Accurate prediction of asphalt pavement condition is important to guide pavement maintenance practices. The existing models for pavement condition predictions are predominantly based on linear regressions or simple machine learning techniques. However, additional work on these models is needed to improve their basic assumptions, training efficiency, and interpretability. To this end, a new modeling approach is proposed in this manuscript, which includes a ThunderGBM-based ensemble learning model, coupled with the Shapley Additive Explanation (SHAP) method, to predict the International Roughness Index (IRI) of asphalt pavements. The SHAP method was applied to interpret the underlying influencing factors and their interactions. Twenty features were initially identified as the model inputs, and 2,699 observations were extracted from the Long-Term Pavement Performance (LTPP) database. Three benchmark models, namely the Mechanistic-Empirical Pavement Design Guide (MEPDG) model, the ANN model and the RF model, were used for comparison. The results showed that the developed model achieved a satisfactory result with a R-squared ($\mathbf {R}^{2}$) value of 0.88 and Root Mean Square Error (RMSE) of 0.08, both better than three benchmark models. It ran 86 times and 2.3 times faster than the ANN and RF model, respectively. Feature interpretation was performed to identify the top influencing factors of IRI. The 20-feature model was further simplified based on the analysis result. The simplified model only required six features to efficiently and effectively predict IRI using the proposed ThunderGBM-based approach, which can reduce the workload in data collection and management for pavement engineers.

We introduce graph normalizing flows: a new, reversible graph neural network model for prediction and generation. On supervised tasks, graph normalizing flows perform similarly to message passing neural networks, but at a significantly reduced memory footprint, allowing them to scale to larger graphs. In the unsupervised case, we combine graph normalizing flows with a novel graph auto-encoder to create a generative model of graph structures. Our model is permutation-invariant, generating entire graphs with a single feed-forward pass, and achieves competitive results with the state-of-the art auto-regressive models, while being better suited to parallel computing architectures.

Many modern recommender systems use collaborative filtering or historical engagement data to serve the best recommendations for each item. However, the context of each recommendation instance can be very different. Some users may be casually browsing, while others are searching with high intent. At Pinterest, we realized that building our system solely on aggregated historical data or pin-board collaborative filtering [1] would not be able to capture these differences. Incorporating contextual signals helps us serve better recommendations for every instance.

This position paper discusses the use of the Zero Robotics Summer Program competition as a tool to teach programing to students in middle school (ages 11-14). The benefits of teaching programing at that age are discussed, including grasping the student attention early on and providing a useful skill. Zero Robotics is a free programming competition where students program microsatellites to compete with other student-programmed satellites in a virtual game using an online simulation. The finalists see their code compete on the SPHERES satellites aboard the International Space Station, during a final competition transmitted live. The game and curriculum teaches students physics, mathematics, and programming concepts. This position paper argues that it is possible to engage students in programing by providing the right incentive (space) through a competitive environment where teachers have a curriculum to back them up, without becoming a standard classroom exercise.

Users make lasting judgments about a website's appeal within a split second of seeing it for the first time. This first impression is influential enough to later affect their opinions of a site's usability and trustworthiness. In this paper, we demonstrate a means to predict the initial impression of aesthetics based on perceptual models of a website's colorfulness and visual complexity. In an online study, we collected ratings of colorfulness, visual complexity, and visual appeal of a set of 450 websites from 548 volunteers. Based on these data, we developed computational models that accurately measure the perceived visual complexity and colorfulness of website screenshots. In combination with demographic variables such as a user's education level and age, these models explain approximately half of the variance in the ratings of aesthetic appeal given after viewing a website for 500ms only.

Does the emotional content of a robot's speech affect how people teach it? In this experiment, participants were asked to demonstrate several "dances" for a robot to learn. Participants moved their bodies in response to instructions displayed on a screen behind the robot. Meanwhile, the robot faced the participant and appeared to emulate the participant's movements. After each demonstration, the robot received an accuracy score and the participant chose whether or not to demonstrate that dance again. Regardless of the participant's input, however, the robot's dancing and the scores it received were arranged in advance and constant across all participants. The only variation between groups in this study was what the robot said in response to its scores. Participants saw one of three conditions: appropriate emotional responses, often-inappropriate emotional responses, or apathetic responses. Participants that taught the robot with appropriate emotional responses demonstrated the dances, on average, significantly more frequently and significantly more accurately than participants in the other two conditions.

Research Supported By National Science Foundation Grant Number Ccr-0104800. Richard Ladner was supported in part by the Boeing Professor-ship in Computer Science and Engineering. Contact Information: Professor Agnieszka Miguel, Department of Electrical & Computer Engineering Seattle University, 901 12th Avenue, P.O. Box 222000, Seattle, WA 98122-1090, (206)296-5965, [email protected]. ABSTRACT Algorithms for near-lossless compression of hyperspectral images are presented. They guarantee that the intensity of any pixel in the decompressed image(s) differs from its original value by no more than a user-specified quantity. To reduce the bit rate required to code images while providing significantly more compression than lossless algorithms, linear prediction between the bands is used. Each band is predicted by a previously transmitted band. The prediction is subtracted from the original band, and the residual is compressed with a bit plane coder which uses context-based adaptive binary arithmetic coding. To find the best prediction algorithm, the impact of various band orderings and optimization techniques on the compression ratios is studied.