Explore the vast range of titles available.

Over the years, considerable research has been conducted to investigate the mechanisms of speech perception and recognition. Electroencephalography (EEG) is a powerful tool for identifying brain activity; therefore, it has been widely used to determine the neural basis of speech recognition. In particular, for the classification of speech recognition, deep learning-based approaches are in the spotlight because they can automatically learn and extract representative features through end-to-end learning. This study aimed to identify particular components that are potentially related to phoneme representation in the rat brain and to discriminate brain activity for each vowel stimulus on a single-trial basis using a bidirectional long short-term memory (BiLSTM) network and classical machine learning methods. Nineteen male Sprague-Dawley rats subjected to microelectrode implantation surgery to record EEG signals from the bilateral anterior auditory fields were used. Five different vowel speech stimuli were chosen, /a/, /e/, /i/, /o/, and /u/, which have highly different formant frequencies. EEG recorded under randomly given vowel stimuli was minimally preprocessed and normalized by a z-score transformation to be used as input for the classification of speech recognition. The BiLSTM network showed the best performance among the classifiers by achieving an overall accuracy, f1-score, and Cohen’s κ values of 75.18%, 0.75, and 0.68, respectively, using a 10-fold cross-validation approach. These results indicate that LSTM layers can effectively model sequential data, such as EEG; hence, informative features can be derived through BiLSTM trained with end-to-end learning without any additional hand-crafted feature extraction methods.

Cardiovascular diseases are the major cause of death globally and require ubiquitous monitoring due to their asymptomatic yet modifiable nature. Photoplethysmography is an effective optical sensing technique for non-invasive health monitoring. However, its reliance on the current relatively large and rigid inorganic semiconductor-based light-emitting diodes and silicon photodiodes hampers high-resolution integration thus restricts a sensing from single measurement point. So, it limits detectable biomarkers to monitor cardiovascular diseases in a ubiquitous manner. In order to facilitate, here we report a single smartphone type multi-functional cardiovascular health monitor based on the massive array of organic photodiodes integrated into the most user interactive display device. Therefore, we achieved: 1) multi-point concurrent photoplethysmography and high-resolution dynamic image sensing, and 2) user-interactive sensing within the large display area. These advancements enabled new functions, including high-accuracy screening for cardiovascular diseases, blood pressure monitoring from both fingers, monitoring of finger blood vessels and flow dynamics, and single-device-based biofeedback. Applied machine learning enhanced diagnostic accuracy, with pilot studies showing results comparable to medical-grade devices. As a result, we believe smartphones harnessing the sensor organic light-emitting diode display could evolve into mobile health monitors and digital therapeutics thus revolutionizing diagnostic and treatment. Cardiovascular diseases require precise and continuous monitoring, but current PPG technology is limited to single-point sensing. Here, the authors present a display with organic photodiodes that enables multi-point PPG, high-resolution imaging, and user-interactive sensing.

In the Korean power system, growing power loads have recently created the problems of voltage instability and fault current in the Seoul Capital Area (SCA). Accordingly, the back-to-back (BTB) voltage source converter (VSC) high-voltage direct-current (HVDC) system is emerging to resolve such problems with grid segmentation. However, non-convergence problems occur in this metropolitan area, due to the large change of power flow in some contingencies. Therefore, this paper proposes two kinds of AC transmission emulation control (ATEC) strategies to improve the metropolitan transient stability, and to resolve the non-convergence problem. The proposed ATEC strategies are able to mitigate possible overloading of adjacent AC transmission, and maintain power balance between metropolitan regions. The first ATEC strategy uses a monitoring system that permits the reverse power flow of AC transmission, and thus effectively improves the grid stability based on the power transfer equation. The second ATEC strategy emulates AC transmission with DC link capacitors in a permissible DC-link voltage range according to angle difference, and securely improves the gird stability, without requiring grid operator schedule decisions. This paper compares two kinds of ATEC schemes: it demonstrates the first ATEC strategy with specific fault scenario with PSS/E (Power Transmission System Planning Software), and evaluates the second ATEC strategy with internal controller performance with PSCAD/EMTDC (Power System Electromagnetic Transients Simulation Software).

