Word embedding techniques have been proposed in the literature to analyze and determine the sentiments expressed in various textual documents such as social media posts, online product reviews, and so forth. However, it is difficult to capture the entire gamut of intricate inter-dependencies among words in the textual documents using a specific word embedding technique. In this article, we aim to address this issue by proposing a computation-efficient stacking ensemble based sentiment analysis framework using multiple word embeddings. The proposed framework uses a combination of three distinct word embeddings generated by three different state of the art word embedding techniques, namely, Word2Vec, GloVe, and BERT for performing the sentiment analysis task. It uses an explicitly trained Word2Vec model to generate the first set of 200-dimensional word embedding. Similarly, pre-trained GloVe and BERT models are used to generate the other two sets of 200-dimensional and a 768-dimensional word embeddings, respectively. These three distinct word embedding sets are then used to train a heterogeneous stacking ensemble based classifier model comprising LSTM, GRU, and Bi-GRU based base-level classifiers, and a LSTM based meta-level classifier. Experimental results on four different datasets, 530

Nowadays lots of work is going to be done on the field of image fusion and also used in various application such as medical imaging and multi spectra sensor image fusing etc. For fusing the image various techniques has been proposed by different previous works such as wavelet transform, IHS (Intensity, Hue and Saturation) and Principal Component Analysis (PCA), based methods etc. In this paper literature of the image fusion is discussed with implementation using wavelet transform used for the specific application as in the image restoration field. Using Image fusion may improve the perceptual quality of the restored images. Usually image deblurring methods are used at the front end for restoration and then image fusion is used for improving the visual quality. Paper uses three de-blurring technique to blindly restoring the image then use statistical parameters for adopting the best fused images out of various hybrid fusion results. Performance is tested on images with distinct features.

No abstract