arXiv subjects

Bo Zhou

Publications and source records attributed to Bo Zhou.

At least 199 records · Page 11Linked to original sources

arXiv2023

TAI-GAN: Temporally and Anatomically Informed GAN for early-to-late frame conversion in dynamic cardiac PET motion correction

The rapid tracer kinetics of rubidium-82 ($^{82}$Rb) and high variation of cross-frame distribution in dynamic cardiac positron emission tomography (PET) raise significant challenges for inter-frame motion correction, particularly for the early frames where conventional intensity-based image registration techniques are not applicable. Alternatively, a promising approach utilizes generative methods to handle the tracer distribution changes to assist existing registration methods. To improve frame-wise registration and parametric quantification, we propose a Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) to transform the early frames into the late reference frame using an all-to-one mapping. Specifically, a feature-wise linear modulation layer encodes channel-wise parameters generated from temporal tracer kinetics information, and rough cardiac segmentations with local shifts serve as the anatomical information. We validated our proposed method on a clinical $^{82}$Rb PET dataset and found that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, motion estimation accuracy and clinical myocardial blood flow (MBF) quantification were improved compared to using the original frames. Our code is published at https://github.com/gxq1998/TAI-GAN.

eess.IV↗

arXiv2023

MONA: An Efficient and Scalable Strategy for Targeted k-Nodes Collapse

The concept of k-core plays an important role in measuring the cohesiveness and engagement of a network. And recent studies have shown the vulnerability of k-core under adversarial attacks. However, there are few researchers concentrating on the vulnerability of individual nodes within k-core. Therefore, in this paper, we attempt to study Targeted k-Nodes Collapse Problem (TNsCP), which focuses on removing a minimal size set of edges to make multiple target k-nodes collapse. For this purpose, we first propose a novel algorithm named MOD for candidate reduction. Then we introduce an efficient strategy named MONA, based on MOD, to address TNsCP. Extensive experiments validate the effectiveness and scalability of MONA compared to several baselines. An open-source implementation is available at https://github.com/Yocenly/MONA.

cs.SI↗

arXiv2023

Worker Activity Recognition in Manufacturing Line Using Near-body Electric Field

Manufacturing industries strive to improve production efficiency and product quality by deploying advanced sensing and control systems. Wearable sensors are emerging as a promising solution for achieving this goal, as they can provide continuous and unobtrusive monitoring of workers' activities in the manufacturing line. This paper presents a novel wearable sensing prototype that combines IMU and body capacitance sensing modules to recognize worker activities in the manufacturing line. To handle these multimodal sensor data, we propose and compare early, and late sensor data fusion approaches for multi-channel time-series convolutional neural networks and deep convolutional LSTM. We evaluate the proposed hardware and neural network model by collecting and annotating sensor data using the proposed sensing prototype and Apple Watches in the testbed of the manufacturing line. Experimental results demonstrate that our proposed methods achieve superior performance compared to the baseline methods, indicating the potential of the proposed approach for real-world applications in manufacturing industries. Furthermore, the proposed sensing prototype with a body capacitive sensor and feature fusion method improves by 6.35%, yielding a 9.38% higher macro F1 score than the proposed sensing prototype without a body capacitive sensor and Apple Watch data, respectively.

cs.LG↗

arXiv2023

Two-stage Early Prediction Framework of Remaining Useful Life for Lithium-ion Batteries

Early prediction of remaining useful life (RUL) is crucial for effective battery management across various industries, ranging from household appliances to large-scale applications. Accurate RUL prediction improves the reliability and maintainability of battery technology. However, existing methods have limitations, including assumptions of data from the same sensors or distribution, foreknowledge of the end of life (EOL), and neglect to determine the first prediction cycle (FPC) to identify the start of the unhealthy stage. This paper proposes a novel method for RUL prediction of Lithium-ion batteries. The proposed framework comprises two stages: determining the FPC using a neural network-based model to divide the degradation data into distinct health states and predicting the degradation pattern after the FPC to estimate the remaining useful life as a percentage. Experimental results demonstrate that the proposed method outperforms conventional approaches in terms of RUL prediction. Furthermore, the proposed method shows promise for real-world scenarios, providing improved accuracy and applicability for battery management.

cs.LG↗

arXiv2023

On Bounded Completeness and the $L_1$-Denseness of Likelihood Ratios

The classical concept of bounded completeness and its relation to sufficiency and ancillarity play a fundamental role in unbiased estimation, unbiased testing, and the validity of inference in the presence of nuisance parameters. In this short note, we provide a direct proof of a little-known result by \cite{Far62} on a characterization of bounded completeness based on an $L^1$ denseness property of the linear span of likelihood ratios. As an application, we show that an experiment with infinite-dimensional observation space is boundedly complete iff suitably chosen restricted subexperiments with finite-dimensional observation spaces are.

