Assigning a written document to one or more classes or groups is referred to as this task. We will go over a number of fundamental supervised text classification techniques, such as Decision Trees (DT), Naive Bayes, Support Vector Machines (SVM), Logistic Regression, and k Nearest Neighbor (kNN).
Author(s) Details
Adebola K. Ojo
Department of Computer Science, University of Ibadan, Ibadan,
Nigeria.
Please see the book here:- https://doi.org/10.9734/bpi/mono/978-81-972870-5-3/CH11
The increase in demand for gold in the world over the past
three decades has witnessed an increase in the gold price to accommodate more
efforts of mining and exploration in the gold mining industry. Categorization
of gold mines based on rom-tonnage and grade would be more useful if it can
statistically be used to predict the cost of gold mining. This paper focuses on
establishing logistic and ANN models of the cost effect of run-of-mine tonnage
and grade in the justification of the categorization of gold mines. Gold mines
could be categorized based on the abilities of rom-grade and rom-tonnage to
predict cost. The data used in the generation of the logistic and ANN models
were cash-cost as the dependent variable vs. rom-grade, and rom-tonnage as
independent variables together with the type of mine. The data were obtained
from 160 gold mines selected from the top 20 gold-rich countries in the period
of 7 years from 2002 to 2008. The first analysis was the Logistic Regression
Analysis which was carried out in the SPSS software to determine the
probability of occurrence of low cost given rom-grade and rom-tonnage for
either an open pit, underground, or both mines together. The second analysis
was based on ANN which was carried out to develop the ANN model. Using a
Multilayer perceptron neural network and backpropagation, the ANN Model was
trained to predict the cost. The main results for both logistic and ANN Models
indicated that only rom-grade with a cut-off value of 5.385 g/t can be used to
categorize gold mines as low and high grade while there was not enough evidence
to categorize gold mines based on their rom-tonnage. The only evidence provided
by ANN indicated that the normalized importance of rom-grade was 100% while for
rom tonnage was 48.65. The full models established in this study have a
percentage correct of 62.9 for logistic and 64 for ANN compared to 57.9 by
guess. The relationship between cost vs. rom-grade and rom-tonnage indicated
that only 6.9 percent of the cost is accounted for by rom-grade and
rom-tonnage. This is a weak relation indicating that rom-grade and rom-tonnage
are not the only determinants and therefore on their own must be used with
precaution. Validation of the model agrees well with the actual results. Future
research should focus on the other determinants which account for the remaining
unaccounted 37.6%.
Author(s) Details
Karim Rajabu Baruti
School of Mines and Geosciences, University of Dar es
Salaam, Tanzania.
Please see the book here:- https://doi.org/10.9734/bpi/caert/v5/5929E
In this work, a survey was conducted in five selected towns in
Osun State, Nigeria, based on seventeen identified behavioural characteristics
using a developed structured questionnaire to collect data on identified
behavioural characteristics that could trigger psychopathy personality traits.
Psychopathic traits have eroded our society as they increase daily, thus
leading to increased crime. It refers to the full range of physical and
emotional behaviours that humans engage in. Physical or verbal aggression
between spouses, siblings, or parents who use it as punishment for their
children begins at home. Because of misunderstandings, neighbours frequently
demonstrate hostility, pessimism, trust, and envious behaviours. Two personality traits considered in this
work are aggressiveness and goal setting, while the considered behavioural
characteristics are family upbringing, confidence in government, society
values, industrialization, civilization, unemployment rate, technology
advancement, socio-political class, impunity, environmental impact, embracing
foreign culture based on materialism, religion believes, peer group influence,
academic attainment, high wealth procession, family believes, and power
intoxication. The data harvested from the questionnaire on behavioural
characteristics from the five hundred and eight respondents were subjected to
principal component analysis to investigate behavioural characteristics that
are likely to be responsible for psychopathic traits in humans. Results from
the principal component analysis confirmed that family upbringing, confidence
in government, society values, industrialization, and civilization
significantly contributed to psychopathic traits. Goal-setting is highly
influenced by foreign cultures, high money possession, religious views, power
intoxication, and technical advancement. These findings were obtained from a
binary logistic regression study that used aggression and goal-setting as
dependent factors. Conversely, it was discovered that the aggression personality
trait was significantly influenced by power intoxication, environmental impact,
impunity, and government confidence.
