arXiv subjects

Yi Zou

Publications and source records attributed to Yi Zou.

At least 37 records · Page 2Linked to original sources

arXiv2025

A Novel Discrete Memristor-Coupled Heterogeneous Dual-Neuron Model and Its Application in Multi-Scenario Image Encryption

Simulating brain functions using neural networks is an important area of research. Recently, discrete memristor-coupled neurons have attracted significant attention, as memristors effectively mimic synaptic behavior, which is essential for learning and memory. This highlights the biological relevance of such models. This study introduces a discrete memristive heterogeneous dual-neuron network (MHDNN). The stability of the MHDNN is analyzed with respect to initial conditions and a range of neuronal parameters. Numerical simulations demonstrate complex dynamical behaviors. Various neuronal firing patterns are investigated under different coupling strengths, and synchronization phenomena between neurons are explored. The MHDNN is implemented and validated on the STM32 hardware platform. An image encryption algorithm based on the MHDNN is proposed, along with two hardware platforms tailored for multi-scenario police image encryption. These solutions enable real-time and secure transmission of police data in complex environments, reducing hacking risks and enhancing system security.

cs.IR↗

arXiv2025

MambaMIC: An Efficient Baseline for Microscopic Image Classification with State Space Models

In recent years, CNN and Transformer-based methods have made significant progress in Microscopic Image Classification (MIC). However, existing approaches still face the dilemma between global modeling and efficient computation. While the Selective State Space Model (SSM) can simulate long-range dependencies with linear complexity, it still encounters challenges in MIC, such as local pixel forgetting, channel redundancy, and lack of local perception. To address these issues, we propose a simple yet efficient vision backbone for MIC tasks, named MambaMIC. Specifically, we introduce a Local-Global dual-branch aggregation module: the MambaMIC Block, designed to effectively capture and fuse local connectivity and global dependencies. In the local branch, we use local convolutions to capture pixel similarity, mitigating local pixel forgetting and enhancing perception. In the global branch, SSM extracts global dependencies, while Locally Aware Enhanced Filter reduces channel redundancy and local pixel forgetting. Additionally, we design a Feature Modulation Interaction Aggregation Module for deep feature interaction and key feature re-localization. Extensive benchmarking shows that MambaMIC achieves state-of-the-art performance across five datasets. code is available at https://zs1314.github.io/MambaMIC

cs.CV↗

arXiv2025

Fraesormer: Learning Adaptive Sparse Transformer for Efficient Food Recognition

In recent years, Transformer has witnessed significant progress in food recognition. However, most existing approaches still face two critical challenges in lightweight food recognition: (1) the quadratic complexity and redundant feature representation from interactions with irrelevant tokens; (2) static feature recognition and single-scale representation, which overlook the unstructured, non-fixed nature of food images and the need for multi-scale features. To address these, we propose an adaptive and efficient sparse Transformer architecture (Fraesormer) with two core designs: Adaptive Top-k Sparse Partial Attention (ATK-SPA) and Hierarchical Scale-Sensitive Feature Gating Network (HSSFGN). ATK-SPA uses a learnable Gated Dynamic Top-K Operator (GDTKO) to retain critical attention scores, filtering low query-key matches that hinder feature aggregation. It also introduces a partial channel mechanism to reduce redundancy and promote expert information flow, enabling local-global collaborative modeling. HSSFGN employs gating mechanism to achieve multi-scale feature representation, enhancing contextual semantic information. Extensive experiments show that Fraesormer outperforms state-of-the-art methods. code is available at https://zs1314.github.io/Fraesormer.

cs.CV↗

arXiv2025

Learning Dual-Domain Multi-Scale Representations for Single Image Deraining

Existing image deraining methods typically rely on single-input, single-output, and single-scale architectures, which overlook the joint multi-scale information between external and internal features. Furthermore, single-domain representations are often too restrictive, limiting their ability to handle the complexities of real-world rain scenarios. To address these challenges, we propose a novel Dual-Domain Multi-Scale Representation Network (DMSR). The key idea is to exploit joint multi-scale representations from both external and internal domains in parallel while leveraging the strengths of both spatial and frequency domains to capture more comprehensive properties. Specifically, our method consists of two main components: the Multi-Scale Progressive Spatial Refinement Module (MPSRM) and the Frequency Domain Scale Mixer (FDSM). The MPSRM enables the interaction and coupling of multi-scale expert information within the internal domain using a hierarchical modulation and fusion strategy. The FDSM extracts multi-scale local information in the spatial domain, while also modeling global dependencies in the frequency domain. Extensive experiments show that our model achieves state-of-the-art performance across six benchmark datasets.

cs.CV↗

arXiv2025

A Flexible Precision Scaling Deep Neural Network Accelerator with Efficient Weight Combination

