arXiv subjects

Yuki Yoshihara

Publications and source records attributed to Yuki Yoshihara.

3 recordsLinked to original sources

arXiv2026

Monolithic Magneto-Optical Mach-Zehnder Isolator Using Laser-Annealed Iron Garnet on a Silicon Waveguide

Stable silicon photonic circuits require monolithically integrated optical isolators based on magneto-optical garnet. However, crystallizing the garnet by conventional furnace annealing exposes the entire chip to high temperature and degrades the silicon waveguides and the metal electrodes. Here we avoid this degradation by using local laser annealing in vacuum to crystallize cerium-substituted yttrium iron garnet (Ce:YIG), deposited by ion beam sputtering without a seed layer, directly within a silicon-based Mach-Zehnder interferometer. A 915 nm beam heats only the garnet region confined in micrometer-scale trenches, leaving the surrounding circuit and electrodes intact. The device achieves an isolation ratio of 13.6 dB at a wavelength of 1540 nm, corresponding to a Faraday rotation of 0.092$°$/$μ$m, with an insertion loss of 20.4 dB and a propagation loss of 9.5 dB. Transmission electron microscopy reveals the crystallized Ce:YIG and a ~10 nm boundary region at the interface with the Si waveguide. These results demonstrate that thermally sensitive silicon photonic devices and magneto-optical thin films requiring high-temperature processing can be integrated by a high-throughput technique compatible with mass production.

physics.optics↗

arXiv2025

Understanding Driving Risks using Large Language Models: Toward Elderly Driver Assessment

This study investigates the potential of a multimodal large language model (LLM), specifically ChatGPT-4o, to perform human-like interpretations of traffic scenes using static dashcam images. Herein, we focus on three judgment tasks relevant to elderly driver assessments: evaluating traffic density, assessing intersection visibility, and recognizing stop signs recognition. These tasks require contextual reasoning rather than simple object detection. Using zero-shot, few-shot, and multi-shot prompting strategies, we evaluated the performance of the model with human annotations serving as the reference standard. Evaluation metrics included precision, recall, and F1-score. Results indicate that prompt design considerably affects performance, with recall for intersection visibility increasing from 21.7% (zero-shot) to 57.0% (multi-shot). For traffic density, agreement increased from 53.5% to 67.6%. In stop-sign detection, the model demonstrated high precision (up to 86.3%) but a lower recall (approximately 76.7%), indicating a conservative response tendency. Output stability analysis revealed that humans and the model faced difficulties interpreting structurally ambiguous scenes. However, the model's explanatory texts corresponded with its predictions, enhancing interpretability. These findings suggest that, with well-designed prompts, LLMs hold promise as supportive tools for scene-level driving risk assessments. Future studies should explore scalability using larger datasets, diverse annotators, and next-generation model architectures for elderly driver assessments.

cs.CV↗

arXiv2023

Estimating Driver Personality Traits from On-Road Driving Data

This paper focuses on the estimation of a driver's psychological characteristics using driving data for driving assistance systems. Driving assistance systems that support drivers by adapting individual psychological characteristics can provide appropriate feedback and prevent traffic accidents. As a first step toward implementing such adaptive assistance systems, this research aims to develop a model to estimate drivers' psychological characteristics, such as cognitive function, psychological driving style, and workload sensitivity, from on-road driving behavioral data using machine learning and deep learning techniques. We also investigated the relationship between driving behavior and various cognitive functions, including the Trail Making Test (TMT) and Useful Field of View (UFOV) test, through regression modeling. The proposed method focuses on road type information and captures various durations of time-series data observed from driving behaviors. First, we segment the driving time-series data into two road types, namely, arterial roads and intersections, to consider driving situations. Second, we further segment data into many sequences of various durations. Third, statistics are calculated from each sequence. Finally, these statistics are used as input features of machine learning models to estimate psychological characteristics. The experimental results show that our model can estimate a driver's cognitive function, namely, the TMT~(B) and UFOV test scores, with Pearson correlation coefficients $r$ of 0.579 and 0.708, respectively. Some characteristics, such as psychological driving style and workload sensitivity, are estimated with high accuracy, but whether various duration segmentation improves accuracy depends on the characteristics, and it is not effective for all characteristics.

cs.LG↗