Therefore, based on the available data in this study and the analysis
carried out, civilization and confidence in government are the main significant
behavioural characteristics that trigger personality traits in the region
covered in the study. Future works can be extended to cover the entire country
for a more robust study in investigating psychopathic behavioural
characteristics.
Author(s)
Details
K. S.
Adekeye
Department of Mathematics and Statistics, Redeemer’s University,
Ede, Nigeria.
O. A.
Ayodeji
Department of Mathematics and Statistics, Redeemer’s University, Ede, Nigeria.
D. M.
Okewole
Department of Mathematics and Statistics, Redeemer’s University,
Ede, Nigeria.
Please see the book here:- https://doi.org/10.9734/bpi/mcscd/v2/384
This chapter explores the construction of a detailed machine
learning (ML) framework for predicting diabetes using diverse real-world
datasets. The alarming rise in diabetes prevalence globally and particularly in
developing nations such as India necessitates innovative approaches for early
detection and intervention. Traditional diagnostic techniques, though
clinically established, often fall short in scalability and adaptability. This
study focuses on bridging this gap by integrating ML methodologies that not
only offer superior prediction accuracy but also provide transparency through
interpretability tools.
Key contributions of this work include the comprehensive data
preprocessing steps (missing value treatment, normalisation, encoding, and
SMOTE-based class balancing), the comparative evaluation of three widely used
classifiers (Logistic Regression, Random Forest, and XGBoost), and the use of
SHAP values for enhancing model interpretability. Among the models tested,
XGBoost achieved the highest performance with an accuracy of 97.93%, AUC of
0.9974, and excellent sensitivity and specificity values, confirming its
suitability for real-world healthcare applications. The chapter concludes with
discussions on model performance, interpretability, clinical relevance,
limitations, and avenues for future research.
Author(s)
Details
Mounika
Panjala
Department of Statistics, Osmania University, Hyderabad-7,
Telangana, India.
Bhatracharyulu
N.Ch.
Department of Statistics, Osmania University, Hyderabad-7,
Telangana, India.
Please see the book here:- https://doi.org/10.9734/bpi/nhstc/v3/5950
Developing countries, including Benin, are characterized by very
high fertility. The consequences result in the precarious health of women and
children, slow economic growth, poverty, overcrowding of schools and health
facilities, overload of infrastructure and depletion of natural resources.
Additionally, high fertility rates contribute to rising unemployment,
increasing social inequalities, and the escalation of social conflicts. This
article assesses the unmet needs for family planning among women of
childbearing age in the Donga department, Benin. This goal is therefore to
guide the intervention strategies of the various projects and programs aimed at
filling the unmet needs in family planning for the achievement of the
Sustainable Development Goals (SDGs), and the well-being of the Beninese
population in general and that of Donga in particular. A mixed method
(quantitative and qualitative) was used based on data from a field survey
conducted among 466 women of childbearing age in 280 households and 57 resource
people. The qualitative component carried out through observations, in-depth
individual interviews with resource people, and focus group discussions with
homogeneous subgroups of women, men, and young people, provided explanations
and information to complete the quantitative component. In addition, the collection
of quantitative data was carried out electronically from smartphones using a
digital questionnaire using CS PRO version 6.3 software. To this end, multiple
correspondence analysis (MCA) and logistic regression were used to identify the
profiles of women with unmet needs and the factors associated with them. The
results indicate that 89.6% of unmet needs concern birth spacing, while 10.4%
concern birth control. The explanatory multivariate analysis made it possible
to identify the woman’s age, the ideal number of children, the type of
household the woman belongs to, the woman’s area of residence, her level of
education, and her main occupation as significant determinants of unmet need
for birth spacing. As for unmet needs for birth control, only the woman’s age
group and ideal number of children had a significant influence at the 5%
threshold. In-depth interviews with resource persons highlighted that education
is a central element influencing the unmet need for family planning. Adult
women face considerably higher unmet needs compared to teenagers, while
cultural norms around ideal family size significantly reduce unmet needs for
those preferring larger families. Other factors such as place of residence,
education level, employment status, and type of union show trends that warrant
further investigation but do not have statistically significant impacts in this
study. The study recommended improving awareness about family planning services
by promoting education for all, integrating sexual and reproductive health into
school curricula, and raising awareness not only among women but also among
men.
