scholarly journals Real-time Detection of Driver’s Movement Intention in Response to Traffic Lights

2019 ◽  
Author(s):  
Zahra Khaliliardali ◽  
Ricardo Chavarriaga ◽  
Huaijian Zhang ◽  
Lucian A. Gheorghe ◽  
Serafeim Perdikis ◽  
...  
Keyword(s):  
Real Time ◽  
Area Under The Curve ◽  
Classification Performance ◽  
Brain State ◽  
Single Trial ◽  
Slow Cortical Potentials ◽  
Traffic Lights ◽  
Brain States ◽  
Movement Intention ◽  
Cortical Potentials

AbstractMovements are preceded by certain brain states that can be captured through various neuroimaging techniques. Brain-Computer Interfaces can be designed to detect the movement intention brain state during driving, which could be beneficial in improving the interaction between a smart car and its driver, by providing assistance in-line with the driver’s intention. In this paper, we present an Electroencephalogram based decoder of such brain states preceding movements performed in response to traffic lights in two experiments: in a car simulator and a real car. The results of both experiments (N=10: car simulator, N=8: real car) confirm the presence of anticipatory Slow Cortical Potentials in response to traffic lights for accelerating and braking actions. Single-trial classification performance exhibits an Area Under the Curve (AUC) of 0.71±0.14 for accelerating and 0.75±0.13 for braking. The AUC for the real car experiment are 0.63±0.07 and 0.64±0.13 for accelerating and braking respectively. Moreover, we evaluated the performance of real-time decoding of the intention to brake during online experiments only in the car simulator, yielding an average accuracy of 0.64±0.1. This paper confirm the existence of the anticipatory slow cortical potentials and the feasibility of single-trial detection these potentials in driving scenarios.

Roles of default-mode network and supplementary motor area in human vigilance performance: evidence from real-time fMRI

2013 ◽  
Vol 109 (5) ◽  
pp. 1250-1258 ◽  
Author(s):  
Oliver Hinds ◽  
Todd W. Thompson ◽  
Satrajit Ghosh ◽  
Julie J. Yoo ◽  
Susan Whitfield-Gabrieli ◽  
...  
Keyword(s):  
Real Time ◽  
Default Mode Network ◽  
Human Performance ◽  
Supplementary Motor Area ◽  
Brain Regions ◽  
Motor Area ◽  
Neural Systems ◽  
Brain State ◽  
Default Mode ◽  
Brain States

We used real-time functional magnetic resonance imaging (fMRI) to determine which regions of the human brain have a role in vigilance as measured by reaction time (RT) to variably timed stimuli. We first identified brain regions where activation before stimulus presentation predicted RT. Slower RT was preceded by greater activation in the default-mode network, including lateral parietal, precuneus, and medial prefrontal cortices; faster RT was preceded by greater activation in the supplementary motor area (SMA). We examined the roles of these brain regions in vigilance by triggering trials based on brain states defined by blood oxygenation level-dependent activation measured using real-time fMRI. When activation of relevant neural systems indicated either a good brain state (increased activation of SMA) or a bad brain state (increased activation of lateral parietal cortex and precuneus) for performance, a target was presented and RT was measured. RTs on trials triggered by a good brain state were significantly faster than RTs on trials triggered by a bad brain state. Thus human performance was controlled by monitoring brain states that indicated high or low vigilance. These findings identify neural systems that have a role in vigilance and provide direct evidence that the default-mode network has a role in human performance. The ability to control and enhance human behavior based on brain state may have broad implications.

Detection of movement intention from single-trial movement-related cortical potentials using random and non-random paradigms

2015 ◽  
Vol 2 (1) ◽  
pp. 29-39 ◽  
Author(s):  
Susan Aliakbaryhosseinabadi ◽  
Ning Jiang ◽  
Aleksandra Vuckovic ◽  
Kim Dremstrup ◽  
Dario Farina ◽  
...  
Keyword(s):  
Single Trial ◽  
Movement Intention ◽  
Cortical Potentials

scholarly journals EEG-triggered TMS reveals stronger brain state-dependent modulation of motor evoked potentials at weaker stimulation intensities

2018 ◽  
Author(s):  
Natalie Schaworonkow ◽  
Jochen Triesch ◽  
Ulf Ziemann ◽  
Christoph Zrenner
Keyword(s):  
Evoked Potentials ◽  
Real Time ◽  
Motor Evoked Potentials ◽  
Corticospinal Excitability ◽  
Brain State ◽  
Stimulation Intensity ◽  
Negative Peak ◽  
State Dependent ◽  
Wide Range ◽  
Brain States

AbstractBackgroundCorticospinal excitability depends on the current brain state. The recent development of real-time EEG-triggered transcranial magnetic stimulation (EEG-TMS) allows studying this relationship in a causal fashion. Specifically, it has been shown that corticospinal excitability is higher during the scalp surface negative EEG peak compared to the positive peak of µ-oscillations in sensorimotor cortex, as indexed by larger motor evoked potentials (MEPs) for fixed stimulation intensity.ObjectiveWe further characterize the effect of µ-rhythm phase on the MEP input-output (IO) curve by measuring the degree of excitability modulation across a range of stimulation intensities. We furthermore seek to optimize stimulation parameters to enable discrimination of functionally relevant EEG-defined brain states.MethodsA real-time EEG-TMS system was used to trigger MEPs during instantaneous brain-states corresponding to µ-rhythm surface positive and negative peaks with five different stimulation intensities covering an individually calibrated MEP IO curve in 15 healthy participants.ResultsMEP amplitude is modulated by µ-phase across a wide range of stimulation intensities, with larger MEPs at the surface negative peak. The largest relative MEP-modulation was observed for weak intensities, the largest absolute MEP-modulation for intermediate intensities. These results indicate a leftward shift of the MEP IO curve during the µ-rhythm negative peak.ConclusionThe choice of stimulation intensity influences the observed degree of corticospinal excitability modulation by µ-phase. Lower stimulation intensities enable more efficient differentiation of EEG µ-phase-defined brain states.

