Bike-Sharing Demand Prediction at Community Level under COVID-19 Using Deep Learning.

An important question in planning and designing bike-sharing services is to support the user's travel demand by allocating bikes at the stations in an efficient and reliable manner which may require accurate short-time demand prediction. This study focuses on the short-term forecasting, 15 min ahead, of the shared bikes demand in Montreal using a deep learning approach. Having a set of bike trips, the study first identifies 6 communities in the bike-sharing network using the Louvain algorithm. Then, four groups of LSTM-based architectures are adopted to predict pickup demand in each community. A univariate ARIMA model is also used to compare results as a benchmark. The historical trip data from 2017 to 2021 are used in addition to the extra inputs of demand related engineered features, weather conditions, and temporal variables. The selected timespan allows predicting bike demand during the COVID-19 pandemic. Results show that the deep learning models significantly outperform the ARIMA one. The hybrid CNN-LSTM achieves the highest prediction accuracy. Furthermore, adding the extra variables improves the model performance regardless of its architecture. Thus, using the hybrid structure enriched with additional input features provides a better insight into the bike demand patterns, in support of bike-sharing operational management.

Environmental and health impacts of transportation and land use scenarios in 2061.

We compared numbers of trips and distances by transport mode, air pollution and health impacts of a Business As Usual (BAU) and an Ideal scenario with urban densification and reductions in car share (76%-62% in suburbs; 55%-34% in urban areas) for the Greater Montreal (Canada) for 2061. We estimated the population in 87 municipalities using a demographic model and population projections. Year 2031 (Y2031) trips (from mode choice modeling) and distances were used to estimate those of Y2061. Emissions of nitrogen dioxide (NO2) and carbon dioxide (CO2) were estimated and NO2 used with dispersion modeling to estimate concentrations. Walking and Public Transit (PT) use and corresponding distances walked in Y2061 were >70% higher for the Ideal scenario vs the BAU, while car share and distances were <40% lower. NO2 levels were slightly lower in the Ideal scenario vs the BAU, but always higher in the urban core. Health impacts, summarized with disability adjusted life years (DALY), differed between urban and suburb areas but globally, the Ideal scenario reduced the impacts of the Y2061 BAU by 33% DALY. Percentages of car and PT trips were similar for the Y2031 and Y2061 BAU but kms travelled by car, CO2 and NO2 increased, due to increased populations. Drastic measures to decrease car share appear necessary to substantially reduce impacts of transportation.

INTERACT: A comprehensive approach to assess urban form interventions through natural experiments.

BACKGROUND: Urban form interventions can result in positive and negative impacts on physical activity, social participation, and well-being, and inequities in these outcomes. Natural experiment studies can advance our understanding of causal effects and processes related to urban form interventions. The INTErventions, Research, and Action in Cities Team (INTERACT) is a pan-Canadian collaboration of interdisciplinary scientists, urban planners, and public health decision makers advancing research on the design of healthy and sustainable cities for all. Our objectives are to use natural experiment studies to deliver timely evidence about how urban form interventions influence health, and to develop methods and tools to facilitate such studies going forward. METHODS: INTERACT will evaluate natural experiments in four Canadian cities: the Arbutus Greenway in Vancouver, British Columbia; the All Ages and Abilities Cycling Network in Victoria, BC; a new Bus Rapid Transit system in Saskatoon, Saskatchewan; and components of the Sustainable Development Plan 2016-2020 in Montreal, Quebec, a plan that includes urban form changes initiated by the city and approximately 230 partnering organizations. We will recruit a cohort of between 300 and 3000 adult participants, age 18 or older, in each city and collect data at three time points. Participants will complete health and activity space surveys and provide sensor-based location and physical activity data. We will conduct qualitative interviews with a subsample of participants in each city. Our analysis methods will combine machine learning methods for detecting transportation mode use and physical activity, use temporal Geographic Information Systems to quantify changes to urban intervention exposure, and apply analytic methods for natural experiment studies including interrupted time series analysis. DISCUSSION: INTERACT aims to advance the evidence base on population health intervention research and address challenges related to big data, knowledge mobilization and engagement, ethics, and causality. We will collect ~ 100 TB of sensor data from participants over 5 years. We will address these challenges using interdisciplinary partnerships, training of highly qualified personnel, and modern methodologies for using sensor-based data.

