An Uncertainty-based Neural Network for Explainable Trajectory Segmentation

As a variant task of time-series segmentation, trajectory segmentation is a key task in the applications of transportation pattern recognition and traffic analysis. However, segmenting trajectory is faced with challenges of implicit patterns and sparse results. Although deep neural networks have tremendous advantages in terms of high-level feature learning performance, deploying as a blackbox seriously limits the real-world applications. Providing explainable segmentations has significance for result evaluation and decision making. Thus, in this article, we address trajectory segmentation by proposing a Bayesian Encoder-Decoder Network (BED-Net) to provide accurate detection with explainability and references for the following active-learning procedures. BED-Net consists of a segmentation module based on Monte Carlo dropout and an explanation module based on uncertainty learning that provides results evaluation and visualization. Experimental results on both benchmark and real-world datasets indicate that BED-Net outperforms the rival methods and offers excellent explainability in the applications of trajectory segmentation.

Sensitivity, Optimal Control, and Cost-Effectiveness Analysis of Intervention Strategies of Filariasis

In this work, sensitivity, optimal control, and cost-effectiveness of several intervention strategies of filariasis are discussed. We study the intervention strategies that are related to bednet use, insecticide, and the combination of bed-net use and insecticide. We use Pontryagin’s maximum principle to characterize the optimal controls. The Average Cost-Effectiveness Ratio (ACER) and Infection Averted Ratio (IAR) are used to identify the most cost-effective strategy. We also determine the basic reproduction number and investigate the sensitivity of the basic reproduction number on the parameters that are related to bed-net use and insecticide. Based on the ACER values, the most cost-effective strategy to control filariasis is insecticide intervention. On the other hand, the IAR values indicates that bed-net use intervention is the most cost-effective strategy. Furthermore, it is also the most effective strategy to eliminate filariasis. The sensitivity analysis results show that the control parameter related to bed net use and treatment have a central role in reducing the basic reproduction number and filariasis spread.

Malaria infection and anemia status in under-five children from Southern Tanzania where seasonal malaria chemoprevention is being implemented

Background Malaria and anemia remain major public health challenges in Tanzania. Household socioeconomic factors are known to influence these conditions. However, it is not clear how these factors influence malaria transmission and anemia in Masasi and Nanyumbu Districts. This study presents findings on malaria and anemia situation in under-five children and its influencing socioeconomic factors in Masasi and Nanyumbu Districts, surveyed as part of an ongoing seasonal malaria chemoprevention operational study. Methods A community-based cross-sectional survey was conducted between August and September 2020. Finger-prick blood samples collected from children aged 3–59 months were used to test for malaria infection using malaria rapid diagnostic test (mRDT), thick smears for determination of asexual and sexual parasitemia, and thin smear for parasite speciation. Hemoglobin concentration was measured using a HemoCue spectrophotometer. A structured questionnaire was used to collect household socioeconomic information from parents/caregivers of screened children. The prevalence of malaria was the primary outcome. Chi-square tests, t-tests, and logistic regression models were used appropriately. Results Overall mRDT-based malaria prevalence was 15.9% (373/2340), and was significantly higher in Nanyumbu (23.7% (167/705) than Masasi District (12.6% (206/1635), p<0.001. Location (Nanyumbu), no formal education, household number of people, household number of under-fives, not having a bed net, thatched roof, open/partially open eave, sand/soil floor, and low socioeconomic status were major risks for malaria infection. Some 53.9% (1196/2218) children had anemia, and the majority were in Nanyumbu (63.5% (458/705), p<0.001. Location (Nanyumbu), mRDT positive, not owning a bed net, not sleeping under bed net, open/partially open eave, thatched window, sex of the child, and age of the child were major risk factors for anemia. Conclusion Prevalence of malaria and anemia was high and was strongly associated with household socioeconomic factors. Improving household socioeconomic status is expected to reduce the prevalence of the conditions in the area.