scholarly journals Comparing Task-Relevant Information Across Different Methods of Extracting Functional Connectivity

2018 ◽  
Author(s):  
Sophie Benitez Stulz ◽  
Andrea Insabato ◽  
Gustavo Deco ◽  
Matthieu Gilson ◽  
Mario Senden
Keyword(s):  
Functional Connectivity ◽  
Large Scale ◽  
Cross Validation ◽  
Activity Patterns ◽  
Relevant Information ◽  
Brain Regions ◽  
Classification Performance ◽  
Phase Coherence ◽  
Brain State ◽  
Brain States

AbstractThe concept of brain states, functionally relevant large-scale activity patterns, has become popular in neuroimaging. Not all components of such patterns are equally characteristic for each brain state, but machine learning provides a possibility for extracting and comparing the structure of brain states from functional data. However, their characterization in terms of functional connectivity measures varies widely, from cross-correlation to phase coherence, and the idea that different measures provide similar or coherent information is a common assumption made in neuroimaging. Here, we compare the brain state signatures extracted from of phase coherence, pairwise covariance, correlation, regularized covariance and regularized precision for a dataset of subjects performing five different cognitive tasks. In addition, we compare the classification performance in identifying the tasks for each connectivity measure. The measures are evaluated in their ability to discriminate the five tasks with two types of cross-validation: within-subject cross-validation, which reflects the stability of the signature over time; and between-subject cross-validation, which aims at extracting signatures that generalize across subjects. Secondly, we compare the informative features (connections or links between brain regions/areas) across measures to test the assumption that similar information is obtained about brain state signatures from different connectivity measures. In our results, the different types of cross-validation give different classification performance and emphasize that functional connectivity measures on fMRI require observation windows of sufficient duration. Furthermore, we find that informative links for the classification, meaning changes between tasks that are consistent across subjects, are entirely uncorrelated between BOLD correlations and covariances. These results indicate that the corresponding FC signature can strongly differ across FC methods used and that interpretation is subject to caution in terms of subnetworks related to a task.

Detection of movement intention from single-trial movement-related cortical potentials

2011 ◽  
Vol 8 (6) ◽  
pp. 066009 ◽  
Author(s):  
Imran Khan Niazi ◽  
Ning Jiang ◽  
Olivier Tiberghien ◽  
Jørgen Feldbæk Nielsen ◽  
Kim Dremstrup ◽  
...  
Keyword(s):  
Single Trial ◽  
Movement Intention ◽  
Cortical Potentials

Perancangan Sistem Kontrol Lampu Lalulintas Cerdas Dengan Menggunakan Mikrokontroler dan Kamera

Jurnal MIPA ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 200
Author(s):  
Tjerie Pangemanan ◽  
Arnold Rondonuwu
Keyword(s):  
Real Time ◽  
Digital Image ◽  
Red Light ◽  
Green Light ◽  
Processing Method ◽  
Traffic Lights ◽  
Traffic System ◽  
Road Users ◽  
Adjustment System ◽  
System Time

Masalah lalu lintas  merupakan salah satu  masalah yang sangat sulit diatasi dengan hanya menggunakan system waktu (timer). Oleh sebab itu diperlukan suatu system pengaturan otomatis yang bersifat real-time sehingga waktu pengaturan lampu lalu lintas dapat disesuaikan dnegan keadaan di lapangan. Penelitian ini bertujuan mengembangkan suatu simulasi sistem yang mampu mengestimasi panjang antrian kendaraan menggunakan metoda pengolahan citra digital hanya dengan menggunakan satu kamera untuk dijadikan parameter masukan  dalam menghitung lama waktu nyala lampu merah dan lampu hijau. Oleh karena itu, sistem lalulintas sangatlah diperlukan, sebagai sarana dan prasarana untuk menjadikan lalulintas lancar, aman, bahkan sebagai media pembelajaran disiplin bagi masyarakat pengguna jalan raya. Penelitian ini penulis menggunakan sistem pengontrolan berbasis citra digital dimana camera sebagai sensor. Untuk aplikasi dari  semua metode dalam penelitian ini digunakan Microcontroller AurdinoTraffic problems is one of the problems that is very difficult to overcome by only using the system time (timer). Therefore we need an automatic real-time adjustment system so that the time settings for traffic lights can be adjusted according to the conditions on the ground. This study aims to develop a system simulation that is able to estimate the length of the vehicle queue using a digital image processing method using only one camera to be used as input parameters in calculating the length of time the red light and green light. Therefore, the traffic system is very necessary, as a means and infrastructure to make traffic smooth, safe, even as a medium for disciplined learning for road users. In this study the authors used a digital image-based control system where the camera as a sensor. For the application of all methods in this study, Aurdino Microcontroller is used

Sign in / Sign up

Export Citation Format

Share Document