An adaptive fuzzy min-max conflict-resolving classifier

This paper describes a novel adaptive network, which agglomerates a procedure based on the fuzzy min-max clustering method, a supervised ART (Adaptive Resonance Theory) neural network, and a constructive conflict-resolving algorithm, for pattern classification. The proposed classifier is a fusion of the ordering algorithm, Fuzzy ARTMAP (FAM) and the Dynamic Decay Adjustment (DDA) algorithm. The network, called Ordered FAMDDA, inherits the benefits of the trio, viz . an ability to identify a fixed order of training pattern presentation for good generalisation; stable and incrementally learning architecture; and dynamic width adjustment of the weights of hidden nodes of conflicting classes. Classification performance of the Ordered FAMDDA is assessed using two benchmark datasets. The performances are analysed and compared with those from FAM and Ordered FAM. The results indicate that the Ordered FAMDDA classifier performs at least as good as the mentioned networks. The proposed Ordered FAMDDA network is then applied to a condition monitoring problem in a power generation station. The process under scrutiny is the Circulating Water (CW) system, with prime attention to condition monitoring of the heat transfer efficiency of the condensers. The results and their implications are analysed and discussed.

Boosting the performance of the fuzzy min-max neural network in pattern classification tasks

In this paper, a boosted Fuzzy Min-Max Neural Network (FMM) is proposed. While FMM is a learning algorithm which is able to learn new classes and to refine existing classes incrementally, boosting is a general method for improving accuracy of any learning algorithm. In this work, AdaBoost is applied to improve the performance of FMM when its classification results deteriorate from a perfect score. Two benchmark databases are used to assess the applicability of boosted FMM, and the results are compared with those from other approaches. In addition, a medical diagnosis task is employed to assess the effectiveness of boosted FMM in a real application. All the experimental results consistently demonstrate that the performance of FMM can be considerably improved when boosting is deployed.

Application of the fuzzy min-max neural network to fault detection and diagnosis of induction motors

In this paper, an application of the motor current signature analysis (MCSA) method and the fuzzy min–max (FMM) neural network to detection and classification of induction motor faults is described. The finite element method is employed to generate simulated data pertaining to changes in the stator current signatures under different motor conditions. The MCSA method is then used to process the stator current signatures. Specifically, the power spectral density is employed to extract harmonics features for fault detection and classification with the FMM network. Various types of induction motor faults, which include stator winding faults and eccentricity problems, under different load conditions are experimented. The results are analyzed and compared with those from other methods. The outcomes indicate that the proposed technique is effective for fault detection and diagnosis of induction motors under different conditions.

Transfer learning using the online Fuzzy Min-Max neural network

In this paper, we present an empirical analysis on transfer learning using the Fuzzy Min–Max (FMM) neural network with an online learning strategy. Three transfer learning benchmark data sets, i.e., 20 Newsgroups, WiFi Time, and Botswana, are used for evaluation. In addition, the data samples are corrupted with white Gaussian noise up to 50 %, in order to assess the robustness of the online FMM network in handling noisy transfer learning tasks. The results are analyzed and compared with those from other methods. The outcomes indicate that the online FMM network is effective for undertaking transfer learning tasks in noisy environments.

Joint resource allocation for max-min throughput in multicell networks

We investigate the resource-allocation problem in multicell networks targeting the max-min throughput of all cells. A joint optimization over power control, channel allocation, and user association is considered, and the problem is then formulated as a nonconvex mixed-integer nonlinear problem (MINLP). To solve this problem, we proposed an alternating-optimization-based algorithm, which applies branch-and-bound and simulated annealing in solving subproblems at each optimization step. We also demonstrate the convergence and efficiency of the proposed algorithms by thorough numerical experiments. The experimental results show that joint optimization over all resources outperforms the restricted optimization over individual resources significantly.

An enhanced fuzzy min-max neural network for pattern classification

An enhanced fuzzy min-max (EFMM) network is proposed for pattern classification in this paper. The aim is to overcome a number of limitations of the original fuzzy min-max (FMM) network and improve its classification performance. The key contributions are three heuristic rules to enhance the learning algorithm of FMM. First, a new hyperbox expansion rule to eliminate the overlapping problem during the hyperbox expansion process is suggested. Second, the existing hyperbox overlap test rule is extended to discover other possible overlapping cases. Third, a new hyperbox contraction rule to resolve possible overlapping cases is provided. Efficacy of EFMM is evaluated using benchmark data sets and a real medical diagnosis task. The results are better than those from various FMM-based models, support vector machine-based, Bayesian-based, decision tree-based, fuzzy-based, and neural-based classifiers. The empirical findings show that the newly introduced rules are able to realize EFMM as a useful model for undertaking pattern classification problems.

