A Mental Workload Evaluation Model Based on Improved Multibranch LSTM Network with Attention Mechanism
People’s study, life, and work pressures have increased dramatically in recent years, as the pace of life has accelerated. Long-term high mental stress causes physiological secretion dysfunction and decreased immunity, resulting in a variety of diseases and even the risk of karoshi. Mental workload...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Advances in Multimedia |
| Online Access: | http://dx.doi.org/10.1155/2022/9601946 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850227399694745600 |
|---|---|
| author | Hongning Zhang |
| author_facet | Hongning Zhang |
| author_sort | Hongning Zhang |
| collection | DOAJ |
| description | People’s study, life, and work pressures have increased dramatically in recent years, as the pace of life has accelerated. Long-term high mental stress causes physiological secretion dysfunction and decreased immunity, resulting in a variety of diseases and even the risk of karoshi. Mental workload is another important factor that contributes to mental illness. Accurate assessment of mental workload is a method of effectively coping with physical and mental illness. Traditional physiological indicator measurement is inaccurate because changes caused by physiological indicators may not be solely due to psychological factors. As a result, based on the long short-term memory network, this paper proposes a mental workload evaluation model of multibranch LSTM with attention mechanism (LSTM). This model introduces an attention mechanism based on the classic LSTM network, which can screen the features differently, not only improving the utilization of effective information but also reducing calculation parameters and simplifying the model. This study employs a multibranch LSTM to improve the network’s generalization performance and stability. The basic idea behind multibranch LSTM is to train the branch LSTM network model separately using a variety of data, resulting in a branch LSTM network with a specific structure for the input EEG data. Finally, a total prediction result is obtained by combining the prediction outputs of multiple branch LSTM networks, which is used as the final mental workload evaluation result. The experimental results show that the model used in this paper has higher accuracy and more stable evaluation results in assessing psychological load. This study has a certain amount of reference value. |
| format | Article |
| id | doaj-art-13d08d05a9bb47a69e168fb0cc4ff595 |
| institution | OA Journals |
| issn | 1687-5699 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Multimedia |
| spelling | doaj-art-13d08d05a9bb47a69e168fb0cc4ff5952025-08-20T02:04:51ZengWileyAdvances in Multimedia1687-56992022-01-01202210.1155/2022/9601946A Mental Workload Evaluation Model Based on Improved Multibranch LSTM Network with Attention MechanismHongning Zhang0School of EducationPeople’s study, life, and work pressures have increased dramatically in recent years, as the pace of life has accelerated. Long-term high mental stress causes physiological secretion dysfunction and decreased immunity, resulting in a variety of diseases and even the risk of karoshi. Mental workload is another important factor that contributes to mental illness. Accurate assessment of mental workload is a method of effectively coping with physical and mental illness. Traditional physiological indicator measurement is inaccurate because changes caused by physiological indicators may not be solely due to psychological factors. As a result, based on the long short-term memory network, this paper proposes a mental workload evaluation model of multibranch LSTM with attention mechanism (LSTM). This model introduces an attention mechanism based on the classic LSTM network, which can screen the features differently, not only improving the utilization of effective information but also reducing calculation parameters and simplifying the model. This study employs a multibranch LSTM to improve the network’s generalization performance and stability. The basic idea behind multibranch LSTM is to train the branch LSTM network model separately using a variety of data, resulting in a branch LSTM network with a specific structure for the input EEG data. Finally, a total prediction result is obtained by combining the prediction outputs of multiple branch LSTM networks, which is used as the final mental workload evaluation result. The experimental results show that the model used in this paper has higher accuracy and more stable evaluation results in assessing psychological load. This study has a certain amount of reference value.http://dx.doi.org/10.1155/2022/9601946 |
| spellingShingle | Hongning Zhang A Mental Workload Evaluation Model Based on Improved Multibranch LSTM Network with Attention Mechanism Advances in Multimedia |
| title | A Mental Workload Evaluation Model Based on Improved Multibranch LSTM Network with Attention Mechanism |
| title_full | A Mental Workload Evaluation Model Based on Improved Multibranch LSTM Network with Attention Mechanism |
| title_fullStr | A Mental Workload Evaluation Model Based on Improved Multibranch LSTM Network with Attention Mechanism |
| title_full_unstemmed | A Mental Workload Evaluation Model Based on Improved Multibranch LSTM Network with Attention Mechanism |
| title_short | A Mental Workload Evaluation Model Based on Improved Multibranch LSTM Network with Attention Mechanism |
| title_sort | mental workload evaluation model based on improved multibranch lstm network with attention mechanism |
| url | http://dx.doi.org/10.1155/2022/9601946 |
| work_keys_str_mv | AT hongningzhang amentalworkloadevaluationmodelbasedonimprovedmultibranchlstmnetworkwithattentionmechanism AT hongningzhang mentalworkloadevaluationmodelbasedonimprovedmultibranchlstmnetworkwithattentionmechanism |