Recognition of brain stroke shape using multiscale morphological image processing

Lakshmi, S. Venkata; Rejula, M. Anline; Sujatha, K.; Ahilan, A.

doi:10.1080/13682199.2022.2146877

Cited by 2 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the second portion of the equation, this algorithm evades optimal local convergence and is more reliable. As F increases, the vulture explores other regions for the solution, while as F decreases, it arrives at the exploitation phase, aiming to improve the solution's quality [20,21].…”

Section: African Vulture Optimization (Avo) Algorithmmentioning

confidence: 99%

Technique De Contrôle Intégrée Optimisée Pour Vautour Africain Pour Application De Pompe À Moteur À Induction À Enroulement Ouvert À Alimentation Pv

VENUGOPALAN,

VARGHESE,

THANKASWAMY

2024

RRST-EE

View full text Add to dashboard Cite

Open-end winding induction motors (OEWIM) have gained much attention, and they are used for solar photovoltaic (PV) fed pumping applications as a compromise alternative to multi-level inverters. Solar irradiance conditions further exacerbate the nonlinear control problem, resulting in significant loss of power and low reliability, which affects motor operation. To overcome these issues, this paper presents an optimized integrated control technique-based PV integrated three-level dual inverter fed Open-end winding induction motors for pumping application. An integrated African vulture optimization algorithm and scalar coupled pulse width modulation (AVO-SCPWM) based control techniques are proposed to extract the maximum power from the solar PV source and control the induction motor pump. Here, the AVO-based maximum power point tracking (MPPT) technique adjusts the modulation index (ma) by insolation and temperature. The proposed technique balances the zero-sequence current, reduces THD, and reduces the switching losses over the inverter. The proposed work is evaluated in MATLAB/Simulink software and compared with the existing conventional induction motor (IM), Conventional OEWIM Drive, and scalar decoupled PWM-based IM techniques under two climatic conditions. Thus, the simulation results demonstrate that the proposed technique accomplishes better than the existing techniques.

show abstract

Section: African Vulture Optimization (Avo) Algorithmmentioning

confidence: 99%

Technique De Contrôle Intégrée Optimisée Pour Vautour Africain Pour Application De Pompe À Moteur À Induction À Enroulement Ouvert À Alimentation Pv

VENUGOPALAN,

VARGHESE,

THANKASWAMY

2024

RRST-EE

View full text Add to dashboard Cite

show abstract

“…Users only need to understand the network structure and do not have to rely on the characteristics of the data like feature extraction. Therefore, Previous studies have found that when using multiple single character images to train a network model, due to the large sample size, it requires a lot of time and computer resources to train a model well [5][6][7]. Although distributed parallel computing can accelerate model training, the computer resources occupied have not decreased.…”

Section: Text Recognitionmentioning

confidence: 99%

“…In order to improve the LRN layer in the AlexNet network, it can be considered to increase the degree of positive excitation, so as to exert stronger positive effects on responsive neurons. This can further enhance the model's learning ability for important features, thereby improving the model's performance [8].…”

Section: Text Recognitionmentioning

confidence: 99%

A Financial Accounting Voucher Recognition Strategy Based on Deep Learning

Yang,

Li,

2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

In order to improve the accuracy and efficiency of paper financial reimbursement vouchers, a deep learning based automatic recognition strategy for financial accounting vouchers is proposed. This article designs the basic process of deep learning for image classification and text recognition, and establishes invoice image datasets for training CNN networks. Next, parameter design is performed on the AlexNet network structure, and the trained network model is used to improve the digital recognition method. The experimental part of the text annotation system collected multiple invoice text recognition datasets, and the optimized model is subjected to network training and testing experiments on the dataset. The test results show that the detection accuracy of specific fields in the invoice image reaches over 95%, and the single item recognition rate of each field reaches about 95%. The model accuracy and inference speed can meet the performance requirements.

show abstract

Recognition of brain stroke shape using multiscale morphological image processing

Cited by 2 publications

References 24 publications

Technique De Contrôle Intégrée Optimisée Pour Vautour Africain Pour Application De Pompe À Moteur À Induction À Enroulement Ouvert À Alimentation Pv

Technique De Contrôle Intégrée Optimisée Pour Vautour Africain Pour Application De Pompe À Moteur À Induction À Enroulement Ouvert À Alimentation Pv

A Financial Accounting Voucher Recognition Strategy Based on Deep Learning

Contact Info

Product

Resources

About