Accuracy and Efficiency Comparison of Object Detection Open-Source Models

Jabir, Brahim; Falih, Noureddine; Rahmani, Khalid Imam

doi:10.3991/ijoe.v17i05.21833

Cited by 37 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Data Augmentation has a major in building an improved Deep Learning model. Data augmentation is the last stage in the preparing process of the dataset [20][21] [22].…”

Section: Data Augmentationmentioning

confidence: 99%

Employing Transfer Learning for Diagnosing COVID-19 Disease

et al. 2022

View full text Add to dashboard Cite

Corona virus’s correct and accurate diagnosis is the most important reason for contributing to the treatment of this disease. Radiography is one of the simplest methods to detect virus infection. In this research, a method has been proposed that can diagnose disease based on radiography (X-ray chest) and deep learning techniques. We conducted a comparative study by using three diagnosis models; the first one was developed by using traditional CNN, while the two others are our proposed models (second and third models). The proposed models can diagnose the COVID-19 infection, normal cases, lung opacity, and Viral Pneumonia according to the four categories in the covid19 radiography dataset. The transfer learning technology had used to increase the robustness and reliability of our model, also, data augmentation was used for reducing the overfitting and to increase the accuracy of the model by scaling rotation, zooming, and translation. The third model showed higher training accuracy of 93.18% compared to the two other models that are dependent on using traditional convolution neural networks with an accuracy of 70.28% of the first model, while the accuracy of the second model that uses data augmentation with traditional convolution neural is 90.1%, while the testing accuracy models was 68.27% for the first model, 87.55% for the second model, and 86.03% for the third model.

show abstract

“…Data Augmentation has a major in building an improved Deep Learning model. Data augmentation is the last stage in the preparing process of the dataset [20][21] [22].…”

Section: Data Augmentationmentioning

confidence: 99%

Employing Transfer Learning for Diagnosing COVID-19 Disease

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The proposed models could help clinical laboratories to classify the white blood cell subtypes efficiently. To conclude, using transfer learning to solve new problems [20][21] instead of building models from scratch is a sufficient solution. In addition to the high performance, it reduces models' training time.…”

Section: Comparison Of Vgg-16 and Mobilenet Based Modelsmentioning

confidence: 99%

WBC-CNN: Efficient CNN-Based Models to Classify White Blood Cells Subtypes

2021

View full text Add to dashboard Cite

Blood is essential to life. The number of blood cells plays a significant role in observing an individual’s health status. Having a lower or higher number of blood cells than normal may be a sign of various diseases. Thus it is important to precisely classify blood cells and count them to diagnose different health conditions. In this paper, we focused on classifying white blood cells subtypes (WBC) which are the basic parts of the immune system. Classification of WBC subtypes is very useful for diagnosing diseases, infections, and disorders. Deep learning technologies have the potential to enhance the process and results of WBC classification. This study presented two fine-tuned CNN models and four hybrid CNN-based models to classify WBC. The VGG-16 and MobileNet are the CNN architectures used for both feature extraction and classification in fine-tuned models. The same CNN architectures are used for feature extraction in hybrid models; however, the Support Vector Machines (SVM) and the Quadratic Discriminant Analysis (QDA) are the classifiers used for classification. Among all models, the fine-tuned VGG-16 performs best, its classification accuracy is 99.81%. Our hybrid models are efficient in detecting WBC as well. 98.44% is the classification accuracy of the VGG-16+SVM model, and 98.19% is the accuracy of the MobileNet+SVM.

show abstract

“…Já é provado por meio de estudos que o uso de herbicidas possui potencial de poluição e impacto na saúde de seres vivos (JABIR et al, 2021). O uso de maneira inadequada de agrotóxicos são um grave problema para a saúde pública (NAGABOOSHANAM et al, 2021).…”

Section: Introductionunclassified

Inteligência Artificial No Controle De Plantas Daninhas: Perspectivas E Refinamentos

Marra¹,

Silva²,

Furlan³

2022

Tecnologia E Novos Modelos De Negócios No Campo

View full text Add to dashboard Cite

RESUMOA necessidade de incluir tecnologia no campo, visando ganho de precisão e auxílio na vida do produtor agrícola, vem abrindo cada vez mais espaço para o uso de ferramentas de machine learning e inteligência artificial (IA). Através da utilização da IA, é possível gerar uma economia significante de volume de herbicida, sem perder eficiência na redução da interferência das plantas daninhas, o que fundamenta a agricultura digital e de precisão. Nessa circunstância, revisamos artigos científicos na base Scopus sobre deep learning (DL) e plantas daninhas, utilizando as palavras-chave "deep learning" e "weed" no período de 2013 até 2022, onde os artigos foram escolhidos criteriosamente, levando em consideração fatores como a qualidade da pesquisa e abrangência do assunto abordado dentro do escopo desta revisão. Essas práticas são favoráveis ao produtor, uma vez que o mesmo consegue reduzir o custo de controle químico e aumenta a eficiência do processo, além de evitar a poluição ambiental. O DL permite o controle automatizado por robôs e a pulverização localizada de herbicidas, sendo totalmente plausível pensar na possibilidade de superar a dependência de mão de obra e controle químico com preços elevados. Esse tipo de ferramenta fornece o benefício do auxílio da tomada de decisão por parte do agricultor, onde ele pode agir de maneira eficiente na hora e no lugar correto, seja para mapear, replantar ou fertilizar áreas que produzem fontes de alimentos ou bioenergia. Tal tecnologia é flexível e se adequa bem em diferentes lavouras. Assim, podemos explorá-los estrategicamente para pulverizar ingredientes ativos e espalhar bioagentes entomopatogênicos (por exemplo, Cotesia flavipes e Thricrogramma spp.) no campo, em quaisquer lugares estratégicos, visando suprimir pragas economicamente relevantes (por exemplo, Diatraea saccharalis , Mahanarva fimbriolata, vírus do mosaico da cana-de-açúcar e ervas daninhas) com mais precisão e responsabilidade ambiental do que é possível com as abordagens tradicionais, evitando tráfego intenso de maquinário e contato com o objeto. Isso mostra que os insights sobre as informações resultantes de nossa revisão integrativa são oportunos. Eles fornecerão conhecimento para progredir na proeminência do campo na operação de máquinas voadoras (aviões e VANT's), visando sempre elevar o custo-benefício da produção de cana-de-açúcar com foco nos maiores desafios do setor, como alcançar a segurança alimentar e energética, prosperando em um mundo

show abstract

Accuracy and Efficiency Comparison of Object Detection Open-Source Models

Cited by 37 publications

References 18 publications

Employing Transfer Learning for Diagnosing COVID-19 Disease

Employing Transfer Learning for Diagnosing COVID-19 Disease

WBC-CNN: Efficient CNN-Based Models to Classify White Blood Cells Subtypes

Inteligência Artificial No Controle De Plantas Daninhas: Perspectivas E Refinamentos

Contact Info

Product

Resources

About