Searcharxiv⌕ Search

arXiv subjects

Tomoaki Ohtsuki

Publications and source records attributed to Tomoaki Ohtsuki.

At least 19 recordsLinked to original sources

Cross-Linguistic Acoustic Biomarkers of Cognitive Impairment Across Interactive and Single-Speaker Speech Tasks

Multilingual dementia detection is essential for scalable and equitable screening. In recent years, automated speech analysis has emerged as a promising approach for supporting dementia detection by enabling non-invasive and scalable assessment of cognitive function. However, existing studies that use automated speech analysis often rely on one type of task, such as picture description, and use black-box models. These studies often neglect the role of task and language. To address these gaps, we performed a cross-linguistic and cross-task acoustic analysis that integrates a conversational dataset with structured speech tasks across four languages (Spanish, Mandarin, English, Japanese). We applied statistical, linguist-/clinician-guided, and machine learning model-based feature selection to derive compact acoustic feature sets while maintaining classification performance. This enabled systematic comparison of cognitive impairment-relevant features across datasets and tasks. Our results revealed that acoustic features did not generalize uniformly across tasks and languages. Temporal features remained robust across all datasets, consistently capturing timing disruption regardless of language or task. In contrast, speech rate showed strong task dependence -- emerging as informative mainly in single-speaker tasks with externally anchored content and pacing, but becoming less reliable when speech content was highly individualized. Pitch-related features further exhibited language-specific patterns, favoring chroma-related features in tonal languages (e.g., Mandarin) and F0-related features in non-tonal languages. These findings caution against indiscriminate pooling of heterogeneous speech data and underscore the need for interpretable, context-aware approaches to multilingual dementia detection using automated speech analysis.

cs.AI↗

Eco-MobiLLM: Efficient LLM Fine-Tuning on the Mobile Device via Server Assisted Side-Tuning

There is a huge gap between numerous intriguing applications fostered by on-device large language model (LLM) fine-tuning (FT) from fresh mobile data and the limited resources of a mobile device. While existing server-assisted methods (e.g., split learning or side-tuning) may enable LLM FT on the local mobile device, they suffer from heavy communication burdens of activation transmissions. In addition, their multiple on-device forward passes over the same samples across training epochs lead to substantial iterative computation on the mobile device. To address those issues, we develop Eco-MobiLLM, an efficient LLM FT method which can be deployed on the mobile device via server-assisted side-tuning. To reduce communication cost, Eco-MobiLLM develops an activation shortcut that transmits only the tokens involved in the loss calculation instead of full activation matrices to guide the side network tuning. Besides, to improve computing efficiency and further accelerate FT convergence, Eco-MobiLLM introduces a novel two-stage training paradigm, which allows the server to reuse historical activations and saves the mobile device from repeatedly computing forward passes for the recurring data samples. Extensive experimental results demonstrate Eco-MobiLLM's superiority.

cs.LG↗

LLM eBay: A Simple and Truthful Marketplace for Fine-Tuned LLMs Trading

Personalized fine-tuning of Large Language Models (LLMs) enhances user experience but incurs substantial computational costs. Recent studies show that initializing training from a style-similar fine-tuned model reduces adaptation overhead, turning such checkpoints into reusable, tradable assets. A marketplace for these checkpoints, however, faces information asymmetry: sellers may misreport a checkpoint's style, while buyers cannot verify its usefulness before purchase, which invites adverse selection. We introduce LLM eBay, a simple single-round marketplace for trading fine-tuned LLMs. Sellers are paid per purchase at a posted price, and a truncated quadratic proper scoring rule adjusts each payment according to how well the seller's style report agrees with a style signal that the platform measures by generating text on hidden prompts. We show that the score elicits the verifier's expected signal, characterize exactly when truthful reporting is a seller best response under per-purchase demand, and bound the downside risk from noisy verification. In an end-to-end study with real LoRA checkpoints on two base models and three buyer tasks, LLM eBay reduces measured convergence steps by 8.5\% relative to retrieval over self-reported style (95\% CI [1.0\%, 15.9\%]). In model-based market simulations built on a measured style-to-cost relationship, it cuts style-claim error by 96.5\% (from 0.424 to 0.015), recovers 96.3\% of Oracle welfare, saves 72.4\% of the cost of fine-tuning from the base model, and keeps all providers profitable in the default setting.

eess.SY↗

Robust Resource Allocation for STAR-RIS-Assisted ISAC Networks Using Deep Learning

