Search

This study examines the effectiveness of traditional machine learning classifiers versus deep learning models for detecting the imagined speech using electroencephalogram data. Specifically, we evaluated conventional machine learning techniques such as CSP-SVM and LDA-SVM classifiers alongside deep learning architectures such as EEGNet, ShallowConvNet, and DeepConvNet. Machine learning classifiers exhibited significantly lower precision and recall, indicating limited feature extraction capabilities and poor generalization between imagined speech and idle states. In contrast, deep learning models, particularly EEGNet, achieved the highest accuracy of 0.7080 and an F1 score of 0.6718, demonstrating their enhanced ability in automatic feature extraction and representation learning, essential for capturing complex neurophysiological patterns. These findings highlight the limitations of conventional machine learning approaches in brain-computer interface (BCI) applications and advocate for adopting deep learning methodologies to achieve more precise and reliable classification of detecting imagined speech. This foundational research contributes to the development of imagined speech-based BCI systems.

In recent years, brain-computer interfaces have made advances in decoding various motor-related tasks, including gesture recognition and movement classification, utilizing electroencephalogram (EEG) data. These developments are fundamental in exploring how neural signals can be interpreted to recognize specific physical actions. This study centers on a written alphabet classification task, where we aim to decode EEG signals associated with handwriting. To achieve this, we incorporate hand kinematics to guide the extraction of the consistent embeddings from high-dimensional neural recordings using auxiliary variables (CEBRA). These CEBRA embeddings, along with the EEG, are processed by a parallel convolutional neural network model that extracts features from both data sources simultaneously. The model classifies nine different handwritten characters, including symbols such as exclamation marks and commas, within the alphabet. We evaluate the model using a quantitative five-fold cross-validation approach and explore the structure of the embedding space through visualizations. Our approach achieves a classification accuracy of 91 % for the nine-class task, demonstrating the feasibility of fine-grained handwriting decoding from EEG., Comment: 4 pages, 2 figures, 1 table, Name of Conference: International Conference on Brain-Computer Interface

QCD gives rise to a rich spectrum of excited baryon states. Understanding their internal structure is important for many areas of nuclear physics, such as nuclear forces, dense matter, and neutrino-nucleus interactions. Generalized parton distributions (GPDs) are an established tool for characterizing the QCD structure of the ground-state nucleon. They are used to create 3D tomographic images of the quark/gluon structure and quantify the mechanical properties such as the distribution of mass, angular momentum and forces in the system. Transition GPDs extend these concepts to $N \rightarrow N^\ast$ transitions and can be used to characterize the 3D structure and mechanical properties of baryon resonances. They can be probed in high-momentum-transfer exclusive electroproduction processes with resonance transitions $e + N \rightarrow e' + M + N^\ast$, such as deeply-virtual Compton scattering ($M = \gamma$) or meson production ($M = \pi, K$, $etc.$), and in related photon/hadron-induced processes. This White Paper describes a research program aiming to explore baryon resonance structure with transition GPDs. This includes the properties and interpretation of the transition GPDs, theoretical methods for structures and processes, first experimental results from JLab 12 GeV, future measurements with existing and planned facilities (JLab detector and energy upgrades, COMPASS/AMBER, EIC, EicC, J-PARC, LHC ultraperihperal collisions), and the theoretical and experimental developments needed to realize this program.

Brain-to-speech technology represents a fusion of interdisciplinary applications encompassing fields of artificial intelligence, brain-computer interfaces, and speech synthesis. Neural representation learning based intention decoding and speech synthesis directly connects the neural activity to the means of human linguistic communication, which may greatly enhance the naturalness of communication. With the current discoveries on representation learning and the development of the speech synthesis technologies, direct translation of brain signals into speech has shown great promise. Especially, the processed input features and neural speech embeddings which are given to the neural network play a significant role in the overall performance when using deep generative models for speech generation from brain signals. In this paper, we introduce the current brain-to-speech technology with the possibility of speech synthesis from brain signals, which may ultimately facilitate innovation in non-verbal communication. Also, we perform comprehensive analysis on the neural features and neural speech embeddings underlying the neurophysiological activation while performing speech, which may play a significant role in the speech synthesis works., Comment: 4 pages

Ferromagnets generate an anomalous Hall effect even without the presence of a magnetic field, something that conventional antiferromagnets cannot replicate but noncollinear antiferromagnets can. The anomalous Hall effect governed by the resistivity tensor plays a crucial role in determining the presence of time reversal symmetry and the topology present in the system. In this work we reveal the complex origin of the anomalous Hall effect arising in noncollinear antiferromagnets by performing Hall measurements with fields applied in selected directions in space with respect to the crystalline axes. Our coplanar magnetic field geometry goes beyond the conventional perpendicular field geometry used for ferromagnets and allows us to suppress any magnetic dipole contribution. It allows us to map the in-plane anomalous Hall contribution and we demonstrate a 120$^\circ$ symmetry which we find to be governed by the octupole moment at high fields. At low fields we subsequently discover a surprising topological Hall-like signature and, from a combination of theoretical techniques, we show that the spins can be recast into dipole, emergent octupole and noncoplanar effective magnetic moments. These co-existing orders enable magnetization dynamics unachievable in either ferromagnetic or conventional collinear antiferromagnetic materials.

