Retracted Article
Research on artificial intelligence learning system based on psychological knowledge to adjust anxiety and depression
Bibliographic Data
| ID | 21452166 |
|---|---|
| Authors | Xiaocong Li (0000-0001-9908-0888, Business School of Hohai University, Nanjing, People’s Republic of China), Pengfei Zhou (0000-0003-1053-9029, Chongqing Normal University, corresponding author), Jiyu Wu (Lanzhou University), A Shanthini (SRM University), Thanjai Vadivel (0000-0002-8754-1947, Department of Computer Science and Engineering, Veltech University, Chennai, India) |
| Year | 2023 |
| Volume | 42 |
| Issue | 11 |
| Pages | i-xiii |
| Publication date | 2023-08-18 |
| Peer Reviewed | Yes |
| Open Access | No |
| Type | ARTICLE |
| Venue | Behaviour and Information Technology (JOURNAL) |
| Journal identifiers | ISSN: 0144-929X • E-ISSN: 1362-3001 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/0144929x.2020.1846077 |
| OpenAlex | W3112018255 |
| Language | EN |
| References cited | 2 |
As a countermeasure to an increasing occurrence of mental illness worldwide, monitoring mental health has received significant attention. The application of artificial intelligence to mental health has immense potential to personalise treatment selection, monitoring, reoccurrence prediction, diagnosis, and prevention of disorders of mental well-being before they are symptomatic at clinical levels and even treating them. Therefore, in this paper, a Deep learning-based integrated psychological activity monitoring system (DLIPAMS) has been proposed to predict the anxiety and depression of humans. For a prediction of mental illness, the nature of machine learning algorithms and artificial intelligence can be fully exploited. When implemented in real-time, these systems can support society by serving as a monitoring tool for individuals with immoral behaviour. The data has been pre-processed using the correlation-based filtering approach, and the essential features have been selected. The responses to the questionnaire derived from the target group were first exposed to deep learning strategies. By calculating the dice coefficient ratio, the labels obtained as a result of the classification, and it has been validated. These cluster labels were used to create classifications to predict an individual's mental health. The target groups were populations from various groups such as high school graduates, university students, and job professionals. The work analyzes how the above deep learning methods are adapted to the target groups and suggests guidelines for future practices
Anxiety · Countermeasure · Deep learning · Depression (economics) · Machine learning · Mental health · Mental illness · Psychiatry · Applied Psychology · Artificial Intelligence · Clinical Psychology · Computer Science · Digital Mental Health Interventions · Engineering · Mental Health Research Topics · Mental Health via Writing · Psychology
| Citation velocity | historical |
|---|---|
| Highly cited | No |