Search

This paper present an initial effort of collaborating hybrid bacteria foraging oriented particle swarm optimization with linear quadratic regulator (LQR) design for automatic generation control (AGC) of power delivery system having power generation through hydro turbines in interconnected control areas to match the frequency variations as well as tie-power interchange to the well planned value after sudden load disturbance in interconnected system. The enactment of LQR highly depend upon the selection of state cost weighing matrix (Q) and control cost weighting matrix (R) in order to achieve the best control efforts. However, most of the researchers assume the structure of Q and R to be an identity and hence the LQR control action was restricted within certain range. Hence, an early attempt is made to compute the structure of Q and R for LQR through hybrid bacteria foraging oriented PSO for AGC of hydro system and application results are computed for various cases considering error evaluated and graphical AGC responses for step load alteration, influence of AGC non-linearities on the output of AGC, parametric alterations and random load alteration to show the efficacy as well as robustness of the present control design. [ABSTRACT FROM AUTHOR]

• 3 layer neural networks outperform other ML algorithms in automated assessments. • In subjective assignments, deep neural networks can improve score prediction. • Word embeddings and linguistic feature results in more precise text mining models. • Extraction and selection of appropriate features can improve results. Machine learning (ML) has recently gained popularity in a variety of domains for automating tasks. This has also been used in the evaluation of student responses/ assignments. This paper presents a qualitatively enhanced methodology for automated score prediction of subjective assignments. To consider all the major aspects of a human grader, 21 linguistic features related to syntactical, grammatical, sentimental, and readability are analyzed from the assignments. This study makes use of the ASAP competition dataset from Kaggle. The evaluation metric used is Quadratic Weighted Kappa (QWK), which measures the agreement between the human graded score and the predicted score. The effect of appropriate feature selection has been observed using Mutual Information Regression. Four ML algorithms are investigated on identified linguistic features. 3 Layer Neural Network with feature selection performed well among all chosen ML algorithms with average QWK of 0.678. To include the benefits of deep learning, a new hybrid model (LF-BiLSTM-att-FS) is proposed that combines a higher level deep neural network (DNN) with the selected features. Pre-trained Glove embedding is used to include contextual information of the text. The proposed model results demonstrated an improvement in overall accuracy, with an average QWK value of 0.768. [ABSTRACT FROM AUTHOR]

In this paper a hybrid approach for image encryption is proposed by combining AES, a standard cryptography algorithm, along with splitting and block permutation. A standard image (Lena) is taken as an input and to enhance the security, the image is divided into 4*4 matrix followed by block permutation before encryption of the image with AES. Comparison of various parameters with and without block permutation confirms the superiority of the proposed method in terms of better results after using splitting and permutation functions. [ABSTRACT FROM AUTHOR]