scholarly journals Depression Diagnosis by Deep Learning Using EEG Signals: A Systematic Review

2021 ◽  
Author(s):  
Atefeh Safayari ◽  
Hamidreza Bolhasani
Keyword(s):  
Deep Learning ◽  
Human Life ◽  
Eeg Signals ◽  
Future Directions ◽  
Public And Private ◽  
Depression Diagnosis ◽  
Step Procedure ◽  
Diverse Field ◽  
Depression Detection ◽  
Almost All

Depression is considered by WHO as the main contributor to global disability and it poses dangerous threats to approximately all aspects of human life, in particular public and private health. This mental disorder is usually characterized by considerable changes in feelings, routines, or thoughts. With respect to the fact that early diagnosis of this illness would be of critical importance ineffective treatment, some development has occurred in the purpose of depression detection. EEG signals reflect the working status of the human brain by which are considered the most proper tools for a depression diagnosis. Deep learning algorithms have the capacity of pattern discovery and extracting features from the raw data which is fed into them. Owing to this significant characteristic of deep learning, recently, these methods have intensely utilized in the diverse field of researches, specifically medicine and healthcare. Thereby, in this article, we aimed to review all papers concentrated on using deep learning to detect or predict depressive subjects with the help of EEG signals as input data. Regarding the adopted search method, we finally evaluated 22 articles between 2016 and 2021. This article which is organized according to the systematic literature review (SLR) method, provides complete summaries of all exploited studies and compares the noticeable aspects of them. Moreover, some statistical analysis performs to gain a depth perception of the general ideas of the latest researches in this area. A pattern of a five-step procedure was also established by which almost all reviewed articles fulfilled the goal of depression detection. Finally, open issues and challenges in this way of depression diagnosis or prediction and suggested works as the future directions discussed.

scholarly journals A Composite Deep Learning Access for Leaf Species Classification

2019 ◽  
Vol 8 (11S) ◽  
pp. 42-45
Keyword(s):  
Deep Learning ◽  
Human Life ◽  
Real Life ◽  
Recognition System ◽  
Raw Material ◽  
Species Classification ◽  
Classification Management ◽  
Almost All ◽  
Deep Learning Model

Plants are an integral part of the human life one way or the other. They have multi-dimensional use as food, medicine, clothing, art, industrial raw material and are vital for sustaining the ecological balance of our planet. All these real life applications make the identification of plants intensely important and useful. This dictates to design an accurate recognition system of plants. It will be useful to facilitate faster classification, management and apprehension. Almost all the plants are accompanied by unique leaves. In this paper, we have used this property of leaf identification for the identification of plants. In this study, we have applied a composite deep learning model, where Inception-v3 model is used for feature engineering and Stacking Ensemble model is used for the detection and classification of leaves from images. We have used a modified Flavia dataset of 1287 leaf images divided amongst 21 distinct plant species to test the proposed approach. On comparing our proposed work with other pre-existing algorithms (RF, SVM, kNN and Tree), it is found that it surpassed them, obtaining an accuracy of 99.5%.

Depression Diagnosis Modeling With Advanced Computational Methods: Frequency-Domain eMVAR and Deep Learning

2021 ◽  
pp. 155005942110185
Author(s):  
Caglar Uyulan ◽  
Sara de la Salle ◽  
Turker T. Erguzel ◽  
Emma Lynn ◽  
Pierre Blier ◽  
...  
Keyword(s):  
Deep Learning ◽  
Frequency Domain ◽  
Short Term Memory ◽  
Computational Techniques ◽  
Specific Information ◽  
Eeg Signals ◽  
Directed Transfer Function ◽  
Depression Diagnosis ◽  
Conventional Machine ◽  
Electroencephalogram Eeg

Electroencephalogram (EEG)-based automated depression diagnosis systems have been suggested for early and accurate detection of mood disorders. EEG signals are highly irregular, nonlinear, and nonstationary in nature and are traditionally studied from a linear viewpoint by means of statistical and frequency features. Since, linear metrics present certain limitations and nonlinear methods have proven to be an efficient tool in understanding the complexities of the brain in the identification of underlying behavior of biological signals, such as electrocardiogram, EEG and magnetoencephalogram and thus, can be applied to all nonstationary signals. Various nonlinear algorithms can be used in the analysis of EEG signals. In this research paper, we aim to develop a novel methodology for EEG-based depression diagnosis utilizing 2 advanced computational techniques: frequency-domain extended multivariate autoregressive (eMVAR) and deep learning (DL). We proposed a hybrid method comprising a pretrained ResNet-50 and long-short term memory (LSTM) to capture depression-specific information and compared with a strong conventional machine learning (ML) framework having eMVAR connectivity features. The following 8 causality measures, which interpret the interaction mechanisms among spectrally decomposed oscillations, were used to extract features from multivariate EEG time series: directed coherence (DC), directed transfer function (DTF), partial DC (PDC), generalized PDC (gPDC), extended DC (eDC), delayed DC (dDC), extended PDC (ePDC), and delayed PDC (dPDC). The classification accuracies were 84% with DC, 85% with DTF, 95.3% with PDC, 95.1% with gPDC, 84.8% with eDC, 84.6% with dDC, 84.2% with ePDC, and 95.9% with dPDC for the eMVAR framework. Through a DL framework (ResNet-50 + LSTM), the classification accuracy was achieved as 90.22%. The results demonstrate that our DL methodology is a competitive alternative to the strong feature extraction-based ML methods in depression classification.

