arXiv subjects

Bruno S. Chang

Publications and source records attributed to Bruno S. Chang.

9 recordsLinked to original sources

arXiv2026

Distortion-Aware Integrated Sensing and Communication with Affine Filter Bank Modulation

The stringent energy-efficiency requirements of future Integrated Sensing and Communications (ISAC) systems are fundamentally challenged. Unlike conventional communication systems, ISAC transmitters must radiate significantly higher power to ensure reliable target detection, forcing the High-Power Amplifier (HPA) to operate closer to saturation, where nonlinear distortions become unavoidable. Consequently, the robustness of every candidate ISAC waveform to HPA nonlinearities must be carefully assessed. In this context, this paper investigates the robustness of Affine Filter Bank Modulation (AFBM), a recently proposed waveform that combines the delay-Doppler resilience of affine modulation with reduced Peak-to-Average Power Ratio (PAPR) and improved spectral containment. We develop a statistical characterization of the Ambiguity Function (AF) of the amplified AFBM waveform, deriving approximate expressions for its mean, variance, and Rician-distributed magnitude. Furthermore, a low-complexity Gaussian belief propagation receiver accounting for HPA nonlinearities is proposed for communication detection. Simulation results validate the analytical framework and demonstrate that AFBM preserves favorable sensing characteristics and robust Bit Error Rate (BER) performance even under severe nonlinear amplification.

eess.SP↗

arXiv2026

WiFuse: An Attention Mechanism for Human Activity Recognition using Fused CSI Amplitude and Delay-Doppler Channel Features

Recently, Wi-Fi sensing has played a significant role in Human Activity Recognition (HAR), as it enables the detection of various activities using only Wi-Fi signals, ensuring privacy and remaining non-intrusive for the user. However, environmental characteristics such as reflective surfaces, hardware offsets, and other physical impairments affect recognition by the neural network, subsequently causing errors and significantly reducing model accuracy. To overcome this problem we present the WiFuse framework, a dual-stream Channel State Information (CSI) framework for human activity recognition (HAR) that pairs denoised time-domain amplitude variations with 2D-FFT-derived Delay-Doppler motion representations computed from the sanitized channel phase. The fused representation feeds a hybrid ResNet-Temporal Convolutional Network (TCN) neural architecture augmented with channel and spatio-temporal attention, where the ResNet extracts spatial-spectral features and the TCN models long-range temporal dependencies; a decoupled two-stage transfer learning strategy is employed to improve optimization stability and feature reuse. We conduct extensive experiments on two public datasets, including comparisons against state-of-the-art methods and alternative hybrid architectures, ablation studies, and cross-dataset and domain-adaptation evaluations. The proposed framework reaches an overall accuracy of up to 95.28% across the four environments of the XRF55 dataset and up to 98.20% on the multi-user Wi-MIR dataset. Overall, the results indicate that combining amplitude and Delay-Doppler representations within a dual-stream strategy, enhanced by transfer learning, improves recognition performance under conditions that typically degrade deep neural networks, such as class overlap, multipath propagation, noise, and interference.

cs.CV↗

arXiv2026

IBIS: A Hybrid Inception-BiLSTM and SVM Ensemble for Robust Doppler-based Human Activity Recognition

Wi-Fi sensing is a leading technology for Human Activity Recognition (HAR), offering a non-intrusive and cost-effective solution for healthcare and smart environments. Despite its potential, existing methods struggle with domain shift issues, often failing to generalize to unseen environments due to overfitting. This paper proposes IBIS, a robust ensemble framework combining Inception-Bidirectional Long Short-Term Memory (BiLSTM) for feature extraction and Support Vector Machine (SVM) for classification of Doppler signatures. The proposed architecture specifically targets generalization capabilities. Experimental results on multiple datasets show that IBIS achieves 95.40% accuracy, delivering a 7.58% performance gain compared to standard architectures in cross-scenario evaluations on external datasets. The analysis confirms that IBIS effectively mitigates environmental dependency in Wi-Fi-based HAR.

cs.CV↗

arXiv2026

On the Robustness of AFBM Sensing to Power Amplifier Nonlinearities

We investigate the impact of power amplifier (PA) nonlinearities on the sensing performance of affine filter bank modulation (AFBM). While AFBM offers several advantageous properties for integrated sensing and communications (ISAC) - including reduced out-of-band emission (OOBE), low peak-to-average power ratio (PAPR), and natural robustness to doubly-dispersive (DD) channel effects - mitigating waveform distortion typically requires highly linear PAs. This creates a fundamental contradiction with ISAC applications, which demand high transmit power for reliable sensing. Our analytical results reveal that the structure of the effective AFBM modulation matrix dictates how distortion propagates within the ambiguity function (AF). Furthermore, simulations demonstrate that both the AF and the overall sensing performance of AFBM remain remarkably insensitive to such nonlinearities. These findings highlight the robustness of AFBM, making it a highly viable candidate for practical ISAC deployments constrained by hardware impairments.

