Automated Discovery of Network Cameras in Heterogeneous Web Pages

Reduction in the cost of Network Cameras along with a rise in connectivity enables entities all around the world to deploy vast arrays of camera networks. Network cameras offer real-time visual data that can be used for studying traffic patterns, emergency response, security, and other applications. Although many sources of Network Camera data are available, collecting the data remains difficult due to variations in programming interface and website structures. Previous solutions rely on manually parsing the target website, taking many hours to complete. We create a general and automated solution for aggregating Network Camera data spread across thousands of uniquely structured web pages. We analyze heterogeneous web page structures and identify common characteristics among 73 sample Network Camera websites (each website has multiple web pages). These characteristics are then used to build an automated camera discovery module that crawls and aggregates Network Camera data. Our system successfully extracts 57,364 Network Cameras from 237,257 unique web pages.

KnowMore: an automated knowledge discovery tool for the FAIR SPARC datasets

Background: This manuscript provides the methods and outcomes of KnowMore, the Grand Prize winning automated knowledge discovery tool developed by our team during the 2021 NIH SPARC FAIR Data Codeathon. The National Institutes of Health Stimulating Peripheral Activity to Relieve Conditions (NIH SPARC) program generates rich datasets from neuromodulation researches, curated according to the Findable, Accessible, Interoperable, and Reusable (FAIR) SPARC data standards. Currently, the process of simultaneously comparing and analyzing multiple SPARC datasets is tedious because it requires investigating each dataset of interest individually and downloading all of them to conduct cross-analyses. It is crucial to enhance this process to enable rapid discoveries across SPARC datasets. Methods: To fill this need, we created KnowMore, a tool integrated into the SPARC Portal that only requires the user to select their datasets of interest to launch an automated discovery process. KnowMore uses several SPARC resources (Pennsieve, o²S²PARC, SciCrunch, protocols.io, Biolucida), data science methods, and machine learning algorithms in the back end to generate various visualizations in the front end intended to help the user identify potential similarities, differences, and relations across the datasets. These visualizations can lead to a new discovery, new hypothesis, or simply guide the user to the next logical step in their discovery process. Results: The outcome of this project is a SPARC portal-ready code architecture that helps researchers to use SPARC datasets more efficiently and fully leverages their FAIR characteristics. The tool has been built and documented such that more data analysis methods and visualization items could be easily added. Conclusions: The potential for automated discoveries from SPARC datasets is huge given the unique SPARC data ecosystem promoting FAIR data practices, and KnowMore has only demonstrated a small highlight of what could be achieved to speed up discoveries from SPARC datasets.

A Fresh Look at Zones and Octagons

Zones and Octagons are popular abstract domains for static program analysis. They enable the automated discovery of simple numerical relations that hold between pairs of program variables. Both domains are well understood mathematically but the detailed implementation of static analyses based on these domains poses many interesting algorithmic challenges. In this article, we study the two abstract domains, their implementation and use. Utilizing improved data structures and algorithms for the manipulation of graphs that represent difference-bound constraints, we present fast implementations of both abstract domains, built around a common infrastructure. We compare the performance of these implementations against alternative approaches offering the same precision. We quantify the differences in performance by measuring their speed and precision on standard benchmarks. We also assess, in the context of software verification, the extent to which the improved precision translates to better verification outcomes. Experiments demonstrate that our new implementations improve the state of the art for both Zones and Octagons significantly.

KnowMore: An Automated Knowledge Discovery Tool for the FAIR SPARC Datasets

This manuscript provides the methods and outcomes of KnowMore, the Grand Prize winning automated knowledge discovery tool developed by our team during the 2021 NIH SPARC FAIR Data Codeathon. The NIH SPARC program generates rich datasets from neuromodulation researches, curated according to the Findable, Accessible, Interoperable, and Reusable (FAIR) SPARC data standards. These datasets are publicly available through the SPARC Data Portal at sparc.science. Currently, the process of simultaneously comparing and analyzing multiple SPARC datasets is tedious because it requires investigating each dataset of interest individually and downloading all of them to conduct cross-analyses. It is crucial to enhance this process to enable rapid discoveries across SPARC datasets. To fill this need, we created KnowMore, a tool integrated into the SPARC Portal that only requires the user to select their datasets of interest to launch an automated discovery process. KnowMore uses several SPARC resources (Pennsieve, o2S2PARC, SciCrunch, protocols.io, Biolucida), data science methods, and Machine Learning algorithms in the back end to generate various visualizations in the front end intended to help the user identify potential similarities, differences, and relations across the datasets. These visualizations can lead to a new discovery, new hypothesis, or simply guide the user to the next logical step in their discovery process. The outcome of this project is a SPARC portal-ready code architecture that helps researchers to use SPARC datasets more efficiently and fully leverages their FAIR characteristics. The tool has been built and documented such that more data analysis methods and visualization items could be easily added. The potential for automated discoveries from SPARC datasets is huge given the unique SPARC data ecosystem promoting FAIR data practices, and KnowMore has only demonstrated a small highlight of what could be achieved to speed up discoveries from SPARC datasets.

Human–Machine Scientific Discovery

Humanity is facing existential, societal challenges related to food security, ecosystem conservation, antimicrobial resistance, etc, and Artificial Intelligence (AI) is already playing an important role in tackling these new challenges. Most current AI approaches are limited when it comes to ‘knowledge transfer’ with humans, i.e. it is difficult to incorporate existing human knowledge and also the output knowledge is not human comprehensible. In this chapter we demonstrate how a combination of comprehensible machine learning, text-mining and domain knowledge could enhance human-machine collaboration for the purpose of automated scientific discovery where humans and computers jointly develop and evaluate scientific theories. As a case study, we describe a combination of logic-based machine learning (which included human-encoded ecological background knowledge) and text-mining from scientific publications (to verify machine-learned hypotheses) for the purpose of automated discovery of ecological interaction networks (food-webs) to detect change in agricultural ecosystems using the Farm Scale Evaluations (FSEs) of genetically modified herbicide-tolerant (GMHT) crops dataset. The results included novel food-web hypotheses, some confirmed by subsequent experimental studies (e.g. DNA analysis) and published in scientific journals. These machine-leaned food-webs were also used as the basis of a recent study revealing resilience of agro-ecosystems to changes in farming management using GMHT crops.

A customisable pipeline for the semi-automated discovery of online activists and social campaigns on Twitter

Substantial research is available on detecting influencers on social media platforms. In contrast, comparatively few studies exists on the role of online activists, defined informally as users who actively participate in socially-minded online campaigns. Automatically discovering activists who can potentially be approached by organisations that promote social campaigns is important, but not easy, as they are typically active only locally, and, unlike influencers, they are not central to large social media networks. We make the hypothesis that such interesting users can be found on Twitter within temporally and spatially localised contexts. We define these as small but topical fragments of the network, containing interactions about social events or campaigns with a significant online footprint. To explore this hypothesis, we have designed an iterative discovery pipeline consisting of two alternating phases of user discovery and context discovery. Multiple iterations of the pipeline result in a growing dataset of user profiles for activists, as well as growing set of online social contexts. This mode of exploration differs significantly from prior techniques that focus on influencers, and presents unique challenges because of the weak online signal available to detect activists. The paper describes the design and implementation of the pipeline as a customisable software framework, where user-defined operational definitions of online activism can be explored. We present an empirical evaluation on two extensive case studies, one concerning healthcare-related campaigns in the UK during 2018, the other related to online activism in Italy during the COVID-19 pandemic.