Feature selection and the concept of immediate neighborhood in the context of clustering techniques

The concept of feature selection in a nonparametric unsupervised learning environment is practically undeveloped because no true measure for the effectiveness of a feature exists in such an environment. The lack of a feature selection phase preceding the clustering process seriously affects the reliability of such learning. New concepts such as significant features, level of significance of features, and immediate neighborhood are introduced which result in meeting implicitly the need for feature slection in the context of clustering techniques.

Feature selection and the concept of immediate neighborhood in the context of clustering techniques

The concept of feature selection in a nonparametric unsupervised learning environment is practically undeveloped because no true measure for the effectiveness of a feature exists in such an environment. The lack of a feature selection phase preceding the clustering process seriously affects the reliability of such learning. New concepts such as significant features, level of significance of features, and immediate neighborhood are introduced which result in meeting implicitly the need for feature slection in the context of clustering techniques.

Home and Workplace Built Environment Supports for Physical Activity

BACKGROUND: Physical inactivity has been associated with obesity and related chronic diseases. Understanding built environment (BE) influences on specific domains of physical activity (PA) around homes and workplaces is important for public health interventions to increase population PA.

PURPOSE: To examine the association of home and workplace BE features with PA occurring across specific life domains (work, leisure, and travel).

METHODS: Between 2012 and 2013, telephone interviews were conducted with participants in four Missouri metropolitan areas. Questions included sociodemographic characteristics, home and workplace supports for PA, and dietary behaviors. Data analysis was conducted in 2013; logistic regression was used to examine associations between BE features and domain-specific PA.

RESULTS: In home neighborhoods, seven of 12 BE features (availability of fruits and vegetables, presence of shops and stores, bike facilities, recreation facilities, crime rate, seeing others active, and interesting things) were associated with leisure PA. The global average score of home neighborhood BE features was associated with greater odds of travel PA (AOR=1.99, 95% CI=1.46, 2.72); leisure PA (AOR=1.84, 95% CI=1.44, 2.34); and total PA (AOR=1.41, 95% CI=1.04, 1.92). Associations between workplace neighborhoods' BE features and workplace PA were small but in the expected direction.

CONCLUSIONS: This study offers empirical evidence on BE supports for domain-specific PA. Findings suggest that diverse, attractive, and walkable neighborhoods around workplaces support walking, bicycling, and use of public transit. Public health practitioners, researchers, and worksite leaders could benefit by utilizing worksite domains and measures from this study for future BE assessments.

Body Mass Index and Neighborhood Socioeconomic Status in Washington State

Thesis (Master's)--University of Washington, 2015-12

Perceptions about the local neighborhood and walking and cycling among children

Background. This study examined associations between perceptions of the local neighborhood and walking and cycling among children. Methods. Children aged 5–6 years (n = 291) and 10–12 years (n = 919) were recruited from 19 Australian primary schools. Parents reported their child's usual walking or cycling to local destinations and their perceptions of their neighborhood. Ten- to twelve-year-olds were asked their perceptions of traffic, strangers, road safety and sporting venues, and their perceptions of their parent's views on these issues. Results. Five- to six-year-old boys whose parents believed there was heavy traffic in their area were 2.8 times more likely (95%CI = 1.1–6.8), and 5- to 6-year-old girls whose parents owned more than one car were 70% less likely (95%CI = 0.1–0.8), and whose parents believed that public transport was limited in their area were 60% less likely (95%CI = 0.2–0.9) than other children to walk or cycle at least three times per week. Parental belief that there were no lights or crossings was associated with walking or cycling among 10- to 12-year-old boys (OR = 0.4, 95%CI = 0.2–0.7). Among older girls, parent's belief that their child needed to cross several roads to reach play areas (OR = 0.4, 95%CI = 0.2–0.8) and that there is limited public transport in their area (OR = 0.7, 95%CI = 0.4–0.97), and child's belief that there were no parks or sports grounds near home (OR = 0.5, 95%CI = 0.3–0.8) were associated with a lower likelihood of walking or cycling. Conclusion. Perceptions of the local neighborhood may influence children's physical activity.