A modified fuzzy min-max neural network for data clustering and its application to power quality monitoring

When no prior knowledge is available, clustering is a useful technique for categorizing data into meaningful groups or clusters. In this paper, a modified fuzzy min-max (MFMM) clustering neural network is proposed. Its efficacy for tackling power quality monitoring tasks is demonstrated. A literature review on various clustering techniques is first presented. To evaluate the proposed MFMM model, a performance comparison study using benchmark data sets pertaining to clustering problems is conducted. The results obtained are comparable with those reported in the literature. Then, a real-world case study on power quality monitoring tasks is performed. The results are compared with those from the fuzzy c-means and k-means clustering methods. The experimental outcome positively indicates the potential of MFMM in undertaking data clustering tasks and its applicability to the power systems domain.

A mobile phone intervention increases physical activity in people with cardiovascular disease: Results from the HEART randomized controlled trial.

AIM: To determine the effectiveness and cost-effectiveness of a mobile phone intervention to improve exercise capacity and physical activity behaviour in people with ischaemic heart disease (IHD).

METHODS AND RESULTS: In this single-blind, parallel, two-arm, randomized controlled trial adults (n = 171) with IHD were randomized to receive a mobile phone delivered intervention (HEART; n = 85) plus usual care, or usual care alone (n = 86). Adult participants aged 18 years or more, with a diagnosis of IHD, were clinically stable as outpatients, able to perform exercise, able to understand and write English, and had access to the Internet. The HEART (Heart Exercise And Remote Technologies) intervention involved a personalized, automated package of text messages and a secure website with video messages aimed at increasing exercise behaviour, delivered over 24 weeks. All participants were able to access usual community-based cardiac rehabilitation, which involves encouragement of physical activity and an offer to join a local cardiac support club. All outcomes were assessed at baseline and 24 weeks and included peak oxygen uptake (PVO2; primary outcome), self-reported physical activity, health-related quality of life, self-efficacy and motivation (secondary outcomes). Results showed no differences in PVO2 between the two groups (difference -0.21 ml kg(-1)min(-1), 95% CI: -1.1, 0.7; p = 0.65) at 24 weeks. However significant treatment effects were observed for selected secondary outcomes, including leisure time physical activity (difference 110.2 min/week, 95% CI: -0.8, 221.3; p = 0.05) and walking (difference 151.4 min/week, 95% CI: 27.6, 275.2; p = 0.02). There were also significant improvements in self-efficacy to be active (difference 6.2%, 95% CI: 0.2, 12.2; p = 0.04) and the general health domain of the SF36 (difference 2.1, 95% CI: 0.1, 4.1; p = 0.03) at 24 weeks. The HEART programme was considered likely to be cost-effective for leisure time activity and walking.

CONCLUSIONS: A mobile phone intervention was not effective at increasing exercise capacity over and above usual care. The intervention was effective and probably cost-effective for increasing physical activity and may have the potential to augment existing cardiac rehabilitation services.

Effects of exercise on the desire to smoke and physiological responses to temporary smoking abstinence: a crossover trial

RATIONALE: Exercise has been shown to attenuate cigarette cravings during temporary smoking abstinence; however, the mechanisms of action are not clearly understood. OBJECTIVES: The objectives of the study were to compare the effects of three exercise intensities on desire to smoke and explore potential neurobiological mediators of desire to smoke. METHODS: Following overnight abstinence, 40 participants (25 males, 18-59 years) completed three 15 min sessions of light-, moderate-, or vigorous-intensity exercise on a cycle ergometer in a randomized crossover design. Ratings of desire to smoke were self-reported pre- and post-exercise and heart rate variability was measured throughout. Saliva and blood were analyzed for cortisol and noradrenaline in a sub-sample. RESULTS: Exercise influenced desire to smoke (F [2, 91] = 7.94, p < 0.01), with reductions greatest immediately after vigorous exercise. There were also significant time x exercise intensity interaction effects for heart rate variability and plasma noradrenaline (F [8, 72] = 2.23, p = 0.03), with a bias in noradrenaline occurring between light and vigorous conditions (adjusted mean difference [SE] = 2850 ng/ml [592], p < 0.01) at 5 min post-exercise. There was no interaction of time x exercise intensity for plasma and salivary cortisol levels. CONCLUSIONS: These findings support the use of vigorous exercise to reduce cigarette cravings, showing potential alterations in a noradrenergic marker.

