EEG signal classification for BCI applications by wavelets and interval type-2 fuzzy logic systems

The nonlinear, noisy and outlier characteristics of electroencephalography (EEG) signals inspire the employment of fuzzy logic due to its power to handle uncertainty. This paper introduces an approach to classify motor imagery EEG signals using an interval type-2 fuzzy logic system (IT2FLS) in a combination with wavelet transformation. Wavelet coefficients are ranked based on the statistics of the receiver operating characteristic curve criterion. The most informative coefficients serve as inputs to the IT2FLS for the classification task. Two benchmark datasets, named Ia and Ib, downloaded from the brain-computer interface (BCI) competition II, are employed for the experiments. Classification performance is evaluated using accuracy, sensitivity, specificity and F-measure. Widely-used classifiers, including feedforward neural network, support vector machine, k-nearest neighbours, AdaBoost and adaptive neuro-fuzzy inference system, are also implemented for comparisons. The wavelet-IT2FLS method considerably dominates the comparable classifiers on both datasets, and outperforms the best performance on the Ia and Ib datasets reported in the BCI competition II by 1.40% and 2.27% respectively. The proposed approach yields great accuracy and requires low computational cost, which can be applied to a real-time BCI system for motor imagery data analysis.

Medical data classification using interval type-2 fuzzy logic system and wavelets

This paper introduces an automated medical data classification method using wavelet transformation (WT) and interval type-2 fuzzy logic system (IT2FLS). Wavelet coefficients, which serve as inputs to the IT2FLS, are a compact form of original data but they exhibits highly discriminative features. The integration between WT and IT2FLS aims to cope with both high-dimensional data challenge and uncertainty. IT2FLS utilizes a hybrid learning process comprising unsupervised structure learning by the fuzzy c-means (FCM) clustering and supervised parameter tuning by genetic algorithm. This learning process is computationally expensive, especially when employed with high-dimensional data. The application of WT therefore reduces computational burden and enhances performance of IT2FLS. Experiments are implemented with two frequently used medical datasets from the UCI Repository for machine learning: the Wisconsin breast cancer and Cleveland heart disease. A number of important metrics are computed to measure the performance of the classification. They consist of accuracy, sensitivity, specificity and area under the receiver operating characteristic curve. Results demonstrate a significant dominance of the wavelet-IT2FLS approach compared to other machine learning methods including probabilistic neural network, support vector machine, fuzzy ARTMAP, and adaptive neuro-fuzzy inference system. The proposed approach is thus useful as a decision support system for clinicians and practitioners in the medical practice. copy; 2015 Elsevier B.V. All rights reserved.

Sprint interval and moderate-intensity continuous training have equal benefits on aerobic capacity, insulin sensitivity, muscle capillarisation and endothelial eNOS/NAD(P)Hoxidase protein ratio in obese men

Key points: Skeletal muscle capillary density and vasoreactivity are reduced in obesity, due to reduced nitric oxide bioavailability. Sprint interval training (SIT) has been proposed as a time efficient alternative to moderate-intensity continuous training (MICT), but its effect on the skeletal muscle microvasculature has not been studied in obese individuals. We observed that SIT and MICT led to equal increases in capillarisation and endothelial eNOS content, while reducing endothelial NOX2 content in microvessels of young obese men. We conclude that SIT is equally effective at improving skeletal muscle capillarisation and endothelial enzyme balance, while being a time efficient alternative to traditional MICT. Sprint interval training (SIT) has been proposed as a time efficient alternative to moderate-intensity continuous training (MICT), leading to similar improvements in skeletal muscle capillary density and microvascular function in young healthy humans. In this study we made the first comparisons of the muscle microvascular response to SIT and MICT in an obese population. Sixteen young obese men (age 25 ± 1 years, BMI 34.8 ± 0.9 kg m-2) were randomly assigned to 4 weeks of MICT (40-60 min cycling at ∼65% V˙O2 peak , 5 times per week) or constant load SIT (4-7 constant workload intervals of 200% Wmax 3 times per week). Muscle biopsies were taken before and after training from the m. vastus lateralis to measure muscle microvascular endothelial eNOS content, eNOS serine1177 phosphorylation, NOX2 content and capillarisation using quantitative immunofluorescence microscopy. Maximal aerobic capacity (V˙O2 peak ), whole body insulin sensitivity and arterial stiffness were also assessed. SIT and MICT increased skeletal muscle microvascular eNOS content and eNOS ser1177 phosphorylation in terminal arterioles and capillaries (P < 0.05), but the latter effect was eliminated when normalised to eNOS content (P = 0.217). SIT and MICT also reduced microvascular endothelial NOX2 content (P < 0.05) and both increased capillary density and capillary-fibre perimeter exchange index (P < 0.05). In parallel, SIT and MICT increased V˙O2 peak (P < 0.05) and whole body insulin sensitivity (P < 0.05), and reduced central artery stiffness (P < 0.05). As no significant differences were observed between SIT and MICT it is concluded that SIT is a time efficient alternative to MICT to improve aerobic capacity, insulin sensitivity and muscle capillarisation and endothelial eNOS/NAD(P)Hoxidase protein ratio in young obese men.

