arXiv subjects

Hung-Yu Wei

Publications and source records attributed to Hung-Yu Wei.

10 recordsLinked to original sources

arXiv2025

Measurement-Driven Early Warning of Reliability Breakdown in 5G NSA Railway Networks

This paper presents a measurement-driven study of early warning for reliability breakdown events in 5G non-standalone (NSA) railway networks. Using 10~Hz metro-train measurement traces with serving- and neighbor-cell indicators, we benchmark six representative learning models, including CNN, LSTM, XGBoost, Anomaly Transformer, PatchTST, and TimesNet, under multiple observation windows and prediction horizons. Rather than proposing a new prediction architecture, this study develops a measurement-driven benchmark to quantify the feasibility and operating trade-offs of seconds-ahead reliability prediction in 5G NSA railway environments. Experimental results show that learning models can anticipate radio link failure (RLF)-related reliability breakdown events seconds in advance using lightweight radio features available on commercial devices. The presented benchmark provides insights for sensing-assisted communication control and offers an empirical foundation for integrating sensing and analytics into future mobility control.

cs.NI↗

arXiv2025

Robust Photoplethysmography Signal Denoising via Mamba Networks

Photoplethysmography (PPG) is widely used in wearable health monitoring, but its reliability is often degraded by noise and motion artifacts, limiting downstream applications such as heart rate (HR) estimation. This paper presents a deep learning framework for PPG denoising with an emphasis on preserving physiological information. In this framework, we propose DPNet, a Mamba-based denoising backbone designed for effective temporal modeling. To further enhance denoising performance, the framework also incorporates a scale-invariant signal-to-distortion ratio (SI-SDR) loss to promote waveform fidelity and an auxiliary HR predictor (HRP) that provides physiological consistency through HR-based supervision. Experiments on the BIDMC dataset show that our method achieves strong robustness against both synthetic noise and real-world motion artifacts, outperforming conventional filtering and existing neural models. Our method can effectively restore PPG signals while maintaining HR accuracy, highlighting the complementary roles of SI-SDR loss and HR-guided supervision. These results demonstrate the potential of our approach for practical deployment in wearable healthcare systems.

cs.LG↗

arXiv2025

HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment

Modern speech quality prediction models are trained on audio data resampled to a specific sampling rate. When faced with higher-rate audio at test time, these models can produce biased scores. We introduce HighRateMOS, the first non-intrusive mean opinion score (MOS) model that explicitly considers sampling rate. HighRateMOS ensembles three model variants that exploit the following information: (i) a learnable embedding of speech sampling rate, (ii) Wav2vec 2.0 self-supervised embeddings, (iii) multi-scale CNN spectral features, and (iv) MFCC features. In AudioMOS 2025 Track3, HighRateMOS ranked first in five out of eight metrics. Our experiments confirm that modeling the sampling rate directly leads to more robust and sampling-rate-agnostic speech quality predictions.

eess.AS↗

arXiv2021

Age-Optimal Power Allocation in Industrial IoT: A Risk-Sensitive Federated Learning Approach

This work studies a real-time environment monitoring scenario in the industrial Internet of things, where wireless sensors proactively collect environmental data and transmit it to the controller. We adopt the notion of risk-sensitivity in financial mathematics as the objective to jointly minimize the mean, variance, and other higher-order statistics of the network energy consumption subject to the constraints on the age of information (AoI) threshold violation probability and the AoI exceedances over a pre-defined threshold. We characterize the extreme AoI staleness using results in extreme value theory and propose a distributed power allocation approach by weaving in together principles of Lyapunov optimization and federated learning (FL). Simulation results demonstrate that the proposed FL-based distributed solution is on par with the centralized baseline while consuming 28.50% less system energy and outperforms the other baselines.

cs.NI↗

arXiv2021

Medium Access Strategies for Integrated Access and Backhaul at mmWaves Unlicensed Spectrum

The unlicensed spectrum is recently considered one of the defining solutions to meet the steadily growing traffic demand. This, in turn, has led to the enhancement for LTE in Release-13 to enable Licensed-Assisted Access (LAA) operations. The design of the medium access control (MAC) protocol for the LAA system to harmonically coexist with the incumbent WLAN system operating in an unlicensed band is critical and challenging. In this paper, we consider an Integrated Access and Backhaul (IAB) system coexisting with a Wi-Fi network operating at millimeter-wave (mmWave) unlicensed spectrum, for which a listen-before-talk-based (LBT) based medium access mechanism is carefully designed. Additionally, we have considered an in-band system that supports both access and backhaul in a single node where the small-cell or the IAB nodes compete with the WiGig for medium access. We present comprehensive experimental results and give design insights based on the simulation results.

cs.NI↗

arXiv2018

SDN - Architectural Enabler for Reliable Communication over Millimeter-Wave 5G Networks

