多特征融合的抑郁倾向识别方法

doi:10.11772/j.issn.1001-9081.2018051180

计算机应用 ›› 2019, Vol. 39 ›› Issue (1): 168-175.DOI: 10.11772/j.issn.1001-9081.2018051180

多特征融合的抑郁倾向识别方法

周莹^1,2,3, 王红^1,2,3, 任衍具⁴, 胡晓红^1,2,3

1. 山东师范大学信息科学与工程学院, 济南 250358;
2. 山东省分布式计算机软件新技术重点实验室(山东师范大学), 济南 250014;
3. 山东师范大学生命科学研究院, 济南 250358;
4. 山东师范大学心理学院, 济南 250358

收稿日期:2018-06-08 修回日期:2018-07-24 出版日期:2019-01-10 发布日期:2019-01-21
通讯作者: 王红
作者简介:周莹(1993-),女,山东潍坊人,硕士研究生,CCF会员,主要研究方向:眼动追踪、机器学习、数据挖掘;王红(1966-),女,天津人,教授,博士,CCF高级会员,主要研究方向:移动社会软件、复杂网络、工作流;任衍具(1977-),男,山东济宁人,副教授,博士,主要研究方向:视知觉、视觉注意、工作记忆及其应用;胡晓红(1993-),女,山东枣庄人,硕士研究生,CCF会员,主要研究方向:机器学习、数据挖掘、眼动追踪、在线广告。
基金资助:
国家自然科学基金资助项目（61672329，61373149，61472233，61572300，81273704）；山东省科技计划项目（2014GGX101026）；山东省教育科学规划项目（ZK1437B010）；山东省泰山学者基金资助项目（TSHW201502038，20110819）；山东省精品课程项目（2012BK294，2013BK399，2013BK402）；山东师范大学研究生科研创新基金资助项目（SCX201747）。

Identification method of depressive tendency with multiple feature fusion

ZHOU Ying^1,2,3, WANG Hong^1,2,3, REN Yanju⁴, HU Xiaohong^1,2,3

1. School of Information Science and Engineering, Shandong Normal University, Jinan Shandong 250358, China;
2. Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology(Shandong Normal University), Jinan Shandong 250014, China;
3. Institute of Life Sciences, Shandong Normal University, Jinan Shandong 250358, China;
4. School of Psychology, Shandong Normal University, Jinan Shandong 250358, China

Received:2018-06-08 Revised:2018-07-24 Online:2019-01-10 Published:2019-01-21
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61672329, 61373149, 61472233, 61572300, 81273704), the Shandong Province Science and Technology Program (2014GGX101026), the Shandong Province Education Science Planning Program (ZK1437B010), the Taishan Scholar Fund Project of Shandong Province (TSHW201502038, 20110819), the Shandong Province Excellent Course Program (2012BK294, 2013BK399, 2013BK402), the Graduate Scientific Research Innovation Fund of Shandong Normal University (SCX201747).

摘要/Abstract

摘要： 近些年，抑郁倾向趋于年轻化和常态化，虽然相关研究已取得一定成果，但仍缺乏更为客观、准确的抑郁倾向识别方法，也缺乏从不同角度研究抑郁倾向，因此，提出将心理健康自查表和眼动追踪结合作为识别抑郁倾向的方法，并且创新地从多角度对抑郁倾向进行研究，即将眼动特征、记忆力特征、认知风格特征以及网络行为特征多种类型特征融合。为了处理复杂的特征关系，提出扫描过程来处理复杂的特征关系，并将扫描过程与堆叠法结合提出抑郁倾向识别模型——扫描堆叠模型。为了全面客观评价扫描堆叠模型的性能，对扫描过程和堆叠法的独立贡献进行了实验。实验结果显示扫描过程独立贡献为0.03，堆叠法独立贡献为0.02，并且扫描堆叠模型与多种模型从参数R平方、均方误差、平均绝对误差进行比较，结果为扫描堆叠模型的预测效果较好。

