Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: algorytm NSGA-II

Sortuj według:

Ogranicz wyniki do:

Optimal Design of a Novel Magnetic Twisting Device based on NSGA-II Algorithm

Qiao Xu, Yuchen He, Shunqi Mei, Zhen Chen, Shaojun Wang, Xuemei Tang

Autex Research Journal

2022

Vol. 22, no. 2

194--200

This paper presents a novel magnetic twisting device with a coaxial double rotor based on non-contact transmission characteristics of magnetic drive technology. When the twisting device rotates one cycle, the yarn can get triple twists. This means the new device can twist three times more than what the traditional single twist does. The structure of the magnetic twisting device is designed according to the twisting principle. The influence of main structural parameters on the magnetic torque is analyzed. To optimize the maximum transmission torque and the minimum magnet volume, the multi-objective optimization design model for the twisting device is established. Main parameters such as the relative angle of active disc assembly and passive disc assembly, the thickness of magnet, and the average radius of the magnet distribution are optimized by NSGA-II algorithm. Optimization results show that the proposed structural optimization design of a twisting device based on the magnetic drive has excellent performance and is effective for industrial application.

Stacking-based multi-objective evolutionary ensemble framework for prediction of diabetes mellitus

Singh Namrata, Singh Pradeep

Biocybernetics and Biomedical Engineering

2020

Vol. 40, no. 1

1--22

Diabetes mellitus (DM) is a combination of metabolic disorders characterized by elevated blood glucose levels over a prolonged duration. Undiagnosed DM can give rise to a host of associated complications like retinopathy, nephropathy and neuropathy and other vascular abnormalities. In this background, machine learning (ML) approaches can play an essential role in the early detection, diagnosis and therapeutic monitoring of the disease. Recently, several research works have been proposed to predict the onset of DM. To this end, we develop a stacking-based evolutionary ensemble learning system ‘‘NSGA-II-Stacking’’ for predicting the onset of Type-2 diabetes mellitus (T2DM) within five years. For this purpose, publicly accessible Pima Indian diabetes (PID) dataset is utilized. As a data pre-processing step, the missing values and outliers are identified and imputed with the median values. For base learner selection, a multi-objective optimization algorithm is utilized which simultaneously maximizes the classification accuracy and minimizes the ensemble complexity. As for model combination, k-nearest neighbor (K-NN) is employed as a meta-classifier that combines the predictions of the base learners. The comparative results demonstrate that the proposed NSGA-II-Stacking method significantly outperforms several individual ML approaches and conventional ensemble approaches. In terms of performance metrics, the proposed system achieves the highest accuracy of 83.8 %, sensitivity of 96.1 %, specificity of 79.9 %, f-measure of 88.5 % and area under ROC curve of 85.9 %.

Generalized route planning approach for hazardous materials transportation with equity consideration

Chai H., He R.-C., Jia X.-yan, Ma Ch.-x, Dai C.-jie

Archives of Transport

2018

Vol. 46, iss. 2

33--46

Hazardous materials transportation should consider risk equity and transportation risk and cost. In the hazardous materials transportation process, we consider risk equity as an important condition in optimizing vehicle routing for the long-term transport of hazardous materials between single or multiple origin-destination pairs (O-D) to reduce the distribution difference of hazardous materials transportation risk over populated areas. First, a risk equity evaluation scheme is proposed to reflect the risk difference among the areas. The evaluation scheme uses standard deviation to measure the risk differences among populated areas. Second, a risk distribution equity model is proposed to decrease the risk difference among populated areas by adjusting the path frequency between O-D pairs for hazardous materials transportation. The model is converted into two sub models to facilitate decision-making, and an algorithm is provided for each sub model. Finally, we design a numerical example to verify the accuracy and rationality of the model and algorithm. The numerical example shows that the proposed model is essential and feasible for reducing the complexity and increasing the portability of the transportation process.