5 research outputs found
Self-correcting Bayesian target tracking
No full textThe copyright of this thesis rests with the author and no quotation from it or information derived from it may be published without the prior written consent of the authorAbstract
Visual tracking, a building block for many applications, has challenges such as occlusions,illumination changes, background clutter and variable motion dynamics that may degrade the
tracking performance and are likely to cause failures. In this thesis, we propose Track-Evaluate-Correct framework (self-correlation) for existing trackers in order to achieve a robust tracking.
For a tracker in the framework, we embed an evaluation block to check the status of tracking quality and a correction block to avoid upcoming failures or to recover from failures. We present a generic representation and formulation of the self-correcting tracking for Bayesian trackers using a Dynamic Bayesian Network (DBN). The self-correcting tracking is done similarly to a selfaware
system where parameters are tuned in the model or different models are fused or selected in a piece-wise way in order to deal with tracking challenges and failures. In the DBN model
representation, the parameter tuning, fusion and model selection are done based on evaluation and correction variables that correspond to the evaluation and correction, respectively. The inferences
of variables in the DBN model are used to explain the operation of self-correcting tracking. The specific contributions under the generic self-correcting framework are correlation-based selfcorrecting
tracking for an extended object with model points and tracker-level fusion as described below.
For improving the probabilistic tracking of extended object with a set of model points, we use Track-Evaluate-Correct framework in order to achieve self-correcting tracking. The framework
combines the tracker with an on-line performance measure and a correction technique. We correlate model point trajectories to improve on-line the accuracy of a failed or an uncertain tracker. A model point tracker gets assistance from neighbouring trackers whenever degradation in its
performance is detected using the on-line performance measure. The correction of the model point state is based on the correlation information from the states of other trackers. Partial Least
Square regression is used to model the correlation of point tracker states from short windowed trajectories adaptively. Experimental results on data obtained from optical motion capture systems show the improvement in tracking performance of the proposed framework compared to the
baseline tracker and other state-of-the-art trackers. The proposed framework allows appropriate re-initialisation of local trackers to recover from failures that are caused by clutter and missed
detections in the motion capture data.
Finally, we propose a tracker-level fusion framework to obtain self-correcting tracking. The
fusion framework combines trackers addressing different tracking challenges to improve the
overall performance. As a novelty of the proposed framework, we include an online performance measure to identify the track quality level of each tracker to guide the fusion. The trackers
in the framework assist each other based on appropriate mixing of the prior states. Moreover, the track quality level is used to update the target appearance model. We demonstrate the framework
with two Bayesian trackers on video sequences with various challenges and show its robustness
compared to the independent use of the trackers used in the framework, and also compared to
other state-of-the-art trackers. The appropriate online performance measure based appearance
model update and prior mixing on trackers allows the proposed framework to deal with tracking
challenges
Effect of feeding different ratios of dried brewery grain and surplus cafeteria food on feed intake, body weight gain and carcass characteristics of Wogera sheep
No full textThe demand for animal protein is increased due to the high global human population increase. Therefore, this study aims to evaluate the effects of feeding different ratios of dried brewers grain and surplus cafeteria food on feed intake, body weight gain, and carcass characteristics of Wogera sheep. Twenty-yearling Wogera ram lambs with an average body weight of 19.48 ± 1.64 kg were assigned to one of the five treatments using a randomized complete block design. The treatments were T1-100 % dried brewers grain (DBG), T2-70 % DBG + 30 % Student surplus Cafeteria Food (SCF), T3-50 % DBG + 50 % SCF, T4-30 % DBG + 70 % SCF, and T5- 100 % SCF. Grass hay was used as a basal diet. Grass hay and total dry matter intake were different (P ≤ 0.05) between treatments, with the highest record for T1. There were high records (P ≤ 0.05) of body weight change at T3 and low in T1. Blood, heart, kidney fat, liver with bile, intestinal free gut as well as nonedible components had differences (P ≤ 0.05) between treatments. In conclusion, supplementation of 50% DBG + 50% student SCF can improve the final body weight of fattening Wogera sheep
Cloth sharing with a scabies case considerably explains human scabies among children in a low socioeconomic rural community of Ethiopia
No full textAbstract Background In 2020, scabies were integrated into the WHO roadmap for neglected tropical diseases, aimed at ending the negligence to realize the SDGs. Ethiopia has also introduced scabies as a notifiable disease in drought-prone localities since 2015. Many of the previous studies employed study designs that might be subject to bias. Moreover, there is no scientific evidence about scabies in this area. Hence, this study aimed to determine the prevalence and associated factors of scabies among children aged below 15 years in rural Ethiopia. Methods A community-based cross-sectional study was carried out among 942 children in rural kebeles of Lay Gayent District from March through May 15, 2021. A two-stage sampling technique was applied. Data on sociodemographics, housing, water supply and sanitation, children’s personal hygiene, and caregivers’ knowledge about scabies were collected by a structured questionnaire. Data quality was maintained through pretesting, training of data collectors and supervisors, and supervision. An adjusted binary logistic regression was modelled to identify factors associated with scabies. The Hosmer–Lemeshow goodness-of-fit test was run to check the model fitness. Results The prevalence of scabies was 21.5% (95% CI 19.0–24.3). Maternal illiteracy (adjusted odds ratio (AOR) = 1.61; 95% CI 1.07–2.43); low household wealth (AOR = 2.04; 95% CI 1.25–3.33); unimproved water source (AOR = 1.58; 95% CI 1.05–2.40); not cleaning a house daily (AOR = 2.43; 95% CI 1.63–3.62); not trimming nails (AOR = 2.21; 95% CI 1.50–3.25); cloth sharing with a scabies case (AOR = 11.77; 95% CI 6.94–19.97); and low caregiver knowledge about scabies (AOR = 2.44; 95% CI 1.64–3.63) were factors associated with scabies. Conclusions Scabies remains a significant public health issue among children aged below 15 years in the district. Maternal illiteracy, low household wealth, unimproved water source, not cleaning a house daily, not trimming nails, cloth sharing with a scabies case, and low caregiver knowledge about scabies were factors associated with scabies. Community-wide interventions with prime emphasis on improving maternal education and caregivers’ knowledge about scabies, upgrading household wealth, ensuring a safe water supply, providing healthy housing, and ensuring adequate personal hygiene are warranted
Seroprevalence of hepatitis B and C viruses and some possible associated factors among cancer patients at the Oncology Treatment Center, Gondar, Northwest Ethiopia: A cross-sectional study.
