Searcharxiv⌕ Search

arXiv subjects

Yaqian Xu

Publications and source records attributed to Yaqian Xu.

8 recordsLinked to original sources

An In-Ear Sleep Modulation SoC Featuring a CNN-LSTM Accelerator with Long-Kernel Memory Reuse and Runtime Dynamic Quantization

This work presents a 65 nm SoC for closed-loop in-ear sleep modulation. The SoC performs low-noise in-ear EEG sensing, CNN-LSTM-based sleep stage classification, and phase-specific auditory stimulation under 1 mW. A dedicated accelerator is developed, featuring a memory reuse technique to efficiently process long kernels required for low-frequency EEG feature extraction. A runtime dynamic quantization is incorporated, reducing model size by 3.88 times with only a 0.28% loss in accuracy. A sensitivity of 98.3% is achieved for deep sleep detection, enabling effective sleep modulation.

eess.SP↗

A Mixed-Precision CNN-LSTM Accelerator Featuring Long-Kernel Memory Reuse and Dynamic Quantization for Sleep Staging

This letter presents a mixed-precision CNN-LSTM accelerator for EEG-based sleep staging. To efficiently execute long temporal convolutions, a serpentine dataflow propagates activations between neighboring processing elements, reducing memory accesses by 6.2 times and 2.25 times compared with output- and weight-stationary dataflows, respectively. A hybrid quantization scheme applies runtime dynamic quantization to the LSTM and MLP layers and assigns mixed precision on a layer-by-layer basis, reducing model size by 4.16 times. Combined with a bit-flexible MAC architecture and channel-grouped memory scheduling, the accelerator supports INT2/4/8/16 inference. Fabricated in 65 nm CMOS, the accelerator consumes 0.40 mW and achieves a 258 times speedup over an iso-frequency 32b RISC-V processor. Evaluated across all 62 subjects in the public MASS-SS3 dataset using 31-fold leave-two-subject-out cross-validation, the mixed-precision approach with hybrid quantization maintains 5-class accuracy within 0.15% of the floating-point baseline when optimized for general sleep staging and N3 sensitivity within 0.51% when optimized for deep-sleep detection. The developed techniques are broadly applicable to EEG-based DL workloads.

cs.AR↗

FPGA Acceleration of CNN-BiLSTM for EEG-Based Sleep Staging Featuring FFT-Based Non-Unit Stride Fast Convolution

Deep learning (DL) models for real-time wearable sleep staging often rely on long-kernel temporal convolutions, a requirement that current accelerators struggle to support efficiently. To overcome this, we present an FPGA-based CNN-BiLSTM accelerator that incorporates several algorithm-hardware co-design techniques to enable efficient edge inference. Central to this design is an FFT-based non-unit stride fast convolution, which performs accumulation in the frequency domain to enable a single IFFT per block, reducing post-processing complexity to $O(N\log N)$. On the target long-kernel convolution layer, this yields a 20.5$\times$ reduction in arithmetic operations. Power-of-two quantization is applied across the pipeline, including FFT-based convolution and BiLSTM activations, with an average accuracy degradation of only 0.11% relative to the floating-point baseline across all subjects on the public MASS-SS3 dataset. Additional optimizations, including block convolution, depth-first execution, and hardware engine reuse minimize memory access and enhance resource utilization. The accelerator, implemented on a Xilinx Zynq-7000 FPGA, operates at 10 MHz and consumes 11 mW of dynamic power including data handling and configuration overhead from a microcontroller. The design achieves a DSP power efficiency of 0.91 GOPS/W/DSP using only 4 DSPs, demonstrating scalable and energy-efficient DL acceleration for sleep staging that can be extended to other wearable applications.

cs.AR↗

Asymptotic spreading speeds of a road-field reaction-diffusion predator-prey model

