A5101796433- Market Dynamics and Volatility
- Stock Market Forecasting Methods
- Artificial Intelligence in Healthcare
- Speech and Audio Processing
- Sentiment Analysis and Opinion Mining
- Speech Recognition and Synthesis
- Petroleum Processing and Analysis
- Text and Document Classification Technologies
- Imbalanced Data Classification Techniques
- Maternal and Perinatal Health Interventions
- Composting and Vermicomposting Techniques
- Smart Agriculture and AI
- Forecasting Techniques and Applications
- Healthcare and Environmental Waste Management
- Financial Distress and Bankruptcy Prediction
- Helminth infection and control
- Energy Load and Power Forecasting
- COVID-19 and Mental Health
- Smart Grid Security and Resilience
- Advanced Text Analysis Techniques
- Online Learning and Analytics
- Anomaly Detection Techniques and Applications
- Spectroscopy and Chemometric Analyses
- Network Security and Intrusion Detection
- Opioid Use Disorder Treatment
Hajee Mohammad Danesh Science and Technology University
2016-2025
Deakin University
2023-2025
Florida College
2025
University of Florida
2025
Comilla University
2024
United International University
2023
Gazipur Agricultural University
2021-2022
Bangladesh Livestock Research Institute
2020
Mawlana Bhashani Science and Technology University
2020
Green University of Bangladesh
2020
Agriculture is the most critical sector for food supply on earth, and it also responsible supplying raw materials other industrial productions. Currently, growth in agricultural production not sufficient to keep up with growing population, which may result a shortfall world’s inhabitants. As result, increasing crucial developing nations limited land resources. It essential select suitable crop specific region increase its rate. Effective forecasting that area based historical data, including...
Abstract To efficiently capture diverse fluctuation profiles in forecasting crude oil prices, we here propose to combine heterogenous predictors for the prices of oil. Specifically, a model is developed using blended ensemble learning that combines various machine methods, including k -nearest neighbor regression, regression trees, linear ridge and support vector regression. Data Brent WTI at time series frequencies are used validate proposed blending approach. show validity model, its...
Electric vehicles (EVs) are commonly recognized as environmentally friendly modes of transportation. They function by converting electrical energy into mechanical using different types motors, which aligns with the sustainable principles embraced smart cities. The motors EVs store and consume power from renewable (RE) sources through interfacing connections electronics technology to provide rotation. reliable operation an EV mainly relies on condition in EV, particularly connection between...
Happiness is a state of contentment, joy, and fulfillment, arising from relationships, accomplishments, inner peace, leading to well-being positivity. The greatest happiness principle posits that morality determined by pleasure, aiming for society where individuals are content free suffering. While factors vary, some universally recognized. World Report (WHR), published annually, includes data on ‘GDP per capita’, ‘social support’, ‘life expectancy’, ‘freedom make life choices’,...
Heart disease is one of the primary causes morbidity and death worldwide. Millions people have had heart attacks every year, only early-stage predictions can help to reduce number. Researchers are working on designing developing prediction systems using different advanced technologies, machine learning (ML) them. Almost all existing ML-based works consider same dataset (intra-dataset) for training validation their method. In particular, they do not inter-dataset performance checks, where...
The teacher-student relationship has far-reaching implications for educational outcomes at the tertiary level. Teachers contribute to students’ success in various ways, including academic support, career counseling, personal mentoring, etc., that help them succeed academically and professionally. COVID-19 disrupted interaction hindered flow of teacher’s support students. damage caused by pandemic higher education sector mostly recovered. However, trusting between teacher student is yet get...
Heart disease is the prominent life-threating cause of death. Early stage prediction can reduce death percentage. This paper investigates effect different imbalance data handling techniques on accuracy to predict heart using machine learning, deep learning methods and an ensemble method. Most algorithms show better in balanced instead data. Support Vector Machine, Multilayer Perceptron, Logistic Regression Perceptron shows 96% SMOTETomek hybrid balancing techniques. Accuracy, Precision,...
During the academic career, students achieve numerous credentials. These educational credentials are offered by student while applying for a job or scholarship. Therefore, goal of this paper is to propose theoretical blockchain-based certificate verification system on cloud that can offer potential solution issuing and where cryptocurrencies banned. By regarding in research, we address Blockchain (BC) technology solving these problems. This BC be capable providing immutability publicly...
The mother's mode of delivery greatly impacts the relationship between newborn baby and mother, as well baby's health. Currently, cesarean rate is increasing at an alarming rate. inability to predict health status are mainly responsible for this situation. Support Vector Machine (SVM), Decision Tree, Random Forest (RF), Gradient Boosting Classifier(GBC), Logistic Regression, Gaussian Naive Bayes, Stochastic Descent, CatBoost (CB), Adaptive (AB), Naïve Extreme Boosting(XGB) used delivery....
Burning fossil fuels like coal, oil, and natural gas releases significant CO2, driving carbon emissions in electricity production. This contributes to global warming, leading climate change, extreme weather, rising sea levels, harm ecosystems human health. Achieving zero requires transitioning low-carbon energy sources. study uses various Machine Learning (ML) models for predicting low generation additionally eXpalinalbe Artificial Intelligence (XAI) elucidate how ML model works suggest some...
This study investigated the clinical benefit of counseling as a complement to buprenorphine treatment for opioid use disorder (OUD). The research addresses critical gap in understanding whether counseling, when received concurrently with buprenorphine, can enhance patient outcomes. We conducted retrospective cohort using data from Massachusetts Department Public Health's Health Data Warehouse (PHD). included patients who initiated between January 2015 and December 2019. Investigators...
The rise of social media has changed how people view connections. Machine Learning (ML)-based sentiment analysis and news categorization help understand emotions access news. However, most studies focus on complex models requiring heavy resources slowing inference times, making deployment difficult in resource-limited environments. In this paper, we process both structured unstructured data, determining the polarity text using TextBlob scheme to determine headlines. We propose a Stochastic...
Classification is a predictive modelling task in machine learning (ML), where the class label determined for specific example of predefined features. In determining handwriting characters, identifying spam, detecting disease, signals, and so on, classification requires training data with many features instances. medical informatics, high precision recall are mandatory issues besides accuracy ML classifiers. Most real-life datasets have imbalanced characteristics that hamper overall...
Disease samples are naturally fewer than healthy which introduces bias in the training of machine learning (ML) models. Current study focuses discriminating patterns between cesarean and non-cesarean phenomena based on a dataset consisting 161 features total 692 5465 comes as four folds different hospitals (hospital A, B, C D). The is noisy, contains missing values, at scales above all, quite large number risks containing unnecessary information with respect to separate C-section class from...