Modeling and optimization of tannase production with Triphala in packed bed reactor by response surface methodology, genetic algorithm, and artificial neural network.

In this research, optimization of the production medium to enhance tannase production by Bacillus gottheilii M2S2 in laboratory-scale packed bed reactor was studied. Amount of substrate Triphala, moisture content, aeration rate, and fermentation period was chosen for optimization study. During one variable at a time optimization, the highest tannase activity of 0.226 U/gds was shown with Triphala as a substrate at the fermentation period of 32 h. Furthermore, the optimum conditions predicted by response surface methodology (RSM) and genetic algorithm (GA) were found to be 11.532 g of substrate Triphala, 47.071% of the moisture content, and 1.188 L/min of an aeration rate with uppermost tannase activity of 0.262 U/gds. In addition, the single hidden layer feedforward neural network (SLFNN) and the radial basis function neural network (RBFNN) of an artificial neural network (ANN) were adopted to compare the prediction performances of the RSM and GA. It revealed that the ANN models (SLFNN, R 2 = 0.9930; and RBFNN, R 2 = 0.9949) were better predictors than the RSM (R 2 = 0.9864). Finally, the validation experiment exhibited 0.265 U/gds of tannase activity at the optimized conditions, which is an 11-fold increase compared to unoptimized media in shake flask.

Drug Resistance Pattern of MTB Isolates from PTB Patients.

Background. TB is a global pandemic disease. All TB control programs were not successful due to the emergence of multidrug resistance in M. tuberculosis strains. Objective of the present study was to detect the rate of MDR-MTB in this part of India. Methods. One hundred and thirty clinical MTB strains isolated from patients on treatment and confirmed as MTB by MPT64 antigen detection were tested for drug susceptibility against Streptomycin, INH, Rifampicin, and Ethambutol by MBBact automated system. Result. Thirty-two were MDRs (25.61%). 31.2%, 28%, 17.6%, and 21.6% were resistant to INH, RIF, Ethambutol, and Streptomycin, respectively. Resistance to either INH or Rifampicin was 20.8% and 13.88%, respectively. Combined INH and Rifampicin resistance was seen in 18.05% isolates. Conclusion. Drug resistance rate is high in patients treated previously and who have been irregular on treatment.

Evaluation of effectiveness of wavelet based denoising schemes using ANN and SVM for bearing condition classification.

The wavelet based denoising has proven its ability to denoise the bearing vibration signals by improving the signal-to-noise ratio (SNR) and reducing the root-mean-square error (RMSE). In this paper seven wavelet based denoising schemes have been evaluated based on the performance of the Artificial Neural Network (ANN) and the Support Vector Machine (SVM), for the bearing condition classification. The work consists of two parts, the first part in which a synthetic signal simulating the defective bearing vibration signal with Gaussian noise was subjected to these denoising schemes. The best scheme based on the SNR and the RMSE was identified. In the second part, the vibration signals collected from a customized Rolling Element Bearing (REB) test rig for four bearing conditions were subjected to these denoising schemes. Several time and frequency domain features were extracted from the denoised signals, out of which a few sensitive features were selected using the Fisher's Criterion (FC). Extracted features were used to train and test the ANN and the SVM. The best denoising scheme identified, based on the classification performances of the ANN and the SVM, was found to be the same as the one obtained using the synthetic signal.