Data visualization with simultaneous feature selection

Data visualization algorithms and feature selection techniques are both widely used in bioinformatics but as distinct analytical approaches. Until now there has been no method of measuring feature saliency while training a data visualization model. We derive a generative topographic mapping (GTM) based data visualization approach which estimates feature saliency simultaneously with the training of the visualization model. The approach not only provides a better projection by modeling irrelevant features with a separate noise model but also gives feature saliency values which help the user to assess the significance of each feature. We compare the quality of projection obtained using the new approach with the projections from traditional GTM and self-organizing maps (SOM) algorithms. The results obtained on a synthetic and a real-life chemoinformatics dataset demonstrate that the proposed approach successfully identifies feature significance and provides coherent (compact) projections. © 2006 IEEE.

Stock selection with full-scale optimization and differential evolution

When composing stock portfolios, managers frequently choose among hundreds of stocks. The stocks' risk properties are analyzed with statistical tools, and managers try to combine these to meet the investors' risk profiles. A recently developed tool for performing such optimization is called full-scale optimization (FSO). This methodology is very flexible for investor preferences, but because of computational limitations it has until now been infeasible to use when many stocks are considered. We apply the artificial intelligence technique of differential evolution to solve FSO-type stock selection problems of 97 assets. Differential evolution finds the optimal solutions by self-learning from randomly drawn candidate solutions. We show that this search technique makes large scale problem computationally feasible and that the solutions retrieved are stable. The study also gives further merit to the FSO technique, as it shows that the solutions suit investor risk profiles better than portfolios retrieved from traditional methods.

Editorial : which weight loss diet?

Full editorial: A recent study evaluating the long-term (2 yr) weight reducing efficacy of different types of diets – high or low in carbohydrates (CHOs), protein or fat - confirmed that it is calorie deficit not dietary composition that determines the loss and maintenance of body weight.1 Is there any advantage in following a specific weight loss diet? Short-term use of nutritionally complete commercially available (very) low calorie diets has benefited people with diabetes when  supported by education programmes.2 Initial weight loss has been encouraging with some fad diets eg the Atkins and the South Beach diets, but these diets are difficult to maintain and there are safety issues regarding their short- and long-term use – especially in people with diabetes.3 The types of macronutrients consumed can have a considerable impact on glycaemic control and energy metabolism. Although a low CHO diet additionally enhances initial weight loss by reducing cellular water content, if fat is not proportionally reduced the diet may not benefit the lipid profile for vascular disease risk. High fat and high protein diets – which are simultaneously low in CHOs – increase vulnerability to hypoglycaemia in people taking insulin secretagogues or on insulin therapy, and may promote excess fat metabolism and ketogenesis, particularly in people vulnerable to lack of insulin. Very low protein diets are not recommended as lean body mass tends to be reduced in diabetes. Altering the macronutrient balance has implications for the micronutrient mix: deficiencies are higher if more foods are excluded and conversely specific micronutrient excess can occur with some fad diets. The altered nutrient mix affects intestinal fauna and flora, and gut motility and glycaemic control are influenced by the quantity and type of fibre consumed. Support programmes help individuals achieve long term weight loss and there is mounting evidence that community schemes which educate and promote lifestyle changes may stem the rising tide of obesity and consequent type 2 diabetes.4 Consuming smaller portions of a balanced diet (and adjusting antidiabetic medications accordingly) will create an energy deficit to promote healthy weight loss. Increased movement/exercise will enhance this energy deficit. Knowledge (eg 1g fat has 2.25 times more energy than 1g CHO) allows sensible food choices and compensation for inclusion of small volumes of  ‘naughty but nice’ foods. Ultimately weight control requires self control. References 1. Sacks FM, Bray GA, Carey VJ et al. Comparison of weight-loss diets with different compositions of fat, protein, and carbohydrates. N Engl J Med 2009;360:859–73. 2. Bennett P. Obesity, diabetes and VLCD. Br J Diabetes Vasc Dis 2004;4:328–30. 3. Baldwin EJ. Fad diets in diabetes. Br J Diabetes Vasc DIs 2004;4:333–7. 4. Romon M, Lommoz A, Tafflet M et al. Downward trends in the prevalence of childhood overweight in the setting of 12-year school- and community-based programmes. Public Health Nutr 2008; Dec 28, 1–8 [Epub ahead of print].