Deploying mixed-precision neural networks on edge devices is friendly to hardware resources and power consumption. To support fully mixed-precision neural network inference, it is necessary to design flexible hardware accelerators for continuous varying precision operations. However, the previous works have issues on hardware utilization and overhead of reconfigurable logic. In this paper, we propose an efficient accelerator for 2~8-bit precision scaling with serial activation input and parallel weight preloaded. First, we set two loading modes for the weight operands and decompose the weight into the corresponding bitwidths, which extends the weight precision support efficiently. Then, to improve hardware utilization of low-precision operations, we design the architecture that performs bit-serial MAC operation with systolic dataflow, and the partial sums are combined spatially. Furthermore, we designed an efficient carry save adder tree supporting both signed and unsigned number summation across rows. The experiment result shows that the proposed accelerator, synthesized with TSMC 28nm CMOS technology, achieves peak throughput of 4.09TOPS and peak energy efficiency of 68.94TOPS/W at 2/2-bit operations.

cs.AR↗

arXiv2024

Co-benefits of Agricultural Diversification and Technology for Food and Nutrition Security in China

China is the leading crop producer and has successfully implemented sustainable development programs related to agriculture. Sustainable agriculture has been promoted to achieve national food security targets such as food self-sufficiency through the well-facilitated farmland construction (WFFC) approach. The WFFC is introduced in Chinas current national 10-year plan to consolidate farmlands into large and simplified production areas to maximise automation, and improve soil fertility and productivity. However, research suggests that diversified and smaller farms faciliate ecosystem services, can improve yield resilience, defuse human health threats, and increase farm profitability. Currently, WFFC has not considered ecological farmland improvements and it may miss long-term environmental benefits including ecosystem service preservation conducive to yields. Moreover, the nutritional status in China has changed in recent decades with undernutrition being dramatically reduced, but the prevalence of overweight, obesity, and chronic diseases being increased. While a strategic choice and management of crop and livestock species can improve nutrition, the environmental and production benefits of agricultural diversification are currently not well interlinked with Chinas food and nutrition security discussions. Lastly, the role of agricultural technology for socioeconomic benefits and the link with diversified agricultural production may provide vast benefits for food security. Here, we focus on the opportunities and co-benefits of agricultural diversification and technology innovations to advance food and nutrition security in China through ecosystem service and yield benefits. Our applied five-point research agenda can provide evidence-based opportunities to support China in reaching its ambitious food security targets through agricultural diversification with global ramifications.

econ.GN↗

arXiv2024

SoK: Rowhammer on Commodity Operating Systems

Rowhammer has drawn much attention from both academia and industry in the past years as rowhammer exploitation poses severe consequences to system security. Since the first comprehensive study of rowhammer in 2014, a number of rowhammer attacks have been demonstrated against dynamic random access memory (DRAM)-based commodity systems to break software confidentiality, integrity and availability. Accordingly, numerous software defenses have been proposed to mitigate rowhammer attacks on commodity systems of either legacy (e.g., DDR3) or recent DRAM (e.g., DDR4). Besides, multiple hardware defenses (e.g., Target Row Refresh) from the industry have been deployed into recent DRAM to eliminate rowhammer, which we categorize as production defenses. In this paper, we systematize rowhammer attacks and defenses with a focus on DRAM-based commodity systems. Particularly, we have established a unified framework demonstrating how a rowhammer attack affects a commodity system. With the framework, we characterize existing attacks, shedding light on new attack vectors that have not yet been explored. We further leverage the framework to categorize software and production defenses, generalize their key defense strategies and summarize their key limitations, from which potential defense strategies are identified.

cs.CR↗

arXiv2023

ESGReveal: An LLM-based approach for extracting structured data from ESG reports

ESGReveal is an innovative method proposed for efficiently extracting and analyzing Environmental, Social, and Governance (ESG) data from corporate reports, catering to the critical need for reliable ESG information retrieval. This approach utilizes Large Language Models (LLM) enhanced with Retrieval Augmented Generation (RAG) techniques. The ESGReveal system includes an ESG metadata module for targeted queries, a preprocessing module for assembling databases, and an LLM agent for data extraction. Its efficacy was appraised using ESG reports from 166 companies across various sectors listed on the Hong Kong Stock Exchange in 2022, ensuring comprehensive industry and market capitalization representation. Utilizing ESGReveal unearthed significant insights into ESG reporting with GPT-4, demonstrating an accuracy of 76.9% in data extraction and 83.7% in disclosure analysis, which is an improvement over baseline models. This highlights the framework's capacity to refine ESG data analysis precision. Moreover, it revealed a demand for reinforced ESG disclosures, with environmental and social data disclosures standing at 69.5% and 57.2%, respectively, suggesting a pursuit for more corporate transparency. While current iterations of ESGReveal do not process pictorial information, a functionality intended for future enhancement, the study calls for continued research to further develop and compare the analytical capabilities of various LLMs. In summary, ESGReveal is a stride forward in ESG data processing, offering stakeholders a sophisticated tool to better evaluate and advance corporate sustainability efforts. Its evolution is promising in promoting transparency in corporate reporting and aligning with broader sustainable development aims.