Impact of sublethal pyrethroid exposure on resistant Anopheles gambiae mosquitoes’ fitness

Background: There is increasing evidence of insecticide resistance spreading among wild mosquito populations, which is widely believed to compromise vector control once it reaches a threshold that enables mosquitoes to survive exposure to long lasting treated bed-net (LLIN) or indoor residual spraying (IRS). However, very little is known about the long-term impact of insecticide resistance on malaria transmission, which makes the consequence of insecticide resistance spreading difficult to predict. Methods: To gain more clarity, we have assessed five life-history traits of a resistant Anopheles gambiae laboratory strain that was repeatedly exposed to a LLIN and compared with individuals issued from the same strain but exposed to an untreated bed-net. Results: Out of the five measured life-history traits, four were significantly affected by exposure to insecticides. Indeed, the Kolmogorov-Smirnov non-parametric test revealed a significant (i) drop in blood feeding mean rates (P=0.000000494), (ii) increase in 24-hours post-exposure (P= 0.000008559) and (iii) end of gonotrophic cycle mortality (P =0.0005749), and (iv) drop in egg laying rate (P=0.000107) when mosquitoes were exposed. Conclusion: Our study shows that in a context of widespread of resistance to insecticides, current pyrethroid-based vector control tools can still confer protection against malaria

Effects of indoor air movement and ambient temperature on mosquito (Anopheles gambiae) behaviour around bed nets: implications for malaria prevention initiatives

Background Until recently, relatively little research has been done on how mosquitoes behave around the occupied bed net in the indoor environment. This has been partly remedied in the last few years through laboratory and field studies, most of these using video methods and mosquito flight tracking. Despite these recent advances, understanding of the mosquito-bed net environment system, and the principles that underlie mosquito behaviour within it, is limited. This project aimed to further understand this system by studying the effects of gently moving air (such as might be introduced through room design to make the indoor environment more comfortable and conducive to ITN use) and warmer vs. cooler ambient conditions on mosquito activity around ITNs and other bed nets. Methods The activity of colonized female Anopheles gambiae around an occupied untreated bed net set up in a mosquito-proof tent in a large laboratory space was recorded under different ambient conditions using a laser detection-video recording system. Conditions tested were ‘cool’ (23–25 °C) and ‘warm’ (27–30 °C) air temperatures and the presence or absence of a cross-flow produced by a small central processing unit (CPU) fan pointed at the side of the net so that it produced a ‘low-’ or ‘high-’ speed cross-draught (approx. 0.1 and 0.4 m/s, respectively). Near-net activity in recordings was measured using video image analysis. Results In cool, still air conditions, more than 80% of near-net activity by An. gambiae occurred on the net roof. Introduction of the low-speed or high-speed cross-draught resulted in an almost total drop off in roof activity within 1 to 2 min and, in the case of the high-speed cross-draught, a complementary increase in activity on the net side. In warm, still conditions, near-net activity appeared to be lower overall than in cool, still air conditions and to be relatively less focussed on the roof. Introduction of the high-speed cross-draught in warm conditions resulted in a decrease in roof activity and increase in side activity though neither effect was statistically significant. Conclusions Results are interpreted in terms of the flow of the stimulatory odour plume produced by the net occupant which, consistent with established principles of fluid dynamics, appears to rise quickly and remain more intact above the net occupant in cool, still air than in warm, still air. Cross-draught effects are ascribed to the changes they cause in the flow of the host odour plume as opposed to mosquito flight directly. The implications of these results for house designs that promote indoor air movement, on bed net design, and on other vector control measures are discussed. How mosquitoes approach a net is influenced both by indoor temperature and ventilation and their interaction. This system is in need of further study.

