Yulong Pei
YOU?
Author Swipe
View article: Microbial Dynamics in a Musalais Wine Fermentation: A Metagenomic Study
Microbial Dynamics in a Musalais Wine Fermentation: A Metagenomic Study Open
This study provides a comprehensive analysis of the microbial dynamics involved in the fermentation process of traditional Musalais wine, an intangible cultural heritage of Xinjiang. Utilizing metagenomic sequencing, we identified 2894 mic…
View article: Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation
Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation Open
Despite significant advancements in active learning and adversarial attacks, the intersection of these two fields remains underexplored, particularly in developing robust active learning frameworks against dynamic adversarial threats. The …
View article: BuDDIE: A Business Document Dataset for Multi-task Information Extraction
BuDDIE: A Business Document Dataset for Multi-task Information Extraction Open
The field of visually rich document understanding (VRDU) aims to solve a multitude of well-researched NLP tasks in a multi-modal domain. Several datasets exist for research on specific tasks of VRDU such as document classification (DC), ke…
View article: A Structural-Clustering Based Active Learning for Graph Neural Networks
A Structural-Clustering Based Active Learning for Graph Neural Networks Open
In active learning for graph-structured data, Graph Neural Networks (GNNs) have shown effectiveness. However, a common challenge in these applications is the underutilization of crucial structural information. To address this problem, we p…
View article: Heterophily-Based Graph Neural Network for Imbalanced Classification
Heterophily-Based Graph Neural Network for Imbalanced Classification Open
Graph neural networks (GNNs) have shown promise in addressing graph-related problems, including node classification. However, conventional GNNs assume an even distribution of data across classes, which is often not the case in real-world s…
View article: You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets
You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets Open
Recent works have impressively demonstrated that there exists a subnetwork in randomly initialized convolutional neural networks (CNNs) that can match the performance of the fully trained dense networks at initialization, without any optim…
View article: FAL-CUR: Fair Active Learning using Uncertainty and Representativeness on Fair Clustering
FAL-CUR: Fair Active Learning using Uncertainty and Representativeness on Fair Clustering Open
Active Learning (AL) techniques have proven to be highly effective in reducing data labeling costs across a range of machine learning tasks. Nevertheless, one known challenge of these methods is their potential to introduce unfairness towa…
View article: Individual Fairness Evaluation for Automated Essay Scoring System
Individual Fairness Evaluation for Automated Essay Scoring System Open
In Automated Essay Scoring (AES) systems, many previous works have studied group fairness using the demographic features of essay writers. However, individual fairness also plays an important role in fair evaluation and has not been yet ex…
View article: Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training
Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training Open
Recent works on sparse neural network training (sparse training) have shown that a compelling trade-off between performance and efficiency can be achieved by training intrinsically sparse neural networks from scratch. Existing sparse train…
View article: Semantic-Based Few-Shot Learning by Interactive Psychometric Testing
Semantic-Based Few-Shot Learning by Interactive Psychometric Testing Open
Few-shot classification tasks aim to classify images in query sets based on only a few labeled examples in support sets. Most studies usually assume that each image in a task has a single and unique class association. Under these assumptio…
View article: Direction-Aggregated Attack for Transferable Adversarial Examples
Direction-Aggregated Attack for Transferable Adversarial Examples Open
Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters …
View article: A Novel Fault Tolerant Machine With Integral Slot Non-Overlapping Concentrated Winding
A Novel Fault Tolerant Machine With Integral Slot Non-Overlapping Concentrated Winding Open
A novel fault tolerant machine with integral slot non-overlapping concentrated winding (ISNCW) is proposed in this paper. With the distribution of phase windings in axial, the proposed machine realized excellent isolation capability betwee…
View article: Magnet Shape Optimization of Two-Layer Spoke-Type Axial Flux Interior Permanent Magnet Machines
Magnet Shape Optimization of Two-Layer Spoke-Type Axial Flux Interior Permanent Magnet Machines Open
In this paper, the two-layer spoke-type (TLST) axial flux interior permanent magnet (AFIPM) machine is proposed. Simple flux barriers are added to optimize the air gap flux density, in which way there is no need to change the surface of th…
View article: Temperature Field Accurate Modeling and Cooling Performance Evaluation of Direct-Drive Outer-Rotor Air-Cooling In-Wheel Motor
Temperature Field Accurate Modeling and Cooling Performance Evaluation of Direct-Drive Outer-Rotor Air-Cooling In-Wheel Motor Open
High power density outer-rotor motors commonly use water or oil cooling. A reasonable thermal design for outer-rotor air-cooling motors can effectively enhance the power density without the fluid circulating device. Research on the heat di…
View article: Analytical Calculation of D- and Q-axis Inductance for Interior Permanent Magnet Motors Based on Winding Function Theory
Analytical Calculation of D- and Q-axis Inductance for Interior Permanent Magnet Motors Based on Winding Function Theory Open
Interior permanent magnet (IPM) motors are widely used in electric vehicles (EVs), benefiting from the excellent advantages of a more rational use of energy. For further improvement of energy utilization, this paper presents an analytical …
View article: Investigation of a Novel Mechanical to Thermal Energy Converter Based on the Inverse Problem of Electric Machines
Investigation of a Novel Mechanical to Thermal Energy Converter Based on the Inverse Problem of Electric Machines Open
A novel converter that can directly transform electrical, wind, hydraulic and other types of mechanical energy into thermal energy is presented in this study. First, the thermal energy of the converter is classified and then calculated by …