The problems of quality management system readiness to integrate modern digital technologies

2020 ◽  
pp. 17-23
Author(s):  
E.A. Kovrigin ◽  
◽  
V.A. Vasilyev ◽  
Keyword(s):  
Quality Management ◽  
Quality Management System ◽  
Human Life ◽  
Digital Technologies ◽  
Modern World ◽  
Readiness Assessment ◽  
Quality Management Model ◽  
Modelling Techniques ◽  
Almost All ◽  
Generalize Information

Given the trends in the modern world, as well as the rapid growth of digitalization, it is safe to say that it will inevitably affect almost all areas of human life and activities. Dmitriev’s English dictionary defines the word readiness: «It is a state where everything is done to start doing something.» Accordingly, an assessment of the company’s readiness to integrate modern digital technologies will identify opportunities, risks and threats, strengths and weaknesses of the enterprise, as well as to formulate a list of initial measures that need to be implemented. Thus, there is an urgent need to find an answer to the following questions: «How (by, what criteria and indicators) to measure readiness?», «What are the approaches to readiness assessment?» The purpose of this article is to develop a model and algorithm to assess the company’s readiness to integrate modern digital technologies. Modelling techniques were used to achieve this goal, as well as to analyze and generalize information. As a result of the research, a model for assessing the company’s readiness to integrate modern digital technologies has been developed and tested, based on the quality management model presented in the ISO 9000 series standards. A particular example shows how to use it and what it ultimately allows you to see and evaluate.

scholarly journals Twelve Years of the Italian Program to Enhance Relational and Communication Skills (PERCS)

2021 ◽  
Vol 18 (2) ◽  
pp. 439
Author(s):  
Lidia Borghi ◽  
Elaine C. Meyer ◽  
Elena Vegni ◽  
Roberta Oteri ◽  
Paolo Almagioni ◽  
...  
Keyword(s):  
Communication Skills ◽  
Repeated Measures ◽  
Behavioral Changes ◽  
Chi Square ◽  
Future Directions ◽  
Public And Private ◽  
Learner Centered ◽  
Difficult Conversations ◽  
Booster Sessions ◽  
Before And After

To describe the experience of the Italian Program to Enhance Relations and Communication Skills (PERCS-Italy) for difficult healthcare conversations. PERCS-Italy has been offered in two different hospitals in Milan since 2008. Each workshop lasts 5 h, enrolls 10–15 interdisciplinary participants, and is organized around simulations and debriefing of two difficult conversations. Before and after the workshops, participants rate their preparation, communication, relational skills, confidence, and anxiety on 5-point Likert scales. Usefulness, quality, and recommendation of the program are also assessed. Descriptive statistics, t-tests, repeated-measures ANOVA, and Chi-square were performed. A total of 72 workshops have been offered, involving 830 interdisciplinary participants. Participants reported improvements in all the dimensions (p < 0.001) without differences across the two hospitals. Nurses and other professionals reported a greater improvement in preparation, communication skills, and confidence, compared to physicians and psychosocial professionals. Usefulness, quality, and recommendation of PERCS programs were highly rated, without differences by discipline. PERCS-Italy proved to be adaptable to different hospital settings, public and private. After the workshops, clinicians reported improvements in self-reported competencies when facing difficult conversations. PERCS-Italy’s sustainability is based on the flexible format combined with a solid learner-centered approach. Future directions include implementation of booster sessions to maintain learning and the assessment of behavioral changes.

scholarly journals EEG Emotion Classification Using an Improved SincNet-Based Deep Learning Model

2019 ◽  
Vol 9 (11) ◽  
pp. 326 ◽  
Author(s):  
Hong Zeng ◽  
Zhenhua Wu ◽  
Jiaming Zhang ◽  
Chen Yang ◽  
Hua Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Speaker Recognition ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Signal To Noise Ratio ◽  
Single Subject ◽  
Emotion Classification ◽  
Eeg Signals ◽  
Electroencephalogram Eeg ◽  
Deep Learning Model

Deep learning (DL) methods have been used increasingly widely, such as in the fields of speech and image recognition. However, how to design an appropriate DL model to accurately and efficiently classify electroencephalogram (EEG) signals is still a challenge, mainly because EEG signals are characterized by significant differences between two different subjects or vary over time within a single subject, non-stability, strong randomness, low signal-to-noise ratio. SincNet is an efficient classifier for speaker recognition, but it has some drawbacks in dealing with EEG signals classification. In this paper, we improve and propose a SincNet-based classifier, SincNet-R, which consists of three convolutional layers, and three deep neural network (DNN) layers. We then make use of SincNet-R to test the classification accuracy and robustness by emotional EEG signals. The comparable results with original SincNet model and other traditional classifiers such as CNN, LSTM and SVM, show that our proposed SincNet-R model has higher classification accuracy and better algorithm robustness.

scholarly journals Deep Learning for Radio-based Human Sensing: Recent Advances and Future Directions

2021 ◽  
pp. 1-1
Author(s):  
Isura Nirmal ◽  
Abdelwahed Khamis ◽  
Mahbub Hassan ◽  
Wen Hu ◽  
Xiaoqing Zhu
Keyword(s):  
Deep Learning ◽  
Future Directions ◽  
Recent Advances ◽  
Human Sensing
Sign in / Sign up

Export Citation Format

Share Document