arXiv subjects

Bo Zhou

Publications and source records attributed to Bo Zhou.

At least 163 records · Page 9Linked to original sources

arXiv2024

Remaining useful life prediction of Lithium-ion batteries using spatio-temporal multimodal attention networks

Lithium-ion batteries are widely used in various applications, including electric vehicles and renewable energy storage. The prediction of the remaining useful life (RUL) of batteries is crucial for ensuring reliable and efficient operation, as well as reducing maintenance costs. However, determining the life cycle of batteries in real-world scenarios is challenging, and existing methods have limitations in predicting the number of cycles iteratively. In addition, existing works often oversimplify the datasets, neglecting important features of the batteries such as temperature, internal resistance, and material type. To address these limitations, this paper proposes a two-stage RUL prediction scheme for Lithium-ion batteries using a spatio-temporal multimodal attention network (ST-MAN). The proposed ST-MAN is to capture the complex spatio-temporal dependencies in the battery data, including the features that are often neglected in existing works. Despite operating without prior knowledge of end-of-life (EOL) events, our method consistently achieves lower error rates, boasting mean absolute error (MAE) and mean square error (MSE) of 0.0275 and 0.0014, respectively, compared to existing convolutional neural networks (CNN) and long short-term memory (LSTM)-based methods. The proposed method has the potential to improve the reliability and efficiency of battery operations and is applicable in various industries.

cs.LG↗

arXiv2024

iKAN: Global Incremental Learning with KAN for Human Activity Recognition Across Heterogeneous Datasets

This work proposes an incremental learning (IL) framework for wearable sensor human activity recognition (HAR) that tackles two challenges simultaneously: catastrophic forgetting and non-uniform inputs. The scalable framework, iKAN, pioneers IL with Kolmogorov-Arnold Networks (KAN) to replace multi-layer perceptrons as the classifier that leverages the local plasticity and global stability of splines. To adapt KAN for HAR, iKAN uses task-specific feature branches and a feature redistribution layer. Unlike existing IL methods that primarily adjust the output dimension or the number of classifier nodes to adapt to new tasks, iKAN focuses on expanding the feature extraction branches to accommodate new inputs from different sensor modalities while maintaining consistent dimensions and the number of classifier outputs. Continual learning across six public HAR datasets demonstrated the iKAN framework's incremental learning performance, with a last performance of 84.9\% (weighted F1 score) and an average incremental performance of 81.34\%, which significantly outperforms the two existing incremental learning methods, such as EWC (51.42\%) and experience replay (59.92\%).

cs.LG↗

arXiv2024

iMove: Exploring Bio-impedance Sensing for Fitness Activity Recognition

Automatic and precise fitness activity recognition can be beneficial in aspects from promoting a healthy lifestyle to personalized preventative healthcare. While IMUs are currently the prominent fitness tracking modality, through iMove, we show bio-impedence can help improve IMU-based fitness tracking through sensor fusion and contrastive learning.To evaluate our methods, we conducted an experiment including six upper body fitness activities performed by ten subjects over five days to collect synchronized data from bio-impedance across two wrists and IMU on the left wrist.The contrastive learning framework uses the two modalities to train a better IMU-only classification model, where bio-impedance is only required at the training phase, by which the average Macro F1 score with the input of a single IMU was improved by 3.22 \% reaching 84.71 \% compared to the 81.49 \% of the IMU baseline model. We have also shown how bio-impedance can improve human activity recognition (HAR) directly through sensor fusion, reaching an average Macro F1 score of 89.57 \% (two modalities required for both training and inference) even if Bio-impedance alone has an average macro F1 score of 75.36 \%, which is outperformed by IMU alone. In addition, similar results were obtained in an extended study on lower body fitness activity classification, demonstrating the generalisability of our approach.Our findings underscore the potential of sensor fusion and contrastive learning as valuable tools for advancing fitness activity recognition, with bio-impedance playing a pivotal role in augmenting the capabilities of IMU-based systems.

eess.SP↗

arXiv2024

Distribution of signless Laplacian eigenvalues and graph invariants

For a simple graph on $n$ vertices, any of its signless Laplacian eigenvalues is in the interval $[0, 2n-2]$. In this paper, we give relationships between the number of signless Laplacian eigenvalues in specific intervals in $[0, 2n-2]$ and graph invariants including matching number and diameter.

