Time Series Prediction of Viable Embryo and Automatic Grading in IVF using Deep Learning

Background: The process of In Vitro Fertilization (IVF) involves collecting multiple samples of mature eggs that are fertilized with sperms in the IVF laboratory. They are eventually graded, and the most viable embryo out of all the samples is selected for transfer in the mother’s womb for a healthy pregnancy. Currently, the process of grading and selecting the healthiest embryo is performed by visual morphology, and manual records are maintained by embryologists. Objectives: Maintaining manual records makes the process very tedious, time-consuming, and error-prone. The absence of a universal grading leads to high subjectivity and low success rate of pregnancy. To improve the chances of pregnancy, multiple embryos are transferred in the womb elevating the risk of multiple pregnancies. In this paper, we propose a deep learning-based method to perform the automatic grading of the embryos using time series prediction with Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN). Methods: CNN extracts the features of the images of embryos, and a sequence of such features is fed to LSTM for time series prediction, which gives the final grade. Results: Our model gave an ideal accuracy of 100% on training and validation. A comparison of obtained results is made with those obtained from a GRU model as well as other pre-trained models. Conclusion: The automated process is robust and eliminates subjectivity. The days-long hard work can now be replaced with our model, which gives the grading within 8 seconds with a GPU.

Developing an Online Test to Measure Writing and Speaking Skills Automatically

As a result of the Japanese Ministry of Education's recent edict that students' written and spoken English should be assessed in university entrance exams, there is an urgent need for tools to help teachers and students prepare for these exams. Although some commercial tools already exist, they are generally expensive and inflexible. To address these shortcomings, a new open-source, online test for assessing English ability was developed. The test features the automatic grading not only of reading and listening, but also of speaking and writing. Thus, the general English ability of large numbers of students can be checked quickly online, making the test suitable for use in entrance exams and placements tests. It is based around the Moodle LMS and features several new plugins to automatically grade speaking and writing. This paper details plugin development, shows preliminary samples, and explains how test reliability will be verified by comparing students' scores with human-ratings and widely used tests such as IELTS, TOEIC, and CASEC.

Grading Method of Potted Anthurium Based on RGB-D Features

A grading method of potted Anthurium based on machine vision is proposed. A detection system is designed to acquire color images and depth images of potted Anthurium, and the three-dimensional point-cloud image is reconstructed after registration. According to the testing requirements of potted Anthurium, the minimum enclosing rectangle method is used to measure the width of crowns and spathes. The bubble sequencing method is used to measure the plant height, and the clustering segmentation method is used to calculate the number of spathes. Online automatic grading software for potted Anthurium is developed. Compared with manual measurement, the average measurement accuracies of machine vision for crown width, plant height, spathe width, and spathe number are 98.4%, 98.4%, 98.8%, and 86.7%, respectively. The accuracy rate of grading is 85.86%, which can meet the requirements of automatic grading of potted Anthurium.

Evaluation of an Algorithm for Automatic Grading of Forum Messages in MOOC Discussion Forums

Discussion forums are a valuable source of information in educational platforms such as Massive Open Online Courses (MOOCs), as users can exchange opinions or even help other students in an asynchronous way, contributing to the sustainability of MOOCs even with low interaction from the instructor. Therefore, the use of the forum messages to get insights about students’ performance in a course is interesting. This article presents an automatic grading approach that can be used to assess learners through their interactions in the forum. The approach is based on the combination of three dimensions: (1) the quality of the content of the interactions, (2) the impact of the interactions, and (3) the user’s activity in the forum. The evaluation of the approach compares the assessment by experts with the automatic assessment obtaining a high accuracy of 0.8068 and Normalized Root Mean Square Error (NRMSE) of 0.1799, which outperforms previous existing approaches. Future research work can try to improve the automatic grading by the training of the indicators of the approach depending on the MOOCs or the combination with text mining techniques.