Epilepsy is a common neurological disorder with sudden and recurrent seizures. Early prediction of seizures and effective intervention can significantly reduce the harm suffered by patients. In this paper, a method based on nonlinear features of EEG signal and gradient boosting decision tree (GBDT) is proposed for early prediction of epilepsy seizures. First, the EEG signals were divided into two categories: those that had seizures onset over a period of time (represented by InT) and those that did not. Second, the noise in the EEG was removed using complementary ensemble empirical mode decomposition (CEEMD) and wavelet threshold denoising. Third, the nonlinear features of the two categories of EEG were extracted, including approximate entropy, sample entropy, permutation entropy, spectral entropy and wavelet entropy. Fourth, a GBDT classifier with random forest as the initial result was designed to distinguish the two categories of EEG. Fifth, a two-step “k of n” method was used to reduce the number of false alarms. The proposed method was evaluated on 13 patients’ EEG data from the CHB-MIT Scalp EEG Database. Based on ten-fold cross validation, the average accuracy was 91.76% when the InT was taken at 30 min, and 38 out of 39 seizures were successfully predicted. When the InT was taken for 40 min, the average accuracy was 92.50% and all 42 seizures selected were successfully predicted. The results indicate the effectiveness of the proposed method for predicting epilepsy seizures.
The dislocated development of population, land, and economy will disturb the urban system, cause ecological risk problems, and ultimately affect regional habitat and quality development. Based on social statistics and nighttime lighting data from 2000 to 2018, we used mathematical statistics and spatial analysis methods to analyze the change process of urbanization’s coupling coordination degree and ecological risk response pattern in the Yangtze River Delta. Results show that: ① From 2000 to 2018, the coupling coordination degree of urbanization in the Yangtze River Delta increased, with high values in Suzhou-Wuxi-Changzhou, Shanghai, Nanjing and Hangzhou regions. ② The ecological risk in the Yangtze River Delta weakened, and the vulnerability and disturbance of landscape components together constitute the spatial differentiation pattern of regional ecological risk, which presented homogeneous aggregation and heterogeneous isolation. ③ The overall ecological stress of urbanization in the Yangtze River Delta decreased. ④ The population aggregation degree, socio-economic development level and built-up area expansion trend contributed to the spatiotemporal differentiation of urbanization’s ecological risks through the synergistic effects of factor concentration and diffusion, population quality cultivation and improvement, technological progress and dispersion, industrial structure adjustment and upgrading. This study can provide a reference for regional urbanization to deal with ecological risks reasonably and achieve high-quality development.
This paper analyzes the spatiotemporal patterns, water yield and water conservation function of different land use types in Poyang Lake Region, China, during 1990–2020 by using national land use, meteorological, soil, DEM data, etc., based on the InVEST model. The results showed that: (1) Cultivated land, forestland and water area were the main land use types in Poyang Lake Region during 1990–2020. Construction land and forestland were increasing, while grassland, unused land, cultivated land and water area were decreasing. (2) The increasing construction land was mainly derived from cultivated land. Mutual transfer existed between cultivated land and forestland, as well as between cultivated land and water area. (3) With a downward–upward–downward fluctuating trend, the average annual water yield of Poyang Lake Region was 16.17 × 109 m³, and the water conservation was 53.11 × 108 m³. The average water conservation capacity was 270.98 mm. The vegetation cover area with high water conservation value was mainly concentrated in the northwest of Jiujiang City and the northeast of Poyang County. (4) The average water conservation of different land use types during 1990–2020 was ranked as follows: water area > cultivated land > forestland > construction land > grassland > unused land. The water conservation capacity was ranked as follows: water area > grassland > forestland > cultivated land > construction land > unused land.
In view of the fact that current attention-recognition studies are mostly single-level-based, this paper proposes a multi-level attention-recognition method based on feature selection. Four experimental scenarios are designed to induce high, medium, low, and non-externally directed attention states. A total of 10 features are extracted from 10 electroencephalogram (EEG) channels, respectively, including time-domain measurements, sample entropy, and frequency band energy ratios. Based on all extracted features, an 88.7% recognition accuracy is achieved when classifying the four different attention states using the support vector machine (SVM) classifier. Afterwards, the sequence-forward-selection method is employed to select the optimal feature subset with high discriminating power from the original feature set. Experimental results show that the classification accuracy can be improved to 94.1% using the filtered feature subsets. In addition, the average recognition accuracy based on single subject classification is improved from 90.03% to 92.00%. The promising results indicate the effectiveness of feature selection in improving the performance of multi-level attention-recognition tasks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.