Exploiting deep learning and volunteered geographic information for mapping buildings in Kano, Nigeria.
Ontology highlight
ABSTRACT:
SUBMITTER: Yuan J
PROVIDER: S-EPMC6198754 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Accurate understanding and forecasting of traffic is a key contemporary problem for policymakers. Road networks are increasingly congested, yet traffic data is often expensive to obtain, making informed policy-making harder. This paper explores the extent to which traffic disruption can be estimated using features from the volunteered geographic information site OpenStreetMap (OSM). We use OSM features as predictors for linear regressions of counts of traffic disruptions and traffic volume at 6,500 points in the road network within 112 regions of Oxfordshire, UK. We show that more than half the variation in traffic volume and disruptions can be explained with OSM features alone, and use cross-validation and recursive feature elimination to evaluate the predictive power and importance of different land use categories. Finally, we show that using OSM's granular point of interest data allows for better predictions than the broader categories typically used in studies of transportation and land use.
| S-EPMC6985234 | biostudies-literature
Project description:Collective intelligence is the idea that under the right circumstances collections of individuals are smarter than even the smartest individuals in the group (Suroweiki 2004), that is a group has an "intelligence" that is independent of the intelligence of its members. The ideology of collective intelligence undergirds much of the enthusiasm about the use of "volunteered" or crowdsourced geographic information. Literature from a variety of fields makes clear that not all groups possess collective intelligence, this paper identifies four pre-conditions for the emergence of collective intelligence and then examine the extent to which collectively generated mapping systems satisfy these conditions. However, the "intelligence" collectively generated maps is hard to assess because there are two difficult to reconcile perspectives on map quality- the credibility perspective and the accuracy perspective. Much of the current literature on user generated maps focuses on assessing the quality of individual contributions. However, because user generated maps are complex social systems and because the quality of a contribution is difficult to assess this strategy may not yield an "intelligent" end product. The existing literature on collective intelligence suggests that the structure of groups more important that the intelligence of group members. Applying this idea to user generated suggests that systems should be designed to foster conditions known to produce collective intelligence rather than privileging particular contributions/contributors. The paper concludes with some design recommendations and by considering the implications of collectively generated maps for both expert knowledge and traditional state sponsored mapping programs.
| S-EPMC4238431 | biostudies-literature
Project description:The growing use of crowdsourced geographic information (CGI) has prompted the employment of several methods for assessing information quality, which are aimed at addressing concerns on the lack of quality of the information provided by non-experts. In this work, we propose a taxonomy of methods for assessing the quality of CGI when no reference data are available, which is likely to be the most common situation in practice. Our taxonomy includes 11 quality assessment methods that were identified by means of a systematic literature review. These methods are described in detail, including their main characteristics and limitations. This taxonomy not only provides a systematic and comprehensive account of the existing set of methods for CGI quality assessment, but also enables researchers working on the quality of CGI in various sources (e.g., social media, crowd sensing, collaborative mapping) to learn from each other, thus opening up avenues for future work that combines and extends existing methods into new application areas and domains.
| S-EPMC5993263 | biostudies-literature
Project description:This data presents the distribution of physical activities in the Shenzhen greenway network (GN) in January, April and July, 2014. The volunteered geographic on physical activity is overlaid with the greenways data, to describe the distribution of physical activities in the greenways. The data are summarized to show the distribution characteristics geographically from different aspects in Shenzhen, China. Data were used to explore the effect of the Shenzhen GN on supporting physical activities, "Where do networks really work? The effects of Shenzhen greenway network on supporting physical activities" (Liu et al., 2016) [2].
