人工智能技术价值激励领域指标在学员适应不良预测中的应用
- 作者: Yatmanov A.N.1,2, Apchel V.Y.1,3, Ovchinnikov D.V.1, Yusupov V.V.1, Ovchinnikov B.V.1, Starenchenko Y.L.1, Babin Y.М.1, Korzunin A.V.1, Tsvetkov D.S.1
-
隶属关系:
- Kirov Military Medical Academy
- Naval Academy named after Admiral of the Fleet of the Soviet Union N.G. Kuznetsov
- Herzen State Pedagogical University of Russia
- 期: 卷 26, 编号 4 (2024)
- 页面: 587-596
- 栏目: Original Study Article
- URL: https://bakhtiniada.ru/1682-7392/article/view/285207
- DOI: https://doi.org/10.17816/brmma635764
- ID: 285207
如何引用文章
详细
一项回顾性队列研究。从2013年到2021年,对库兹涅佐夫海军学院军事教学和研究中心的734名学员进行了调查,其中48人被诊断为适应不良。使用神经网络对适应不良的预测进行数学模拟。进行了8个周期神经网络训练和7个周期的神经网络模型验证。论证利用人工智能技术价值激励领域指标预测学员适应不良的可能性。随着事实材料的增加,使用神经网络预测学员适应不良的模型的灵敏度增加:30.MLP 16-7-2;28.MLP 16-13-2;30.MLP 16-22-2 ;29.MLP 16-31-2;42.MLP 16-39-2;19.MLP 16-45-2;16.MLP 16-48-2;30.MLP 16-30-2 ,从0.43到1个标准单位(y = 0.017x2 - 0.0647x + 0.4898,R²= 0.8264);特异性 — 从0.96到1个标准单位(y = -0.002x2 + 0.0211x + 0.9462,R²= 0.8923);预测能力从91.8%提高到99.45%(y = -0.1477x2 + 2.3309x + 90.238,R²=0.9368)。在新样本上验证模型时,灵敏度平均为0.45个标准单位,呈上升趋势(y = 0.0207x2 - 0.1214x + 0.5271 , R ²= 0.6945),特异性 — 0.97个标准单位(y= -0.0048x2 + 0.0388x + 0.9086,R²= 0.772),预测能力 — 92.6%(y = -0.4962x2 + 3.5402x + 88.447,R²= 0.6598)。由此可见,利用神经网络预测学员适应不良的模型,可以识别出适应不良的学员,准确率在32%到 72%之间,而在没有适应不良的学员中,错误预测的比例不超过6%。该模型的预测能力指标在内容上接近于以65-70%的标准指标预测专业适应性的绝对准确率。研究中验证模型的预测能力从89.7%到 96.4%,这证实神经网络用于预测适应不良的高效率。被调查的价值激励领域指标与预测学员适应不良的神经网络的相结合,创建了一个高效的人工智能系统。为了最优化的选拔和辅导,将这种方法应用于军事大学军人的医疗和心理辅导措施中是可以接受的。
作者简介
Alexey N. Yatmanov
Kirov Military Medical Academy; Naval Academy named after Admiral of the Fleet of the Soviet Union N.G. Kuznetsov
编辑信件的主要联系方式.
Email: vmeda-nio@mil.ru
ORCID iD: 0000-0003-0043-3255
SPIN 代码: 4151-0625
MD, Cand. Sci. (Medicine)
俄罗斯联邦, Saint-Petersburg; Saint-PetersburgVasiliy Ya. Apchel
Kirov Military Medical Academy; Herzen State Pedagogical University of Russia
Email: vmeda-nio@mil.ru
ORCID iD: 0000-0001-7658-4856
SPIN 代码: 4978-0785
MD, Dr. Sci. (Medicine), professor
俄罗斯联邦, Saint-Petersburg; Saint-PetersburgDmitrii V. Ovchinnikov
Kirov Military Medical Academy
Email: vmeda-nio@mil.ru
ORCID iD: 0000-0001-8408-5301
SPIN 代码: 5437-3457
MD, Cand. Sci. (Med.), associate professor
俄罗斯联邦, Saint PetersburgVladislav V. Yusupov
Kirov Military Medical Academy
Email: vmeda-nio@mil.ru
ORCID iD: 0000-0002-5236-8419
SPIN 代码: 9042-3320
MD, Dr. Sci. (Medicine), professor
俄罗斯联邦, Saint PetersburgBoris V. Ovchinnikov
Kirov Military Medical Academy
Email: vmeda-nio@mil.ru
ORCID iD: 0000-0002-7669-7049
SPIN 代码: 5086-8427
Yuri L. Starenchenko
Kirov Military Medical Academy
Email: vmeda-nio@mil.ru
ORCID iD: 0009-0003-2755-1419
SPIN 代码: 9590-3548
Cand. Sci. (History), associate professor
俄罗斯联邦, Saint PetersburgYuri М. Babin
Kirov Military Medical Academy
Email: vmeda-nio@mil.ru
ORCID iD: 0009-0005-1819-9729
SPIN 代码: 5993-0815
Andrey V. Korzunin
Kirov Military Medical Academy
Email: vmeda-nio@mil.ru
ORCID iD: 0009-0007-9267-9450
SPIN 代码: 1086-3283
MD, Cand. Sci. (Medicine)
俄罗斯联邦, Saint PetersburgDenis S. Tsvetkov
Kirov Military Medical Academy
Email: vmeda-nio@mil.ru
ORCID iD: 0000-0001-7213-804X
therapist
俄罗斯联邦, Saint Petersburg参考
- Mosyagin IG. Role and place of maritime medicine. Marine Medicine. 2023;9(3):7–12. EDN: FJMQXK doi: 10.22328/2413-5747-2023-9-3-7-12
- Kryukov EV, Ivchenko EV, Yusupov VV, et al. Relationship of professional success and development of cognitive mental processes and personal qualities of Vietnam naval specialists. Bulletin of the Russian Military Medical Academy. 2024;26(1):7–14. EDN: GYBLZE doi: 10.17816/brmma624879