math.CO↗

arXiv2024

Diameter vs Laplacian eigenvalue distribution

Let $G$ be a simple graph of order $n$. It is known that any Laplacian eigenvalue of $G$ belongs to the interval $[0,n]$. For an interval $I\subseteq [0, n]$, denote by $m_GI$ the number of Laplacian eigenvalues of $G$ in $I$, counted with multiplicity. When $G$ is connected, known results on the Laplacian eigenvalue distribution related to the diameter $d$ of $G$ include: $m_G[n-d+2,n]\le n-d$ if $2\le d\le n-3$ and $m_G[n-d+1,n]\le n-d+1$ if $1\le d\le n-3$. In this paper, we show that $m_G[n-d,n]\le n-d+2$ if $2\le d\le n-4$, and $m_G[n-2d+4,n]\le n-2$ if $2\le d\le \lfloor\frac{n}{2} \rfloor$.

math.CO↗

arXiv2024

Disproof of a conjecture on the edge Mostar index

For a given connected graph $G$, the edge Mostar index $Mo_e(G)$ is defined as $Mo_e(G)=\sum_{e=uv \in E(G)}|m_u(e|G) - m_v(e|G)|$, where $m_u(e|G)$ and $m_v(e|G)$ are respectively, the number of edges of $G$ lying closer to vertex $u$ than to vertex $v$ and the number of edges of $G$ lying closer to vertex $v$ than to vertex $u$. We determine a sharp upper bound for the edge Mostar index on bicyclic graphs and identify the graphs that attain the bound, which disproves a conjecture proposed by Liu et al. [Iranian J. Math. Chem. 11(2) (2020) 95--106].

math.CO↗

arXiv2024

Origami Single-end Capacitive Sensing for Continuous Shape Estimation of Morphing Structures

In this work, we propose a novel single-end morphing capacitive sensing method for shape tracking, FxC, by combining Folding origami structures and Capacitive sensing to detect the morphing structural motions using state-of-the-art sensing circuits and deep learning. It was observed through embedding areas of origami structures with conductive materials as single-end capacitive sensing patches, that the sensor signals change coherently with the motion of the structure. Different from other origami capacitors where the origami structures are used in adjusting the thickness of the dielectric layer of double-plate capacitors, FxC uses only a single conductive plate per channel, and the origami structure directly changes the geometry of the conductive plate. We examined the operation principle of morphing single-end capacitors through 3D geometry simulation combined with physics theoretical deduction, which deduced similar behaviour as observed in experimentation. Then a software pipeline was developed to use the sensor signals to reconstruct the dynamic structural geometry through data-driven deep neural network regression of geometric primitives extracted from vision tracking. We created multiple folding patterns to validate our approach, based on folding patterns including Accordion, Chevron, Sunray and V-Fold patterns with different layouts of capacitive sensors using paper-based and textile-based materials. Experimentation results show that the geometry primitives predicted from the capacitive signals have a strong correlation with the visual ground truth with R-squared value of up to 95% and tracking error of 6.5 mm for patches. The simulation and machine learning constitute two-way information exchange between the sensing signals and structural geometry.

cs.HC↗

arXiv2024

BeSound: Bluetooth-Based Position Estimation Enhancing with Cross-Modality Distillation

Smart factories leverage advanced technologies to optimize manufacturing processes and enhance efficiency. Implementing worker tracking systems, primarily through camera-based methods, ensures accurate monitoring. However, concerns about worker privacy and technology protection make it necessary to explore alternative approaches. We propose a non-visual, scalable solution using Bluetooth Low Energy (BLE) and ultrasound coordinates. BLE position estimation offers a very low-power and cost-effective solution, as the technology is available on smartphones and is scalable due to the large number of smartphone users, facilitating worker localization and safety protocol transmission. Ultrasound signals provide faster response times and higher accuracy but require custom hardware, increasing costs. To combine the benefits of both modalities, we employ knowledge distillation (KD) from ultrasound signals to BLE RSSI data. Once the student model is trained, the model only takes as inputs the BLE-RSSI data for inference, retaining the advantages of ubiquity and low cost of BLE RSSI. We tested our approach using data from an experiment with twelve participants in a smart factory test bed environment. We obtained an increase of 11.79% in the F1-score compared to the baseline (target model without KD and trained with BLE-RSSI data only).

cs.LG↗

arXiv2024

1/2$^-$ $α$ cluster resonances of $^{13}$C studied by the analytic continuation in the coupling constant

The 1/2$^-$ resonant states in $^{13}{\rm C}$ are investigated to search for the Hoyle-analog state. In order to treat the resonance states located around the 3$α+n$ threshold, the analytic continuation in the coupling constant (ACCC) has been combined with the real-time evolution method (REM). The properties of the 1/2$^-$ resonance states such as the radii and monopole transition probabilities are calculated. We show the 1/2$^-_3$ and 1/2$^-_4$ states are well-developed $α$ cluster states, and the 1/2$^-_4$ state is a candidate of the Hoyle-analog state.

