The electrochemical impedance spectroscopy, the cyclic voltammetry, and the constant power charge/discharge methods have been applied to establish the electrochemical characteristics for the electrical double–layer capacitor consisting of the 1 M (C2H5)3CH3NBF4 electrolyte in acetonitrile. The microporous carbon electrodes prepared from D-(+)-glucose by the hydrothermal carbonization method and subsequent pyrolysis and carbon dioxide activation steps. The total Brunauer-Emmett-Teller specific surface area (SBET ≤ 1539 m2 g−1), micropore surface area (Smicro ≤ 1534 m2 g−1), total pore volume (Vtot ≤ 0.694 cm3 g−1) and the size distribution of the pores, obtained from the N2 sorption data and using the non–local density functional theory, have been correlated with the electrochemical characteristics for electrical double–layer capacitors as the region of ideal polarizability (ΔE ≤ 3.0 V), characteristic time constant (0.34 s) and the high series capacitance (126 F g−1), dependent on the carbon activation conditions, have been calculated.

No abstract

We present CloudScan; an invoice analysis system that requires zero configuration or upfront annotation.In contrast to previous work, CloudScan does not rely on templates of invoice layout, instead it learns a single global model of invoices that naturally generalizes to unseen invoice layouts.The model is trained using data automatically extracted from end-user provided feedback. This automatic training data extraction removes the requirement for users to annotate the data precisely.We describe a recurrent neural network model that can capture long range context and compare it to a baseline logistic regression model corresponding to the current CloudScan production system.We train and evaluate the system on 8 important fields using a dataset of 326,471 invoices. The recurrent neural network and baseline model achieve 0.891 and 0.887 average F1 scores respectively on seen invoice layouts. For the harder task of unseen invoice layouts, the recurrent neural network model outperforms the baseline with 0.840 average F1 compared to 0.788.

No abstract

No abstract