An automated method for accurate prediction of seizures is critical to enhance the quality of epileptic patients While numerous existing studies develop models and methods to identify an efficient feature selection and classification of electroencephalograph (EEG) data, recent studies emphasize on the development of ensemble learning methods to efficiently classify EEG signals in effective detection of epileptic seizures. Since EEG signals are non-stationary, traditional machine learning approaches may not suffice in effective identification of epileptic seizures. The paper proposes a hybrid ensemble learning framework that systematically combines pre-processing methods with ensemble machine learning algorithms. Specifically, principal component analysis (PCA) or t-distributed stochastic neighbor embedding (t-SNE) combined along k-means clustering followed by ensemble learning such as extreme gradient boosting algorithms (XGBoost) or random forest is considered. Selection of ensemble learning methods is justified by comparing the mean average precision score with well known methodologies in epileptic seizure detection domain when applied to real data set. The proposed hybrid framework is also compared with other simple supervised machine learning algorithms with training set of varying size. Results suggested that the proposed approach achieves significant improvement in accuracy compared with other algorithms and suggests stability in classification accuracy even with small sized data.

Advancements in sensors and image acquisition devices lead to tremendous increase in creation of unlabeled database of images, and traditional image retrieval approaches are inefficient in retrieving semantic images. Neural network is emerging as popular method to solve most of the state-of-the-art problems in filling the gap between low level features and high level semantics. Convolution neural network (CNN) is a category of neural network which automatically extracts the important features without any human intervention, with considerably reduced set of parameters. In this paper, a model is generated using CNN (VGG-16) architecture which combines convolution and max pooling layers at different levels using effective regularization and transfer learning with data augmentation. The effectiveness of proposed model is demonstrated on benchmarking Caltech 101 and 256 datasets. The results obtained have proven the capacity of model in understanding high level semantics and outperformed several contemporary techniques.

<p>Localizing and recognizing arbitrarily oriented text in natural scene images is the biggest challenge. It is because scene texts are often erratic in shapes. This paper presents a simple and effective graph representational algorithm for detecting arbitrary-oriented text location to smoothen the text recognition process because of its high impact and simplicity of representation. An arbitrarily oriented text can be horizontal, vertical, perspective, curved (diagonal/off-diagonal), or even a combination. As a pre-processing step, image enhancement is performed in the frequency domain to improve the representation of images that are invariant to intensity. It is necessary to draw bounding boxes for each candidate character in the scene images to extract text regions. This step is carried out by utilizing the advantage of the region-based approach called maximally stable extremal regions. A typical problem with curved text localization is that non-text objects may occur within localized text regions. Our method is the first in the literature that searches for dominating sets to solve this problem. This dominating set method outperforms several traditional methods, including deep learning methods used for arbitrary text localization, on challenging datasets like 13^th international conference on document analysis and recognition (ICDAR 2015), multi-script robust reading competition (MRRC), CurvedText 80 (CUTE80), and arbitrary text (ArT).</p>