Junhua Liu

Inner Mongolia Electric Power Survey & Design Institute (China)

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Kwan Hui Lim

Singapore University of Technology and Design

Kristin L. Wood

University of Colorado Denver

Luciënne Blessing

Singapore University of Technology and Design

Trisha Singhal

Singapore University of Technology and Design

Le Luo Guan

University of Alberta

Weiyun Zhu

Nanjing Agricultural University

Sarah A. Strode

Morgan State University

Shengyong Mao

Nanjing Agricultural University

Fei Xie

Taiyuan University of Science and Technology

Huazhe Si

Jilin Agricultural University

Cooperative Institutions

Chinese Academy of Sciences

University of Science and Technology of China

Singapore University of Technology and Design

Shanghai Jiao Tong University

University of Chinese Academy of Sciences

National University of Defense Technology

University of Electronic Science and Technology of China

National University of Singapore

Tsinghua University

Huazhong University of Science and Technology

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Investigation of multi-agent based online partial discharge monitoring system for generator

Linpeng Yao Chengjun Huang Hui Wang Junhua Liu Yong Qian

In the contribution, we applied the artificial intelligence to the partial discharge (PD) online diagnosis for generator, and a PD diagnosis multi-agent system was established. For problems exist in partial discharge evaluation, such as preprocessing, features extraction, trend and fingerprint analysis, corresponding methods and schemes were described, and furthermore, the framework of the Multi-Agent system and detailed design of each agent were depicted.

Source

Cite

Citations (0)

A Transformer-based Framework for POI-level Social Post Geolocation

arXiv (Cornell University) (2022)

Menglin Li Kwan Hui Lim Teng Guo Junhua Liu

POI-level geo-information of social posts is critical to many location-based applications and services. However, the multi-modality, complexity and diverse nature of social media data and their platforms limit the performance of inferring such fine-grained locations and their subsequent applications. To address this issue, we present a transformer-based general framework, which builds upon pre-trained language models and considers non-textual data, for social post geolocation at the POI level. To this end, inputs are categorized to handle different social data, and an optimal combination strategy is provided for feature representations. Moreover, a uniform representation of hierarchy is proposed to learn temporal information, and a concatenated version of encodings is employed to capture feature-wise positions better. Experimental results on various social datasets demonstrate that three variants of our proposed framework outperform multiple state-of-art baselines by a large margin in terms of accuracy and distance error metrics.

Geolocation

Margin (machine learning)

Geotagging

Feature (linguistics)

10.48550/arxiv.2211.01336

Cite

Citations (0)

Sample ECCOH OH Parameterization

Zenodo (CERN European Organization for Nuclear Research) (2022)

Daniel C. Anderson Melanie B. Follette‐Cook Sarah A. Strode Julie M. Nicely Junhua Liu

A sample parameterization of OH for July created to be used with the ECCOH module of the GEOS Earth System Model. The methodology to generate the parameterization is described in detail in the GMD article "A Machine Learning Methodology for the Generation of a Parameterization of the Hydroxyl Radical". The parameterization is included as an example and should not be used for research purposes without consulting the publication and/or the authors. We have also included the dataset used to train the parameterization (OHParameterization_TrainingSet_1980_2019_M07.dat) as well as the training targets (OHParameterization_Targets_1980_2019_M07.dat). The training data are from the NASA MERRA2 GMI simulation (https://acd-ext.gsfc.nasa.gov/Projects/GEOSCCM/MERRA2GMI/). The scripts used to generate the training dataset and the parameterization can be found at https://zenodo.org/record/6046037.

Sample (material)

10.5281/zenodo.6604129

Cite

Citations (0)

Research on surface morphology analysis of aramid paper

Junhua Liu X Liu High

para-aramid paper is made by cut fiber having a rigid rod structure and pulp having hairiness structure. Because there is no bonding force, the morphology, surface properties and bonding status become the vital factor affecting wet formation, surface and internal strength. Therefore it is necessary to study the surface morphology of aramid fiber. In this paper, the analysis on aramid paper surface and aramid fiber was carried out.

Aramid

Morphology

Cite

Citations (0)

Learning Efficient Lexically-Constrained Neural Machine Translation with External Memory

arXiv (Cornell University) (2019)

Ya Li Xinyu Liu Dan Liu Xueqiang Zhang Junhua Liu

Recent years has witnessed dramatic progress of neural machine translation (NMT), however, the method of manually guiding the translation procedure remains to be better explored. Previous works proposed to handle such problem through lexcially-constrained beam search in the decoding phase. Unfortunately, these lexically-constrained beam search methods suffer two fatal disadvantages: high computational complexity and hard beam search which generates unexpected translations. In this paper, we propose to learn the ability of lexically-constrained translation with external memory, which can overcome the above mentioned disadvantages. For the training process, automatically extracted phrase pairs are extracted from alignment and sentence parsing, then further be encoded into an external memory. This memory is then used to provide lexically-constrained information for training through a memory-attention machanism. Various experiments are conducted on WMT Chinese to English and English to German tasks. All the results can demonstrate the effectiveness of our method.