No full textBackgroundCancer patients are prone to infections such as hepatitis B virus (HBV) and hepatitis C virus (HCV), which pose a major public health challenge, especially in developing countries. However, little is known about the magnitude of these infections among cancer patients in Ethiopia. Thus, this study determined the prevalence of HBV and HCV in cancer patients at the Oncology Treatment Center, Gondar, Northwest Ethiopia.Materials and methodsAn institutional-based cross-sectional study was conducted on 115 cancer patients from 15 April to 22 July 2023 at the Oncology Treatment Center, Gondar, Northwest Ethiopia. Sociodemographic, clinical, and other relevant data were collected using a pretested structured questionnaire. Five milliliters of venous blood were collected using a vacutainer tube, serum was harvested and tested for HBV and HCV using a one-step HBsAg and anti-HCV test strip with further confirmation through an ELISA test kit. Data were analyzed using SPSS version 20 and Fisher exact test was used to determine the association between HBV/HCV infection and associated factors.ResultsOut of 115 cancer patients, the majority (62.6%) were females. The median age was 50 (IQR; 40-56) years. The overall prevalence of HBV and HCV infections was 4.3% (95% CI; 0.6-8%) and 6.1% (95% CI; 1.7-10.5%), respectively. Sex was significantly associated with the prevalence of HCV (p = 0.011) with higher anti-HCV positivity in males (14%) than in females (1.4%).ConclusionsIn this study, the prevalence of HCV was higher and the HBV prevalence was intermediate in cancer patients. To reduce the burden of HBV and HCV infections, it is crucial to provide access to HBV and HCV screening services, strengthen vaccination, and improve prompt treatment in cancer patients
Living in a large family and low daily water consumption substantially expose for human scabies in rural Ethiopia: a matched analysis
No full textAbstract Background Scabies has been added to the neglected tropical diseases portfolio for large-scale disease control action since 2017 and is part of the WHO roadmap for NTDs 2021–2030, targeted at ending the neglect to achieve the sustainable development goals. Previous studies have not fitted matched analysis to identify predictors of scabies infestation in Ethiopia. Information is also scarce about predictors of scabies infestation in this area. Therefore, this study aimed to identify predictors of scabies infestation in rural Aneded District, northwest Ethiopia. Methods A community-based matched case–control study involving 183 cases and 549 controls was undertaken from March 1 to May 31, 2021, in rural Aneded District. A two-stage sampling technique with a house-to-house census for the screening of scabies cases was employed. A structured questionnaire with questions on sociodemographics, behavior, water supply, sanitation, and hygiene, and delivery of scabies-specific interventions was used. Pretesting, training of data collectors and supervisors, and supervision were applied to keep the data quality. A multivariable conditional logistic regression model was fitted to identify predictors of scabies. Results Unmarried individuals or those in separated families (adjusted matched odds ratio (AmOR = 2.71; 95% CI 1.30–5.65); those unable to read and write or in illiterate families (AmOR = 5.10; 95% CI 1.81–14.36); those in large families (AmOR = 6.67; 95% CI 2.83–15.73); households that had longer travel times for water collection (AmOR = 2.27; 95% CI 1.08–4.76); those that had low daily water consumption (AmOR = 6.69; 95% CI 2.91–15.37); households that disposed of solid wastes in open fields (AmOR = 5.60; 95% CI 2.53–12.40); and households that did not receive scabies-specific interventions (AmOR = 2.98; 95% CI 1.39–6.39) had increased odds of scabies. Conclusions Being unmarried, illiteracy, large family, long travel time for water collection, low daily water consumption, open dumping of solid wastes, and inaccessibility of scabies-specific interventions are predictors of scabies. This information is instrumental for redesigning improved scabies-specific interventions that consider educational status, marital status, family size, water collection time, daily water consumption, solid waste disposal, and equity and optimization in delivering existing interventions in rural Ethiopia