cs.CL↗

arXiv2023

SleepEGAN: A GAN-enhanced Ensemble Deep Learning Model for Imbalanced Classification of Sleep Stages

Deep neural networks have played an important role in automatic sleep stage classification because of their strong representation and in-model feature transformation abilities. However, class imbalance and individual heterogeneity which typically exist in raw EEG signals of sleep data can significantly affect the classification performance of any machine learning algorithms. To solve these two problems, this paper develops a generative adversarial network (GAN)-powered ensemble deep learning model, named SleepEGAN, for the imbalanced classification of sleep stages. To alleviate class imbalance, we propose a new GAN (called EGAN) architecture adapted to the features of EEG signals for data augmentation. The generated samples for the minority classes are used in the training process. In addition, we design a cost-free ensemble learning strategy to reduce the model estimation variance caused by the heterogeneity between the validation and test sets, so as to enhance the accuracy and robustness of prediction performance. We show that the proposed method can improve classification accuracy compared to several existing state-of-the-art methods using three public sleep datasets.

eess.SP↗

arXiv2022

Artificial gauge field enabled low-crosstalk, broadband, half-wavelength-pitched waveguide arrays

Dense waveguide arrays with half-wavelength-pitch, low-crosstalk, broadband, and flexible routing capability are essential for integrated photonics. However, achieving such performance is challenging due to the relatively weaker confinement of dielectric waveguides and the increased interactions among densely packed waveguides. Here, leveraging the artificial gauge field mechanism, we demonstrate half-wavelength-pitched dense waveguide arrays, consisting of 64 waveguides, in silicon with -30dB crosstalk suppression from 1480nm to 1550nm. The waveguide array features negligible insertion loss for 90-degree bending. Our approach enables flexibly routing a large-scale dense waveguide array that significantly reduces on-chip estate, leading to a high-density photonic integrated circuit, and may open up opportunities for important device performance improvement, such as half-wavelength-pitch OPA and ultra-dense space-division multiplexing

physics.optics↗

arXiv2021

A High-Q Vertical Light Emission From Active Parity-Time Symmetric Gratings

This work presents a theoretical investigation of an active photonic grating of the parity-time (PT) symmetric architecture. The analytical study of the free-space mode propagation from the grating structure indicates the unique bifurcation property due to the PT-symmetry modulation. It is shown that both the gain/loss contrast and the lattice constant parameters are critical factors to modulate the active photonic system in between the PT-symmetry to the symmetry-broken phases. Furthermore, numerical simulations via the Rigorous Coupled-Wave Analysis (RCWA) method discover the existence of a unique Spectral Singularity (SS) phenomenon in this PT grating structure, which corresponds to a non-trivial single-mode and near-zero bandwidth photonic resonant emission. Also, the guiding procedure for fulfilling SS modes is found to be related to the unique formation of the scattering matrix applied in the PT-symmetric photonic gratings. This theoretical work takes a fresh look into the active PT-symmetric photonic gratings focusing on the discovery of new free-space emission modes rather than the commonly studied unidirectional properties, which could contribute to the development of novel low-threshold and super-coherent surface-emitting devices.

physics.optics↗

arXiv2021

MELONS: generating melody with long-term structure using transformers and structure graph

The creation of long melody sequences requires effective expression of coherent musical structure. However, there is no clear representation of musical structure. Recent works on music generation have suggested various approaches to deal with the structural information of music, but generating a full-song melody with clear long-term structure remains a challenge. In this paper, we propose MELONS, a melody generation framework based on a graph representation of music structure which consists of eight types of bar-level relations. MELONS adopts a multi-step generation method with transformer-based networks by factoring melody generation into two sub-problems: structure generation and structure conditional melody generation. Experimental results show that MELONS can produce structured melodies with high quality and rich contents.

cs.SD↗

arXiv2021

Topological Sensing with Photonic Arrays of Resonant Circular Waveguides

We propose that a photonic array of resonant circular dielectric waveguides with subwavelength grating can be designed as a robust and sensitive topological chemical sensor. The device can detect trace amounts of a given chemical species through photonic edge modes that are impervious to most sources of disorder. We perform a simulation in the mid-infrared that accounts for the absorption loss introduced by chemical molecules in contact with a strongly coupled photonic lattice of resonators. Due to the topological nature of the device, its chemical sensitivity scales linearly with the system size and can reach parts-per-billion range at the millimeter scale. Our findings suggest that topological chemical sensors could empower the development of novel on-chip integrated photonic sensing technologies.

