EEG-based mild depression recognition using convolutional neural network

Li, Xiaowei; La, Rong; Wang, Ying; Niu, Junhong; Zeng, Shuai; Sun, Shuting; Zhu, Jing

doi:10.1007/s11517-019-01959-2

Cited by 93 publications

(60 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The learning rate was 10 −3 , and the decay rates of the first and second moments were 0.9 and 0.999, respectively. The weight initialization method we used was Xavier (Glorot and Bengio, 2010), which has been shown to be effective in network training (Jiao et al, 2018). We also used early stopping to monitor the performance of the model over the validation sets.…”

Section: Trainingmentioning

confidence: 99%

A Deep Learning Approach for Mild Depression Recognition Based on Functional Connectivity Using Electroencephalography

Wang

et al. 2020

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

Section: Trainingmentioning

confidence: 99%

A Deep Learning Approach for Mild Depression Recognition Based on Functional Connectivity Using Electroencephalography

Wang

et al. 2020

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

“…So there are many seeks for new ways to diagnose depression, such as EEG based depression recognition (Li et al, 2019), or voice acoustics (Hashim et al, 2017). EEG is might be a good biomarker for depression, for example, a recent EEG study suggests that P1 amplitude to sad face showed potential as a state marker of depression (Ruohonen et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Screening Depressive Disorders With Tree-Drawing Test

Liu

Liang

et al. 2020

Front. Psychol.

View full text Add to dashboard Cite

Objective: Diagnosis of psychiatric disease is still a major issue. Two key reasons are-there are variations in the opinions of the medical doctors and the presentation of a disease among the patients. Here we introduce a kind of mental projective test, tree-drawing test, trying to extract and analyze objective indexes in tree-drawing test in patients with depression. Methods: The tree-drawing test was administered to 43 patients with major depressive disorders, 48 sub-threshold subjects, and 59 healthy subjects. Features of the drawing trees were analyzed using a kind of computer image recognition and data acquisition software. Quantitative indexes collected from pictures drawn by patients with major depression, patients with sub-threshold depression, and control subjects were compared using the ANOVA test. Results: Five quantitative features (canopy area, canopy height, canopy width, trunk width, and total area of trees) were found to be statistically significant among the groups, while seven other features (trunk area, trunk height, root width, root height, root area, ratio of crown to trunk height, and ratio of crown to trunk area) showed no statistical significance. Further analysis with LSD-t test revealed that six quantitative indexes were significantly related to the depression symptoms, and six others were not statistically significant. Eleven quantitative indexes were not statistically significant when the depressive symptoms were compared with the subthreshold depression group, and the only index with statistical significance was canopy width. Conclusion: Five quantitative indexes in the drawing tree are statistically significant in the depression patients were compared with those of the control subjects. Quantitative indexes of the tree-drawing test are of great value in assisting with the diagnosis of psychiatric disorders.

show abstract

“…And Zhu et al studied the problem of automatic diagnosis of depression and proposed a new approach to predict the Beck Depression Inventory II (BDI-II) values from video data based on the deep networks [34]. In addition, many scholars use deep network framework and mathematical analysis methods to explore the special characteristics of depression in brain signal [35], [36] and genetic engineering [37]. However, according to the above introduction, most existing studies focus on user behavior performance to detect whether a user suffers from depression or any mental illness.…”

Section: B Ai For Depression Detectionmentioning

confidence: 99%

MEMO Box: Health Assistant for Depression With Medicine Carrier and Exercise Adjustment Driven by Edge Computing

et al. 2020

View full text Add to dashboard Cite

According to the report by the World Health Organization, depression, as the leading disabling disease in the world, has aroused widespread social concern. However, the shortage of medical and nursing staff in psychiatry conflicts with the rising nursing needs of depressed patients. First, depression is a chronic mental illness, its cure course is relatively long, and stable drug treatment and healthy living habits are keys to the curing process. Second, the disease feature where depression patients have stronger emotional needs and more sensitive mental states is ignored in existing health monitoring systems. In consideration of the above two aspects, a health management assistant is proposed in this paper, called MEMO box system, that focuses on emotion and with smart medicine box as carrier. Specifically, the MEMO box system is composed of electronic medicine box and smart applications on mobile device, and electronic medicine box can collect the multi-mode data of patients, including their medication behaviors, daily activities, physical exercise data, and so on, which provide data basis for the health assistant. Emotion recognition and exercise recommend algorithms are deployed in the edge cloud, which can quickly respond to health service requests from patients. With the cooperation of hardware and software in this system, patients are urged to take medicines on time to effectively control their conditions, and emotion cognition and exercise adjustment recommendation can be realized for depression patients, thus providing patients with empathic sports recommendations.

show abstract

EEG-based mild depression recognition using convolutional neural network

Cited by 93 publications

References 41 publications

A Deep Learning Approach for Mild Depression Recognition Based on Functional Connectivity Using Electroencephalography

A Deep Learning Approach for Mild Depression Recognition Based on Functional Connectivity Using Electroencephalography

Screening Depressive Disorders With Tree-Drawing Test

MEMO Box: Health Assistant for Depression With Medicine Carrier and Exercise Adjustment Driven by Edge Computing

Contact Info

Product

Resources

About