arXiv subjects

Hua Fang

Publications and source records attributed to Hua Fang.

10 recordsLinked to original sources

arXiv2026

Multi-Modal Sensing and Fusion in mmWave Beamforming for Connected Vehicles: A Transformer Based Framework

Millimeter wave (mmWave) communication, utilizing beamforming techniques to address the inherent path loss limitation, is considered as one of the key technologies to support ever increasing high throughput and low latency demands of connected vehicles. However, adopting standard defined beamforming approach in highly dynamic vehicular environments often incurs high beam training overheads and reduction in the available airtime for communications, which is mainly due to exchanging pilot signals and exhaustive beam measurements. To this end, we present a multi-modal sensing and fusion learning framework as a potential alternative solution to reduce such overheads. In this framework, we first extract the representative features from the sensing modalities by modality specific encoders, then, utilize multi-head cross-modal attention to learn dependencies and correlations between different modalities, and subsequently fuse the multimodal features to obtain predicted top-k beams so that the best line-of-sight links can be proactively established. To show the generalizability of the proposed framework, we perform a comprehensive experiment in four different vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) scenarios from real world multimodal and 60 GHz mmWave wireless sensing data. The experiment reveals that the proposed framework (i) achieves up to 96.72% accuracy on predicting top-15 beams correctly, (ii) incurs roughly 0.77 dB average power loss, and (iii) improves the overall latency and beam searching space overheads by 86.81% and 76.56% respectively for top-15 beams compared to standard defined approach.

cs.NI↗

arXiv2025

Evaluating Vulnerabilities of Connected Vehicles Under Cyber Attacks by Attack-Defense Tree

Connected vehicles represent a key enabler of intelligent transportation systems, where vehicles are equipped with advanced communication, sensing, and computing technologies to interact not only with one another but also with surrounding infrastructures and the environment. Through continuous data exchange, such vehicles are capable of enhancing road safety, improving traffic efficiency, and ensuring more reliable mobility services. Further, when these capabilities are integrated with advanced automation technologies, the concept essentially evolves into connected and autonomous vehicles (CAVs). While connected vehicles primarily focus on seamless information sharing, autonomous vehicles are mainly dependent on advanced perception, decision-making, and control mechanisms to operate with minimal or without human intervention. However, as a result of connectivity, an adversary with malicious intentions might be able to compromise successfully by breaching the system components of CAVs. In this paper, we present an attack-tree based methodology for evaluating cyber security vulnerabilities in CAVs. In particular, we utilize the attack-defense tree formulation to systematically assess attack-leaf vulnerabilities, and before analyzing the vulnerability indices, we also define a measure of vulnerabilities, which is based on existing cyber security threats and corresponding defensive countermeasures.

cs.CR↗

arXiv2025

Impute-MACFM: Imputation based on Mask-Aware Flow Matching

Tabular data are central to many applications, especially longitudinal data in healthcare, where missing values are common, undermining model fidelity and reliability. Prior imputation methods either impose restrictive assumptions or struggle with complex cross-feature structure, while recent generative approaches suffer from instability and costly inference. We propose Impute-MACFM, a mask-aware conditional flow matching framework for tabular imputation that addresses missingness mechanisms, missing completely at random, missing at random, and missing not at random. Its mask-aware objective builds trajectories only on missing entries while constraining predicted velocity to remain near zero on observed entries, using flexible nonlinear schedules. Impute-MACFM combines: (i) stability penalties on observed positions, (ii) consistency regularization enforcing local invariance, and (iii) time-decayed noise injection for numeric features. Inference uses constraint-preserving ordinary differential equation integration with per-step projection to fix observed values, optionally aggregating multiple trajectories for robustness. Across diverse benchmarks, Impute-MACFM achieves state-of-the-art results while delivering more robust, efficient, and higher-quality imputation than competing approaches, establishing flow matching as a promising direction for tabular missing-data problems, including longitudinal data.

cs.LG↗

arXiv2025

Multi-Modal Sensing Aided mmWave Beamforming for V2V Communications with Transformers

