SU+ Digital Repository

SU+ is an online repository for the preservation and promotion of assorted digital content at Strathmore University

Off-Campus Access to restriced resources (including the ExamsBank) now requires registration using an @strathmore.edu email address

Authentication is NOT required for On-Campus Access to content

Photo by @inspiredimages

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 5 of 7

Conferences / Workshops / Seminars + 474
Documents and Proceedings of Conferences, Seminars, Workshops (and more) held at Strathmore University
Digital Archives 178
Assorted collections of resources covering various subject themes contributed by Faculty and Library Staff
Reports / Policies + 10
Public reports and policy documents
Research / Researchers / Publications 4412
Researcher Profiles / Conference presentations / Published research articles / Faculty and Corporate research outputs
Strathmore Heritage Collection 41
A digital chronicle of the History of the University presented through a mix of pictures, videos and digitized publications

Recent Submissions

A Low cost automatic cooking oil vending machine for small scale traders
(Strathmore University, 2024) Koi, G. A.
People are always looking for convenience in handling commodities and other basic needs in life and vending machines have played a vital role in making human life easier. However, due to the nature and design of vending machines, they are either too expensive or too large to meet a small-scale trader’s needs. Most small-scale sellers have limited resources and small spaces for operation, introducing the vending machines present in the market would be very costly and will occupy a lot of space leaving them with limited or no space to operate in. Therefore, small-scale traders remain comfortable with the old ways of manually measuring liquids, in this case the cooking oil, as the new technology in liquid dispensing does not cater to their needs. In this study, a low cost automatic cooking oil vending machine that allows the desired amount of oil to be dispensed was fabricated. Though there are some earlier versions of these machines available, this study focused on providing a low cost, simple design that could be easily accessed by small scale traders. This enables easy and accurate measurement in the selling of cooking oil eliminated physical measuring. It is a cheap and efficient way of selling cooking oil, simple and specific to a local seller. The main objective of the study was to develop a low cost automatic cooking oil vending machine for small scale traders. This encompassed looking into existing technologies used by automatic vending machines and the limitations of the current vending machines for small scale traders. The researcher went ahead to design, develop and test the cooking oil vending machine for small scale traders. The study employed a descriptive research design. The various identified features formed the basis for crafting the system tests for the final developed system. An Agile Software development methodology was also employed and the system underwent four main phases: Designing, Development, Testing and Deployment. Key Words: Arduino-Uno microcontroller, Small scale traders, Vending machines, Cooking oil.
A Model for predicting tea yield for enhanced food security in Kenya
(Strathmore University, 2024) Masai, J. J.
The increasing uncertainty caused by climate change and its effects on crop yields have made it essential to develop accurate predictive models for crop yield in Kenya. By accurately predicting crop yields, stakeholders can effectively plan and manage crop production, ensuring food security and preventing potential food emergencies. This study aims to address this need by utilizing artificial intelligence techniques to develop a predictive model specifically for tea crop yield. The developed model leverages on machine learning algorithms to analyze historical data on tea yield, rainfall, temperature, soil water deficit, and hail damage. These variables are crucial factors influencing tea crop production in Kenya. By training the model with this data, it was able to make predictions about future tea crop yields. The performance and accuracy of the model was evaluated using the Root Mean Squared Error (RMSE) metric, which measures the differences between the predicted and actual values. The outcomes of this research underscore the potential of artificial intelligence techniques in accurately predicting tea crop yield. Leveraging machine learning algorithms and historical data on crucial variables such as tea yield, rainfall, temperature, soil water deficit, and hail damage, the developed model shows promising predictive prowess. This research augments agricultural planning and management practices, bolstering food security and resilience amidst the uncertainties posed by climate change. Key words: artificial intelligence, climate change, crop yield, food security, Kenya, machine learning, predictive modeling.
A Web application for reporting and identification of missing persons in Kenya
(Strathmore University, 2024) Koima, L. J.
In Kenya, the escalating number of missing individuals, including both children and adults, has become a pressing issue. The existing methods for reporting missing persons are often inefficient, relying heavily on manual processes that consume significant time and resources. This research endeavours to tackle this challenge by developing a web-based system designed to manage cases of missing individuals. Central to this system is the integration of a facial recognition module, allowing for the comparison of facial features against a centralized database of missing persons. This integration aims to enhance the efficiency and accuracy of the search process. Authorized personnel are granted access to update and maintain the missing persons database within the system, further streamlining the search process. Additionally, the system incorporates Google Maps functionality, enabling users to pinpoint the precise location of a disappearance or where an individual was found. To ensure unbiasedness and effectiveness, the system underwent rigorous testing and evaluation using a diverse range of facial images. This evaluation aimed to verify its performance across various facial types while guarding against biases or discriminatory outcomes. By offering an efficient and precise mechanism for reporting and searching for missing persons, this research strives to enhance the efficacy of reuniting individuals with their families, thereby addressing the critical need for improved missing persons management in Kenya.
