ABSTRACT The rapid development of smart power marketing demands the building of very accurate and efficient predictive models to optimize customer segmentation, demand forecasting, and fraud detection. Traditional classification techniques are generally incapable of dealing with large‐scale, complex energy consumption data sets due to redundant attributes, class imbalance, and overfitting issues. In order to solve these problems, the paper suggests applying the Optimized C5.0 Decision Tree with Entropy‐Based Feature Selection for smart power trading to a higher level. The model proposed not only includes the traditional decision tree classification but also the entropy‐based feature selection, pruning, and advanced techniques in data preprocessing like normalization, imputation of missing data, and Synthetic Minority Over‐Sampling Technique for class imbalance and robustness of classification. The first step in the process of building a decision tree is to find out the entropy, which indicates how uncertain the dataset is. The Information Gain of each attribute is then calculated, and the one with the highest IG is taken as the root node. The data is partitioned repeatedly until a stop criterion is reached, which is where the condition to avoid the model being too complex and thus overfitting comes in. Along with the use of pruning techniques such as Reduced Error Pruning and Gini Index‐based feature scoring, the optimum classification accuracy is achieved. The results of the performance evaluation show that the Optimized C5.0 Decision Tree is better than classical classifiers.

Recent work on scene classification still makes use of generic CNN features in a rudimentary manner. In this paper, we present a novel pipeline built upon deep CNN features to harvest discriminative visual objects and parts for scene classification. We first use a region proposal technique to generate a set of high-quality patches potentially containing objects, and apply a pre-trained CNN to extract generic deep features from these patches. Then we perform both unsupervised and weakly supervised learning to screen these patches and discover discriminative ones representing category-specific objects and parts. We further apply discriminative clustering enhanced with local CNN fine-tuning to aggregate similar objects and parts into groups, called meta objects. A scene image representation is constructed by pooling the feature response maps of all the learned meta objects at multiple spatial scales. We have confirmed that the scene image representation obtained using this new pipeline is capable of delivering state-of-the-art performance on two popular scene benchmark datasets, MIT Indoor 67 [22] and Sun397 [31].

Line drawings and digital arts appear everywhere, from simple icons and logos to cartoons, maps, and illustrations. We define art patterns as the subset of line drawings and digital arts that are comprised of repeated elements. There exist textures that share characteristics with art patterns. Examples of such textures include piled discrete elements with curved contours. Inspired by recent success of exemplar-based texture synthesis, in this paper, we focus on synthesizing art patterns and textures with curvilinear features from exemplars, which we cast as a global optimization problem. Our energy function for this problem measures both the appearance similarity of color patterns and shape similarity of curvilinear features between an input exemplar and a synthesized image. We develop an overall expectation-maximization-style algorithm for minimizing this energy function. The shape similarity part of the energy is minimized through an innovative application of the level set method. We further generalize our energy function and optimization algorithm to multilayer pattern and texture synthesis. Our generalized optimization can effectively handle multiple layers and synthesize valid instances of interaction.

Recognizing the category of a visual object remains a challenging computer vision problem. In this paper we develop a novel deep learning method that facilitates example-based visual object category recognition. Our deep learning architecture consists of multiple stacked layers and computes an intermediate representation that can be fed to a nearest-neighbor classifier. This intermediate representation is discriminative and structure-preserving. It is also capable of extracting essential characteristics shared by objects in the same category while filtering out nonessential differences among them. Each layer in our model is a nonlinear mapping, whose parameters are learned through two sequential steps that are designed to achieve the aforementioned properties. The first step computes a discrete mapping called supervised Laplacian Eigenmap. The second step computes a continuous mapping from the discrete version through nonlinear regression. We have extensively tested our method and it achieves state-of-the-art recognition rates on a number of benchmark datasets.