physics.optics↗

arXiv2021

Context-aware Ensemble of Multifaceted Factorization Models for Recommendation Prediction in Social Networks

This paper describes the solution of Shanda Innovations team to Task 1 of KDD-Cup 2012. A novel approach called Multifaceted Factorization Models is proposed to incorporate a great variety of features in social networks. Social relationships and actions between users are integrated as implicit feedbacks to improve the recommendation accuracy. Keywords, tags, profiles, time and some other features are also utilized for modeling user interests. In addition, user behaviors are modeled from the durations of recommendation records. A context-aware ensemble framework is then applied to combine multiple predictors and produce final recommendation results. The proposed approach obtained 0.43959 (public score) / 0.41874 (private score) on the testing dataset, which achieved the 2nd place in the KDD-Cup competition.

cs.IR↗

arXiv2020

Parity-Time Symmetry in Non-Hermitian Complex Optical Media

The explorations of the quantum-inspired symmetries in optical and photonic systems have witnessed immense research interests both fundamentally and technologically in a wide range of subjects of physics and engineering. One of the principal emerging fields in this context is non-Hermitian physics based on parity-time symmetry, originally proposed in the studies pertaining to quantum mechanics and quantum field theory, recently ramified into diverse set of areas, particularly in optics and photonics. The intriguing physical effects enabled by non-Hermitian physics and PT symmetry have enhanced significant applications prospects and engineering of novel materials. In addition, it has observed increasing research interests in many emerging directions beyond optics and photonics. This Review paper attempts to bring together the state of the art developments in the field of complex non-Hermitian physics based on PT symmetry in various physical settings along with elucidating key concepts and background and a detailed perspective on new emerging directions. It can be anticipated that this trendy field of interest can be indispensable in providing new perspectives in maneuvering the flow of light in the diverse physical platforms in optics, photonics, condensed matter, opto-electronics and beyond, and offer distinctive applications prospects in novel functional materials.

physics.optics↗

arXiv2018

High-Q mid-infrared chalcogenide glass resonators

In this letter, we fabricated and characterized chalcogenide glass resonators monolithically integrated on mid-infrared transparent CaF2 substrates. The devices feature an intrinsic Q-factor of 4E5 at 5.2 micron wavelength, which represents the highest Q-factor reported in planar mid-infrared resonators. It is found that moisture can significantly impact the device performance when the device was exposed to an ambient environment, although the high-Q characteristics can be restored after undergoing an annealing treatment. Using these devices, we further demonstrated on-chip cavity-enhanced spectroscopy to quantify mid-IR absorption of ethanol solutions around 5.2 micron wavelength.

cond-mat.mtrl-sci↗

arXiv2014

Electric field sensor based on electro-optic polymer refilled silicon slot photonic crystal waveguide coupled with bowtie antenna

We present the design of a compact and highly sensitive electric field sensor based on a bowtie antenna-coupled slot photonic crystal waveguide (PCW). An electro-optic (EO) polymer with a large EO coefficient, r33=100pm/V, is used to refill the PCW slot and air holes. Bowtie-shaped electrodes are used as both poling electrodes and as receiving antenna. The slow-light effect in the PCW is used to increase the effective in-device r33>1000pm/V. The slot PCW is designed for low-dispersion slow light propagation, maximum poling efficiency as well as optical mode confinement inside the EO polymer. The antenna is designed for operation at 10GHz.

physics.optics↗

arXiv2013

High-Performance, High-Index-Contrast Chalcogenide Glass Photonics on Silicon and Unconventional Non-planar Substrates

This paper reports a versatile, roll-to-roll and backend compatible technique for the fabrication of high-index-contrast photonic structures on both silicon and plastic substrates. The fabrication technique combines low-temperature chalcogenide glass film deposition and resist-free single-step thermal nanoimprint to process low-loss (1.6 dB/cm), sub-micron single-mode waveguides with a smooth surface finish using simple contact photolithography. Using this approach, the first chalcogenide glass micro-ring resonators are fabricated by thermal nanoimprint. The devices exhibit an ultra-high quality-factor of 400,000 near 1550 nm wavelength, which represents the highest value reported in chalcogenide glass micro-ring resonators. Furthermore, sub-micron nanoimprint of chalcogenide glass films on non-planar plastic substrates is demonstrated, which establishes the method as a facile route for monolithic fabrication of high-index-contrast devices on a wide array of unconventional substrates.

physics.optics↗