math.ST↗

arXiv2023

PressureTransferNet: Human Attribute Guided Dynamic Ground Pressure Profile Transfer using 3D simulated Pressure Maps

We propose PressureTransferNet, a novel method for Human Activity Recognition (HAR) using ground pressure information. Our approach generates body-specific dynamic ground pressure profiles for specific activities by leveraging existing pressure data from different individuals. PressureTransferNet is an encoder-decoder model taking a source pressure map and a target human attribute vector as inputs, producing a new pressure map reflecting the target attribute. To train the model, we use a sensor simulation to create a diverse dataset with various human attributes and pressure profiles. Evaluation on a real-world dataset shows its effectiveness in accurately transferring human attributes to ground pressure profiles across different scenarios. We visually confirm the fidelity of the synthesized pressure shapes using a physics-based deep learning model and achieve a binary R-square value of 0.79 on areas with ground contact. Validation through classification with F1 score (0.911$\pm$0.015) on physical pressure mat data demonstrates the correctness of the synthesized pressure maps, making our method valuable for data augmentation, denoising, sensor simulation, and anomaly detection. Applications span sports science, rehabilitation, and bio-mechanics, contributing to the development of HAR systems.

cs.CV↗

arXiv2023

Dynamic Domain Discrepancy Adjustment for Active Multi-Domain Adaptation

Multi-source unsupervised domain adaptation (MUDA) aims to transfer knowledge from related source domains to an unlabeled target domain. While recent MUDA methods have shown promising results, most focus on aligning the overall feature distributions across source domains, which can lead to negative effects due to redundant features within each domain. Moreover, there is a significant performance gap between MUDA and supervised methods. To address these challenges, we propose a novel approach called Dynamic Domain Discrepancy Adjustment for Active Multi-Domain Adaptation (D3AAMDA). Firstly, we establish a multi-source dynamic modulation mechanism during the training process based on the degree of distribution differences between source and target domains. This mechanism controls the alignment level of features between each source domain and the target domain, effectively leveraging the local advantageous feature information within the source domains. Additionally, we propose a Multi-source Active Boundary Sample Selection (MABS) strategy, which utilizes a guided dynamic boundary loss to design an efficient query function for selecting important samples. This strategy achieves improved generalization to the target domain with minimal sampling costs. We extensively evaluate our proposed method on commonly used domain adaptation datasets, comparing it against existing UDA and ADA methods. The experimental results unequivocally demonstrate the superiority of our approach.

cs.LG↗

arXiv2023

Selecting the motion ground truth for loose-fitting wearables: benchmarking optical MoCap methods

To help smart wearable researchers choose the optimal ground truth methods for motion capturing (MoCap) for all types of loose garments, we present a benchmark, DrapeMoCapBench (DMCB), specifically designed to evaluate the performance of optical marker-based and marker-less MoCap. High-cost marker-based MoCap systems are well-known as precise golden standards. However, a less well-known caveat is that they require skin-tight fitting markers on bony areas to ensure the specified precision, making them questionable for loose garments. On the other hand, marker-less MoCap methods powered by computer vision models have matured over the years, which have meager costs as smartphone cameras would suffice. To this end, DMCB uses large real-world recorded MoCap datasets to perform parallel 3D physics simulations with a wide range of diversities: six levels of drape from skin-tight to extremely draped garments, three levels of motions and six body type - gender combinations to benchmark state-of-the-art optical marker-based and marker-less MoCap methods to identify the best-performing method in different scenarios. In assessing the performance of marker-based and low-cost marker-less MoCap for casual loose garments both approaches exhibit significant performance loss (>10cm), but for everyday activities involving basic and fast motions, marker-less MoCap slightly outperforms marker-based MoCap, making it a favorable and cost-effective choice for wearable studies.

cs.CV↗

arXiv2023

Transformer-based Dual-domain Network for Few-view Dedicated Cardiac SPECT Image Reconstructions

Cardiovascular disease (CVD) is the leading cause of death worldwide, and myocardial perfusion imaging using SPECT has been widely used in the diagnosis of CVDs. The GE 530/570c dedicated cardiac SPECT scanners adopt a stationary geometry to simultaneously acquire 19 projections to increase sensitivity and achieve dynamic imaging. However, the limited amount of angular sampling negatively affects image quality. Deep learning methods can be implemented to produce higher-quality images from stationary data. This is essentially a few-view imaging problem. In this work, we propose a novel 3D transformer-based dual-domain network, called TIP-Net, for high-quality 3D cardiac SPECT image reconstructions. Our method aims to first reconstruct 3D cardiac SPECT images directly from projection data without the iterative reconstruction process by proposing a customized projection-to-image domain transformer. Then, given its reconstruction output and the original few-view reconstruction, we further refine the reconstruction using an image-domain reconstruction network. Validated by cardiac catheterization images, diagnostic interpretations from nuclear cardiologists, and defect size quantified by an FDA 510(k)-cleared clinical software, our method produced images with higher cardiac defect contrast on human studies compared with previous baseline methods, potentially enabling high-quality defect visualization using stationary few-view dedicated cardiac SPECT scanners.

