Leah Mutanu

Dr. Leah Mutanu

United States International University Africa, Nairobi, Nairobi City, Kenya
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 October 2022 in Sensors
Verified
Journal Article
Open access
PDF file
LMLeah Mutanu
Leah Mutanu
JGJeet Gohil
Jeet Gohil
Khushi GuptaKhushi Gupta
Khushi Gupta
PWPerpetua Wagio
Perpetua Wagio
GKGerald Kotonya
Gerald Kotonya
Automated bioacoustics classification has received increasing attention from the research community in recent years due its cross-disciplinary nature and its diverse application. Applications in bioacoustics classification range from smart acoustic sensor networks that investigate the effects of acoustic vocalizations on species to context-aware edge devices that anticipate changes in their environment adapt their sensing and processing accordingly. The research described here is an in-depth survey of the current state of bioacoustics classification and monitoring. The survey examines bioacoustics classification alongside general acoustics to provide a representative picture of the research landscape. The survey reviewed 124 studies spanning eight years of research. The survey identifies the key application areas in bioacoustics research and the techniques used in audio transformation and feature extraction. The survey also examines the classification algorithms used in bioacoustics systems. Lastly, the survey examines current challenges, possible opportunities, and future directions in bioacoustics.

27 March 2023 in The Electronic Journal of Information Systems in Developing Countries
Verified
Journal Article
Closed access
JNJoshua Rumo Arongo Ndiege
Joshua Rumo Arongo Ndiege
LMLeah Mutanu
Leah Mutanu
FCFoster Christopher
Foster Christopher

7 December 2017 in Service Oriented Computing and Applications
Verified
Journal Article
Closed access
PDF file
LMLeah Mutanu
Leah Mutanu
GKGerald Kotonya
Gerald Kotonya

1 February 2019 in IET Software
Verified
Journal Article
Open access
PDF file
LMLeah Mutanu
Leah Mutanu
GKGerald Kotonya
Gerald Kotonya
Software as a Service reflects a ‘service‐oriented’ approach to software development that is based on the notion of composing applications by discovering and invoking network‐available services to accomplish some task. However, as more business organisations adopt service‐oriented solutions and the demands on them grow, the problem of ensuring that the software systems can adapt fast and effectively to changing business needs, changes in their runtime environment and failures in provided services has become an increasingly important research problem. Dynamic adaptation has been proposed as a way to address the problem. However, for adaptation to be effective several other factors need to be considered. This study identifies the key factors that influence runtime adaptation in service‐oriented systems (SOSs) and examines how well they are addressed in 29 adaptation approaches intended to support SOSs.

29 March 2023 in Software
Verified
Journal Article
Open access
PDF file
LMLeah Mutanu
Leah Mutanu
JGJeet Gohil
Jeet Gohil
Khushi GuptaKhushi Gupta
Khushi Gupta
The last two years have seen a rapid rise in the duration of time that both adults and children spend on screens, driven by the recent COVID-19 health pandemic. A key adverse effect is digital eye strain (DES). Recent trends in human-computer interaction and user experience have proposed voice or gesture-guided designs that present more effective and less intrusive automated solutions. These approaches inspired the design of a solution that uses facial expression recognition (FER) techniques to detect DES and autonomously adapt the application to enhance the user’s experience. This study sourced and adapted popular open FER datasets for DES studies, trained convolutional neural network models for DES expression recognition, and designed a self-adaptive solution as a proof of concept. Initial experimental results yielded a model with an accuracy of 77% and resulted in the adaptation of the user application based on the FER classification results. We also provide the developed application, model source code, and adapted dataset used for further improvements in the area. Future work should focus on detecting posture, ergonomics, or distance from the screen.

16 June 2018
Verified
Book Chapter
Closed access
PDF file
LMLeah Mutanu
Leah Mutanu
GKGerald Kotonya
Gerald Kotonya