The automatic seizure detection is significant for epilepsy diagnosis and it can alleviate the work intensity of inspecting prolonged electroencephalogram （EEG）. This paper presents and investigates a novel machine ...The automatic seizure detection is significant for epilepsy diagnosis and it can alleviate the work intensity of inspecting prolonged electroencephalogram （EEG）. This paper presents and investigates a novel machine learning approach utilizing gradient boosting to detect seizures from long-term EEG. We apply relative fluctuation index to extract features of long-term intracranial EEG data. A classifier trained with the gradient boosting algorithm is adopted to discriminate the seizure and non-seizure EEG signals. Smoothing and collar technique are finally used as post-processing in order to improve the detection accuracy further. The seizure detection method is assessed on Freiburg EEG datasets from 21 patients. The experimental results indicate that the proposed method yields an average sensitivity of 94. 60% with a false detection rate of 0. 18/h.展开更多
The Chinese government adopted six ecological restoration programs to improve its natural environments. Although these programs have proven successful in improving local environments, some studies have questioned thei...The Chinese government adopted six ecological restoration programs to improve its natural environments. Although these programs have proven successful in improving local environments, some studies have questioned their performance when regions suffer from drought. Whether we should consider the effects of drought on vegetation change in assessments of the benefits of ecological restoration programs is unclear. Therefore, taking the Grain for Green Program(GGP) region as a study area, we estimated vegetation growth in the region from 2000–2010 to clarify the trends in vegetation and their driving forces. Results showed that: 1) vegetation growth increased in the GGP region during 2000–2010, with 59.4% of the area showing an increase in the Normalized Difference Vegetation Index(NDVI). This confirmed the benefits of the ecological restoration program. 2) Drought can affect the vegetation change trend, but human activity plays a significant role in altering vegetation growth, and the slight downward trend in the NDVI was not consistent with the severity of the drought. Positive human activity led to increased NDVI in 89.13% of areas. Of these, 22.52% suffered drought, but positive human activity offset the damage in part. 3) Results of this research suggest that appropriate human activity can maximize the benefits of ecological restoration programs and minimize the effects of extreme weather. We therefore recommend incorporating eco-risk assessment and scientific management mechanisms in the design and management of ecosystem restoration programs.展开更多
基金Key Program of Natural Science Foundation of Shandong Province(No.ZR2013FZ002)The Program of Science and Technology of Suzhou(No.ZXY2013030)Independent Innovation Foundation of Shandong University(No.11170074611102)
文摘The automatic seizure detection is significant for epilepsy diagnosis and it can alleviate the work intensity of inspecting prolonged electroencephalogram （EEG）. This paper presents and investigates a novel machine learning approach utilizing gradient boosting to detect seizures from long-term EEG. We apply relative fluctuation index to extract features of long-term intracranial EEG data. A classifier trained with the gradient boosting algorithm is adopted to discriminate the seizure and non-seizure EEG signals. Smoothing and collar technique are finally used as post-processing in order to improve the detection accuracy further. The seizure detection method is assessed on Freiburg EEG datasets from 21 patients. The experimental results indicate that the proposed method yields an average sensitivity of 94. 60% with a false detection rate of 0. 18/h.
基金Under the auspices of the National Key R&D Program of China(No.2017YFC0504701)Science and Technology Service Network Initiative Project of Chinese Academy of Sciences(No.KFJ-STS-ZDTP-036)+1 种基金Fundamental Research Funds for the Central Universities(No.GK201703053)China Postdoctoral Science Foundation(No.2017M623114)
文摘The Chinese government adopted six ecological restoration programs to improve its natural environments. Although these programs have proven successful in improving local environments, some studies have questioned their performance when regions suffer from drought. Whether we should consider the effects of drought on vegetation change in assessments of the benefits of ecological restoration programs is unclear. Therefore, taking the Grain for Green Program(GGP) region as a study area, we estimated vegetation growth in the region from 2000–2010 to clarify the trends in vegetation and their driving forces. Results showed that: 1) vegetation growth increased in the GGP region during 2000–2010, with 59.4% of the area showing an increase in the Normalized Difference Vegetation Index(NDVI). This confirmed the benefits of the ecological restoration program. 2) Drought can affect the vegetation change trend, but human activity plays a significant role in altering vegetation growth, and the slight downward trend in the NDVI was not consistent with the severity of the drought. Positive human activity led to increased NDVI in 89.13% of areas. Of these, 22.52% suffered drought, but positive human activity offset the damage in part. 3) Results of this research suggest that appropriate human activity can maximize the benefits of ecological restoration programs and minimize the effects of extreme weather. We therefore recommend incorporating eco-risk assessment and scientific management mechanisms in the design and management of ecosystem restoration programs.
