Thin MobileNet: An Enhanced MobileNet Architecture

Sinha, Debjyoti; El-Sharkawy, Mohamed

doi:10.1109/uemcon47517.2019.8993089

Cited by 147 publications

(54 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 3 reflects our proposed approach’s performance and other related approaches in terms of Sensitivity, Specificity, Accuracy, JSI, and MCC. The MobileNet-based models exhibited a better performance in classifying the region of interest with minimal computational efforts; the MobileNet V2 exhibited an optimal efficiency in disease classification [ 70 ]. The MobileNet V2 model encompassed LSTM which has an impact on the crucial parameters like learning rates and input and output gates that yield a better outcome.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Srinivasu

SivaSai

Ijaz

et al. 2021

Sensors

451

169

View full text Add to dashboard Cite

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region’s image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

show abstract

Section: Resultsmentioning

confidence: 99%

“…The two hyper-features width multiplier and the resolution multiplier help adjust the optimal size window for accurate prediction based on the context [ 70 ]. In the proposed model, the input size of the image is 224 × 224 × 3.…”

Section: Methodsmentioning

confidence: 99%

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Srinivasu

SivaSai

Ijaz

et al. 2021

Sensors

451

169

View full text Add to dashboard Cite

show abstract

“…A Tabela 7 apresenta os resultados obtidos por trabalhos correlatos com utilização de CNNs com arquiteturas semelhantes às que implementamos em nosso estudo. Pode-se notar que os resultados obtidos em nosso trabalho com os algoritmos HGBC e as CNNs com arquitetura VGG19 e ResNet 152 V2 se mostram favoráveis para utilização dos algoritmos implementados na classificação das lesões malignas da pele, superando os valores obtidos por [19], [20], [21] e [22] e ficando bem próximos dos valores alcançados por [17] e [18]. Para tal comparação foi escolhida a métrica acurácia por ser objetiva em seu resultado trazendo o número de acertos positivos pelo número total de instâncias.…”

Section: Discussionunclassified

Aprendizado de máquina aplicado ao diagnóstico de câncer de pele

Silva¹,

Souza²,

Bambil³

et al. 2021

Anais Do 15. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

Na última década, as imagens médicas têm demonstrado relevante papel no diagnóstico precoce de câncer de pele, notadamente, com o advento das tecnologias de inteligência artificial que aprendem a diferenciar classes de imagens com base em imagens pré-classificadas, como por exemplo, aquelas obtidas em bancos de imagens médicas contendo lesões cutâneas classificadas como malignas ou benignas. Neste estudo apresentamos os resultados de identificação e classificação de lesões de pele quanto à malignidade usando uma plataforma de aprendizado de máquina desenvolvida em nosso laboratório — a “FAON_Machine_Learning_Platform (FAON_MLP)” — e as redes neurais convolucionais pré-treinadas ResNet 152 V2, VGG16, VGG19 e AlexNet. Para a avaliação de desempenho dos algoritmos segundo métricas objetivas, se usou um banco de dados público com imagens contendo lesões de pele classificadas como benignas ou malignas. Para ser mais preciso, o banco de dados de imagens possui 1800 imagens diagnosticadas com benignas e 1497 imagens diagnosticadas como malignas. São apresentados os resultados de desempenho dos diversos algoritmos. É discutida também uma avaliação comparativa entre as técnicas utilizadas e com outras técnicas reportadas na literatura. Os resultados se mostraram promissores na diferenciação entre lesões benignas e malignas, com grande potencial para auxiliar profissionais da área da saúde no diagnóstico precoce de câncer de pele, evitando os desdobramentos da sua não ocorrência, como procedimentos cirúrgicos, metástases e até mesmo óbito.

show abstract

“…For object detection, the Single Shot multi-box Detector (SSD) [5] has been widely used because of the simplicity of the architecture. Therefore, the combination of MobileNet and SSD may be used to improve the accuracy of object detection on COVID-19, as shown in the Thin MobileNet [6] with SSD. However, the conventional combination of MobileNet or Thin MobileNet and SSD tends to increase the model size and computation cost, which makes it less efficient to deploy the object detection model on embedded devices.…”

Section: Introductionmentioning

confidence: 99%

Light-weight MobileNet for Fast Detection of COVID-19

Firmansyah

Koh

Dewanto

et al. 2021

J-TIT

View full text Add to dashboard Cite

The machine learning models based on Convolutional Neural Networks (CNNs) can be effectively used for detection and recognition of objects, such as Corona Virus Disease 19 (COVID-19). In particular, the MobileNet and Single Shot multi-box Detector (SSD) have recently been proposed as the machine learning model for object detection. However, there are still some challenges for deployment of such architectures on the embedded devices, due to the limited computational power. Another problem is that the accuracy of the associated machine learning model may be decreased, depending on the number of concerned parameters and layers. This paper proposes a light-weight MobileNet (LMN) architecture that can be used to improve the accuracy of the machine learning model, with a small number of layers and lower computation time, compared to the existing models. By experimentation, we show that the proposed LMN model can be effectively used for detection of COVID-19 virus. The proposed LMN can achieve the accuracy of 98% with the file size of 27.8 Mbits by replacing the standard CNN layers with separable convolutional layers.

show abstract

Thin MobileNet: An Enhanced MobileNet Architecture

Cited by 147 publications

References 10 publications

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Aprendizado de máquina aplicado ao diagnóstico de câncer de pele

Light-weight MobileNet for Fast Detection of COVID-19

Contact Info

Product

Resources

About