This paper discusses the problem of minimizing the power loss in unbalanced distribution systems through phase-balancing with the phase swapping concept from substation (HV/MV) to all MV/LV substations. This paper pro...
详细信息
This paper presents an analytical study and a technique for extracting the features of a common case of images of the iris called off-angle iris which was taken for persons identification systems. The main problem whe...
详细信息
Skin cancer is one of the most common types of cancer in the world, and it poses major health risks due to its ability to spread quickly and metastasize. Early and accurate identification is crucial for treatment succ...
详细信息
In this paper, we have implemented Davide Pradovera’s minimal sampling algorithm for adaptive frequency sampling in electromagnetic simulation. This algorithm is basically a modified AAA (Adaptive Antoulas– Anderson...
详细信息
ISBN:
(数字)9798331543259
ISBN:
(纸本)9798331543266
In this paper, we have implemented Davide Pradovera’s minimal sampling algorithm for adaptive frequency sampling in electromagnetic simulation. This algorithm is basically a modified AAA (Adaptive Antoulas– Anderson) version. Compared to the conventional AAA algorithm, this approach does not require a prior user-defined dataset to find out the next frequency sample point while meeting the specified error criteria. Pradrovera has introduced a pseudo error to find out the next frequency sample in an adaptive way incorporating the AAA algorithm. MATLAB R2023a was used to demonstrate two examples of electromagnetic simulation. This algorithm shows outstanding accuracy and speed performance.
Determining the health and resilience of ecosystems depends on an understanding of the dynamics of zooplankton abundance in tropical temporary ponds. Using ensemble modelling and explainable artificial intelligence (X...
详细信息
ISBN:
(数字)9798350355499
ISBN:
(纸本)9798350355505
Determining the health and resilience of ecosystems depends on an understanding of the dynamics of zooplankton abundance in tropical temporary ponds. Using ensemble modelling and explainable artificial intelligence (XAI) techniques, this paper explores the complex dynamics of zooplankton abundance in tropical temporary ponds. This study uses a Machine Learning framework to evaluate the predictive performance of models such as k-nearest Neighbors ($k N N$) regression, Random Forest Regression, Lasso Regression, Passive Aggressive Regression, Ridge Regression, and Ensemble Voting Regression. Among the machine learning models tested, the ensemble model, which combines ridge and ridge CV, performs best, with metrics such as MAE of 0.02, MSE of 0.00, and $\mathbf{R 2}$ of 1.00. The Shapley Additive ExPlanations (SHAP) analysis identifies ‘Rotifers’, ‘Culex’, ‘Chironomodidae’, and ‘Calanoids’ as significant predictors. Data preprocessing techniques improve the dataset derived from a study of fish predation effects in tropical temporary ponds. Our research advances our understanding of zooplankton ecology and provides insights into conservation strategies and management practices in these ecosystems. Using ensemble modelling and explainable AI, we contribute to developing accurate predictive models for the long-term management of tropical temporary pond ecosystems.
The only way to prevent blindness from eye problems is by early detection and prompt treatment. Although colour fundus photography (CFP) is useful for fundus inspection, there is a need for computer-assisted automated...
详细信息
This article introduces a DC-DC converter designed for various applications, including battery chargers and electric vehicles. The input stage features an EMC/EMI filter to mitigate noise. A Power Factor Correction (P...
详细信息
ISBN:
(数字)9798331525132
ISBN:
(纸本)9798331525149
This article introduces a DC-DC converter designed for various applications, including battery chargers and electric vehicles. The input stage features an EMC/EMI filter to mitigate noise. A Power Factor Correction (PFC) circuit efficiently converts 220 V AC power into 400 V DC for the DC-DC converter's input. The converter utilizes a PID controller and Pulse Frequency (PF) modulation for switching control. This modulation technique adjusts the switching frequency in response to changes in load or input voltage, ensuring output voltage stability while maintaining high system efficiency across different load conditions. Simulation results validate the proposed converter design's effectiveness, demonstrating its ability to maintain a stable output voltage under varying conditions.
The efficient and appropriate power flow technologies are necessary for better performance of renewable energy system applications. The comparative study of different MPPT algorithms, which are best for RES applicatio...
详细信息
ISBN:
(数字)9798331529833
ISBN:
(纸本)9798331529840
The efficient and appropriate power flow technologies are necessary for better performance of renewable energy system applications. The comparative study of different MPPT algorithms, which are best for RES applications due to their influence on efficiency, low response time and the stability under different intervals of irradiance and temperature. When comes to this context, the key focus is evaluation of algorithms to the converter which is bidirectional by considering the desired operational conditions. The observations of this study are a forward step to optimization of systems with bidirectional converters in improving the reliability and sustainability.
Compensation mechanisms are used to counterbalance the discomfort suffered by users due to quality service issues. Such mechanisms are currently used for different purposes in the electrical power and energy sector, e...
详细信息
The State of Charge (SoC) estimation of lithiumion batteries is a critical aspect in the domain of plug-in electric vehicles (PEVs), influencing their performance, range, and overall efficiency. This paper addresses t...
详细信息
ISBN:
(数字)9798331519568
ISBN:
(纸本)9798331519575
The State of Charge (SoC) estimation of lithiumion batteries is a critical aspect in the domain of plug-in electric vehicles (PEVs), influencing their performance, range, and overall efficiency. This paper addresses the improvements and limitations of SoC estimate methods, with an emphasis on lithium-ion batteries used in PEVs. The paper comprehensively analyzes a range of strategies used to determine SoC, including traditional methods and modern approaches, including model-based predictions and machine-learning (ML) algorithms. This work employs ML techniques such as Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). In order to analyze SoC predictions, this paper proposes a hybrid ML strategy that combines CNN and LSTM. An effective SoC prediction is achieved using CNN, LSTM, and an integration of both. A comparison of the findings shows that the hybrid ML model outperforms CNN and LSTM in predicting the SoC of PEVs. The hybrid model exhibits impressive performance with a mean absolute error (MAE) of 1.92%, indicating a significant enhancement in accuracy compared to CNN and LSTM, which have MAE values of 2.12% and 4.2%, respectively.
暂无评论