Effect of roof colour on indoor temperature and human comfort levels, with implications for malaria control: a pilot study using experimental houses in rural Gambia

Background In rural sub-Saharan Africa, thatch roofs are being replaced by metal roofs. Metal roofing, however, increases indoor temperatures above human comfort levels, and thus makes it more likely that residents will not use an insecticide-treated bed net (ITN) at night. Whether the colour of a metal roof affects indoor temperature and human comfort was assessed. Methods Two identical, experimental houses were constructed with metal roofs in rural Gambia. Roof types were: (1) original bare-metal, (2) painted with red oxide primer or (3) white gloss, to reflect solar radiation. Pairwise comparisons were run in six, five-night blocks during the malaria season 2018. Indoor climate was measured in each house and multivariate analysis used to compare indoor temperatures during the day and night. Results From 21.00 to 23.59 h, when most residents decide whether to use an ITN or not, the indoor temperature of a house with a bare metal roof was 31.5 °C (95% CI 31.2–31.8 °C), a red roof, 30.3 °C (95% CI 30.0–30.6) and a white roof, 29.8 °C (95% CI 29.4–30.1). During the same period, red-roofed houses were 1.23 °C cooler (95% CI 1.22–1.23) and white roofs 1.74 °C cooler (95% CI 1.70–1.79) than bare-metal roofed houses (p < 0.001). Similar results were found from 00.00 to 06.00 h. Maximum daily temperatures were 0.93 °C lower in a white-roofed house (95% CI 0.10–0.30, p < 0.001), but not a red roof (mean maximum temperature difference = 0.44 °C warmer, 95% CI 0.43–0.45, p = 0.081), compared with the bare-metal roofed houses. Human comfort analysis showed that from 21.00 to 23.59 h houses with white roofs (comfortable for 87% time) were more comfortable than bare-metal roofed houses (comfortable for 13% time; odds ratio = 43.7, 95% CI 27.5–69.5, p < 0.001). The cost of painting a metal roof white is approximately 31–68 USD. Conclusions Houses with a white roof were consistently cooler and more comfortable than those with a bare metal roof. Painting the roofs of houses white is a cheap way of making a dwelling more comfortable for the occupants and could potentially increase bed net use in hot humid countries.

Household Predictors of Malaria Episode in Northern Uganda: Its Implication for Future Malaria Control

Background: Uses of indoor residual spraying (IRS), long-lasting insecticidal nets (LLINS) and treatment with artemisinin-based combination therapy (ACT) are greatly promoted in northern part of Uganda as mitigating strategies for malaria episodes. Unfortunately, the region still records the highest malaria prevalence of 63%. This study assesses household predicators of malaria in the region and their impact on malaria episodes at the household levels.Methods: A cross-sectional study was conducted in four districts of Gulu, Oyam, Kitgum and Agago covering sixteen villages in northern Uganda. In total, 193 households were surveyed. Data was collected through pre-tested structured questionnaire and systematically coded for analysis using R software.Results:Women headed 58% of the 193 households surveyed. Six hundred and five (605) individuals were declared to have spent the previous night in these households. On average, there were two bed nets per household and 502 (86%) spent the night prior to interview under a bed net. Overall, malaria episodes were strongly related to lack of bed nets or lack of use thereof, and directly linked to the number of individuals in a household. Children were prone to malaria more than adults by a ratio of 2:1. When given a choice between insecticides (IRS) and treated bed nets, 1 in 3 households preferred treated bed nets. At the same time, data suggests that bed nets were perceived unnecessary once IRS was applied. If true, the driving force to spraying insecticides indoor then becomes lack of a bed net. Conclusions:Household predicators of incidence of malaria in northern Uganda includes bed nets, use of treated bed nets, and indoor residual spraying with households not practicing any of these bearing the heaviest burden of malaria. Hierarchical clustering on principal components (HCPC) clusters households into four types in northern Uganda, 1) household that use bed nets and sleep in houses sprayed with insecticides; 2) households that use bed nets but no indoor residual spraying with insecticides; 3) households that have no bed nets and no indoor residual spraying; and 4) test bed nets before use. Malaria incidence was higher in children as compared to the adults.

