Ensemble learning techniques have achieved state-of-the-art performance in diverse machine applications by combining the predictions from two or more base models. This paper presents a concise overview of ensemble learning, covering three main methods: bagging, boosting, and stacking, their early development to recent algorithms. The study focuses on widely used algorithms, including random forest, adaptive boosting (AdaBoost), gradient extreme (XGBoost), light (LightGBM), categorical...

Abstract Computer networks intrusion detection systems (IDSs) and prevention (IPSs) are critical aspects that contribute to the success of an organization. Over past years, IDSs IPSs using different approaches have been developed implemented ensure computer within enterprises secure, reliable available. In this paper, we focus on built machine learning (ML) techniques. based ML methods effective accurate in detecting attacks. However, performance these decreases for high dimensional data...

Heart disease is the leading cause of death globally, and early detection crucial in preventing progression disease. In this paper, an improved machine learning method proposed for prediction heart risk. The technique involves randomly partitioning dataset into smaller subsets using a mean based splitting approach. various partitions are then modeled classification regression tree (CART). A homogeneous ensemble created from different CART models accuracy weighted aging classifier ensemble,...

In recent years, the increased use of wireless networks for transmission large volumes information has generated a myriad security threats and privacy concerns; consequently, there been development number preventive protective measures including intrusion detection systems (IDS). Intrusion mechanisms play pivotal role in securing computer network systems; however, various IDS, performance remains major issue. Moreover, accuracy existing methodologies IDS using machine learning is heavily...

Abstract The recent advances of e-commerce and e-payment systems have sparked an increase in financial fraud cases such as credit card fraud. It is therefore crucial to implement mechanisms that can detect the Features frauds play important role when machine learning used for detection, they must be chosen properly. This paper proposes a (ML) based detection engine using genetic algorithm (GA) feature selection. After optimized features are chosen, proposed uses following ML classifiers:...

Many real-world machine learning applications require building models using highly imbalanced datasets. Usually, in medical datasets, the healthy patients or samples are dominant, making them majority class, while sick few, minority class. Researchers have proposed numerous methods to predict diagnosis. Still, class imbalance problem makes it difficult for classifiers adequately learn and distinguish between classes. Cost-sensitive resampling techniques used deal with problem. This research...

Precision weed control in vegetable fields can substantially reduce the required inputs. Rapid and accurate detection is a challenging task due to presence of wide variety species at various growth stages densities. This paper presents novel deep-learning-based method for that recognizes crops classifies all other green objects as weeds.The optimal confidence threshold values YOLO-v3, CenterNet, Faster R-CNN were 0.4, 0.6, 0.4/0.5, respectively. These deep-learning models had average...

Credit cards play an essential role in today's digital economy, and their usage has recently grown tremendously, accompanied by a corresponding increase credit card fraud. Machine learning (ML) algorithms have been utilized for fraud detection. However, the dynamic shopping patterns of holders class imbalance problem made it difficult ML classifiers to achieve optimal performance. In order solve this problem, paper proposes robust deep-learning approach that consists long short-term memory...

Algorithms are used to optimize both single and multi-objective system limits. This research aimed detect the optimal location size of DGs, which can significantly minimize power loss improve stability voltage. The uses binary particle swarm optimization shuffled frog leap (BPSO-SLFA) algorithms for simulation testing an flow (OPF) on 33 69 bus radial distribution system. result shows that give better DG allocation minimizes losses but at nascent stage advancement. associated with have...

Load frequency control or automatic generation is one of the main operations that take place daily when considering a modern power system not. The objectives load are to maintain balance between interconnected areas and flow in tie-lines. Electric cannot be stocked large quantity why its production must equal consumption each time. This equation constituted key for good management any introduces need more controllers taking into account integration renewable energy sources traditional...

In this paper a two stage method is proposed to effectively predict heart disease. The first involves training an improved sparse autoencoder (SAE), unsupervised neural network, learn the best representation of data. second using artificial network (ANN) health status based on learned records. SAE was optimized so as train efficient model. experimental result shows that improves performance ANN classifier, and more robust compared other methods similar scholarly works.

The advance in technologies such as e-commerce and financial technology (FinTech) applications have sparked an increase the number of online card transactions that occur on a daily basis. As result, there has been spike credit fraud affects issuing companies, merchants, banks. It is therefore essential to develop mechanisms ensure security integrity transactions. In this research, we implement machine learning (ML) based framework for detection using real world imbalanced datasets were...

Heart disease is the leading cause of death globally. The most common type heart coronary disease, which occurs when there a build-up plaque inside arteries that supply blood to heart, making circulation difficult. prediction challenge in clinical machine learning. Early detection people at risk vital preventing its progression. This paper proposes deep learning approach achieve improved disease. An enhanced stacked sparse autoencoder network (SSAE) developed efficient feature consists...

This paper investigates energy management systems in micro-grid using an optimization-based approach, optimizing the operating cost related to purchased from utility grid, operation of storage system, and revenue selling grid. research uses a constrained Particle Swarm Optimization-Based Model Predictive Control (CPSO-MPC) Linear Program-Based Optimization approach solve optimization problem formulated management. Due absence constraint strategies traditional PSO algorithm, it is incapable...

The efforts to revolutionize electric power generation and produce clean sustainable electricity have led the exploration of renewable energy systems (RES). This form is replenished cost-effective in terms production maintenance. However, RES, such as solar wind energies, intermittent; this one drawbacks its usage. In order overcome limitation, studies been undertaken forecast availability output. current trending method forecasting generated by RES artificial intelligence (AI) method. with...

This paper presents a novel nature-inspired meta-heuristic optimization algorithm known as the Enhanced Whale Optimization Algorithm (EWOA), which imitates humpback whales' social behavior to solve of multi-area automatic load frequency control (LFC) problems stochastic renewable energy-based power system with superconducting magnetic energy storage (SMES). An EWOA is presented in response limitations conventional WOA algorithm, including its sluggish convergence time, low accuracy, and...

With the rapid developments in electronic commerce and digital payment technologies, credit card transactions have increased significantly. Machine learning (ML) has been vital analyzing customer data to detect prevent fraud. However, presence of redundant irrelevant features most real-world degrades performance ML classifiers. This study proposes a hybrid feature-selection technique consisting filter wrapper steps ensure that only relevant are used for machine learning. The proposed method...