2647 research outputs found
Sort by
Development of early warning system for human wildlife conflict using deep learning, IoT and SMS
Get PDFA Project Report Submitted in Partial Fullfilment of the Requirements for the Degree of Master of Science in Embedded and Mobile Systems of the Nelson Mandela African Institution of Science and TechnologyHuman-wildlife conflict is a significant challenge to communities living in areas close to
wildlife game parks and reserves. It is more evident in the United Republic of Tanzania whose
economy depends on agriculture and wildlife tourism as a significant source of income for her
citizens and foreign exchange respectively. The proposed system is a low-power and low-cost
early-warning system using deep learning, Internet of Things (IoT) and Short Message Service
(SMS) to support human-wildlife conflict response teams in mitigating these problems. The
proposed system comprises three basic units: sensing unit, processing unit, and alerting unit.
The sensing unit consists of a Global Positioning System (GPS) module, a passive infrared
(PIR) sensor, and a Raspberry Pi camera. The PIR sensor module detects animal nearby using
its heat signature, the GPS collects and records the current system location while the Raspberry
pi camera takes an image after the PIR sensor has detected the animal nearby using its heat
signature. The processing unit with the main unit uses a Raspberry microcomputer to perform
image inferencing using the “you look only once” (YOLO) algorithm and data processing. The
last unit is an alerting unit that uses Global System for Mobile Communications module to send
an alerting SMS message to the community response team leader and the human-wildlife
conflict response team whenever wild animals are detected near the park’s border. Therefore,
the system detects, identifies, and reports wild animals detected using SMS. General Packet
Radio Service cellular network provides internet connectivity for the purpose of data collection
to enable monitoring and storage in the cloud. An online visualization system was developed
using google maps to show the location of wildlife detected by the camera trap. The park
rangers track the wildlife online to acquire important information before the wildlife wanders
out of the park. This system was developed using the open-source Raspberry pi which is cost effective even for low-income communities who are targeted by the syste
Mobile Based Application for E-Services and E-Payments: a Study Case of Habari Node Public Limited Company in Arusha, Tanzania.
Get PDFA research article was published by EasyChair Preprint № 9835, 2023.Technology is being involved in different sectors to improve service delivery. Habari Node PLC (Public Limited Company), located in Arusha, Tanzania, offers Internet Services and various additional ICT-based business solutions. The company has a website that is used to provide information related to the services they provide with their cost. However, the current website is not mobile user-friendly and is not integrated with an electronic payment to pay for those services because the fees are currently paid manually. This study aimed to develop a Mobile Based Application for E-services and E-payment which will allow the user to access all information related to the services provided by this company and be able to perform e-payment to the subscribes services. The payment will be made through mobile money or credit card, depending on the customer's choice
Highly sensitive biosensor based on a microstructured photonic crystal fibre for alcohol sensing
Get PDFThis research article was published by Elsevier 2023A microstructure alcohol biosensor has been proposed to operate in the wavelength range of 0.8 to 2.0 μm for the
sensing of propanol, butanol, and pentanol, unveiling impressive results of relative sensitivity and confinement
loss. The results are achieved by implementing closely arranged cladding air holes of 3 rings with a single
elliptical core hole for analyte infiltration. Performance evaluation of the sensor was conducted using COMSOL
Multiphysics software and yields relative sensitivity of 96.75%, 89.60%, and 82.02% for propanol, butanol, and
pentanol, respectively, and confinement losses of 5.49 × 10 12 dB/m for propanol, 1.98 × 10 12 dB/m for
butanol, and 9.36 × 10 13 dB/m for pentanol. Other optical parameters have also been analysed that recorded
effective refractive index, high power fraction, low birefringence, small effective area, and large nonlinear co-
efficients. The proposed biosensor is eligible for practical application in alcohol sensing with these results.
Moreover, this proposed biosensor is suitable as a supercontinuum source in optical communication systems
because of the high nonlinear coefficients
Population genetics of the hound needlefish Tylosurus crocodilus (Belonidae) indicate high connectivity in Tanzanian coastal waters
Get PDFA research article was submitted to Marine Biology Research Volume 19, 2023.