What doesn’t kill you makes you fitter: A systematic review of high-intensity interval exercise for patients with cardiovascular and metabolic diseases

High-intensity interval exercise (HIIE) has gained popularity in recent years for patients with cardiovascular and metabolic diseases. Despite potential benefits, concerns remain about the safety of the acute response (during and/or within 24 hours postexercise) to a single session of HIIE for these cohorts. Therefore, the aim of this study was to perform a systematic review to evaluate the safety of acute HIIE for people with cardiometabolic diseases. Electronic databases were searched for studies published prior to January 2015, which reported the acute responses of patients with cardiometabolic diseases to HIIE (≥80% peak power output or ≥85% peak aerobic power, VO2peak). Eleven studies met the inclusion criteria (n = 156; clinically stable, aged 27-66 years), with 13 adverse responses reported (∼8% of individuals). The rate of adverse responses is somewhat higher compared to the previously reported risk during moderate-intensity exercise. Caution must be taken when prescribing HIIE to patients with cardiometabolic disease. Patients who wish to perform HIIE should be clinically stable, have had recent exposure to at least regular moderate-intensity exercise, and have appropriate supervision and monitoring during and after the exercise session.

Prediction interval-based modelling and control of nonlinear processes

 Novel computational intelligence-based methods have been investigated to quantify uncertainties prevalent in the operation of chemical plants. A new family of predication interval-based controlling algorithms is proposed and successfully applied to chemical reactors in order to minimise energy consumption and operational cost.

Low-volume high-intensity interval training in a gym setting improves cardio-metabolic and psychological health

Background Within a controlled laboratory environment, high-intensity interval training (HIT) elicits similar cardiovascular and metabolic benefits as traditional moderate-intensity continuous training (MICT). It is currently unclear how HIT can be applied effectively in a real-world environment. Purpose To investigate the hypothesis that 10 weeks of HIT, performed in an instructor-led, groupbased gym setting, elicits improvements in aerobic capacity (VO2max), cardio-metabolic risk and psychological health which are comparable to MICT. Methods Ninety physically inactive volunteers (42±11 y, 27.7±4.8 kg.m-2) were randomly assigned to HIT or MICT group exercise classes. HIT consisted of repeated sprints (15-60 seconds, >90% HRmax) interspersed with periods of recovery cycling (≥25 min.session-1, 3 sessions. week-1). MICT participants performed continuous cycling (70%HRmax, 30-45 min.session-1, 5 sessions.week-1). VO2max, markers of cardio-metabolic risk, and psychological health were assessed pre and post-intervention. Results Mean weekly training time was 55±10 (HIT) and 128±44 min (MICT) (p<0.05), with greater adherence to HIT (83±14% vs. 61±15% prescribed sessions attended, respectively; p<0.05). HIT improved VO2max, insulin sensitivity, reduced abdominal fat mass, and induced favourable changes in blood lipids (p<0.05). HIT also induced beneficial effects on health perceptions, positive and negative affect, and subjective vitality (p<0.05). No difference between HIT and MICT was seen for any of these variables. Conclusions HIT performed in a real-world gym setting improves cardio-metabolic risk factors and psychological health in physically inactive adults. With a reduced time commitment and greater adherence than MICT, HIT offers a viable and effective exercise strategy to target the growing incidence of metabolic disease and psychological ill-being associated with physical inactivity.