Designing a mobile diet diary application with and for older adults with AMD:a case ctudy

Age-Related Macular Degeneration (AMD) is the UK’s leading cause of severe visual impairment amongst the elderly. It accounts for 16,000 blind/partial sight registrations per year and is the leading cause of blindness among people aged 55 years and older in western countries (Bressler, 2004). Our research aims to design and develop a self-monitoring, ability-reactive technology (SMART) for users with AMD to support their dietary-based AMD risk mitigation and progression retardation over time. In this paper, we reflect on our experience of adapting and applying a participatory design (PD) approach to support the effective design of our application with and for older adults with AMD. We introduce the outcome of a series of PD sessions with older adults with AMD - that is, a paper prototype of our proposed application which focuses on accessibility for our target users - and discuss implications for the eventual prototype development

A novel adaptive weight selection algorithm for multi-objective multi-agent reinforcement learning

To solve multi-objective problems, multiple reward signals are often scalarized into a single value and further processed using established single-objective problem solving techniques. While the field of multi-objective optimization has made many advances in applying scalarization techniques to obtain good solution trade-offs, the utility of applying these techniques in the multi-objective multi-agent learning domain has not yet been thoroughly investigated. Agents learn the value of their decisions by linearly scalarizing their reward signals at the local level, while acceptable system wide behaviour results. However, the non-linear relationship between weighting parameters of the scalarization function and the learned policy makes the discovery of system wide trade-offs time consuming. Our first contribution is a thorough analysis of well known scalarization schemes within the multi-objective multi-agent reinforcement learning setup. The analysed approaches intelligently explore the weight-space in order to find a wider range of system trade-offs. In our second contribution, we propose a novel adaptive weight algorithm which interacts with the underlying local multi-objective solvers and allows for a better coverage of the Pareto front. Our third contribution is the experimental validation of our approach by learning bi-objective policies in self-organising smart camera networks. We note that our algorithm (i) explores the objective space faster on many problem instances, (ii) obtained solutions that exhibit a larger hypervolume, while (iii) acquiring a greater spread in the objective space.

Self Evolving Character Recognition Using Genetic Operators

In this paper, a novel approach for character recognition has been presented with the help of genetic operators which have evolved from biological genetics and help us to achieve highly accurate results. A genetic algorithm approach has been described in which the biological haploid chromosomes have been implemented using a single row bit pattern of 315 values which have been operated upon by various genetic operators. A set of characters are taken as an initial population from which various new generations of characters are generated with the help of selection, crossover and mutation. Variations of population of characters are evolved from which the fittest solution is found by subjecting the various populations to a new fitness function developed. The methodology works and reduces the dissimilarity coefficient found by the fitness function between the character to be recognized and members of the populations and on reaching threshold limit of the error found from dissimilarity, it recognizes the character. As the new population is being generated from the older population, traits are passed on from one generation to another. We present a methodology with the help of which we are able to achieve highly efficient character recognition.

Self-adaptive probabilistic roadmap generation for intelligent virtual agents

Agents inhabiting large scale environments are faced with the problem of generating maps by which they can navigate. One solution to this problem is to use probabilistic roadmaps which rely on selecting and connecting a set of points that describe the interconnectivity of free space. However, the time required to generate these maps can be prohibitive, and agents do not typically know the environment in advance. In this paper we show that the optimal combination of different point selection methods used to create the map is dependent on the environment, no point selection method dominates. This motivates a novel self-adaptive approach for an agent to combine several point selection methods. The success rate of our approach is comparable to the state of the art and the generation cost is substantially reduced. Self-adaptation therefore enables a more efficient use of the agent's resources. Results are presented for both a set of archetypal scenarios and large scale virtual environments based in Second Life, representing real locations in London.

Self-adaptive volunteered services composition through stimulus-and time-awareness

Volunteered Service Composition (VSC) refers to the process of composing volunteered services and resources. These services are typically published to a pool of voluntary resources. Selection and composition decisions tend to encounter numerous uncertainties: service consumers and applications have little control of these services and tend to be uncertain about their level of support for the desired functionalities and non-functionalities. In this paper, we contribute to a self-awareness framework that implements two levels of awareness, Stimulus-awareness and Time-awareness. The former responds to basic changes in the environment while the latter takes into consideration the historical performance of the services. We have used volunteer service computing as an example to demonstrate the benefits that self-awareness can introduce to self-adaptation. We have compared the Stimulus-and Time-awareness approaches with a recent Ranking approach from the literature. The results show that the Time-awareness level has the advantage of satisfying higher number of requests with lower time cost.

