HIHiroki Ishikura

Hiroki Ishikura

*This is an algorithmically generated author record based on publicly available information.

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


Hiroki Ishikura has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Integrating learning-based and TSP solvers for the cylinder replacement problem

    by Akihiro Yoshida, Nozomi Hata, Keiichiro Yamamura, Hiroki Ishikura, Katsuki Fujisawa

    In the liquefied petroleum gas industry, service providers must regularly visit customers to replace gas cylinders. Efficiently scheduling these visits gives rise to the Cylinder Replacement Problem (CRP), a variant of the classical capacitated vehicle routing problem that involves additional complexity due to strict, customer-specific time windows determined by remaining gas levels. Recently, neural combinatorial solvers have been actively studied as a means of quickly inferring heuristic solutions. However, existing solvers are unsuitable for directly solving CRPs because (i) they cannot adequately handle strict customer-specific delivery constraints, and (ii) obtaining optimal solutions for training is computationally expensive. To address these issues, we propose a hybrid optimization framework that combines a neural combinatorial solver with traveling salesperson problem (TSP) solvers. We observe that the delivery constraints in the bilevel approach can be reformulated as an optimal transport problem. For end-to-end training, we first train a surrogate network to estimate the optimal TSP cost and then freeze its parameters before training the cost-estimation network. The remaining route optimization consists of a collection of small traveling salesperson problems, which can be solved efficiently. Experimental results show that our framework significantly outperforms the Gurobi Optimizer in both feasibility and computational efficiency. In particular, it achieves more than a 2 $$\times $$ × speedup and improves feasibility up to 31%. Moreover, solutions from our framework can serve as high-quality initializations for traditional solvers, further accelerating convergence-especially valuable in real-world scenarios that require flexible and rapid rescheduling due to fluctuating gas consumption.

  • QUBO-Based Subset Selection for Efficient Fine-Tuning of Vision–Language Models

    by Akihiro Yoshida, Keiichiro Yamamura, Hiroki Ishikura, Shinjiro Hirai, Ken Kawano, Yoshihiko Fujisawa, Katsuki Fujisawa

  • Open Access

    Automated Tabu Tenure Tuning by Trajectory Metrics for Quadratic Unconstrained Binary Optimization

    by Masahiko Sugimura, Keiichiro Yamamura, Hiroki Ishikura, Akihiro Yoshida, Ken Kawano, Matthieu Parizy, Katsuki Fujisawa

    Tabu Search is a promising approach for solving quadratic unconstrained binary optimization (QUBO) problems. A key parameter in Tabu Search is tabu tenure, which governs the balance between intensification and diversification in the search process. In this work, we aim to develop a systematic method for determining the effective tabu tenure tailored to each QUBO instance, thereby enhancing overall solver performance. To achieve this, we focus on the statistics obtained during the search, which we term “trajectory metrics.” We consolidate existing trajectory metrics from the literature with newly proposed ones and analyze their responses to variations in tabu tenure using three criteria: suitability for tuning, noise robustness, and classification potential. Based on this analysis, we introduce a method for determining the effective tabu tenure and evaluate its performance across several problem instances. Experimental results demonstrate that the proposed approach improves solving performance compared to a well-known standard Tabu Search-based method.

  • Open Access

    Optimization of transporting time through load shuffling in automated storage and retrieval system and evaluation via demonstration experiments

    by Hiroki Ishikura, Makoto Tsukamoto, Shingo Egi, Keiichiro Yamamura, Yoshihiko Fujisawa, Akihiro Yoshida, Hiroyuki Koshiro, Katsuki Fujisawa

    An automated storage and retrieval system (AS/RS) is a system that automates storing and retrieving raw materials and products in factories and distribution centers. The storage/retrieval machines (S/R machines) can automatically transport loads without human labor. In this paper, we focus on “load shuffling,” which is changing the storage location of the load once it is stored in the AS/RS. In the proposed method, load shuffling is formulated to minimize the transporting time by S/R machines as a relocation problem of loads in the AS/RS, using a 0–1 integer programming problem. By solving this problem and reallocating the loads, we aim to reduce the time spent transporting loads during the production process in factory operations. Two types of numerical experiments were conducted: one using simulation and the other using an actual factory. Simulation experiments confirmed that using load shuffling reduced the time transporting loads. The demonstration experiment using an actual factory confirmed that load shuffling reduces the time required for the machine to transport loads despite the restrictions imposed by actual production activities.


  • Enhancing Output Diversity Improves Conjugate Gradient-Based Adversarial Attacks

    by Keiichiro Yamamura, Issa Oe, Hiroki Ishikura, Katsuki Fujisawa

  • Superpixel Attack

    by Issa Oe, Keiichiro Yamamura, Hiroki Ishikura, Ryo Hamahira, Katsuki Fujisawa

  • Scheduling system for automated storage and retrieval system with multiple machines using a time-expanded network

    by Hiroki Ishikura, Nariaki Tateiwa, Shingo Egi, Issa Oe, Nozomi Hata, Toru Mitsutake, Keiichiro Yamamura, Miyu Fujii, Katsuki Fujisawa


  • Expectations for escape from restraints on Japanese digital transformation during COVID-19

    by Hiroki Ishikura, Anshuman Khare

    Japan’s per capita nominal GDP peaked in 1995, and has been declining every year when compared to other developed countries. The Japanese economy has been stagnant since the beginning of the information age, starting in the mid-1990s. This means that Japan could not adapt to the information age. In developed countries, more than three-quarters of workers are engaged in tertiary industries. It is essential to add value to the service industry. The Japanese service industry has not been able to increase its productivity or add value to its services. An advanced service industry has not been born due to the delay in a digital transformation. It is thought that companies that utilize economies of scale with clear goals have an advantage in digitization. The reason is that the Japanese work ethic does not aim to clarify goals and dramatically exceed them, but only to find the immediate purpose of the work in order to improve what is immediately in front of them. In the future, as digital innovation continues to develop unique technologies such as AI and robots, Japanese companies will promote the development of the IT infrastructure because of the external pressure exerted by COVID-19 and will improve the efficiency of their service and manufacturing products through the use of AI. In this way, we may find hope for a revival of the Japanese economy.

  • Japanese Business Operations in an Uncertain World

    by Anshuman Khare, Nobutaka Odake, Hiroki Ishikura

    This book looks at Japanese companies in manufacturing and services sectors and how they are trying to emerge from the prolonged uncertainty of the pandemic. The chapters are written by those dealing with Japanese business under the shadow of the pandemic and being influenced by the continuous and rapid adoption of digital technologies in business and our daily lives. This book brings together the experiences of big and small corporations while looking at how digital transformation and the pandemic combined have led to a transformation in the product, production processes and services. It highlights the role played by robots, 3-D printing and renewable energy in manufacturing while the impact can be seen in the changes coming to future offices, how we work and interact and how we relax through tourism and travel on the service side. The services sector is as much impacted by digital transformation and the pandemic as any other field in business. Aimed at academics, researchers and practitioners, Japanese Business Operations in an Uncertain World will provide valuable insights into how Japanese organizations are adapting to the dual impact of the pandemic and advancements in digital technologies.