Rural–urban dimensions of the perception of malaria severity and practice of malaria preventive measures: insight from the 2018 Nigeria Demographic and Health Survey

Morbidities and mortalities caused by malaria are still a serious issue in Nigeria, with the country accounting for 25% of malaria morbidities and 24% of malaria mortalities globally in 2018. Treated bed nets reduce the incidence of malaria, but not all Nigerians use them. This study aimed to examine the factors associated with treated bed net usage, including perceived severity of malaria, and the rural–urban differences in the relationship between socio-demographic factors and use of treated bed nets in Nigeria. The analytic sample size comprised 40,693 women aged 15–49 years. Poisson regression and bivariable and multivariable analyses were used to test the study hypothesis that women who agreed that malaria could potentially lead to death would be more likely to adopt malaria preventive measures, including treated bed net use. About 48% of the women slept under a treated mosquito net the night before the survey. Those who perceived that malaria could lead to death had a higher likelihood of using a treated bed net in the urban, rural and combined samples. However, in the multivariable model, the association between perceived malaria severity and use of a treated bed net was only significant for rural women (APR=0.964, 95% CI: 0.933, 0.996). The results unexpectedly suggest that rural Nigerian women who perceive malaria to be severe have a lower likelihood of using treated bed nets. Also, rural–urban variations in the relationship between the socio-demographic variables and use of treated bed nets were observed. Policies should consider the observed rural–urban dichotomy in the influence of perceived severity of malaria and other socio-demographic factors on women’s use of treated bed nets in Nigeria.

The role of ideation on the effect of an SBC intervention on consistent bed net use among caregivers of children under 5 years in Nigeria: a multilevel mediation analysis

Background Malaria remains a significant public health challenge in Nigeria. Consistent bed net use (sleeping under a treated net every night) has been identified as a key malaria prevention behavior. This paper explores the relationship between mass media social and behavior change interventions, psychosocial factors, and consistent bed net use. Methods Data is from the endline survey of a USAID-funded social and behavior change communication campaign conducted from 2012 to 2017 across five states in Nigeria. The outcome measure was consistent bed net use, and the mediator variable was a composite measure called ideation from a set of psychosocial factors believed to influence bed net use. The independent variable was recall of malaria specific media messages. Multilevel mediation analysis explored if recall of malaria specific media messages had any effect on bed net related ideation and if this ideation had any effect on consistent net use. Results Respondents included in this study were on average aged 31 years, mostly married or cohabiting (97.5%) and female 75%. Four in 10 (39.7%) respondents were able to recall malaria specific messages. Respondents with low, moderate and high recall were 23, 32 and 80% more likely to have a higher ideational score in the emotional domain compared to those not able to recall. Respondents were more likely to have higher ideational scores in the cognitive domain if they had low (AOR = 1.26, 95% CI 1.15–1.38), moderate (AOR = 1.16, 95% CI 1.00–1.34) or high recall (AOR = 1.55, 95% CI 1.16–2.06), respectively compared to those with no recall. Similarly, respondents with low (AOR = 1.03, 95% CI .99–1.08), moderate (AOR = 1.15, 95% CI 1.08–1.23) and high (AOR = 1.15, 95% CI 1.01–1.30) recall were more likely to have a higher ideational score in the social domain compared to those with no recall. After adjusting for recall of media messages and other potential covariates, all three ideational domains also had a significant positive effect on consistent bed net use. For every unit increase in ideational score, the likelihood of reporting consistent bed net use increased by 5 to 10%. There was a significant indirect effect of recalling malaria specific messages on consistent bed net use through each of the ideational domains. Conclusion Access to a bed net is a critical first step in the process of bed net utilization. However, psychosocial factors e.g., emotional, cognitive, and social domains of ideation also play a major role in bed net use. Mass media SBC interventions could potentially influence bed net related ideation and consequently improve net use behavior. Future Social and behavior change interventions should employ approaches that improve these domains of ideation within their audiences in order to increase bed net utilization.