The hound needlefishTylosurus crocodilus(Belonidae) is a highly demandedfish in the localmarkets of Tanzania, but the growing coastal population threatens its sustainability. As belonidsare highly migratoryfishes utilising various parts of the seascape, increasedfishing pressuremay disrupt connectivity patterns on different spatiotemporal scales and disaggregatepopulations. Using the COI gene, this study assessed the genetic population structure,connectivity patterns, and historical demography ofT. crocodiluscollected in seven sites spreadalong Tanzanian coastal waters. Results showed fourteen haplotypes with low overallnucleotide and haplotype diversity. Pairwise FSTcomparisons revealed no significant differencesamongthesampledsites,exceptforthenorthernmostsite(Tanga)andanislandinthesouth(Songosongo). Analysis of molecular variance (AMOVA) revealed a non-significant geneticstructure among populations (FST= 0.01782), suggesting thefishery across Tanzanian watersexploits the same population. Moreover, there was no correlative relationship between geneticand pairwise geographic distances, rejecting the isolation by distance hypothesis. However,neutrality tests and mismatch distribution analysis revealed that recent demographic expansionmight exist. Empirical evidence of panmixia suggests high genetic connectivity. In combinationwith low genetic diversity, management shouldbe directed to actions that prevent geneticdiversity loss and the effect of genetic drift on populations
Influence of farmers’ socio- economic characteristics on nutrient flow and implications for system sustainability in smallholdings: a review
Get PDFA research article was submitted to Soil Management volume 3, 2023The rise in global human population, coupled with the effects of climate change,
has increased the demand for arable land. Soil fertility has been the most
affected, among other things. Many approaches to soil fertility management
have been proposed by studies in Sub-Saharan Africa (SSA); however, the
question of sustainability remains. Nutrient monitoring (NUTMON), which
combines biophysical and socio-economic features for soil fertility
management, gives an in-situ soil fertility status of a given land use system,
which ultimately provides guidance in proposing appropriate soil management
techniques in a given land use system. In this review, the Preferred Reporting
Items for Systematic Review and Meta-Analysis (PRISMA) approach was deployed
for a systematic search of the literature materials. The review evaluated various
studies on nutrient monitoring in SSA soils in order to understand the
socioeconomic attributes and their influence on farming systems, as well as
nutrient flow and balances. The review identified two dominant smallholder
farming systems in SSA: mixed crop-livestock and mixed crop farming systems.
Also, this review revealed that most nutrient balance studies in SSA have been
done in mixed crop and livestock farming systems. However, regardless of the
farming systems, the overall mean nutrient balances in all studies, particularly
those of nitrogen (N) and potassium (K), were negative, indicating significant
nutrient mining. The review further revealed a vast range of biophysical soil
fertility management technologies; however, their adoption has been limited by
socio-economic aspects including land ownership, gender, financial position,
literacy level, and access to inputs. Therefore, in view of this situation, integrating
biophysical and socioeconomic disciplines could address the problem of soil
nutrient depletion holistically, thus decreasing the existing negative nutrient
balances in the SSA region
Development of intelligent hybrid power transfer switch to support optimization of water supply scheme: case of Arusha
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 TechnologyWater demand and energy usage are inextricably related in water supply systems, because
using, distributing, and extracting water requires a lot of energy. Any improvement in the
scheme’s energy conservation, particularly pumping conservation, results in a significant
reduction in total operating costs. This necessitates the development of methods for analyzing
and optimizing systems that consume electrical energy, which are typically more complicated
than traditional water systems. Previous techniques had a narrow scope and could not be
applied to all sorts of water supply plan designs and systems. This study explored the viability
of adopting an intelligent hybrid power transfer switch system to mitigate high energy
consumption, and so forth, in order to improve the operation of the Ngaramtoni Water Supply
Scheme, located in Arusha Tanzania. This system detects, transmits, and receives water level
data through an algorithm that is intelligently programmed to switch to the necessary power
source (solar or grid), and it also has additional features like an automatic transfer switch in the
event of a power cut or signal failure and, user safety mode among others. Wi-Fi is used for
output parameters monitoring, while LoRa is used for communication. The power source input
into the pump controller is controlled by the system. The data obtained during the experiment
demonstrates the system's effectiveness and capabilities in terms of switching mechanisms,
water level detection and transmission, data retrieval from the ESP32-WROOM-32
microcontrollers via Wi-Fi and a communication module PZEM-04T-V3.0, and visualization
using the Blynk app and a Liquid Crystal display
Conservation of forest biomass and forest–dependent wildlife population: Uncertainty quantification of the model parameters
Get PDFThis research article was published by Heliyon 9 (2023)The ecosystem is confronted with numerous challenges as a consequence of the escalating human
population and its corresponding activities. Among these challenges lies the degradation of forest
biomass, which directly contributes to a reduction in forested areas and poses a significant threat
to the survival of wildlife species through the intensification of intraspecific competition. In this
paper, a non–linear mathematical model to study the conservation of forest and wildlife species
that are reliant on forest ecosystem within the framework of human population dynamics and
its related activities is developed and analysed. The study assessed the impacts of economic
measures in the form of incentives on reducing population pressure on forest resources as
well as the potential benefits of technological efforts to accelerate the rate of reforestation.
