上海中医药大学在校大学生不同情感状态脉图特征参数分析与识别
|
摘要
目的对上海中医药大学在校大学生不同情感状态下脉图特征参数进行分析与识别,以期为大学生情感状态的辨识提供客观的参考依据。方法选择上海中医药大学11名身心健康的大学生,以中医情志脉象理论为基础,通过素材诱导,激发受试者不同情感表达。采用ZBOX-Ⅰ型脉象数字化采集分析仪采集受试者平静、喜悦、恐惧、悲伤4种不同情感状态下的脉图共224人次,提取4组情感状态下脉图时域参数和多尺度熵参数,采用非参数检验统计4组脉图特征参数差异,随机森林分类器对情感状态进行分类识别。结果 4组脉图时域参数及多尺度熵参数差异有统计学意义(P<0.05);基于脉图时域参数对不同情感状态进行识别,识别率为70.52%,基于脉图时域和多尺度熵参数进行识别,识别率提高至74.52%。结论脉图特征参数可为情感状态的辨识提供客观参考依据,脉图时域参数结合多尺度熵参数可提高情感状态识别率。
Objective To analyze and identify the pulse characteristic parameters under different emotional status of students of Shanghai University of Traditional Chinese Medicine; To provide an objective reference for the identification of emotional status of college students. Methods Based on the theory of TCM emotions and meridians, setting eleven students of Shanghai University of Traditional Chinese Medicine as the research object, through the material(film) induction method, students' different emotion expressions were stimulated. The ZBOX-Ⅰ pulse digital acquisition analyzer was used to collect 224 person-times of the four different emotional status of calm, joy, fear and sadness of college students. The time domain parameters and multi-scale entropy parameters of the pulse patterns of the four groups of emotional status were extracted. The non-parametric test method was used to calculate the difference of the characteristic parameters of the four groups of pulse patterns. The random forest classifier was used to classify and recognize the emotional status. Results The time domain parameters and multi-scale entropy parameters of the four groups of pulse diagrams were statistically significantly different(P<0.05). The different time-domain parameters were used to identify the different emotional status, and the recognition rate was 70.52%. Based on pulse time-domain parameters and multi-scale entropy parameters, the recognition rate increased to 74.52%. Conclusion The pulse characteristic parameters can provide an objective reference for the identification of emotional status. Pulse time-domain parameters combined with multi-scale entropy parameters can improve the recognition rate of emotional status.
Objective To analyze and identify the pulse characteristic parameters under different emotional status of students of Shanghai University of Traditional Chinese Medicine; To provide an objective reference for the identification of emotional status of college students. Methods Based on the theory of TCM emotions and meridians, setting eleven students of Shanghai University of Traditional Chinese Medicine as the research object, through the material(film) induction method, students' different emotion expressions were stimulated. The ZBOX-Ⅰ pulse digital acquisition analyzer was used to collect 224 person-times of the four different emotional status of calm, joy, fear and sadness of college students. The time domain parameters and multi-scale entropy parameters of the pulse patterns of the four groups of emotional status were extracted. The non-parametric test method was used to calculate the difference of the characteristic parameters of the four groups of pulse patterns. The random forest classifier was used to classify and recognize the emotional status. Results The time domain parameters and multi-scale entropy parameters of the four groups of pulse diagrams were statistically significantly different(P<0.05). The different time-domain parameters were used to identify the different emotional status, and the recognition rate was 70.52%. Based on pulse time-domain parameters and multi-scale entropy parameters, the recognition rate increased to 74.52%. Conclusion The pulse characteristic parameters can provide an objective reference for the identification of emotional status. Pulse time-domain parameters combined with multi-scale entropy parameters can improve the recognition rate of emotional status.
引文
[1]葛臣,刘光远,龙正吉.情感识别中脉搏信号的特征提取与分析[J].西南师范大学学报(自然科学版),2010,35(3):243-246.
[2]何成.基于多生理信号的情绪识别方法研究[D].杭州:浙江大学,2016.