Estimating the health benefits of planned public transit investments in Montreal.

BACKGROUND: Since public transit infrastructure affects road traffic volumes and influences transportation mode choice, which in turn impacts health, it is important to estimate the alteration of the health burden linked with transit policies. OBJECTIVE: We quantified the variation in health benefits and burden between a business as usual (BAU) and a public transit (PT) scenarios in 2031 (with 8 and 19 new subway and train stations) for the greater Montreal region. METHOD: Using mode choice and traffic assignment models, we predicted the transportation mode choice and traffic assignment on the road network. Subsequently, we estimated the distance travelled in each municipality by mode, the minutes spent in active transportation, as well as traffic emissions. Thereafter we estimated the health burden attributed to air pollution and road traumas and the gains associated with active transportation for both the BAU and PT scenarios. RESULTS: We predicted a slight decrease of overall trips and kilometers travelled by car as well as an increase of active transportation for the PT in 2031 vs the BAU. Our analysis shows that new infrastructure will reduce the overall burden of transportation by 2.5 DALYs per 100,000 persons. This decrease is caused by the reduction of road traumas occurring in the inner suburbs and central Montreal region as well as gains in active transportation in the inner suburbs. CONCLUSION: Based on the results of our study, transportation planned public transit projects for Montreal are unlikely to reduce drastically the burden of disease attributable to road vehicles and infrastructures in the Montreal region. The impact of the planned transportation infrastructures seems to be very low and localized mainly in the areas where new public transit stations are planned.

Compliance potential mapping: a tool to assess potential contributions of walking towards physical activity guidelines.

BACKGROUND: Walking for transport is increasingly considered an important component for meeting physical activity guidelines. This is true for individuals of all ages, and particularly important for seniors, for whom other physical activities may not be recommended. In order to evaluate the potential contributions of walking to physical activity, in this paper the concept of Compliance Potential Mapping is introduced. The concept is illustrated using seniors as a case study. METHODS: Based on estimates of walking trip distance and frequency, estimates of expected total daily walking distance are obtained. These estimates are converted to weekly walking minutes, which are in turn compared to recommended physical activity guidelines for seniors. Once estimates of travel behavior are available, the approach is straightforward and based on relatively simple map algebra operations. RESULTS: Compliance Potential Mapping as a tool to assess the potential contributions of walking towards physical activity is demonstrated using data from Montreal's 2008 travel survey. The results indicate that the central parts of Montreal Island display higher potential for compliance with physical activity guidelines, but with variations according to age, income, occupation, possession of driver's license and vehicle, and neighborhood and accessibility parameters. CONCLUSIONS: Compliance Potential Maps offer valuable information for public health and transportation planning and policy analysis.

Neighborhood social inequalities in road traffic injuries: the influence of traffic volume and road design.

OBJECTIVES: We examined the extent to which differential traffic volume and road geometry can explain social inequalities in pedestrian, cyclist, and motor vehicle occupant injuries across wealthy and poor urban areas. METHODS: We performed a multilevel observational study of all road users injured over 5 years (n=19,568) at intersections (n=17,498) in a large urban area (Island of Montreal, Canada). We considered intersection-level (traffic estimates, major roads, number of legs) and area-level (population density, commuting travel modes, household income) characteristics in multilevel Poisson regressions that nested intersections in 506 census tracts. RESULTS: There were significantly more injured pedestrians, cyclists, and motor vehicle occupants at intersections in the poorest than in the richest areas. Controlling for traffic volume, intersection geometry, and pedestrian and cyclist volumes greatly attenuated the event rate ratios between intersections in the poorest and richest areas for injured pedestrians (-70%), cyclists (-44%), and motor vehicle occupants (-44%). CONCLUSIONS: Roadway environment can explain a substantial portion of the excess rate of road traffic injuries in the poorest urban areas.

Accessibility to health care facilities in Montreal Island: an application of relative accessibility indicators from the perspective of senior and non-senior residents.