The emergence of spin-orbit torques as a promising approach to energy-efficient magnetic switching has generated large interest in material systems with easily and fully tunable spin-orbit torques. Here, current-induced spin-orbit torques in VO$_2$/NiFe heterostructures were investigated using spin-torque ferromagnetic resonance, where the VO$_2$ layer undergoes a prominent insulator-metal transition. A roughly two-fold increase in the Gilbert damping parameter, $\alpha$, with temperature was attributed to the change in the VO$_2$/NiFe interface spin absorption across the VO$_2$ phase transition. More remarkably, a large modulation ($\pm$100%) and a sign change of the current-induced spin-orbit torque across the VO$_2$ phase transition suggest two competing spin-orbit torque generating mechanisms. The bulk spin Hall effect in metallic VO$_2$, corroborated by our first-principles calculation of spin Hall conductivity, $\sigma_{SH} \approx 10^4 \frac{\hbar}{e} \Omega^{-1} m^{-1}$, is verified as the main source of the spin-orbit torque in the metallic phase. The self-induced/anomalous torque in NiFe, of the opposite sign and a similar magnitude to the bulk spin Hall effect in metallic VO$_2$, could be the other competing mechanism that dominates as temperature decreases. For applications, the strong tunability of the torque strength and direction opens a new route to tailor spin-orbit torques of materials which undergo phase transitions for new device functionalities., Comment: 16 pages, 5 figures

Generating pure spin currents via the spin Hall effect in heavy metals has been an active topic of research in the last decade. In order to reduce the energy required to efficiently switch neighbouring ferromagnetic layers for applications, one should not only increase the charge- to-spin conversion efficiency but also decrease the longitudinal resistivity of the heavy metal. In this work, we investigate the spin Hall conductivity in W_{1-x}Ta_{x} / CoFeB / MgO (x = 0 - 0.2) using spin torque ferromagnetic resonance measurements. Alloying W with Ta leads to a factor of two change in both the damping-like effective spin Hall angle (from - 0.15 to - 0.3) and longitudinal resistivity (60 - 120 {\mu}W cm). At 11% Ta concentration, a remarkably high spin Hall angle value of - 0.3 is achieved with a low longitudinal resistivity 100 {\mu}W cm, which could lead to a very low power consumption for this W-based alloy. This work demonstrates sputter-deposited W-Ta alloys could be a promising material for power-efficient spin current generation., Comment: 15 pages, 3 figures

Deployment of Internet of Things (IoT) in smart buildings has received considerable interest from both the academic community and commercial sectors. Unfortunately, widespread adoption of current smart building solutions is inhibited by the high costs associated with installation and maintenance. Moreover, different types of IoT devices from different manufacturers typically form distinct networks and data silos. There is a need to use a common backbone network that facilitates interoperability and seamless data exchange in a uniform way. In this paper, we present EMIoT, a novel solution for smart buildings that breaks these barriers by leveraging existing emergency lighting systems. In EMIoT, we embed a wireless LoRa module in each emergency light to turn them into wireless routers. EMIoT has been deployed in more than 50 buildings of different types in Sydney Australia and has been successfully running over two years. We present the design and implementation of EMIoT in this paper. Moreover, we use the deployment in a residential building as a use case to show the performance of EMIoT in real-world environments and share lessons learned. Finally, we discuss the advantages and disadvantages of EMIoT. This paper provides practical insights for IoT deployment in smart buildings for practitioners and solution providers., Comment: 7 pages, 5 figures

In recent years, we have witnessed the rapid development of LoRa technology, together with extensive studies trying to understand its performance in various application settings. In contrast to measurements performed in large outdoor areas, limited number of attempts have been made to understand the characterization and performance of LoRa technology in indoor environments. In this paper, we present a comprehensive study of LoRa technology in multi-floor buildings. Specifically, we investigate the large-scale fading characteristic, temporal fading characteristic, coverage and energy consumption of LoRa technology in four different types of buildings. Moreover, we find that the energy consumption using different parameter settings can vary up to 145 times. These results indicate the importance of parameter selection and enabling LoRa adaptive data rate feature in energy-limited applications. We hope the results in this paper can help both academia and industry understand the performance of LoRa technology in multi-floor buildings to facilitate developing practical indoor applications., Comment: 10 pages, 9 figures