This paper is devoted to studying asymptotic spreading speeds of a road-field reaction-diffusion predator-prey system, in which predators diffuse faster on the straight line $\R\times \{0\}$ than in the half plane $\R\times (0,+\infty)$. We give a sharp characterization of the spreading properties of solutions of the system with compactly supported initial values by appealing to the invasion speed of the prey when predators are absent, and the invasion speed of predators when the prey is saturated. Notably, since the line may accelerate the expansion of predators in a cone of directions, the invasion speed of predators varies with the direction. To overcome the difficulty arising from the coupling between the predator-prey interaction and the road-field interaction, we first derive pointwise comparisons between predators and the prey and then reduce the components of predators in the system to a truncated field-road system depending on the invasion speed of the prey. By using known results for the single-species field-road model, we further show the propagation properties of the truncated system. This step is very crucial. Once the propagation properties of the truncated system are established, we can obtain the expected spreading properties of solutions to the original system by applying the comparison principle and contradiction arguments, and constructing appropriate Lyapunov functionals.

math.AP↗

FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA

Financial QA systems are typically improved before deployment through better retrieval, prompting, or agent coordination, leaving their reliability behavior fixed thereafter. In practice, new SEC-filing questions repeatedly expose heterogeneous errors in period, entity, evidence use, and calculation. Existing self-improvement methods can turn failures into new behaviors, but offer limited control over where a correction should apply or which previously correct answers it may break. We therefore frame post-deployment improvement as controlled behavioral maintenance: recurring failures should become scoped skill patches, and each patch should earn deployment with- out introducing regressions. We instantiate this view in FINSKILLOPS, a multi-agent system for SEC filing QA. FINSKILLOPS derives reusable skills from evidence-grounded, typed failure diagnoses and governs them through targeted validation, protected-case regression checks, negative controls, and versioned replacement or retirement. Across six financial QA benchmarks, a single frozen skill registry achieves the highest verdict-weighted correctness and reference consistency among the evaluated systems. Evolved skills raise correctness from 3.70 to 4.55 on our enhanced benchmark. In a separate 12-round operational study, only six of 33 proposed skills are promoted, while the monitoring non-correct rate falls from 20.0% to 12.5%. These results establish controlled skill scope, admission, and lifecycle management as the foundation for reliable self-improvement.

cs.AI↗

Federated Covariate Shift Adaptation for Missing Target Output Values

The most recent multi-source covariate shift algorithm is an efficient hyperparameter optimization algorithm for missing target output. In this paper, we extend this algorithm to the framework of federated learning. For data islands in federated learning and covariate shift adaptation, we propose the federated domain adaptation estimate of the target risk which is asymptotically unbiased with a desirable asymptotic variance property. We construct a weighted model for the target task and propose the federated covariate shift adaptation algorithm which works preferably in our setting. The efficacy of our method is justified both theoretically and empirically.

stat.ML↗

A Closed-loop Sleep Modulation System with FPGA-Accelerated Deep Learning

Closed-loop sleep modulation is an emerging research paradigm to treat sleep disorders and enhance sleep benefits. However, two major barriers hinder the widespread application of this research paradigm. First, subjects often need to be wire-connected to rack-mount instrumentation for data acquisition, which negatively affects sleep quality. Second, conventional real-time sleep stage classification algorithms give limited performance. In this work, we conquer these two limitations by developing a sleep modulation system that supports closed-loop operations on the device. Sleep stage classification is performed using a lightweight deep learning (DL) model accelerated by a low-power field-programmable gate array (FPGA) device. The DL model uses a single channel electroencephalogram (EEG) as input. Two convolutional neural networks (CNNs) are used to capture general and detailed features, and a bidirectional long-short-term memory (LSTM) network is used to capture time-variant sequence features. An 8-bit quantization is used to reduce the computational cost without compromising performance. The DL model has been validated using a public sleep database containing 81 subjects, achieving a state-of-the-art classification accuracy of 85.8% and a F1-score of 79%. The developed model has also shown the potential to be generalized to different channels and input data lengths. Closed-loop in-phase auditory stimulation has been demonstrated on the test bench.

eess.SP↗

An Ontology-Based Reasoning Framework for Context-Aware Applications

Context-aware applications process context information to support users in their daily tasks and routines. These applications can adapt their functionalities by aggregating context information through machine-learning and data processing algorithms, supporting users with recommendations or services based on their current needs. In the last years, smartphones have been used in the field of context-awareness due to their embedded sensors and various communication interfaces such as Bluetooth, WiFi, NFC or cellular. However, building context-aware applications for smartphones can be a challenging and time-consuming task. In this paper, we describe an ontology-based reasoning framework to create context-aware applications. The framework is based on an ontology as well as micro-services to aggregate, process and represent context information.

cs.HC↗