In this demo paper, we present the new module of our HealthDist system that performs contact tracing in a privacy-preserving manner and considers the COVID-19 exposure risk. This is achieved by answering a new spatio-temporal query, dubbed ST-Aggregate Join, which calculates the COVID-19 exposure risk of an individual on their devices. It utilizes a special-purpose access structure to record the trajectories of users on their devices and optimize the ST-Aggregate Join processing. We demonstrate interactively using a smartphone application how our system can provide effective contact tracing within a university campus. We also illustrate how our new module is working through an intuitive web interface that shows the exposure risk of a person by coloring the trajectory of the infected person and the person(s) in high risk in a preloaded real dataset.

Since the onset of the Covid-19 pandemic, an over-whelming amount of related data has been released. In an attempt to gain insights from that data, multiple public data visualization dashboards have been deployed. Differently from such dashboards, which mainly support basic data filtering and visualization of separate datasets, in this work, we propose CovidLens, which: 1) integrates various Covid-19 indicators and is centred around the Google Community Mobility Report dataset, 2) supports similarity search for finding similar and correlated patterns and trends across the integrated datasets, and 3) automatically recommends insightful visualizations that unlocks valuable insights into the pandemic effects. To that end, we will be presenting the employed dataset, together with the design, implementation, and multiple usage scenarios of our proposed CovidLens.

Driven by the increasing gap between the exponential growth of data and the limited human ability to comprehend them, recently, a novel interactive data exploration approach called Explore-by-Examples has generated a lot of attention for its capabilities to bridge this gap and to help the user obtain high-value content from the data that are often hidden using the traditional search methods. However, despite their effectiveness in extracting valuable information, existing Explore-by-Examples systems focus solely on structured data, which represents a small portion of the data available today. In this work, we present a novel data exploration framework, namely ExNav (Exploration Navigator), which enables the user to effortlessly explore the world of unstructured data for insights that are often unreachable from traditional search and exploration methods. In particular, we exploit the space of advanced machine learning, data embedding, and active learning algorithms to design effective exploration and space pruning approaches tailored for unstructured datasets. Our experimental evaluation using multiple real-world unstructured datasets (i.e., text, image, and graph) show that ExNav can reduce users' effort by up to 9x while still achieving the same accuracy as the state-of-the-art alternative. Moreover, ExNav is also able to identify relevant data items that are often undetectable by current techniques, even when a large number of samples are explored.

Existing visualization recommendation approaches introduced an overwhelmingly large number of utility functions (UFs) to rank the visualizations (i.e., views). In order to discover the ideal UF and their tunable parameters that are most suited for a particular analysis context, recent works have proposed Interactive View Recommendation (IVR). IVR identifies the ideal UF by learning from the interactions with the user during the analysis process. We claim that the user is usually unable to provide an accurate real number between 0 and 1, indicating the view interestingness, and in this work, propose three alternative feedback types: binary, Likert scale, and pairwise comparison. We further developed ranking algorithms for the three feedback types. Finally, we propose different example selection strategies, and experimentally evaluate them on the three feedback types. We found that uncertainty-based and hybrid-based strategies usually outperforms the random strategy in terms of recommendation accuracy across all feedback types, while the interestingness-based strategy usually performs worse than the random strategy.

Existing view recommendation approaches proposed a variety of utility functions in selecting useful views. Even though each utility function might be suitable for specific scenarios, identifying the most appropriate ones, along with their tunable parameters, which represent the user's intention during an exploration, is a challenge for both expert and non-expert users. This paper presents an attempt towards interactive view recommendation that automatically discovers the utility function composition during an exploration that best matches the user's intentions and exploration task.

There is more to images than their objective physical content: for example, advertisements are created to persuade a viewer to take a certain action. We propose the novel problem of automatic advertisement understanding. To enable research on this problem, we create two datasets: an image dataset of 64,832 image ads, and a video dataset of 3,477 ads. Our data contains rich annotations encompassing the topic and sentiment of the ads, questions and answers describing what actions the viewer is prompted to take and the reasoning that the ad presents to persuade the viewer (What should I do according to this ad, and why should I do it?), and symbolic references ads make (e.g. a dove symbolizes peace). We also analyze the most common persuasive strategies ads use, and the capabilities that computer vision systems should have to understand these strategies. We present baseline classification results for several prediction tasks, including automatically answering questions about the messages of the ads.

With the wide application of OFDM technology, the security of OFDM system is becoming more and more important. In this paper, we propose a secrecy transmission scheme with phase rotation and sub-carrier mapping based on chaos sequences. The scheme employs the characteristics of pseudorandom and sensitivity to initial conditions of chaos sequences. We have studied on the observed signal features, computational complexity and possible key number, as well as error-correcting performance of proposed scheme. It's shown by simulation results and analysis that the scheme is able to effectively encrypt the information and enhance the randomness of output signals. The malicious receiver cannot estimate the message through the statistic characteristics of received signals, which ensure the aim of secure communication.