2647 research outputs found
Sort by
A smart environmental monitoring system for data centres using IOT and machine learning
Get PDFA Project Report Submitted in Partial Fulfilment of the Requirements for the Degree of
Master of Science in Embedded and Mobile Systems of the Nelson Mandela African
Institution of Science and TechnologyData centres are a crucial part of many organizations in the world today consisting of expensive
assets that store and process critical business data as well as applications responsible for their
daily operations. Unconducive environmental conditions can lead to decline in performance,
sporadic failures and total damage of equipment in the data centers which can consequently
lead to data loss as well as disruption of the continuity of business operations. The objective of
this project was to develop an environmental monitoring system that employs Internet of
Things (IoT) and machine learning to monitor and predict important environmental parameters
within a data centre setting. The system comprises of a Wireless Sensor Network (WSN) of
four (4) sensor nodes and a sink node. The sensor nodes measure environmental parameters of
temperature, humidity, smoke, water, voltage and current. The readings captured from the
sensor nodes are sent wirelessly to a database on a Raspberry Pi 4 for local storage as well as
the ThingSpeak platform for cloud data logging and real-time visualization. An audio alarm is
triggered, and email, Short Message Service (SMS), as well as WhatsApp alert notifications
are sent to the data centre administrators in case any undesirable environmental condition is
detected. Time series forecasting machine learning models were developed to predict future
temperature and humidity trends. The models were trained using Facebook Prophet, Auto Regressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ES)
algorithms. Facebook Prophet manifested the best performance with a Mean Absolute
Percentage Error (MAPE) of 5.77% and 8.98% for the temperature and humidity models
respectively. In conclusion, the developed environmental monitoring system for data centers
surpasses existing alternatives by integrating forecasting capabilities, monitoring several
critical parameters, and offering scalability for improved efficiency and reliability. The study
recommendations include exploring a Web of Things (WoT) approach and incorporating
instant corrective measures for improved performance
Investigating the Optimal Treatment to Improve Cashew Apple Juice Quality and Shelf Life
Get PDFThis research article was published in the Journal of Food Processing and Preservation, Volume 2023, Article ID 4155761, 12 pages, 2023An investigation was carried out to extend the shelf life of cashew apple juice (CAJ) by up to 90 days from its natural shelf life. CAJ was obtained by pressing apples. Then, extracted juice was clarified, pasteurized, and added with preservatives, citric acid (0.01%), and sodium benzoate (0.01%). The juice was analyzed for physicochemical qualities, sugars, microbial (total bacteria, yeast, and mould) and sensory evaluation tests for appearance (yellow and brown color), aroma, and taste (astringent, bitter, and sweet). CAJ was stored at refrigeration (4°C) and ambient temperature (22.6-32.5°C) for 90 days. Sensory and shelf life analyses were conducted at 0, 15, 30, 45, 60, 75, and 90 days during storage. The results showed that cashew apple juice had strong vitamin C content (256.5 mg/100 mL). At ambient storage, there was high decrease of vitamin C (6.2-59.8%) and low decrease at refrigeration storage (1.6-10.5%). pH was found to decrease (4.4-3.15) and TSS (11–10.6°Bx), while titratable acidity (0.4–0.59%) increases with time at refrigerating storage. Also, at ambient storage, CAJ showed the similar trend, having decrease in pH (4.4-3.06) and TSS (11-10.3°Bx), while titratable acidity increased (0.4-0.61%). Moreover, sugar content for juice had minimum and maximum decrease at refrigeration and ambient temperatures, respectively. Storage at ambient temperature resulted in growth of microbes which was observed after 15 days for juices without preservatives and 75 days for juices with preservatives, with no E. coli growth. Juice on refrigeration had higher intensity of yellow color (7.50) and sweetness (5.58) while low intensity for astringency (1.58) (). Sensory evaluation of the beverage was found to be satisfactory. Thus, shelf life of cashew apple juice was extended to 90 days satisfactorily, ensuring consumption-safe parameters and satisfactory sensory qualities
Characterization of fruit juices and effect of pasteurization and storage conditions on their microbial, physicochemical, and nutritional quality
Get PDFThis research article was published in the Journal of Food Bioscience Volume 51, February 2023Characterization, pasteurization and storage are essential steps in fruit juice processing. Watermelon, pineapple, and mango juices were pasteurized at 80 ± 2 °C and held at different treatment times (1, 2.5, 5, 10, and 15 min). Juice yield, pH, proximate composition, total soluble solids, color, vitamin C, microbial quality, mineral content, enzyme activity (polyphenol oxidase (PPO), and peroxidase (POD)), total phenolic content, and antioxidant capacity were measured during pasteurization and cold storage (4 °C). Results showed that watermelon juice had the highest crude protein, pH, and moisture content, pineapple juice had the highest titratable acidity, vitamin C and mineral content (potassium, calcium, magnesium, manganese, and zinc) and mango juice had the highest juice yield, and total soluble solids. Regardless of the holding time, pasteurization reduced total plate counts and yeast and molds to below detectable limits (1 log CFU/mL). Vitamin C was undetectable in watermelon juice after 10 min of pasteurization compared to mango juice with a 27% reduction. Pasteurization preserved mango juice color, but watermelon juice became less red and more yellow with increasing treatment time. POD was more thermoresistant than PPO and needed a treatment time of at least 5 min to obtain 80% reduction. Storage of more than 9 days negatively affected the watermelon color, total phenolic content and antioxidant capacities of watermelon juice pasteurized at 15 min and vitamin C content of unpasteurized mango juice. Thus, pasteurization and storage affect fruit juice quality depending on the type of fruit and their composition
