Melinda Rácz

Mx. Melinda Rácz

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 January 2020 in Journal of Neural Engineering
Verified
Journal Article
Closed access
PDF file
Melinda RáczMelinda Rácz
Melinda Rácz
CLCsaba Liber
Csaba Liber
ENErik Németh
Erik Németh
RFRichárd Fiáth
Richárd Fiáth
JRJános Rokai
János Rokai
GMGergely Márton
Gergely Márton
Objective . The extraction and identification of single-unit activities in intracortically recorded electric signals have a key role in basic neuroscience, but also in applied fields, like in the development of high-accuracy brain–computer interfaces. The purpose of this paper is to present our current results on the detection, classification and prediction of neural activities based on multichannel action potential recordings. Approach . Throughout our investigations, a deep learning approach utilizing convolutional neural networks and a combination of recurrent and convolutional neural networks was applied, with the latter used in case of spike detection and the former used for cases of sorting and predicting spiking activities. Main results . In our experience, the algorithms applied prove to be useful in accomplishing the tasks mentioned above: our detector could reach an average recall of 69%, while we achieved an average accuracy of 89% in classifying activities produced by more than 20 distinct neurons. Significance . Our findings support the concept of creating real-time, high-accuracy action potential based BCIs in the future, providing a flexible and robust algorithmic background for further development.

16 March 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Melinda RáczMelinda Rácz
Melinda Rácz
Erick NoboaErick Noboa
Erick Noboa
BDBorsa Détár
Borsa Détár
ÁNÁdám Nemes
Ádám Nemes
Péter GalambosPéter Galambos
Péter Galambos
Tamás HaideggerTamás Haidegger
Tamás Haidegger
Given the rising popularity of robotics, student-driven robot development projects are playing a key role in attracting more people towards engineering and science studies. This article presents the early development process of an open-source mobile robot platform—named PlatypOUs—which can be remotely controlled via an electromyography (EMG) appliance using the MindRove brain–computer interface (BCI) headset as a sensor for the purpose of signal acquisition. The gathered bio-signals are classified by a Support Vector Machine (SVM) whose results are translated into motion commands for the mobile platform. Along with the physical mobile robot platform, a virtual environment was implemented using Gazebo (an open-source 3D robotic simulator) inside the Robot Operating System (ROS) framework, which has the same capabilities as the real-world device. This can be used for development and test purposes. The main goal of the PlatypOUs project is to create a tool for STEM education and extracurricular activities, particularly laboratory practices and demonstrations. With the physical robot, the aim is to improve awareness of STEM outside and beyond the scope of regular education programmes. It implies several disciplines, including system design, control engineering, mobile robotics and machine learning with several application aspects in each. Using the PlatypOUs platform and the simulator provides students and self-learners with a firsthand exercise, and teaches them to deal with complex engineering problems in a professional, yet intriguing way.

7 April 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
Melinda RáczMelinda Rácz
Melinda Rácz
MBMelinda Becske
Melinda Becske
TMTímea Magyaródi
Tímea Magyaródi
GKGergely Kitta
Gergely Kitta
MSMárton Szuromi
Márton Szuromi
GMGergely Márton
Gergely Márton
Flow is the state of optimal experience which can lead to outstanding performance. Our study demonstrates the feasibility of detecting and monitoring flow using wearable devices. Twenty-eight Hungarian adults participated in the experiment. They played a game at different levels to induce flow and anti-flow states, which was tested with questionnaires. We measured electroencephalography (EEG), heart rate (HR), blood oxygen saturation (SpO2) and galvanic skin response (GSR) signals as well as head and hand motion. We isolated EEG delta, theta, alpha and beta band power, HR, SpO2 and GSR average and standard deviation, as well as acceleration and angular velocity standard deviation. In flow condition, alpha and theta power were the dominant components, in accordance with the transient hypofrontality hypothesis. We also replicated the U-shaped characteristic of the heart rate variability; in addition, we propose an inverse U-shaped and a U-shaped characteristic for SpO2 and SpO2 variability, respectively. On the basis of motion tracking, subjects were the least physically active in flow, signifying a focused state, and the most active in boredom. Our results support the applicability of lightweight, wearable devices for monitoring mental state that can be utilized to improve well-being at work or in everyday situations.