Qualitative and quantitative analyses reveals that economic and technological factors have the
potential to contribute to resource conservation efforts. However, these efforts can only be used
to a limited extent, and contrary to that, the system will be destabilised. Sensitivity analysis
identified the parameters pertaining to human population, human activities, economic measures,
and technological efforts as the most influential factors in the mode
Development of intelligent hybrid power transfers switch to support optimization of water supply scheme: case of Arusha
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 TechnologyWater demand and energy usage are inextricably related in water supply systems, because
using, distributing, and extracting water requires a lot of energy. Any improvement in the
scheme’s energy conservation, particularly pumping conservation, results in a significant
reduction in total operating costs. This necessitates the development of methods for analyzing
and optimizing systems that consume electrical energy, which are typically more complicated
than traditional water systems. Previous techniques had a narrow scope and could not be
applied to all sorts of water supply plan designs and systems. This study explored the viability
of adopting an intelligent hybrid power transfer switch system to mitigate high energy
consumption, and so forth, in order to improve the operation of the Ngaramtoni Water Supply
Scheme, located in Arusha Tanzania. This system detects, transmits, and receives water level
data through an algorithm that is intelligently programmed to switch to the necessary power
source (solar or grid), and it also has additional features like an automatic transfer switch in the
event of a power cut or signal failure and, user safety mode among others. Wi-Fi is used for
output parameters monitoring, while LoRa is used for communication. The power source input
into the pump controller is controlled by the system. The data obtained during the experiment
demonstrates the system's effectiveness and capabilities in terms of switching mechanisms,
water level detection and transmission, data retrieval from the ESP32-WROOM-32
microcontrollers via Wi-Fi and a communication module PZEM-04T-V3.0, and visualization
using the Blynk app and a Liquid Crystal display
Physicochemical and microbiological characterization and of hospital wastewater in Tanzania
Get PDFThis research article was published by Total Environment Research Themes in 2023Given the complex composition of hospital wastewater and the high risk of initiating disease outbreaks, comprehensive monitoring and treatment of hospital wastewater are required to prevent social and environmental consequences. This study investigated the physicochemical and microbiological characteristics of wastewater from the Benjamin Mkapa Hospital in Dodoma Tanzania. The wastewater from this hospital is treated in a horizontal flow Constructed Wetland (CW) planted with Typha latifolia before being discharged into the environments. Wastewater samples were collected at the CW inlet and outlet from 02nd May 2022 to 25th July 2022. The results shows that the effluent discharged had pH 7.48 ± 0.63, electrical conductivity 2441 ± 623 µS/cm, Total dissolved solids 1305.5 ± 396 mg/L, Total suspended solids 49.17 ± 53.11 mg/L, Turbidity 9.1 ± 14.83 NTU, COD 170.4 ± 40.6 mg/L, BOD5 74.8 ± 33.5 mg/L, NO3-N 45.4 ± 39.97 mg/L and PO4-P 4.52 ± 2.30 mg/L. The CW removed TSS by 82% and turbidity 94%. COD, BOD and NO3-N were removed by 48%, 47% and 58% respectively. E. coli concentration in effluent samples ranged from 1.1 × 101 CFU/mL to 1.1 × 102 CFU/mL with an average of 1.77logCFU/mL. Average BOD5/COD ratio was 0.5 and 0.4 for influent and effluent respectively. The effluent contained higher levels of EC, TDS, and PO4-P than the influent. According to the findings of this study, most of the parameters of wastewater effluent discharged wasn't within the effluent discharge standards
Deep learning model for predicting stock prices in Tanzania
Get PDFA Dissertation Submitted in Partial Fulfillment of the Requirements for the Degree of Master’s in Information and Communication Science and Engineering of the Nelson Mandela African Institution of Science and Technologye prediction models help to provide investors with tools for making better data driven decisions. Machine learning and deep learning techniques have been successively
utilized in various countries to develop these models. However, there is a shortage of literature
on the efforts to exploit these techniques to forecast stock prices in Tanzania. Hence, this study
was conducted to address this gap. The study selected active companiesfrom the Dar es Salaam
Stock Exchange (DSE) and developed Long Short-Term Memory (LSTM), Bidirectional Long
Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU) models to forecast the next
day closing prices of the companies. Long Short-Term Memory was the overall best model
with a Root Mean Square Error (RMSE) of 4.1818 and Mean Absolute Error (MAE) of 2.1695.
Findings revealed that it was significant to account for the number of outstanding shares of
each company when developing a joint model for forecasting the stock prices of multiple
companies. Specifically, LSTM attained an RMSE of 10.4734 before accounting for
outstanding shares and 4.7424 after accounting for outstanding shares, showing an
improvement of 54.72%. Furthermore, findings showed that investors’ participation attributes
helped to improve prediction accuracy. Specifically, LSTM realized an RMSE of 4.1818 when
these attributes were appended from that of 4.7424 without them, showing an improvement of
11.8%. The resulting model was deployed in a web-based prototype, whereby, end-user
validation results indicated that 76% of respondents rated the system as High in terms of its
forecasting ability. In future, the study recommends exploration of more features