Automatic Grading System Research Articles

AI in Education: Benefits and Concerns

Artificial Intelligence (AI) has rapidly transformed numerous industries, with education emerging as one of the most impacted fields. The global AI market, valued at $196.63 billion in 2023, is projected to expand significantly, reflecting the growing adoption of AI technologies. In education, AI-driven tools such as personalized learning platforms, automated grading systems, and accessibility-enhancing technologies are revolutionizing teaching and learning experiences. These advancements align with Sustainable Development Goal 4 (SDG 4) by promoting inclusive, high-quality education and lifelong learning opportunities for all. Examples like Duolingo, CoGrader, and the BBC’s AI investments demonstrate how technology is reshaping education to better engage students and improve outcomes. However, the integration of AI raises critical concerns about algorithmic bias, ethical decision-making, and data privacy. While AI can reduce human bias and improve efficiency, it risks perpetuating disparities if training data lacks diversity. Additionally, reliance on large datasets demands stringent data security measures to protect student privacy. Addressing these challenges requires collaboration among educators, policymakers, and developers to ensure AI is used responsibly. This paper examines the transformative potential of AI in education while emphasizing the need for ethical oversight and equity. Future research must focus on refining AI to meet diverse learning needs without compromising inclusivity or fairness.

Harnessing Artificial Intelligence to Transform Secondary Education in India: Innovations, Challenges, and Future Directions

India's National Education Policy (NEP) 2020 envisions a comprehensive education system that is inclusive, fair, and geared towards lifelong learning. Artificial Intelligence (AI) has a pivotal role in achieving these goals by enhancing personalized learning experiences, streamlining assessments, and promoting inclusivity within secondary education. This paper explores the integration of AI in Indian secondary education, analyzing its alignment with NEP 2020 objectives. It highlights AI innovations, such as adaptive learning platforms and automated grading systems, while also addressing challenges like data privacy, infrastructure limitations, and the need for teacher training. Through a review of recent literature and case studies, this paper offers recommendations for the responsible adoption of AI in India, underscoring the importance of policy support, ethical standards, and regional infrastructure development.

Examining refusal and acceptance sequences employing a data-driven binary rating approach

This paper presents the development and preliminary validation of a data-driven analytic binary rating rubric for assessing roleplay-elicited pragmatic performance of learners. The roleplay task consists of two items—one lunch invitation to elicit a refusal and one gift offer to elicit an acceptance in Chinese, both of which involve initiating proposals to return an earlier favor. Responses to return-to-favor invitations or offers in Chinese are challenging for L2 learners as they involve complicated discursive features. To create a practical, reliable tool for evaluating L2 performance, the researchers conducted a discourse analysis of L1 Chinese performance data (N = 22) to identify key discursive features in two domains— Intention (i.e., refusing the return-for-favor intention) and Decision (i.e., refusing/accepting the offer/invitation). A roleplay can receive up to 4 points in both domains, including one point each for orientation/directness, position, modification, and justification, for 8 total possible points. Scores assigned to both L1 and L2 performance according to the rubric reflected high inter-rater reliability. The effect of proficiency was significant on learner scores and interacted with rating domains and scenarios. Lower-level learners scored lower with addressing the interlocutor's return-for-favor intention than with the invitation or offer itself; they also scored lower with refusing than accepting an offer. By focusing on key discursive features rather than exhaustive interactional details, the rubric streamlines the evaluation process while maintaining accuracy and reliability. Future studies may extend the use of the rubric to other speech act sequences and languages and apply it to automated grading systems.

Automated grading system for quantifying KOH microscopic images in dermatophytosis

Concerning the progression of dermatophytosis and its prognosis, quantification studies play a significant role. Present work aims to develop an automated grading system for quantifying fungal loads in KOH microscopic images of skin scrapings collected from dermatophytosis patients. Fungal filaments in the images were segmented using a U-Net model to obtain the pixel counts. In the absence of any threshold value for pixel counts to grade these images as low, moderate, or high, experts were assigned the task of manual grading. Grades and corresponding pixel counts were subjected to statistical procedures involving cumulative receiver operating characteristic curve analysis for developing an automated grading system. The model’s specificity, accuracy, precision, and sensitivity metrics crossed 92%, 86%, 82%, and 76%, respectively. ’Almost perfect agreement’ with Fleiss kappa of 0.847 was obtained between automated and manual gradings. This pixel count-based grading of KOH images offers a novel, cost-effective solution for quantifying fungal load.

