkinson’s disease classification. In preprocessing, noise is reduced and important information is retained, resulting in increased performance and data augmentation is performed to avoid overfitting issues and increase the size of the dataset. The main aim of this paper is to derive an optimal feature selection design for an effective Parkinson’s disease classification. Improved Pigeon-Inspired Optimization (IPIO) algorithm is introduced to enhance the performance of the classifier. Thus, the classification result improved by the optimal features and also increased the sensitivity, accuracy, and specificity in the medical image diagnosis. The proposed scheme is implemented in PYTHON and compared with traditional feature selection models and other classification approaches. The efficacy of the performances is evaluated using a Parkinson’s Progression Markers Initiative (PPMI) dataset. The integration of the stacked denoising autoencoder and Improved pigeon inspired optimization method produced the greatest results, with 99.17% accuracy, 98.74% sensitivity, and 98.96% specificity. Furthermore, our finding outperforms the most recent research in the field.
Artykuł
Otwarty dostęp
Square grid path planning for mobile anchor-based localization in wireless sensor networks
(Wydawnictwa AGH, 2023) Boukhari, Nawel; Bouamama, Salim
Localization is to provide all sensor nodes with their geographical positions. A mobile anchor-based localization in wireless sensor networks uses a mobile anchor equipped with GPS, which travels along a predetermined path. At each specified beacon point, it broadcasts its current known position to help other sensor nodes with unknown locations estimate their positions. This paper analyzes the determination of beacon points based on a square grid. We propose an improved path planning model named Union-curve. Our proposed model incorporates all beacon points of five previously developed paths, namely, SCAN, HILBERT, S-type, Z-curve, and ?-Scan on the commonly used square grid decomposition of area. Unknown sensor nodes estimate their positions using two techniques, APT and WCWCL-RSSI. Simulation results show that the proposed model has higher accuracy, with a big difference in error rate compared to the other models. In addition, this model guarantees maximum coverage with less path resolution value.
Artykuł
Otwarty dostęp
Process of fingerprint authentication using cancelable biohashed template
(Wydawnictwa AGH, 2023) Mamatha, K R; Radhika, K R
Template protection using cancelable biometrics prevents data loss and hacking stored templates, by providing considerable privacy and security. Hashing and salting techniques are used to build resilient systems. Salted password method is employed to protect passwords against different types of attacks namely brute-force attack, dictionary attack, rainbow table attacks. Salting claims that random data can be added to input of hash function to ensure unique output. Hashing are speed bumps in an attacker’s road to breach user’s data. Research proposes a contemporary two factor authenticator called Biohashing. Biohashing procedure is implemented by recapitualted inner product over a pseudo random number generator key, as well as fingerprint features that are a network of minutiae. Cancelable template authentication used in fingerprint-based sales counter accelerates payment process. Fingerhash is code produced after applying biohashing on fingerprint. Fingerhash is a binary string procured by choosing individual bit of sign depending on a preset threshold. Experiment is carried using benchmark FVC 2002 DB1 dataset. Authentication accuracy is found to be nearly 97%. Results compared with state-of-art approaches finds promising.
Artykuł
Otwarty dostęp
Survey on the most current image processing methods in huntington’s disease diagnostics and progression assessment
(Wydawnictwa AGH, 2023) Kawala-Sterniuk, Aleksandra; Mikolajewski, Dariusz; Bryniarska, Anna; Myslicka, Maria; Czarnecki, Damian; Junkiert-Czarnecka, Anna; Sudol, Adam; Mikolajewska, Emilia; Pawlowski, Mateusz; Wlodarczyk, Anna; Walecki, Piotr; Gasz, Rafal; Libionka, Witold; Panczyszak, Bartosz; Pelc, Mariusz; Zygarlicki, Jaroslaw; Racheniuk, Henryk; Bojkowska-Otrebska, Katarzyna; Sterniuk, Piotr; Gorzelanczyk, Edward Jacek; Ferri, Raffaele
Huntington’s disease (HD) is a rare, incurable neurodegenerative disorder where fast and non-invasive diagnosis targeting patients’ condition plays a crucial role. In modern medicine, various scientific areas are being combined, such as computing, medicine and biomedical engineering. This survey is focused on the most recent image processing methods applied not only for the purpose of diagnosing HD but also for the assessment of its progression severity, in order to contribute to the effort to prolong life of and to improve its quality.