Ashesi Institutional Repository
Welcome to the Ashesi Institutional Repository (AIR), an archive for preserving and sharing scholarly work at Ashesi University.
Contributors to the repository ensure that their scholarly and creative work is preserved, indexed and showcased for a global audience. Students who produce strong research work have the privilege of getting their work published on AIR. Ashesi Community members can make submissions through firstname.lastname@example.org.
The repository is organized in "Communities" that group publications by department and/or subject. You can browse the "Community" by Collection, Author, Title, or Issue Date. Alternatively, a search function enables easy access to information.
Select a community to browse its collections.
Using IoT to assist monitoring of the methane gas extraction at Lake Kivu
Methane gas is a powerful greenhouse gas with global warming potential. The current techniques being used to monitor the leaks are expensive and likely onerous and demands for trained operators. There are available solutions tried by the space agencies such as National Aeronautics and Space Administration (NASA) and European Space Agency (ESA) using satellites to better understand the distribution of greenhouse gases on regional and global scales. Those are ENVISAT, GOSAT, OCO-2, and the recently launched TROPOMI instrument on the Sentinel 5P satellite, but all these, regardless of the advanced technology associated cannot pinpoint the source of emissions. In this study, the performance of low-cost Internet of Things (IoT) sensors and isolation forest anomaly detection machine learning technique was implemented. Isolation Forest is one of the outstanding outlier detectors in the real-time DataStream for faulty detection, and money laundering in banking industry. It was tested in this system to improve the accuracy in detecting the methane gas leak. According to the experimental results, the anomaly detection based on isolation forest achieved an excellent performance in terms of accuracy of outlier detection while minimizing the false positives. Decarbonization is an essential component in the climate system, and this plays a key role in reducing methane emissions. Finally, the study presents future research directions to carry out research on the machine learning with Internet of Things (IoT).
Electricity bill calculation for compound houses in Ghana using Artificial Neural Network (ANN)
In Ghana, people live in a housing arrangement where members (tenants) of the household share basic facilities such as washrooms, kitchens and electricity meter - this is called a compound house. Over the years, there have been several complaints regarding these shared facilities but one remains paramount and is the lectric meters. Tenants mostly have concerns about how electricity bills are shared amongst themselves. It is assumed that tenants may not consume electric power as much as others do and as a result conclude bills are not shared fairly. Previous research has been done to verify the ability to spolit bills by implementing the Non-Intrusive Load monitoring system with focus on identifying different appliances used by different tenants. However, this did not take into consideration similar appliances used by different tenants. This paper investigates the possibility of distinguisihing between similar appliances used by different teanants. It was discovered that the Time Series Classification Algorithm had a higher overall performance when compared to the Multilayer Perceptron (MLP) henece is efficient for distinguising between similar applicances used by tenants.
Power optimal inverse kinematics for quadruped robot
Our world of today has become complex and sophisticated, and so have our problems. One of the eye-opening solutions to these problems has been made available through science and technology. Science and technology have given humans the opportunity to engineer life changing solutions. One of these life-changing solutions is a robot. This project is aimed at making a power optimal quadruped robot using inverse kinematics. The MSP430 was used in the embedded systems of this project, along with SG90 servo motors which served as the joints between the body, upper limb and lower limb of my 8DOF quadruped robot. The Inverse Kinematics of the robot was achieved usig the Denavit-Hartenberg convention and with this there was a successful achievement of two gait processes, walking and trotting.
Internet of BioNano Things
Internet of Bio-Nano things refers to the internet of things on a nanoscale where these things can be interconnected to communicate. Similarly, the means of communication of these 'things' can be extended to other application domains, including biological systems. Thus far, nanomaterials such as graphene have inspired the concept of the internet of things; however, some challenges have been encountered concerning trying to deploy these materials in a biological system because they pose a threat to health since they are artificial. This, therefore, inaugurates an idea to reprogramme or administer synthetic bacteria cells for intrabody operations in areas such as the guts of a human body to aid in digestive complications such as gluten intolerance. Essentially, some similarities were discovered between the internet of things and biology, which inspired the various forms of communication, sensing, and actuation of a bacterium cell. Through the use of a motility recognition program, microscopic footage of bacteria activity was processed to provide a graphical representation of bacteria attraction to concentration levels of 30,10, 5, and 0.5 m/l of gluten for a test of concept. Under optimal conditions, for a recorded number of 211 bacteria, their mean speed, mean displacement, mean distance, and mean percentage motile were 9.04, 42.23, 66.59 μ/m, and 96.92, respectively.
Building a low-cost motion capture suit for animation
Motion capture has become a major player in the film and animation industry. Mimicking natural and subtle movements of humans and animals has made animation a lot more believable and engaging. This paper presents a low-cost design of a motion capture unit based on the ESP32 and a 9-DOF inertial sensor Bno055. A calibration method based on a standing posture is used. The sensors data are retrieved via the serial port of the Arduino IDE and sent to Blender, a 3D program, to display real-time motion. If a believable performance can be achieved with low-cost inertial sensors, then the overall cost of existing motion capture technology can be reduced.