Application of cluster repeated mini-batch training method to classify electroencephalography for grab and lift tasks.

Modern deep neural network training is based on mini-batch stochastic gradient optimization. While using extensive mini-batches improves the computational parallelism, the small batch training proved that it delivers improved generalization performance and allows a significantly smaller memory, which might also improve machine throughput. However, mini-batch size and characteristics, a key factor for training deep neural networks, has not been sufficiently investigated in training correlated group features and looping with highly complex ones. In addition, the unsupervised learning method clusters the data into different groups with similar properties to make the training process more stable and faster. Then, the supervised learning algorithm was applied with the cluster repeated mini-batch training (CRMT) methods. The CRMT algorithm changed the random minibatch characteristics in the training step into training in order of clusters. Specifically, the self-organizing maps (SOM) were used to cluster the information into n groups based on the dataset's labels Then, neural network models (ANN) were trained with each cluster using the cluster repeated mini-batch training method. Experiments conducted on EEG datasets demonstrate the survey of the proposed method and optimize it. In addition, the results in our research outperform other state-of-the-art methods.

Choline chloride-based deep eutectic solvents as effective electrolytes for dye-sensitized solar cells.

Electrolytes for dye-sensitized solar cells remain a challenge for large-scale production and commercialization, hindering the wide application of solar cells. We have developed two new electrolyte-based deep eutectic solvents using a mixture of choline chloride with urea and with ethylene glycol for dye-sensitized solar cells. The prominent features of the two deep eutectic solvent electrolytes are simple preparation for large-scale production with inexpensive, available, and nontoxic starting materials and biodegradability. The solar cell devices proceeded in a safe manner as the two deep eutectic solvents afforded low-cost technology and comparative conversion efficiency to a popular ionic liquid, namely 1-ethyl-3-methylimidazolium tetracyanoborate. Results showed that devices with choline chloride and urea electrolyte exhibited improved open circuit voltage values (V OC), while the ones with choline chloride and ethylene glycol showed an increase in the short circuit current (I sc). Characterization of the devices by electrochemical impedance spectroscopy helped explain the effects of their molecular structures on the enhancement of either V OC or I sc values. These new solvents expand the electrolyte choices for designing dye-sensitized solar cells, especially for the purpose of using low-cost and eco-friendly materials for massive production.