Cortical signals analysis to recognize intralimb mobility using modified RNN and various EEG quantities.

Electroencephalogram (EEG) signals are critical in interpreting sensorimotor activities for predicting body movements. However, their efficacy in identifying intralimb movements, such as the dorsiflexion and plantar flexion of the foot, remains suboptimal. This study aims to explore whether various EEG signal quantities can effectively recognize intralimb movements to facilitate the development of Brain-Computer Interface (BCI) devices for foot rehabilitation. This research involved twenty-two healthy, right-handed participants. EEG data were collected using 21 electrodes positioned over the motor cortex, while two electromyography (EMG) electrodes recorded the onset of ankle joint movements. The study focused on analyzing slow cortical potential (SCP) and sensorimotor rhythms (SMR) in alpha and beta bands from the EEG. Five key features-fourth-order Autoregressive feature, variance, waveform length, standard deviation, and permutation entropy-were extracted. A modified Recurrent Neural Network (RNN) including Long Short-term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms was developed for movement recognition. These were compared against conventional machine learning algorithms, including nonlinear Support Vector Machine (SVM) and k Nearest Neighbourhood (kNN) classifiers. The performance of the proposed models was assessed using two data schemes: within-subject and across-subjects. The findings demonstrated that the GRU and LSTM models significantly outperformed traditional machine learning algorithms in recognizing different EEG signal quantities for intralimb movement. The study indicates that deep learning models, particularly GRU and LSTM, hold superior potential over standard machine learning techniques in identifying intralimb movements using EEG signals. Where the accuracies of LSTM for within and across subjects were 98.87 ± 1.80 % and 87.38 ± 0.86 % respectively. Whereas the accuracy of GRU within and across subjects were 99.18 ± 1.28 % and 86.44 ± 0.69 % respectively. This advancement could significantly benefit the development of BCI devices aimed at foot rehabilitation, suggesting a new avenue for enhancing physical therapy outcomes.

Brain MRI sequence and view plane identification using deep learning.

Brain magnetic resonance imaging (MRI) scans are available in a wide variety of sequences, view planes, and magnet strengths. A necessary preprocessing step for any automated diagnosis is to identify the MRI sequence, view plane, and magnet strength of the acquired image. Automatic identification of the MRI sequence can be useful in labeling massive online datasets used by data scientists in the design and development of computer aided diagnosis (CAD) tools. This paper presents a deep learning (DL) approach for brain MRI sequence and view plane identification using scans of different data types as input. A 12-class classification system is presented for commonly used MRI scans, including T1, T2-weighted, proton density (PD), fluid attenuated inversion recovery (FLAIR) sequences in axial, coronal and sagittal view planes. Multiple online publicly available datasets have been used to train the system, with multiple infrastructures. MobileNet-v2 offers an adequate performance accuracy of 99.76% with unprocessed MRI scans and a comparable accuracy with skull-stripped scans and has been deployed in a tool for public use. The tool has been tested on unseen data from online and hospital sources with a satisfactory performance accuracy of 99.84 and 86.49%, respectively.

SpecSeg Network for Specular Highlight Detection and Segmentation in Real-World Images.

Specular highlights detection and removal in images is a fundamental yet non-trivial problem of interest. Most modern techniques proposed are inadequate at dealing with real-world images taken under uncontrolled conditions with the presence of complex textures, multiple objects, and bright colours, resulting in reduced accuracy and false positives. To detect specular pixels in a wide variety of real-world images independent of the number, colour, or type of illuminating source, we propose an efficient Specular Segmentation (SpecSeg) network based on the U-net architecture that is expeditious to train on nominal-sized datasets. The proposed network can detect pixels strongly affected by specular highlights with a high degree of precision, as shown by comparison with the state-of-the-art methods. The technique proposed is trained on publicly available datasets and tested using a large selection of real-world images with highly encouraging results.

Pulvinar Sign, Stroke and Their Relationship with Fabry Disease: A Systematic Review and Metanalysis.