Deep Learning-Based Decision Support System for Automatic Detection and Grading of Surface Corrosion on Galvanized Steel Sheets

Corrosion in the sheets produced leads to significant material losses, including the loss of resources, capital, labor, energy and knowledge. Corrosion control is significant for sheets produced and sent to customers in iron and steel factories. Surface corrosion testing of produced sheets and the accurate detection of corrosion levels are of great importance. The corrosion detection process for sheets in steel factories is performed visually with the naked eye. This is a subjective and time-consuming method. Identifying corrosion damage by visual detection and accurately determining the type and extent of corrosion requires expertise. Wrong decisions at this stage lead to losses during the production phase. Therefore, there is a need for systems that can automate this process and make it human-independent. In this study, a decision support system was designed to automatically detect the level of corrosion in galvanized sheets using convolutional neural networks. The average accuracy of the system is 97.5%, the average precision is 0.98, the average recall is 1 and the average F1 score is 0.99. The results we obtained indicate that a successful system has been developed for the detection and determination of corrosion levels. The high performance of the convolutional neural network models used for corrosion detection supports the practical applicability of the developed system. This system will increase the reliability and efficiency of industrial processes by enabling the accurate and automatic classification of corrosion. This system, which meets a significant need in this area for industrial organizations, reduces production costs and also makes the corrosion detection process more consistent and faster.

Automatic Acne Severity Grading with a Small and Imbalanced Data Set of Low-Resolution Images.

Developing automatic acne vulgaris grading systems based on machine learning is an expensive endeavor in terms of data acquisition. A machine learning practitioner will need to gather high-resolution pictures from a considerable number of different patients, with a well-balanced distribution between acne severity grades and potentially very tedious labeling. We developed a deep learning model to grade acne severity with respect to the Investigator's Global Assessment (IGA) scale that can be trained on low-resolution images, with pictures from a small number of different patients, a strongly imbalanced severity grade distribution and minimal labeling. A total of 1374 triplets of images (frontal and lateral views) from 391 different patients suffering from acne labeled with the IGA severity grade by an expert dermatologist were used to train and validate a deep learning model that predicts the IGA severity grade. On the test set we obtained 66.67% accuracy with an equivalent performance for all grades despite the highly imbalanced severity grade distribution of our database. Importantly, we obtained performance on par with more tedious methods in terms of data acquisition which have the same simple labeling as ours but require either a more balanced severity grade distribution or large numbers of high-resolution images. Our deep learning model demonstrated promising accuracy despite the limited data set on which it was trained, indicating its potential for further development both as an assistance tool for medical practitioners and as a way to provide patients with an immediately available and standardized acne grading tool. chinadrugtrials.org.cn identifier CTR20211314.

ADRGS: an automatic diabetic retinopathy grading system through machine learning

ADRGS: an automatic diabetic retinopathy grading system through machine learning

Transformer-Based Sequence Modeling Short Answer Assessment Framework

Automated subjective assessment presents a significant challenge due to the complex nature of human language and reasoning characterized by semantic variability, subjectivity, language ambiguity, and judgment levels. Unlike objective exams, subjective assessments involve diverse answers, posing difficulties in automated scoring. The paper proposes a novel approach that integrates advanced natural language processing (NLP) techniques with principled grading methods to address this challenge. Combining Transformer-based Sequence Language Modeling with sophisticated grading mechanisms aims to develop more accurate and efficient automatic grading systems for subjective assessments in education. The proposed approach consists of three main phases: Content Summarization: Relevant sentences are extracted using self-attention mechanisms, enabling the system to effectively summarize the content of the responses. Key Term Identification and Comparison: Key terms are identified within the responses and treated as overt tags. These tags are then compared to reference keys using cross-attention mechanisms, allowing for a nuanced evaluation of the response content. Grading Process: Responses are graded using a weighted multi-criteria decision method, which assesses various quality aspects and assigns partial scores accordingly. Experimental results on the SQUAD dataset demonstrate the approach’s effectiveness, achieving an impressive F-score of 86%. Furthermore, significant improvements in metrics like ROUGE, BLEU, and METEOR scores were observed, validating the efficacy of the proposed approach in automating subjective assessment tasks. Doi: 10.28991/HIJ-2024-05-03-06 Full Text: PDF

Harnessing the potential of AI applications in Education: Opportunities, challenges, and future directions

The potential of artificial intelligence (AI) applications in education to revolutionize teaching and learning has attracted a lot of interest in recent years. This research paper presents an in-depth review of the many AI uses in education, such as virtual reality simulations, automated grading systems, intelligent tutoring systems, and personalized learning platforms. This article explores the potential that AI technologies offer to improve educational practices, including individualized instruction, better learning outcomes, and increased student engagement. It does this by drawing on current literature and empirical data. It also discusses the challenges and ethical encounters that come with incorporating AI into the classroom, like algorithmic bias, data privacy issues, and the digital divide. This paper delves deeper into a several possibilities for future research and development in artificial intelligence (AI) applications in education, highlighting the significance of interdisciplinary collaboration, building robust frameworks for assessment, and promoting equity and inclusivity in AI-powered learning environments.

