What Makes Deviant Places?

Urban safety plays an essential role in the quality of citizens' lives and in the sustainable development of cities. In recent years, researchers have attempted to apply machine learning techniques to identify the role of location-specific attributes in the development of urban safety. However, existing studies have mainly relied on limited images (e.g., map images, single- or four-directional images) of areas based on a relatively large geographical unit and have narrowly focused on severe crime rates, which limits their predictive performance and implications for urban safety. In this work, we propose a novel method that predicts "deviance," which includes formal deviant crimes (e.g., murders) and informal deviant behaviors (e.g., loud parties at night). To do this, we first collect a large-scale geo-tagged dataset consisting of incident report data for seven metropolitan cities, along with corresponding sequential images around incident sites obtained from Google Street View. We then design a convolutional neural network that learns spatio-temporal visual attributes of deviant streets. Experimental results show that our framework is able to reliably recognize real-world deviance in various cities. Furthermore, we analyze which visual attribute is important for deviance identification and severity estimation with respect to social science as well as activated feature maps in the neural network. We have released our dataset and source codes on https://github.com/JinhwiPark/DevianceNet/.

Full-Control and Switching of Optical Fano Resonance by Continuum State Engineering.

Fano resonance, known for its unique asymmetric line shape, has gained significant attention in photonics, particularly in sensing applications. However, it remains difficult to achieve controllable Fano parameters with a simple geometric structure. Here, a novel approach of using a thin-film optical Fano resonator with a porous layer to generate entire spectral shapes from quasi-Lorentzian to Lorentzian to Fano is proposed and experimentally demonstrated. The glancing angle deposition technique is utilized to create a polarization-dependent Fano resonator. By altering the linear polarization between s- and p-polarization, a switchable Fano device between quasi-Lorentz state and negative Fano state is demonstrated. This change in spectral shape is advantageous for detecting materials with a low-refractive index. A bio-particle sensing experiment is conducted that demonstrates an enhanced signal-to-noise ratio and prediction accuracy. Finally, the challenge of optimizing the film-based Fano resonator due to intricate interplay among numerous parameters, including layer thicknesses, porosity, and materials selection, is addressed. The inverse design tool is developed based on a multilayer perceptron model that allows fast computation for all ranges of Fano parameters. The method provides improved accuracy of the mean validation factor (MVF = 0.07, q-q') compared to the conventional exhaustive enumeration method (MVF = 0.37).