Background: Fabry disease (FD) is the second most common lysosomal storage disorder. This disorder affects multiple systems that include the cardiac, renal, and nervous system. The pulvinar sign (PS) is a relatively common sign seen in patients with FD. The PS is a bilateral, symmetrical pulvinar high signal relative to the signal intensity seen on unenhanced T1-weighted brain MR imaging. Methods: We conducted a systematic review with metanalysis to analyze the pool prevalence of the disorder. We used the Moose Guidelines and PRISMA Protocol for this systematic review and Robins 1 to access the BIAS of the study. To analyze the pool prevalence, we used "Open Meta-Analysis" software for analyzing the study. We used "Review Manager 5.4" to analyze the odds ratio between patients with and without the PS and patients with and without stroke among patients with FD. Results: We gather 12 studies from 2003 to 2021 for the analysis of this study. The pool prevalence of the study was 0.146 (0.076−0.217) (62/385 cases) with a 95% CI (0.0945−0.415) (p < 0.01). The prevalence was much higher in men (59 cases) than in women (3 cases). There was no relationship between the pulvinar sign and patients with stroke among patients with Fabry disease. Odds ratio 1.97 95% CI (0.35−11.21), p = 0.44; Tau2 = 0.77. There seems to be a correlation with renal failure (RF), but there were very few studies to conduct a metanalysis with RF. Conclusions: The prevalence of the PS among all studies was 23.9%; the prevalence of this sign is higher among males. We found that FD patients who had strokes did not have higher odds of presenting with the Pulvinar Sign than the FD patients who did not suffer a stroke. Patients with renal failure and FD seem to have a higher tendency to have the PS, but there were not enough studies to analyze that theory. Overall, we think the pulvinar sign has a poor prognostic value in patients with Fabry's disease.

Resilience-Building for Mental Health among Early Childhood Educators: A Systematic Review and Pilot-Study towards an EEG-VR Resilience Building Intervention.

Resilience is a key factor that reflects a teacher's ability to utilize their emotional resources and working skills to provide high-quality teaching to children. Resilience-building interventions aim to promote positive psychological functioning and well-being. However, there is lack of evidence on whether these interventions improve the well-being or mental health of teachers in early childhood education (ECE) settings. This review examined the overall effectiveness of resilience-building interventions conducted on teachers working in the ECE field. A systematic approach is used to identify relevant studies that focus on resilience-building in countering work stress among early childhood educators. Findings from this review observed a preference of group approaches and varying durations of interventions. This review highlights the challenges of the group approach which can lead to lengthy interventions and attrition amongst participants. In addition to the concerns regarding response bias from self-report questionnaires, there is also a lack of physiological measures used to evaluate effects on mental health. The large efforts by 11 studies to integrate multiple centres into their intervention and the centre-based assessment performed by four studies highlight the need for a centre-focused approach to build resilience among teachers from various ECE centres. A pilot study is conducted to evaluate the feasibility of an integrated electroencephalography-virtual reality (EEG-VR) approach in building resilience in teachers, where the frontal brain activity can be monitored during a virtual classroom task. Overall, the findings of this review propose the integration of physiological measures to monitor changes in mental health throughout the resilience-building intervention and the use of VR as a tool to design a unique virtual environment.

Towards Automatic License Plate Detection.

Automatic License Plate Detection (ALPD) is an integral component of using computer vision approaches in Intelligent Transportation Systems (ITS). An accurate detection of vehicles' license plates in images is a critical step that has a substantial impact on any ALPD system's recognition rate. In this paper, we develop an efficient license plate detecting technique through the intelligent combination of Faster R-CNN along with digital image processing techniques. The proposed algorithm initially detects vehicle(s) in the input image through Faster R-CNN. Later, the located vehicle is analyzed by a robust License Plate Localization Module (LPLM). The LPLM module primarily uses color segmentation and processes the HSV image to detect the license plate in the input image. Moreover, the LPLM module employs morphological filtering and dimension analysis to find the license plate. Detailed trials on challenging PKU datasets demonstrate that the proposed method outperforms few recently developed methods by producing high license plates detection accuracy in much less execution time. The proposed work demonstrates a great feasibility for security and target detection applications.

Workplace Mental State Monitoring during VR-Based Training for Offshore Environment.