eess.IV↗

arXiv2023

Real-Time Detection of Local No-Arbitrage Violations

This paper focuses on the task of detecting local episodes involving violation of the standard Itô semimartingale assumption for financial asset prices in real time that might induce arbitrage opportunities. Our proposed detectors, defined as stopping rules, are applied sequentially to continually incoming high-frequency data. We show that they are asymptotically exponentially distributed in the absence of Ito semimartingale violations. On the other hand, when a violation occurs, we can achieve immediate detection under infill asymptotics. A Monte Carlo study demonstrates that the asymptotic results provide a good approximation to the finite-sample behavior of the sequential detectors. An empirical application to S&P 500 index futures data corroborates the effectiveness of our detectors in swiftly identifying the emergence of an extreme return persistence episode in real time.

econ.EM↗

arXiv2023

Age of Information in Ultra-Dense IoT Systems: Performance and Mean-Field Game Analysis

In this paper, a dense Internet of Things (IoT) monitoring system is considered in which a large number of IoT devices contend for channel access so as to transmit timely status updates to the corresponding receivers using a carrier sense multiple access (CSMA) scheme. Under two packet management schemes with and without preemption in service, the closed-form expressions of the average age of information (AoI) and the average peak AoI of each device is characterized. It is shown that the scheme with preemption in service always leads to a smaller average AoI and a smaller average peak AoI, compared to the scheme without preemption in service. Then, a distributed noncooperative medium access control game is formulated in which each device optimizes its waiting rate so as to minimize its average AoI or average peak AoI under an average energy cost constraint on channel sensing and packet transmitting. To overcome the challenges of solving this game for an ultra-dense IoT, a mean-field game (MFG) approach is proposed to study the asymptotic performance of each device for the system in the large population regime. The accuracy of the MFG is analyzed, and the existence, uniqueness, and convergence of the mean-field equilibrium (MFE) are investigated. Simulation results show that the proposed MFG is accurate even for a small number of devices; and the proposed CSMA-type scheme under the MFG analysis outperforms three baseline schemes with fixed and dynamic waiting rates. Moreover, it is observed that the average AoI and the average peak AoI under the MFE do not necessarily decrease with the arrival rate.

cs.IT↗

arXiv2023

Laplacain eigenvalue distribution and diameter of graphs

Let $G$ be a connected graph on $n$ vertices with diameter $d$. It is known that if $2\le d\le n-2$, there are at most $n-d$ Laplacian eigenvalues in the interval $[n-d+2, n]$. In this paper, we show that if $1\le d\le n-3$, there are at most $n-d+1$ Laplacian eigenvalues in the interval $[n-d+1, n]$. Moreover, we try to identify the connected graphs on $n$ vertices with diameter $d$, where $2\le d\le n-3$, such that there are at most $n-d$ Laplacian eigenvalues in the interval $[n-d+1, n]$.

math.CO↗

arXiv2023

Largest and Least H-Eigenvalues of Symmetric Tensors and Hypergraphs

In tensor eigenvalue problems, one is likely to be more interested in H-eigenvalues of tensors. The largest H-eigenvalue of a nonnegative tensor or of a uniform hypergraph is the spectral radius of the tensor or of the uniform hypergraph. We find upper bounds and lower bounds (interlacing inequalities) for the largest H-eigenvalue of a principal subtensor of a symmetric zero diagonal tensor that is of even order or nonnegative, as well as lower bounds for the largest H-eigenvalue of a uniform hypergraph with some vertices or edges removed. We also investigate similar problems for the least H-eigenvalues. We give examples to verify the sharpness of the bounds or in some cases for uniform hypergraphs, we characterize the equality. Particularly, for a connected linear $k$-uniform hypergraph $G$ with $v\in V(G)$, we give a sharp lower bound for the spectral radius of $G-v$ in terms of the spectral radius of $G$ and the degree of $v$ and characterize the extremal hypergraphs, and show that the maximum spectral radius of the subhypergraphs with one vertex removed is greater than or equal to the spectral radius of the hypergraph minus one, which is attained if and only if it is a Steiner system $S(2,k,n)$.

math.NA↗

arXiv2023

Proof of a conjecture on distribution of Laplacian eigenvalues and diameter, and beyond