Author
(s) Details
Amboise
Tchando Nahini
Département de Population, Démographie et Environnement Naturel,
Ecole Doctorale des Sciences Agronomiques et de l’Eau (EDSAE), Université de
Parakou, Parakou, Benin, Département de Démographie, Laboratoire de Recherche
en Sciences de la Population et du Développement (LaReSPD), Université de
Parakou, Parakou, Bénin, Département de Sociologie, Laboratoire de Recherche sur
les Dynamiques Sociales et le Développement Local (LASDEL), Parakou, Bénin and
Ecole Nationale de Statistique, de Planification et de Démographie (ENSPD),
Université de Parakou, Parakou, Bénin.
Emmanuel
N’Kou´e Sambieni
Département de Population, Démographie et Environnement Naturel,
Ecole Doctorale des Sciences Agronomiques
et de l’Eau (EDSAE), Université de Parakou, Parakou, Benin and Département de
Sociologie, Laboratoire de Recherche sur les Dynamiques Sociales et le
Développement Local (LASDEL), Parakou, Bénin.
Mouftaou
Amadou Sanni
Département de Population, Démographie et Environnement Naturel,
Ecole Doctorale des Sciences Agronomiques et de l’Eau (EDSAE), Université de
Parakou, Parakou, Benin, Département de Démographie, Laboratoire de Recherche en
Sciences de la Population et du Développement (LaReSPD), Université de Parakou,
Parakou, Bénin and Ecole Nationale de Statistique, de Planification et de
Démographie (ENSPD), Université de Parakou, Parakou, Bénin.
Please see the book here:- https://doi.org/10.9734/bpi/nicass/v1/4491
The number of financial crimes has increased in modern times. Financial fraud must be identified to ensure that transactions remain secure and to maintain public trust. Machine Learning algorithms like Logistic Regression, Decision Trees, and Random Forests help us achieve this. The straight-forward method of Logistic Regression is used to identify linear relationships. Decision Trees, on the other hand, are more suitable to handle complex fraud patterns as they can capture non-linear relationships. Random Forests use numerous decision trees making them best suited for datasets which are at risk of overfitting.
Algorithms get evaluated by performance criteria such as F1 score,
accuracy and precision. Out of all the transactions labelled as fraud,
precision is the proportion of correctly identified fraud transactions. The
proportion of accurately classified transactions is known as accuracy. The
harmonic mean of precision and recall gives us the F1 score and a normalized
score of the model's performance is obtained by balancing.
Statistical hypothesis tests are applied for an accurate
comparison is used to compare. When three or more algorithms are to be compared
to check for a statistically significant difference between their means, we use
Analysis of Variance (ANOVA). This study aims to understand the effectiveness
of the ML algorithms in fraud detection by performing ANOVA tests on the
selected performance metrics. Here synthetic data set is generated and applied
statistical techniques for evaluation.
Author
(s) Details
W. Grace Shanthi
Kakatiya Institute of Technology and Science, Warangal, India.
Please see the book here:- https://doi.org/10.9734/bpi/mono/978-93-48859-10-5/CH5
This study has used the socio-economic, demographic, and
geographic variables from the national household survey data. The volume of an
internal migration is affected by the gaps of pull and push factors between the
places of origin and destination. However, the proportion of internal migration
due to the family reasons could be large, which is less affected by pull and
push factors. This paper studies the non-family-reason internal migration
(NFIM) and shows that the non-familyreason internal migration population has
different characteristics from the other population and internal migrants. The
NFIM and internal migration regression coefficients had the same sign for
hill/terai geographical belts, age-group, nonpoor, farm household, and
ethnicity. This paper studied the NFIM population’s characteristics using the
second Nepal Living Standards Survey 2003/04 data. It is possible that there
are similar characteristics of the NFIM population in other geographical areas.
Author(s) Details:
Binod Manandhar,
Department of Mathematical Sciences, Clark Atlanta University,
Atlanta, GA, USA.
Please see the link here: https://stm.bookpi.org/RRAASS-V8/article/view/14198
Heart disease persists to be a major all-encompassing public health issue, contributing to infinite deaths and disabilities. Effective deterrent interventions and individualized situation programs depend on timely and exact risk prediction of myocardial infarction. Significant advancements in the field of cardiac affliction prediction have been created thanks to the development of machine intelligence techniques. This book chapter offers a all-encompassing analysis of the strengths, imperfections, and overall effectiveness of the various machine intelligence models used for heart disease indicator.
