Various kinds of nanostructured materials have been extensively investigated as lithium ion battery electrode derived from their numerous advantageous features including enhanced energy and power density cyclability. However, little is known about the microscopic origin how nanostructures can enhance storage performance. Herein, we identify in anatase TiO2 nanostructure report a reversible stable route to achieve capacity TiO2. We designed hollow composed interconnected ∼5 nm sized...

Non-invasive brain-computer interface (BCI) has been developed for recognizing and classifying human mental states with high performances. Specifically, pilots' accurately is a critical issue because their cognitive states, which are induced by fatigue, workload, distraction, may be fundamental in catastrophic accidents. In this study, we present an electroencephalogram (EEG) classification of four (fatigue, the normal state) from EEG signals both offline pseudo-online analyses. To best our...

Non-invasive brain-computer interfaces (BCI) have been developed for recognizing human mental states with high accuracy and decoding various types of conditions. In particular, accurately a pilot’s state is critical issue as more than 70% aviation accidents are caused by factors, such fatigue or drowsiness. this study, we report the classification not only two (i.e., alert drowsy states) but also five drowsiness levels from electroencephalogram (EEG) signals. To best our knowledge, approach...

Abstract Background Non-invasive brain–computer interfaces (BCIs) have been developed for realizing natural bi-directional interaction between users and external robotic systems. However, the communication BCI systems through artificial matching is a critical issue. Recently, BCIs to adopt intuitive decoding, which key solving several problems such as small number of classes manually commands with device control. Unfortunately, advances in this area slow owing lack large uniform datasets....

A new kind of sequence-to-sequence model called a transformer has been applied to electroencephalogram (EEG) systems. However, the majority EEG-based models have attention mechanisms temporal domain, while connectivity between brain regions and relationship different frequencies neglected. In addition, many related studies on imagery-based brain-computer interface (BCI) limited classifying EEG signals within one type imagery. Therefore, it is important develop general learn various types...

Brain–computer interface (BCI) is a technology that allows users to control computers by reflecting their intentions. Electroencephalogram (EEG)–based BCI has been developed because of its potential, however, decoding performance still insufficient apply in the real–world environment. As deep learning methods achieve significant various domains, it applied EEG–based domain. In particular, ShallowConvNet one most widely used robust multiple datasets. However, model's parameters have be...

Electroencephalography (EEG) signals are the brain acquired using non-invasive approach. Owing to high portability and practicality, EEG have found extensive application in monitoring human physiological states across various domains. In recent years, deep learning methodologies been explored decode intricate information embedded signals. However, since from humans, it has issues with acquiring enormous amounts of data for training models. Therefore, previous research attempted develop...

Recent advances in brain-computer interface (BCI) techniques have led to increasingly refined interactions between users and external devices. Accurately decoding kinematic information from brain signals is one of the main challenges encountered control human-like robots. In particular, although forearm an upper extremity frequently used daily life for high-level tasks, only few studies addressed movement. this study, we focus on classification movements according elaborated rotation angles...

Noninvasive brain-computer interface (BCI) decodes brain signals to understand user intention. Recent advances have been developed for the BCI-based drone control system as demand increases. Especially, swarm based on could provide various industries such military service or industry disaster. This paper presents a prototype of brain-swarm variety scenarios using visual imagery paradigm. We designed experimental environment that acquire under simulator environment. Through system, we...

Detection of the pilots' mental states is particularly critical because their abnormal (AbSs) could cause catastrophic accidents. In this study, we presented feasibility classifying various specific AbSs (namely, low fatigue, high workload, distraction, and distraction) by applying deep learning method. To best our knowledge, study first attempt to classify multiple pilots. We proposed hybrid neural networks with five convolutional blocks two long short-term memory layers for decoding AbSs....

Non-invasive brain-computer interface (BCI) has been developed for understanding users' intentions by using electroencephalogram (EEG) signals. With the recent development of artificial intelligence, there have many developments in drone control system. BCI characteristic that can reflect led to BCI-based When swarm, we more advantages, such as mission diversity, than a single drone. In particular, swarm could provide advantages various industries military service or industry disaster....

Brain-computer interface (BCI) is a communication system between humans and computers reflecting human intention without using physical control device. Since deep learning robust in extracting features from data, research on decoding electroencephalograms by applying has progressed the BCI domain. However, application of domain issues with lack data overconfidence. To solve these issues, we proposed novel augmentation method, CropCat. CropCat consists two versions, CropCat-spatial...

Non-invasive brain-computer interface technology has been developed for detecting human mental states with high performances. Detection of the pilots' is particularly critical because their abnormal could cause catastrophic accidents. In this study, we presented feasibility classifying distraction levels (namely, normal state, low distraction, and distraction) by applying deep learning method. To best our knowledge, study first attempt to classify under a flight environment. We proposed...

Speech impairments due to cerebral lesions and degenerative disorders can be devastating. For humans with severe speech deficits, imagined in the brain-computer interface has been a promising hope for reconstructing neural signals of production. However, studies EEG-based domain still have some limitations high variability spatial temporal information low signal-to-noise ratio. In this paper, we investigated two groups native speakers tasks different languages, English Chinese. Our...

Brain-computer interface (BCI) is a technology that controls computers by reflecting users' intentions. Especially the electroencephalogram (EEG)-based BCI systems have been developed because of their potential utility. In studies, controlling drone swarm one important issues since it improves work efficiency and safety. Also, current research has investigated how swarms are controlled imagining formations using visual imagery (VI)-based EEG signals. The raw signals spectrogram widely used...

The detection of pilots' mental states is important due to the potential for their abnormal result in catastrophic accidents. This study introduces feasibility employing deep learning techniques classify different work-load levels, specifically normal state, low workload, and high workload. To best our knowledge, this first attempt workload levels pilots. Our approach involves hybrid neural network that consists five convolutional blocks one long short–term memory block extract significant...

The detection of pilots' mental states is critical, as abnormal have the potential to cause catastrophic accidents. This study demonstrates feasibility using deep learning techniques classify different fatigue levels, specifically a normal state, low fatigue, and high fatigue. To best our knowledge, this first levels in pilots. Our approach employs hybrid neural network comprising five convolutional blocks one long short-term memory block extract significant features from...

Electroencephalography (EEG) is a generally used neuroimaging approach in brain-computer interfaces due to its non-invasive characteristics and convenience, making it an effective tool for understanding human intentions. Therefore, recent research has focused on decoding intentions from EEG signals utilizing deep learning methods. However, since are highly susceptible noise during acquisition, there high possibility of the existence noisy data dataset. Although pioneer studies have assumed...

Brain-computer interface (BCI) enables the communication between humans and devices by reflecting humans' intentions status. Endogenous BCI is imagined-based it has advantage that fatigue level of body, especially eyes, relatively low no additional equipment for offering stimulation required. When conducting imagined speech, one endogenous paradigms, users imagine pronunciation as if actually speaking. In contrast, overt speech directly pronounce words. We proposed transfer learning-based...