关键词: 眼动追踪, 抑郁倾向, 多特征融合, 扫描堆叠模型

Abstract: In recent years, the tendency of depression tends to occur at a younger age and affects more people. Although research on the topic has achieved some results, it still lacks a more objective and accurate method for identifying depressive tendencies, and research on depressive tendencies from multiple perspectives is lacking. Therefore, the combination of mental health self-check table and eye-tracking was proposed as a method for identifying depressive tendencies and was studied from multiple perspectives. The innovative features of eye movement, memory, cognitive style, and network behaviors were incorporated. In order to address complex feature relationship and extract more useful information, a scanning process with combining a stacking method was proposed to form a proposed recognition model for depressive tendencies called scanning stacking model. To comprehensively and objectively evaluate the performance of scanning and stacking model, the independent contributions of both scanning process and stacking method were evaluated in the experiment. The experimental results show that the independent contribution of scanning process is 0.03, and the independent contribution of stacking method is 0.02. In addition, the scanning stacking model was compared with several models from parameter R-squared, Mean Square Error (MSE) and average absolute error, and the results show that the scanning stacking model has better prediction effect.

Key words: eye-tracking, depressive tendency, multiple feature fusion, scanning stacking model

中图分类号:

TP181

周莹, 王红, 任衍具, 胡晓红. 多特征融合的抑郁倾向识别方法[J]. 计算机应用, 2019, 39(1): 168-175.

ZHOU Ying, WANG Hong, REN Yanju, HU Xiaohong. Identification method of depressive tendency with multiple feature fusion[J]. Journal of Computer Applications, 2019, 39(1): 168-175.

参考文献

[1] COOHEY C, EASTON S D. Distal stressors and depression among homeless men[J]. Health & Social Work, 2016, 41(2):111.
[2] KATON W, VON KORFF M, LIN E, et al. Collaborative management to achieve treatment guidelines:impact on depression in primary care[J]. The Journal of the American Medical Association, 1995, 273(13):1026-1031.
[3] ZUNG W W. A self-rating depression scale[J]. Archives of General Psychiatry, 1965, 12(12):63.
[4] JOORMANN J, GOTLIB I H. Selective attention to emotional faces following recovery from depression[J]. Journal of Abnormal Psychology, 2007, 116(1):80-85.
[5] HELLER W, ETIENNE M A, MILLER G A. Patterns of perceptual asymmetry in depression and anxiety:implications for neuropsychological models of emotion and psychopathology[J]. Journal of Abnormal Psychology, 1995, 104(2):327.
[6] FRITZSCHE A, DAHME B, GOTLIB I H, et al. Specificity of cognitive biases in patients with current depression and remitted depression and in patients with asthma[J]. Psychological Medicine, 2010, 40(5):815-826.
[7] 任力杰,陆兵勋,吴明祥,等.抑郁症患者工作记忆损害与磁共振扩散张量成像部分各向异性值相关性的研究[J].中华行为医学与脑科学杂志,2010,19(4):325-327.(REN L J, LU B X, WU M X, et al. Correlation between working memory impairment and partial anisotropy of magnetic resonance diffusion tensor imaging in patients with depression[J]. Chinese Journal of Behavioral Medicine and Brain Science, 2010, 19(4):325-327.)
[8] SAKI N, DEHGHANI FARD A, KAVIANI S, et al. Beta thalasemia:epidemiology, diagnostic and treatment approach in Iran[J]. Genetics in Millennium, 2012, 20(8):26-39.
[9] MAJOR B, MUELLER P, HILDEBRANDT K. Attributions, expectations, and coping with abortion[J]. Journal of Personality & Social Psychology, 1985, 48(3):585.
[10] EYSENCK H J. Cognitive styles:essence and origins[J]. Personality & Individual Differences, 1982, 3(1):103-103.
[11] BRUNSWIK E. Perception and representative design of psychological experiments[J]. Philosophical Quarterly, 1958, 8(33):42-61.
[12] LI L, LI A, HAO B, et al. Predicting active users' personality based on micro-blogging behaviors[J]. PLoS One, 2013, 9(1):84-97.
[13] 胡志海.大学生互联网使用行为影响因素分析[J].中国公共卫生,2008,24(3):294-295.(HU Z H. An analysis of the influence factors of college students' Internet use behavior[J]. Chinese Journal of Public Health, 2008, 24(3):294-295.)
[14] MORENO M A, JELENCHICK L A, EGAN K G, et al. Feeling bad on Facebook:depression disclosures by college students on a social networking site[J]. Depression & Anxiety, 2011, 28(6):447-455.
[15] KATIKALAPUDI R, CHELLAPPAN S, MONTGOMERY F, et al. Associating Internet usage with depressive behavior among college students[J]. IEEE Technology & Society Magazine, 2012, 31(4):73-80.
[16] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436.
[17] PITTS W. A logical calculus of the ideas immanent in nervous activity[J]. Bulletin of Mathematical Biology, 1990, 52(1):99-115.
[18] WEI X S, ZHOU Z H. An empirical study on image bag generators for multi-instance learning[J]. Machine Learning, 2016, 105(2):1-44.
[19] GUO G, WANG H, BELL D, et al. KNN model-based approach in classification[C]//Proceedings of the 2003 OTM Confederated International Conferences "On the Move to Meaningful Internet Systems". Berlin:Springer, 2003:986-996.
[20] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[21] BATES J M, GRANGER C W J. The combination of forecasts[J]. Journal of the Operational Research Society, 1969, 20(4):451-468.
[22] WOLPERT D H. Stacked generalization[J]. Neural Networks, 1992, 5(2):241-259.
[23] BREIMAN L. Bagging predictors[J]. Machine Learning, 1996, 24(2):123-140.
[24] WEST D, DELLANA S, QIAN J. Neural network ensemble strategies for financial decision applications[J]. Computers & Operations Research, 2005, 32(10):2543-2559.
[25] BLAND J M, ALTMAN D G. Cronbach's Alpha[J]. British Medical Journal, 1997, 314(7080):572.
[26] 龚耀先,谢光荣,江达威,等.修订韦氏记忆量表[C]//全国第四届心理学学术会议.北京:[出版者不详],1981:120-123.(GONG Y X, XIE G R, JIANG D W, et al. Revising Wechsler memory scale[C]//Proceedings of the Fourth National Conference on Psychology. Beijing:[s.n.], 1981:120-123.)
[27] WITKIN H A, MOORE C A, GOODENOUGH D R, et al. Field-dependent and field-independent cognitive styles and their educational implications[J]. ETS Research Bulletin, 1975, 1975(2):1-64.
[28] 李珩,朱靖波,姚天顺.基于Stacking算法的组合分类器及其应用于中文组块分析[J].计算机研究与发展,2005,42(5):844-848.(LI H, ZHU J B, YAO T S. A combined classifier based on stacking algorithm and its application in Chinese chunk block analysis[J]. Journal of Computer Research and Development, 2005, 42(5):844-848.)
[29] METZ C E. Basic principles of ROC analysis[J]. Seminars in Nuclear Medicine, 1978, 8(4):283.