Extreme Rainfall Event Classification Using Machine Learning for Kikuletwa River Floods
Get PDFA research article was submitted to Water 2023, volume 15Advancements in machine learning techniques, availability of more data sets, and increased computing power have enabled a significant growth in a number of research areas. Predicting, detecting, and classifying complex events in earth systems which by nature are difficult to model is one such area. In this work, we investigate the application of different machine learning techniques
for detecting and classifying extreme rainfall events in a sub-catchment within the Pangani River Basin, found in Northern Tanzania. Identification and classification of extreme rainfall event is a preliminary crucial task towards success in predicting rainfall-induced river floods. To identify a rain condition in the selected sub-catchment, we use data from five weather stations that have been labeled for the whole sub-catchment. In order to assess which machine learning technique is better suited for rainfall classification, we apply five different algorithms in a historical dataset for the period of 1979 to 2014. We evaluate the performance of the models in terms of precision and recall, reporting random forest and XGBoost as having the best overall performances. However, because the class distribution is imbalanced, a generic multi-layer perceptron performs best when identifying
heavy rainfall events, which are eventually the main cause of rainfall-induced river floods in the Pangani River Basi
Assessing protected area effectiveness in western Tanzania: Insights from repeated line transect surveys
Get PDFA research article was submitted to The African Journal of Ecology Volume 61, Issue 3 September 2023In many parts of East Africa, wildlife populations have declined over the past decades. Given these trends, site-based studies are needed to assess how protected areas with differing management strategies enable the effective conservation of wildlife populations. In Tanzania, game reserves are managed for tourist hunting, while national parks are managed for non-consumptive wildlife-based tourism. To assess the relative performance of these management strategies, we here focus on two areas: Rukwa Game Reserve (RGR) and Katavi National Park (KNP). Based on systematically designed line distance surveys in 2004 and 2021, we compared densities and group sizes of large mammal populations (African elephant, giraffe, buffalo, zebra, topi, and hartebeest) over time. Contrary to published ecosystem-wide declines observed in numerous species which considered earlier baselines, we did not detect significant population declines between 2004 and 2021. While these new results showing apparent stable populations do not invalidate earlier studies on wildlife declines, they could indicate a stabilisation phase after declines. This highlights the importance of considering appropriate temporal baselines and historical contexts when assessing conservation effectiveness
Viability of non-edible oilseed plants and agricultural wastes as feedstock for biofuels production: A techno-economic review from an African perspective
Get PDFThis research articles was published in Journals Biofuels Bioproducts& Biorefining Volume 17, Issue 5,2023Given the benefits of biofuels over conventional fuels, there is concern that widespread production of biofuels from edible feedstocks to meet demand will lead to food insecurity and other socioeconomic challenges. Thus, the goal of this research is to look into the techno-economic potential of non-edible oilseed plants and agricultural wastes as primary feedstocks for biofuel production in Africa. The inability of biofuel to cope in the fuel market has been demonstrated to be due to the high production costs, which limit profitability because the end price is heavily influenced by that of conventional fuel. However, the high production costs are entirely due not only to components such as feedstock, conversion processes, and infrastructure but also to a lack of techno-economic assessment (TEA). African biofuel production can be competitively industrialized through the adoption of strong supportive policies and programs. Adoption of these policies and programs is critical for capitalizing on the benefits of non-edible feedstocks in biofuel production while also boosting rural development through job creation. Techno-economic assessment of conversion processes and infrastructure is recommended to provide a clear picture of the techno-economic aspects, serving as a blueprint for the design of biofuel production facilities. Further, TEA has been shown to be a useful tool in the development process of new technologies aimed at lowering overall production costs and making biofuel more affordable. The combination of TEA and enabling policies and programs will increase the price competitiveness of biofuels, allowing them to capture a sizable share of the fuel market. © 2023 Society of Industrial Chemistry and John Wiley & Sons Ltd
Antibiotic Resistance Patterns of Escherichia coli, Klebsiella pneumoniae, and Pseudomonas aeruginosa Isolated from Hospital Wastewater
