Search

Music Information Retrieval (MIR) is the task of extracting high-level information, such as genre, artist or instrumentation from music. Genre classification is an important and rapidly evolving research area of MIR. To date, only a small amount of research work has been done on the automatic genre classification of Nigerian songs. Hence, this study presents a new music dataset, namely the ORIN dataset, consisting of only Nigerian songs. The study dataset contains 478 Nigerian traditional songs from five genres: fuji, juju, highlife, waka and apala. The timbral texture and tempo features were mined from 30-second segments of each song using the Librosa Python library. For genre classification, the ORIN datasets was trained on 4 different classifiers- k-Nearest Neighbhour, Support Vector Machine, eXtreme Gradient Boosting (XGBoost) and Random Forest- with 85–15 train-test splits. The results obtained for the five different genres indicates that XGBoost classifier is a better model, having the highest accuracy of 81.94% and recall of 84.57%. This study uses the global mean (Tree SHAP) method to determine feature importance and impact on the classification model. Further analysis on the individual genres found some nearness in the timbral properties between some of the genres. This analysis was confirmed by human observation.

COVI-19 is a variant of coronavirus diseases that has destabilised the entire world and whose cure as at mid-2020 has become elusive. Social media is ablaze with discussions around the pandemic. There is the dire need to delineate the on-going conversations on the infection with the intention of creating awareness on people’s reaction, opinion, action and recommendation that are inimical to the wellbeing of the populace. Hence, this study is geared towards performing thematic analysis of the discussions on social media about COVID-19. We programmatically retrieved data from twitter between 1st March, 2020 to 30th June 2020 with covid-19 related keywords. We processed the data and later categorised them into themes that evolved from the tweets namely Herbs and Vegetables as COVID-10 Panacea, Self-Medication Due to Prescription by Non-Medical Practitioners on Social Media, Conspiracy Theories on COVID-19 and Fear and Anxiety Associated with COVID-19. The results show that many are resulting to herbs to protect themselves against the disease; taking drugs without doctor’s prescription; believing in conspiracy theories and having certain degree of fear.

South Africa (SA) records high mortality originating from traffic accident annually making the country to be ranked highly among nations with the highest traffic mortality globally. There is seemingly no study that has attempted to forecast when and where next accident will occur in SA. This study aims to use machine learning method to predict traffic accident in SA for every hour ranging between 1 January and 31 March 2019 at a segment ID. We obtained details of accidents that occurred in Cape Town, SA between 2016 and 2019 SANRAL, Uber Movement and Cape Town FMS via Zindi competition platform. This research adopted Catboost and LightGBM models to predict the traffic incident occurrence. Our model shows a F1 score of 0.11. The results of this research will aid prediction of accident occurrence at a particular road segment hourly.

Background Many low- and middle-income countries are facing a double burden of disease with persisting high levels of infectious disease, and an increasing prevalence of non-communicable disease (NCD). Within these settings, complex processes and transitions concerning health and population are underway, altering population dynamics and patterns of disease. Understanding the mechanisms through which changing socioeconomic and environmental contexts may influence health is central to developing appropriate public health policy. Migration, which involves a change in environment and health exposure, is one such mechanism. Methods This study uses Competing Risk Models to examine the relationship between internal migration and premature mortality from AIDS/TB and NCDs. The analysis employs 9 to 14 years of longitudinal data from four Health and Demographic Surveillance Systems (HDSS) of the INDEPTH Network located in Kenya and South Africa (populations ranging from 71 to 223 thousand). The study tests whether the mortality of migrants converges to that of non-migrants over the period of observation, controlling for age, sex and education level. Results In all four HDSS, AIDS/TB has a strong influence on overall deaths. However, in all sites the probability of premature death (45q15) due to AIDS/TB is declining in recent periods, having exceeded 0.39 in the South African sites and 0.18 in the Kenyan sites in earlier years. In general, the migration effect presents similar patterns in relation to both AIDS/TB and NCD mortality, and shows a migrant mortality disadvantage with no convergence between migrants and non-migrants over the period of observation. Return migrants to the Agincourt HDSS (South Africa) are on average four times more likely to die of AIDS/TB or NCDs than are non-migrants. In the Africa Health Research Institute (South Africa) female return migrants have approximately twice the risk of dying from AIDS/TB from the year 2004 onwards, while there is a divergence to higher AIDS/TB mortality risk amongst female migrants to the Nairobi HDSS from 2010. Conclusion Results suggest that structural socioeconomic issues, rather than epidemic dynamics are likely to be associated with differences in mortality risk by migrant status. Interventions aimed at improving recent migrant’s access to treatment may mitigate risk.