In this paper, we propose a system for inferring the pinch-to-zoom gesture using surface EMG (Electromyography) signals in real time. Pinch-to-zoom, which is a common gesture in smart devices such as an iPhone or an Android phone, is used to control the size of images or web pages according to the distance between the thumb and index finger. To infer the finger motion, we recorded EMG signals obtained from the first dorsal interosseous muscle, which is highly related to the pinch-to-zoom gesture, and used a support vector machine for classification between four finger motion distances. The powers which are estimated by Welch’s method were used as feature vectors. In order to solve the multiclass classification problem, we applied a one-versus-one strategy, since a support vector machine is basically a binary classifier. As a result, our system yields 93.38% classification accuracy averaged over six subjects. The classification accuracy was estimated using 10-fold cross validation. Through our system, we expect to not only develop practical prosthetic devices but to also construct a novel user experience (UX) for smart devices.

Background:Even though several mobile apps that can measure blood pressure have been developed, the data about the accuracy of these apps are limited.Objective:We assessed the accuracy of AlwaysBP (test) in blood pressure measurement compared with the standard, cuff-based, manual method of brachial blood pressure measurement (reference).Methods:AlwaysBP is a smartphone software that estimates systolic blood pressure (SBP) and diastolic blood pressure (DBP) based on pulse transit time (PTT). PTT was calculated with a finger photoplethysmogram and seismocardiogram using, respectively, the camera and inertial measurement unit sensor of a commercially available smartphone. After calculating PTT, SBP and DBP were estimated via the Bramwell-Hill and Moens-Korteweg equations. A calibration process was carried out 3 times for each participant to determine the input parameters of the equations. This study was conducted from March to August 2021 at Chungnam National University Sejong Hospital with 87 participants aged between 19 and 70 years who met specific conditions. The primary analysis aimed to evaluate the accuracy of the test method compared with the reference method for the entire study population. The secondary analysis was performed to confirm the stability of the test method for up to 4 weeks in 15 participants. At enrollment, gender, arm circumference, and blood pressure distribution were considered according to current guidelines.Results:Among the 87 study participants, 45 (52%) individuals were male, and the average age was 35.6 (SD 10.4) years. Hypertension was diagnosed in 14 (16%) participants before this study. The mean test and reference SBPs were 120.0 (SD 18.8) and 118.7 (SD 20.2) mm Hg, respectively (difference: mean 1.2, SD 7.1 mm Hg). The absolute differences between the test and reference SBPs were <5, <10, and <15 mm Hg in 57.5% (150/261), 84.3% (220/261 ), and 94.6% (247/261) of measurements. The mean test and reference DBPs were 80.1 (SD 12.6) and 81.1 (SD 14.4) mm Hg, respectively (difference: mean −1.0, SD 6.0 mm Hg). The absolute differences between the test and reference DBPs were <5, <10, and <15 mm Hg in 75.5% (197/261), 93.9% (245/261), and 97.3% (254/261) of measurements, respectively. The secondary analysis showed that after 4 weeks, the differences between SBP and DBP were 0.1 (SD 8.8) and −2.4 (SD 7.6) mm Hg, respectively.Conclusions:AlwaysBP exhibited acceptable accuracy in SBP and DBP measurement compared with the standard measurement method, according to the Association for the Advancement of Medical Instrumentation/European Society of Hypertension/International Organization for Standardization protocol criteria. However, further validation studies with a specific validation protocol designed for cuffless blood pressure measuring devices are required to assess clinical accuracy. This technology can be easily applied in everyday life and may improve the general population’s awareness of hypertension, thus helping to control it.

A series of bis(4-alkoxyphenyl) viologen bis(triflimide) salts with alkoxy chains of different lengths were synthesized by the metathesis reaction of respective bis(4-alkoxyphenyl) viologen dichloride salts, which were in turn prepared from the reaction of Zincke salt with the corresponding 4-n-alkoxyanilines, with lithium triflimide in methanol. Their chemical structures were characterized by 1H and 13C nuclear magnetic resonance spectra and elemental analysis. Their thermotropic liquid-crystalline (LC) properties were examined by differential scanning calorimetry, polarizing optical microscopy, and variable temperature X-ray diffraction. Salts with short length alkoxy chains had crystal-to-liquid transitions. Salts of intermediate length alkoxy chains showed both crystal-to-smectic A (SmA) transitions, Tms, and SmA-to-isotropic transitions, Tis. Those with longer length of alkoxy chains had relatively low Tms at which they formed the SmA phases that persisted up to the decomposition at high temperatures. As expected, all of them had excellent thermal stabilities in the temperature range of 330–370 °C. Their light-emitting properties in methanol were also included.

