Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Liang Zhao has a total of 78 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Deployment-oriented benchmarking of YOLO detectors for multiclass pavement distress inspection using street-view imagery

    by Haiyan Zhuang, Rimsa Goperma, Rojan Basnet, Man Zhou, Kai-Chun Chang, Liang Zhao

    1. The durability and serviceability of pavement infrastructure are essential for safe, efficient, and sustainable transportation systems. Pavement surface distresses, including cracking, potholes,...

  • Open Access

    Sublinear Scaling in Subnational Parliaments: Empirical Evidence from G20 Countries

    by Akiko Tanimoto, Nicolas Lucic, Liang Zhao

    This paper examines the relationship between population size and the size of subnational legislatures, a question that has received far less attention than its national-level counterpart despite its importance for political representation. While a substantial literature shows that national parliaments tend to scale sublinearly with population—most commonly between square-root and cubic-root laws—little is known about whether similar patterns hold below the national level. Using an original dataset covering 804 subnational units across the nineteen sovereign G20 countries, including overseas, special, and outlying territories, this study analyzes the scaling relationship between population and the number of legislative seats in the highest subnational institutions. The sample spans a wide diversity of political systems, including federal and unitary states as well as democratic, hybrid, and authoritarian regimes. We estimate two complementary models, a log-linear specification and a nonlinear raw-data specification, to evaluate for sublinear scaling without imposing strong prior assumptions. The results show that proportional scaling has been abandoned at the subnational level and that sublinear scaling dominates across countries. Most countries exhibit scaling coefficients between 0.3 and 0.5, consistent with findings for national parliaments. These results document a first-order institutional regularity at the subnational level, with direct implications for the political economy of legislative design and the governance of population change. We discuss the convergence of scaling behavior across heterogeneous political systems and its implications for institutional reform.

  • Open Access

    Cross-Attentive Prototypical Few-Shot Learning for Early Diagnosis of AMD and Glaucoma from Volumetric OCT Data

    by Rimsa Goperma, Rojan Basnet, Liang Zhao

    Early diagnosis of glaucoma and age-related macular degeneration (AMD) from volumetric optical coherence tomography (OCT) is critical for preventing vision loss, yet current approaches face challenges including time-consuming manual review, inter-reader variability, and scarcity of labeled data. This work introduces CAP-FSL (Cross-Attentive Prototypical Few-Shot Learning), a framework designed for 3D OCT analysis that maintains strong diagnostic performance with only a handful of labeled volumes. Unlike standard Prototypical Networks that form static support-only centroids, CAP-FSL employs query → support cross-attention to dynamically condition support embeddings before prototype formation, yielding query-aware class exemplars that better capture subtle pathological variations. The architecture integrates a 3D ResNet-50 backbone with squeeze-and-excitation (SE) attention to effectively capture volumetric structural patterns while remaining label-efficient and quick to adapt. Evaluated on two public OCT cohorts—one focusing on optic nerve head (ONH) for glaucoma detection and another on macular scans for AMD diagnosis—CAP-FSL consistently outperforms established metric-learning baselines including Matching Networks, standard Prototypical Networks, and Deep Subspace Networks in both 1-shot and 5-shot scenarios. In 5-shot testing, the method achieves classification accuracies of 95.74% ± 2.18% for glaucoma, 93.85% ± 2.70% for AMD, and 92.73% ± 3.18% for normal cases, representing substantial improvements over baseline Prototypical Networks. High sensitivity and specificity metrics with low variance across ten random seeds demonstrate the method’s reliability under data scarcity conditions. The cross-attention mechanism produces interpretable attention maps that align with known disease biomarkers, enhancing clinical interpretability. By combining query-conditioned prototypes with efficient 3D feature extraction, CAP-FSL offers a practical approach for rapidly adapting OCT screening and triage models in data-constrained clinical settings. Code and trained models are publicly available at https://github.com/Rimsa78/CAP-FSL.

