Tianrui Li
YOU?
Author Swipe
View article: Comparative Analysis of Regularization Methods for Predicting Student Certification
Comparative Analysis of Regularization Methods for Predicting Student Certification Open
This chapter uses predicting student certification in online courses hosted on edX to demonstrate how to apply three powerful regularization methods, namely Least Absolute Shrinkage and Selection Operator (LASSO), Smoothly Clipped Absolute…
View article: Strategic intercropping with mulberry (Morus alba L.) predictably modulates rhizosphere microbiome assembly and enriches pathways for secondary metabolite production
Strategic intercropping with mulberry (Morus alba L.) predictably modulates rhizosphere microbiome assembly and enriches pathways for secondary metabolite production Open
Intercropping is a key strategy for sustainable agriculture, but its effects on the rhizosphere microbiome remain poorly understood. Here, we investigated how intercropping mulberry (Morus alba L.) with functionally distinct partners-a nit…
View article: Corrigendum to “CFD of the diffusion movement and concentration distribution of culinary particles in the respiratory zone of restaurant diners” [Heliyon Volume 10, Issue 13, July 2024, Article e33610]
Corrigendum to “CFD of the diffusion movement and concentration distribution of culinary particles in the respiratory zone of restaurant diners” [Heliyon Volume 10, Issue 13, July 2024, Article e33610] Open
View article: Study on Lightning-Induced Plasma Extinguishing in 10 kV Distribution Network Lines Based on Electronegative Gas Trifluoroiodomethane
Study on Lightning-Induced Plasma Extinguishing in 10 kV Distribution Network Lines Based on Electronegative Gas Trifluoroiodomethane Open
Plasma arcs generated by lightning strikes are prone to tripping distribution lines, especially 10 kV lines. To reduce the lightning-induced tripping rate of 10 kV distribution lines and ensure the safe operation of power systems, this pap…
View article: TRUST-FS: Tensorized Reliable Unsupervised Multi-View Feature Selection for Incomplete Data
TRUST-FS: Tensorized Reliable Unsupervised Multi-View Feature Selection for Incomplete Data Open
Multi-view unsupervised feature selection (MUFS), which selects informative features from multi-view unlabeled data, has attracted increasing research interest in recent years. Although great efforts have been devoted to MUFS, several chal…
View article: Microstructure and mechanical properties of steel/aluminum circular oscillation laser welded joint
Microstructure and mechanical properties of steel/aluminum circular oscillation laser welded joint Open
The lap welding experiments of DP590 dual phase steel and 6022 aluminum alloys were carried out by using circular oscillation laser. The mechanism of circular oscillation on the morphology, element distribution, grain size and mechanical p…
View article: MHSNet: A Multi-Scale Hidden State Interaction Network for Fault Diagnosis of Rotating Machinery
MHSNet: A Multi-Scale Hidden State Interaction Network for Fault Diagnosis of Rotating Machinery Open
View article: FNH-TTS: A Fast, Natural, and Human-Like Speech Synthesis System with advanced prosodic modeling based on Mixture of Experts
FNH-TTS: A Fast, Natural, and Human-Like Speech Synthesis System with advanced prosodic modeling based on Mixture of Experts Open
Achieving natural and human-like speech synthesis with low inference costs remains a major challenge in speech synthesis research. This study focuses on human prosodic patterns and synthesized spectrum harmony, addressing the challenges of…
View article: Rendering algorithm for 3D model of goods in power warehouse based on linear interpolation and 2D texture mapping
Rendering algorithm for 3D model of goods in power warehouse based on linear interpolation and 2D texture mapping Open
Given the technical requirements for equipment storage in the power industry, conventional storage methods prove inadequate for managing specialized materials such as precision instruments. To address texture distortion and detail loss in …
View article: Beyond Fixed Variables: Expanding-variate Time Series Forecasting via Flat Scheme and Spatio-temporal Focal Learning
Beyond Fixed Variables: Expanding-variate Time Series Forecasting via Flat Scheme and Spatio-temporal Focal Learning Open
View article: Improving Open-world Continual Learning under the Constraints of Scarce Labeled Data
Improving Open-world Continual Learning under the Constraints of Scarce Labeled Data Open
View article: ModelNet40-E: An Uncertainty-Aware Benchmark for Point Cloud Classification
ModelNet40-E: An Uncertainty-Aware Benchmark for Point Cloud Classification Open
We introduce ModelNet40-E, a new benchmark designed to assess the robustness and calibration of point cloud classification models under synthetic LiDAR-like noise. Unlike existing benchmarks, ModelNet40-E provides both noise-corrupted poin…
View article: ErrorEraser: Unlearning Data Bias for Improved Continual Learning
ErrorEraser: Unlearning Data Bias for Improved Continual Learning Open
Continual Learning (CL) primarily aims to retain knowledge to prevent catastrophic forgetting and transfer knowledge to facilitate learning new tasks. Unlike traditional methods, we propose a novel perspective: CL not only needs to prevent…
View article: Simulation study of nonlinear conductivity and electric field distribution in cross-linked polyethylene (XLPE) cables under multiphysics coupling
Simulation study of nonlinear conductivity and electric field distribution in cross-linked polyethylene (XLPE) cables under multiphysics coupling Open
The reliable operation of high-voltage power cables largely depends on accurately predicting the internal electric field distribution under complex service conditions. In cross-linked polyethylene (XLPE) insulated cables, prolonged direct …
View article: Acoustic Fault Diagnosis Method for Rotating Machinery Based on Collaborative Perception Information Aggregation Guidance Network
Acoustic Fault Diagnosis Method for Rotating Machinery Based on Collaborative Perception Information Aggregation Guidance Network Open
The non-contact and directional nature of acoustic fault diagnosis offers a distinct advantage for fault detection in complex environments, ensuring the safe and stable operation of rotating machinery. However, challenges such as complex w…
View article: Can diffusion-based generated magnetic resonance images predict glioma methylation accurately?