In this paper, we focus on investigating the resource allocation in an integrated sensing and communication (ISAC) system assisted by a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS). Due to the coupled non-convex nature of the optimization problem, solving the above joint resource optimization problem while guaranteeing superior sensing performance is challenging, especially in dynamic environment. To conquer such challenge, prior iterative optimization algorithms have been presented. However, practical implementations of these prior algorithms face notable computational challenges, e.g., the reliance on accurate global channel information and the assumption of ideal phase shifts. In this context, we propose a model-driven deep learning framework for jointly optimizing the transmit beamforming and waveform in ISAC networks with low-overhead. In addition, we adopt the Cramer-Rao lower bound (CRLB) as the sensing performance metric, and the multi-user interference (MUI) energy as the communication performance metric for performance evaluation. Besides, our framework jointly optimizes the transmit beamforming, waveform and the STAR-RIS reflection/transmission coefficient matrices by minimizing the weighted sum of MUI energy and CRLB. Our study also considers the impact of imperfect channel information, making the research scenario more aligned with real-world applications. Simulation results validate that the proposed framework not only achieves higher sum-rate performance comparable to traditional iterative algorithms but also significantly reduces computational complexity in terms of algorithm execution time, as well as exhibits inherent robustness.

cs.PF↗

A Privacy-Preserving Federated Learning Method for Heterogeneous Clients

Federated Learning (FL) with Differential Privacy (DP) can ensure the protection of healthcare data privacy against malicious user attacks. However, FL with the DP method faces an inherent trade-off: stronger privacy protection degrades predictive accuracy due to injected noise. On the other hand, Homomorphic Encryption (HE) enables computations on encrypted data and the aggregation of encrypted gradients without introducing DP-induced noise, thereby potentially increasing the predictive accuracy. However, it may increase the computation cost. To improve the predictive accuracy while considering the computational ability of heterogeneous clients, we propose a Privacy-Preserving Machine Learning (PPML)-Hybrid method. In the proposed PPML-Hybrid method, clients distributedly select either HE or DP based on their computational resources, so that HE clients contribute noise-free updates while DP clients reduce computational overhead. Meanwhile, clients with high computational resources can flexibly adopt HE or DP according to their privacy needs. Performance evaluation on omics datasets shows that our proposed method achieves comparable predictive accuracy while significantly reducing computation time relative to HE-only. Additionally, it outperforms DP-only methods under equivalent or stricter privacy budgets.

cs.CR↗

Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation

Radar camera depth estimation turns a very sparse but metric radar signal into a dense depth map. Existing methods combine radar and image features outside the sequence operator of the backbone, through concatenation, confidence gating, sparse supervision, or graph based extraction. Mamba variants for multimodal fusion also leave the selection mechanism itself unimodal. We argue that selection is the right place for radar to enter. We introduce Radar-Modulated Selection (RMS), which injects radar inside the selective scan of Mamba. Radar adds learned perturbations, initialised at zero, to the step size $Δ$ and the readout $\mathbf{C}$. The input projection $\mathbf{B}$ and the state matrix $\mathbf{A}$ never see radar. At initialisation the block equals a pretrained image Mamba, so radar gains influence only where it improves accuracy. The construction also couples the two modalities at linear cost and falls back to the image backbone when radar is missing. We deploy RMS in a Multi-View Scan Pyramid (MVSP) that matches the fusion operator to the reach of radar at each scale. On nuScenes, SemoDepth reduces MAE by 34.0%, 29.9%, and 29.9% over the previous best within 50, 70, and 80 m. It also has the lowest single frame latency among methods with a public release (26.8 ms). A feature blend placed before the scan adds no accuracy on top of RMS, which supports the view that selection inside the scan can replace fusion outside it. When twice as many spurious radar returns as true ones are injected, the MAE@80 of SemoDepth rises by 1.4%, against 33.6% for a Mamba baseline that fuses radar before the scan.

cs.CV↗

Rate-Splitting Multiple Access for RIS-Enabled Full-Duplex Communications with User Relaying

Rate splitting multiple access (RSMA) has emerged as a promising non-orthogonal transmission mechanism to improve spectral- and energy efficiency, and user fairness in multi-antenna broadband channels. To further enhance its performance, in this paper we investigate a novel cooperative RSMA (C-RSMA) transmission framework assisted by reconfigurable intelligent surface (RIS) and user relaying. More specifically, we first formulate the common- and private-rate maximization problem satisfying the transmit power constraint, by jointly optimizing the transmit beamformers at the BS and the reflective beamformer at the RIS. The above formulated problem is an intractable and NP-hard problem as the optimization variables are coupled and the strong residual self-interference (SI) is involved. To conquer the challenge mentioned above, we propose a low-complexity alternative optimization approach to jointly optimize the transmit and reflective beamforming. Simulation results show that our approach is capable of enabling superior sum-rate performance than the RIS-assisted space division multiple access (SDMA), half-duplex RSMA, and SDMA without using RIS schemes.

