arXiv subjects

Katsuya Suto

Publications and source records attributed to Katsuya Suto.

6 recordsLinked to original sources

arXiv2026

Radio Map Construction with Post-Hoc Location Calibration under Quasi-Static Positioning Errors: Joint Estimation, Performance Bounds, and GNSS-Based Evaluation

Radio maps enable environment-aware wireless and Internet-of-Things applications and can be constructed from location-tagged received signal strength (RSS) measurements collected by mobile devices. In urban environments, temporally correlated GNSS errors can shift an entire sensing trajectory, causing systematic spatial misregistration that is not mitigated by collecting more measurements. This paper presents a radio-map construction framework that uses the radio measurements themselves to calibrate erroneous location tags after data collection. The dominant positioning error is modeled as a sensor-specific quasi-static offset, which is jointly estimated with radio-propagation parameters in a Gaussian process regression (GPR) framework by exploiting complementary spatial information from distance-dependent path loss and spatially correlated shadowing. We establish lower and upper bounds on the conditional Bayes risk and show that, under a translation-invariant trajectory model, trajectory information alone cannot identify the quasi-static offset, thereby motivating the use of RSS-derived spatial information for calibration. Numerical evaluations across propagation conditions show that the proposed method reduces the mean squared error (MSE) gap from ideal GPR to approximately $3.26\mathrm{dB}^2$, compared with about $10\mathrm{dB}^2$ for position-error-agnostic and noisy-input GPR baselines. Evaluation using positioning-error models derived from smartphone GNSS measurements shows that the proposed method outperforms a KF--RTS trajectory-smoothing baseline despite unmodeled time-varying positioning errors, remaining within approximately $5\mathrm{dB}^2$ of ideal GPR at the median MSE. These results demonstrate that RSS measurements can serve not only as observations for radio-map reconstruction but also as spatial cues for post-hoc calibration of imperfectly geotagged sensing data.

eess.SP↗

arXiv2025

Compressing Multi-Task Model for Autonomous Driving via Pruning and Knowledge Distillation

Autonomous driving systems rely on panoptic perception to jointly handle object detection, drivable area segmentation, and lane line segmentation. Although multi-task learning is an effective way to integrate these tasks, its increasing model parameters and complexity make deployment on on-board devices difficult. To address this challenge, we propose a multi-task model compression framework that combines task-aware safe pruning with feature-level knowledge distillation. Our safe pruning strategy integrates Taylor-based channel importance with gradient conflict penalty to keep important channels while removing redundant and conflicting channels. To mitigate performance degradation after pruning, we further design a task head-agnostic distillation method that transfers intermediate backbone and encoder features from a teacher to a student model as guidance. Experiments on the BDD100K dataset demonstrate that our compressed model achieves a 32.7% reduction in parameters while segmentation performance shows negligible accuracy loss and only a minor decrease in detection (-1.2% for Recall and -1.8% for mAP50) compared to the teacher. The compressed model still runs at 32.7 FPS in real-time. These results show that combining pruning and knowledge distillation provides an effective compression solution for multi-task panoptic perception.

cs.CV↗

arXiv2025

RMT-PPAD: Real-time Multi-task Learning for Panoptic Perception in Autonomous Driving

Autonomous driving systems rely on panoptic driving perception that requires both precision and real-time performance. In this work, we propose RMT-PPAD, a real-time, transformer-based multi-task model that jointly performs object detection, drivable area segmentation, and lane line segmentation. We introduce a lightweight module, a gate control with an adapter to adaptively fuse shared and task-specific features, effectively alleviating negative transfer between tasks. Additionally, we design an adaptive segmentation decoder to learn the weights over multi-scale features automatically during the training stage. This avoids the manual design of task-specific structures for different segmentation tasks. We also identify and resolve the inconsistency between training and testing labels in lane line segmentation. This allows fairer evaluation. Experiments on the BDD100K dataset demonstrate that RMT-PPAD achieves state-of-the-art results with mAP50 of 84.9% and Recall of 95.4% for object detection, mIoU of 92.6% for drivable area segmentation, and IoU of 56.8% and accuracy of 84.7% for lane line segmentation. The inference speed reaches 32.6 FPS. Moreover, we introduce real-world scenarios to evaluate RMT-PPAD performance in practice. The results show that RMT-PPAD consistently delivers stable performance. The source codes and pre-trained models are released at https://github.com/JiayuanWang-JW/RMT-PPAD.

cs.CV↗

arXiv2024

Bayesian Optimization Framework for Channel Simulation-Based Base Station Placement and Transmission Power Design

This study proposes an adaptive experimental design framework for a channel-simulation-based base station (BS) design that supports the joint optimization of transmission power and placement. We consider a system in which multiple transmitters provide wireless services over a shared frequency band. Our objective is to maximize the average throughput within an area of interest. System operators can design the system configurations prior to deployment by iterating them through channel simulations and updating the parameters. However, accurate channel simulations are computationally expensive; therefore, it is preferable to configure the system using a limited number of simulation iterations. We develop a solver for the problem based on Bayesian optimization (BO), a black-box optimization method. The numerical results demonstrate that our proposed framework can achieve 18-22% higher throughput performance than conventional placement and power optimization strategies.

cs.NI↗

arXiv2021

Cell Zooming with Masked Data for Off-Grid Small Cell Networks: Distributed Optimization Approach

Cell zooming has been becoming an essential enabler for off-grid small cell networks. Traditional models often utilize the numbers of active users in order to determine cell zooming strategies. However, such confidential measurement data must be concealed from others. We therefore propose a novel cell zooming method with masking noise. The proposed algorithm is designed based on distributed optimization, in which each SBS locally solves a divided optimization problem and learns how much a global constraint is satisfied or violated for temporal solutions. The important feature of this distributed control method is robustness against masking noise. We analyze the trade-off between confidentiality and optimization accuracy, using the notion of differential privacy. Numerical simulations show that the proposed distributed control method outperforms a standard centralized control method in the presence of masking noise.

eess.SY↗

arXiv2017

Cooperative Edge Caching in User-Centric Clustered Mobile Networks

With files proactively stored at base stations (BSs), mobile edge caching enables direct content delivery without remote file fetching, which can reduce the end-to-end delay while relieving backhaul pressure. To effectively utilize the limited cache size in practice, cooperative caching can be leveraged to exploit caching diversity, by allowing users served by multiple base stations under the emerging user-centric network architecture. This paper explores delay-optimal cooperative edge caching in large-scale user-centric mobile networks, where the content placement and cluster size are optimized based on the stochastic information of network topology, traffic distribution, channel quality, and file popularity. Specifically, a greedy content placement algorithm is proposed based on the optimal bandwidth allocation, which can achieve (1-1/e)-optimality with linear computational complexity. In addition, the optimal user-centric cluster size is studied, and a condition constraining the maximal cluster size is presented in explicit form, which reflects the tradeoff between caching diversity and spectrum efficiency. Extensive simulations are conducted for analysis validation and performance evaluation. Numerical results demonstrate that the proposed greedy content placement algorithm can reduce the average file transmission delay up to 50% compared with the non-cooperative and hit-ratio-maximal schemes. Furthermore, the optimal clustering is also discussed considering the influences of different system parameters.

cs.NI↗