Prediction interval-based control of nonlinear systems using neural networks

Prediction interval (PI) is a promising tool for quantifying uncertainties associated with point predictions. Despite its informativeness, the design and deployment of PI-based controller for complex systems is very rare. As a pioneering work, this paper proposes a framework for design and implementation of PI-based controller (PIC) for nonlinear systems. Neural network (NN)-based inverse model within internal model control structure is used to develop the PIC. Firstly, a PI-based model is developed to construct PIs for the system output. This model is then used as an online estimator for PIs. The PIs from this model are fed to the NN inverse model along with other traditional inputs to generate the control signal. The performance of the proposed PIC is examined for two case studies. This includes a nonlinear batch polymerization reactor and a numerical nonlinear plant. Simulation results demonstrated that the proposed PIC tracking performance is better than the traditional NN-based controller.

High-intensity interval training for improving health-related fitness in adolescents: a systematic review and meta-analysis

BACKGROUND: High-intensity interval training (HIIT) may be a feasible and efficacious strategy for improving health-related fitness in young people. The objective of this systematic review and meta-analysis was to evaluate the utility of HIIT to improve health-related fitness in adolescents and to identify potential moderators of training effects. METHODS: Studies were considered eligible if they: (1) examined adolescents (13-18 years); (2) examined health-related fitness outcomes; (3) involved an intervention of ≥4 weeks in duration; (4) included a control or moderate intensity comparison group; and (5) prescribed high-intensity activity for the HIIT condition. Meta-analyses were conducted to determine the effect of HIIT on health-related fitness components using Comprehensive Meta-analysis software and potential moderators were explored (ie, study duration, risk of bias and type of comparison group). RESULTS: The effects of HIIT on cardiorespiratory fitness and body composition were large, and medium, respectively. Study duration was a moderator for the effect of HIIT on body fat percentage. Intervention effects for waist circumference and muscular fitness were not statistically significant. CONCLUSIONS: HIIT is a feasible and time-efficient approach for improving cardiorespiratory fitness and body composition in adolescent populations.

Preliminary efficacy and feasibility of embedding high intensity interval training into the school day: A pilot randomized controlled trial

Current physical activity and fitness levels among adolescents are low, increasing the risk of chronic disease. Although the efficacy of high intensity interval training (HIIT) for improving metabolic health is now well established, it is not known if this type of activity can be effective to improve adolescent health. The primary aim of this study is to assess the effectiveness and feasibility of embedding HIIT into the school day. A 3-arm pilot randomized controlled trial was conducted in one secondary school in Newcastle, Australia. Participants (n = 65; mean age = 15.8(0.6) years) were randomized into one of three conditions: aerobic exercise program (AEP) (n = 21), resistance and aerobic exercise program (RAP) (n = 22) and control (n = 22). The 8-week intervention consisted of three HIIT sessions per week (8-10 min/session), delivered during physical education (PE) lessons or at lunchtime. Assessments were conducted at baseline and post-intervention to detect changes in cardiorespiratory fitness (multi-stage shuttle-run), muscular fitness (push-up, standing long jump tests), body composition (Body Mass Index (BMI), BMI-z scores, waist circumference) and physical activity motivation (questionnaire), by researchers blinded to treatment allocation. Intervention effects for outcomes were examined using linear mixed models, and Cohen's d effect sizes were reported. Participants in the AEP and RAP groups had moderate intervention effects for waist circumference (p = 0.024), BMI-z (p = 0.037) and BMI (not significant) in comparison to the control group. A small intervention effect was also evident for cardiorespiratory fitness in the RAP group.