Millimeter-wave (mmWave) frequency bands offer a new frontier for next-generation wireless networks, popularly known as 5G, to enable multi-gigabit communication; however, the availability and reliability of mmWave signals are significantly limited due to its unfavorable propagation characteristics. Thus, mmWave networks rely on directional narrow-beam transmissions to overcome severe path-loss. To mitigate the impact of transmission-reception directionality and provide uninterrupted network services, ensuring the availability of mmWave transmission links is important. In this paper, we proposed a new flexible network architecture to provide efficient resource coordination among serving basestations during user mobility. The key idea of this holistic architecture is to exploit the software-defined networking (SDN) technology with mmWave communication to provide a flexible and resilient network architecture. Besides, this paper presents an efficient and seamless uncoordinated network operation to support reliable communication in highly-dynamic environments characterized by high density and mobility of wireless devices. To warrant high-reliability and guard against the potential radio link failure, we introduce a new transmission framework to ensure that there is at least one basestation is connected to the UE at all times. We validate the proposed transmission scheme through simulations.

cs.NI↗

arXiv2018

Enabling Millimeter-Wave 5G Networks for Massive IoT Applications

Internet of Things is one of the most promising technology of the fifth-generation (5G) mobile broadband systems. Data-driven wireless services of 5G systems require unprecedented capacity and availability. The millimeter-wave based wireless communication technologies are expected to play an essential role in future 5G systems. In this article, we describe the three broad categories of fifth-generation services, viz., enhanced mobile broadband, ultra-reliable and low-latency communications, and massive machine-type communications. Furthermore, we introduce the potential issues of consumer devices under a unifying 5G framework. We provide the state-of-the-art overview with an emphasis on technical challenges when applying millimeter-wave (mmWave) technology to support the massive Internet of Things applications. Our discussion highlights the challenges and solutions, particularly for communication/computation requirements in consumer devices under the millimeter-wave 5G framework.

cs.NI↗

arXiv2018

Safe Driving Capacity of Autonomous Vehicles

An excellent self-driving car is expected to take its passengers safely and efficiently from one place to another. However, different ways of defining safety and efficiency may significantly affect the conclusion we make. In this paper, we give formal definitions to the safe state of a road and safe state of a vehicle using the syntax of linear temporal logic (LTL). We then propose the concept of safe driving throughput (SDT) and safe driving capacity (SDC) which measure the amount of vehicles in the safe state on a road. We analyze how SDT is affected by different factors. We show the analytic difference of SDC between the road with perception-based vehicles (PBV) and the road with cooperative-based vehicles (CBV). We claim that through proper design, the SDC of the road filled with PBVs will be upper-bounded by the SDC of the road filled with CBVs.

eess.SP↗

arXiv2018

QoE-Oriented Resource Allocation for 360-degree Video Transmission over Heterogeneous Networks

Immersive media streaming, especially virtual reality (VR)/360-degree video streaming which is very bandwidth demanding, has become more and more popular due to the rapid growth of the multimedia and networking deployments. To better explore the usage of resource and achieve better quality of experience (QoE) perceived by users, this paper develops an application-layer scheme to jointly exploit the available bandwidth from the LTE and Wi-Fi networks in 360-degree video streaming. This newly proposed scheme and the corresponding solution algorithms utilize the saliency of video, prediction of users' view and the status information of users to obtain an optimal association of the users with different Wi-Fi access points (APs) for maximizing the system's utility. Besides, a novel buffer strategy is proposed to mitigate the influence of short-time prediction problem for transmitting 360-degree videos in time-varying networks. The promising performance and low complexity of the proposed scheme and algorithms are validated in simulations with various 360-degree videos.

cs.MM↗

arXiv2010

Multicasting Homogeneous and Heterogeneous Quantum States in Quantum Networks

In this paper, we target the practical implementation issues of quantum multicast networks. First, we design a recursive lossless compression that allows us to control the trade-off between the circuit complexity and the dimension of the compressed quantum state. We give a formula that describes the trade-off, and further analyze how the formula is affected by the controlling parameter of the recursive procedure. Our recursive lossless compression can be applied in a quantum multicast network where the source outputs homogeneous quantum states (many copies of a quantum state) to a set of destinations through a bottleneck. Such a recursive lossless compression is extremely useful in the current situation where the technology of producing large-scale quantum circuits is limited. Second, we develop two lossless compression schemes that work for heterogeneous quantum states (many copies of a set of quantum states) when the set of quantum states satisfies a certain structure. The heterogeneous compression schemes provide extra compressing power over the homogeneous compression scheme. Finally, we realize our heterogeneous compression schemes in several quantum multicast networks, including the single-source multi-terminal model, the multi-source multi-terminal model, and the ring networks. We then analyze the bandwidth requirements for these network models.

quant-ph↗