Nairobi HDSS Competing Risk Models. (DOCX 30 kb)

Africa Health Research Institute HDSS Competing Risk Models. (DOCX 30 kb)

Agincourt HDSS Competing Risk Models. (DOCX 31 kb)

Kisumu HDSS Competing Risk Models. (DOCX 29 kb)

BACKGROUND: Sexual activity may be less likely to occur during periods of school enrolment because of the structured and supervised environment provided the education obtained and the safer peer networks encountered while enrolled. We examined whether school enrolment was associated with teen pregnancy in South Africa. METHODS: Using longitudinal demographic surveillance data from the rural Agincourt sub-district we reconstructed the school enrolment status from 2000 through 2011 for 15 457 young women aged 12-18 years and linked them to the estimated conception date for each pregnancy during this time. We examined the effect of time-varying school enrolment on teen pregnancy using a Cox proportional hazard model adjusting for: age; calendar year; household socioeconomic status; household size; and gender educational attainment and employment of household head. A secondary analysis compared the incidence of pregnancy among school enrolees by calendar time: school term vs school holiday. RESULTS: School enrolment was associated with lower teen pregnancy rates [adjusted hazard ratio (95% confidence interval): 0.57 (0.50 0.65)].This association was robust to potential misclassification of school enrolment. For those enrolled in school pregnancy occurred less commonly during school term than during school holidays [incidence rate ratio (95% confidence interval): 0.90 (0.78 1.04)]. CONCLUSIONS: Young women who drop out of school may be at higher risk for teen pregnancy and could likely benefit from receipt of accessible and high quality sexual health services. Preventive interventions designed to keep young women in school or addressing the underlying causes of dropout may also help reduce the incidence of teen pregnancy. (c) The Author 2015; all rights reserved. Published by Oxford University Press on behalf of the International Epidemiological Association.

Migration has been hypothesised to be selective on health but this healthy migrant hypothesis has generally been tested at destinations, and for only one type of flow, from deprived to better-off areas. The circulatory nature of migration is rarely accounted for. This study examines the relationship between different types of internal migration and adult mortality in Health and Demographic Surveillance System (HDSS) populations in West, East, and Southern Africa, and asks how the processes of selection, adaptation and propagation explain the migration-mortality relationship experienced in these contexts. The paper uses longitudinal data representing approximately 900 000 adults living in nine sub-Saharan African HDSS sites of the INDEPTH Network. Event History Analysis techniques are employed to examine the relationship between all-cause mortality and migration status, over periods ranging from 3 to 14 years for a total of nearly 4.5 million person-years. The study confirms the importance of migration in explaining variation in mortality, and the diversity of the migration-mortality relationship over a range of rural and urban local areas in the three African regions. The results confirm that the pattern of migration-mortality relationship is not exclusively explained by selection but also by propagation and adaptation. Consequences for public health policy are drawn.

Background: Education, as a key indicator of human capital, is considered one of the major determinants of internal migration, with previous studies suggesting that human capital accumulates in urban areas at the expense of rural areas. However, there is fragmentary evidence concerning the educational correlates of internal migration in sub-Saharan Africa. Objective: The study questions whether more precise measures of migration in Health and Demographic Surveillance System (HDSS) populations support the hypothesis that migrants are self-selected on human capital and more educated people are more likely to leave rural areas or enter urban areas within a geographical region. Methods: Using unique longitudinal data representing approximately 900,000 people living in eight sub-Saharan African HDSS sites that are members of the INDEPTH Network, the paper uses Event History Analysis techniques to examine the relationship between formal educational attainment and in- and out-migration, over the period 2009 to 2011. Results: Between 7Š and 27Š of these local populations are moving in or out of the HDSS area over this period. Education is positively associated with both in- and out-migration in the Kenyan HDSS areas; however, the education effect has no clear pattern in the HDSS sites in Burkina Faso, Mozambique, and South Africa. Conclusions: Empirical results presented in this paper confirm a strong age profile of migration consistent with human capital expectation, yet the results point to variability in the association of education and the propensity to migrate. In particular, the hypothesis of a shift of human capital from rural to urban areas is not universally valid.