Adults are constantly exposed to stressful conditions at their workplace, and this can lead to decreased job performance followed by detrimental clinical health problems. Advancement of sensor technologies has allowed the electroencephalography (EEG) devices to be portable and used in real-time to monitor mental health. However, real-time monitoring is not often practical in workplace environments with complex operations such as kindergarten, firefighting and offshore facilities. Integrating the EEG with virtual reality (VR) that emulates workplace conditions can be a tool to assess and monitor mental health of adults within their working environment. This paper evaluates the mental states induced when performing a stressful task in a VR-based offshore environment. The theta, alpha and beta frequency bands are analysed to assess changes in mental states due to physical discomfort, stress and concentration. During the VR trials, mental states of discomfort and disorientation are observed with the drop of theta activity, whilst the stress induced from the conditional tasks is reflected in the changes of low-alpha and high-beta activities. The deflection of frontal alpha asymmetry from negative to positive direction reflects the learning effects from emotion-focus to problem-solving strategies adopted to accomplish the VR task. This study highlights the need for an integrated VR-EEG system in workplace settings as a tool to monitor and assess mental health of working adults.

Performance Evaluation of EEG Based Mental Stress Assessment Approaches for Wearable Devices.

Mental stress has been identified as the root cause of various physical and psychological disorders. Therefore, it is crucial to conduct timely diagnosis and assessment considering the severe effects of mental stress. In contrast to other health-related wearable devices, wearable or portable devices for stress assessment have not been developed yet. A major requirement for the development of such a device is a time-efficient algorithm. This study investigates the performance of computer-aided approaches for mental stress assessment. Machine learning (ML) approaches are compared in terms of the time required for feature extraction and classification. After conducting tests on data for real-time experiments, it was observed that conventional ML approaches are time-consuming due to the computations required for feature extraction, whereas a deep learning (DL) approach results in a time-efficient classification due to automated unsupervised feature extraction. This study emphasizes that DL approaches can be used in wearable devices for real-time mental stress assessment.

Evidence-based chlorination targets for household water safety in humanitarian settings: Recommendations from a multi-site study in refugee camps in South Sudan, Jordan, and Rwanda.

The current Sphere guideline for water chlorination in humanitarian emergencies fails to reliably ensure household water safety in refugee camps. We investigated post-distribution chlorine decay and household water safety in refugee camps in South Sudan, Jordan, and Rwanda between 2013-2015 with the goal of demonstrating an approach for generating site-specific and evidence-based chlorination targets that better ensure household water safety than the status quo Sphere guideline. In each of four field studies we conducted, we observed how water quality changed between distribution and point of consumption. We implemented a nonlinear optimization approach for the novel technical challenge of modelling post-distribution chlorine decay in order to generate estimates on what free residual chlorine (FRC) levels must be at water distribution points, in order to provide adequate FRC protection up to the point of consumption in households many hours later at each site. The site-specific FRC targets developed through this modelling approach improved the proportion of households having sufficient chlorine residual (i.e., ≥0.2 mg/L FRC) at the point of consumption in three out of four field studies (South Sudan 2013, Jordan 2014, and Rwanda 2015). These sites tended to be hotter (i.e., average mid-afternoon air temperatures >30°C) and/or had poorer water, sanitation, and hygiene (WASH) conditions, contributing to considerable chlorine decay between distribution and consumption. Our modelling approach did not work as well where chlorine decay was small in absolute terms (Jordan 2015). In such settings, which were cooler (20 to 30°C) and had better WASH conditions, we found that the upper range of the current Sphere chlorination guideline (i.e., 0.5 mg/L FRC) provided sufficient residual chlorine for ensuring household water safety up to 24 hours post-distribution. Site-specific and evidence-based chlorination targets generated from post-distribution chlorine decay modelling could help improve household water safety and public health outcomes in refugee camp settings where the current Sphere chlorination guideline does not provide adequate residual protection. Water quality monitoring in refugee/IDP camps should shift focus from distribution points to household points of consumption in order to monitor if the intended public health goal of safe water at the point of consumption is being achieved.

Intracerebral hemorrhage outcomes in patients using direct oral anticoagulants versus vitamin K antagonists: a meta-analysis.

