Searcharxiv⌕ Search

arXiv subjects

Can Li

Publications and source records attributed to Can Li.

At least 73 records · Page 4Linked to original sources
arXiv2023

DiskANN++: Efficient Page-based Search over Isomorphic Mapped Graph Index using Query-sensitivity Entry Vertex

Given a vector dataset $\mathcal{X}$ and a query vector $\vec{x}_q$, graph-based Approximate Nearest Neighbor Search (ANNS) aims to build a graph index $G$ and approximately return vectors with minimum distances to $\vec{x}_q$ by searching over $G$. The main drawback of graph-based ANNS is that a graph index would be too large to fit into the memory especially for a large-scale $\mathcal{X}$. To solve this, a Product Quantization (PQ)-based hybrid method called DiskANN is proposed to store a low-dimensional PQ index in memory and retain a graph index in SSD, thus reducing memory overhead while ensuring a high search accuracy. However, it suffers from two I/O issues that significantly affect the overall efficiency: (1) long routing path from an entry vertex to the query's neighborhood that results in large number of I/O requests and (2) redundant I/O requests during the routing process. We propose an optimized DiskANN++ to overcome above issues. Specifically, for the first issue, we present a query-sensitive entry vertex selection strategy to replace DiskANN's static graph-central entry vertex by a dynamically determined entry vertex that is close to the query. For the second I/O issue, we present an isomorphic mapping on DiskANN's graph index to optimize the SSD layout and propose an asynchronously optimized Pagesearch based on the optimized SSD layout as an alternative to DiskANN's beamsearch. Comprehensive experimental studies on eight real-world datasets demonstrate our DiskANN++'s superiority on efficiency. We achieve a notable 1.5 X to 2.2 X improvement on QPS compared to DiskANN, given the same accuracy constraint.

cs.IR↗
arXiv2023

UniMOS: A Universal Framework For Multi-Organ Segmentation Over Label-Constrained Datasets

Machine learning models for medical images can help physicians diagnose and manage diseases. However, due to the fact that medical image annotation requires a great deal of manpower and expertise, as well as the fact that clinical departments perform image annotation based on task orientation, there is the problem of having fewer medical image annotation data with more unlabeled data and having many datasets that annotate only a single organ. In this paper, we present UniMOS, the first universal framework for achieving the utilization of fully and partially labeled images as well as unlabeled images. Specifically, we construct a Multi-Organ Segmentation (MOS) module over fully/partially labeled data as the basenet and designed a new target adaptive loss. Furthermore, we incorporate a semi-supervised training module that combines consistent regularization and pseudolabeling techniques on unlabeled data, which significantly improves the segmentation of unlabeled data. Experiments show that the framework exhibits excellent performance in several medical image segmentation tasks compared to other advanced methods, and also significantly improves data utilization and reduces annotation cost. Code and models are available at: https://github.com/lw8807001/UniMOS.

eess.IV↗
arXiv2023

A Feasible Conjugate Gradient Method for Calculating $\mathcal B$-Eigenpairs of Symmetric Tensors

In this paper, we propose a feasible conjugate gradient (FCG) method for calculating ${\mathcal B}$-eigenpairs of a symmetric tensor ${\mathcal A}$. The method is an extension of the well-known conjugate gradient method for unconstrained optimization problems to some curve constrained optimization problems. The proposed FCG method can find a ${\mathcal B}$-eigenpair of a symmetric tensor ${\mathcal A}$ without the requirement that the orders of ${\mathcal A}$ and $\mathcal B$ are equal. We pay particular attention to the Polak-Ribíre-Polyak (PRP) type conjugate gradient method. We show that the FCG method with some Armijo-type line search is globally convergent. Our numerical experiments indicate the promising performance of the proposed method.

math.OC↗
arXiv2023

SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features

In comparison to conventional RGB cameras, the superior temporal resolution of event cameras allows them to capture rich information between frames, making them prime candidates for object tracking. Yet in practice, despite their theoretical advantages, the body of work on event-based multi-object tracking (MOT) remains in its infancy, especially in real-world settings where events from complex background and camera motion can easily obscure the true target motion. In this work, an event-based multi-object tracker, called SpikeMOT, is presented to address these challenges. SpikeMOT leverages spiking neural networks to extract sparse spatiotemporal features from event streams associated with objects. The resulting spike train representations are used to track the object movement at high frequency, while a simultaneous object detector provides updated spatial information of these objects at an equivalent frame rate. To evaluate the effectiveness of SpikeMOT, we introduce DSEC-MOT, the first large-scale event-based MOT benchmark incorporating fine-grained annotations for objects experiencing severe occlusions, frequent trajectory intersections, and long-term re-identification in real-world contexts. Extensive experiments employing DSEC-MOT and another event-based dataset, named FE240hz, demonstrate SpikeMOT's capability to achieve high tracking accuracy amidst challenging real-world scenarios, advancing the state-of-the-art in event-based multi-object tracking.

