Qi Yu
YOU?
Author Swipe
View article: Prediction of the optimal dose of exenatide in patients with type 2 diabetes mellitus with renal impairment using physiologically based pharmacokinetic modeling
Prediction of the optimal dose of exenatide in patients with type 2 diabetes mellitus with renal impairment using physiologically based pharmacokinetic modeling Open
Although exenatide is approved for patients with type 2 diabetes mellitus (T2DM) with mild to moderate renal impairment, specific dosing guidelines for this population remain undefined. To address this gap, we developed a physiologically b…
"Gold-Standard" $Δ$-Machine Learned and Transferable Potential for Linear Alkanes Open
The conformational properties of linear alkanes, C$_n$H$_{2n+2}$, have been of intense interest for many years. Experiments and corresponding electronic structure calculations were first reported in the mid-2000s and continue to the presen…
EquAct: An SE(3)-Equivariant Multi-Task Transformer for Open-Loop Robotic Manipulation Open
Transformer architectures can effectively learn language-conditioned, multi-task 3D open-loop manipulation policies from demonstrations by jointly processing natural language instructions and 3D observations. However, although both the rob…
Multimodal cortical connectome in the default mode network across the adult lifespan Open
The default mode network (DMN) critically underpins cognitive and affective functions throughout the adult lifespan; however, detailed insights into its complex neuroarchitecture and connectivity patterns across aging remain limited. Lever…
Predictive modeling of 3D reconstruction trajectories for potential programmable materials Open
Introduction Shape-morphing programmable materials, capable of dynamically adjusting their properties in response to external stimuli, hold significant potential in adaptive design and smart manufacturing. However, accurately predicting th…
View article: Adaptive boundary-enhanced Dice loss for image segmentation
Adaptive boundary-enhanced Dice loss for image segmentation Open
Deep learning is widely utilized for medical image segmentation, and its effectiveness is significantly influenced by the choice of specialized loss functions. In this study, we introduce an adaptive boundary-enhanced Dice (ABeDice) loss f…
Advancing Dynamic Emergency Route Optimization with a Composite Network Deep Reinforcement Learning Model Open
Emergency logistics is essential for rapid and efficient disaster response, ensuring the timely availability and deployment of resources to affected areas. In the process of rescue work, the dynamic changes in rescue point information grea…
View article: ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter
ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter Open
Robotic grasping in cluttered environments remains a significant challenge due to occlusions and complex object arrangements. We have developed ThinkGrasp, a plug-and-play vision-language grasping system that makes use of GPT-4o's advanced…
Design optimization of wide-gate swing E-mode GaN HEMTs with junction barrier Schottky gate Open
To increase the gate swing, a GaN-based high-electron-mobility transistor with a junction barrier Schottky gate (JBS-HEMT) was proposed. Compared to conventional p-GaN Schottky gate HEMTs (Conv-HEMT), the high electric field at the surface…
Guidance of Hope: The Link of Social Support Influences the Career Educational Response of Senior High School Students Open
Background: This research aims to investigate the relationships between social support, hope, career exploration, career adaptability, and reactions to career education among Chinese high school students. The study sample consists of 418 C…
Bad play: real-world issues for players who are involved with inappropriate boundary-crossing behaviors in virtual world Open
This study investigated changes in players' personal boundary adjustments encompassing physical, emotional and physiological boundaries in virtual worlds. Personal boundaries (or so-called psychological boundary) are defined as rules disti…
Bayesian deep neural network for low-carbon scheduling strategy planning of V2G Open
With the increasing adoption of electric vehicles, the Vehicle-to-Grid (V2G) model has become crucial in integrating renewable energy generation. However, challenges exist in developing grid scheduling strategies that are tailored to diffe…
Neoadjuvant chemotherapy for breast cancer: an evaluation of its efficacy and research progress Open
Neoadjuvant chemotherapy (NAC) for breast cancer is widely used in the clinical setting to improve the chance of surgery, breast conservation and quality of life for patients with advanced breast cancer. A more accurate efficacy evaluation…
STGIN: Spatial-Temporal Graph Interaction Network for Large-scale POI Recommendation Open
In Location-Based Services, Point-Of-Interest(POI) recommendation plays a crucial role in both user experience and business opportunities. Graph neural networks have been proven effective in providing personalized POI recommendation servic…
The Remote Transmission and Analysis Framework of Physical Guiding Data Based on Information Technology Open
Aiming at the problem that traditional physical education activities need to occupy a large space and more human resources, the paper analyzes and designs a remote physical education data transmission and analysis platform based on WEB ser…
STARS: Spatial-Temporal Active Re-sampling for Label-Efficient Learning from Noisy Annotations Open
Active learning (AL) aims to sample the most informative data instances for labeling, which makes the model fitting data efficient while significantly reducing the annotation cost. However, most existing AL models make a strong assumption …
Dual functional states of working memory realized by memristor-based neural network Open
Working memory refers to the brain's ability to store and manipulate information for a short period. It is disputably considered to rely on two mechanisms: sustained neuronal firing, and “activity-silent” working memory. To develop a highl…