Automated Grading Model with Adjusted Level of Lenience for Short Answer Questions using Natural Language Processing

Automated grading of short answer questions is a challenging task that involves understanding and evaluating free-text responses. This research presents an innovative model that combines the capabilities of the language model all-mpnet-base-v2 with a machine learning-based lenience adjustment mechanism to enhance the accuracy and fairness of automated grading systems. The proposed model utilizes all-mpnet-base-v2 for natural language understanding and feature extraction from student responses. To address the variability in acceptable answers and provide a fair grading system, a machine learning-based model is integrated to adjust the level of lenience dynamically. This dual approach ensures that the grading system can handle a wide range of responses while maintaining consistency and reliability. The experimental results demonstrate that the combination of all-mpnet-base-v2 with the lenience adjustment model significantly improves grading accuracy compared to traditional methods. This model represents a significant advancement in the field of educational technology, offering a robust solution for automated grading systems that can adapt to diverse educational contexts and requirements.

Framework for automation of short answer grading based on domain-specific pre-training

In the education sector, there is a growing need for efficient Automatic Short Answer Grading (ASAG) systems that require less training time, have faster inference, and provide higher accuracy. Over the past five years, researchers have made progress using deep learning for ASAG, but acquiring domain-specific labeled data remains a significant challenge. This study introduces an ASAG framework designed to learn from unlabeled domain-specific contexts while minimizing training and inference times. Our framework involves three main phases: 1) Building an unlabeled domain-specific corpus. 2) Training a pre-trained language model with this corpus. 3) Fine-tuning the pre-trained model with limited labeled domain-specific data. We explored various domain adaptations using two types of vocabulary during the pretraining stage. Our approach achieved an accuracy of 88.77% and an F1-score of 91.59% on the SPRAG dataset, improving state-of-the-art methods by 4%–5.7%. The models, including one trained from scratch with domain-specific data and vocabulary, showed robust performance, enhancing accuracy by 5.7% and F1-score by 4.84%. However, the framework's effectiveness in handling different languages or multilingual datasets remains to be explored. This framework's adaptability and efficiency enable educators to use AI for automated grading in various educational domains.

Deep learning detection of diabetic retinopathy in Scotland’s diabetic eye screening programme

Background/AimsSupport vector machine-based automated grading (known as iGradingM) has been shown to be safe, cost-effective and robust in the diabetic retinopathy (DR) screening (DES) programme in Scotland. It triages screening...

The affordances of artificial intelligence-based tools for supporting 21st-century skills:

Twenty-first-century skills should be integrated into higher education to prepare students for complex working-life challenges. Artificial intelligence (AI)-powered tools have the potential to optimise skill development among higher education students. Therefore, it is important to conceptualise relevant affordances of AI systems for 21st-century skills development in higher education. This study aimed to present an overview of journal articles published in the Web of Science database that specifically addressed the affordances of AI-based tools for 21st-century skills development. Four distinct categories of AI-based tools (intelligent tutoring systems, chatbots, AI-powered dashboards and automated grading systems) were identified as capable of promoting six main 21st-century skills (collaboration, communication, creativity, critical thinking, information and communication technology and problem-solving). The review revealed that the utilisation of AI-based tools might contribute to the simultaneous development of multiple 21st-century skills (e.g., collaboration and critical thinking). The results showed that adaptive feedback from AI plays a significant role as a facilitator in the development of 21st-century skills. Furthermore, the utilisation of diverse functional AI affordances (e.g., prediction and profiling) might contribute to the development of various skills. AI-based technologies appeared to target the 21st-century skills of problem-solving and its subskills the most. Implications for practice or policy: More functional affordances of AI (e.g., prediction and profiling) should be employed in AI-based tools. This could support higher education students’ 21st-century skills. AI-based tools (e.g., chatbots and intelligent tutors) interact with end users through their data. AI systems have the potential to promote 21st-century skills by using students’ multimodal data. AI technologies should be more integrated into the social sciences and humanities in the higher education context to support students’ 21st-century skills.