Can diffusion-based generated magnetic resonance images predict glioma methylation accurately? Open
Our diffusion-based model demonstrates promise in accelerating magnetic resonance image acquisition while preserving vital pathological detail, suggesting enhanced diagnostic capabilities. Future research will evaluate its clinical applica…
View article: Non-collective Calibrating Strategy for Time Series Forecasting
Non-collective Calibrating Strategy for Time Series Forecasting Open
Deep learning-based approaches have demonstrated significant advancements in time series forecasting. Despite these ongoing developments, the complex dynamics of time series make it challenging to establish the rule of thumb for designing …
View article: One year in the classroom with ChatGPT: empirical insights and transformative impacts
One year in the classroom with ChatGPT: empirical insights and transformative impacts Open
Generative Artificial Intelligence (GAI), such as OpenAI’s ChatGPT, has rapidly emerged as a transformative tool in higher education, offering opportunities to enhance teaching and learning. This paper describes the design and implementati…
View article: Less is More: Efficient Point Cloud Reconstruction via Multi-Head Decoders
Less is More: Efficient Point Cloud Reconstruction via Multi-Head Decoders Open
We challenge the common assumption that deeper decoder architectures always yield better performance in point cloud reconstruction. Our analysis reveals that, beyond a certain depth, increasing decoder complexity leads to overfitting and d…
View article: Neural Associative Skill Memories for safer robotics and modelling human sensorimotor repertoires
Neural Associative Skill Memories for safer robotics and modelling human sensorimotor repertoires Open
Modern robots face challenges shared by humans, where machines must learn multiple sensorimotor skills and express them adaptively. Equipping robots with a human-like memory of how it feels to do multiple stereotypical movements can make r…
View article: Near-boundary noise improved few-shot out-of-distribution detection
Near-boundary noise improved few-shot out-of-distribution detection Open
View article: MSTI-Plus: Introducing Non-Sarcasm Reference Materials to Enhance Multimodal Sarcasm Target Identification
MSTI-Plus: Introducing Non-Sarcasm Reference Materials to Enhance Multimodal Sarcasm Target Identification Open
View article: TIME-FS: Joint Learning of Tensorial Incomplete Multi-View Unsupervised Feature Selection and Missing-View Imputation
TIME-FS: Joint Learning of Tensorial Incomplete Multi-View Unsupervised Feature Selection and Missing-View Imputation Open
Multi-view unsupervised feature selection (MUFS) has received considerable attention in recent years. Existing MUFS methods for processing unlabeled incomplete multi-view data, where some samples are missing in certain views, first impute …
View article: Scalable and Trustworthy Learning in Heterogeneous Networks
Scalable and Trustworthy Learning in Heterogeneous Networks Open
To build a responsible data economy and protect data ownerhip, it is crucial to enable learning models from separate, heterogeneous data sources without centralization. For example, federated learning (FL) aims to train models across massi…
View article: Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration
Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration Open
Understanding how humans cooperatively utilize semantic knowledge to explore unfamiliar environments and decide on navigation directions is critical for house service multi-robot systems. Previous methods primarily focused on single-robot …
View article: Inner-shell electrons enable both high power and energy densities
Inner-shell electrons enable both high power and energy densities Open
Energy supply technologies are mainly based on lithium-ion batteries, which are approaching their theoretical power density of 1901 W⋅L−1 and energy density of 568 Wh⋅kg−1 with the use of outer-shell electrons. The above limitations are re…
View article: Dual‐Branch Graph Neural Network for Predicting Molecular Odors and Discovering the Relationship Between Functional Groups and Odors
Dual‐Branch Graph Neural Network for Predicting Molecular Odors and Discovering the Relationship Between Functional Groups and Odors Open
Prediction of molecular odors is crucial for synthetic chemistry and the perfume industry. This paper presents a dual‐branch graph neural network model for predicting molecular odors, named ScentGraphX, which combines transfer learning wit…
View article: In Situ Crystallization of Copper(I)‐Based Hybrid Halides Assisted by Carboxymethylcellulose Sodium for a Large‐Area Scintillation Imaging Screen
In Situ Crystallization of Copper(I)‐Based Hybrid Halides Assisted by Carboxymethylcellulose Sodium for a Large‐Area Scintillation Imaging Screen Open
Exploring new types of scintillators, especially fabricating large‐area scintillating screens, is essential in applications of life science, industry, and material science. However, the thickness and light scattering in composite scintilla…
View article: Reliability analysis of passive residual heat removal system for large advanced pressurized water reactors
Reliability analysis of passive residual heat removal system for large advanced pressurized water reactors Open
This paper focuses on the passive residual heat removal system of a typical large advanced pressurized water reactor, analyzing its design, performance, and reliability during station blackout conditions combined with the failure of the au…
View article: Tackling Small Sample Survival Analysis via Transfer Learning: A Study of Colorectal Cancer Prognosis
Tackling Small Sample Survival Analysis via Transfer Learning: A Study of Colorectal Cancer Prognosis Open
Survival prognosis is crucial for medical informatics. Practitioners often confront small-sized clinical data, especially cancer patient cases, which can be insufficient to induce useful patterns for survival predictions. This study deals …