A longitudinal evaluation of the acceptability and impact of a diet diary app for older adults with age-related macular degeneration

Ongoing advances in technology are increasing the scope for enhancing and supporting older adults’ daily living. The digital divide between older and younger adults raises concerns, however, about the suitability of technological solutions for older adults, especially for those with impairments. Taking older adults with Age-Related Macular Degeneration (AMD) as a case study, we used user-centred and participatory design approaches to develop an assistive mobile app for self-monitoring their intake of food [12,13]. In this paper we report on findings of a longitudinal field evaluation of our app that was conducted to investigate how it was received and adopted by older adults with AMD and its impact on their lives. Demonstrating the benefit of applying inclusive design methods for technology for older adults, our findings reveal how the use of the app raises participants’ awareness and facilitates self-monitoring of diet, encourages positive (diet) behaviour change, and encourages learning.

Is pregnancy a teachable moment for diet and physical activity behaviour change? An interpretative phenomenological analysis of the experiences of women during their first pregnancy

OBJECTIVES: Pregnancy may provide a 'teachable moment' for positive health behaviour change, as a time when women are both motivated towards health and in regular contact with health care professionals. This study aimed to investigate whether women's experiences of pregnancy indicate that they would be receptive to behaviour change during this period. DESIGN: Qualitative interview study. METHODS: Using interpretative phenomenological analysis, this study details how seven women made decisions about their physical activity and dietary behaviour during their first pregnancy. RESULTS: Two women had required fertility treatment to conceive. Their behaviour was driven by anxiety and a drive to minimize potential risks to the pregnancy. This included detailed information seeking and strict adherence to diet and physical activity recommendations. However, the majority of women described behaviour change as 'automatic', adopting a new lifestyle immediately upon discovering their pregnancy. Diet and physical activity were influenced by what these women perceived to be normal or acceptable during pregnancy (largely based on observations of others) and internal drivers, including bodily signals and a desire to retain some of their pre-pregnancy self-identity. More reasoned assessments regarding benefits for them and their baby were less prevalent and influential. CONCLUSIONS: Findings suggest that for women who conceived relatively easily, diet and physical activity behaviour during pregnancy is primarily based upon a combination of automatic judgements, physical sensations, and perceptions of what pregnant women are supposed to do. Health professionals and other credible sources appear to exert less influence. As such, pregnancy alone may not create a 'teachable moment'. Statement of contribution What is already known on this subject? Significant life events can be cues to action with relation to health behaviour change. However, much of the empirical research in this area has focused on negative health experiences such as receiving a false-positive screening result and hospitalization, and in relation to unequivocally negative behaviours such as smoking. It is often suggested that pregnancy, as a major life event, is a 'teachable moment' (TM) for lifestyle behaviour change due to an increase in motivation towards health and regular contact with health professionals. However, there is limited evidence for the utility of the TM model in predicting or promoting behaviour change. What does this study add? Two groups of women emerged from our study: the women who had experienced difficulties in conceiving and had received fertility treatment, and those who had conceived without intervention. The former group's experience of pregnancy was characterized by a sense of vulnerability and anxiety over sustaining the pregnancy which influenced every choice they made about their diet and physical activity. For the latter group, decisions about diet and physical activity were made immediately upon discovering their pregnancy, based upon a combination of automatic judgements, physical sensations, and perceptions of what is normal or 'good' for pregnancy. Among women with relatively trouble-free conception and pregnancy experiences, the necessary conditions may not be present to create a 'teachable moment'. This is due to a combination of a reliance on non-reflective decision-making, perception of low risk, and little change in affective response or self-concept.

Linking herbivory and pollination: Costs and selection implications in Centrosema virginianum Bentham (Fabaceae: Papilionoideae)