Children's perceptions of their home and neighborhood environments, and their association with objectively measured physical activity: A qualitative and quantitative study

Environmental factors may have an important influence on children’s physical activity, yet children’s perspectives of their home and neighborhood environments have not been widely assessed. The aim of this study was to investigate children’s perceptions of their environments, and to examine associations between these perceptions and objectively measured physical activity. The sample consisted of 147, 10-year-old Australian children, who drew maps of their home and neighborhood environments. A subsample of children photographed places and things in these environments that were important to them. The maps were analyzed for themes, and for the frequency with which particular objects and locations appeared. Physical activity was objectively measured using accelerometers. Six themes emerged from the qualitative analysis of the maps and photographs: the family home; opportunities for physical activity and sedentary pursuits; food items and locations; green space and outside areas; the school and opportunities for social interaction. Of the 11 variables established from these themes, one home and two neighborhood factors were associated with children’s physical activity. These findings contribute to a broader understanding of children’s perceptions of their environment, and highlight the potential importance of the home and neighborhood environments for promoting physical activity behavior.

Neighborhood walkability and the walking behavior of Australian adults

Background
The physical attributes of residential neighborhoods, particularly the connectedness of streets and the proximity of destinations, can influence walking behaviors. To provide the evidence for public health advocacy on activity-friendly environments, large-scale studies in different countries are needed. Associations of neighborhood physical environments with adults’ walking for transport and walking for recreation must be better understood.

Method
Walking for transport and walking for recreation were assessed with a validated survey among 2650 adults recruited from neighborhoods in an Australian city between July 2003 and June 2004, with neighborhoods selected to have either high or low walkability, based on objective measures of connectedness and proximity derived from geographic information systems (GIS) databases. The study design was stratified by area-level socioeconomic status, while analyses controlled for participant age, gender, individual-level socioeconomic status, and reasons for neighborhood self-selection.

Results
A strong independent positive association was found between weekly frequency of walking for transport and the objectively derived neighborhood walkability index. Preference for walkable neighborhoods moderated the relationship of walkability with weekly minutes, but not the frequency of walking for transport—walkability was related to higher frequency of transport walking, irrespective of neighborhood self-selection. There were no significant associations between environmental factors and walking for recreation.

Conclusions
Associations of neighborhood walkability attributes with walking for transport were confirmed in Australia. They accounted for a modest but statistically significant proportion of the total variation of the relevant walking behavior. The physical environment attributes that make up the walkability index are potentially important candidate factors for future environmental and policy initiatives designed to increase physical activity.

Neighborhood walkability and TV viewing time among Australian adults

Background
Built-environment attributes of a neighborhood are associated with participation in physical activity and may also influence time spent in sedentary behaviors. Associations of neighborhood walkability (based on dwelling density, street connectivity, land-use mix, and net retail area) and television viewing time were compared in a large, spatially-derived sample of Australian adults.

Methods
Neighborhood-level variables (walkability and socioeconomic status [SES]) were calculated in 154 Australian census collection districts using Geographic Information Systems. Individual-level variables (TV viewing time, time spent in leisure-time physical activity, height, weight, and sociodemographic variables) were collected from adults living in urban areas of Adelaide, Australia using a mail survey (N=2224) in 2003–2004. Multilevel linear regression analysis was conducted in 2006 separately for men and women to examine variations in TV viewing time across tertiles of walkability.

Results
Neighborhood walkability was negatively associated with TV viewing time in women, but not in men. After controlling for neighborhood SES, body mass index, physical activity, and sociodemographic variables, women living in medium- and high-walkable neighborhoods reported significantly less TV viewing time per day (14 minutes and 17 minutes, respectively) compared to those residing in low-walkable neighborhoods.

Conclusions
Built-environment attributes of neighborhoods that are related to physical activity also may play an important role in influencing sedentary behavior, particularly among women. Considering the effects of prolonged sedentary time on health risks, which are independent of physical activity, there is the need for further research to explore how environmental characteristics may contribute to the amount of time spent in sedentary behavior.

Development of a reliable measure of walking within and outside the local neighbourhood: RESIDE's neighborhood physical activity questionnarire.

Background: The RESIDential Environment project (RESIDE) is a longitudinal study evaluating the impact of a new residential design code on walking. Objective: To develop a reliable measure of walking – undertaken within and outside the neighborhood – and overall physical activity. Methods: A test–retest reliability study was undertaken (n = 82, mean age 39 years). The instrument was based on the International Physical Activity Questionnaire (IPAQ-short version) and Active Australia Survey. It measured usual frequency and duration of (1) recreational- and transport-related walking within and outside the neighborhood and (2) other vigorous and moderate physical activities. Results: Reliability of recall of whether participants had walked within (k = 0.84) and outside (0.73) the neighborhood was acceptable. Similarly, recall of frequency and duration of transport and recreational-related walking within the neighborhood was excellent (ICC ≥ 0.82), as was recall of transport-related walking trips outside the neighborhood (ICC ≥ 0.84). Reliability for duration of recreational walking outside the neighborhood was fair to good (ICC = 0.55). The reliability of indices of total physical activity based on MET min/week (ICC = 0.82) and MET min/week dichotomized to ‘sufficient’ physical activity for health (kappa = 0.67) were both acceptable. Conclusions:  The Neighborhood Physical Activity Questionnaire (NPAQ) is sufficiently reliable for studies examining environmental correlates of walking within the neighborhood.

