My work on the PhD thesis concerns human-like reasoning about relations between spatial objects and the way they change in time. In particular, my research is focused on logic-based reasoning systems that model human spatial reasoning methods and may enable better understanding of humans reasoning mechanisms in future. Importantly, such formalisms are also interested from the practical point of view – they have a number of potential applications, e.g., in robotics, architecture design, databases, among others.

We address the coarse-grained disambiguation of the spatial prepositions as the first step towards spatial role labeling using deep learning models. We propose a hybrid feature of word embeddings and linguistic features, and compare its performance against a set of linguistic features, pre-trained word embeddings, and corpus-trained embeddings using seven classical machine learning classifiers and two deep learning models. We also compile a dataset of 43,129 sample sentences from Pattern Dictionary of English Prepositions (PDEP). The comprehensive experimental results suggest that the combination of the hybrid feature and a convolutional neural network outperforms state-of-the-art methods and reaches the accuracy of 94.21% and F1-score of 0.9398.

Geospatial data is at the core of the Semantic Web, of which the largest knowledge base contains more than 30 billions facts. Reasoning on these large amounts of geospatial data requires efficient methods for the computation of links between the resources contained in these knowledge bases. In this paper, we present Radon – efficient solution for the discovery of topological relations between geospatial resources according to the DE9-IM standard. Our evaluation shows that we outperform the state of the art significantly and by several orders of magnitude.

In this paper we present a novel geometric method for the problem of global pairwise alignment of protein-protein interaction (PPI) networks. A PPI network can be viewed as a node-edge graph and its alignment often needs to solve some generalized version of the subgraph isomorphism problem which is notoriously challenging and NP-hard. All existing research has focused on designing algorithms with good practical performance. In this paper we propose a two-step algorithm for the global pairwise PPI network alignment which consists of a Geometric Step and an MCMF Step. Our algorithm first applies a graph embedding technique that preserves the topological structure of the original PPI networks and maps the problem from graph domain to geometric domain, and computes a rigid transformation for one of the embedded PPI networks so as to minimize its Earth Mover's Distance (EMD) to the other PPI network. It then solves a Min-Cost Max-Flow problem using the (scaled) inverse of sequence similarity scores as edge weight. By using the flow values from the two steps (i.e., EMD and Min-Cost Max-Flow) as the matching scores, we are able to combine the two matching results to obtain the desired alignment. Unlike other popular alignment algorithms which are either greedy or incremental, our algorithm globally optimizes the problem to yield an alignment with better quality.

It's easy to forget that even with the fanciest of machine learning models, we still need humans in the trenches cleaning input data. Descartes Labs, a startup that combines satellite imagery with data about our planet to produce insights and forecasts, knows this all too well. The company ended up building its own cloud-based parallel computing infrastructure to clean and process its massive corpus of satellite imagery. Companies like Descartes Labs cannot just throw raw satellite imagery into machine learning models to extract insights. Images captured contain clouds, cloud shadows and other atmospheric aberrations that make it impossible to compare images taken at different times.

Using analogical model formulation with sketches to solve Bennett Mechanical Comprehension Test problems.

Spatial Visualization Using R: One of the less understood aspects of R is in spatial data visualization. The below article will outline two case studies on using R to spatially visualize data. Our first step is figuring out how to use the Census API within R. Given below are the key data Source Details from the Census ACS Data We use the acs.lookup function & use the keywords to find the required data across all ACS tables. For example, the following are the search results for the keywords owner, occupied, and median. Using the Choroplethr package make it really easy to create thematic maps in R.

Everyone knows businesses today are grappling with the explosion of data. What's less well-known is the value of location data and the intelligence that geospatial analysis can provide business decision makers, beyond those that are GIS (geographic information system) professionals. Location data is already and will continue to be a growing component of all business data. Smartphone penetration is on the rise around the world, location infrastructure--such as cell towers, beacons, RFID and GPS--is proliferating, and the Internet of Things is poised to go mainstream within a few years. However, rather than adding to the complexity of the data landscape, location has the power to bring order to it.

Airbnb boasts almost two million listings in 34,000 cities, and according to data from Inside Airbnb, a independent data analysis website, listed about 36000 apartments in New York as of July 5, 2016. This data exploration sets out to visualize how Airbnb operates in New York City. Airbnb's presence in NYC has been clouded in controversy from the beginning, with law makers arguing that Airbnb drive up rents for New York residents, as well as facilitating a lot of illegal hosting activities, all the while not paying any of the fees hotels are subjected to. Rent is drived up when landlords decide to rather rent apartments to short-term guests at higher rates, compared to signing up tenants for yearlong leases. In a study conducted in 2014, The New York State Attorney General concluded that 72%of all units used as private short-term rentals on Airbnb during 2010 through mid-2014 appeared to violate both state and local New York laws.