Concurrent exercise incorporating high-intensity interval or continuous training modulates mTORC1 signaling and microRNA expression in human skeletal muscle

We compared the effects of concurrent exercise, incorporating either high-intensity interval training (HIT) or moderate-intensity continuous training (MICT), on mechanistic target of rapamycin complex 1 (mTORC1) signaling and microRNA expression in skeletal muscle, relative to resistance exercise (RE) alone. Eight males (mean ± SD: age, 27 ± 4 yr; V̇o2 peak , 45.7 ± 9 ml·kg(-1)·min(-1)) performed three experimental trials in a randomized order: 1) RE (8 × 5 leg press repetitions at 80% 1-repetition maximum) performed alone and RE preceded by either 2) HIT cycling [10 × 2 min at 120% lactate threshold (LT); HIT + RE] or 3) work-matched MICT cycling (30 min at 80% LT; MICT + RE). Vastus lateralis muscle biopsies were obtained immediately before RE, either without (REST) or with (POST) preceding endurance exercise and +1 h (RE + 1 h) and +3 h (RE + 3 h) after RE. Prior HIT and MICT similarly reduced muscle glycogen content and increased ACC(Ser79) and p70S6K(Thr389) phosphorylation before subsequent RE (i.e., at POST). Compared with MICT, HIT induced greater mTOR(Ser2448) and rps6(Ser235/236) phosphorylation at POST. RE-induced increases in p70S6K and rps6 phosphorylation were not influenced by prior HIT or MICT; however, mTOR phosphorylation was reduced at RE + 1 h for MICT + RE vs. both HIT + RE and RE. Expression of miR-133a, miR-378, and miR-486 was reduced at RE + 1 h for HIT + RE vs. both MICT + RE and RE. Postexercise mTORC1 signaling following RE is therefore not compromised by prior HIT or MICT, and concurrent exercise incorporating HIT, but not MICT, reduces postexercise expression of miRNAs implicated in skeletal muscle adaptation to RE.

High-intensity interval training on cognitive and mental health in adolescents

PURPOSE: Emerging literature suggests that physical activity and fitness may have a positive impact on cognitive and mental health for adolescents. The purpose of the current study was to evaluate the efficacy of two high intensity interval training (HIIT) protocols for improving cognitive and mental health outcomes (executive function, psychological wellbeing, psychological distress and physical self-concept) in adolescents.

METHODS: Participants (n=65; mean age=15.8±0.6) were randomized to three conditions: aerobic exercise program (AEP; n=21), resistance and aerobic exercise program (RAP; n=22) and control (n=22). HIIT sessions (8-10min/session) were delivered during physical education lessons or at lunchtime three times/week for 8-weeks. Assessments were conducted at baseline and immediate post-intervention to detect changes in executive function (Trail Making Test, TMT), psychological wellbeing, psychological distress and physical self-description, by researchers blinded to treatment allocation. Intervention effects were examined using linear mixed models. Cohen's d effect sizes and clinical inference were also calculated.

RESULTS: Small improvements in executive function (d=-0.32, 95%CI -9.12 to 9.77; p=0.386) and psychological wellbeing (d=0.34, 95%CI -1.73 to 2.37; p=0.252) were evident in the AEP group. Moderate improvements in executive function (d=-0.51, 95% CI -8.92 to 9.73; p=0.171), and small improvements in wellbeing (d=0.35, 95%CI -1.46 to 2.53; p=0.219) and perceived appearance (d=0.35, 95%CI -0.74 to 0.41; p=0.249), were observed for the RAP group. Mean feelings state scores improved from pre-workout to post-post workout in both HIIT conditions, with significant results for the AEP (p=0.001).

CONCLUSIONS: This study highlights the potential of embedding HIIT within the school day for improving cognitive and mental health among adolescents.

Reachable sets bounding for generalized neural networks with interval time-varying delay and bounded disturbances

This paper deals with the problem of finding outer bound of forwards reachable sets and interbound of backwards reachable sets of generalized neural network systems with interval nondifferentiable time-varying delay and bounded disturbances. Based on constructing a suitable Lyapunov–Krasovskii functional and utilizing some improved Jensen integral-based inequalities, two sufficient conditions are derived for the existence of: (1) the smallest possible outer bound of forwards reachable sets and (2) the largest possible interbound of backwards reachable sets. These conditions are delay dependent and in the form of matrix inequalities, which therefore can be efficiently solved by using existing convex algorithms. Three numerical examples with simulation results are provided to demonstrate the effectiveness of our results.