This report is a thesis in mechanical engineering with a focus on development assistance. The thesis was carried out in collaboration with the Gombe Youth Development Organization.
The task was to develop an adequate system to collect, purify and store water in the two rural villages Gombe and Kayunga in Uganda. The system takes into account local weather, water quality, population, water consumption and types of water sources.
The final system has a low manufacturing cost, simple maintenance, low operating cost, is electrical independent and can be manufactured and repaired with local available components.
The report presents various types of sources of water and purification of varying suitability for these conditions. The report also includes operation and maintenance manual and an approximate budget.
The result of this work is a combined system of rainwater harvesting, flocculation and one "up flow" rapid sand filter with built-in storage tank. Given that only rainwater collection is not enough to cover a normal sized family of 10 individuals consumption of water, due to this water from natural sources is also used.
Demand forecasting is central to decision making and operations in organisations. As the volume of forecasts increases, for example due to an increased product customisation that leads to more SKUs being traded, or a reduction in the length of the forecasting cycle, there is a pressing need for reliable automated forecasting. Conventionally, companies rely on a statistical baseline forecast that captures only past demand patterns, which is subsequently adjusted by human experts to incorporate additional information such as promotions. Although there is evidence that such process adds value to forecasting, it is questionable how much it can scale up, due to the human element. Instead, in the literature it has been proposed to enhance the baseline forecasts with external well-structured information, such as the promotional plan of the company, and let experts focus on the less structured information, thus reducing their workload and allowing them to focus where they can add most value. This change in forecasting support systems requires reliable multivariate forecasting models that can be automated, accurate and robust. This paper proposes an extension of the recently proposed Multiple Aggregation Prediction Algorithm (MAPA), which uses temporal aggregation to improve upon the established exponential smoothing family of methods. MAPA is attractive as it has been found to increase both the accuracy and robustness of exponential smoothing. The extended multivariate MAPA is evaluated against established benchmarks in modelling a number of heavily promoted products and is found to perform well in terms of forecast bias and accuracy. Furthermore, we demonstrate that modelling time series using multiple temporal aggregation levels makes the final forecast robust to model mis-specification.
This study illustrates the sporadic distribution of metals in fluvial systems flowing from catchments to urban settlements. This is a detailed study prognosticating the deteriorating quality of rivers at specific locations due to metal pollution. Heavy metals like cadmium, lead, nickel and mercury are prominent in industrial sector. Contour plots derived using spatial and temporal data could determine the focal point of metal pollution and its gradation. Metal values recorded were cadmium 157 mg/L, lead 47 mg/L, nickel 61 mg/L and mercury 0.56 mg/L. Prokaryote diversity was less in polluted water and it harboured metal tolerant bacteria, which were isolated from these polluted sites. Actinomycetes like Streptomyces and several other bacteria like Stenotrophomonas and Pseudomonas isolated from the polluted river sites exhibited changes in morphology in presence of heavy metals. This stress response offered remedial measures as Streptomyces were effective in biosorption of cadmium, nickel and lead and Stenotrophomonas and Pseudomonas were effective in the bioaccumulation of lead and cadmium. The amount of 89 mg of lead and 106 mg of nickel could be adsorbed on one gram of Streptomyces biomass-based biosorbent. Such biological remedies can be further explored to remove metals from polluted sites and from metal contaminated industrial or waste waters.
Shorter product life cycles and aggressive marketing, among other factors, have increased the complexity of sales forecasting. Forecasts are often produced using a Forecasting Support System that integrates univariate statistical forecasting with managerial judgment. Forecasting sales under promotional activity is one of the main reasons to use expert judgment. Alternatively, one can replace expert adjustments by regression models whose exogenous inputs are promotion features (price, display, etc). However, these regression models may have large dimensionality as well as multicollinearity issues. We propose a novel promotional model that overcomes these limitations. It combines Principal Component Analysis to reduce the dimensionality of the problem and automatically identifies the demand dynamics. For items with limited history, the proposed model is capable of providing promotional forecasts by selectively pooling information across established products. The performance of the model is compared against forecasts provided by experts and statistical benchmarks, on weekly data; outperforming both substantially.