nucl-th↗

arXiv2024

Multifractal Dimension Spectrum Analysis for Nuclear Density Distribution

We present an integral density method for calculating the multifractal dimension spectrum for the nucleon distribution in atomic nuclei. This method is then applied to analyze the non-uniformity of the density distribution in several typical types of nuclear matter distributions, including the Woods-Saxon distribution, the halo structure and the tetrahedral $α$ clustering. The subsequent discussion provides a comprehensive and detailed exploration of the results obtained. The multifractal dimension spectrum shows remarkable sensitivity to the density distribution, establishing it as an effective tool for studying the distribution of nucleons in nuclear multibody systems.

nucl-th↗

arXiv2024

Improving Network Degree Correlation by Degree-preserving Rewiring

Degree correlation is a crucial measure in networks, significantly impacting network topology and dynamical behavior. The degree sequence of a network is a significant characteristic, and altering network degree correlation through degree-preserving rewiring poses an interesting problem. In this paper, we define the problem of maximizing network degree correlation through a finite number of rewirings and use the assortativity coefficient to measure it. We analyze the changes in assortativity coefficient under degree-preserving rewiring and establish its relationship with the s-metric. Under our assumptions, we prove the problem to be monotonic and submodular, leading to the proposal of the GA method to enhance network degree correlation. By formulating an integer programming model, we demonstrate that the GA method can effectively approximate the optimal solution and validate its superiority over other baseline methods through experiments on three types of real-world networks. Additionally, we introduce three heuristic rewiring strategies, EDA, TA and PEA, and demonstrate their applicability to different types of networks. Furthermore, we extend our investigation to explore the impact of these rewiring strategies on several spectral robustness metrics based on the adjacency matrix. Finally, we examine the robustness of various centrality metrics in the network while enhancing network degree correlation using the GA method.

cs.SI↗

arXiv2024

MeciFace: Mechanomyography and Inertial Fusion-based Glasses for Edge Real-Time Recognition of Facial and Eating Activities

The increasing prevalence of stress-related eating behaviors and their impact on overall health highlights the importance of effective and ubiquitous monitoring systems. In this paper, we present MeciFace, an innovative wearable technology designed to monitor facial expressions and eating activities in real-time on-the-edge (RTE). MeciFace aims to provide a low-power, privacy-conscious, and highly accurate tool for promoting healthy eating behaviors and stress management. We employ lightweight convolutional neural networks as backbone models for facial expression and eating monitoring scenarios. The MeciFace system ensures efficient data processing with a tiny memory footprint, ranging from 11KB to 19 KB. During RTE evaluation, the system achieves an F1-score of < 86% for facial expression recognition and 94% for eating/drinking monitoring, for the RTE of unseen users (user-independent case).

cs.CV↗

arXiv2024

iFace: Hand-Over-Face Gesture Recognition Leveraging Impedance Sensing

Hand-over-face gestures can provide important implicit interactions during conversations, such as frustration or excitement. However, in situations where interlocutors are not visible, such as phone calls or textual communication, the potential meaning contained in the hand-over-face gestures is lost. In this work, we present iFace, an unobtrusive, wearable impedance-sensing solution for recognizing different hand-over-face gestures. In contrast to most existing works, iFace does not require the placement of sensors on the user's face or hands. Instead, we proposed a novel sensing configuration, the shoulders, which remains invisible to both the user and outside observers. The system can monitor the shoulder-to-shoulder impedance variation caused by gestures through electrodes attached to each shoulder. We evaluated iFace in a user study with eight participants, collecting six kinds of hand-over-face gestures with different meanings. Using a convolutional neural network and a user-dependent classification, iFace reaches 82.58 \% macro F1 score. We discuss potential application scenarios of iFace as an implicit interaction interface.

cs.HC↗

arXiv2024

Active Admittance Control with Iterative Learning for General-Purpose Contact-Rich Manipulation

Force interaction is inevitable when robots face multiple operation scenarios. How to make the robot competent in force control for generalized operations such as multi-tasks still remains a challenging problem. Aiming at the reproducibility of interaction tasks and the lack of a generalized force control framework for multi-task scenarios, this paper proposes a novel hybrid control framework based on active admittance control with iterative learning parameters-tunning mechanism. The method adopts admittance control as the underlying algorithm to ensure flexibility, and iterative learning as the high-level algorithm to regulate the parameters of the admittance model. The whole algorithm has flexibility and learning ability, which is capable of achieving the goal of excellent versatility. Four representative interactive robot manipulation tasks are chosen to investigate the consistency and generalisability of the proposed method. Experiments are designed to verify the effectiveness of the whole framework, and an average of 98.21% and 91.52% improvement of RMSE is obtained relative to the traditional admittance control as well as the model-free adaptive control, respectively.