cs.CV↗
arXiv2023

Diagnosing Infeasible Optimization Problems Using Large Language Models

Decision-making problems can be represented as mathematical optimization models, finding wide applications in fields such as economics, engineering and manufacturing, transportation, and health care. Optimization models are mathematical abstractions of the problem of making the best decision while satisfying a set of requirements or constraints. One of the primary barriers to deploying these models in practice is the challenge of helping practitioners understand and interpret such models, particularly when they are infeasible, meaning no decision satisfies all the constraints. Existing methods for diagnosing infeasible optimization models often rely on expert systems, necessitating significant background knowledge in optimization. In this paper, we introduce OptiChat, a first-of-its-kind natural language-based system equipped with a chatbot GUI for engaging in interactive conversations about infeasible optimization models. OptiChat can provide natural language descriptions of the optimization model itself, identify potential sources of infeasibility, and offer suggestions to make the model feasible. The implementation of OptiChat is built on GPT-4, which interfaces with an optimization solver to identify the minimal subset of constraints that render the entire optimization problem infeasible, also known as the Irreducible Infeasible Subset (IIS). We utilize few-shot learning, expert chain-of-thought, key-retrieve, and sentiment prompts to enhance OptiChat's reliability. Our experiments demonstrate that OptiChat assists both expert and non-expert users in improving their understanding of the optimization models, enabling them to quickly identify the sources of infeasibility.

cs.HC↗
arXiv2023

Realizing In-Memory Baseband Processing for Ultra-Fast and Energy-Efficient 6G

To support emerging applications ranging from holographic communications to extended reality, next-generation mobile wireless communication systems require ultra-fast and energy-efficient baseband processors. Traditional complementary metal-oxide-semiconductor (CMOS)-based baseband processors face two challenges in transistor scaling and the von Neumann bottleneck. To address these challenges, in-memory computing-based baseband processors using resistive random-access memory (RRAM) present an attractive solution. In this paper, we propose and demonstrate RRAM-implemented in-memory baseband processing for the widely adopted multiple-input-multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) air interface. Its key feature is to execute the key operations, including discrete Fourier transform (DFT) and MIMO detection using linear minimum mean square error (L-MMSE) and zero forcing (ZF), in one-step. In addition, RRAM-based channel estimation module is proposed and discussed. By prototyping and simulations, we demonstrate the feasibility of RRAM-based full-fledged communication system in hardware, and reveal it can outperform state-of-the-art baseband processors with a gain of 91.2$\times$ in latency and 671$\times$ in energy efficiency by large-scale simulations. Our results pave a potential pathway for RRAM-based in-memory computing to be implemented in the era of the sixth generation (6G) mobile communications.

eess.SP↗
arXiv2023

High-precision and low-latency widefield diamond quantum sensing with neuromorphic vision sensors

During the past decade, interest has grown significantly in developing ultrasensitive widefield diamond magnetometry for various applications. Despite attempts to improve the adoption of conventional frame-based sensors, achieving high temporal resolution and sensitivity simultaneously remains a key challenge. This is largely due to the transfer and processing of massive amounts of sensor data to capture the widefield fluorescence intensity changes of spin defects in diamonds. In this study, we adopt a neuromorphic vision sensor to address this issue. This sensor pre-processes the detected signals in optically detected magnetic resonance (ODMR) measurements for quantum sensing, employing a working principle that closely resembles the operation of the human vision system. By encoding the changes of light intensity into spikes, this approach results in a vast dynamic range, high temporal resolution, and exceptional signal-to-background ratio. After a thorough evaluation of theoretical feasibility, our experiment with an off-the-shelf event camera demonstrated a 13x improvement in temporal resolution with comparable precision of detecting ODMR resonance frequencies compared with the state-of-the-art highly specialized frame-based approach. A specialized camera system with the same mechanism has the potential to enhance these benefits further. This performance improvement is primarily attributable to orders of magnitude smaller data volumes and, thus, reduced latency. We further showcase the deployment of this technology in monitoring dynamically modulated laser heating of gold nanoparticles coated on a diamond surface, a recognizably difficult task using existing approaches. The current development provides new insights for high-precision and low-latency widefield quantum sensing, with possibilities for integration with emerging memory devices for more efficient event-based data processing.

