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 warrenlibrary@ashesi.edu.gh.

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.

 

Communities

Select a community to browse its collections.

Now showing 1 - 3 of 3

Recent Submissions

Item
Skaïgreen: An aerial drone and deep learning project for the counting and nitrogen deficiency detection of coconut trees
(2023-05) Adu-Sarkodee, Emmanuel Nkunim; Eshun, Michael Kwame
This capstone project involved the implementation of a drone system to obtain an aerial view of a coconut farm, with the goal of using deep learning models to detect and count coconut plants, as well as identify nitrogen-deficient plants. The YOLOv5 algorithm was used for object detection, with a unique ID assigned to each plant for counting. A VGGNet convolutional neural network was trained on a dataset of labeled coconut plant images to classify plants as "healthy" or "unhealthy". The results of the project included an automated drone system that could fly and capture footage with a single click, allowing for efficient counting of coconut plants and detection of nitrogen-deficient plants.
Item
Building a Buddy-Up pairing application for the Office of Diversity and International Programs (ODIP) at Ashesi University
(2023-05) Amah, Ngoh Rodney
Today's technology has created opportunities for connecting people faster than it used to two decades ago. Most applications like Twitter, Facebook, and Instagram have shown us how meaningful connections can be fostered effectively and efficiently. Understanding how social networks like Facebook and Twitter are designed and how they handle pairing constraints is essential to creating other systems that connect people. This applied project discusses designing and implementing a student buddy-up pairing system for the Office of Diversity and International Programs (ODIP) at Ashesi University, Ghana. Every academic year, the ODIP pairs continuing student buddies to serve as mentors with incoming first-year students. This pairing aims to ensure incoming first-year students transition well into college life and studies at Ashesi University. Similar to other pairing systems, the proposed system in this applied project handles several user constraints such as gender, preferred nationality, and the number of freshers continuing students would like to be paired with. However, it differs from other matching systems because it applies only a one-way matching relationship. Only continuing students specify the attributes of freshers they would like to be paired with. The outcome of this applied project is a buddy-up pairing application system that pairs freshers and continuing students while incorporating specific constraints.
Item
Ubuntu: An Ashesi group work platform with digitally assisted peer evaluation
(2023-05) Amarteyfio , Philip Kwaku
One of the most essential parts of education is learning how to collaborate with other people to accomplish a particular task or goal. From extremely large tasks such as running a multi-million dollar company to finishing a simple high school group assignment, the ability to work with other people as a team is a major factor in ensuring success. With the advent of technology, collaborative software has become an integral part of teamwork, providing a more organized platform for collaborative work both physically and remotely. However, students at Ashesi University encounter several difficulties when working collaboratively, including organizing team activities and timelines, agreeing on suitable meeting times, and ensuring that all team members make equal contributions. Additionally, the traditional method of evaluating peers through digital and paper surveys has its limitations. To address these challenges, the Ubuntu project presents a web-based collaborative platform specifically for Ashesi students. This web application combines the classic features of collaborative software such as meeting scheduling and task management with uniquely designed features for the academic setting. The highlight of this platform is a digitally assisted peer assessment score calculator to provide an innovative and efficient way of conducting peer evaluations. The platform shows the potential to be an effective collaboration application that contributes to improving the quality of teamwork within the university by providing a more organized way of tackling team activities and also improving peer evaluation.
Item
ROADIO: A system for automated estimation and visualization of crowdsourced road surface quality using mobile phones
(2023-05) Bonsu, Gideon Donkor; Ofori-Addo, Sean
Road infrastructure is crucial for economic growth as it facilitates the transportation of goods, services and people. However, poor road conditions can negatively impact the economy and hinder the timely delivery of goods and services. In Ghana, limited quality road infrastructure remains a challenge, and reliable information on road systems is needed to make informed decisions on infrastructure development. Mobile technology presents a promising opportunity to develop participatory sensing systems for collecting and processing road data. This study aims to further the development of a system for gathering, processing, and displaying data on road surface quality using crowdsourced sensory data from mobile devices in Ghana. The study seeks to create and efficient and cost-effective system that can significantly improve the state of road infrastructure in Ghana by leveraging the advancements in mobile technology and participatory sensing. We designed and implemented a three-tiered architecture software that enables large-scale detection of road surface quality through mobile phones. The system accommodates a machine learning algorithm for classifying road readings from accelerometers, and a service to address the problem of aggregating crowdsourced data which has not been effectively handled in previous research in the Ghanaian context. The classified road surface data is then visualized on a web interface that integrates a Google Maps API.
Item
Career Buddy: A digital system to streamline career-related actions between students and the career centre
(2023-05) Alhassan. Hassan; Ibrahim, Faddal
The fourth industrial revolution has had a significant impact on the global market, leading to increased competition among firms. Consequently, employers are seeking highly skilled employees who can provide substantial value to their organizations. In response, universities have established career services departments to prepare students for the job market. The primary objective of these departments is to assist students in discovering and defining their career paths and achieving their career goals. Ashesi University, like most institutions, has a career services department that requires digitalization to effectively streamline departmental activities and provide students with high-quality career guidance and services. This paper proposes a web application called Career Buddy to aid the Ashesi Career Services Department in enhancing its services. The proposed solution aims to facilitate departmental activities and ensure that students have easy access to career guidance and opportunities. The successful implementation of the proposed solution would enable the Ashesi Career Services Department to efficiently manage its resources and provide students with top-notch career guidance and services. By using Career Buddy, students would have access to a comprehensive suite of career resources and services, enabling them to make informed career decisions and achieve their career goals. Ultimately, this web application would be a valuable asset to the university's career services department and would contribute to the institution's efforts to prepare students for the job market.