多特征融合的抑郁倾向识别方法

Identification method of depressive tendency with multiple feature fusion

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

[1]	郭可心, 张宇翔. 基于多层次空间注意力的图文评论情感分析方法[J]. 计算机应用, 2021, 41(10): 2835-2841.
[2]	杨博, 蔺素珍, 禄晓飞, 李大威, 秦品乐, 左健宏. 基于多特征融合与分层数据关联的空中红外多目标跟踪方法[J]. 计算机应用, 2020, 40(10): 3075-3080.
[3]	胡晓红, 王红, 任衍具, 周莹. 多重因素下基于多模态特征的网页广告效果[J]. 计算机应用, 2018, 38(4): 987-994.
[4]	杨硕, 张波, 张志杰. 多特征融合的车牌定位算法[J]. 计算机应用, 2016, 36(6): 1730-1734.
[5]	王海玲王建印桂生乔付周波. 多特征融合的网格模型简化方法[J]. 计算机应用, 2013, 33(11): 3167-3171.
[6]	赵谦周勇曾召华侯媛彬刘树林. 基于多准则特征融合的自适应跟踪算法[J]. 计算机应用, 2013, 33(09): 2584-2587.
[7]	李睿刘昌旭年福忠. 基于自适应背景的多特征融合目标跟踪[J]. 计算机应用, 2013, 33(03): 651-655.
[8]	林建华刘党辉邵显奎. 多特征融合的Camshift算法及其进一步改进[J]. 计算机应用, 2012, 32(10): 2814-2816.
[9]	曾伟朱桂斌陈杰唐丁丁. 多特征融合的鲁棒粒子滤波跟踪算法[J]. 计算机应用, 2010, 30(3): 643-645.
[10]	陈丽陈静. 基于支持向量机和k-近邻分类器的多特征融合方法[J]. 计算机应用, 2009, 29(3): 833-835.
[11]	张恒吴晓娟董文会. 基于模糊融合的驾驶员眼睛状态识别[J]. 计算机应用, 2007, 27(2): 349-350.