physics.ins-det↗
arXiv2023

Combinatorial-restless-bandit-based Transmitter-Receiver Online Selection for Distributed MIMO Radars With Non-Stationary Channels

We track moving targets with a distributed multiple-input multiple-output (MIMO) radar, for which the transmitters and receivers are appropriately paired and selected with a limited number of radar stations. We aim to maximize the sum of the signal-to-interference-plus-noise ratios (SINRs) of all the targets by sensibly selecting the transmitter-receiver pairs during the tracking period. A key is to model the optimization problem of selecting the transmitter-receiver pairs by a restless multi-armed bandit (RMAB) model that is able to formulate the time-varying signals of the transceiver channels whenever the channels are being probed or not. We regard the estimated mean reward (i.e., SINR) as the state of an arm. If an arm is probed, the estimated mean reward of the arm is the weighted sum of the observed reward and the predicted mean reward; otherwise, it is the predicted mean reward. We associate the predicted mean reward with the estimated mean reward at the previous time slot and the state of the target, which is estimated via the interacting multiple model-unscented Kalman filter (IMM-UKF). The optimized selection of transmitter-receiver pairs at each time is accomplished by using Binary Particle Swarm Optimization (BPSO) based on indexes of arms, each of which is designed by the upper confidence bound (UCB1) algorithm. Above all, a multi-group combinatorial-restless-bandit technique taking into account of different combinations of transmitters and receivers and the closed-loop scheme between transmitter-receiver pair selection and target state estimation, namely MG-CRB-CL, is developed to achieve a near-optimal selection strategy and improve multi-target tracking performance. Simulation results for different scenarios are provided to verify the effectiveness and superior performance of our MG-CRB-CL algorithm.

eess.SY↗
arXiv2023

A Voice Disease Detection Method Based on MFCCs and Shallow CNN

The incidence rate of voice diseases is increasing year by year. The use of software for remote diagnosis is a technical development trend and has important practical value. Among voice diseases, common diseases that cause hoarseness include spasmodic dysphonia, vocal cord paralysis, vocal nodule, and vocal cord polyp. This paper presents a voice disease detection method that can be applied in a wide range of clinical. We cooperated with Xiangya Hospital of Central South University to collect voice samples from sixty-one different patients. The Mel Frequency Cepstrum Coefficient (MFCC) parameters are extracted as input features to describe the voice in the form of data. An innovative model combining MFCC parameters and single convolution layer CNN is proposed for fast calculation and classification. The highest accuracy we achieved was 92%, it is fully ahead of the original research results and internationally advanced. And we use Advanced Voice Function Assessment Databases (AVFAD) to evaluate the generalization ability of the method we proposed, which achieved an accuracy rate of 98%. Experiments on clinical and standard datasets show that for the pathological detection of voice diseases, our method has greatly improved in accuracy and computational efficiency.

cs.SD↗
arXiv2023

Scalable Causal Structure Learning: Scoping Review of Traditional and Deep Learning Algorithms and New Opportunities in Biomedicine

Causal structure learning refers to a process of identifying causal structures from observational data, and it can have multiple applications in biomedicine and health care. This paper provides a practical review and tutorial on scalable causal structure learning models with examples of real-world data to help health care audiences understand and apply them. We reviewed traditional (combinatorial and score-based methods) for causal structure discovery and machine learning-based schemes. We also highlighted recent developments in biomedicine where causal structure learning can be applied to discover structures such as gene networks, brain connectivity networks, and those in cancer epidemiology. We also compared the performance of traditional and machine learning-based algorithms for causal discovery over some benchmark data sets. Machine learning-based approaches, including deep learning, have many advantages over traditional approaches, such as scalability, including a greater number of variables, and potentially being applied in a wide range of biomedical applications, such as genetics, if sufficient data are available. Furthermore, these models are more flexible than traditional models and are poised to positively affect many applications in the future.

cs.LG↗
arXiv2022

Robust Multitarget Tracking in Interference Environments: A Message-Passing Approach