Beamforming techniques are utilized in millimeter wave (mmWave) communication to address the inherent path loss limitation, thereby establishing and maintaining reliable connections. However, adopting standard defined beamforming approach in highly dynamic vehicular environments often incurs high beam training overheads and reduces the available airtime for communications, which is mainly due to exchanging pilot signals and exhaustive beam measurements. To this end, we present a multi-modal sensing and fusion learning framework as a potential alternative solution to reduce such overheads. In this framework, we first extract the features individually from the visual and GPS coordinates sensing modalities by modality specific encoders, and subsequently fuse the multimodal features to obtain predicted top-k beams so that the best line-of-sight links can be proactively established. To show the generalizability of the proposed framework, we perform a comprehensive experiment in four different vehicle-to-vehicle (V2V) scenarios from real-world multi-modal sensing and communication dataset. From the experiment, we observe that the proposed framework achieves up to 77.58% accuracy on predicting top-15 beams correctly, outperforms single modalities, incurs roughly as low as 2.32 dB average power loss, and considerably reduces the beam searching space overheads by 76.56% for top-15 beams with respect to standard defined approach.

cs.NI↗

arXiv2025

Multi-Modality Sensing in mmWave Beamforming for Connected Vehicles Using Deep Learning

Beamforming techniques are considered as essential parts to compensate severe path losses in millimeter-wave (mmWave) communications. In particular, these techniques adopt large antenna arrays and formulate narrow beams to obtain satisfactory received powers. However, performing accurate beam alignment over narrow beams for efficient link configuration by traditional standard defined beam selection approaches, which mainly rely on channel state information and beam sweeping through exhaustive searching, imposes computational and communications overheads. And, such resulting overheads limit their potential use in vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communications involving highly dynamic scenarios. In comparison, utilizing out-of-band contextual information, such as sensing data obtained from sensor devices, provides a better alternative to reduce overheads. This paper presents a deep learning-based solution for utilizing the multi-modality sensing data for predicting the optimal beams having sufficient mmWave received powers so that the best V2I and V2V line-of-sight links can be ensured proactively. The proposed solution has been tested on real-world measured mmWave sensing and communication data, and the results show that it can achieve up to 98.19% accuracies while predicting top-13 beams. Correspondingly, when compared to existing been sweeping approach, the beam sweeping searching space and time overheads are greatly shortened roughly by 79.67% and 91.89%, respectively which confirm a promising solution for beamforming in mmWave enabled communications.

cs.NI↗

arXiv2024

Position Aware 60 GHz mmWave Beamforming for V2V Communications Utilizing Deep Learning

Beamforming techniques are considered as essential parts to compensate the severe path loss in millimeter-wave (mmWave) communications by adopting large antenna arrays and formulating narrow beams to obtain satisfactory received powers. However, performing accurate beam alignment over such narrow beams for efficient link configuration by traditional beam selection approaches, mainly relied on channel state information, typically impose significant latency and computing overheads, which is often infeasible in vehicle-to-vehicle (V2V) communications like highly dynamic scenarios. In contrast, utilizing out-of-band contextual information, such as vehicular position information, is a potential alternative to reduce such overheads. In this context, this paper presents a deep learning-based solution on utilizing the vehicular position information for predicting the optimal beams having sufficient mmWave received powers so that the best V2V line-of-sight links can be ensured proactively. After experimental evaluation of the proposed solution on real-world measured mmWave sensing and communications datasets, the results show that the solution can achieve up to 84.58% of received power of link status on average, which confirm a promising solution for beamforming in mmWave at 60 GHz enabled V2V communications.

cs.NI↗

arXiv2023

mmWave Enabled Connected Autonomous Vehicles: A Use Case with V2V Cooperative Perception

Connected and autonomous vehicles (CAVs) will revolutionize tomorrow's intelligent transportation systems, being considered promising to improve transportation safety, traffic efficiency, and mobility. In fact, envisioned use cases of CAVs demand very high throughput, lower latency, highly reliable communications, and precise positioning capabilities. The availability of a large spectrum at millimeter-wave (mmWave) band potentially promotes new specifications in spectrum technologies capable of supporting such service requirements. In this article, we specifically focus on how mmWave communications are being approached in vehicular standardization activities, CAVs use cases and deployment challenges in realizing the future fully connected settings. Finally, we also present a detailed performance assessment on mmWave-enabled vehicle-to-vehicle (V2V) cooperative perception as an example case study to show the impact of different configurations.

