EEG-based finger movement classification with intrinsic time-scale decomposition.

Introduction: Brain-computer interfaces (BCIs) are systems that acquire the brain's electrical activity and provide control of external devices. Since electroencephalography (EEG) is the simplest non-invasive method to capture the brain's electrical activity, EEG-based BCIs are very popular designs. Aside from classifying the extremity movements, recent BCI studies have focused on the accurate coding of the finger movements on the same hand through their classification by employing machine learning techniques. State-of-the-art studies were interested in coding five finger movements by neglecting the brain's idle case (i.e., the state that brain is not performing any mental tasks). This may easily cause more false positives and degrade the classification performances dramatically, thus, the performance of BCIs. This study aims to propose a more realistic system to decode the movements of five fingers and the no mental task (NoMT) case from EEG signals. Methods: In this study, a novel praxis for feature extraction is utilized. Using Proper Rotational Components (PRCs) computed through Intrinsic Time Scale Decomposition (ITD), which has been successfully applied in different biomedical signals recently, features for classification are extracted. Subsequently, these features were applied to the inputs of well-known classifiers and their different implementations to discriminate between these six classes. The highest classifier performances obtained in both subject-independent and subject-dependent cases were reported. In addition, the ANOVA-based feature selection was examined to determine whether statistically significant features have an impact on the classifier performances or not. Results: As a result, the Ensemble Learning classifier achieved the highest accuracy of 55.0% among the tested classifiers, and ANOVA-based feature selection increases the performance of classifiers on five-finger movement determination in EEG-based BCI systems. Discussion: When compared with similar studies, proposed praxis achieved a modest yet significant improvement in classification performance although the number of classes was incremented by one (i.e., NoMT).

Estimating Cognitive Load in a Mobile Personal Health Record Application: A Cognitive Task Analysis Approach.

OBJECTIVES: Mobile health applications that are designed without considering usability criteria can lead to cognitive overload, resulting in the rejection of these apps. To avoid this problem, the user interface of mobile health applications should be evaluated for cognitive load. This evaluation can contribute to the improvement of the user interface and help prevent cognitive overload for the user. METHODS: In this study, we evaluated a mobile personal health records application using the cognitive task analysis method, specifically the goals, operators, methods, and selection rules (GOMS) approach, along with the related updated GOMS model and gesture-level model techniques. The GOMS method allowed us to determine the steps of the tasks and categorize them as physical or cognitive tasks. We then estimated the completion times of these tasks using the updated GOMS model and gesture-level model. RESULTS: All 10 identified tasks were split into 398 steps consisting of mental and physical operators. The time to complete all the tasks was 5.70 minutes and 5.45 minutes according to the updated GOMS model and gesture-level model, respectively. Mental operators covered 73% of the total fulfillment time of the tasks according to the updated GOMS model and 76% according to the gesture-level model. The inter-rater reliability analysis yielded an average of 0.80, indicating good reliability for the evaluation method. CONCLUSIONS: The majority of the task execution times comprised mental operators, suggesting that the cognitive load on users is high. To enhance the application's implementation, the number of mental operators should be reduced.

Subjective Cognitive Load Evaluation of a Mobile Personal Health Record Application.

Mobile Personal Health Records (mPHRs), which make it possible to track and manage users' health information, can be an important aid in improving people's health. Despite its potential benefits, poor usability of systems can hinder the adoption and use of mPHRs. This study aims to evaluate the usability of a mobile health application in terms of perceived cognitive workload and performance. The cognitive workload experienced by 30 volunteers (15 experienced and 15 inexperienced), was measured while performing the given tasks with the NASA-Task Load Index (NASA-RTLX) scale, and the duration of the fulfillment of the tasks by eye tracking device. While there was no significant difference between the two user groups in the completion time of the tasks, a significant difference was found in the perceived cognitive load. "Making an appointment", which could take much longer to complete than other tasks, resulted in the highest cognitive load for all users. Further usability research using think-aloud protocols and user interviews could provide insights into design improvements for reducing cognitive load and enhancing performance.

Statistically significant features improve binary and multiple Motor Imagery task predictions from EEGs.

