Extreme learning machine based mutual information estimation with application to time-series change-points detection

Oh, Beom-Seok; Sun, Lei; Ahn, Chung Soo; Yeo, Yong Kiang; Yan, Yang; Liu, Nan; Lin, Zhiping

doi:10.1016/j.neucom.2015.11.138

Cited by 6 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many classical in-laboratory stress protocols which have been proved to be effective in eliciting stress, and thus enabling the investigation of stress under controlled conditions [23]. Such stress protocols include Cold Pressor Test (CPT) [41], Trier Social Stress Test (TSST) [25], the SCWT [26], [27], N-back task [30], etc. The CPT is a test in which the participants are required to place their nondominant hand in a box filled with ice-cold water for as long as possible.…”

Section: B Stresses Induced By Scwt Vs By Drivingmentioning

confidence: 99%

“…Many researches make use of EEG [5], [6], [7] and ECG [8], [9], [10], [30] signals to design stress classifiers to monitor or analyze stresses. The general strategy is to use a stressorthe technical term of the stress inducing factor -to evolve stresses of testers, collect EEG or ECG signals, extract related features from the signals, and finally train and verify classifiers using machine learning methods.…”

Section: Introductionmentioning

confidence: 99%

“…The general strategy is to use a stressorthe technical term of the stress inducing factor -to evolve stresses of testers, collect EEG or ECG signals, extract related features from the signals, and finally train and verify classifiers using machine learning methods. The commonly used stressors include Stroop color word test (SCWT) [6], [8], undertaking real work with different levels of stress [5], performing arithmetic calculation [7], [10], N-back task [30], and watching videos [5], [9]. In training and testing of classifiers, statistical machine leaning methods such as Support Vector Machine (SVM) [6], [7], [9] and -Nearest Neighbor ( -NN) [8], [9] are more often used than neural networks [10].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Identification of Stress State for Drivers Under Different GPS Navigation Modes

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

It is commonly known that Global Positioning System (GPS) can alleviate travelling difficulties of automobile drivers, and generally we hold the view that it reduces the driver's stress when they are in unfamiliar road conditions. In this research, an in-laboratory experiment and an in-car experiment are conducted to find out whether GPS instructions can reduce or may induce additional mental stress of drivers. Electrocardiography (ECG) signals are collected in the experiments and the extracted heart rate variability (HRV) features are used for analysis. Three binary classifiers, specifically Support Vector Machine,-Nearest Neighbor (k-NN) and Random Forest, are trained based on the data collected in the in-laboratory experiment, where the stress state is elicited by the Stroop color word Test. The k-NN classifier outperforms the other two classifiers, and thus is applied to the data collected in the in-car experiment, to identify drivers' stress state under different driving events, such as waiting for traffic lights, turning, under GPS instructions, and traffic conditions like overtaking, or changing lanes. During each event, whether the driver is in stress or relaxed state for each time instant is predicted based on the trained classifier. The percentages of time that the driver is in stress state for each type of events are computed. It shows that GPS instructions cause the second largest time-percentage of stress state, lower than that caused by the turning event, but higher than that caused by the events of waiting for traffic lights and other traffic conditions. INDEX TERMS Driver stress, GPS navigation, k-NN classifier, Stroop color word test, HRV features, ECG signal Jingbin Li received the B.Eng. degree in Information Engineering from the Southern

show abstract

Section: B Stresses Induced By Scwt Vs By Drivingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Stress State for Drivers Under Different GPS Navigation Modes

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, Adaboost with Eigenspace denoising ELM (AE-ELM) is proposed to achieve robust ECG anomaly detection [82]. ELM-MI method [23] Furthermore, the detailed background of the ELM and its variants will be presented in Chapter 2.3. LODA [83] is a lightweight anomaly detector that ensembles different detectors and is suitable for data streams.…”

Section: Common Methods For Anomaly Detectionmentioning

confidence: 99%

“…To balance the learning ability and the computational resources requirements, extreme learning machine (ELM) [22] based frameworks, which have the advantages of low training cost and good generalization performance, are potential solutions for anomaly detection tasks. Furthermore, the extreme learning machine with mutual information estimation (ELM-MI) [23] has been proposed for detecting change points in time-series data with promising results. However, change points are only one of the potential types of anomalies [24].…”

Section: Background and Motivationmentioning

confidence: 99%

Event recognition and anomaly detection using machine learning

Peng

View full text Add to dashboard Cite

I sincerely express my greatest gratitude to my supervisor Prof. Zhiping Lin, for being the most crucial guide academically and mentally throughout my Ph.D. career. He is kind, wise, and hard-working, providing me with numerous resources, patience and attention for my research. He immediately advises me when I have doubts about research and daily-life trifles. Also, his highest moral and academic standards influence me well. He undeniably sets an excellent example for my later career and life. I feel very fortunate to be his student. I thank Prof. Guang-Bin Huang for his supervision in the first two years. I would thank Dr. Hanhui Li, Prof. Huiping Zhuang, Prof. Qi Cao，Mr. Rongzihan Song and Ms. Yuxuan Lin for their valuable advice and discussions with me. I also like to thank my old friends in China and other colleagues in NTU.I would express my greatest gratefulness to my parents. They have spent as much as they can to support my education since my kindergarten. They always try their best to provide me with the best, even beyond their capability. They choose to accept all my negative feelings and make me believe families always stand behind me. The love they give me can not be expressed in words. I express my deep thanks to my parents-in-law, too. They treat me as their son and give me great patience and support in my life in Singapore. I would also like to thank my other family members, especially my cousin and brother-in-law, who frequently share academic advice and life tips.Finally, but most importantly, I would like to express my greatest thanks to my wife, Yi Luo, who left her job in China and started the journey with me without hesitation. This journey started right away after our marriage, and we started v vi our new married life in Singapore from nothing. My Ph.D. career is more than an academic pursuit but is more like an adventure. With the accompany by her, it will become one of the most valuable memories in my life. I overcame obstacles with her accompany, encouragement, support and love. More importantly, we share laughs and tears all the time. No matter good or bad, we are always together. She trusts me and makes me responsible and reliable. Words cannot express my gratitude and love. Being with her makes me the luckiest man in the world. Ever thine, ever mine, ever ours.

show abstract