eess.SP↗

arXiv2026

Hybrid Deep Learning Framework for CSI-Based Activity Recognition in Bandwidth-Constrained Wi-Fi Sensing

This paper presents a novel hybrid deep learning framework designed to enhance the robustness of CSI-based Human Activity Recognition (HAR) within bandwidth-constrained Wi-Fi sensing environments. The core of our proposed methodology is a preliminary Doppler trace extraction stage, implemented to amplify salient motion-related signal features before classification. Subsequently, these enhanced inputs are processed by a hybrid neural architecture, which integrates Inception networks responsible for hierarchical spatial feature extraction and Bidirectional Long Short-Term Memory (BiLSTM) networks that capture temporal dependencies. A Support Vector Machine (SVM) is then utilized as the final classification layer to optimize decision boundaries. The framework's efficacy was systematically validated using a public dataset across 20, 40, and 80 MHz bandwidth configurations. The model yielded accuracies of 89.27% (20 MHz), 94.13% (40 MHz), and 95.30% (80 MHz), respectively. These results confirm a marked superiority over standalone deep learning baselines, especially in the most constrained low-bandwidth scenarios. This study underscores the utility of combining Doppler-based feature engineering with a hybrid learning architecture for reliable HAR in bandwidth-limited wireless sensing applications.

eess.SP↗

arXiv2025

SIR Analysis for Affine Filter Bank Modulation

The signal-to-interference ratio (SIR) of the Affine Filter Bank Modulation (AFBM) waveform is analyzed under minimum mean square error (MMSE) equalization in two domains; namely, the affine domain and the filtered time-domain (TD). Due to the incorporation of the discrete affine Fourier transform (DAFT) and despreading/mapping, an interesting and counter-intuitive cancellation of the unwanted combination of the channel induced interference with the orthogonality approximation error is seen in the filtered TD, a process which does not occur in the affine domain. The direct impact on bit error rate (BER) provides a thorough validation of the proposed analysis and explains the substantial gains in performance of the filtered TD detection scheme as opposed to its affine domain equivalent

eess.SP↗

arXiv2025

Affine Filter Bank Modulation (AFBM): A Novel 6G ISAC Waveform with Low PAPR and OOBE

We propose the affine filter bank modulation (AFBM) waveform for enhanced integrated sensing and communications (ISAC) in sixth generation (6G), designed by drawing on concepts from classical filter bank multicarrier modulation (FBMC) theory and recent advances in chirp-domain waveforms, particularly affine frequency division multiplexing (AFDM). Specifically, AFBM exhibits several desirable properties, with emphasis on its remarkably low peak-to-average power ratio (PAPR) and reduced out-of-band emission (OOBE) when benchmarked against the conventional AFDM waveform under doubly-dispersive (DD) channel conditions. In the communications setting, reliable symbol detection is achieved using a tailored low-complexity Gaussian belief propagation (GaBP)-based algorithm, while in the sensing setting, a range and velocity estimation approach is developed that integrates an expectation maximization (EM)-assisted probabilistic data association (PDA) framework to accurately identify surrounding targets. The highlighted performance and benefits of AFBM are validated through analytical and numerical evaluations, including conventional metrics such as ambiguity function (AF), bit error rate (BER), and root mean square error (RMSE), consolidating its position as a promising waveform for next-generation wireless systems.

eess.SP↗

arXiv2025

Low-Complexity Receiver Design for Affine Filter Bank Modulation

We propose a low-complexity receiver structure for the recently introduced Affine Filter Bank Modulation (AFBM) scheme, which is a novel waveform designed for integrated sensing and communications (ISAC) systems operating in doubly-dispersive (DD) channels. The proposed receiver structure is based on the Gaussian Belief Propagation (GaBP) framework, making use of only element-wise scalar operations to perform detection of the transmitted symbols. Simulation results demonstrate that AFBM in conjunction with GaBP outperforms affine frequency division multiplexing (AFDM) in terms of bit error rates (BERs) in DD channels, while achieving very low out-of-band emissions (OOBE) in high-mobility scenarios.

eess.SP↗

arXiv2025

Affine Filter Bank Modulation: A New Waveform for High Mobility Communications

We propose a new waveform suitable for integrated sensing and communications (ISAC) systems facing doubly-dispersive (DD) channel conditions, as typically encountered in high mobility scenarios. Dubbed Affine Filter Bank Modulation (AFBM), this novel waveform is designed based on a filter-bank structure, known for its ability to suppress out-of-band emissions (OOBE), while integrating a discrete affine Fourier transform (DAFT) precoding stage which yields low peak-to-average power ratio (PAPR) and robustness to DD distortion, as well as other features desirable for ISAC. Analytical and simulation results demonstrate that AFBM maintains quasi-orthogonality similar to that of affine frequency division multiplexing (AFDM) in DD channels, while achieving PAPR levels 3 dB lower, in addition to OOBE as low as -100 dB when implemented with PHYDYAS prototype filters.

eess.SP↗