To have an objective depression diagnosis, numerous studies based on machine learning and deep learning using electroencephalogram (EEG) have been conducted. Most studies depend on one-dimensional raw data and required fine feature extraction. To solve this problem, in the EEG visualization research field, short-time Fourier transform (STFT), wavelet, and coherence commonly used as method s for transferring EEG data to 2D images. However, we devised a new way from the concept that EEG’s asymmetry was considered one of the major biomarkers of depression. This study proposes a deep-asymmetry methodology that converts the EEG’s asymmetry feature into a matrix image and uses it as input to a convolutional neural network. The asymmetry matrix image in the alpha band achieved 98.85% accuracy and outperformed most of the methods presented in previous studies. This study indicates that the proposed method can be an effective tool for pre-screening major depressive disorder patients.

ObjectivesBreast cancer is the second most common cancer among Korean women. Because breast cancer is strongly associated with negative emotional and physical changes, early detection and treatment of breast cancer are very important. As a supporting tool for classifying breast cancer, we tried to identify the best meta-learner model in a stacking ensemble when the same machine learning models for the base learner and meta-learner are used.MethodsWe used machine learning models, such as the gradient boosted model, distributed random forest, generalized linear model, and deep neural network in a stacking ensemble. These models were used to construct a base learner, and each of them was used as a meta-learner again. Then, we compared the performance of machine learning models in the meta-learner to determine the best meta-learner model in the stacking ensemble.ResultsExperimental results showed that using the GBM as a meta-learner led to higher accuracy than that achieved with any other model for breast cancer data and using the GLM as a meta learner led to low root-mean-squared error for both sets of breast cancer data.ConclusionsWe compared the performance of every meta-learner model in a stacking ensemble as a supporting tool for classifying breast cancer. The study showed that using specific models as a metalearner resulted in better performance than single classifiers, and using GBM and GLM as a meta-learner is appropriate as a supporting tool for classifying breast cancer data.

be employed as transparent TFTs. [13][14][15] Recently, rapid advance in transparent electronic devices for transparent TV, mobile, wearable, and even VR devices require the development of transparent TFTs and their high-performance channel layers. Moreover, AOS-based TFTs could meet the requirement of the next-generation organic light emitting diode TV, such as ultra-high frame rate, larger size, and higher resolution, due to their high mobility. [16,17] Among various metal oxide semiconductor channel materials, multicomponent metal oxide semiconductors based on the In and Zn cations matrix are considered as promising candidates for channel materials for transparent TFTs, since they have inherent merits, such as high mobility, large area uniformity from their amorphous structure, and compatibility with various processing methods. [18][19][20][21][22][23] For the realization of highperformance and highly stable oxide semiconductor-based TFTs, the control of atomic ratio in the metal oxide semiconductor channel is a key factor. For this purpose, there have been a lot of research efforts on the compositional control or doping process of the oxide semiconductor channel layer. [24][25][26][27][28][29][30][31] Olziersky et al. have reported on the role of composition of InGaZnO channel on the performance of TFT devices. [31] They referred that the InGaZnO TFTs showed improved performance and worse stability characteristics, when the In/Ga ratio is higher according to the electrical resistivity of channel films. The In cations generally play a role as a mobility enhancer, due to the spheric s orbital of the indium oxide. The TFTs with indium oxide matrix showed high mobility of 10-30 cm 2 V −1 s −1 and large current at on-state, becasue the largely overlapped s orbital of In 2 O 3 enhanced the conductivity of the electrons. [32][33][34] However, the poor stability issue of TFTs with large indium contents-channel induced by the oxygen vacancies still remain a critical drawback. [35] Several elements with high bonding strength with oxygen, such as, gallium (Ga), zirconium (Zr), hafnium (Hf), and yttrium (Y), are adopted in the indium oxide channel material as an oxygen binder and a stabilizer of the channel layer. [36][37][38][39][40][41][42][43][44][45][46][47][48][49][50][51][52] Although several elements have been employed as stabilizer in oxide semiconductor channel-based TFTs, investigation of the stabilizing element in oxide semiconductor is still lacking. In particular, The Hf-doped indium zinc tin oxide (Hf:InZnSnO) channel for high performance and stable transparent thin film transistors (TFTs) is developed by using a simultaneous cosputtering of InZnSnO and HfO 2 targets. The effects of In and Hf composition in Hf:InZnSnO channel on the performance and stability under bias stress for the Hf:InZnSnO channel-based TFTs are investigated. Herein, the In cations enhance the electrical properties, while the Hf cations reduce the oxygen vacancies in the Hf:InZnSnO channel layer. Adjusting the atomic ratio of In of the...

We demonstrated the characteristics of a transparent, flexible silver nanowire-embedded silk fibroin substrate that can be used as a flexible and biocompatible electrode for wearable electronics.