cs.IT↗

Design and Implementation of Schwarz Information Criterion-Aided Intelligent Decentralized Resource Allocation in Dynamic LoRa Networks

This paper proposes a lightweight distributed learning method for selecting transmission parameters in Long-Range (LoRa) networks that adapts to dynamically changing communication environments. In the proposed method, the Thompson Sampling (TS) is adopted for transmission parameter selection, whereas the Schwarz Information Criterion (SIC) is employed for environmental change detection. TS is a reinforcement learning approach that effectively balances exploration and exploitation by updating parameters based on probability distributions. Additionally, it demonstrates stable performance even with a small number of trials, thereby making it well-suited for LoRa end devices (EDs) with limited memory capacity and computational resources. Furthermore, to address the issue that TS-based methods strongly depend on past learning histories and therefore adapt slowly to abrupt changes in communication environments, a statistical change detection mechanism based on the SIC is integrated into our proposed method. SIC is adopted because it can detect environmental changes with low computational cost and is suitable for implementation on resource-constrained LoRa EDs. When a change in the communication environment is detected by SIC, the learning history of TS is reset, thereby enabling rapid re-learning under new environmental conditions. Moreover, to achieve fully distributed communication parameter selection while enhancing transmission reliability and energy efficiency, the proposed method relies solely on Acknowledgment (ACK) feedback and the selected transmission parameters. Experimental results demonstrate that the proposed method improves the transmission success rate from 64.0% to 71.1% and increases energy efficiency from 293.9 bit/J to 328.3 bit/J compared with the conventional Upper Confidence Bound (UCB)1-tuned scheme under high-density dynamic LoRa networks.

cs.DC↗

Flexible Intelligent Metasurface-Aided ISAC: User Fairness Optimization and Performance Evaluation

This paper investigates max-min user fairness optimization for flexible intelligent metasurface (FIM) and non-orthogonal multiple access (NOMA)-assisted integrated sensing and communication (ISAC) systems with active self-localization. To tackle the multi-user interference, performance imbalance, and neglected sensing accuracy problems encountered in conventional ISAC designs, we derive the closed-form Cramer-Rao lower bound (CRLB) for angle-of-departure (AoD) estimation in target sensing and embed it into a max-min fairness optimization framework. The optimization problem, which jointly designs the base station transmit beamforming, FIM reflection coefficients, and surface deformation, is non-convex and solved by an alternating optimization (AO) algorithm. Notably, the devised optimization framework facilitates superior performance trade-off in terms of spectrum resource utilization between communication and sensing tasks. Simulation results validate that the proposed scheme significantly improves user fairness, balances communication performance and sensing precision effectively, and reveals the coupling characteristic between signal-to-interference-plus-noise ratio (SINR) and sensing CRLB. This work provides a feasible solution for FIM-aided ISAC system optimization in 6G networks.

cs.IT↗

RePos: Relative-to-Absolute Pose Factorization for Cross-Environment WiFi-Based 3D Human Pose Estimation

Device-free 3D human pose estimation from commodity WiFi Channel State Information (CSI) enables human sensing that preserves privacy and tolerates poor illumination, but its deployment is limited by poor generalization across environments. Unlike images, CSI measurements have no spatially localized correspondence to body parts and are heavily affected by multipath propagation. Consequently, models that regress absolute poses entangle body structure with location cues specific to each environment. Within a single environment this coupling is not problematic: RePos-D, a direct model that regresses the absolute pose, already achieves the best reported accuracy on Person-in-WiFi-3D, a 3.4% gain over the previous best WiFi method, DT-Pose. Across environments, however, the same model overfits position and degrades sharply. We therefore propose RePos, a factorized framework that separates root-relative pose estimation from root localization. By shielding the structure branch from absolute position, RePos learns robust pose representations. Specifically, it groups CSI features into latent tokens organized by body part that a skeleton-guided module refines into the pose, while a separate network estimates the root position from CSI amplitude through a differentiable spatial decomposition. Under the strict MM-Fi cross-environment protocol, RePos reduces the mean per-joint position error (MPJPE) by 10-21% over existing WiFi methods. The improvement is consistent across activity protocols, holds when each environment is held out in turn, and survives few-shot transfer without data leakage. Further analysis shows that the relative pose predictions remain largely independent of position, whereas root localization remains dependent on the environment.

cs.CV↗

Schwarz Information Criterion Aided MAB for Resource Allocation in Dynamic LoRa System

