Green Coffee Beans Classification Using Attention-Based Features and Knowledge Transfer

Yang, Po-Yen; Jhong, Sin-Ye; Hsia, Chih-Hsien

doi:10.1109/icce-tw52618.2021.9603134

Cited by 8 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, the ResNet18 in this experiment was not the optimal model, resulting in a low accuracy rate of the lightweight model. In contrast to Yang et al [19], the precision of LDCNN increased by 2.12%, Recall was raised by 0.36%, and F1-score gained by 1.74%. Finally, the LDCNN was placed on Raspberry Pi 4B to execute the green coffee bean quality detection system (see Table 6).…”

Section: Comparison Of Model Efficiency and Embedded Systemcontrasting

confidence: 84%

“…The accuracy rate of the lightweight model reached up to 91% with parameters of 256,779. As illustrated in Table 5, Yang et al [19] put forward DSC, SAM, SpinalNet, and KD methods to train the model when the F1 score achieved 96.54%. Compared with LDCNN, the previous model [18] had higher accuracy, and lower parameters since the latter took ResNet18 as the teacher model for training.…”

Section: Comparison Of Model Efficiency and Embedded Systemmentioning

confidence: 99%

“…Next, they applied YoloV3 to divide good and bad beans which had a recognition rate of 94.63%. Yang et al [19] employed the CNN model based on KD, spatial-wise attention module (SAM), and Spinal-Net [26] to achieve an accuracy rate of 96.54% on the F1 score. The recent progress in AI technology enables the labeling of data and the use of neural network design to allow the machine to automatically learn the data, and the neural network to predict and make decisions based on the characteristics of the learned data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Explainable and Lightweight Deep Convolutional Neural Network for Quality Detection of Green Coffee Beans

Hsia¹,

Lee²,

Lai³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

In recent years, the demand for coffee has increased tremendously. During the production process, green coffee beans are traditionally screened manually for defective beans before they are packed into coffee bean packages; however, this method is not only time-consuming but also increases the rate of human error due to fatigue. Therefore, this paper proposed a lightweight deep convolutional neural network (LDCNN) for the quality detection system of green coffee beans, which combined depthwise separable convolution (DSC), squeeze-and-excite block (SE block), skip block, and other frameworks. To avoid the influence of low parameters of the lightweight model caused by the model training process, rectified Adam (RA), lookahead (LA), and gradient centralization (GC) were included to improve efficiency; the model was also put into the embedded system. Finally, the local interpretable model-agnostic explanations (LIME) model was employed to explain the predictions of the model. The experimental results indicated that the accuracy rate of the model could reach up to 98.38% and the F1 score could be as high as 98.24% when detecting the quality of green coffee beans. Hence, it can obtain higher accuracy, lower computing time, and lower parameters. Moreover, the interpretable model verified that the lightweight model in this work is reliable, providing the basis for screening personnel to understand the judgment through its interpretability, thereby improving the classification and prediction of the model.

show abstract

Section: Comparison Of Model Efficiency and Embedded Systemcontrasting

confidence: 84%

Section: Comparison Of Model Efficiency and Embedded Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Explainable and Lightweight Deep Convolutional Neural Network for Quality Detection of Green Coffee Beans

Hsia¹,

Lee²,

Lai³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…[3] The face is the most expressive and communicative part of a human being. [4][5] A face alignment is performed, and the aligned image crops the face to obtain the entire face area as input. In the training process of the macro-expression detection model, an attention mechanism is added to allow the model to focus only on the facial regions that are helpful for the emotion classification results and enhance the generalization ability of the model.…”

Section: Literature Surveymentioning

confidence: 99%

Student Expression Detection in E-Learning Platforms

K. Sai Bhavya Sri,

K. Sai Swetha,

K. Bhavani

et al. 2024

EPRA

View full text Add to dashboard Cite

Our research suggests a deep learning method for determining how engaged students are with their online courses. Our method makes use of convolutional neural networks (CNNs) to interpret facial expressions that are recorded via webcams during online conversations. To provide the best possible model input, we preprocess face photos and select a varied dataset. The CNN architecture captures both spatial and temporal dependencies, enhancing engagement level detection accuracy. Our model performs well in classifying expressions that indicate curious, distracted, enthusiastic, observant, uninterested through training and validation. In conclusion, that the online learning experience may be enhanced by using deep learning algorithms for engagement detection, making it more advantageous and successful for students. KEYWORDS – CNN, Webcams, Engagement level, Online learning, Deep Learning, Facial expressions

show abstract

A coffee bean classifier system by roast quality using convolutional neural networks and computer vision implemented in an NVIDIA Jetson Nano

Vilcamiza

Trelles

Vinces

et al. 2022

2022 Congreso Internacional De Innovación Y Tendencias en Ingeniería (CONIITI)

View full text Add to dashboard Cite

Green Coffee Beans Classification Using Attention-Based Features and Knowledge Transfer

Cited by 8 publications

References 3 publications

An Explainable and Lightweight Deep Convolutional Neural Network for Quality Detection of Green Coffee Beans

An Explainable and Lightweight Deep Convolutional Neural Network for Quality Detection of Green Coffee Beans

Student Expression Detection in E-Learning Platforms

A coffee bean classifier system by roast quality using convolutional neural networks and computer vision implemented in an NVIDIA Jetson Nano

Contact Info

Product

Resources

About