This research first evaluated levels and type of herbivory experienced by Centrosema virginianum plants in their native habitat and how florivory affected the pollinator activity. I found that populations of C. virginianum in two pine rockland habitat fragments experienced higher herbivory levels (15% and 22%) compared with plants in the protected study site (8.6%). I found that bees (Hymenoptera) pollinated butterfly pea. Furthermore, I found that florivores had a negative effect in the pollinators visitation rates and therefore in the seed set of the population. ^ I then conducted a study using a greenhouse population of C. virginianum. I applied artificial herbivory treatments: control, mild herbivory and severe herbivory. Flower size, pollen produced, ovules produced and seeds produced were negatively affected by herbivory. I did not find difference in nectar volume and quality by flowers among treatments. Surprisingly, severely damaged plants produced flowers with larger pollen than those from mildly damaged and undamaged plants. Results showed that plants tolerated mild and severe herbivory with 6% and 17% reduction of total fitness components, respectively. However, the investment of resources was not equisexual. ^ A comparison in the ability of siring seeds between large and small pollen was necessary to establish the biological consequence of size in pollen performance. I found that fruits produced an average of 18.7 ± 1.52 and 17.7 ± 1.50 from large and small pollen fertilization respectively. These findings supported a pollen number-size trade-off in plants under severe herbivory treatments. As far as I know, this result has not previously been reported. ^ Lastly, I tested how herbivory influenced seed abortion patterns in plants, examining how resources are allocated on different regions within fruits under artificial herbivory treatments. I found that self-fertilized fruits had greater seed abortion rates than cross-fertilized fruits. The proportion of seeds aborted was lower in the middle regions of the fruits in cross-fertilized fruits, producing more vigorous progeny. Self-fertilized fruits did not show patterns of seedling vigor. I also found that early abortion was higher closer to the peduncular end of the fruits. Position of seeds within fruits could be important in the seed dispersion mechanism characteristic of this species. ^

Impact of a cognitive-behavioral weight control program on body weight, diet quality, and smoking cessation in weight-concerned female smokers

Many people use smoking as a weight control mechanism and do not want to quit because they fear weight gain. These weight-concerned smokers tend to be female, are significantly less likely to stop smoking, are less likely to join smoking cessation programs, and will relapse more often than smokers who are not weight-concerned. Research suggests that a woman’s confidence in her ability to control her weight after quitting relates positively with her intention to quit smoking. Likewise, success in smoking cessation has been associated with increased self-efficacy for weight control. It has been shown that success in changing one negative health behavior may trigger success in changing another, causing a synergistic effect. Recently research has focused on interventions for weight-concerned smokers who are ready to quit smoking. The present study investigated the effect of a cognitive based weight control program on self-efficacy for weight control and the effect on smoking behavior for a group of female weight concerned smokers. Two hundred and sixteen subjects who wanted to lose weight but who were not ready to quit smoking were recruited to participate in a 12-week, cognitive-behavioral weight control program consisting of twelve one-hour sessions. Subjects were randomly assigned to either (1) the weight-control program (intervention group), or (2) the control group. Results of this study demonstrated that subjects in the intervention group increased self-efficacy for weight control, which was associated with improved healthy eating index scores, weight loss, increased self-efficacy for quitting smoking, a decrease in number of cigarettes smoked and triggered positive movement in stage of change towards smoking cessation compared to the control subjects. For these subjects, positive changes in self-efficacy for one behavior (weight control) appeared to have a positive effect on their readiness to change another health behavior (smoking cessation). Further study of the psychological variables that influence weight-concerned female smokers’ decisions to initiate changes in these behaviors and their ability to maintain those changes are warranted.

Selection and passage of county land preservation voter referendum: The role of government

County jurisdictions in America are increasingly exercising self-government in the provision of public community services through the context of second order federalism. In states exercising this form of contemporary governance, county governments with "reformed" policy-making structures and professional management practices, have begun to rival or surpass municipalities in the delivery of local services with regional implications such as environmental protection (Benton 2002, 2003; Marando and Reeves, 1993). ^ The voter referendum, a form of direct democracy, is an important component of county land preservation and environmental protection governmental policies. The recent growth and success of land preservation voter referendums nationwide reflects an increase in citizen participation in government and their desire to protect vacant land and its natural environment from threats of over-development, urbanization and sprawl, loss of open space and farmland, deterioration of ecosystems, and inadequate park and recreational amenities. ^ The study's design employs a sequential, mixed method. First, a quantitative approach employs the Heckman two-step model. It is fitted with variables for the non-random sample of 227 voter referendum counties and all non-voter referendum counties in the U.S. from 1988 to 2009. Second, the qualitative data collected from the in-depth investigation of three South Florida county case studies with twelve public administrator interviews is transformed for integration with the quantitative findings. The purpose of the qualitative method is to complement, explain and enrich the statistical analysis of county demographic, socio-economic, terrain, regional, governance and government, political preference, environmentalism, and referendum-specific factors. ^ The research finds that government factors are significant in terms of the success of land preservation voter referendums; more specifically, the presence of self-government authority (home rule charter), a reformed structure (county administrator/manager or elected executive), and environmental interest groups. In addition, this study concludes that successful counties are often located coastal, exhibit population and housing growth, and have older and more educated citizens who vote democratic in presidential elections. The analysis of case study documents and public administrator interviews finds that pragmatic considerations of timing, local politics and networking of regional stakeholders are also important features of success. Further research is suggested utilizing additional public participation, local government and public administration factors.^