- Andriychenko AM, Emushintsev PA. Application of objective diagnostic methods to assess professionally important qualities of divers. Marine Medicine. 2023;9(2):77–89. EDN: QPYTMV doi: 10.22328/2413-5747-2023-9-2-77-89
- Babin YuM, Yusupov VV, Blaginin AA, et al. Psychological and psychophysiological criteria for professional selection of aviation system operators. Military Medical Journal. 2024;345(8):43–50. EDN: EYPFFE
- Dorofeev II, Korzunin VA, Ovchinnikov BV, et al. Methodological aspects of allocation of categories of medical and psychological support of students. Clinical Psychology and Special Education. 2016;5(2):113–120. EDN: WGFEXT doi: 10.17759/cpse.2016050208
- Ovchinnikov BV, Dnov KV, Zaitsev AG, et al. Values and motivation in the professionalization of the serviceman. Bulletin of the Russian Military Medical Academy. 2017;(4):135–139. EDN: YLNRQY
- Kryukov EV, Ivchenko EV, Shamrey VK, et al. Modern approaches to the assessment of stress resistance in military personnel. Military Medical Journal. 2023;344(7):4–15. EDN: FNCQIP
- Ivchenko EV, Ovchinnikov DV Organization of scientific work as a guarantee of successful development of military medicine. In: 3rd Asian-Pacific Congress on Military Medicine. Congress Proceedings. 2016. P. 24–25. (In Russ.)
- Lipsky DL, Gura MS, Luchkin IV, et al. Application of machine learning in the medical and psychological support of military service services of foreign states. Living Psychology. 2023;10(4):15–24. EDN: PQSOJZ doi: 10.58551/24136522_2023_10_4_15
- Soshkin PA. distress tolerance and adaptive capabilities in naval specialists with signs of professional burnout. Marine Medicine. 2021;7(3): 62–70. EDN: RZUUGE doi: 10.22328/2413-5747-2021-7-3-62-70
- Lichko A.E. Psychopathy and character accentuations in adolescents. Leningrad: Medicine; 1983. 255 p. (In Russ.)
- Yusupov VV, Fishchenko DE, Yatmanov AN, et al. Machine learning in building cadet maladaptation forecasts. Medicо-Biological and Socio-Psychological Problems of Safety in Emergency Situations. 2023;(4):90–96. EDN: REWQVC doi: 10.25016/2541-7487-2023-0-4-90-96
- Baskin YuG, Svidzinskaya GB. Experience of using the semantic differential method in the educational process. Bulletin of the St. Petersburg University of the State Fire Service of the Ministry of Emergency Situations of Russia. 2021;(1):158–165. EDN: ZPNLEZ
- Borisov DN, Koluzov AV, Serezhkin IA. Opportunities for the development of artificial intelligence and big data in the field of health of servicemen In: State and prospects of development of modern science in the direction of “ASU, information and telecommunication systems”. 2020;3:177–183. EDN: XCNRHN
- Terletskiy AS, Terletskaya ES. Neural Networks and Artificial Intelligence: Foundations of Neural Networks in Python. Lipetsk; 2023. 76 p. (In Russ.) EDN: UGIPEE
- Apchel Vya, Bulka AP, Sysoev VN. Use of a mathematical model of a fuzzy neural network for professional psychological selection of personnel. Academic Journal. 2007;(5):136–143. (In Russ.) EDN: XWYOHB
- Zaitsev AG, Rezvantsev MV, Tegza VYu, et al. Mathematical model of forecast successfulness of N.G. Kuznetsov naval academy cadets’ professional military adaptation. Bulletin of the Russian Military Medical Academy. 2018;(1):160–163. EDN: YXCBUD
- Yatmanov AN. Psychological features of cadets with military professional maladjustment. Bulletin of the Russian Military Medical Academy. 2019;(2):92–96. (In Russ.) EDN: KFFMDW
补充文件