Author(s) Details:
Sunanda Budihal,
Department
of Computer Science, Shah Sogamal Peeraji Oswal Government First Grade College,
Muddebhihal, Vijayapura, Karnataka, India.
Sheetalrani
Rukmaji Kawale,
Department
of Computer Science, Karnataka State Akkamahadevi Women University, Vijayapura,
Karnataka, India.
Aparna Atul Junnarkar,
Department of Information Technology, Vishwakarma Institute of
Information Technology (VIIT), Pune, Maharashtra, India.
H. Faritha Begam,
Seethalakshmi Achi College for Women, Pallathur 630 107, Tamilnadu,
India.
Girish M.,
Department
of Computer Science and Engineering, Gopalan College of Engineering and
Management, Bangalore, Karnataka, India.
Please see the link here: https://stm.bookpi.org/ACST-V2/article/view/11926
This member compares the estimation of vaccine efficiency between the unoriginal method, logistic model, and Cox regression model in consideration of improve belief of vaccine efficacy a suggestion of correction using unoriginal methods. It also aims to recognize additional doing factors in evaluating cure efficacy among differing vaccines. Vaccination plays a vital act in eradicating and controlling the expansive spread of diseases like smallpox, polio, measles, nervous system infection and leprosy throughout the world. In a potential cohort study 1,71,400 things were enrolled and they were confirmed as athletic with routine healing checkups. Various regression models such as Cox reversion, binomial regression, Poisson reversion model have been applied to find the bettering in the estimation of Vaccine Efficacy. The participants were made inquiries through two subsequent surveys accompanying two to three year interval. The reversion models were built utilizing the individuals' demographic and dispassionate information. We were capable to calculate the odds percentages from the regression models and estimate the regulated relative risk as well as vaccine influence. Estimated relative risks obtained from Logistic regression and Poisson reversion models give comparable results in second resurvey. By comparing the estimated cure efficacy utilizing conventional methods accompanying regression models the Vaccines ICRC and BCG+Kml have maximum guardianship and Logistic regression models provides appropriate results than the Cox reversion model. Vaccine ICRC and BCG+Kml gives better protection results grazing between 63 and 76 than vaccines BCG and M.w, which have cure efficacy 'tween 24 and 35 in second resurvey.
Author(s) Details:
A. Venmani,
Department
of Mathematics and Statistics, Faculty of Science and Humanities, SRM Institute
of Science and Technology, Kattankulathur – 603203, Chengalpattu District,
Tamil Nadu, India.
Please see the link here: https://stm.bookpi.org/CIDHR-V3/article/view/11354
India uses the most groundwater, with over 230 cubic kiloliters produced annually by its 27.5 million wells. Vertical artesian wells are dug in the surface's subsurface aquifer to gather water for a number of uses. of objectives. Due to the rising need for artesian wells, more are being drilled each year. factors including decreased rainfall, water scarcity, and groundwater depletion etc. The motor is removed as the water dries, and the exterior is not adequately sealed or covered. The borewell's diameter is big enough for a kid to fall into. into the interior of the at present disused or inoperative well. Apparently, one Sadly, more than 40 kids have fallen into wells since 2009, according to a report. portion of Rescue efforts have fallen short. The present study includes an analysis. of the Kaggle dataset derived from the drill holes. The purpose of this work is aims to create predictive models using basic machine learning techniques. ANN models, logistic regression, and bays to "forecasting existing equipment failure wells that will soon be reported and confiscated." i.e., to identify non-operational bore wells that demand quick intervention. The effectiveness of the measures were used to assess the model. Good results from logistic regression performance in identifying deadly inactive wells.
Despite its relevance, the impact of household endowments (financial and human assets) on household wellbeing has received insufficient study. This study aims to investigate into the impact of household endowments in reducing poverty among rural households in Ijebu-Jesa, Osun State, due to the high occurrence of poverty in Sub-Saharan African nations, notably Nigeria. A multistage sampling procedure was used to collect data from 120 households, which was then analysed using frequencies and percentages, the Foster Greer and Thorbecke (FGT) index, and logistic regression analysis. According to the findings, rural households are modestly impoverished (48.3 percent ). Age, gender, years of schooling, cooperative participation, access to credit, household income, mobile phone access, and household size are all factors that influence the function of household endowment in poverty reduction. Gender (p 0.030), cooperative society membership (p 0.036), household income (p 0.009), mobile phone access (p 0.037), and household size (p 0.000) are all significant variables in explaining the influence of household endowment on poverty reduction. As a result, it is suggested that the government implement programmes and regulations aimed at easing the formation of cooperative groups in the studied area. Furthermore, telecommunications costs should be subsidised to encourage more people to use and access mobile phones.