[3]邵慧江,杨蔚,潘纬榕,等.大学生不同情感状态的脉图分析[J].世界科学技术-中医药现代化,2017,19(7):1214-1218.
[4]唐秋萍,程灶火,袁爱华,等.SCL-90在中国的应用与分析[J].中国临床心理学杂志,1999,7(1):19-23.
[5]李娜,邹小娟,王忆勤.支气管哮喘与慢性胃炎患者寸口6部脉图的比较研究[J].世界科学技术-中医药现代化,2015,17(2):343-349.
[6]程悦蕾,朱惠蓉,杨琼,等.100例湿热蕴结型大肠癌患者治疗前后舌脉象参数特征分析[J].辽宁中医杂志,2015,42(2):230-235.
[7]郭睿,王忆勤,燕海霞,等.脉图的递归定量分析及对冠心病颈动脉血管硬化程度的评价[J].中华中医药杂志,2016,31(5),1695-1699.
[8]COSTA M,GOLDBERGER A L,PENG C K.Multiscale entropy analysis of complex physiologic time series[J].Physical Review Letters,2002,89(6):068102.
[9]COSTA M,GOLDBERGER A L,PENG C K.Multiscale entropy analysis of biological signals[J].Physical Review E,2005,71(2):021906.
[10]BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[11]寿小云.中医心理脉象的临床识别[J].北京中医药大学学报,1997,20(3):16-20.
[12]寿小云.中医脉象振动觉临床识别[J].北京中医药大学学报,1999,22(2):14-16.
[13]章道宁,王天芳.《黄帝内经》情志脉象浅析[J].安徽中医药大学学报,2015,34(3):4-6.
[14]张晶.古代情志相关医案中情志因子与脉象的典型相关分析[J].四川中医,2011,29(7):26-27.
[15]陈君臻,滕晶.郁闷不舒状态临床脉势分析[J].山东中医杂志,2017,36(10):898-899.
[2]何成.基于多生理信号的情绪识别方法研究[D].杭州:浙江大学,2016.
[3]邵慧江,杨蔚,潘纬榕,等.大学生不同情感状态的脉图分析[J].世界科学技术-中医药现代化,2017,19(7):1214-1218.
[4]唐秋萍,程灶火,袁爱华,等.SCL-90在中国的应用与分析[J].中国临床心理学杂志,1999,7(1):19-23.
[5]李娜,邹小娟,王忆勤.支气管哮喘与慢性胃炎患者寸口6部脉图的比较研究[J].世界科学技术-中医药现代化,2015,17(2):343-349.
[6]程悦蕾,朱惠蓉,杨琼,等.100例湿热蕴结型大肠癌患者治疗前后舌脉象参数特征分析[J].辽宁中医杂志,2015,42(2):230-235.
[7]郭睿,王忆勤,燕海霞,等.脉图的递归定量分析及对冠心病颈动脉血管硬化程度的评价[J].中华中医药杂志,2016,31(5),1695-1699.
[8]COSTA M,GOLDBERGER A L,PENG C K.Multiscale entropy analysis of complex physiologic time series[J].Physical Review Letters,2002,89(6):068102.
[9]COSTA M,GOLDBERGER A L,PENG C K.Multiscale entropy analysis of biological signals[J].Physical Review E,2005,71(2):021906.
[10]BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[11]寿小云.中医心理脉象的临床识别[J].北京中医药大学学报,1997,20(3):16-20.
[12]寿小云.中医脉象振动觉临床识别[J].北京中医药大学学报,1999,22(2):14-16.
[13]章道宁,王天芳.《黄帝内经》情志脉象浅析[J].安徽中医药大学学报,2015,34(3):4-6.
[14]张晶.古代情志相关医案中情志因子与脉象的典型相关分析[J].四川中医,2011,29(7):26-27.
[15]陈君臻,滕晶.郁闷不舒状态临床脉势分析[J].山东中医杂志,2017,36(10):898-899.