An Intelligent chatbot implementation for early detection and intervention for anorexia nervosa
(Strathmore University, 2024) Ochieng, R. A. J.
Anorexia nervosa (AN), an exhausting and potentially fatal eating disorder, has long been a significant public health concern. Characterized by extreme eating habits and an intense fear of gaining weight, this disorder may lead to other mental illnesses such as depression, obsessive compulsive disorder (OCD), borderline personality disorder (BPD) and sometimes self-harm. Notwithstanding its devastating consequences and prevalence amongst adolescence and youths especially women, its early detection and intervention remains challenging. This research presents a novel approach in addressing anorexia through utilization of random forest, a machine learning algorithm and natural language processing to create an intelligent chatbot for detection and provision of personalized intervention for anorexia patients. The chatbot is built based on RASA framework and it is deployed on Telegram, a social media platform where it can engage users in supportive dialogues to detect potential risk factors and deliver timely intervention for anorexia nervosa. The implications of this research underscore the value of machine learning in mental health detection and treatment. Besides provision of a toolkit that could be used by medical practitioners, it introduces an accessible means of reaching individuals who may not seek help through the conventional means. Additionally, it connects individuals to health care professionals and support networks enhancing early detection and reducing further complications. To assess the feasibility of the proposed concept, a functional chatbot prototype was developed using a Rapid Application Development (RAD) approach. The training and testing data were split n an 80/20 ratio, and the Telegram messaging platform was utilized for user interaction testing. While the study presents promising results, some of the limitations included constraints of limited data set and the need for ongoing refinement of the chatbot’s algorithm. There is also limited research regarding anorexia. Future studies could investigate refining the technology, expanding the dataset, and addressing ethical concerns around mental health with an aim to contribute to more effective and accessible mental health support. Keywords: Anorexia, Chatbot, Machine Learning, Natural Language Processing, Eating Disorder, Sentimental Analysis
Application of Internet of Things (IoT) sensors to support electrical load planning in solar-powered resorts in Kenya
(Strathmore University, 2024) Murungi, T. M.
Internet of Things (IoT) has evolved has emerged as a powerful new technological paradigm in recent years. It makes it possible to interconnect all types of physical objects and offers real-time collection and processing of sensor data. The rapid development of renewable energy sources, in particular solar energy, has resulted in an increase in availability of clean electrical power that can be efficiently stored and utilized. However, the variability of solar energy based on weather conditions affects its reliability. This makes it difficult for the planning and performing of tasks in resorts, which harness solar energy, such as laundry and food preparation, that require electrical power. This thesis investigates the adoption of Internet of Things (IoT) to optimize the use solar power for meeting electricity demand at solar-powered resorts. This thesis seeks to implement a system that automatically alternates between grid power and solar energy sources, with the aim of optimizing solar energy utilization by performing load planning. This will be achieved by considering the predetermined electrical demand of the resort, employing a predictive model, and using real-time Internet of Things (IoT) sensor data. The prediction model will project solar energy generation which will be compared with real-time IoT sensor readings, for load planning purposes. For the predetermined electrical load of the resort, the system will automatically transition between grid power and solar energy based on whether the two values align or exceed a predefined system threshold. The predictive model will use weather forecast data obtained from publicly accessible sources on the internet, which are usually an approximation, as its input while the IoT sensors will capture real-time measurements relating to weather conditions, solar energy generated and subsequently stored. The overall objective is to optimize the utilization and load planning of solar-generated electrical energy in solar-powered resorts. Ultimately the system will facilitate determination of adequate capacity of expensive solar power storage systems and minimization of the volume of consumed grid electricity. This research adopts an analytical and prototyping methodology. The research will review literature on off-grid solar power installations and their control systems, IoT architectures and Machine Learning techniques which will be adopted in designing the predictive model. Keywords: solar energy; prediction models; energy management; load planning; Internet of Things (IoT) machine learning; renewable energy forecasting; solar powered resorts