Machine learning has grown in popularity as a result of the widespread application of its algorithms in numerous data science projects across many industries, particularly in the health-care industry. Machine learning technologies must be used to assist researchers and medical professionals in the early diagnosis of diseases such as heart disease, which is one of the world's leading causes of death. Correct heart disease prediction can save lives and avoid health problems, but inaccurate heart disease prediction can be fatal. Machine learning algorithms excel at learning from data, and because healthcare providers collect massive amounts of data on a regular basis, these algorithms have a lot of room to grow in this industry. A comparative analytical technique was used in this research study to determine which algorithm works better under the specified conditions. Various tests were carried out using 5 and 10 fold cross validation to confirm that the models produced were sufficiently generalizable. The data for this study comes from a machine learning database at the University of California, Irvine (UCI), which contains 303 instances with 14 attributes. The obtained data is normalised using the Min-Max method. Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Logistic Regression (LR), Nave Bayes (NB), Random Forest (RF), and Gradient Boosting ensemble approach are some of the common models developed utilising supervised machine learning classification algorithms on scaled data. Standard performance criteria such as accuracy, recall, and F1-score are also used to evaluate these methods. Based on the results of the studies, it can be determined that SVM outperforms the other algorithms.
One of the major issues with the binary logistic regression model is that the explanatory variables that are taken into account for the logistic regression model are strongly correlated. Multicollinearity affects confidence intervals and hypothesis tests by causing unstable estimates and inconsistent variances. The aim of this paper was to address some diagnostic metrics for detecting multicollinearity, such as tolerance and the Variance Inflation Factor. Variance proportions, condition index, and (VIF). Data from a survey of road injuries is used to demonstrate the adapted diagnostics. Secondary data for this analysis was obtained from the Traffic Police Headquarters in Colombo, Sri Lanka, from 2014 to 2016. The answer component is accident severity, which is divided into two categories: grave and non-grave. The correlation matrix, tolerance, and VIF are used to detect multicollinearity. The condition index and variance proportions were used to validate the values. Increase the sample size, remove one of the associated variables, and combine variables into an index are some of the logistic regression solutions available. It can be safely inferred that omitting one of the associated variables can significantly reduce multicollinearity without raising sample size. As a result, a stable and valid predictive logistic regression model can be developed based on adequate inspection and anti-multicollinearity steps.
Author(s) DetailsObjective: The scale and features of the medical database are also increasingly growing with the continued production of medical devices and advances in data collection. The majority of current cancer diagnosis, however, still depends on the examination and testing of doctors with samples of cell tissue who do not appear to use the medical database to its full potential. Therefore, the research focus for this thesis was to explore whether we can use artificial intelligence to recognise trends that can be predictive of cancer detection in medical databases. Therefore, different methods of machine learning (ML) have been investigated for their predictive efficiency with the goal of how they can assist doctors in diagnosing cancer.
Methods: This study uses 154,899 screening mammogram records from the Breast
Cancer Surveillance Consortium (BCSC) dataset. This dataset comprises 12
independent variables and 1 dependent variable in a labelled data format. Using
well-established machine learning algorithms, we developed four prediction
models: Logistic Regression, Naïve Bayes, Support Vector Machine (SVM), and
Bayesian Network, by training them on 80% of the data and testing their
prediction output on the remaining 20% of data. We carried out a comparative
study of the results of these models of machine learning.
Results: Naïve Bayes showed the best prediction accuracy for the malignant
samples, which is predictive of the risk of cancer, among the four models. The
Bayesian Network model had the second best results. For predicting malignant
cases and thus the risk of breast cancer, both Logistic Regression and SVM
yielded poor prediction results.
Author (s) Details
Mochen Li
School of Engineering
Technology, Purdue University, West Lafayette, IN 47907, USA.
Dr. Gaurav Nanda
School of Engineering Technology,
Purdue University, West Lafayette, IN 47907, USA.
Raji Sundararajan
School of Engineering Technology,
Purdue University, West Lafayette, IN 47907, USA.