Get PDFThis research article was published by Applied Microbiology in 2023Antibiotic-resistant bacteria (ARB) and antibiotic resistance genes (ARGs) in treated hospital wastewater effluents constitute a major environmental and public health concern. The aim of this study was to investigate the antibiotic resistance patterns of Escherichia coli, Klebsiella pneumoniae, and Pseudomonas aeruginosa isolated from wastewater effluent at the Benjamin Mkapa Hospital (BMH) in Dodoma, Tanzania. These bacteria were selected to represent the most prevalent gram-negative bacteria found in hospital wastewater, and they have the potential to generate resistance and spread resistance genes to antibiotics. The wastewater BMH is treated in a Constructed Wetland (CW) planted with Typha latifolia before being released into the environment. The bacteria were isolated from wastewater effluent collected at the outlet of the CW. Isolated bacteria were analyzed for antibiotic resistance by disc diffusion method. Molecular identification of bacterial species was performed by using 16S rRNA. The results show that Klebsiella ssp. was the most common isolate detected, with a prevalence of 39.3%, followed by E. coli (27.9%) and Pseudomonas ssp. (18.0%). Klebsiella ssp. were more resistant than Pseudomonas ssp. for Tetracycline, Gentamycin, Ciprofloxacin, and Sulfamethoxazole. Pseudomonas ssp. were more resistant than Klebsiella ssp. for Ceftriaxone and Azithromycin. Klebsiella ssp. harbored more resistance genes (40%), followed by Pseudomonas ssp. (35%) and E. coli (20%). The findings of this investigation indicate that the effluent from the CW requires additional treatment to reduce discharged ARB and ARGs in the receiving water bodies. As a result, the effluent quality of the CW should be continuously monitored and assessed, and further developments for treating the final effluent are necessary
Geochemistry of Potentially Toxic Elements in Soil and Sediments of a Tanzanian Small-Scale Gold Mining Area
Get PDFthis article is published at scientific research publishing at 17,november 2023Small-scale gold mining is linked to significant environmental pollution by
potentially toxic elements (PTEs). However, research on the pollution caused
by such mining activities remains insufficient especially in developing coun-
tries. In the present study, a systematic investigation assessed the pollution
and level of ecological risk of PTEs in soil and stream sediments in an active
small scale gold mining area of Isanga, in Nzega, Tanzania. Samples amount-
ing to 16 soil and 20 sediment were gathered from the study area and ana-
lyzed for five PTEs concentrations (As, Cd, Cr, Hg and Pb) using the AAS
method. The contamination level and ecological risk were assessed using sev-
eral pollution indices. The results suggest that the assessed environmental
systems of the Isanga mining area and its vicinities are lowly contaminated by
PTEs and have a low potential to pose ecological risks. Hg and Cd with mean
concentrations of 0.09 mg/kg and 0.26 mg/kg respectively were found to be
the most enriched PTEs in soil, compared to their average continental crust
concentrations (0.056 mg/kg and 0.102 mg/kg respectively). The levels of the
evaluated PTEs in the study area are susceptible to increase over time if
proactive steps are not taken to control mining and waste disposal activitie
Machine learning model for predicting Peste des Petits Ruminants
Get PDFThis research article was published by IEEEPeste des petits ruminants (PPR) is a viral disease that affects small ruminants and is prevalent in many developing countries, particularly in Africa and Asia. It can spread through direct contact, air, and contaminated feed and water. PPR can result in significant economic losses and has a detrimental impact on small ruminant production and trade. Clinical signs include fever, respiratory distress, and diarrhoea, and prevention is primarily through vaccination with a live attenuated vaccine. In this study, 24 samples were selected, pre-processed and synthesized using the Conditional Tabular Generative Adversarial Networks (CTGAN) model. Feature extraction was performed, revealing difficult_breathing as the most important feature in predicting PPR in ruminants. The study used Random Forest Classifier which was fine-tuned using Bayesian Optimization to attain an accuracy of 91%
An Integrated Deep Learning-based Lane Departure Warning and Blind Spot Detection System: A Case Study for the Kayoola Buses
Get PDFThis research article was published by IEEEDeep learning-based driver assistance systems (ADAS) have attracted interest from researchers due to their impact on improving vehicle safety and reducing road traffic accidents. In Uganda, road accidents have continued to soar with an increase of up to 42% in 2021 due to the growing road traffic density. To curb the high rates of road accidents, especially for heavy-duty vehicles, Kiira Motors Corporation a state-owned mobility solutions enterprise needs advanced driver assistance systems for improved safety of their market entry products- the Kayoola buses. This research presents an approach to vehicular safety enhancement through the integration of Lane Departure Warning (LDW) and Blind Spot Detection systems (BSD) using advanced deep learning algorithms. The resultant LDW and BSD system is realized on the Raspberry Pi platform, incorporating diverse sensors. By combining these advanced features, the study not only bridges an essential research void but also offers a practical resolution to pressing road safety concerns in the East African context. The integration of LDW and BSD systems through deep learning techniques marks a pivotal advancement in vehicular safety. The lane detection model was tested on DET and TuSimple datasets. Our model attained a mean F1 Score of 77.59% and a mean IoU of 65.26% on the Dataset for Lane Extraction (DET) and an overall accuracy of 97.96% on the TuSimple dataset. Our work presents an integrated lane departure warning and blind spot detection system that will be able to alert the driver using the graphical user interface, and auditory feedback. The anticipated real-world implementation is poised to substantiate the system’s effectiveness, thereby contributing to safer roads regionally and inspiring innovation in automotive engineering by leveraging artificial intelligence