cs.RO↗

arXiv2024

Text me the data: Generating Ground Pressure Sequence from Textual Descriptions for HAR

In human activity recognition (HAR), the availability of substantial ground truth is necessary for training efficient models. However, acquiring ground pressure data through physical sensors itself can be cost-prohibitive, time-consuming. To address this critical need, we introduce Text-to-Pressure (T2P), a framework designed to generate extensive ground pressure sequences from textual descriptions of human activities using deep learning techniques. We show that the combination of vector quantization of sensor data along with simple text conditioned auto regressive strategy allows us to obtain high-quality generated pressure sequences from textual descriptions with the help of discrete latent correlation between text and pressure maps. We achieved comparable performance on the consistency between text and generated motion with an R squared value of 0.722, Masked R squared value of 0.892, and FID score of 1.83. Additionally, we trained a HAR model with the the synthesized data and evaluated it on pressure dynamics collected by a real pressure sensor which is on par with a model trained on only real data. Combining both real and synthesized training data increases the overall macro F1 score by 5.9 percent.

cs.LG↗

arXiv2024

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

Inter-frame motion in dynamic cardiac positron emission tomography (PET) using rubidium-82 (82-Rb) myocardial perfusion imaging impacts myocardial blood flow (MBF) quantification and the diagnosis accuracy of coronary artery diseases. However, the high cross-frame distribution variation due to rapid tracer kinetics poses a considerable challenge for inter-frame motion correction, especially for early frames where intensity-based image registration techniques often fail. To address this issue, we propose a novel method called Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) that utilizes an all-to-one mapping to convert early frames into those with tracer distribution similar to the last reference frame. The TAI-GAN consists of a feature-wise linear modulation layer that encodes channel-wise parameters generated from temporal information and rough cardiac segmentation masks with local shifts that serve as anatomical information. Our proposed method was evaluated on a clinical 82-Rb PET dataset, and the results show that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, the motion estimation accuracy and subsequent myocardial blood flow (MBF) quantification with both conventional and deep learning-based motion correction methods were improved compared to using the original frames.

eess.IV↗

arXiv2024

Chiral and non-chiral swift mode conversion near an exception point with dynamic adiabaticity engineering

The eigenvalue of a non-Hermitian Hamiltonian often forms a self-intersecting Riemann surface, leading to a unique mode conversion phenomenon when the Hamiltonian evolves along certain loop paths around an exceptional point (EP). However, two fundamental problems exist with the conventional scheme of EP encircling: the speed of mode conversion is restricted by the adiabatic requirement, and the chirality cannot be freely controlled. Here, we introduce a method which dynamically engineers the adiabaticity in the evolution of non-Hermitian Hamiltonians that allows for both chiral and non-chiral mode conversion on the same path. Our method is based on quantifying and controlling the instantaneous adiabaticity, allowing for non-uniform evolution throughout the entire path. We apply our method into the microwave waveguide system and by optimizing the distributed adiabaticity along the evolution loop, we achieve the same quality of mode conversion as conventional quasi-adiabatic evolution in only one-fourth of the time. Our approach provides a comprehensive and universal solution to address the speed and chirality challenges associated with EP encircling. It also facilitates the dynamic manipulation and regulation of non-adiabatic processes, thereby accelerating the operation and allowing for a selection among various mode conversion patterns.

quant-ph↗

arXiv2024

POUR-Net: A Population-Prior-Aided Over-Under-Representation Network for Low-Count PET Attenuation Map Generation

Low-dose PET offers a valuable means of minimizing radiation exposure in PET imaging. However, the prevalent practice of employing additional CT scans for generating attenuation maps (u-map) for PET attenuation correction significantly elevates radiation doses. To address this concern and further mitigate radiation exposure in low-dose PET exams, we propose POUR-Net - an innovative population-prior-aided over-under-representation network that aims for high-quality attenuation map generation from low-dose PET. First, POUR-Net incorporates an over-under-representation network (OUR-Net) to facilitate efficient feature extraction, encompassing both low-resolution abstracted and fine-detail features, for assisting deep generation on the full-resolution level. Second, complementing OUR-Net, a population prior generation machine (PPGM) utilizing a comprehensive CT-derived u-map dataset, provides additional prior information to aid OUR-Net generation. The integration of OUR-Net and PPGM within a cascade framework enables iterative refinement of $μ$-map generation, resulting in the production of high-quality $μ$-maps. Experimental results underscore the effectiveness of POUR-Net, showing it as a promising solution for accurate CT-free low-count PET attenuation correction, which also surpasses the performance of previous baseline methods.

cs.CV↗