Assessing cognitive mental workload via EEG signals and an ensemble deep learning classifier based on denoising autoencoders

Yang, Shuo; Yin, Zhong; Wang, Yagang; Zhang, Wei; Wang, Yongxiong; Zhang, Jianhua

doi:10.1016/j.compbiomed.2019.04.034

Cited by 56 publications

(22 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various DCNN architectures with different parameters were selected for this experiment. However, only a few studies in the literature focused on the aggregation of multiple deep CNN models [ 41 , 56 ]. Hence, we were highly motivated to explore the potential of an ensemble model to apply more non-linearities, by connecting the trained weights of the best models obtained from study 2 to improve the final performance.…”

Section: Resultsmentioning

confidence: 99%

An Aggregated-Based Deep Learning Method for Leukemic B-lymphoblast Classification

2020

View full text Add to dashboard Cite

Leukemia is a cancer of blood cells in the bone marrow that affects both children and adolescents. The rapid growth of unusual lymphocyte cells leads to bone marrow failure, which may slow down the production of new blood cells, and hence increases patient morbidity and mortality. Age is a crucial clinical factor in leukemia diagnosis, since if leukemia is diagnosed in the early stages, it is highly curable. Incidence is increasing globally, as around 412,000 people worldwide are likely to be diagnosed with some type of leukemia, of which acute lymphoblastic leukemia accounts for approximately 12% of all leukemia cases worldwide. Thus, the reliable and accurate detection of normal and malignant cells is of major interest. Automatic detection with computer-aided diagnosis (CAD) models can assist medics, and can be beneficial for the early detection of leukemia. In this paper, a single center study, we aimed to build an aggregated deep learning model for Leukemic B-lymphoblast classification. To make a reliable and accurate deep learner, data augmentation techniques were applied to tackle the limited dataset size, and a transfer learning strategy was employed to accelerate the learning process, and further improve the performance of the proposed network. The results show that our proposed approach was able to fuse features extracted from the best deep learning models, and outperformed individual networks with a test accuracy of 96.58% in Leukemic B-lymphoblast diagnosis.

show abstract

Section: Resultsmentioning

confidence: 99%

An Aggregated-Based Deep Learning Method for Leukemic B-lymphoblast Classification

2020

View full text Add to dashboard Cite

show abstract

“…In our study, the controllers dealt with realistic ATM tasks in ecological settings. Thirdly, studies employing multimodal and machine-learning approaches did not consider the importance and meaning of the selected neurophysiological features 58,[61][62][63] . In fact, they usually made blind selections from a very large set of features in order to achieve high-classification accuracy.…”

Section: Neurophysiology Of Stressmentioning

confidence: 99%

A multimodal and signals fusion approach for assessing the impact of stressful events on Air Traffic Controllers

Borghini

Flumeri

Aricò

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Stress is a word used to describe human reactions to emotionally, cognitively and physically challenging experiences. A hallmark of the stress response is the activation of the autonomic nervous system, resulting in the "fight-freeze-flight" response to a threat from a dangerous situation. Consequently, the capability to objectively assess and track a controller's stress level while dealing with air traffic control (ATC) activities would make it possible to better tailor the work shift and maintain high safety levels, as well as to preserve the operator's health. In this regard, sixteen controllers were asked to perform a realistic air traffic management (ATM) simulation during which subjective data (i.e. stress perception) and neurophysiological data (i.e. brain activity, heart rate, and galvanic skin response) were collected with the aim of accurately characterising the controller's stress level experienced in the various experimental conditions. In addition, external supervisors regularly evaluated the controllers in terms of manifested stress, safety, and efficiency throughout the ATM scenario. The results demonstrated 1) how the stressful events caused both supervisors and controllers to underestimate the experienced stress level, 2) the advantage of taking into account both cognitive and hormonal processes in order to define a reliable stress index, and 3) the importance of the points in time at which stress is measured owing to the potential transient effect once the stressful events have ceased. Stress in air traffic management. The air traffic management (ATM) system is currently going through a major restructuring process, covering the entire architecture of process, personnel, and management environments. The increase in the level of automation as support tools for air traffic control (ATC) activities is one of the main technological challenges which will be faced in the future 1,2. Automation, digitalisation of information and virtualisation of the ATC operations will require a transformation of tasks and working methods. For example, with the prospect of an increasing in the volume of air traffic to be managed, controllers will be expected to delegate more activities and decisions to automation. In ATC, high demand is usually associated with a high mental workload and level of responsibility, while stress is linked to available time, team support, adherence to procedures and control over the planning and execution of tasks. The concepts of mental workload and stress are often used ambiguously, especially because of their relationship with performance when they reach very low or high values. In such cases, performance drops dramatically. However, certain levels of mental workload and

show abstract

“…Therefore, the application of Machine Learning has been considered the solution for classifying the workload and overcoming these issues typical of real applications. The preliminary analysis of the works carried out so far in this context has shown that it is possible to discriminate with acceptable accuracy only two levels of workload [6], [18], [22], [24], [25], [27]- [29], [33], [36]- [39], [42], [45], [46], [58], even though, above all in view of a practical application of the workload measurement, it is necessary to establish at least the value of two thresholds to define the underload and the overload state. The most frequently employed features are the spectral ones, because they can be calculated with a high temporal resolution (up to one second) and allow to monitor brain activity in a quantitative manner without temporal triggers.…”

Section: Discussionmentioning

confidence: 99%

“…Once defined a meaningful set of features, it is necessary to choose a model to define the workload level. In the literature innumerable algorithms, essentially of a supervised nature, have been used to define the workload level of a subject starting from his brain signals, belonging to both the so-called Shallow learning and deep Learning domains [45], [46]. In all cases the efficiency of such algorithms is usually presented in terms of accuracy.…”

Section: Machine Learning To Get Back Out-of-the-labmentioning

confidence: 99%

On the Use of Machine Learning for EEG-Based Workload Assessment: Algorithms Comparison in a Realistic Task

Sciaraffa

Aricò

Borghini

et al. 2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

The measurement of the mental workload during real tasks by means of neurophysiological signals is still challenging. The employment of Machine Learning techniques has allowed a step forward in this direction, however, most of the work has dealt with binary classification. This study proposed to examine the surveys already performed in the context of EEG-based workload classification and to test different machine learning algorithms on real multitasking activity like the Air Traffic Management. The results obtained on 35 professional Air Traffic Controllers showed that a KNN algorithm allows discriminating up to three workload levels (low, medium and high) with more than 84 % of accuracy on average. Moreover, in such realistic employment it emerges how important is to opportunely choose the set of features to ward off that task-related confounds could affect the workload assessment.

show abstract

Assessing cognitive mental workload via EEG signals and an ensemble deep learning classifier based on denoising autoencoders

Cited by 56 publications

References 47 publications

An Aggregated-Based Deep Learning Method for Leukemic B-lymphoblast Classification

An Aggregated-Based Deep Learning Method for Leukemic B-lymphoblast Classification

A multimodal and signals fusion approach for assessing the impact of stressful events on Air Traffic Controllers

On the Use of Machine Learning for EEG-Based Workload Assessment: Algorithms Comparison in a Realistic Task

Contact Info

Product

Resources

About