In recent studies, in the field of Brain-Computer Interface (BCI), researchers have focused on Motor Imagery tasks. Motor Imagery-based electroencephalogram (EEG) signals provide the interaction and communication between the paralyzed patients and the outside world for moving and controlling external devices such as wheelchair and moving cursors. However, current approaches in the Motor Imagery-BCI system design require effective feature extraction methods and classification algorithms to acquire discriminative features from EEG signals due to the non-linear and non-stationary structure of EEG signals. This study investigates the effect of statistical significance-based feature selection on binary and multi-class Motor Imagery EEG signal classifications. In the feature extraction process performed 24 different time-domain features, 15 different frequency-domain features which are energy, variance, and entropy of Fourier transform within five EEG frequency subbands, 15 different time-frequency domain features which are energy, variance, and entropy of Wavelet transform based on five EEG frequency subbands, and 4 different Poincare plot-based non-linear parameters are extracted from each EEG channel. A total of 1,364 Motor Imagery EEG features are supplied from 22 channel EEG signals for each input EEG data. In the statistical significance-based feature selection process, the best one among all possible combinations of these features is tried to be determined using the independent t-test and one-way analysis of variance (ANOVA) test on binary and multi-class Motor Imagery EEG signal classifications, respectively. The whole extracted feature set and the feature set that contain statistically significant features only are classified in this study. We implemented 6 and 7 different classifiers in multi-class and binary (two-class) classification tasks, respectively. The classification process is evaluated using the five-fold cross-validation method, and each classification algorithm is tested 10 times. These repeated tests provide to check the repeatability of the results. The maximum of 61.86 and 47.36% for the two-class and four-class scenarios, respectively, are obtained with Ensemble Subspace Discriminant among all these classifiers using selected features including only statistically significant features. The results reveal that the introduced statistical significance-based feature selection approach improves the classifier performances by achieving higher classifier performances with fewer relevant components in Motor Imagery task classification. In conclusion, the main contribution of the presented study is two-fold evaluation of non-linear parameters as an alternative to the commonly used features and the prediction of multiple Motor Imagery tasks using statistically significant features.

Efficiency evaluation of rapid maxillary expansion treatment on nasal septal deviation using tortuosity ratio from cone-beam computer tomography images.

BACKGROUND AND OBJECTIVE: This study aims to assess the effect of Rapid Maxillary Expansion (RME) on Nasal Septal Deviation (NSD) changes from three-dimensional (3D) images. METHODS: In this study, cone-beam computed tomography (CBCT) images from 15 patients with maxillary constriction (mean age 12 ± 1.6 years) were included. RME treatment with Hyrax appliance was performed in all patients. CBCT scans were taken at three different times; before appliance insertion (T0), after active expansion (T1) and 3 months after appliance insertion (T2). We developed a novel Matlab-based application to quantify NSD based on the tortuosity ratio by dividing the actual length of the septum by the ideal length in the mid-sagittal plane by using this application. RESULTS: Tortuosity ratio (TR) values were found as 1.03 ± 0.03 (T0), 1.02 ± 0.02 (T1), and 1.02 ± 0.02 (T2). Differences of TR values among these groups were evaluated using the statistical method of ANOVA (ANalysis Of VAriance) for repeated measures with the significance level of p ≤ .05. Results showed significant reductions in TR values between T0-T1 (p ≤ .05) and between T0-T2 (p ≤ .05). Nonetheless, a significant difference between T1-T2 was not determined (p > .05). CONCLUSIONS: As a result, we can conclude that the NSD degree is affected by the RME treatment. The developed application can be used for both educational and research purposes.

Analysis of social networks among physicians employed at a medical school.

Social network analysis is a well-known method for discovering the social complexities of relationships. In this paper, we present the results of its application in a healthcare environment, i.e. a state university hospital. The sociometric method was adopted to collect social network data. The analysis was performed using Pajek. The medical practice/academic and technological networks among physicians of a state university hospital were explored. Monomorphic and polymorphic opinion leaders (OLs) within the networks were identified using the in-degree measure. Cohesiveness were investigated based on network density and average degree. In addition, it was checked if the mentor system may present impact on the formation of social networks among physicians.

An approach to geotracking patients with Alzheimer's disease.

Recently, numerous systems for geo-tracking Alzheimer's patients with dementia have been developed and reported to be functional for the purposes of security and data collection. However, studies stated possible loss of freedom and autonomy for patients, along with violations of their privacy, which may lead to loss of prestige/dignity. In this study, a geotracking system that aims to balance patients' security and their need for privacy and autonomy is proposed. The system introduces a personalized, four-level temporal geofence based tracking, warning and notification protocol that incorporates a safety check mechanism operating over Global System for Mobile Communications network.