cs.NI↗

arXiv2008

Gravitational waves from intermediate-mass-ratio inspirals for ground-based detectors

We explore the prospects for Advanced LIGO to detect gravitational waves from neutron stars and stellar mass black holes spiraling into intermediate-mass ($M\sim 50 M_\odot$ to $350 M_\odot$) black holes. We estimate an event rate for such \emph{intermediate-mass-ratio inspirals} (IMRIs) of up to $\sim 10$--$30 \mathrm{yr}^{-1}$. Our numerical simulations show that if the central body is not a black hole but its metric is stationary, axisymmetric, reflection symmetric and asymptotically flat then the waves will likely be tri-periodic, as for a black hole. We report generalizations of a theorem due to Ryan (1995) which suggest that the evolutions of the waves' three fundamental frequencies and of the complex amplitudes of their spectral components encode (in principle) a full map of the central body's metric, full details of the energy and angular momentum exchange between the central body and the orbit, and the time-evolving orbital elements. We estimate that Advanced LIGO can measure or constrain deviations of the central body from a Kerr black hole with modest but interesting accuracy.

gr-qc↗

arXiv2008

"Kludge" gravitational waveforms for a test-body orbiting a Kerr black hole

One of the most exciting potential sources of gravitational waves for low-frequency, space-based gravitational wave (GW) detectors such as the proposed Laser Interferometer Space Antenna (LISA) is the inspiral of compact objects into massive black holes in the centers of galaxies. The detection of waves from such "extreme mass ratio inspiral" systems (EMRIs) and extraction of information from those waves require template waveforms. The systems' extreme mass ratio means that their waveforms can be determined accurately using black hole perturbation theory. Such calculations are computationally very expensive. There is a pressing need for families of approximate waveforms that may be generated cheaply and quickly but which still capture the main features of true waveforms. In this paper, we introduce a family of such "kludge" waveforms and describe ways to generate them. We assess performance of the introduced approximations by comparing "kludge" waveforms to accurate waveforms obtained by solving the Teukolsky equation in the adiabatic limit (neglecting GW backreaction). We find that the kludge waveforms do extremely well at approximating the true gravitational waveform, having overlaps with the Teukolsky waveforms of 95% or higher over most of the parameter space for which comparisons can currently be made. Indeed, we find these kludges to be of such high quality (despite their ease of calculation) that it is possible they may play some role in the final search of LISA data for EMRIs.

gr-qc↗

arXiv2005

Tidal coupling of a Schwarzschild black hole and circularly orbiting moon

We describe the possibility of using LISA's gravitational-wave observations to study, with high precision, the response of a massive central body to the tidal gravitational pull of an orbiting, compact, small-mass object. Motivated by this application, we use first-order perturbation theory to study tidal coupling for an idealized case: a massive Schwarzschild black hole, tidally perturbed by a much less massive moon in a distant, circular orbit. We investigate the details of how the tidal deformation of the hole gives rise to an induced quadrupole moment in the hole's external gravitational field at large radii. In the limit that the moon is static, we find, in Schwarzschild coordinates and Regge-Wheeler gauge, the surprising result that there is no induced quadrupole moment. We show that this conclusion is gauge dependent and that the static, induced quadrupole moment for a black hole is inherently ambiguous. For the orbiting moon and the central Schwarzschild hole, we find (in agreement with a recent result of Poisson) a time-varying induced quadrupole moment that is proportional to the time derivative of the moon's tidal field. As a partial analog of a result derived long ago by Hartle for a spinning hole and a stationary distant companion, we show that the orbiting moon's tidal field induces a tidal bulge on the hole's horizon, and that the rate of change of the horizon shape leads the perturbing tidal field at the horizon by a small angle.

gr-qc↗