arXiv subjects

Junhong Chen

Publications and source records attributed to Junhong Chen.

26 records · Page 2Linked to original sources

arXiv2024

DistillGrasp: Integrating Features Correlation with Knowledge Distillation for Depth Completion of Transparent Objects

Due to the visual properties of reflection and refraction, RGB-D cameras cannot accurately capture the depth of transparent objects, leading to incomplete depth maps. To fill in the missing points, recent studies tend to explore new visual features and design complex networks to reconstruct the depth, however, these approaches tremendously increase computation, and the correlation of different visual features remains a problem. To this end, we propose an efficient depth completion network named DistillGrasp which distillates knowledge from the teacher branch to the student branch. Specifically, in the teacher branch, we design a position correlation block (PCB) that leverages RGB images as the query and key to search for the corresponding values, guiding the model to establish correct correspondence between two features and transfer it to the transparent areas. For the student branch, we propose a consistent feature correlation module (CFCM) that retains the reliable regions of RGB images and depth maps respectively according to the consistency and adopts a CNN to capture the pairwise relationship for depth completion. To avoid the student branch only learning regional features from the teacher branch, we devise a distillation loss that not only considers the distance loss but also the object structure and edge information. Extensive experiments conducted on the ClearGrasp dataset manifest that our teacher network outperforms state-of-the-art methods in terms of accuracy and generalization, and the student network achieves competitive results with a higher speed of 48 FPS. In addition, the significant improvement in a real-world robotic grasping system illustrates the effectiveness and robustness of our proposed system.

cs.CV↗

arXiv2024

Leveraging Data Mining, Active Learning, and Domain Adaptation in a Multi-Stage, Machine Learning-Driven Approach for the Efficient Discovery of Advanced Acidic Oxygen Evolution Electrocatalysts

Developing advanced catalysts for acidic oxygen evolution reaction (OER) is crucial for sustainable hydrogen production. This study introduces a novel, multi-stage machine learning (ML) approach to streamline the discovery and optimization of complex multi-metallic catalysts. Our method integrates data mining, active learning, and domain adaptation throughout the materials discovery process. Unlike traditional trial-and-error methods, this approach systematically narrows the exploration space using domain knowledge with minimized reliance on subjective intuition. Then the active learning module efficiently refines element composition and synthesis conditions through iterative experimental feedback. The process culminated in the discovery of a promising Ru-Mn-Ca-Pr oxide catalyst. Our workflow also enhances theoretical simulations with domain adaptation strategy, providing deeper mechanistic insights aligned with experimental findings. By leveraging diverse data sources and multiple ML strategies, we establish an efficient pathway for electrocatalyst discovery and optimization. This comprehensive, data-driven approach represents a paradigm shift and potentially new benchmark in electrocatalysts research.

cond-mat.mtrl-sci↗

arXiv2024

Deep Learning-based Kinetic Analysis in Paper-based Analytical Cartridges Integrated with Field-effect Transistors

This study explores the fusion of a field-effect transistor (FET), a paper-based analytical cartridge, and the computational power of deep learning (DL) for quantitative biosensing via kinetic analyses. The FET sensors address the low sensitivity challenge observed in paper analytical devices, enabling electrical measurements with kinetic data. The paper-based cartridge eliminates the need for surface chemistry required in FET sensors, ensuring economical operation (cost < $0.15/test). The DL analysis mitigates chronic challenges of FET biosensors such as sample matrix interference, by leveraging kinetic data from target-specific bioreactions. In our proof-of-concept demonstration, our DL-based analyses showcased a coefficient of variation of < 6.46% and a decent concentration measurement correlation with an r2 value of > 0.976 for cholesterol testing when blindly compared to results obtained from a CLIA-certified clinical laboratory. These integrated technologies can create a new generation of FET-based biosensors, potentially transforming point-of-care diagnostics and at-home testing through enhanced accessibility, ease-of-use, and accuracy.