FruitVision: A deep learning based automatic fruit grading system

Abstract Quality assessment of fruits plays a key part in the global economy’s agricultural sector. In recent years, it has been shown that fruits are affected by different diseases, which can lead to widespread economic failure in the agricultural industry. Traditional manual visual grading of fruits could be more accurate, making it difficult for agribusinesses to assess quality efficiently. Automatic grading of fruits using computer vision has become a prominent area of study for many researchers. In this study, a deep learning-based model called FruitVision is proposed for the automatic grading of various fruits. The results showed that FruitVision performed all the existing models and obtained an accuracy of 99.42, 99.50, 99.24, 99.12, 99.38, 99.38, 99.17, 98.86, and 97.96% for the apple, banana, guava, lime, orange, pomegranate, Ajwa date, Mabroom date, and mango, respectively, using 5-fold cross-validation. This is a remarkable achievement in the field of AI-based fruit grading systems.

Student Performance Prediction Using Machine Learning Algorithms

Education is crucial for a productive life and providing necessary resources. With the advent of technology like artificial intelligence, higher education institutions are incorporating technology into traditional teaching methods. Predicting academic success has gained interest in education as a strong academic record improves a university’s ranking and increases student employment opportunities. Modern learning institutions face challenges in analyzing performance, providing high-quality education, formulating strategies for evaluating students’ performance, and identifying future needs. E-learning is a rapidly growing and advanced form of education, where students enroll in online courses. Platforms like Intelligent Tutoring Systems (ITS), learning management systems (LMS), and massive open online courses (MOOC) use educational data mining (EDM) to develop automatic grading systems, recommenders, and adaptative systems. However, e-learning is still considered a challenging learning environment due to the lack of direct interaction between students and course instructors. Machine learning (ML) is used in developing adaptive intelligent systems that can perform complex tasks beyond human abilities. Some areas of applications of ML algorithms include cluster analysis, pattern recognition, image processing, natural language processing, and medical diagnostics. In this research work, K-means, a clustering data mining technique using Davies’ Bouldin method, obtains clusters to find important features affecting students’ performance. The study found that the SVM algorithm had the best prediction results after parameter adjustment, with a 96% accuracy rate. In this paper, the researchers have examined the functions of the Support Vector Machine, Decision Tree, naive Bayes, and KNN classifiers. The outcomes of parameter adjustment greatly increased the accuracy of the four prediction models. Naïve Bayes model’s prediction accuracy is the lowest when compared to other prediction methods, as it assumes a strong independent relationship between features.

Performance analysis of Alexnet for Classification of Knee Osteoarthritis.

In recent years, automated grading of knee osteoarthritis (KOA) has focused on determining disease progression. Clinical examinations and radiographic image review are necessary for diagnosis. Timely and accurate diagnosis, along with medical care, can slow down KOA progression. X-rays and MRI are crucial diagnostic tools. KOA diagnosis traditionally relies on radiologists' and clinicians' experience. However, the rapid development of deep learning technology (AI) offers promising solutions for medical applications. The objective of this study was to review and summarize various methods proposed by researchers for the automated grading of KOA. Additionally, this study aimed to evaluate the performance of the AlexNet model in classifying the severity of KOA. The performance of the AlexNet model has been compared to that of other models, and the results have been assessed. A comprehensive review of existing research on automated grading of KOA has been conducted. Various methods proposed by different researchers have been examined and summarized. The AlexNet model has been employed for classifying the severity of KOA, and its performance has been evaluated. A comparative analysis has been carried out to compare the performance of the AlexNet model with that of other models. The results obtained from the evaluation have been assessed to determine the effectiveness of the AlexNet model in the automated grading of KOA. The results of the study indicate that the AlexNet model demonstrates promising performance in classifying the severity of KOA. Comparative analysis reveals that the AlexNet model outperforms other models in terms of accuracy and efficiency. The evaluation of the model's performance provides valuable insights into the effectiveness of deep learning techniques for automated grading of KOA. This study highlights the significance of automated grading in the diagnosis and management of knee osteoarthritis. The utilization of deep learning technology, particularly the AlexNet model, shows promise in accurately classifying the severity of KOA. The findings suggest that automated grading methods can serve as valuable tools for healthcare professionals in assessing the progression of KOA and providing appropriate medical care. Further research and development in this area can contribute to enhancing the efficiency and accuracy of automated grading systems for KOA.

