http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Minimal Redundancy Maximal Relevance Criterion-based Multi-biometric Feature Selection
Yong Jian Chin,Kian Ming Lim,Siew Chin Chong,Chin Poo Lee 한국산학기술학회 2013 SmartCR Vol.3 No.2
Multimodal biometrics are always adopted to improve the recognition performance of single modality biometric systems. Besides introducing more discriminating power to the biometric system, integrating multiple modalities also leads to the curse of dimensionality problem. In this paper, we engage the minimal redundancy maximal relevance criterion to reduce the dimensionality of the feature vector. The minimal redundancy maximal relevance criterion is a feature selection criterion that aims to retain the most relevant elements while discarding the other redundant elements. Our experiments show that, with only 15% of the original feature length, minimal redundancy maximal relevance criterion-based features are able to perform similarly well or even better than the baseline results.
Serene En Hui Tung,Yi Zhang Ch’ng,Thaneswary V Karnan,Pei Nee Chong,Jamil Osman Zubaidah,Yit Siew Chin 한국영양학회 2020 Nutrition Research and Practice Vol.14 No.5
BACKGROUND/OBJECTIVES: A cross-sectional study was undertaken to evaluate fluid intake and hydration status in association with cognitive function among 230 adolescents (10–14 years of age) in Petaling Perdana, Selangor, Malaysia. SUBJECTS/METHODS: Urine color was used to measure hydration status, while fluid intake was assessed using the 15-item beverage intake questionnaire. Cognitive function was assessed using the Wechsler Intelligence Scale for Children, Fourth Edition. RESULTS: More than half of the adolescents were mildly or moderately dehydrated (59.6%) and only one-third (33.0%) were well hydrated. Among the daily fluid types, intakes of soft drinks (r = −0.180; P = 0.006), sweetened tea (r = −0.184; P = 0.005) and total sugar-sweetened beverages (SSBs) (r = −0.199; P = 0.002) were negatively correlated with cognitive function. In terms of hydration status, cognitive function score was significantly higher (F-ratio = 4.102; P = 0.018) among hydrated adolescents (100.38 ± 12.01) than in dehydrated (92.00 ± 13.63) counterparts. Hierarchical multiple linear regression analysis, after adjusting for socio-demographic factors, showed that soft drinks (β = −0.009; P < 0.05) and sweetened tea (β = −0.019; P < 0.05) negatively predicted cognitive function (ΔR2 = 0.044). When further control for sources of fluid, hydration status (β = −2.839; P < 0.05) was shown to negatively predict cognitive function (ΔR2 = 0.021). The above variables contributed 20.1% of the variance in cognitive function. CONCLUSIONS: The results highlight the links between fluid intake (soft drinks, sweetened tea, total SSBs) and hydration status with cognitive function in adolescents. Interventions aimed at decreasing the consumption of SSBs and increasing hydration status through healthy fluid choices, such as water, could improve cognitive performance in adolescents.