Screen-time weight-loss intervention targeting children at home (SWITCH): a randomized controlled trial

BACKGROUND: Screen-based activities, such as watching television (TV), playing video games, and using computers, are common sedentary behaviors among young people and have been linked with increased energy intake and overweight. Previous home-based sedentary behaviour interventions have been limited by focusing primarily on the child, small sample sizes, and short follow-up periods. The SWITCH (Screen-Time Weight-loss Intervention Targeting Children at Home) study aimed to determine the effect of a home-based, family-delivered intervention to reduce screen-based sedentary behaviour on body composition, sedentary behaviour, physical activity, and diet over 24 weeks in overweight and obese children.

METHODS: A two-arm, parallel, randomized controlled trial was conducted. Children and their primary caregiver living in Auckland, New Zealand were recruited via schools, community centres, and word of mouth. The intervention, delivered over 20 weeks, consisted of a face-to-face meeting with the parent/caregiver and the child to deliver intervention content, which focused on training and educating them to use a wide range of strategies designed to reduce their child's screen time. Families were given Time Machine TV monitoring devices to assist with allocating screen time, activity packages to promote alternative activities, online support via a website, and monthly newsletters. Control participants were given the intervention material on completion of follow-up. The primary outcome was change in children's BMI z-score from baseline to 24 weeks.

RESULTS: Children (n = 251) aged 9-12 years and their primary caregiver were randomized to receive the SWITCH intervention (n = 127) or no intervention (controls; n = 124). There was no significant difference in change of zBMI between the intervention and control groups, although a favorable trend was observed (-0.016; 95% CI: -0.084, 0.051; p = 0.64). There were also no significant differences on secondary outcomes, except for a trend towards increased children's moderate intensity physical activity in the intervention group (24.3 min/d; 95% CI: -0.94, 49.51; p = 0.06).

CONCLUSIONS: A home-based, family-delivered intervention to reduce all leisure-time screen use had no significant effect on screen-time or on BMI at 24 weeks in overweight and obese children aged 9-12 years.

Validating the multimedia activity recall for children and adolescents in a large New Zealand sample

The aim of the study was to validate the self-report Multimedia Activity Recall for Children and Adolescents (MARCA) against accelerometry for the assessment of physical activity in New Zealand children. Participants (n = 716, 10-18 years) recalled 3-4 days of activity using the MARCA and underwent a partially overlapping 7-day accelerometry protocol during a national survey. Spearman correlation coefficients (ρ) assessed the association between accelerometer-derived counts per minute and MARCA-derived physical activity level and time in locomotion. Both data sources estimated time spent in light and moderate-vigorous physical activity. Association and agreement between methods for light physical activity and moderate-vigorous physical activity was assessed using correlations and Bland-Altman plots respectively, and paired t-tests conducted. Accelerometer-derived activity counts were moderately correlated with both MARCA-derived physical activity level and locomotion (ρ = 0.38, P < 0.0001). The correlation between methods was -0.14 for light physical activity and 0.28 for moderate-vigorous physical activity (P < 0.0001). The MARCA overestimated moderate-vigorous physical activity compared with accelerometry (120 min, P < 0.0001), which increased as moderate-vigorous physical activity time increased. Some sex and ethnicity (Māori [indigenous] versus non-Māori) differences were observed. Overall, the MARCA indicated moderate validity for assessment of physical activity level, locomotion and moderate-vigorous physical activity and poor validity for assessment of light physical activity. This was comparable to other self-report tools. The MARCA has utility for future large-scale research.

Effects of active video games on body composition: a randomized controlled trial

BACKGROUND: Sedentary activities such as video gaming are independently associated with obesity. Active video games, in which players physically interact with images on screen, may help increase physical activity and improve body composition.

OBJECTIVE: The aim of this study was to evaluate the effect of active video games over a 6-mo period on weight, body composition, physical activity, and physical fitness.

DESIGN: We conducted a 2-arm, parallel, randomized controlled trial in Auckland, New Zealand. A total of 322 overweight and obese children aged 10-14 y, who were current users of sedentary video games, were randomly assigned at a 1:1 ratio to receive either an active video game upgrade package (intervention, n = 160) or to have no change (control group, n = 162). The primary outcome was the change from baseline in body mass index (BMI; in kg/m(2)). Secondary outcomes were changes in percentage body fat, physical activity, cardiorespiratory fitness, video game play, and food snacking.