A series of viologens containing 4-n-alkylbenzenesulfonates were synthesized by the metathesis reaction of 4-n-alkylbenzenesulfonic acids or sodium 4-n-alkylbezenesulfonates with the respective viologen dibromide in alcohols. Their chemical structures were characterized by Fourier Transform Infrared, 1H and 13C Nuclear Magnetic Resonance spectra and elemental analysis. Their thermotropic liquid-crystalline (LC) properties were examined by differential scanning calorimetry and polarizing optical microscopy. They formed LC phases above their melting transitions and showed isotropic transitions. As expected, all the viologen salts had excellent stabilities in the temperature range of 278–295 °C as determined by thermogravimetric analysis.

The purpose of this study is to classify EEG data on imagined speech in a single trial. We recorded EEG data while five subjects imagined different vowels, /a/, /e/, /i/, /o/, and /u/. We divided each single trial dataset into thirty segments and extracted features (mean, variance, standard deviation, and skewness) from all segments. To reduce the dimension of the feature vector, we applied a feature selection algorithm based on the sparse regression model. These features were classified using a support vector machine with a radial basis function kernel, an extreme learning machine, and two variants of an extreme learning machine with different kernels. Because each single trial consisted of thirty segments, our algorithm decided the label of the single trial by selecting the most frequent output among the outputs of the thirty segments. As a result, we observed that the extreme learning machine and its variants achieved better classification rates than the support vector machine with a radial basis function kernel and linear discrimination analysis. Thus, our results suggested that EEG responses to imagined speech could be successfully classified in a single trial using an extreme learning machine with a radial basis function and linear kernel. This study with classification of imagined speech might contribute to the development of silent speech BCI systems.

Memristive synapses, the most promising passive devices for synaptic interconnections in artificial neural networks, are the driving force behind recent research on hardware neural networks. Despite significant efforts to utilize memristive synapses, progress to date has only shown the possibility of building a neural network system that can classify simple image patterns. In this article, we report a high-density cross-point memristive synapse array with improved synaptic characteristics. The proposed PCMO-based memristive synapse exhibits the necessary gradual and symmetrical conductance changes and has been successfully adapted to a neural network system. The system learns and later recognizes, the human thought pattern corresponding to three vowels, i.e. /a /, /i / and /u/, using electroencephalography signals generated while a subject imagines speaking vowels. Our successful demonstration of a neural network system for EEG pattern recognition is likely to intrigue many researchers and stimulate a new research direction.

Human casualties caused by industrial accidents pose a serious threat to corporate management due to the continual strengthening of safety laws as well as changes in the public’s awareness of corporate social responsibility. Accordingly, companies are raising safety awareness among employees by regularly conducting on-site safety activities and training to prevent industrial accidents. However, the safety activities, education, and training of many companies are not carried out voluntarily or in practice by their employees, but mostly through formal implementation. To break away from these customary and passive behaviors and establish a mature safety culture, it is crucial to strengthen the execution capacity of safety management in the field; to this end, we plan to utilize the safety practice index (SPI). The safety practice index (SPI), which quantitatively represents the degree of safety practice, is necessary to increase the effectiveness of safety management for the purpose of preventing accidents. In this study, the correlation was verified by comparing the SPI calculated based on the 2018 and 2019 risk management and the safety activity results of manufacturer A with the reported safety accidents. It was also effective in improving the SPI and reducing safety accidents in 2020 by supplementing the weaknesses of the SPI in 2018 and 2019. According to the results of this study, SPI can be used as an effective indicator for safety accident prevention activities by supplementing weaknesses with strengths through strengthening leadership and safety policies, such as classifying and managing the safety management level of a specific period or department.