Research
Research & Publications
My research investigates methods for detecting and characterizing concept drift and data drift in streaming, non-stationary environments. I develop detectors, classifiers, scoring mechanisms, and statistical metrics suited to real-world adaptive ML systems.
Drift Detection
Feature-rank based methods, KS-test applications, distribution shift measurement in 2D and high-dimensional streams.
Adaptive Classifiers
Ensemble and multi-classifier systems that maintain accuracy under distribution changes in non-stationary data.
Statistical Metrics
Drift scoring, visualization, and quantification moving beyond binary detection to graded measures of drift severity.
Time Series & Likelihood
Likelihood functions for MA and ARMA models; applied to water supply forecasting and epidemiological modeling.
Journal Publications
A novel method for drift detection in streaming data based on measurement of changes in feature ranks
Piotr Porwik, Tomasz Orczyk, Krzysztof Wrobel, Benjamin Mensah Dadzie
Journal of Artificial Intelligence and Soft Computing Research, Vol. 15, Issue 2 (March 2025)
View Paper →A new concept drift detection method based on the ranking of features in data stream
Krzysztof Wrobel, Piotr Porwik, Tomasz Orczyk, Benjamin Mensah Dadzie
Procedia Computer Science, Vol. 225, pp. 3294–3302 (2023)
View Paper →Detection of data drift in a two-dimensional stream using the Kolmogorov-Smirnov test
Piotr Porwik, Benjamin Mensah Dadzie
Procedia Computer Science, Vol. 207, pp. 168–175 (2022)
View Paper →Epidemiological Modelling of Yellow Fever Dynamics
H. Otoo, L. Brew, B. Dadzie-Mensah
Asian Research Journal of Mathematics, 20(8), pp. 119–141 (2024)
Existence of Solutions of a Convolution Integral Equation
H. Otoo, B. Dadzie Mensah, L. Brew
Journal of Applied Mathematics and Physics, 12(5), pp. 1835–1847 (2024)
The Impact of External Debt on the Economic Growth in Ghana
I. Adubofour, T. Mangudhla, B. Dadzie Mensah
EPRA International Journal of Economics, Business and Management Studies, Vol. 8, Issue 9 (2021)
Conference Publications
Feature-Based Drift Detection in Non-Stationary Data Streams Using Multiple Classifiers: A Comprehensive Analysis
Benjamin Mensah Dadzie, Piotr Porwik
17th Asian Conference on Intelligent Information and Database Systems (ACIIDS 2025), pp. 276–291
View Paper →Concept Drift Scoring and Visualization
Tomasz Orczyk, Benjamin Mensah Dadzie
Recent Challenges in Intelligent Information and Database Systems, pp. 48–58
View Paper →