RESULTS: At 24 wk, the treatment effect on BMI (-0.24; 95% CI: -0.44, -0.05; P = 0.02) favored the intervention group. The change (±SE) in BMI from baseline increased in the control group (0.34 ± 0.08) but remained the same in the intervention group (0.09 ± 0.08). There was also evidence of a reduction in body fat in the intervention group (-0.83%; 95% CI: -1.54%, -0.12%; P = 0.02). The change in daily time spent playing active video games at 24 wk increased (10.03 min; 95% CI: 6.26, 13.81 min; P < 0.0001) with the intervention accompanied by a reduction in the change in daily time spent playing nonactive video games (-9.39 min; 95% CI: -19.38, 0.59 min; P = 0.06).

CONCLUSION: An active video game intervention has a small but definite effect on BMI and body composition in overweight and obese children.

Effect of electronic time monitors on children's television watching: pilot trial of a home-based intervention

OBJECTIVES: This pilot study evaluated the feasibility (recruitment, retention, and acceptability) and preliminary efficacy of a six-week home-based electronic time monitor intervention on New Zealand children's television watching in 2008. METHODS: Twenty-nine children aged 9 to 12 years who watched more than 20 h of television per week (62% male, mean age 10.4 years) were randomised to either the intervention or the control group. The intervention group received an electronic TV time monitor for 6 weeks and advice to restrict TV watching to 1 h per day or less. The control group was given verbal advice to restrict TV watching. RESULTS: Participant retention at 6 weeks was 93%. Semi-structured interviews with intervention families confirmed moderate acceptability of TV time monitors and several perceived benefits including better awareness of household TV viewing and improved time planning. Drawbacks reported included disruption to parents' TV watching and increased sibling conflict. Time spent watching television decreased by 4.2 h (mean change [SD]: -254 [536] min) per week in the intervention group compared with no change in the control group (-3 [241] min), but the difference between groups was not statistically significant, p=0.77. Both groups reported decreases in energy intake from snacks and total screen time and increases in physical activity measured by pedometer and between-group differences were not statistically significant. CONCLUSIONS: Electronic TV time monitors are feasible to use for home-based TV watching interventions although acceptability varies between families. Preliminary findings from this pilot suggest that such devices have potential to decrease children's TV watching but a larger trial is needed to confirm effectiveness. Future research should be family-orientated; take account of other screen time activities; and employ TV time monitors as just one of a range of strategies to decrease sedentary behaviour.

Couch potatoes to jumping beans: a pilot study of the effect of active video games on physical activity in children

The primary objective of this pilot study was to evaluate the effect of active video games on children's physical activity levels.Twenty children (mean +/- SD age = 12 +/- 1.5 years; 40% female) were randomised to receive either an active video game upgrade package or to a control group (no intervention). Effects on physical activity over the 12-week intervention period were measured using objective (Actigraph accelerometer) and subjective (Physical Activity Questionnaire for Children [PAQ-C]) measures. An activity log was used to estimate time spent playing active and non-active video games.Children in the intervention group spent less mean time over the total 12-week intervention period playing all video games compared to those in the control group (54 versus 98 minutes/day [difference = -44 minutes/day, 95% CI [-92, 2]], p = 0.06). Average time spent in all physical activities measured with an accelerometer was higher in the active video game intervention group compared to the control group (difference at 6 weeks = 194 counts/min, p = 0.04, and at 12 weeks = 48 counts/min, p = 0.06).This preliminary study suggests that playing active video games on a regular basis may have positive effects on children's overall physical activity levels. Further research is needed to confirm if playing these games over a longer period of time could also have positive effects on children's body weight and body mass index.

Photocatalytic degradation of bisphenol A by HMS/g-C3N4 composite

In this work, hexagonal mesoporous silica/g-C3N4 (HMS/C3N4) was synthesized by heating a mixture of self-prepared HMS and dicyandiamide. The as-prepared materials were characterized by transmission electron microscopy (TEM), X-ray diffractometer (XRD), Fourier transform infrared spectra (FT-IR) and Brunauer–Emmett–Teller analysis (BET). The prepared photocatalysts were applied to decompose bisphenol A (BPA) under UV light illumination. The mass ratios of HMS to melamine were optimized. The results showed that optimal mass ratios HMS to dicyandiamide was 1:1. Even though with the same catalyst dosage (1.0 g/L), the degradation kinetic rate constant of BPA over HMS/C3N4 (0.00526 min&minus;1) was 1.76 times and 1.4 times than those on P25 (0.00298 min&minus;1) and pure C3N4 (0.00383 min&minus;1), while the rate constant of photolysis was only 0.00021 min&minus;1. The enhanced photocatalytic activity of the HMS/C3N4 composite was ascribed to higher specific surface area and less aggregation compared to the pure C3N4. It is feasible and efficient to degrade BPA by HMS/C3N4 composite, which is easier to be separated than pure C3N4 after the pollutant has been removed completely.