| S-EPMC4878787 | biostudies-other
Project description:BACKGROUND:Malaria surveillance system strengthening is essential in the progress towards malaria elimination. In Nigeria, more attention is being given to this recently as the country is striving towards achieving elimination. However, the surveillance system performance is fraught with challenges including poor data quality with varying magnitude by state. This study evaluated the operation of the Kano State malaria surveillance system and assessed its key attributes. METHODS:An observational study design comprising a survey, record review and secondary data analysis, and mixed methods data collection approach were used. Four key stakeholders' and 35 Roll Back Malaria Focal Persons (RBMs) semi-structured interviews on operation of the system and attributes of the surveillance system, were conducted. We analyzed the abstracted 2013-2016 National Health Management Information System web-based malaria datasets. The surveillance system was evaluated using the "2001 United States Centers for Disease Control's updated guidelines for Evaluating Public Health Surveillance Systems". Data were described using means, standard deviation, frequencies and proportions. Chi-squared for linear trends was used. RESULTS:Overall, 24 RBMs (68.6%) had ? 15-year experience on malaria surveillance, 29 (82.9%) had formal training on malaria surveillance; 32 RBMs (91.4%) reported case definitions were easy-to-use, reporting forms were easy-to-fill and data flow channels were clearly defined. Twenty-seven respondents (69.2%) reported data tools could accommodate changes and all RBMs understood malaria case definitions. All respondents (4 stakeholders and 34 RBMs [97.1%]) expressed willingness to continue using the system and 33 (84.6%) reported analyzed data were used for decision-making. Public health facilities constituted the main data source. Overall, 65.0% of funding were from partner agencies. Trend of malaria cases showed significant decline (?2trend?=?7.49; P?=?0.0006). Timeliness of reporting was below the target (? 80%), except being 82% in 2012. CONCLUSIONS:Malaria surveillance system in Kano State was simple, flexible, acceptable, useful and donor-driven but the data were not representative of all health facilities. Timeliness of reporting was suboptimal. We recommended reporting from private health facilities, strengthening human resource capacity for supportive supervision and ensuring adequate government funding to enhance the system's representativeness and improve data quality.
| S-EPMC7008566 | biostudies-literature
Project description:BACKGROUND:In 2013, the Nigeria Federal Ministry of Health established a Master Health Facility List (MHFL) as recommended by WHO. Since then, some health facilities (HFs) have ceased functioning and new facilities were established. We updated the MHFL and assessed service delivery parameters in the Malaria Frontline Project implementing areas in Kano and Zamfara States. METHODS:We assessed all HFs in each of the 34 project local government areas (LGAs) between July and September 2017. Project staff administered a semi-structured questionnaire developed for this assessment to heads of HFs about the type of facility, category and number of staff working at the facility and to record geo-coordinates of facility. RESULTS:In the Kano State project area, 726 HFs were identified and geo-located: 31 were new facilities, 608 (84%), 116 (16%) and two (0.3%) were Primary Health Care (PHC), secondary and tertiary facilities respectively. Using the national definition, there were 710 (98%) functional facilities and 644 (91%) of these reported to the national health information platform, District Health Information System, version 2 (DHIS2). The Zamfara project area had 739 HFs: eight were new, 715 (97%), 22 (3.0%) and two (0.2%) PHCs, secondary and tertiary facilities respectively. There were 695 (94%) functional facilities with 656 (94%) of these reporting to DHIS2. Using national criteria for primary health care designation, only 95 (9%) of all PHCs in the two States met the minimum human resource requirements. CONCLUSION:Most HFs were functional and reported to DHIS2. A comprehensive MHFL having all the important parameters that should be established and updated regularly by authorities to make it more useful for health services administration and management. Most functional facilities are understaffed.