13 October 2023 in Scientific Reports
Verified
Journal Article
Open access
PDF file
DHDávid Horváth
Dávid Horváth
JNJanos Negyesi
Janos Negyesi
Melinda RáczMelinda Rácz
Melinda Rácz
TGTamás Győri
Tamás Győri
ZMZsolt Matics
Zsolt Matics
LRLevente Rácz
Levente Rácz
Neurocognitive assessment tools have been proposed to optimize, maintain, and improve perceptual-cognitive performance. Here, we investigated the feasibility and efficacy of a novel neurofeedback system, neuroMoon (nM), on cognitive abilities compared with one of the most popular perceptual-cognitive training (PCT) tools both in sports and rehabilitation called NeuroTracker (NT). Thirty-one young athletes performed a comprehensive battery of cognitive tests from the Vienna Test System before and after a 12-session computer-based cognitive training program using nM (n = 11, age 22.6 ± 3.8 years), nM sham (CON, n = 10, age 20.3 ± 1.2 years) or NT (n = 10, age 20.5 ± 1.7 years) device. A series of repeated-measures ANOVA was performed to detect changes in cognitive abilities in response to the training. Participants had faster median reaction time in both the color-naming and word-reading conditions of the Stroop test (all p < 0.005), regardless of group. Regarding the task switching test, statistical analysis indicated faster working time and mean reaction time of the incongruent stimuli, repetition task, and shifting task (all p < 0.005), nevertheless, these changes were also regardless of group. In addition, we found fewer omitted (pre: 17.5 ± 8.3, post: 6.4 ± 1.5, d = 1.311) and more correct (pre: 261.6 ± 36.1, post: 278.6 ± 38.7, d = − 1.020) post-intervention answers in the determination test, regardless of group. Finally, participants in each group performed the digit span backward test with larger post (6.42 ± 1.54) vs. pre (5.55 ± 1.43) scores following the PCT (d = − 0.801). Overall, PCT with nM as compared with NT induced similar results in cognitive abilities suggesting its potential to be used to achieve and maintain better mental performance. However, considering that the sham stimulation also induced similar improvements in cognitive abilities, future studies should clearly determine the cognitive measures that could benefit from NF training.

26 April 2021 in Journal of Neural Engineering
Verified
Journal Article
Closed access
PDF file
JRJános Rokai
János Rokai
Melinda RáczMelinda Rácz
Melinda Rácz
RFRichárd Fiáth
Richárd Fiáth
UIUlbert István
Ulbert István
GMGergely Márton
Gergely Márton
Objective. The growing number of recording sites of silicon-based probes means that an increasing amount of neural cell activities can be recorded simultaneously, facilitating the investigation of underlying complex neural dynamics. In order to overcome the challenges generated by the increasing number of channels, highly automated signal processing tools are needed. Our goal was to build a spike sorting model that can perform as well as offline solutions while maintaining high efficiency, enabling high-performance online sorting. Approach. In this paper we present ELVISort, a deep learning method that combines the detection and clustering of different action potentials in an end-to-end fashion. Main results. The performance of ELVISort is comparable with other spike sorting methods that use manual or semi-manual techniques, while exceeding the methods which use an automatic approach: ELVISort has been tested on three independent datasets and yielded average F1 scores of 0.96, 0.82 and 0.81, which comparable with the results of state-of-the-art algorithms on the same data. We show that despite the good performance, ELVISort is capable to process data in real-time: the time it needs to execute the necessary computations for a sample of given length is only 1/15.71 of its actual duration (i.e. the sampling time multiplied by the number of the sampling points). Significance. ELVISort, because of its end-to-end nature, can exploit the massively parallel processing capabilities of GPUs via deep learning frameworks by processing multiple batches in parallel, with the potential to be used on other cutting-edge AI-specific hardware such as TPUs, enabling the development of integrated, portable and real-time spike sorting systems with similar performance to offline sorters.