Multitarget tracking in the interference environments suffers from the nonuniform, unknown and time-varying clutter, resulting in dramatic performance deterioration. We address this challenge by proposing a robust multitarget tracking algorithm, which estimates the states of clutter and targets simultaneously by the message-passing (MP) approach. We define the non-homogeneous clutter with a finite mixture model containing a uniform component and multiple nonuniform components. The measured signal strength is utilized to estimate the mean signal-to-noise ratio (SNR) of targets and the mean clutter-to-noise ratio (CNR) of clutter, which are then used as additional feature information of targets and clutter to improve the performance of discrimination of targets from clutter. We also present a hybrid data association which can reason over correspondence between targets, clutter, and measurements. Then, a unified MP algorithm is used to infer the marginal posterior probability distributions of targets, clutter, and data association by splitting the joint probability distribution into a mean-field approximate part and a belief propagation part. As a result, a closed-loop iterative optimization of the posterior probability distribution can be obtained, which can effectively deal with the coupling between target tracking, clutter estimation and data association. Simulation results demonstrate the performance superiority and robustness of the proposed multitarget tracking algorithm compared with the probability hypothesis density (PHD) filter and the cardinalized PHD (CPHD) filter.

eess.SY↗
arXiv2022

A Bibliometric Analysis and Review on Reinforcement Learning for Transportation Applications

Transportation is the backbone of the economy and urban development. Improving the efficiency, sustainability, resilience, and intelligence of transportation systems is critical and also challenging. The constantly changing traffic conditions, the uncertain influence of external factors (e.g., weather, accidents), and the interactions among multiple travel modes and multi-type flows result in the dynamic and stochastic natures of transportation systems. The planning, operation, and control of transportation systems require flexible and adaptable strategies in order to deal with uncertainty, non-linearity, variability, and high complexity. In this context, Reinforcement Learning (RL) that enables autonomous decision-makers to interact with the complex environment, learn from the experiences, and select optimal actions has been rapidly emerging as one of the most useful approaches for smart transportation. This paper conducts a bibliometric analysis to identify the development of RL-based methods for transportation applications, typical journals/conferences, and leading topics in the field of intelligent transportation in recent ten years. Then, this paper presents a comprehensive literature review on applications of RL in transportation by categorizing different methods with respect to the specific application domains. The potential future research directions of RL applications and developments are also discussed.

cs.LG↗
arXiv2022

DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding

This paper presents DavarOCR, an open-source toolbox for OCR and document understanding tasks. DavarOCR currently implements 19 advanced algorithms, covering 9 different task forms. DavarOCR provides detailed usage instructions and the trained models for each algorithm. Compared with the previous opensource OCR toolbox, DavarOCR has relatively more complete support for the sub-tasks of the cutting-edge technology of document understanding. In order to promote the development and application of OCR technology in academia and industry, we pay more attention to the use of modules that different sub-domains of technology can share. DavarOCR is publicly released at https://github.com/hikopensource/Davar-Lab-OCR.

cs.CV↗
arXiv2022

TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents

Recently, automatically extracting information from visually rich documents (e.g., tickets and resumes) has become a hot and vital research topic due to its widespread commercial value. Most existing methods divide this task into two subparts: the text reading part for obtaining the plain text from the original document images and the information extraction part for extracting key contents. These methods mainly focus on improving the second, while neglecting that the two parts are highly correlated. This paper proposes a unified end-to-end information extraction framework from visually rich documents, where text reading and information extraction can reinforce each other via a well-designed multi-modal context block. Specifically, the text reading part provides multi-modal features like visual, textual and layout features. The multi-modal context block is developed to fuse the generated multi-modal features and even the prior knowledge from the pre-trained language model for better semantic representation. The information extraction part is responsible for generating key contents with the fused context features. The framework can be trained in an end-to-end trainable manner, achieving global optimization. What is more, we define and group visually rich documents into four categories across two dimensions, the layout and text type. For each document category, we provide or recommend the corresponding benchmarks, experimental settings and strong baselines for remedying the problem that this research area lacks the uniform evaluation standard. Extensive experiments on four kinds of benchmarks (from fixed layout to variable layout, from full-structured text to semi-unstructured text) are reported, demonstrating the proposed method's effectiveness. Data, source code and models are available.

cs.CV↗
arXiv2022

Quantum phase transition in magnetic nanographenes on a lead superconductor

Quantum spins, referred to the spin operator preserved by full SU(2) symmetry in the absence of the magnetic anistropy, have been proposed to host exotic interactions with superconductivity4. However, spin orbit coupling and crystal field splitting normally cause a significant magnetic anisotropy for d/f-shell spins on surfaces6,9, breaking SU(2) symmetry and fabricating the spins with Ising properties10. Recently, magnetic nanographenes have been proven to host intrinsic quantum magnetism due to their negligible spin orbital coupling and crystal field splitting. Here, we fabricate three atomically precise nanographenes with the same magnetic ground state of spin S=1/2 on Pb(111) through engineering sublattice imbalance in graphene honeycomb lattice. Scanning tunneling spectroscopy reveals the coexistence of magnetic bound states and Kondo screening in such hybridized system. Through engineering the magnetic exchange strength between the unpaired spin in nanographenes and cooper pairs, quantum phase transition from the singlet to the doublet state has been observed, in consistent with quantum models of spins on superconductors. Our work demonstrates delocalized graphene magnetism host highly tunable magnetic bound states with cooper pairs, which can be further developed to study the Majorana bound states and other rich quantum physics of low-dimensional quantum spins on superconductors.