| S-EPMC7493332 | biostudies-literature
Project description:IntroductionThe knowledge, attitude, and practice of emergency neonatal resuscitation are critical requirements in any facility that offers obstetric and neonatal services. This study aims to conduct a needs assessment survey and obtain individual and facility-level data on expertise and readiness for neonatal resuscitation. We hypothesize that neonatal emergency preparedness among healthcare providers in Kano, Nigeria is associated with the level of knowledge, attitudinal disposition, practice and equipment availability at the facility level.MethodsA semi-structured, self-administered questionnaire was administered to a cross-section of health providers directly involved with neonatal care (n = 112) and attending a neonatal resuscitation workshop in Kano state. Information regarding knowledge, attitude, practice and facility preparedness for neonatal resuscitation was obtained. Bloom's cut-off score and a validated basic emergency obstetric and neonatal care assessment tool were adopted to categorize outcomes. Multivariable logistic regression was employed to determine independent predictors of knowledge and practice.ResultsAlmost half (48% and 42% respectively) of the respondents reported average level of self-assessed knowledge and comfort during resuscitation. Only 7% (95% CI:3.2-13.7) and 5% (95% CI:2.0-11.4) of health providers demonstrated good knowledge and practice scores respectively, with an overall facility preparedness of 46%. Respondents' profession as a physician compared to nurses and midwives predicted good knowledge (aOR = 0.08, 95% CI: 0.01-0.69; p = 0.01), but not practice.ConclusionHealthcare provider's knowledge and practice including facility preparedness for emergency neonatal resuscitation were suboptimal, despite the respondents' relatively high self-assessed attitudinal perception. Physicians demonstrated higher knowledge compared to other health professionals. The low level of respondents' awareness, practice, and facility readiness suggest the current weak state of secondary health systems in Kano.
| S-EPMC8741031 | biostudies-literature
Project description:BackgroundStillbirths are a poignant representation of global inequality. Nigeria is documented to have the second highest rate; yet, the reporting system is inadequate in most Nigerian healthcare facilities. The aim was to identify the determinants of stillbirth among deliveries in the Murtala Muhammad Specialist Hospital (MMSH), Kano, Nigeria.MethodsTwo study designs were used: a case-control study (S1) and a prospective cohort study (S2). Both studies were carried out at the MMSH. For S1, stillbirths were retrospectively matched to a livebirth by time (target of 24 hours' time variation) to establish a case-control study with a 1:1 ratio. Eligibility into S2 included all mothers who were presented at the MMSH in labour regardless of birth outcome. Both were based on recruitment durations, not sample sizes (3 months and 2 months, respectively, 2017-2018). The demographic and clinical data were collected through paper-based questionnaires. Univariable logistic regression was used. Multivariable logistic regression was used to explore relationships between area type and other specific factors.FindingsStillbirth incidence in S2 was 180/1,000 births. Stillbirth was associated with the following factors; no maternal education, previous stillbirth(s), prematurity, living in both semi-rural and rural settings, and having extended time periods between rupture of membranes and delivery. Findings of the multivariable analysis (S1 and S2) indicated that the odds of stillbirth, for those living in a rural area, were further exacerbated in those mothers who had no education, lived in a shack, or had any maternal disease.InterpretationThis research identifies the gravity of this situation in this area and highlights the need for action. Further understanding of some of the findings and exploration into associations are required to inform intervention development.FundingThis collaboration was partially supported by funding from Health and Care Research Wales.
| S-EPMC8795591 | biostudies-literature
Project description: Not available
| S-EPMC10794985 | biostudies-literature
Project description:In recent times, as interest in stress control has increased, many studies on stress recognition have been conducted. Several studies have been based on physiological signals, but the disadvantage of this strategy is that it requires physiological-signal-acquisition devices. Another strategy employs facial-image-based stress-recognition methods, which do not require devices, but predominantly use handcrafted features. However, such features have low discriminating power. We propose a deep-learning-based stress-recognition method using facial images to address these challenges. Given that deep-learning methods require extensive data, we constructed a large-capacity image database for stress recognition. Furthermore, we used temporal attention, which assigns a high weight to frames that are highly related to stress, as well as spatial attention, which assigns a high weight to regions that are highly related to stress. By adding a network that inputs the facial landmark information closely related to stress, we supplemented the network that receives only facial images as the input. Experimental results on our newly constructed database indicated that the proposed method outperforms contemporary deep-learning-based recognition methods.
| S-EPMC8625615 | biostudies-literature