Proteins are linear chain biomolecules composed of 20 different amino acids which form secondary structures such as helixes and loops [8]. Here, we use deep recurrent memory networks and deep convectional networks for predicting secondary structure annotations on sequences from the Uniprot database. We compare different network architectures and memory models, and discuss possible improvements....

nano-sized batio3 powders with particular nb concentrations were prepared by rotary- hydrothermal (rh) method. hydrothermal method was used at 180 °c for 5 hours with new ti pressure and the teflon vessel was rotated at a speed of 160 rpm during the hydrothermal reaction. new hydrothermal method was used instead of previous solid state reaction for the system batio3±nb2o3 in high temperature to...

A compact packaging module for direct liquid cooling of roomtemperature quantum cascade lasers is implemented. The light was coupled out of the hermetically sealed package through a mid-infrared fibre epoxy-bonded to the laser. The threshold current reduces by 10%, compared to convectional substrate-side cooled lasers when using low boiling temperature (boiling point (b.p.)1⁄4 34 C) 3M HFE7000 ...

Image compression technique is used to reduce the number of its required in representing image, which helps to reduce the storage space and transmission cost. In the present research work back propagation neural network training algorithm has been used. Back propagation neural network algorithm helps to increase the performance of the system and to decrease the convergence time for the training...