cond-mat.mes-hall↗
arXiv2022

Unsupervised Knowledge Adaptation for Passenger Demand Forecasting

Considering the multimodal nature of transport systems and potential cross-modal correlations, there is a growing trend of enhancing demand forecasting accuracy by learning from multimodal data. These multimodal forecasting models can improve accuracy but be less practical when different parts of multimodal datasets are owned by different institutions who cannot directly share data among them. While various institutions may can not share their data with each other directly, they may share forecasting models trained by their data, where such models cannot be used to identify the exact information from their datasets. This study proposes an Unsupervised Knowledge Adaptation Demand Forecasting framework to forecast the demand of the target mode by utilizing a pre-trained model based on data of another mode, which does not require direct data sharing of the source mode. The proposed framework utilizes the potential shared patterns among multiple transport modes to improve forecasting performance while avoiding the direct sharing of data among different institutions. Specifically, a pre-trained forecasting model is first learned based on the data of a source mode, which can capture and memorize the source travel patterns. Then, the demand data of the target dataset is encoded into an individual knowledge part and a sharing knowledge part which will extract travel patterns by individual extraction network and sharing extraction network, respectively. The unsupervised knowledge adaptation strategy is utilized to form the sharing features for further forecasting by making the pre-trained network and the sharing extraction network analogous. Our findings illustrate that unsupervised knowledge adaptation by sharing the pre-trained model to the target mode can improve the forecasting performance without the dependence on direct data sharing.

cs.LG↗
arXiv2022

Catalytic growth of ultralong graphene nanoribbons on insulating substrates

Graphene nanoribbons (GNRs) with widths of a few nanometres are promising candidates for future nano-electronic applications due to their structurally tunable bandgaps, ultrahigh carrier mobilities, and exceptional stability. However, the direct growth of micrometre-long GNRs on insulating substrates, which is essential for the fabrication of nano-electronic devices, remains an immense challenge. Here, we report the epitaxial growth of GNRs on an insulating hexagonal boron nitride (h-BN) substrate through nanoparticle-catalysed chemical vapor deposition (CVD). Ultra-narrow GNRs with lengths of up to 10 μm are synthesized. Remarkably, the as-grown GNRs are crystallographically aligned with the h-BN substrate, forming one-dimensional (1D) moiré superlattices. Scanning tunnelling microscopy reveals an average width of 2 nm and a typical bandgap of ~1 eV for similar GNRs grown on conducting graphite substrates. Fully atomistic computational simulations support the experimental results and reveal a competition between the formation of GNRs and carbon nanotubes (CNTs) during the nucleation stage, and van der Waals sliding of the GNRs on the h-BN substrate throughout the growth stage. Our study provides a scalable, single-step method for growing micrometre-long narrow GNRs on insulating substrates, thus opening a route to explore the performance of high-quality GNR devices and the fundamental physics of 1D moiré superlattices.

cond-mat.mes-hall↗
arXiv2022

Experimentally realized memristive memory augmented neural network

Lifelong on-device learning is a key challenge for machine intelligence, and this requires learning from few, often single, samples. Memory augmented neural network has been proposed to achieve the goal, but the memory module has to be stored in an off-chip memory due to its size. Therefore the practical use has been heavily limited. Previous works on emerging memory-based implementation have difficulties in scaling up because different modules with various structures are difficult to integrate on the same chip and the small sense margin of the content addressable memory for the memory module heavily limited the degree of mismatch calculation. In this work, we implement the entire memory augmented neural network architecture in a fully integrated memristive crossbar platform and achieve an accuracy that closely matches standard software on digital hardware for the Omniglot dataset. The successful demonstration is supported by implementing new functions in crossbars in addition to widely reported matrix multiplications. For example, the locality-sensitive hashing operation is implemented in crossbar arrays by exploiting the intrinsic stochasticity of memristor devices. Besides, the content-addressable memory module is realized in crossbars, which also supports the degree of mismatches. Simulations based on experimentally validated models show such an implementation can be efficiently scaled up for one-shot learning on the Mini-ImageNet dataset. The successful demonstration paves the way for practical on-device lifelong learning and opens possibilities for novel attention-based algorithms not possible in conventional hardware.

cs.ET↗