Oluwambo Tolulope Olowe

Oluwambo Tolulope Olowe

Auto-generated profile, based on publicly available information

Oluwambo Tolulope Olowe

Department of Computer Science, Landmark University, Omu Aran, Nigeria

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
1 September 2025 in Data Science and Management
Verified
Journal Article
Open access
EAEmmanuel Oluwatobi Asani
Emmanuel Oluwatobi Asani
MAMojiire Oluwaseun Ayoola
Mojiire Oluwaseun Ayoola
EAEmmanuel Tunbosun Aderemi
Emmanuel Tunbosun Aderemi
VAVictoria Oluwaseyi Adedayo-Ajayi
Victoria Oluwaseyi Adedayo-Ajayi
JAJoyce A. Ayoola
Joyce A. Ayoola
OOOluwambo Tolulope Olowe
Oluwambo Tolulope Olowe

24 September 2025 in Data in Brief
Verified
Journal Article
Open access
OOOluwambo Tolulope Olowe
Oluwambo Tolulope Olowe
AAAyodele Adebiyi
Ayodele Adebiyi
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
This study introduces the Building Materials Dataset as a comprehensive resource for analyzing historical and real-time fluctuations in construction material prices in Nigeria. The dataset was compiled through structured surveys with material suppliers and secondary data from reputable online marketplaces and industry reports. Designed to support cost estimation, procurement planning, and financial forecasting, it enables researchers, policymakers, and industry professionals to assess market trends, optimize budgeting strategies, and mitigate financial risks associated with price volatility. Structured in a tabular, time-series format, the dataset captures key information on material types, pricing variations over multiple years, and economic factors influencing costs. Preprocessing steps included data cleaning, Min-Max normalization, and feature engineering to enhance predictive modeling. The dataset was integrated into the BuildCES system, where a Long Short-Term Memory (LSTM) model was applied for price prediction and cost estimation, facilitating data-driven procurement optimization and contract management. Future enhancements will incorporate Blockchain technology to ensure transaction transparency, real-time pricing updates via API integration, and geospatial data mapping to analyze regional price disparities. By systematically documenting construction material prices in Nigeria, this dataset addresses the gap in structured data availability, providing a scalable foundation for research, industry benchmarking, and policy development. By fostering a data-driven approach to construction management, the dataset contributes to economic stability, transparency, and sustainability in the industry.

5 May 2026 in Computers & Industrial Engineering
Verified
Journal Article
Open access
OOOluwambo T. Olowe
Oluwambo T. Olowe
AAAyodele A. Adebiyi
Ayodele A. Adebiyi
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa

27 July 2026
Verified
Book Chapter
Closed access
PDF file
EIEmmanuel O. Igbekele
Emmanuel O. Igbekele
OOOluwambo T. Olowe
Oluwambo T. Olowe
BMBliss Momoh
Bliss Momoh
Music is one of the soul-lifting and atmosphere-changing acts of modern times. It has helped the sick get better in time, the emotionally down-trodden have been found to be re-invigorated by listening to music. Knowing the genre of music, one is emotionally attached to can be a life-changing knowledge. Machine Learning over the last few decades has made major advances in establishing the boundaries of genres for music. XGBoost is one especially valuable technique in the area of classification. This study traces the development from primitive methods to the advanced methods we use in modern times for investigating how XGBoost has influenced the way we allocate categories of music. Gradient boosting was used in evaluating complicated auditory data and discover previously undetected trends, which resulted in outstanding genre classifications. But there are barriers in the way. One of the main issues involves finding a range of relevant audio datasets for the models‘ training. In this study, we demonstrate the extraordinary ability of XGBoost to enhance paying attention, accuracy, adaptability, and communication possibilities for both great lovers of music and business people. <!----> <!----> <!----> <!---->