Automated Student Review System with Computer Vision and Convolutional Neural Network

Siam, Sadman Chowdhury; Faisal, Abrar; Mahrab, Niazi; Haque, Akm Bahalul; Suvon, Md Naimul Islam

doi:10.1109/icccis51004.2021.9397164

Cited by 8 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is presented how two models were trained using the FER2013 dataset. After 7 epochs of testing, the first model, VGG-16, had a 54% accuracy rate, whereas the second model had a 69% accuracy rate after about 40 epochs [14].An outstanding onedimensional convolutional neural network with an accuracy of 96.60% shone out in study on the identification of negative emotions in Thai language studies. Utilizing a ten-fold crossvalidation technique, the study assessed deep learning methods with a variety of open emotive speech datasets [24].…”

Section: Review Based On Resultsmentioning

confidence: 99%

“…Regarding the purpose of creating reviews of students depending on the mental health of the students of a class, there are numerous manual software methods available. In 2021, Siam et al introduced this kind of computer vision and deep learning-based student emotion detection system [14]. Furthermore, in 2020 Nishchal J. et al will be able to automatically detect suspicious or unethical activity during a test.…”

Section: Background Studymentioning

confidence: 99%

“…This could potentially enhance the accuracy of the model. However, due to limitations in data collection, these options could not be tested in the current work [14]. The accuracy of facial recognition systems is generally lower than fingerprint and iris recognition systems.…”

Section: Limitationsmentioning

confidence: 99%

See 2 more Smart Citations

Emotion Detection Using Machine Learning: An Analytical Review

Shawon,

Tabassum,

Mahmud

2024

Malaysian J. Sci. Adv. Tech.

View full text Add to dashboard Cite

This paper provides an analytical review of emotion detection using machine learning techniques. The study focuses on the attempts made in the past and present to develop emotion detecting systems. Numerous methods for identifying emotions have been introduced by students, and several outstanding works have already been found. In order to identify emotions, machine learning has been the primary focus. This paper also includes a summary of the frameworks, algorithms, and datasets that have been employed thus far to address this issue.

show abstract

Section: Review Based On Resultsmentioning

confidence: 99%

Section: Background Studymentioning

confidence: 99%

See 1 more Smart Citation

Emotion Detection Using Machine Learning: An Analytical Review

Shawon,

Tabassum,

Mahmud

2024

Malaysian J. Sci. Adv. Tech.

View full text Add to dashboard Cite

show abstract

“…We have used CNN [ 3 , 4 ] models because CNN can extract features from the images automatically. On computers, vision approaches need to extract necessary features manually from the image in order to use them to train their models.…”

Section: Introductionmentioning

confidence: 99%

Towards the Segmentation and Classification of White Blood Cell Cancer Using Hybrid Mask-Recurrent Neural Network and Transfer Learning

Das

Islam

Neha

et al. 2021

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

Inside the bone marrow, plasma cells are created, and they are a type of white blood cells. They are made from B lymphocytes. Antigens are produced by plasma cells to combat bacteria and viruses and prevent inflammation and illness. Multiple myeloma is a plasma cell cancer that starts in the bone marrow and causes the formation of abnormal plasma cells. Multiple myeloma is firmly identified by examining bone marrow samples under a microscope for myeloma cells. To diagnose myeloma cells, pathologists have to be very selective. Furthermore, because the ultimate decision is based on human sight and opinion, there is a possibility of error in the result. The nobility of this research is that it provides a computer-assisted technique for recognizing and detecting myeloma cells in bone marrow smears. For recognizing purposes, we have used Mask-Recurrent Convolutional Neural Network, and for detection purposes, Efficient Net B3 has been used. There are already many studies on white blood cell cancer, but very few with both segmentation and classification. We have designed two models. One is for recognizing myeloma cells, and the other is for differentiating them from nonmyeloma cells. Also, a new data set has been made from the multiple myeloma data sets, which has been used in our classification model. This research focuses on hybrid segmentation models and increases the accuracy level of the classification model. Both of our models are trained pretty well, where the Mask-RCNN model gives a mean average precision (mAP) of 93% and the Efficient Net B3 model gives 94.68% accuracy. The result of this research indicates that the Mask-RCNN model can recognize multiple myeloma and Efficient Net B3 can distinguish between myeloma and nonmyeloma cells and beats most of the state of the art in myeloma recognition and detection.

show abstract

Depression Level Determination Using Deep Learning to Help Students in the COVID-19 Pandemic Situation

Thomas¹,

Venkataraman²

2022

Proceedings of Third Doctoral Symposium on Computational Intelligence

View full text Add to dashboard Cite

Automated Student Review System with Computer Vision and Convolutional Neural Network

Cited by 8 publications

References 4 publications

Emotion Detection Using Machine Learning: An Analytical Review

Emotion Detection Using Machine Learning: An Analytical Review

Towards the Segmentation and Classification of White Blood Cell Cancer Using Hybrid Mask-Recurrent Neural Network and Transfer Learning

Depression Level Determination Using Deep Learning to Help Students in the COVID-19 Pandemic Situation

Contact Info

Product

Resources

About