Institution profile

University of Electro-Communications

Academic institutionasia · jp
Official website
Research library144linked papers
Opportunities0open roles
Selected work

Representative Papers

Fuzzy-UCS Revisited: Self-Adaptation of Rule Representations in Michigan-Style Learning Fuzzy-Classifier Systems

Jul 12, 2023Annual Conference on Genetic and Evolutionary Computation

Traditional Michigan-style Learning Fuzzy Classifier Systems (LFCS) suffer from limited generalization in continuous domains due to fixed, pre-specified rule representations that cannot adapt to unknown data characteristics. To address this, we propose an adaptive rule representation mechanism featuring evolvable “fuzzy indicators”—parameters that dynamically select between crisp (hyper-rectangular) and fuzzy (triangular) membership functions, enabling online, context-aware rule-shape adaptation. This approach transcends rigid structural assumptions by unifying fuzzy logic, genetic evolution, and supervised learning within a single cohesive framework. Empirical evaluation across multiple continuous-domain benchmark tasks demonstrates that our method achieves significantly higher classification accuracy than the conventional UCS, while exhibiting superior robustness and stability under uncertainty—including noise corruption and missing values.

4 citationsRead paper

Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information

Mar 07, 2026AIWOLFDIAL

Existing AI agents for Werewolf often exhibit inconsistent statements and role-character drift across multiple rounds of dialogue, undermining their reasoning credibility and gameplay performance. This work proposes a novel approach that integrates large language model–generated dialogue summaries with handcrafted role profiles—including linguistic style templates and example utterances—to explicitly incorporate role-specific information into a contextual summarization mechanism. By fusing explicit role identity with dynamic context tracking, the method enhances long-term behavioral and linguistic consistency throughout the game. Experimental results demonstrate that the resulting agents significantly improve contextual coherence and role stability in self-play settings, effectively preserving consistent speech patterns and strategic behaviors aligned with their assigned roles.

2 citationsRead paper

User Review Writing via Interview with Dialogue Systems

Mar 07, 2026SIGDIAL Conferences

This work proposes an interview-style interactive approach based on a dialogue system to alleviate the time and effort required for users to write product reviews, thereby enhancing both the efficiency and quality of user-generated content on e-commerce platforms. For the first time in review generation, the method incorporates a dialogue-guided mechanism: the system engages users in multi-turn interactions to elicit key information and employs a GPT-4-powered generation module to automatically produce high-quality reviews. Experimental results demonstrate that this approach significantly reduces user authoring burden, yielding reviews that require fewer post-generation edits and are rated by readers as more helpful than those written entirely by humans, thus validating its effectiveness in improving both the efficiency and practical utility of review generation.

1 citationsRead paper

Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimation

Jan 18, 2026

Existing WiFi-based human pose estimation methods rely on camera-coordinate supervision, making them prone to overfitting specific device layouts and limiting their generalization. This work proposes PerceptAlign, a framework that aligns WiFi and visual spaces through a lightweight geometry-aware coordinate unification procedure requiring only two checkerboards and a few photographs. The calibrated transceiver positions are encoded into high-dimensional geometric embeddings and fused with channel state information (CSI) features to enable layout-agnostic 3D pose estimation. PerceptAlign introduces, for the first time, a geometry-conditioned learning mechanism that effectively disentangles human motion from device layout. Evaluated on the largest cross-domain WiFi pose dataset to date, the method reduces in-domain error by 12.3% and achieves over 60% reduction in cross-domain error.

1 citationsRead paper

Augmented Shuffle Protocols for Accurate and Robust Frequency Estimation under Differential Privacy

Apr 10, 2025

Existing differentially private (DP) shuffling models face two critical challenges: poor robustness against local data poisoning attacks—especially under small ε—and vulnerability to privacy budget inflation when the data collector colludes with users. This paper proposes an enhanced shuffling framework that achieves pure ε-DP frequency estimation while provably resisting collusion. Our method introduces a universal protocol requiring no local noise injection, integrates randomized sampling and virtual data injection, and employs an asymmetric two-sided geometric distribution for virtual counts—ensuring strict ε-DP and effectively mitigating poisoning effects. We provide formal theoretical proofs establishing both ε-DP compliance and robustness against adversarial poisoning. Empirical evaluation demonstrates that, under identical privacy budgets, our approach improves estimation accuracy by 15–30% over state-of-the-art methods, achieving a superior balance among utility, computational efficiency, and rigorous privacy guarantees.

1 citationsRead paper
Recent publications

Latest Papers