BACKGROUND: The objective of this paper is to assess the clinical outcomes between non-traumatic intracerebral hemorrhage(ICH) in patients using direct oral anticoagulants(DOAC) versus vitamin K antagonists(VKA) for non-valvular atrial fibrillation. We also evaluated the predictors of the poor post-ICH outcomes. METHODS: We have performed pooled meta-analysis to assess long-term clinical outcomes in patients with DOAC-ICH as compared to those with VKA-ICH. A systematic literature search was conducted by searching the full-text English literature in PubMed, EMBASE, and Cochrane databases for observational studies reporting outcomes on interest. MOOSE guidelines were used to collect data till December 31, 2019 and random effects analysis was carried out to account for heterogeneity. For outcomes, risk ratios(RR) and the mean differences were pooled using a random-effects model and weighted mean differences (WMDs), respectively. RESULTS: Seventeen studies met the inclusion criteria (n = 25,354 patients; DOAC-ICH arms = 5,631; VKA-ICH arm = 19,273). Patients with DOAC-ICH had smaller hematoma volumes (WMD=-9.59; 95%CI=-15.33--3.85; I2 = 68.6%) and reduced mortality rate at discharge (RR = 0.82; 95%CI = 0.71-0.96; I2 = 9.4%). There was no significant difference between the two groups in rate of hematoma expansion (RR = 0.79; 95%CI = 0.56-1.11; I2 = 50.9%), unfavorable functional outcome(Modified Rankin Scale) at discharge (RR = 0.82; 95%CI = 0.56-1.18; I2 = 80.2%), unfavorable outcome at 3-months (RR = 0.77; 95%CI = 0.56-1.06; I2 = 63.9), and mortality at 3-months (RR = 0.90; 95%CI = 0.73-1.10; I2 = 35∙8%). Multivariate meta-regression revealed that the average age of patient population had a significantly negative correlation with(RR=-0.202; p = 0.017) hematoma expansion. CONCLUSION: We conclude that use of DOAC is associated with reduced hematoma volume and mortality rate at discharge. Age is a predictor of the poor outcome of hematoma expansion.

Real-Time Stress Assessment Using Sliding Window Based Convolutional Neural Network.

Mental stress has been identified as a significant cause of several bodily disorders, such as depression, hypertension, neural and cardiovascular abnormalities. Conventional stress assessment methods are highly subjective and tedious and tend to lack accuracy. Machine-learning (ML)-based computer-aided diagnosis systems can be used to assess the mental state with reasonable accuracy, but they require offline processing and feature extraction, rendering them unsuitable for real-time applications. This paper presents a real-time mental stress assessment approach based on convolutional neural networks (CNNs). The CNN-based approach afforded real-time mental stress assessment with an accuracy as high as 96%, the sensitivity of 95%, and specificity of 97%. The proposed approach is compared with state-of-the-art ML techniques in terms of accuracy, time utilisation, and quality of features.

Evaluation of Deep Neural Networks for Semantic Segmentation of Prostate in T2W MRI.

In this paper, we present an evaluation of four encoder-decoder CNNs in the segmentation of the prostate gland in T2W magnetic resonance imaging (MRI) image. The four selected CNNs are FCN, SegNet, U-Net, and DeepLabV3+, which was originally proposed for the segmentation of road scene, biomedical, and natural images. Segmentation of prostate in T2W MRI images is an important step in the automatic diagnosis of prostate cancer to enable better lesion detection and staging of prostate cancer. Therefore, many research efforts have been conducted to improve the segmentation of the prostate gland in MRI images. The main challenges of prostate gland segmentation are blurry prostate boundary and variability in prostate anatomical structure. In this work, we investigated the performance of encoder-decoder CNNs for segmentation of prostate gland in T2W MRI. Image pre-processing techniques including image resizing, center-cropping and intensity normalization are applied to address the issues of inter-patient and inter-scanner variability as well as the issue of dominating background pixels over prostate pixels. In addition, to enrich the network with more data, to increase data variation, and to improve its accuracy, patch extraction and data augmentation are applied prior to training the networks. Furthermore, class weight balancing is used to avoid having biased networks since the number of background pixels is much higher than the prostate pixels. The class imbalance problem is solved by utilizing weighted cross-entropy loss function during the training of the CNN model. The performance of the CNNs is evaluated in terms of the Dice similarity coefficient (DSC) and our experimental results show that patch-wise DeepLabV3+ gives the best performance with DSC equal to 92 . 8 % . This value is the highest DSC score compared to the FCN, SegNet, and U-Net that also competed the recently published state-of-the-art method of prostate segmentation.

Effect of ertugliflozin on glycemic levels, blood pressure and body weight of patients with type 2 diabetes mellitus: a systematic review and meta-analysis.