BACKGROUND: Geographical access to health care facilities is known to influence health services usage. As societies age, accessibility to health care becomes an increasingly acute public health concern. It is known that seniors tend to have lower mobility levels, and it is possible that this may negatively affect their ability to reach facilities and services. Therefore, it becomes important to examine the mobility situation of seniors vis-a-vis the spatial distribution of health care facilities, to identify areas where accessibility is low and interventions may be required. METHODS: Accessibility is implemented using a cumulative opportunities measure. Instead of assuming a fixed bandwidth (i.e. a distance threshold) for measuring accessibility, in this paper the bandwidth is defined using model-based estimates of average trip length. Average trip length is an all-purpose indicator of individual mobility and geographical reach. Adoption of a spatial modelling approach allows us to tailor these estimates of travel behaviour to specific locations and person profiles. Replacing a fixed bandwidth with these estimates permits us to calculate customized location- and person-based accessibility measures that allow inter-personal as well as geographical comparisons. DATA: The case study is Montreal Island. Geo-coded travel behaviour data, specifically average trip length, and relevant traveller's attributes are obtained from the Montreal Household Travel Survey. These data are complemented with information from the Census. Health care facilities, also geo-coded, are extracted from a comprehensive business point database. Health care facilities are selected based on Standard Industrial Classification codes 8011-21 (Medical Doctors and Dentists). RESULTS: Model-based estimates of average trip length show that travel behaviour varies widely across space. With the exception of seniors in the downtown area, older residents of Montreal Island tend to be significantly less mobile than people of other age cohorts. The combination of average trip length estimates with the spatial distribution of health care facilities indicates that despite being more mobile, suburban residents tend to have lower levels of accessibility compared to central city residents. The effect is more marked for seniors. Furthermore, the results indicate that accessibility calculated using a fixed bandwidth would produce patterns of exposure to health care facilities that would be difficult to achieve for suburban seniors given actual mobility patterns. CONCLUSIONS: The analysis shows large disparities in accessibility between seniors and non-seniors, between urban and suburban seniors, and between vehicle owning and non-owning seniors. This research was concerned with potential accessibility levels. Follow up research could consider the results reported here to select case studies of actual access and usage of health care facilities, and related health outcomes.

The Potential Impacts of Urban and Transit Planning Scenarios for 2031 on Car Use and Active Transportation in a Metropolitan Area.

Land use and transportation scenarios can help evaluate the potential impacts of urban compact or transit-oriented development (TOD). Future scenarios have been based on hypothetical developments or strategic planning but both have rarely been compared. We developed scenarios for an entire metropolitan area (Montreal, Canada) based on current strategic planning documents and contrasted their potential impacts on car use and active transportation with those of hypothetical scenarios. We collected and analyzed available urban planning documents and obtained key stakeholders' appreciation of transportation projects on their likelihood of implementation. We allocated 2006-2031 population growth according to recent trends (Business As Usual, BAU) or alternative scenarios (current planning; all in TOD areas; all in central zone). A large-scale and representative Origin-Destination Household Travel Survey was used to measure travel behavior. To estimate distances travelled by mode, in 2031, we used a mode choice model and a simpler method based on the 2008 modal share across population strata. Compared to the BAU, the scenario that allocated all the new population in already dense areas and that also included numerous public transit projects (unlikely to be implemented in 2031), was associated with greatest impacts. Nonetheless such major changes had relatively minor impacts, inducing at most a 15% reduction in distances travel by car and a 28% increase in distances walked, compared to a BAU. Strategies that directly target the reduction of car use, not considered in the scenarios assessed, may be necessary to induce substantial changes in a metropolitan area.

Long-Term Effects of a Multimodal Physiotherapy Program on the Severity of Somatosensory Tinnitus and Identification of Clinical Indicators Predicting Favorable Outcomes of the Program.