  • Open Access

    A unified approach to inferring chemical compounds with the desired aqueous solubility

    by Muniba Batool, Naveed Ahmed Azam, Jianshen Zhu, Kazuya Haraguchi, Liang Zhao, Tatsuya Akutsu

    Aqueous solubility (AS) is a key physiochemical property that plays a crucial role in drug discovery and material design. We report a novel unified approach to predict and infer chemical compounds with the desired AS based on simple deterministic graph-theoretic descriptors, multiple linear regression (MLR), and mixed integer linear programming (MILP). Selected descriptors based on a forward stepwise procedure enabled the simplest regression model, MLR, to achieve significantly good prediction accuracy compared to the existing approaches, achieving accuracy in the range [0.7191, 0.9377] for 29 diverse datasets. By simulating these descriptors and learning models as MILPs, we inferred mathematically exact and optimal compounds with the desired AS, prescribed structures, and up to 50 non-hydrogen atoms in a reasonable time range [6, 1166] seconds. These findings indicate a strong correlation between the simple graph-theoretic descriptors and the AS of compounds, potentially leading to a deeper understanding of their AS without relying on widely used complicated chemical descriptors and complex machine learning models that are computationally expensive, and therefore difficult to use for inference. An implementation of the proposed approach is available at https://github.com/ku-dml/mol-infer/tree/master/AqSol.


  • Open Access

    A Unified Approach to Inferring Chemical Compounds with the Desired Aqueous Solubility

    by Muniba Batool, Naveed Ahmed Azam, Jianshen Zhu, Kazuya Haraguchi, Liang Zhao, Tatsuya Akutsu

    Aqueous solubility (AS) is a key physiochemical property that plays a crucial role in drug discovery and material design. We report a novel unified approach to predict and infer chemical compounds with the desired AS based on simple deterministic graph-theoretic descriptors, multiple linear regression (MLR) and mixed integer linear programming (MILP). Selected descriptors based on a forward stepwise procedure enabled the simplest regression model, MLR, to achieve significantly good prediction accuracy compared to the existing approaches, achieving the accuracy in the range [0.7191, 0.9377] for 29 diverse datasets. By simulating these descriptors and learning models as MILPs, we inferred mathematically exact and optimal compounds with the desired AS, prescribed structures, and up to 50 non-hydrogen atoms in a reasonable time range [6, 1204] seconds. These findings indicate a strong correlation between the simple graph-theoretic descriptors and the AS of compounds, potentially leading to a deeper understanding of their AS without relying on widely used complicated chemical descriptors and complex machine learning models that are computationally expensive, and therefore difficult to use for inference. An implementation of the proposed approach is available at https://github.com/ku-dml/mol-infer/tree/master/AqSol.

  • A Method for Inferring Polymers Based on Linear Regression and Integer Programming

    by Ryota Ido, Shengjuan Cao, Jianshen Zhu, Naveed Ahmed Azam, Kazuya Haraguchi, Liang Zhao, Hiroshi Nagamochi, Tatsuya Akutsu

    A novel framework has recently been proposed for designing the molecular structure of chemical compounds with a desired chemical property using both artificial neural networks and mixed integer linear programming. In this paper, we design a new method for inferring a polymer based on the framework. For this, we introduce a new way of representing a polymer as a form of monomer and define new descriptors that feature the structure of polymers. We also use linear regression as a building block of constructing a prediction function in the framework. The results of our computational experiments reveal a set of chemical properties on polymers to which a prediction function constructed with linear regression performs well. We also observe that the proposed method can infer polymers with up to 50 nonhydrogen atoms in a monomer form


  • Molecular Design Based on Integer Programming and Splitting Data Sets by Hyperplanes

    by Jianshen Zhu, Naveed Ahmed Azam, Kazuya Haraguchi, Liang Zhao, Hiroshi Nagamochi, Tatsuya Akutsu

    A novel framework for designing the molecular structure of chemical compounds with a desired chemical property has recently been proposed. The framework infers a desired chemical graph by solving a mixed integer linear program (MILP) that simulates the computation process of two functions: a feature function defined by a two-layered model on chemical graphs and a prediction function constructed by a machine learning method. To improve the learning performance of prediction functions in the framework, we design a method that splits a given data set $\mathcal {C}$ into two subsets $\mathcal {C}^{(i)},i=1,2$ by a hyperplane in a chemical space so that most compounds in the first (resp., second) subset have observed values lower (resp., higher) than a threshold $\theta$ . We construct a prediction function $\psi$ to the data set $\mathcal {C}$ by combining prediction functions $\psi _{i},i=1,2$ each of which is constructed on $\mathcal {C}^{(i)}$ independently. The results of our computational experiments suggest that the proposed method improved the learning performance for several chemical properties to which a good prediction function has been difficult to construct.