Joseph Acquah

Joseph Acquah

Auto-generated profile, based on publicly available information

Joseph Acquah

Mathematical Sciences Department, University of Mines and Technology, Tarkwa, Ghana

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
25 August 2024 in Heliyon
Verified
Journal Article
Open access
JAJoseph Acquah
Joseph Acquah
SBSenyefia Bosson-Amedenu
Senyefia Bosson-Amedenu
FEFrancis Eyiah-Bediako
Francis Eyiah-Bediako
ABAlbert Buabeng
Albert Buabeng
NONoureddine Ouerfelli
Noureddine Ouerfelli
In this paper, an empirical model with the critical number of incidences and deaths for female cancers as adjustable parameters has been developed using life expectancy data from GLOBOCAN world estimates on cancer types. The model was developed based on the cumulative risk and exponential correlation techniques such that the significance of the adjustable parameters ascertains the strength of this research in two ways. First, it indicates indicates the rapid increase in female cancer morbidity with increase in the number of male cancer cases, regardless of incidence or mortality. Second, it suggests that female cancer cases may approach a virtual limiting value as male cancer cases reach extremely high levels. This projection aligns with the global population trends, indicating a proportional increase in cancer cases each year. Additionally, the cumulative risk of cancer incidences of each sex has been modelled separately against the global cumulative risk of cancer incidences of both sexes which revealed regions that have passed their inflection point and those that are yet to reach the inflection point. There was a curvature change, which indicates an inflection point coinciding with the South-Eastern Region and indicating that for the regions beyond the inflection point, the increase of the cumulative risk of cancer incidences of females against that of males is more accentuated compared with the regions before the inflection point. However, when the cumulative risk of cancer mortality of each sex is modelled separately against the global cumulative risk of cancer mortality of both sexes shows a non-linear dependence and the increase is more accentuated for males than for females. This finding indicates that cumulative risk is influenced by factors beyond the male-female population ratio. This study advances cancer studies as it provides a nuanced understanding of gender-specific cancer trends, crucial for developing targeted cancer prevention and treatment strategies. By elucidating the dynamics of cancer incidences and mortalities across different regions and sexes, the findings can inform public health policies and resource allocation to combat cancer more effectively on a global scale.

4 September 2026 in Scientific African
Verified
Journal Article
Open access
JAJoseph Acquah
Joseph Acquah
SBSenyefia Bosson-Amedenu
Senyefia Bosson-Amedenu
ABAlbert Buabeng
Albert Buabeng
Noureddine OuerfelliNoureddine Ouerfelli
Noureddine Ouerfelli

15 January 2024 in Scientific African
Verified
Journal Article
Open access
AJAcquah Joseph
Acquah Joseph
BSBosson-Amedenu Senyefia
Bosson-Amedenu Senyefia
EFEyiah-Bediako Francis
Eyiah-Bediako Francis
AAAnafo Yen Abdulzeid
Anafo Yen Abdulzeid

1 January 2024 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
JAJoseph Acquah
Joseph Acquah
DODamianus Kofi Owusu
Damianus Kofi Owusu
AAAbdulzeid Anafo
Abdulzeid Anafo
A feature selection technique should, in theory, be able to reliably extract pertinent features, identify non-linear feature interactions, scale linearly with the number of features and dimensions, and permit the integration of known sparsity structure. Identifying a machine learning algorithm that performs best given varied distributions may be quite challenging because not all machine learning algorithms are equally created, even though many of them suit very well for a given task. The heterogeneous ensemble feature selection (HETR-EFS) technique learns to combine the feature subsets provided by base feature selectors in an ensemble. Similarly, the stacked ensemble (SE) technique learns how to best combine base classifier models to form a strong model. As a prognostic model for classifying Head and Neck Squamous Cell Carcinoma {HNSCC} recurrence patterns, this study sought to identify the combination of SE classification model and EFS technique that fit optimally when the same ML classifiers for EFS and SE learning are used. Four SE classification models; in which first one used two base classifiers: gradient boosting machine (GBM) and distributed random forest (DRF); second one used three base classifiers: GBM, DRF, and deep neural network (DNN); third one used four base classifiers: GBM, DRF, DNN, and generalized linear model (GLM); and fourth one used five base classifiers: GBM, DRF, DNN, GLM, and Naïve bayes (NB), were developed based on various EFS techniques, using GBM meta-classifier in each case. The results showed that implementing SE technique consisting of five base classifiers on heterogeneous ensemble feature (HETR-EF) subset achieved better performance than achieved on other EF subsets and implementing this SE technique on HETR-EFs achieved better performance compared to other SE techniques implemented on HETR-EFs and other feature subsets used. Thus, learning SE technique having five base classifiers on HETR-EFs is clinically appropriate as a prognostic model for classifying and predicting HNSCC patients’ recurrence data.