BACKGROUND: Tinnitus, the perception of sound in the absence of external auditory stimuli, is commonly associated with problems of the auditory system. Head and neck disorders can also be involved in tinnitus emergence. In such cases, the term somatosensory tinnitus is used. Physiotherapy treatments have been identified as a promising avenue in the treatment of somatosensory tinnitus. PURPOSE: The aim of the study was to explore the effect of a physiotherapy program on the intensity and severity of somatosensory tinnitus and to identify the clinical characteristics of the patients who respond well to this treatment. RESEARCH DESIGN: Quasi-experimental pre-post single-group design. STUDY SAMPLE: Thirty-one adults with presumed somatosensory tinnitus. INTERVENTION: All participants received on average ten physiotherapy treatments over six weeks. Treatments included cervical and thoracic mobilizations, as well as muscular strengthening, stretching, postural instruction, and cervical stabilization. DATA COLLECTION AND ANALYSIS: Outcomes were measured at baseline, at the end of the physiotherapy program, and three months later. The primary outcomes were the Tinnitus Handicap Inventory and visual analog scales for loudness and annoyance caused by tinnitus. After the last evaluation, participants were divided into two groups: improved and unimproved participants. Participants were considered improved if they (1) showed significant improvement in at least two of the three primary outcome measures and (2) indicated subjective improvement. Thereafter, the baseline characteristics that correctly identify participants susceptible to improve significantly following treatment were determined (Cohen's effect size d > 0.8). RESULTS: A significant improvement in tinnitus intensity was observed at the end of the program. Of the 31 participants, 14 experienced persistent improvement in the intensity of their tinnitus and were classified as improved. Baseline characteristics strongly associated with tinnitus improvement were no increase in tinnitus when exposed to noise (d = -1.57), no family history of tinnitus (d = -1.16), somatosensory modulation in response to the contraction used to resist pressure applied to the forehead (d = 1.20), and recent onset of tinnitus (d = 1.03). CONCLUSIONS: This exploratory study showed that a multimodal physiotherapy program is effective in decreasing the severity of tinnitus, principally in individuals presenting with somatosensory tinnitus in combination with specific clinical characteristics.

Progesterone increases hypoxic ventilatory response and reduces apneas in newborn rats.

We hypothesized that progesterone may enhance the hypoxic ventilatory response and reduce the occurrence of apneas in newborn male rats. We studied 10-day-old rats chronically exposed to progesterone (Prog) or vehicle through the milk of lactating mothers. Respiratory and metabolic recordings were performed using whole body plethysmography under normoxia and during hypoxic exposure (10% O(2)--30 min). While progesterone did not alter baseline breathing and metabolic rate, it increased hypoxic ventilatory response particularly by limiting the magnitude of the ventilatory roll-off during the second phase of the hypoxic ventilatory response (i.e. following 5 min of exposure). In parallel, progesterone lowered the number of spontaneous apneas and drastically reduced the occurrence of post-sigh apneas during hypoxic exposure by limiting the time of the post-sigh expiratory pause. Following domperidone injection (used to block peripheral D2 dopamine receptor), minute ventilation increased in Veh pups and the number of spontaneous apneas decreased. These responses were not observed in Prog pups, suggesting that progesterone reduces peripheral dopaminergic inhibition on breathing. We conclude that progesterone is a potent stimulant of hypoxic ventilatory response in newborn rats and effectively reduces the occurrence of apneas.

Expression of sex-steroid receptors and steroidogenic enzymes in the carotid body of adult and newborn male rats.

This study describes the localization and pattern of expression of estradiol and progesterone receptors as well as key enzymes for steroid synthesis (i.e. P450 side-chain-cleavage--P450scc, and P450 aromatase--P450Aro) in the carotid body (CB) and superior cervical ganglion (SCG) of adult, newborn and late fetal male rats, using immunohistochemistry, Western blot and real-time RT-PCR. Our results show a constitutive expression of the beta estradiol receptor (Erbeta) and the 80 kDa and 60 kDa progesterone receptors (PR-A and PR-C) isoforms in the CB, while in the SCG Eralpha, Erbeta, PR-A and PR-C are expressed. While P450Aro staining was negative, P450scc staining was strong both in the SCG and CB. In late fetal and newborn rats, Eralpha was not detected in the CB or SCG, but a slight staining appeared for P450 aromatase in the CB, and to a lesser extent in SCG. P450scc was strongly expressed in CB and SCG of late fetal and newborn rats. We conclude that the carotid body shows a constitutive expression of Erbeta and PR and may be able to synthesize steroids, including estradiol during late fetal life.

Differences in associations between active transportation and built environmental exposures when expressed using different components of individual activity spaces.

This study assessed relationships between built environmental exposures measured within components of individual activity spaces (i.e., travel origins, destinations and paths in-between), and use of active transportation in a metropolitan setting. Individuals (n=37,165) were categorised as using active or sedentary transportation based on travel survey data. Generalised Estimating Equations analysis was used to test relationships with active transportation. Strength and significance of relationships between exposures and active transportation varied for different components of the activity space. Associations were strongest when including travel paths in expression of the built environment. Land use mix and greenness were negatively related to active transportation.