PURPOSE: To conduct a meta-analysis to evaluate the effect of ertugliflozin on long-term hemoglobin A1c (HbA1c), body weight and blood pressure (BP). METHODS: Online databases available were searched from their inception to February 2020. Randomized controlled trials (RCTs) comparing ertugliflozin to either placebo or an active control drug were included. Data on four efficacy outcomes were extracted, namely: HbA1c, systolic blood pressure (SBP), diastolic blood pressure (DBP) and body weight. Continuous outcomes were pooled using a random-effects model and presented as weighted mean differences (WMDs) and corresponding 95% CIs. Additionally, a subgroup analysis was done to compare two doses of ertugliflozin (5 mg and 15 mg). A sensitivity analysis was also performed by eliminating studies using active drugs as controls. RESULTS: From a total of 123 search results, eight studies were included. Compared to the control group, ertugliflozin was associated with a significant decrease in SBP (WMD: -3.64 mmHg, 95% CI [-4.39,-2.90]; p < 0.001; I2 = 0%) and DBP (WMD: -1.13 mmHg, 95% CI [-1.67,-0.60], p < 0.001; I2 = 0%). Similarly, significant reductions in body weight (WMD: -2.35 kg, 95% CI [-2.94,-1.77]; p < 0.001; I2 = 0%) as well as HbA1c (WMD: -0.41%, 95% CI [-0.62,-0.20]; p < 0.001; I2 = 0%) were seen with ertugliflozin. Subgroup analysis demonstrated no significant difference in efficacy between the two doses in any of the four outcomes. CONCLUSION: Ertugliflozin results in significant reductions in HbA1c, body weight, SBP and DBP, when compared to control. Subgroup analyses suggest that these effects are not dose-dependent.

An EEG-based functional connectivity measure for automatic detection of alcohol use disorder.

BACKGROUND: The abnormal alcohol consumption could cause toxicity and could alter the human brain's structure and function, termed as alcohol used disorder (AUD). Unfortunately, the conventional screening methods for AUD patients are subjective and manual. Hence, to perform automatic screening of AUD patients, objective methods are needed. The electroencephalographic (EEG) data have been utilized to study the differences of brain signals between alcoholics and healthy controls that could further developed as an automatic screening tool for alcoholics. METHOD: In this work, resting-state EEG-derived features were utilized as input data to the proposed feature selection and classification method. The aim was to perform automatic classification of AUD patients and healthy controls. The validation of the proposed method involved real-EEG data acquired from 30 AUD patients and 30 age-matched healthy controls. The resting-state EEG-derived features such as synchronization likelihood (SL) were computed involving 19 scalp locations resulted into 513 features. Furthermore, the features were rank-ordered to select the most discriminant features involving a rank-based feature selection method according to a criterion, i.e., receiver operating characteristics (ROC). Consequently, a reduced set of most discriminant features was identified and utilized further during classification of AUD patients and healthy controls. In this study, three different classification models such as Support Vector Machine (SVM), Naïve Bayesian (NB), and Logistic Regression (LR) were used. RESULTS: The study resulted into SVM classification accuracy=98%, sensitivity=99.9%, specificity=95%, and f-measure=0.97; LR classification accuracy=91.7%, sensitivity=86.66%, specificity=96.6%, and f-measure=0.90; NB classification accuracy=93.6%, sensitivity=100%, specificity=87.9%, and f-measure=0.95. CONCLUSION: The SL features could be utilized as objective markers to screen the AUD patients and healthy controls.

A machine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder (MDD).

Major depressive disorder (MDD), a debilitating mental illness, could cause functional disabilities and could become a social problem. An accurate and early diagnosis for depression could become challenging. This paper proposed a machine learning framework involving EEG-derived synchronization likelihood (SL) features as input data for automatic diagnosis of MDD. It was hypothesized that EEG-based SL features could discriminate MDD patients and healthy controls with an acceptable accuracy better than measures such as interhemispheric coherence and mutual information. In this work, classification models such as support vector machine (SVM), logistic regression (LR) and Naïve Bayesian (NB) were employed to model relationship between the EEG features and the study groups (MDD patient and healthy controls) and ultimately achieved discrimination of study participants. The results indicated that the classification rates were better than chance. More specifically, the study resulted into SVM classification accuracy = 98%, sensitivity = 99.9%, specificity = 95% and f-measure = 0.97; LR classification accuracy = 91.7%, sensitivity = 86.66%, specificity = 96.6% and f-measure = 0.90; NB classification accuracy = 93.6%, sensitivity = 100%, specificity = 87.9% and f-measure = 0.95. In conclusion, SL could be a promising method for diagnosing depression. The findings could be generalized to develop a robust CAD-based tool that may help for clinical purposes.