Quality of life and application of the transtheoretical model to diabetes self -management behaviors in older adults with type 2 diabetes

One in five adults 65 years and older has diabetes. Coping with diabetes is a lifelong task, and much of the responsibility for managing the disease falls upon the individual. Reports of non-adherence to recommended treatments are high. Understanding the additive impact of diabetes on quality of life issues is important. The purpose of this study was to investigate the quality of life and diabetes self-management behaviors in ethnically diverse older adults with type 2 diabetes. The SF-12v2 was used to measure physical and mental health quality of life. Scores were compared to general, age sub-groups, and diabetes-specific norms. The Transtheoretical Model (TTM) was applied to assess perceived versus actual behavior for three diabetes self-management tasks: dietary management, medication management, and blood glucose self-monitoring. Dietary intake and hemoglobin A1c values were measured as outcome variables. Utilizing a cross-sectional research design, participants were recruited from Elderly Nutrition Program congregate meal sites (n = 148, mean age 75). ^ Results showed that mean scores of the SF-12v2 were significantly lower in the study sample than the general norms for physical health (p < .001), mental health (p < .01), age sub-group norms (p < .05), and diabetes-specific norms for physical health (p < .001). A multiple regression analysis found that adherence to an exercise plan was significantly associated with better physical health (p < .001). Transtheoretical Model multiple regression analyses explained 68% of the variance for % Kcal from fat, 41% for fiber, 70% for % Kcal from carbohydrate, and 7% for hemoglobin A 1c values. Significant associations were found between TTM stage of change and dietary fiber intake (p < .01). Other significant associations related to diet included gender (p < .01), ethnicity (p < .05), employment (p < .05), type of insurance (p < .05), adherence to an exercise plan (p < .05), number of doctor visits/year ( p < .01), and physical health (p < .05). Significant associations were found between hemoglobin A1c values and age ( p < .05), being non-Hispanic Black (p < .01), income (p < .01), and eye problems (p < .05). ^ The study highlights the importance of the beneficial effects of exercise on quality of life issues. Furthermore, application of the Transtheoretical Model in conjunction with an assessment of dietary intake may be valuable in helping individuals make lifestyle changes. ^

The relationship of spirituality and the health promoting behaviors of diet and exercise of African -American women

Public health data show that African-Americans have not adopted health-promoting behaviors of diet and exercise. Spirituality, important in the lives of many African-American women, may be associated with health-promoting behaviors. This study was designed to determine how spirituality relates to health-promoting behaviors in African-American women. Burkhardt's theoretical framework for spirituality was adopted and measures were selected for the three elements of the framework: connectedness with self, others, and environment. ^ The study used a descriptive cross sectional correlational design to investigate the relationships of the independent variables of spirituality, sociodemographics, and BMI, to the dependent variables of diet and exercise, to answer the two primary questions: What is the role of spirituality in impacting the health-promoting behaviors of African-American women? Of the independent variables of spirituality, sociodemographics, and BMI, which are the best predictors of diet and exercise? ^ Central and South Floridian African-American women (n = 260) between 18 and 82 years of age completed several questionnaires: Rosenberg's Self-Esteem Scale, Health Promoting Lifestyle Profile II, Spiritual Perspective Scale, Brief Block Food Frequency, and socio-demographic information. ^ Hierarchical regression identified 40% of the variability of diet to be explained by socio-demographic (education) and spirituality variables (stress management and health responsibility) (p < .001). Twenty-nine percent of the variability of exercise was explained by socio-demographic (education) and spirituality variables (stress management) (p < .001). Canonical correlation analysis identified a significant pair of canonical variates which indicated individuals with good nutrition (.95), increased physical activity (.79), and healthy eating (.42) also had better stress management (.88), better health responsibility (.67), higher spiritual growth (.66), better interpersonal relations (.50), more education (.49), and higher self-esteem (.33). The set explained 57% of the variability (p < .001). ^ An understanding of the factors that influence these women's decision to utilize health-promoting strategies could provide health professionals with additional information to enable them to design culturally and spiritually related health messages for African-American women. The findings of this present study speak of the importance of focusing on stress management, health responsibility, spiritual growth, interpersonal relations and self-esteem along with diet and exercise; this will likely provide improvement in the health-promoting behaviors of African-American women. ^