Perceived environment attributes, residential locaction, and walking for particular purposes

Background
Identifying environmental factors that can influence physical activity is a public health priority. We examined associations of perceived environmental attributes with walking for four different purposes: general neighborhood walking, walking for exercise, walking for pleasure, and walking to get to and from places.

Methods
Participants (n =399; 57% women) were surveyed by mail. They reported place of residence, walking behaviors, and perceptions of neighborhood environmental attributes.

Results
Men with the most positive perceptions of neighborhood “aesthetics” were significantly more likely (odds ratio [OR]=7.4) to be in the highest category of neighborhood walking. Men who perceived the weather as not inhibiting their walking were much more likely (OR=4.7) to be high exercise walkers. Women who perceived the weather as not inhibiting their walking were significantly more likely to be high neighborhood walkers (OR=3.8) and those with moderate perceptions of “accessibility” were much more likely to do more walking for pleasure (OR=3.5).

Conclusions
Different environmental attributes were associated with different types of walking and these differed between men and women. Approaches to increasing physical activity might usefully focus on those attributes of the local environment that might influence particular subsets of walking behavior.

Perceptions of neighborhood safety and physical activity among youth : the CLAN study

Background: The purpose of this study was to examine associations between perceptions of neighborhood safety and physical activity among youth. Methods: We completed a cross-sectional study of children age 8 to 9 years (n = 188) and adolescents age 13 to 15 years (n = 346) in areas of varying socioeconomic status in Melbourne, Australia. Parents and adolescents completed questionnaires on perceptions of neighborhood safety. Scores were computed for perceptions of road safety, incivilities, and personal safety of the child or adolescent. Moderate-to-vigorous physical activity (MVPA) before or after school, on evenings, and on weekends was recorded using accelerometers. Results: There were no associations between parental perceptions of neighborhood safety and children’s MVPA outside school hours. Parental perception of personal safety was positively associated with adolescent boys’ MVPA after school. Adolescent girls’ concern about road safety was negatively associated with their MVPA during evenings and outside school hours. Conclusion: Perceptions of neighborhood safety might influence physical activity among youth in different ways according to age group and sex.

Neighborhood road environments and physical activity among youth : the CLAN Study

We examined associations between objective measures of the local road environment and physical activity (including active transport) among youth. There is little empirical evidence of the impact of the road environment on physical activity among children/adolescents in their neighborhoods. Most recent studies have examined perceptions rather than objective measures of the road environment. This was a cross-sectional study of children aged 8–9 years (n = 188) and adolescents aged 13–15 years (n  = 346) who were participants in the 3-year follow-up of the Children Living in Active Neighborhoods (CLAN) longitudinal study in Melbourne, Australia. At baseline (2001), they were recruited from 19 state primary schools in areas of varying socioeconomic status across Melbourne. Habitual walking/cycling to local destinations was parent-reported for children and self-reported for adolescents, while moderate-to-vigorous physical activity (MVPA) outside school hours was recorded using accelerometers. Road environment features in each participant’s neighborhood (area of radius 800 m around the home) were measured objectively using a geographical information system. Regression analyses found no associations between road environment variables and children’s likelihood of making at least seven walking/cycling trips per week to neighborhood destinations. Adolescent girls residing in neighborhoods with two to three traffic/pedestrian lights were more likely to make seven or more walking/cycling trips per week as those whose neighborhoods had fewer traffic lights (OR: 2.7; 95% CI: 1.2–6.2). For adolescent boys, residing on a cul-de-sac, compared with a through road, was associated with increases in MVPA of 9 min after school, 5 min in the evenings, and 22 min on weekend days. Speed humps were positively associated with adolescent boys’ MVPA during evenings. The road environment influences physical activity among youth in different ways, according to age group, sex and type of physical activity.

