Kazuki Uehara | Searcharxiv

arXiv2026

QUBO-Based Optimization of Social Indicator Configurations for Working-Age Population Growth

The decline of the working-age population is a major challenge for regional sustainability, particularly in ageing societies such as Japan. We present a methodological demonstration of a quadratic unconstrained binary optimization (QUBO)-based framework for exploring social-indicator configurations associated with working-age population growth. Using Japanese municipal data, we regressed the 2010-2020 working-age population growth rate on ten discretized social indicators. The resulting quadratic surrogate model showed reasonable predictive performance, with a test-set correlation coefficient of 0.84 and an average R-squared value of 0.76. Its coefficient matrix provides an interpretable representation of individual indicator-level contributions and pairwise associations. We converted the fitted model into a QUBO formulation with one-hot constraints and optimized it using quantum annealing, simulated annealing, and Gurobi. All three methods identified the same optimal feasible configuration, while the annealing-based samplers also generated feasible suboptimal configurations with different predicted growth rates. Municipality-level single-indicator analyses showed that changing one indicator can increase or decrease the predicted growth rate depending on the other indicators. The framework provides an interpretable and optimization-ready approach for connecting municipal social statistics, nonlinear interactions, and model-based scenario generation. It should be regarded as an exploratory tool for policy discussion rather than as a causal estimate of policy interventions.

quant-ph↗

arXiv2018

Object Detection in Satellite Imagery using 2-Step Convolutional Neural Networks

This paper presents an efficient object detection method from satellite imagery. Among a number of machine learning algorithms, we proposed a combination of two convolutional neural networks (CNN) aimed at high precision and high recall, respectively. We validated our models using golf courses as target objects. The proposed deep learning method demonstrated higher accuracy than previous object identification methods.

cs.CV↗

arXiv2017

Object Detection of Satellite Images Using Multi-Channel Higher-order Local Autocorrelation

The Earth observation satellites have been monitoring the earth's surface for a long time, and the images taken by the satellites contain large amounts of valuable data. However, it is extremely hard work to manually analyze such huge data. Thus, a method of automatic object detection is needed for satellite images to facilitate efficient data analyses. This paper describes a new image feature extended from higher-order local autocorrelation to the object detection of multispectral satellite images. The feature has been extended to extract spectral inter-relationships in addition to spatial relationships to fully exploit multispectral information. The results of experiments with object detection tasks conducted to evaluate the effectiveness of the proposed feature extension indicate that the feature realized a higher performance compared to existing methods.

cs.CV↗