Guang-Bin Huang

Zhengzhou University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Zhiping Lin

Nanyang Technological University

P. Saratchandran

Cochin University of Science and Technology

N. Sundararajan

Nanyang Technological University

Dongshun Cui

Nanyang Technological University

Chenwei Deng

Beijing Institute of Technology

Guanghao Zhang

University of Michigan–Ann Arbor

Chamara Kasun Liyanaarachchi Lekamalage

Nanyang Technological University

Yuan Lan

Taiyuan University of Technology

Tianchi Liu

Technical Institute of Physics and Chemistry

Chee‐Kheong Siew

Nanyang Technological University

Cooperative Institutions

Nanyang Technological University

176

Chinese Academy of Sciences

Korea Advanced Institute of Science and Technology

Chongqing University

National University of Singapore

Centre National de la Recherche Scientifique

Tsinghua University

University of Chinese Academy of Sciences

École Polytechnique Fédérale de Lausanne

University of Melbourne

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Guest Editorial: Special Issue on New Trends in Smart Chips and Smart Hardware

IEEE Transactions on Emerging Topics in Computational Intelligence (2019)

Guang-Bin Huang Evangelos Eleftheriou Dhireesha Kudithipudi Jonathan Tapson Hao Yu

The articles in this special section aim to promote novel research investigations in low power and low latency of smart chips and smart hardware for machine learning and biologically-plausible learning.

10.1109/tetci.2018.2890048

Cite

Citations (4)

Systemical convergence rate analysis of convex incremental feedforward neural networks

Neurocomputing (2008)

Lei Chen Guang-Bin Huang Hung Keng Pung

Feedforward neural network

Feed forward

Proper convex function

10.1016/j.neucom.2008.10.016

Cite

Citations (17)

Two-stage structured learning approach for stable occupancy detection

2022 International Joint Conference on Neural Networks (IJCNN) (2016)

Tianchi Liu Yue Li Zuo Bai Jaydeep De Cao Vinh Le

Monitoring the presence of occupants in a room in a timely manner is a fundamental step for effective building management. Environmental sensor networks have the advantages of high cost-efficiency and non-intrusiveness on privacy and are very suitable for room occupancy detection. Nonlinear discriminative models, e.g., support vector machine and neural networks, have shown good detection performance due to their ability to model complex relationship. However, they tend to produce unstable detection with frequent fluctuations over time, because they regard training data as independent and ignore the prior knowledge of the room occupancy, i.e., not changing very frequently. To improve the stability of the detection, we propose a two-stage structured learning approach with Extreme Learning Machine (ELM) as the local classifier. In the first stage, ELM is used as a fast nonlinear classifier to obtain preliminary detection results. In the second stage, we form data sequences consisting of the current and previous data points. The preliminary detection results by ELM of the data sequences are then used as input to a linear support vector machine for structured output to generate the final detection results. We test the proposed two-stage structured learning approach on a real-world dataset and show that the proposed approach outperforms the related machine learning methods.

Extreme Learning Machine

Intrusiveness

Discriminative model

10.1109/ijcnn.2016.7727485

Cite

Citations (16)

Large-Scale Automated Sleep Staging

SLEEP (2017)

Haoqi Sun Jian Jia Balaji Goparaju Guang-Bin Huang Olga Sourina

Automated sleep staging has been previously limited by a combination of clinical and physiological heterogeneity. Both factors are in principle addressable with large data sets that enable robust calibration. However, the impact of sample size remains uncertain. The objectives are to investigate the extent to which machine learning methods can approximate the performance of human scorers when supplied with sufficient training cases and to investigate how staging performance depends on the number of training patients, contextual information, model complexity, and imbalance between sleep stage proportions. A total of 102 features were extracted from six electroencephalography (EEG) channels in routine polysomnography. Two thousand nights were partitioned into equal (n = 1000) training and testing sets for validation. We used epoch-by-epoch Cohen's kappa statistics to measure the agreement between classifier output and human scorer according to American Academy of Sleep Medicine scoring criteria. Epoch-by-epoch Cohen's kappa improved with increasing training EEG recordings until saturation occurred (n = ~300). The kappa value was further improved by accounting for contextual (temporal) information, increasing model complexity, and adjusting the model training procedure to account for the imbalance of stage proportions. The final kappa on the testing set was 0.68. Testing on more EEG recordings leads to kappa estimates with lower variance. Training with a large data set enables automated sleep staging that compares favorably with human scorers. Because testing was performed on a large and heterogeneous data set, the performance estimate has low variance and is likely to generalize broadly.

