The gain spectrum of an Erbium Doped Fiber Amplifier (EDFA) has a peak centered at 1532nm and a broad peak with relatively low gain centered at 1550nm. In many applications like soliton based systems which makes use of EDFA repeaters and Dense Wavelength Division Multiplexing (DWDM) systems where EDFA is used for amplifying a large number of wavelengths, gain fluctuations in EDFA has to be confined within specified limits over a wide span of wavelengths. Many methods of gain stabilization in EDFA has already been proposed in the recent past. In our work, we propose a novel method for gain contouring and output power stabilization in Erbium Doped Fiber Amplifiers. The amplifier with gain control is designed and simulated. The flattening of gain spectrum of EDFA is achieved by photonic switching using Optical Add Drop Multiplexers (OADM) and Fiber Bragg Gratings (FBG). The stabilization of gain and output power of EDFA is also experimentally verified. In the proposed feedforward technique, the output power stabilization is achieved by proper selection of modulator parameters.

Radio over fiber (RoF) systems use a large number of base stations (BSs) and a number of central stations (CSs), which are interlinked together to form the network. RoF systems use multiple wavelengths for communication between CSs or between CSs and BSs to facilitate the huge amount of data traffic due to the multiple services for a large number of users. When erbium-doped fiber amplifiers (EDFAs) are used as amplifiers in such wavelength-division multiplexed systems, the nonuniform gain spectrum of EDFAs causes instability to some of the channels while providing faithful amplification to other channels. To avoid this inconsistency, the gain spectrum of the amplifier needs to be uniform along the whole usable range of wavelengths. A gain contouring technique is proposed to provide uniform gain to all channels irrespective of wavelength. Optical add/drop multiplexers (OADMs) and different lengths of erbium-doped fibers are used to create such a gain contouring mechanism in the optical domain itself. The effect of a cascade of nonuniform gain amplifiers is studied, and the proposed system mitigates the adverse effects caused due to nonuniform gain-induced channel instability effectively.

Evolution of artificial intelligence has significant impact on medical field, especially in disease classification. Lung disease often referred as respiratory infections, sound severe threat to human life. Early interpretation is very much essential for patient survival. Deep network models, especially the technique of ensemble aid the practitioners in automating disease prediction process. In this work, various ensemble strategies such as average, weighted average and stacked ensemble model for four class lung disease classification are proposed. Deep convolutional neural network (CNN) models namely Resnet101, Inception V3 and Mobilenet V2 are used as first level or base models for the ensemble. To study the potency of different meta learners on ensemble stacking, five machine learning models namely Logistic Regression, Support Vector Machine (SVM), Linear Discriminant Analysis, Decision Tree and Naive Bayes are opted as the meta learner models. Here, QaTa-COV 19 dataset is utilized which comprises of 21165 chest x-ray images under four classes - covid19, lung opacity, healthy and viral pneumonia. The experimental results demonstrated that proposed average, weighted average and deep stacked ensemble models outperform, the base predictors and among best, stacked ensemble with support vector machine as meta learner with an overall model accuracy of 98.6%. The proposed model could reduce the variations in heterogeneous base model predictions and resulted in a highly efficient stacking ensemble model with better generalization capability for lung disease prediction.