This paper proposes a lightweight distributed learning method for transmission parameter selection in Long Range (LoRa) networks that can adapt to dynamic communication environments. In the proposed method, each LoRa End Device (ED) employs the Upper Confidence Bound (UCB)1-tuned algorithm to select transmission parameters including channel, transmission power, and bandwidth. The transmission parameters are selected based on the ACKnowledgment (ACK) feedback returned from the gateway after each transmission and the corresponding transmission energy consumption. Hence, it enables devices to simultaneously optimize transmission success rate and energy efficiency in a fully distributed manner. However, although UCB1-tuned based method is effective under stationary conditions, it suffers from slow adaptation in dynamic environments due to its strong reliance on historical observations. To address this limitation, we integrate the Schwarz Information Criterion (SIC) to our proposed method. SIC is adopted because it enables low-cost detection of changes in the communication environment, making it suitable for implementation on resource-constrained LoRa EDs. When a change is detected by SIC, the learning history of UCB1-tuned is reset, allowing rapid re-learning under the new conditions. Experimental results using real LoRa devices demonstrate that the proposed method achieves superior transmission success rate, energy efficiency, and adaptability compared with the conventional UCB1-tuned algorithm without SIC.

cs.NI↗

Memristor-Based Meta-Learning for Fast mmWave Beam Prediction in Non-Stationary Environments

Traditional machine learning techniques have achieved great success in improving data-rate performance and reducing latency in millimeter wave (mmWave) communications. However, these methods still face two key challenges: (i) their reliance on large-scale paired data for model training and tuning, which limits performance gains and makes beam predictions outdated, especially in multi-user mmWave systems with larg antenna arrays, and (ii) meta-learning (ML)-based beamforming solutions are prone to overfitting when trained on a limited number of tasks. To address these challenges, we first propose a memristor-based meta-learning (M-ML) framework to expedite spatial and temporal domain beam prediction. Notably, the M-ML framework generates optimal initialization parameters during the training phase, providing a strong starting point for adapting to unknown environments during the testing phase. By leveraging memory to store key data, M-ML ensures the predicted beamforming vectors are well-suited to episodically dynamic channel distributions, even when testing and training environments do not align. Afterwards, we propose a Gaussian noise-based regularized meta-learning framework to model the uncertainty in the training data and improve its stability and accuracy in complex environments. Simulation results manifest that our approaches deliver high prediction accuracy in new environments, without relying on large datasets. Moreover, M-ML enhances the model's generalization ability and adaptability.

cs.IT↗

Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors

With the rise of AI-generated audio, watermarking has become widely used for detecting misuse and protecting intellectual property. However, adversaries may try to remove these watermarks, making it critical to evaluate how well watermarking schemes withstand removal attacks. Existing attacks are often impractical: they either noticeably degrade perceptual quality or require access to the watermarking scheme. We propose DiffErase, a black-box watermark removal attack that assumes no knowledge of the target watermarking scheme while maintaining perceptual quality. DiffErase perturbs watermarked audio to an intermediate diffusion noise level and regenerates it using a pretrained denoising model, effectively suppressing watermark signals. Theoretical analysis and extensive experiments demonstrate that inaudible audio watermarks are highly vulnerable: across multiple audio domains, DiffErase consistently removes watermarks while preserving perceptual quality. These findings highlight the need for future audio watermarking designs to consider diffusion-based threats. Code and demos are available at https://differase.github.io/DiffErase/.

cs.CR↗

Yours or Mine? Overwriting Attacks Against Neural Audio Watermarking

As generative audio models are rapidly evolving, AI-generated audios increasingly raise concerns about copyright infringement and misinformation spread. Audio watermarking, as a proactive defense, can embed secret messages into audio for copyright protection and source verification. However, current neural audio watermarking methods focus primarily on the imperceptibility and robustness of watermarking, while ignoring its vulnerability to security attacks. In this paper, we develop a simple yet powerful attack: the overwriting attack that overwrites the legitimate audio watermark with a forged one and makes the original legitimate watermark undetectable. Based on the audio watermarking information that the adversary has, we propose three categories of overwriting attacks, i.e., white-box, gray-box, and black-box attacks. We also thoroughly evaluate the proposed attacks on state-of-the-art neural audio watermarking methods. Experimental results demonstrate that the proposed overwriting attacks can effectively compromise existing watermarking schemes across various settings and achieve a nearly 100% attack success rate. The practicality and effectiveness of the proposed overwriting attacks expose security flaws in existing neural audio watermarking systems, underscoring the need to enhance security in future audio watermarking designs.