Bicycle use for transport in an Australian and a Belgian city : associations with built-environment attributes

The walkability attributes of neighborhood environments (residential density, land use mixture, and connectedness of streets) have been found to be associated with higher rates of walking. However, relatively less is known about the associations of walkability attributes with bicycle use for transport. We examined the relationships between adults' bicycle use for transport and measures of neighborhood walkability in two settings: an Australian city (Adelaide) with low rates of bicycle use and a Belgian city (Ghent) with high rates of bicycle use. A total of 2,159 and 382 participants were recruited in Adelaide and Ghent, respectively. A walkability index was derived from objectively measured data in Adelaide, while a similar index was derived from perceived measures in Ghent. Logistic regression models were employed to examine associations of bicycle use with different levels of walkability. There were higher rates of bicycle ownership for Ghent compared to Adelaide participants (96% versus 61%), and there was a higher prevalence of bicycle use for transport for Ghent compared to Adelaide participants (50% vs. 14%). Despite the large differences in bicycle ownership and use, living in a high-walkable neighborhood was associated with significantly higher odds of bicycle use for transport in both cities, after adjusting for relevant confounding factors. Built-environment innovations that are increasingly being advocated by health authorities and transport planners, primarily to promote higher rates of walking for transport, should also impact positively on bicycle use.

Are safety-related features of the road environment associated with smaller declines in physical activity among youth?

This study examined how objective measures of the local road environment related to safety were associated with change in physical activity (including active transport) among youth. Few longitudinal studies have examined the impact of the road environment on physical activity among children/adolescents in their neighborhoods. Participants were children aged 8–9 years (n=170) and adolescents aged 13–15 years (n=276) in 2004. Data were collected in 2004 and 2006 during followup of participants recruited initially in 2001 from 19 primary schools in Melbourne, Australia. Walking/cycling to local destinations was parent-reported for children and self-reported by adolescents. Moderate-to-vigorous physical activity (MVPA) during nonschool hours was recorded using accelerometers. Road environment features in each participant’s neighborhood (area within 800 m radius of their home) were measured objectively using a Geographical Information System. Linear regression analyses examined associations between road features and changes in active transport (AT) and MVPA over 2 years. Children’s AT increased but MVPA levels decreased in both age groups; on average, younger girls recorded the greatest declines. The number of traffic/pedestrian lights was associated with ΔAT among younger girls (B=0.45, p=0.004). The total length of walking tracks (in meters) was associated with ΔAT among younger girls (B=0.0016, p=0.015) and adolescent girls (B=0.0016, p=0.002). For adolescent boys, intersection density was associated with ΔAT (B=0.03, p=0.030). Slow points were associated with ΔMVPA among younger boys before school (B=1.55, p=0.021), while speed humps were associated with ΔMVPA among adolescent boys after school (B=0.23, p=0.015). There were many associations for adolescent girls: for example, the total length of local roads (B=0.49, p=0.005), intersection density (B=0.05, p=0.036), and number of speed humps (B=0.33, p=0.020) were associated with ΔMVPA during nonschool hours. Safety-related aspects of the built environment are conducive to physical activity among youth and may help stem age-related declines in physical activity. Passive road safety interventions may promote AT and physical activity among less active girls, in particular.

Associations between intrapersonal and neighborhood environmental characteristics and cycling for transport and recreation in adults : baseline results from the RESIDE study

Background: This study investigated the relationship between individual and neighborhood environmental factors and cycling for transport and for recreation among adults living in Perth, Western Australia.
Methods: Baseline cross-sectional data from 1813 participants (40.5% male; age range 18 to 78 years) in the Residential Environment (RESIDE) project were analyzed. The questionnaire included information on cycling behavior and on cycling-specific individual, social environmental, and neighborhood environmental attributes. Cycling for transport and recreation were dichotomized as whether or not individuals cycled in a usual week.
Results: Among the individual factors, positive attitudes toward cycling and perceived behavioral control increased the odds of cycling for transport and for recreation. Among the neighborhood environmental attributes, leafy and attractive neighborhoods, access to bicycle/walking paths, the presence of traffic slowing devices and having many 4-way street intersections were positively associated with cycling for transport. Many alternative routes in the local area increased the odds of cycling for recreation.
Conclusions: Effective strategies for increasing cycling (particularly cycling for transport) may include incorporating supportive environments such as creating leafy and attractive neighborhood surroundings, low traffic speed, and increased street connectivity, in addition to campaigns aimed at strengthening positive attitudes and confidence to cycle.