Kappa

Cohen's kappa

Sleep Stages

10.1093/sleep/zsx139

Cite

Citations (100)

Brain-inspired Cognition and Understanding for Next-generation AI: Computational Models, Architectures and Learning Algorithms

Frontiers research topics (2023)

Chenwei Deng Guang-Bin Huang Yuqi Han

10.3389/978-2-83252-116-8

Cite

Citations (1)

Machine Learning Reveals Different Brain Activities in Visual Pathway during TOVA Test

Proceedings in adaptation, learning and optimization (2014)

Haoqi Sun Olga Sourina Yan Yang Guang-Bin Huang Cornelia Denk

10.1007/978-3-319-14063-6_22

Cite

Citations (1)

Simplification of a specific two-hidden-layer feedforward networks

L. Chen Guang-Bin Huang C.K. Siew

A specific two-hidden-layer feedforward networks (TLFNs) proposed by G.B. Huang (2003) is presented in this paper. A method is introduced to simplify the structure of the TLFNs by introducing a new type of quantizers that unite two previous neurons A/sup (p)/ and B/sup (p)/ into a single neuron. Those new quantizers choose a special type of function as the neural network's activation function, which leads to the new TLFNs with 2/spl radic/((m+1)N) hidden neurons can learn N distinct samples (x/sub i/, t/sub i/) with negligibly small error, where m is the number of output neurons, and unlike Huang's TLFNs require 2/spl radic/((m+2)N) hidden neurons. Moreover, it is not necessary to estimate the quantizer value U defined in Huang's TLFNs, which is fixed in our new model of TLFNs. It can reduce significantly and markedly the complexity and computation of neural networks.

Feedforward neural network

Activation function

Feed forward

Value (mathematics)

Echo state network

10.1109/icics.2003.1292609

Cite

Citations (1)

Lactobacillus plantarum KSFY06 on d‐galactose‐induced oxidation and aging in Kunming mice

Food Science & Nutrition (2019)

Fang Li Guang-Bin Huang Fang Tan Ruokun Yi Xianrong Zhou

Abstract Yogurt from Xinjiang, China, is a traditional Chinese fermented food rich in beneficial microorganisms, such as Lactobacillus plantarum KSFY06. In this study, the effect of KSFY06 on oxidative aging was investigated using live animal experiments. Molecular biological methods were used to analyze the serum and tissues of mice with oxidative aging induced by d ‐galactose, which showed that KSFY06 can inhibit the decline of heart, liver, spleen, and kidney caused by aging. The KSFY06 strain increased the activity of superoxide dismutase (SOD), glutathione peroxidase (GSH‐Px), catalase (CAT), and glutathione (GSH) in serum and liver of aging mice, while the content of malondialdehyde (MDA) is reduced. Pathological observation showed that KSFY06 alleviated damage to the liver, spleen, and skin of oxidative aging mice. qPCR showed that, at high dose (2 × 10 9 cfu/kg per day), KSFY06 upregulates copper/zinc superoxide dismutase (SOD1), manganese superoxide dismutase (SOD2), endothelial nitric oxide synthase (eNOS), neuronal nitric oxide synthase (nNOS), catalase (CAT) mRNA expression, and its downstream inducible nitric oxide synthase (iNOS) mRNA expression in liver and spleen tissues induced by d ‐gal. To a certain extent, these findings indicate that L. plantarum KSFY06 is able to protect against oxidative stress in the d ‐gal‐induced aging model. In conclusion, L. plantarum KSFY06 may provide a potential research value in the prevention or alleviation of related diseases caused by oxidative stress.

Malondialdehyde

SOD2

Dismutase

10.1002/fsn3.1318

Cite

Citations (35)

Conditional Random Mapping for Effective ELM Feature Representation

Cognitive Computation (2018)

Cheng Li Chenwei Deng Shichao Zhou Baojun Zhao Guang-Bin Huang

Discriminative model

Feature (linguistics)

Representation