Geng Ji
YOU?
Author Swipe
View article: Prediction of Temperature Distribution on an Aircraft Hot-Air Anti-Icing Surface by ROM and Neural Networks
Prediction of Temperature Distribution on an Aircraft Hot-Air Anti-Icing Surface by ROM and Neural Networks Open
To address the inefficiencies and time-consuming nature of traditional hot-air anti-icing system designs, reduced-order models (ROMs) and machine learning techniques are introduced to predict anti-icing surface temperature distributions. T…
View article: Prediction of Temperature Distribution on Aircraft Hot-air Anti-icing Surface by ROM and Neural Networks
Prediction of Temperature Distribution on Aircraft Hot-air Anti-icing Surface by ROM and Neural Networks Open
This study aims to address the inefficiencies and time-consuming nature of traditional hot-air anti-icing system designs by introducing reduced order models (ROM) and machine learning techniques to predict anti-icing surface temperature di…
View article: Correction to: Learning to bid and rank together in recommendation systems
Correction to: Learning to bid and rank together in recommendation systems Open
View article: Learning to bid and rank together in recommendation systems
Learning to bid and rank together in recommendation systems Open
Many Internet applications adopt real-time bidding mechanisms to ensure different services (types of content) are shown to the users through fair competitions. The service offering the highest bid price gets the content slot to present a l…
View article: Multi-level parallel neural networks based multimodal human brain tumor image segmentation framework
Multi-level parallel neural networks based multimodal human brain tumor image segmentation framework Open
目的 在脑肿瘤临床诊疗过程中，由于医疗资源稀缺与诊断效率偏低，迫切需要高精度的医学图像分割工具进行辅助诊疗。目前，使用卷积神经网络进行脑肿瘤图像分割已经成为主流，但是其对于脑肿瘤信息的利用并不充分，导致精度与效率并不完善，而且重新设计一个全新且高效的深度神经网络模型是一项成本高昂的任务。为了更有效提取脑肿瘤图像中的特征信息，提出了基于多层级并行神经网络的多模态脑肿瘤图像分割框架。方法 该框架基于现有的网络结构进行拓展，以ResNet （residual network）网络…
View article: MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks
MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks Open
In many personalized recommendation scenarios, the generalization ability of\na target task can be improved via learning with additional auxiliary tasks\nalongside this target task on a multi-task network. However, this method often\nsuffe…
View article: EnGAN: Enhancement Generative Adversarial Network in Medical Image Segmentation
EnGAN: Enhancement Generative Adversarial Network in Medical Image Segmentation Open
Deep learning has been widely used in medical image segmentation, although the accuracy is affected by the problems of small sample space, data imbalance, and cross-device differences. Aiming at such issues, a enhancement GAN network is pr…
View article: Generic network for domain adaptation based on self-supervised learning and deep clustering
Generic network for domain adaptation based on self-supervised learning and deep clustering Open
Domain adaptation methods train a model to find similar feature representations between a source and target domain. Recent methods leverage self-supervised learning to discover the analogous representations of the two domains. However, pri…
View article: Table of Contents
Table of Contents Open
View article: A Multi-View Dynamic Fusion Framework: How to Improve the Multimodal Brain Tumor Segmentation from Multi-Views?
A Multi-View Dynamic Fusion Framework: How to Improve the Multimodal Brain Tumor Segmentation from Multi-Views? Open
When diagnosing the brain tumor, doctors usually make a diagnosis by observing multimodal brain images from the axial view, the coronal view and the sagittal view, respectively. And then they make a comprehensive decision to confirm the br…
View article: Chinese Classical Prescription (Liang-Xue-Di-Huang Decoction) for Hemorrhoidal Disease: study protocol for a randomized controlled trial
Chinese Classical Prescription (Liang-Xue-Di-Huang Decoction) for Hemorrhoidal Disease: study protocol for a randomized controlled trial Open
Background: Hemorrhoidal disease (HD) is one of the commonest proctologic condition in the general population. Medical therapy for HD has not been formally confirmed due to the inconsistent of results. Liang-Xue-Di-Huang Decoction, a kind …
View article: Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
Meta-GNN: On Few-shot Node Classification in Graph Meta-learning Open
Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are…
View article: Revocable Cloud-Assisted Attribute-Based Signcryption in Personal Health System
Revocable Cloud-Assisted Attribute-Based Signcryption in Personal Health System Open
PHR System is a favorable platform for personal health information exchange. In order to ensure that the personal information is not falsified and leaked by malicious users, we use the attribute-based signcryption technology to provide sec…
View article: Efficient Variational Inference for Hierarchical Models of Images, Text, and Networks
Efficient Variational Inference for Hierarchical Models of Images, Text, and Networks Open
Variational inference provides a general optimization framework to approximate the posterior distributions of latent variables in probabilistic models. Although effective in simple scenarios, variational inference may be inaccurate or infe…
View article: Ciphertext-Policy Attribute-Based Signcryption With Verifiable Outsourced Designcryption for Sharing Personal Health Records
Ciphertext-Policy Attribute-Based Signcryption With Verifiable Outsourced Designcryption for Sharing Personal Health Records Open
Personal health record (PHR) is a patient-centric model of health information exchange, which greatly facilitates the storage, access, and share of personal health information. In order to share the valuable resources and reduce the operat…
View article: Bayesian Paragraph Vectors
Bayesian Paragraph Vectors Open
Word2vec (Mikolov et al., 2013) has proven to be successful in natural language processing by capturing the semantic relationships between different words. Built on top of single-word embeddings, paragraph vectors (Le and Mikolov, 2014) fi…