Background: There is a high prevalence of hypertension and related cardiovascular diseases in sub-Saharan Africa, yet few large studies exploring hypertension in Africa are available. The actual burden of disease is poorly understood and awareness and treatment to control it is often suboptimal.Objectives: The study sought to report the prevalence of measured hypertension and to assess awareness and control of blood pressure among older adults in rural and urban settings in 6 sites located in West, East, and Southern Africa. In addition, we examined regional, sex, and age differences related to hypertension.Methods: A population-based cross-sectional study was performed at 6 sites in 4 African countries: Burkina Faso (Nanoro), Ghana (Navrongo), Kenya (Nairobi), and South Africa (Agincourt, Dikgale, Soweto). Blood pressure measurements were taken using standardized procedures on 10,696 adults 40 to 60 years of age. Hypertension was defined as systolic blood pressure ≥140 mm Hg or diastolic blood pressure ≥90 mm Hg or taking antihypertensive medication.Results: The mean prevalence of hypertension ranged from 15.1% in Nanoro to 54.1% in Soweto. All 3 of the South African sites had a mean prevalence of hypertension of over 40.0%, significantly higher than in Nairobi (25.6%) and Navrongo (24.5%). Prevalence increased with age in both sexes and at all sites. A significantly higher prevalence of hypertension was observed in women in Agincourt, Dikgale, and Nairobi, whereas in Nanoro this trend was reversed. Within the hypertensive group the average proportion of participants who were aware of their blood pressure status was only 39.4% for men and 53.8% for women, and varied widely across sites.Conclusions: Our study demonstrates that the prevalence of hypertension and the level of disease awareness differ not only between but also within sub-Saharan African countries. Each nation must tailor their regional hypertension awareness and screening programs to match the characteristics of their local populations.HighlightsStark differences in hypertension prevalence, awareness, and control across Africa.Hypertension prevalence ranges between 15.1% and 54.1% in sub-Saharan Africans.Only 47.7% of hypertensive individuals knew their blood pressure status.Levels of blood pressure control ranged from 30.0% to 61.1%.Urgent need for localized monitoring and treatment of blood pressure.

The Agincourt health and socio-demographic surveillance system (HDSS), located in rural northeast South Africa close to the Mozambique border, was established in 1992 to support district health systems development led by the post-apartheid ministry of health. The HDSS (90 000 people), based on an annual update of resident status and vital events, now supports multiple investigations into the causes and consequences of complex health, population and social transitions. Observational work includes cohorts focusing on different stages along the life course, evaluation of national policy at population, household and individual levels and examination of household responses to shocks and stresses and the resulting pathways influencing health and well-being. Trials target children and adolescents, including promoting psycho-social well-being, preventing HIV transmission and reducing metabolic disease risk. Efforts to enhance the research platform include using automated measurement techniques to estimate cause of death by verbal autopsy, full 'reconciliation' of in- and out-migrations, follow-up of migrants departing the study area, recording of extra-household social connections and linkage of individual HDSS records with those from sub-district clinics. Fostering effective collaborations (including INDEPTH multi-centre work in adult health and ageing and migration and urbanization), ensuring cross-site compatibility of common variables and optimizing public access to HDSS data are priorities.

Background : Resolution of public health problems in Africa remains a challenge because of insufficient skilled human resource capacity. The Consortium for Advanced Research Training in Africa (CARTA) was established to enhance capacity in multi-disciplinary health research that will make a positive impact on population health in Africa. Objective : The first cohort of the CARTA program describes their perspectives and experiences during the 4 years of fellowship and puts forward suggestions for future progress and direction of research in Africa. Conclusions : The model of training as shown by the CARTA program is an effective model of research capacity building in African academic institutions. An expansion of the program is therefore warranted to reach out to more African academics in search of advanced research training. Keywords : CARTA; JAS; doctoral fellow; first cohort; advanced research training (Published: 29 September 2014) Citation : Glob Health Action 2014, 7: 25127 - http://dx.doi.org/10.3402/gha.v7.25127

Number and percentage of AIDS/TB and NCD deaths by HDSS site and sex. (DOCX 27 kb)

Number and percentage of AIDS/TB and NCD deaths by HDSS site and sex. (DOCX 27 kb)

Table of person years by HDSS site and sex. (DOCX 34 kb)

Table of person years by HDSS site and sex. (DOCX 34 kb)