We demonstrate SHEVA, a System for Hypothesis Exploration with Visual Analytics. SHEVA adopts an Exploratory Data Analysis (EDA) approach to discovering statistically-sound insights from large datasets. The system addresses three longstanding challenges in Multiple Hypothesis Testing: (i) the likelihood of rejecting the null hypothesis by chance, (ii) the pitfall of not being representative of the input data, and (iii) the ability to navigate among many data regions while preserving the user's train of thought. To address (i) & (ii), SHEVA implements significance adjustment methods that account for data-informed properties such as coverage and novelty. To address (iii), SHEVA proposes to guide users by recommending one-sample and two-sample hypotheses in a stepwise fashion following a data hierarchy. Users may choose from a collection of pre-trained hypothesis exploration policies and let SHEVA guide them through the most significant hypotheses in the data, or intervene to override suggested hypotheses. Furthermore, SHEVA relies on data-to-visual element mappings to convey hypothesis testing results in an interpretable fashion, and allows hypothesis pipelines to be stored and retrieved later to be tested on new datasets.

The achievement of image retrieval systems severally depends on the way the data is represented. This paper proposes a new image representation through an intelligent mechanism via neural networks for semantic-gap and dimensionality reduction. The goal of the multilayer neural network is to represent high-level semantic concepts and knowledge through a pre-defined set of images. As a consequence of this low-level into high-level feature transformation there is a semantic gap reduction between human perception and automatic feature extraction. The experimental results show the effective performance of the proposed technique.

Low-level attributes such as color, shape and texture generally fail in describing the high-level semantic concepts. This work presents, through the formation of a high- level characteristics vector, the representation of the subjective knowledge used by humans for the verification of which aspects are most important for image characterization. Such vector will be formed by using the Artificial Intelligence techniques, more specifically the Artificial Neural Networks, which will generate, through predefined examples, the low-level characteristics forming the new high- level vector, making image retrieval possible. Finally, some tests results are presented and discussed to demonstrate the potentiality of the method.