Ahanjideh, Akbari, Fakharan and Trevisan proposed a conjecture in [Linear Algebra Appl. 632 (2022) 1--14] on the distribution of the Laplacian eigenvalues of graphs: for any connected graph of order $n$ with diameter $d\ge 2$ that is not a path, the number of Laplacian eigenvalues in the interval $[n-d+2,n]$ is at most $n-d$. We show that the conjecture is true, and give a complete characterization of graphs for which the conjectured bound is attained. This establishes an interesting relation between the spectral and classical parameters.

math.CO↗

arXiv2023

CaptAinGlove: Capacitive and Inertial Fusion-Based Glove for Real-Time on Edge Hand Gesture Recognition for Drone Control

We present CaptAinGlove, a textile-based, low-power (1.15Watts), privacy-conscious, real-time on-the-edge (RTE) glove-based solution with a tiny memory footprint (2MB), designed to recognize hand gestures used for drone control. We employ lightweight convolutional neural networks as the backbone models and a hierarchical multimodal fusion to reduce power consumption and improve accuracy. The system yields an F1-score of 80% for the offline evaluation of nine classes; eight hand gesture commands and null activity. For the RTE, we obtained an F1-score of 67% (one user).

cs.LG↗

arXiv2023

WYWEB: A NLP Evaluation Benchmark For Classical Chinese

To fully evaluate the overall performance of different NLP models in a given domain, many evaluation benchmarks are proposed, such as GLUE, SuperGLUE and CLUE. The fi eld of natural language understanding has traditionally focused on benchmarks for various tasks in languages such as Chinese, English, and multilingua, however, there has been a lack of attention given to the area of classical Chinese, also known as "wen yan wen", which has a rich history spanning thousands of years and holds signifi cant cultural and academic value. For the prosperity of the NLP community, in this paper, we introduce the WYWEB evaluation benchmark, which consists of nine NLP tasks in classical Chinese, implementing sentence classifi cation, sequence labeling, reading comprehension, and machine translation. We evaluate the existing pre-trained language models, which are all struggling with this benchmark. We also introduce a number of supplementary datasets and additional tools to help facilitate further progress on classical Chinese NLU. The github repository is https://github.com/baudzhou/WYWEB.

cs.CL↗

arXiv2023

FieldHAR: A Fully Integrated End-to-end RTL Framework for Human Activity Recognition with Neural Networks from Heterogeneous Sensors

In this work, we propose an open-source scalable end-to-end RTL framework FieldHAR, for complex human activity recognition (HAR) from heterogeneous sensors using artificial neural networks (ANN) optimized for FPGA or ASIC integration. FieldHAR aims to address the lack of apparatus to transform complex HAR methodologies often limited to offline evaluation to efficient run-time edge applications. The framework uses parallel sensor interfaces and integer-based multi-branch convolutional neural networks (CNNs) to support flexible modality extensions with synchronous sampling at the maximum rate of each sensor. To validate the framework, we used a sensor-rich kitchen scenario HAR application which was demonstrated in a previous offline study. Through resource-aware optimizations, with FieldHAR the entire RTL solution was created from data acquisition to ANN inference taking as low as 25\% logic elements and 2\% memory bits of a low-end Cyclone IV FPGA and less than 1\% accuracy loss from the original FP32 precision offline study. The RTL implementation also shows advantages over MCU-based solutions, including superior data acquisition performance and virtually eliminating ANN inference bottleneck.

eess.SP↗

arXiv2023

Cross-domain Iterative Network for Simultaneous Denoising, Limited-angle Reconstruction, and Attenuation Correction of Low-dose Cardiac SPECT

Single-Photon Emission Computed Tomography (SPECT) is widely applied for the diagnosis of ischemic heart diseases. Low-dose (LD) SPECT aims to minimize radiation exposure but leads to increased image noise. Limited-angle (LA) SPECT enables faster scanning and reduced hardware costs but results in lower reconstruction accuracy. Additionally, computed tomography (CT)-derived attenuation maps ($μ$-maps) are commonly used for SPECT attenuation correction (AC), but it will cause extra radiation exposure and SPECT-CT misalignments. In addition, the majority of SPECT scanners in the market are not hybrid SPECT/CT scanners. Although various deep learning methods have been introduced to separately address these limitations, the solution for simultaneously addressing these challenges still remains highly under-explored and challenging. To this end, we propose a Cross-domain Iterative Network (CDI-Net) for simultaneous denoising, LA reconstruction, and CT-free AC in cardiac SPECT. In CDI-Net, paired projection- and image-domain networks are end-to-end connected to fuse the emission and anatomical information across domains and iterations. Adaptive Weight Recalibrators (AWR) adjust the multi-channel input features to enhance prediction accuracy. Our experiments using clinical data showed that CDI-Net produced more accurate $μ$-maps, projections, and reconstructions compared to existing approaches that addressed each task separately. Ablation studies demonstrated the significance of cross-domain and cross-iteration connections, as well as AWR, in improving the reconstruction performance.

cs.CV↗