Design and Implementation of Machine Learning Algorithms in Automatic Grading of Students' Assignments

This study introduces machine learning methods for automatically grading students' assignments, catering to the changing demands of education in the digital age. By utilizing diverse techniques, the aim is to simplify the grading process, give prompt feedback, and improve overall efficiency in assessment practices. The research delves into the different types of assignments such as written responses and coding tasks, and presents a range of ML algorithms including NB, Decision Trees (DT), RF, SVM, Linear Regression (LR), KNN, and Ensemble Methods (EMs). The implementation involves extracting relevant features from assignments, preprocessing data to handle noise and outliers, and training models on a varied set of examples. The grading system prioritizes interpretability, accuracy, and efficiency while aligning with educational objectives and grading policies. Evaluation is done using suitable metrics like recall, accuracy, precision, F1 score for each algorithm. The study contributes to the progress of automated grading systems by providing valuable insights for educators on the potential impact of machine learning in enhancing assessment processes. Additionally, the designed algorithms demonstrate adaptability for different types of assignments and serve as a foundation for future enhancements in grading precision and efficiency.

Breaking Traditional Boundaries in Translation Pedagogy; Evaluating How Senior Lecturers Have Incorporated Digital Tools to Enhance Translation Teaching

Digital technology has brought significant transformation in translation pedagogy, mainly in helping lecturers integrate digital tools in teaching translation courses. However, it is significant to gain insights from the experiences of the senior lecturers who are gradually accepting the integration of technology in translation pedagogy. The focus of this paper is to gain insights from Professors in translation pedagogy on their challenges in transiting from traditional teaching systems to digital technological systems, also sharing their solutions to the challenges. Through the use of both survey questionnaires and semi-structured interviews, data was gathered from 93 extensively experienced professors in translation. The gathered data was analyzed using thematic analysis and statistical measures. The results of the data from the interviews showed four main themes, including the theme of transition challenges, the theme of assessment and evaluation challenges, the theme of inclusion and accessibility in digital technology, and the theme of actions the professors had taken in digital technology. The professors confirmed actions such as “finding appropriate online platforms that allowed for real-time cooperation" (Professor 2), "using virtual translation technologies that enabled real-time collaboration on documents" (Professor 5), and "encouraging collaborative translation exercises in real-time Google Docs" (Professor 2)”. The data from the survey questionnaire unveiled specific ways in which digital tools have assisted the senior lecturers in teaching translation courses, including teaching materials for translation courses are now prepared more quickly due to AI technologies, and automated grading systems driven by AI have reduced assessment time and generated feedback for students' translation projects. The Professors generally accepted the impacts of technological advancements, mainly AI tools, in teaching translation and improving the general performance of the learners.

SOCIAL MEDIA AND AI INTEGRATION INTO TEACHING AND LEARNING EXPERIENCE

The dynamics of teaching and learning have changed due to the rise of modern technologies, mainly social media and artificial intelligence (AI). This study determined the elementary teachers' response to the emerging use of social media and AI in educational methods and how these may impact the students' learning. Data was collected using a survey questionnaire composed of social media and AI use and views on the role of educators in the digital age. Statistical methods, including mean and standard deviation, were used in data analysis. The respondents demonstrated their proficiency in using social media and AI, representing a range of instructional roles and experience levels. Results indicate that Facebook and YouTube are frequently used online for assistive instructional information. Moreover, various AI techniques were used, such as automated grading systems, tailored learning platforms, and language translation services. Teachers incorporated these technologies and emphasized the need for further professional development; this shed light on the strategic integration of social media and AI in education holds tremendous potential to revolutionize learning paradigms, foster collaboration, and cultivate personalized learning experiences. However, it requires careful navigation of ethical, privacy, and accessibility considerations to harness its full benefits and ensure inclusivity and integrity within educational ecosystems.

Deep learning-based fully automated grading system for dry eye disease severity.

There is an increasing need for an objective grading system to evaluate the severity of dry eye disease (DED). In this study, a fully automated deep learning-based system for the assessment of DED severity was developed. Corneal fluorescein staining (CFS) images of DED patients from one hospital for system development (n = 1400) and from another hospital for external validation (n = 94) were collected. Three experts graded the CFS images using NEI scale, and the median value was used as ground truth. The system was developed in three steps: (1) corneal segmentation, (2) CFS candidate region classification, and (3) estimation of NEI grades by CFS density map generation. Also, two images taken on different days in 50 eyes (100 images) were compared to evaluate the probability of improvement or deterioration. The Dice coefficient of the segmentation model was 0.962. The correlation between the system and the ground truth data was 0.868 (p<0.001) and 0.863 (p<0.001) for the internal and external validation datasets, respectively. The agreement rate for improvement or deterioration was 88% (44/50). The fully automated deep learning-based grading system for DED severity can evaluate the CFS score with high accuracy and thus may have potential for clinical application.