ENSEMBLE TECHNIQUES FOR DEEPFAKE DETECTION: COMPARING STACKING, WEIGHTED VOTING AND AVERAGING APPROACHES

ABSTRACT Over the years, deepfake detection has been an emerging challenge because of the increase in highly realistic computer-generated synthetic media. Although the study examined deep learning and conventional machine learning models separately, the ideal ensemble technique for integrating CNN-extracted features with SVM and XGBoost classifiers is relatively obscure. Our study shows the comparative analysis

Read More

CLASSIFICATION OF SICKLE CELL ANAEMIA SEVERITY USING HAEMATOLOGICAL PARAMETERS: A MACHINE LEARNING APPROACH

ABSTRACT Sickle Cell Anaemia (SCA) is a genetic blood disorder that caused abnormal haemoglobin and severe health complications. In Nigeria, nearly 150,000 infants, 2% of newborns, were diagnosed annually, highlighting its public health impact. SCA severity varied and was linked to complications like vaso-occlusive and other critical case. Traditional severity assessments were subjective, but machine

Read More

DEVELOPMENT AND CHALLENGES IN INTELLIGENT PREDICTION OF CROP GROWTH: A SYSTEMATIC LITERATURE REVIEW

ABSTRACT Agricultural research is growing. Specifically, crop forecasting is greatly influenced by earth and climate factors, including temperature, humidity, and rainfall. One of the problems in agriculture is that of crop growth prediction. This work provides a methodical review of the approaches to predicting the growth rate of crops. It reviews problems in growth prediction

Read More

HYBRID DETECTION FRAMEWORK FOR REAL-TIME NETWORK ANOMALIES USING THRESHOLD-BASED TRIGGERS AND TEMPORAL SLIDING WINDOW PROFILING

ABSTRACT: The real-time identification of anomalous traffic in modern networks is still a big challenge for cyber security. We propose a hybrid anomaly detection model, which combines the threshold-based triggers with the sliding window temporal profiles, to improve the early detection of DoS attacks and network anomalies. Abnormal behaviors such as traffic volume surges, port scanning, and packet

Read More

AI-DRIVEN SECURE AND SUSTAINABLE SOLUTIONS FOR SMART CITIES IN THE INTERNET OF THING ERA

ABSTRACT Artificial Intelligence (AI) and the Internet of Things (IoT) are reshaping smart cities areas into intelligent, interconnected ecosystems. This study examines how AI-driven technologies can boost security, promote sustainability, also increase the efficiency of city operations. Through AI, systems like traffic control, waste disposal, and environmental monitoring can be significantly improved, eventually enhancing residents’

Read More

METAHEURISTIC ALGORITHMS: A PARADIGM SHIFT IN DIMENSIONALITY REDUCTION IN HEALTHCARE INFORMATICS

ABSTRACT Healthcare informatics leverages on massive data generated at an expeditious rate from diverse domains in healthcare. Such data culminates in redundant, noisy, complex and high dimensional attributes which impose a load on the learning algorithms employed for disease diagnosis, prognosis, prediction and treatment planning. Obtaining relevant information from the chunk of data generated is

Read More

A MACHINE LEARNING AND SPATIAL CLUSTERING FRAMEWORK FOR URBAN AIR QUALITY PREDICTION

ABSTRACT: Urban air pollution presents a significant public health risk, com- pounded by the complexity of multipollutant interactions and modelling uncertainty. This study integrates spatial analysis with ElasticNet regression to predict the Air Quality Index (AQI) using geolocated pollutant data. ElasticNet effectively handles multicollinearity while maintaining model interpretability. We also apply spatial clustering to categorize

Read More

QUANTIFYING DROUGHT PERSISTENCE AND TRANSITION PROBABILITIES USING ADVANCED SPATIAL ANALYSIS OF SPI-24 DATA

ABSTRACT Drought is still a severe worldwide threat to agriculture, water and society. Although current drought watchers combine several indices and satellite information, difficulties remain with respect to spatial location and predictive ability. Conventional methods (e.g., SVMs, NNs) have a problem of spatial autocorrelation and imbalanced data. In this study, drought prediction is augmented via DBSCAN clustering, variogram-based spatial

Read More

VISWIN TRANSFORMER: COULD IT BE THE WAY OUT IN BREAST CANCER DIAGNOSIS? -A CONCEPT PAPER

ABSTRACT For decades, Breast Cancer has been a major cause of death globally. It has been confirmed that early detection of the disease increases the chances of survival. Deep learning models, particularly transformer-based architectures like Vision Transformers (ViTs) and Swin Transformers, have shown potential in breast cancer diagnosis. However, each model has limitations: ViTs are

Read More

A Deterministic Finite Model for Evaluating Performance Variations of Virtual Private Network Tunneling Protocols

ABSTRACT Virtual Private Network (VPN) became a necessary networking technology under consideration. The VPN technology protects information being transmitted over the internet by allowing users to establish a virtual private “tunnel” to securely enter internal network. This possibility enable the user to access resources, data and communications via insecure network such as the internet. This

Read More