Phrase

10.48550/arxiv.1901.11344

Cite

Citations (6)

A Large-scale Industrial and Professional Occupation Dataset

arXiv (Cornell University) (2020)

Junhua Liu Yung Chuen Ng Kwan Hui Lim

There has been growing interest in utilizing occupational data mining and analysis. In today's job market, occupational data mining and analysis is growing in importance as it enables companies to predict employee turnover, model career trajectories, screen through resumes and perform other human resource tasks. A key requirement to facilitate these tasks is the need for an occupation-related dataset. However, most research use proprietary datasets or do not make their dataset publicly available, thus impeding development in this area. To solve this issue, we present the Industrial and Professional Occupation Dataset (IPOD), which comprises 192k job titles belonging to 56k LinkedIn users. In addition to making IPOD publicly available, we also: (i) manually annotate each job title with its associated level of seniority, domain of work and location; and (ii) provide embedding for job titles and discuss various use cases. This dataset is publicly available at https://github.com/junhua/ipod.

Seniority

10.48550/arxiv.2005.02780

Cite

Citations (0)

CrisisBERT: a Robust Transformer for Crisis Classification and Contextual Crisis Embedding

arXiv (Cornell University) (2020)

Junhua Liu Trisha Singhal Luciënne Blessing Kristin L. Wood Kwan Hui Lim

Classification of crisis events, such as natural disasters, terrorist attacks and pandemics, is a crucial task to create early signals and inform relevant parties for spontaneous actions to reduce overall damage. Despite crisis such as natural disasters can be predicted by professional institutions, certain events are first signaled by civilians, such as the recent COVID-19 pandemics. Social media platforms such as Twitter often exposes firsthand signals on such crises through high volume information exchange over half a billion tweets posted daily. Prior works proposed various crisis embeddings and classification using conventional Machine Learning and Neural Network models. However, none of the works perform crisis embedding and classification using state of the art attention-based deep neural networks models, such as Transformers and document-level contextual embeddings. This work proposes CrisisBERT, an end-to-end transformer-based model for two crisis classification tasks, namely crisis detection and crisis recognition, which shows promising results across accuracy and f1 scores. The proposed model also demonstrates superior robustness over benchmark, as it shows marginal performance compromise while extending from 6 to 36 events with only 51.4% additional data points. We also proposed Crisis2Vec, an attention-based, document-level contextual embedding architecture for crisis embedding, which achieve better performance than conventional crisis embedding methods such as Word2Vec and GloVe. To the best of our knowledge, our works are first to propose using transformer-based crisis classification and document-level contextual crisis embedding in the literature.

Word2vec

Robustness

10.48550/arxiv.2005.06627

Cite

Citations (20)

A Noise Points Detection Algorithm for Clustering

Wuning Tong Peng Wang Yang Wang Junhua Liu

10.3850/978-981-18-8813-7_p208-cd

Cite

Citations (0)

システムモデリングに基づく四像限光電検出器アライメントと微小変位測定システム【JST・京大機械翻訳】

Chinese Journal of Lasers (2009)

Xiaojun Tang Li Yujun Junhua Liu Liang Kun

Source

Cite

Citations (0)

Photozilla: An Image Dataset of Photography Styles and its Application to Visual Embedding and Style Detection

Trisha Singhal Junhua Liu Wenchuan Mu Luciënne Blessing Kwan Hui Lim

The widespread sharing of digital photography and images have led to the rapid development of various vision-related applications, such as photography style detection. Towards this effort, we introduce a photography style dataset termed Photozilla, which comprises over 990k images belonging to 10 different photographic styles. We used Photozilla to train 3 classification models for categorizing images into the relevant style and achieve an accuracy of ~96%. To better detect new photography styles that are constantly emerging, we also present a Siamese-based network that uses the trained classification models as the base architecture to adapt and classify unseen styles with only 25 training samples. Experiment results show an accuracy of over 68% in terms of identifying 10 additional distinct categories of photography styles. This dataset can be found at https://trisha025.github.io/Photozilla/.

10.1145/3625007.3627476

Cite

Citations (0)