q-bio.QM↗

arXiv2023

Dietary Assessment with Multimodal ChatGPT: A Systematic Analysis

Conventional approaches to dietary assessment are primarily grounded in self-reporting methods or structured interviews conducted under the supervision of dietitians. These methods, however, are often subjective, potentially inaccurate, and time-intensive. Although artificial intelligence (AI)-based solutions have been devised to automate the dietary assessment process, these prior AI methodologies encounter challenges in their ability to generalize across a diverse range of food types, dietary behaviors, and cultural contexts. This results in AI applications in the dietary field that possess a narrow specialization and limited accuracy. Recently, the emergence of multimodal foundation models such as GPT-4V powering the latest ChatGPT has exhibited transformative potential across a wide range of tasks (e.g., Scene understanding and image captioning) in numerous research domains. These models have demonstrated remarkable generalist intelligence and accuracy, capable of processing various data modalities. In this study, we explore the application of multimodal ChatGPT within the realm of dietary assessment. Our findings reveal that GPT-4V excels in food detection under challenging conditions with accuracy up to 87.5% without any fine-tuning or adaptation using food-specific datasets. By guiding the model with specific language prompts (e.g., African cuisine), it shifts from recognizing common staples like rice and bread to accurately identifying regional dishes like banku and ugali. Another GPT-4V's standout feature is its contextual awareness. GPT-4V can leverage surrounding objects as scale references to deduce the portion sizes of food items, further enhancing its accuracy in translating food weight into nutritional content. This alignment with the USDA National Nutrient Database underscores GPT-4V's potential to advance nutritional science and dietary assessment techniques.

cs.CV↗

arXiv2023

Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification

Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies. We established an uncertainty-inspired open-set (UIOS) model, which was trained with fundus images of 9 retinal conditions. Besides assessing the probability of each category, UIOS also calculated an uncertainty score to express its confidence. Our UIOS model with thresholding strategy achieved an F1 score of 99.55%, 97.01% and 91.91% for the internal testing set, external target categories (TC)-JSIEC dataset and TC-unseen testing set, respectively, compared to the F1 score of 92.20%, 80.69% and 64.74% by the standard AI model. Furthermore, UIOS correctly predicted high uncertainty scores, which would prompt the need for a manual check in the datasets of non-target categories retinal diseases, low-quality fundus images, and non-fundus images. UIOS provides a robust method for real-world screening of retinal anomalies.

cs.LG↗

arXiv2022

Human-Robot Shared Control for Surgical Robot Based on Context-Aware Sim-to-Real Adaptation

Human-robot shared control, which integrates the advantages of both humans and robots, is an effective approach to facilitate efficient surgical operation. Learning from demonstration (LfD) techniques can be used to automate some of the surgical subtasks for the construction of the shared control framework. However, a sufficient amount of data is required for the robot to learn the manoeuvres. Using a surgical simulator to collect data is a less resource-demanding approach. With sim-to-real adaptation, the manoeuvres learned from a simulator can be transferred to a physical robot. To this end, we propose a sim-to-real adaptation method to construct a human-robot shared control framework for robotic surgery. In this paper, a desired trajectory is generated from a simulator using LfD method, while dynamic motion primitives (DMPs) based method is used to transfer the desired trajectory from the simulator to the physical robotic platform. Moreover, a role adaptation mechanism is developed such that the robot can adjust its role according to the surgical operation contexts predicted by a neural network model. The effectiveness of the proposed framework is validated on the da Vinci Research Kit (dVRK). Results of the user studies indicated that with the adaptive human-robot shared control framework, the path length of the remote controller, the total clutching number and the task completion time can be reduced significantly. The proposed method outperformed the traditional manual control via teleoperation.

cs.RO↗

arXiv2015

Load-aware Dynamic Spectrum Access for Small Cell Networks: A Graphical Game Approach

In this letter, we investigate the problem of dynamic spectrum access for small cell networks, using a graphical game approach. Compared with existing studies, we take the features of different cell loads and local interference relationship into account. It is proved that the formulated spectrum access game is an exact potential game with the aggregate interference level as the potential function, and Nash equilibrium (NE) of the game corresponds to the global or local optima of the original optimization problem. A lower bound of the achievable aggregate interference level is rigorously derived. Finally, we propose an autonomous best response learning algorithm to converge towards its NE. It is shown that the proposed game-theoretic solution converges rapidly and its achievable performance is close to the optimum solution.

cs.IT↗

arXiv2010

Solar LImb Prominence CAtcher and Tracker (SLIPCAT): An Automated System and Its Preliminary Statistical Results

In this paper, we present an automated system, which has the capability to catch and track solar limb prominences based on observations from EUV 304 passband. The characteristic parameters and their evolution, including height, position angle, area, length and brightness, are obtained without manual interventions. By applying the system to the STEREO-B/SECCHI/EUVI 304 data during 2007 April -2009 October, we obtain a total of 9477 well-tracked prominences and a catalog of these events available online at http://space.ustc.edu.cn/dreams/slipcat/. A detailed analysis of these prominences suggests that the system has a rather good performance. We have obtained several interesting statistical results based on the catalog. Most prominences appear below the latitude of 60 degrees and at the height of about 26 Mm above the solar surface. Most of them are quite stable during the period they are tracked. Nevertheless, some prominences have an upward speed of more than 100 km/s, and some others show significant downward and/or azimuthal speeds. There are strong correlations among the brightness, area and height. The expansion of a prominence is probably one major cause of its fading during the rising or erupting process.

astro-ph.SR↗