A wavelet-based technique to predict treatment outcome for Major Depressive Disorder.

Treatment management for Major Depressive Disorder (MDD) has been challenging. However, electroencephalogram (EEG)-based predictions of antidepressant's treatment outcome may help during antidepressant's selection and ultimately improve the quality of life for MDD patients. In this study, a machine learning (ML) method involving pretreatment EEG data was proposed to perform such predictions for Selective Serotonin Reuptake Inhibitor (SSRIs). For this purpose, the acquisition of experimental data involved 34 MDD patients and 30 healthy controls. Consequently, a feature matrix was constructed involving time-frequency decomposition of EEG data based on wavelet transform (WT) analysis, termed as EEG data matrix. However, the resultant EEG data matrix had high dimensionality. Therefore, dimension reduction was performed based on a rank-based feature selection method according to a criterion, i.e., receiver operating characteristic (ROC). As a result, the most significant features were identified and further be utilized during the training and testing of a classification model, i.e., the logistic regression (LR) classifier. Finally, the LR model was validated with 100 iterations of 10-fold cross-validation (10-CV). The classification results were compared with short-time Fourier transform (STFT) analysis, and empirical mode decompositions (EMD). The wavelet features extracted from frontal and temporal EEG data were found statistically significant. In comparison with other time-frequency approaches such as the STFT and EMD, the WT analysis has shown highest classification accuracy, i.e., accuracy = 87.5%, sensitivity = 95%, and specificity = 80%. In conclusion, significant wavelet coefficients extracted from frontal and temporal pre-treatment EEG data involving delta and theta frequency bands may predict antidepressant's treatment outcome for the MDD patients.

Effectiveness of emergency water treatment practices in refugee camps in South Sudan.

OBJECTIVE: To investigate the concentration of residual chlorine in drinking water supplies in refugee camps, South Sudan, March-April 2013. METHODS: For each of three refugee camps, we measured physical and chemical characteristics of water supplies at four points after distribution: (i) directly from tapstands; (ii) after collection; (iii) after transport to households; and (iv) after several hours of household storage. The following parameters were measured: free and total residual chlorine, temperature, turbidity, pH, electrical conductivity and oxidation reduction potential. We documented water handling practices with spot checks and respondent self-reports. We analysed factors affecting residual chlorine concentrations using mathematical and linear regression models. FINDINGS: For initial free residual chlorine concentrations in the 0.5-1.5 mg/L range, a decay rate of ~5x10(-3) L/mg/min was found across all camps. Regression models showed that the decay of residual chlorine was related to initial chlorine levels, electrical conductivity and air temperature. Covering water storage containers, but not other water handling practices, improved the residual chlorine levels. CONCLUSION: The concentrations of residual chlorine that we measured in water supplies in refugee camps in South Sudan were too low. We tentatively recommend that the free residual chlorine guideline be increased to 1.0 mg/L in all situations, irrespective of diarrhoeal disease outbreaks and the pH or turbidity of water supplies. According to our findings, this would ensure a free residual chlorine level of 0.2 mg/L for at least 10 hours after distribution. However, it is unknown whether our findings are generalizable to other camps and further studies are therefore required.

Detrended fluctuation analysis for major depressive disorder.

Clinical utility of Electroencephalography (EEG) based diagnostic studies is less clear for major depressive disorder (MDD). In this paper, a novel machine learning (ML) scheme was presented to discriminate the MDD patients and healthy controls. The proposed method inherently involved feature extraction, selection, classification and validation. The EEG data acquisition involved eyes closed (EC) and eyes open (EO) conditions. At feature extraction stage, the de-trended fluctuation analysis (DFA) was performed, based on the EEG data, to achieve scaling exponents. The DFA was performed to analyzes the presence or absence of long-range temporal correlations (LRTC) in the recorded EEG data. The scaling exponents were used as input features to our proposed system. At feature selection stage, 3 different techniques were used for comparison purposes. Logistic regression (LR) classifier was employed. The method was validated by a 10-fold cross-validation. As results, we have observed that the effect of 3 different reference montages on the computed features. The proposed method employed 3 different types of feature selection techniques for comparison purposes as well. The results show that the DFA analysis performed better in LE data compared with the IR and AR data. In addition, during Wilcoxon ranking, the AR performed better than LE and IR. Based on the results, it was concluded that the DFA provided useful information to discriminate the MDD patients and with further validation can be employed in clinics for diagnosis of MDD.