Runsheng Liu
YOU?
Author Swipe
View article: Design, Analysis, and Experiment of an Automatic Lettuce-Harvesting Mechanism
Design, Analysis, and Experiment of an Automatic Lettuce-Harvesting Mechanism Open
The global reduction in agricultural labor owing to rural depopulation and an aging workforce necessitates advancements in agricultural automation. This paper presents the design, optimization, and experimental validation of an innovative …
View article: The Principle and Application of Achromatic Metalens
The Principle and Application of Achromatic Metalens Open
Metalenses, as ultrathin planar optical devices based on metasurfaces, have attracted significant research interest in recent years due to their compact structure and versatile light manipulation, showing great potential to replace traditi…
View article: Generalizable Cervical Cancer Screening via Large-scale Pretraining and Test-Time Adaptation
Generalizable Cervical Cancer Screening via Large-scale Pretraining and Test-Time Adaptation Open
Cervical cancer is a leading malignancy in female reproductive system. While AI-assisted cytology offers a cost-effective and non-invasive screening solution, current systems struggle with generalizability in complex clinical scenarios. To…
View article: GAInS: Gradient Anomaly-aware Biomedical Instance Segmentation
GAInS: Gradient Anomaly-aware Biomedical Instance Segmentation Open
Instance segmentation plays a vital role in the morphological quantification of biomedical entities such as tissues and cells, enabling precise identification and delineation of different structures. Current methods often address the chall…
View article: Holistic and Historical Instance Comparison for Cervical Cell Detection
Holistic and Historical Instance Comparison for Cervical Cell Detection Open
Cytology screening from Papanicolaou (Pap) smears is a common and effective tool for the preventive clinical management of cervical cancer, where abnormal cell detection from whole slide images serves as the foundation for reporting cervic…
View article: A Conditional Privacy-Preserving Identity-Authentication Scheme for Federated Learning in the Internet of Vehicles
A Conditional Privacy-Preserving Identity-Authentication Scheme for Federated Learning in the Internet of Vehicles Open
With the rapid development of artificial intelligence and Internet of Things (IoT) technologies, automotive companies are integrating federated learning into connected vehicles to provide users with smarter services. Federated learning ena…
View article: LIA-V2X: A Lightweight identity mutual and batch authentication protocol for V2X Communication in Internet of Vehicles
LIA-V2X: A Lightweight identity mutual and batch authentication protocol for V2X Communication in Internet of Vehicles Open
Vehicular Ad hoc Networks (VANETs) hold significant importance within the domain of the Internet of Things. However, they face a critical issue concerning security threats. Criminals use open channels to eavesdrop, and tamper with messages…
View article: Hybrid Feature Selection and Fault Identification of Train Bearings Based on Integrated Learning
Hybrid Feature Selection and Fault Identification of Train Bearings Based on Integrated Learning Open
This Fast and accurate implementation of train bearing fault identification has been one of the key tasks of intelligent train health maintenance.In recent years, with the development of deep network technology, some bearing fault identifi…
View article: The intermediate level-sets of the four-dimensional membrane model
The intermediate level-sets of the four-dimensional membrane model Open
In this paper, we consider the discrete membrane model in four dimensions. We confirm the existence of the scaling limit of the intermediate (i.e., a multiple of the expected maximum) level-sets of the model, and show that it is equal in l…
View article: WITHDRAWN: CCR2 Contributes to the Homing of MSCs and Liver Regeneration
WITHDRAWN: CCR2 Contributes to the Homing of MSCs and Liver Regeneration Open
Objective: Mesenchymal stem cells (MSCs) are emerging as a new therapeutic strategy for liver diseases.However, the inability of stem cells to efficiently return to the target tissue is a major obstacle to repair.The chemokine family and i…
View article: Feasibility of in vivo Magnetic Induction Tomography in Rabbits
Feasibility of in vivo Magnetic Induction Tomography in Rabbits Open
Background: As a non-contact, non-invasive medical imaging technique, magnetic induction tomography (MIT) can measure the conductivity distribution inside the human body. Numerical calculation and physical phantom tests have showed the acc…
View article: Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding
Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding Open
The problem of $L_p$-norm constrained coding is to convert signal into code\nthat lies inside an $L_p$-ball and most faithfully reconstructs the signal.\nPrevious works under the name of sparse coding considered the cases of $L_0$\nand $L_…
View article: Screening of good-quality and high-yielding late rice varieties for Ganzhou tobacco-rice rotation area.
Screening of good-quality and high-yielding late rice varieties for Ganzhou tobacco-rice rotation area. Open
View article: Using an Adjustment Training and a Smoothing Mask for Speech Segregation
Using an Adjustment Training and a Smoothing Mask for Speech Segregation Open
This paper focuses on the improvement of speech intelligibility and nature auditory perception. A dual microphone computational auditory scene analysis (CASA) based speech segregation system is proposed. A deep neural network (DNN) is equi…
View article: L p -Norm Constrained Coding With Frank-Wolfe Network.
L p -Norm Constrained Coding With Frank-Wolfe Network. Open
We investigate the problem of $L_p$-norm constrained coding, i.e. converting signal into code that lies inside the $L_p$-ball and most faithfully reconstructs the signal. While previous works known as sparse coding have addressed the cases…
View article: Parameter masks for close talk speech segregation using deep neural networks
Parameter masks for close talk speech segregation using deep neural networks Open
\nA deep neural networks (DNN) based close talk speech segregation algorithm is introduced. One nearby microphone is used to collect the target speech as close talk indicated, and another microphone is used to get the noise in environments…