Development of Classification Features of Mental Disorder Characteristics Using The Fuzzy Logic Mamdani Method

被引:0
|
作者
Silvana, Meza [1 ]
Akbar, Ricky [1 ]
Derisma [2 ]
Audina, Mia [1 ]
Firdaus [3 ]
机构
[1] Univ Andalas, Informat Syst, Padang, Indonesia
[2] Univ Andalas, Comp Syst, Padang, Indonesia
[3] Politeknik Negeri Padang, Elect Engn, Padang, Indonesia
关键词
mental disorders; classify; fuzzy logic; data; symptom;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Mental disorders are related to self-injurious behavior problems of mind, such as the tendency to commit suicide. This research has built a system to classify the disorder. It explains that a system is used to help the people recognize mental illness as a diagnosis detection. Diagnosis can be done in the form of automation system using data mining with Fuzzy Logic method. This system can make decision to classify the mental illnesses based on symptoms. The first stage of the research was collecting and preprocessing the data by type. There are six types of psychiatric disorders that are determined, namely Schizophrenia Paranoid, Phobia, Depression, Anxiety, Obsessive Compulsive Disorder (OCD), and Anti-Social. The source of the data were questionnaires that consisted of the list of symptoms and types of disorders that were distributed to 16 selected respondents, including psychiatric specialists, psychology lecturers, general practitioners, psychiatric hospital nurses, and psychology students. The next stage was building the fuzzy process to determine ten inputs in the form of symptoms. Outputs system were six types of the disease. The fuzzy inference system used Mamdani model and obtained 65 rules in determining the classification. The result of system test is done for both training and testing data and accuracy level of 91.67% for training data and 81.94% for testing data.
引用
收藏
页码:410 / 414
页数:5
相关论文
共 50 条
  • [21] INCREASING CLASSIFICATION QUALITY BY USING FUZZY LOGIC
    Droj, Gabriela
    JOURNAL OF APPLIED ENGINEERING SCIENCES, 2011, 1 (04): : 61 - 72
  • [22] Classification using RBFNs based on fuzzy logic
    Gao, CM
    Shao, MZ
    Gao, SH
    IGARSS 2000: IEEE 2000 INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOL I - VI, PROCEEDINGS, 2000, : 2149 - 2151
  • [23] Classification of power disturbances using fuzzy logic
    Bizjak, Boris
    Planinsic, Peter
    2006 12TH INTERNATIONAL POWER ELECTRONICS AND MOTION CONTROL CONFERENCE, VOLS 1-4, 2006, : 2001 - +
  • [24] Classification using fuzzy geometric features
    Krivsha, VV
    Butenkov, SA
    2002 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE SYSTEMS, PROCEEDINGS, 2002, : 89 - 91
  • [25] A fuzzy logic method for modulation classification in nonideal environments
    Wei, W
    Mendel, JM
    IEEE TRANSACTIONS ON FUZZY SYSTEMS, 1999, 7 (03) : 333 - 344
  • [26] Classification Method for Objects with Fuzzy Values of Features
    V. G. Sinuk
    S. V. Kulabukhov
    Scientific and Technical Information Processing, 2022, 49 : 481 - 485
  • [27] Classification Method for Objects with Fuzzy Values of Features
    Sinuk, V. G.
    Kulabukhov, S. V.
    SCIENTIFIC AND TECHNICAL INFORMATION PROCESSING, 2022, 49 (06) : 481 - 485
  • [28] Calculating G-code for CNC machine using the Mamdani fuzzy logic inference system
    Kalandyk, Dawid
    Kwiatkowski, Bogdan
    Mazur, Damian
    ARCHIVES OF CONTROL SCIENCES, 2024, 34 (03): : 501 - 511
  • [29] A knowledge-based system for breast cancer classification using fuzzy logic method
    Nilashi, Mehrbakhsh
    Ibrahim, Othman
    Ahmadi, Hossein
    Shahmoradi, Leila
    TELEMATICS AND INFORMATICS, 2017, 34 (04) : 133 - 144
  • [30] Intelligent Classification using Adaptive Fuzzy Logic Systems
    Kodogiannis, Vassilis S.
    Petrounias, Ilias
    Lygouras, John N.
    2008 4TH INTERNATIONAL IEEE CONFERENCE INTELLIGENT SYSTEMS, VOLS 1 AND 2, 2008, : 378 - +