cs.CR↗

Generative Model-Aided Continual Learning for CSI Feedback in FDD mMIMO-OFDM Systems

Deep autoencoder (DAE) frameworks have demonstrated their effectiveness in reducing channel state information (CSI) feedback overhead in massive multiple-input multiple-output (mMIMO) orthogonal frequency division multiplexing (OFDM) systems. However, existing CSI feedback models struggle to adapt to dynamic environments caused by user mobility, requiring retraining when encountering new CSI distributions. Moreover, returning to previously encountered environments often leads to performance degradation due to catastrophic forgetting. Continual learning involves enabling models to incorporate new information while maintaining performance on previously learned tasks. To address these challenges, we propose a generative adversarial network (GAN)-based learning approach for CSI feedback. By using a GAN generator as a memory unit, our method preserves knowledge from past environments and ensures consistently high performance across diverse scenarios without forgetting. Simulation results show that the proposed approach enhances the generalization capability of the DAE framework while maintaining low memory overhead. Furthermore, it can be seamlessly integrated with other advanced CSI feedback models, highlighting its robustness and adaptability.

cs.LG↗

Who's Wearing? Ear Canal Biometric Key Extraction for User Authentication on Wireless Earbuds

Ear canal scanning/sensing (ECS) has emerged as a novel biometric authentication method for mobile devices paired with wireless earbuds. Existing studies have demonstrated the uniqueness of ear canals by training and testing machine learning classifiers on ECS data. However, implementing practical ECS-based authentication requires preventing raw biometric data leakage and designing computationally efficient protocols suitable for resource-constrained earbuds. To address these challenges, we propose an ear canal key extraction protocol, \textbf{EarID}. Without relying on classifiers, EarID extracts unique binary keys directly on the earbuds during authentication. These keys further allow the use of privacy-preserving fuzzy commitment scheme that verifies the wearer's key on mobile devices. Our evaluation results demonstrate that EarID achieves a 98.7\% authentication accuracy, comparable to machine learning classifiers. The mobile enrollment time (160~ms) and earbuds processing time (226~ms) are negligible in terms of wearer's experience. Moreover, our approach is robust and attack-resistant, maintaining a false acceptance rate below 1\% across all adversarial scenarios. We believe the proposed EarID offers a practical and secure solution for next-generation wireless earbuds.

cs.CR↗

A Deep Transfer Learning-Based Low-overhead Beam Prediction in Vehicle Communications

Existing transfer learning-based beam prediction approaches primarily rely on simple fine-tuning. When there is a significant difference in data distribution between the target domain and the source domain, simple fine-tuning limits the model's performance in the target domain. To tackle this problem, we propose a transfer learning-based beam prediction method that combines fine-tuning with domain adaptation. We integrate a domain classifier into fine-tuning the pre-trained model. The model extracts domain-invariant features in adversarial training with domain classifier, which can enhance model performance in the target domain. Simulation results demonstrate that the proposed transfer learning-based beam prediction method achieves better achievable rate performance than the pure fine-tuning method in the target domain, and close to those when the training is done from scratch on the target domain.

cs.IT↗

Coverage and Rate Performance Analysis of Multi-RIS-Assisted Dual-Hop mmWave Networks

Millimeter-wave (mmWave) communication, which operates at high frequencies, has gained extensive research interest due to its significantly wide spectrum and short wavelengths. However, mmWave communication suffers from the notable drawbacks as follows: i) The mmWave signals are sensitive to the blockage, which is caused by the weak diffraction ability of mmWave propagation; ii) Even though the introduction of reconfigurable intelligent surfaces (RISs) can overcome the performance degradation caused by serve path loss, the location of users and RISs as well as their densities incur a significant impact on the coverage and rate performance; iii) When the RISs' density is very high, i.e., the network becomes extremely dense, a user sees several line-of-sight RISs and thus experiences significant interference, which degrades the system performance. Motivated by the challenges above, we first analyze distributed multi-RISaided mmWave communication system over Nakagami-m fading from the stochastic geometry perspective. To be specific, we analyze the end-to-end (E2E) signal-to-interference-plus-noiseratio (SINR) coverage and rate performance of the system. To improve the system performance in terms of the E2E SINR coverage probability and rate, we study the optimization of the phase-shifting control of the distributed RISs and optimize the E2E SINR coverage particularly when deploying a large number of reflecting elements in RISs. To facilitate the study, we optimize the dynamic association criterion between the RIS and destination. Furthermore, we optimize the multi-RIS-user association based on the physical distances between the RISs and destination by exploiting the maximum-ratio transmission.

cs.IT↗