We introduce a new Bayesian admixture model intended for exploratory analysis of communication networks--specifically, the discovery and visualization of topic-specific subnetworks in email data sets. Our model produces principled visualizations of email networks, i.e., visualizations that have precise mathematical interpretations in terms of our model and its relationship to the observed data. We validate our modeling assumptions by demonstrating that our model achieves better link prediction performance than three state-of-the-art network models and exhibits topic coherence comparable to that of latent Dirichlet allocation. We showcase our model's ability to discover and visualize topic-specific communication patterns using a new email data set: the New Hanover County email network. We provide an extensive analysis of these communication patterns, leading us to recommend our model for any exploratory analysis of email networks or other similarly-structured communication data. Finally, we advocate for principled visualization as a primary objective in the development of new network models.

Roof type is one of the most critical building characteristics for wind vulnerability modeling. It is also the most frequently missing building feature from publicly available databases. An automatic roof classification framework is developed herein to generate high-resolution roof-type data using machine learning. A Convolutional Neural Network (CNN) was trained to classify roof types using building-level satellite images. The model achieved an F1 score of 0.96 on predicting roof types for 1,000 test buildings. The CNN model was then used to predict roof types for 161,772 single-family houses in New Hanover County, NC, and Miami-Dade County, FL. The distribution of roof type in city and census tract scales was presented. A high variance was observed in the dominant roof type among census tracts. To improve the completeness of the roof-type data, imputation algorithms were developed to populate missing roof data due to low-quality images, using critical building attributes and neighborhood-level roof characteristics.

We introduce a joint model of network content and context designed for exploratory analysis of email networks via visualization of topic-specific communication patterns. Our model is an admixture model for text and network attributes which uses multinomial distributions over words as mixture components for explaining text and latent Euclidean positions of actors as mixture components for explaining network attributes. We demonstrate the capability of our model for descriptive, explanatory, and exploratory analysis by investigating the inferred topic-specific communication patterns of a new government email dataset, the New Hanover County email corpus.

Artificial intelligence-inspired policing technology and techniques like facial recognition software and digital surveillance continue to find traction and champions among law enforcement agencies, but at what cost to the public? Some cities like Wilmington, North Carolina, have even adopted AI-driven policing, where technology like ShotSpotter identifies gunshots and their locations. The software also recommends to patrol officers "next best action" based on their current location, police data on past crime records, time of day, and housing and population density. Renée Cummings, data activist in residence at the University of Virginia's School of Data Science, warns that the rules of citizenship are changing with the development of AI-inspired policing technologies. She explains, "If the rules are changing, then the public needs to have a voice and has the right to provide input on where we need to go with these technologies as well as demand solutions that are accountable, explainable and ethical." As artificial intelligence is used toward the development of technology-based solutions, Cummings' research questions the ethical use of technology to collect and track citizen data, aiming to hold agencies more accountable and to provide citizens greater transparency.

New crisis response and management approaches that incorporate the latest information technologies are essential in all phases of emergency preparedness and response, including the planning, response, recovery, and assessment phases. Accurate and timely information is as crucial as is rapid and coherent coordination among the responding organizations. We are working towards a multi-pronged emergency response tool that provide stakeholders timely access to comprehensive, relevant, and reliable information. The faster emergency personnel are able to analyze, disseminate and act on key information, the more effective and timelier their response will be and the greater the benefit to affected populations. Our tool consists of encoding multiple layers of open source geospatial data including flood risk location, road network strength, inundation maps that proxy inland flooding and computer vision semantic segmentation for estimating flooded areas and damaged infrastructure. These data layers are combined and used as input data for machine learning algorithms such as finding the best evacuation routes before, during and after an emergency or providing a list of available lodging for first responders in an impacted area for first. Even though our system could be used in a number of use cases where people are forced from one location to another, we demonstrate the feasibility of our system for the use case of Hurricane Florence in Lumberton, a town of 21,000 inhabitants that is 79 miles northwest of Wilmington, North Carolina.

When society uses artificial intelligence (AI) to help build judgments about individuals, fairness and equity are critical considerations. On Nov. 12, Brookings Fellow Nicol Turner-Lee sat down with Solon Barocas of Cornell University, Natasha Duarte of the Center for Democracy & Technology, and Karl Ricanek of the University of North Carolina Wilmington to discuss artificial intelligence in the context of societal bias, technological testing, and the legal system. Artificial intelligence is an element of many everyday services and applications, including electronic devices, online search engines, and social media platforms. In most cases, AI provides positive utility for consumers--such as when machines automatically detect credit card fraud or help doctors assess health care risks. However, there is a smaller percentage of cases, such as when AI helps inform decisions on credit limits or mortgage lending, where technology has a higher potential to augment historical biases.

With more than 40 years of experience in the healthcare IT space, Franciscan Missionaries of Our Lady Health System CIO Avery Cloud has seen the value technology brings to healthcare. Some of Mr. Cloud's most memorable moments as CIO at the Baton Rouge, La.-based health system revolve around technology's effect on physicians and patients, ranging from instances when it helped prevent a clinical error to reducing patient anxiety. Prior to joining Franciscan Missionaries of Our Lady Health System, Mr. Cloud served as vice president of innovation and technology at CHI St. Luke's Health in Houston as well as CIO at Wilmington, N.C.-based New Hanover Regional Medical Center and Integris Health in Oklahoma City. Here, Mr. Cloud shares his strategy to build and encourage innovation among staff members. Editor's note: Responses have been lightly edited for clarity and length.

"This is pure corporate laziness," wrote Craig Picken, an executive recruiter based in Wilmington, N.C., who on LinkedIn called the process "D-U-M-B." "Did you hear that?" added Keith Campagna, an Allentown, Penn., regional sales manager for recruiting software company Jobvite. "That was the sound of a whole bunch of well-qualified, passive workers hanging up. Because recruitment is inherently a human process." Companies say they have reason to rethink how they hire now.

As an IBM developerWorks information architect, I gave a presentation last week about cognitive computing to entrepreneurs and staffers at tekMountain, a co-working and tech incubator in Wilmington, North Carolina where I work as a tech mentor. The title is a bit tongue and cheek, but I really tried to position the Watson application development demo I gave as the "applied" part of a series that we launched in the area last year on artificial intelligence. At a previous "Exploring Artificial Intelligence" TechTalk, my buddies Mike Orr (IBM Watson University program chair) and Julian Keith (UNC Wilmington Psychology Chair and brain guy), began a series of conversations about artificial intelligence that quickly blossomed into several different AI events with different AI focuses at different venues. An upcoming talk in this very popular series (for example) is titled "Is artificial intelligence going to do my job better than me?" As a software development enthusiast who sometimes teaches kids and others how to start coding, I naturally conceived of a hands-on version of Watson services as a way to take the conversation further.

We introduce a new Bayesian admixture model intended for exploratory analysis ofcommunication networks--specifically, the discovery and visualization of topic-specific subnetworks in email data sets. Our model produces principled visualizations ofemail networks, i.e., visualizations that have precise mathematical interpretations in terms of our model and its relationship to the observed data. We validate our modeling assumptions by demonstrating that our model achieves better link prediction performance than three state-of-the-art network models and exhibits topic coherence comparable to that of latent Dirichlet allocation. We showcase our model's ability to discover and visualize topic-specific communication patternsusing a new email data set: the New Hanover County email network. We provide an extensive analysis of these communication patterns, leading us to recommend our model for any exploratory analysis of email networks or other similarly-structured communication data. Finally, we advocate for principled visualization asa primary objective in the development of new network models.