In recent years, the rise of advanced artificial intelligence technologies has had a profound impact on many fields, including education and research. One such technology is ChatGPT, powerful large language model developed by OpenAI. This offers exciting opportunities for students educators, personalized feedback, increased accessibility, interactive conversations, lesson preparation, evaluation, new ways to teach complex concepts. However, ChatGPT poses different threats traditional...

In recent years, the rise of advanced artificial intelligence technologies has had a profound impact on many fields, including education and research. One such technology is ChatGPT, powerful large language model developed by OpenAI. This offers exciting opportunities for students educators, personalized feedback, increased accessibility, interactive conversations, lesson preparation, evaluation, new ways to teach complex concepts. However, ChatGPT poses different threats traditional...

Programming is a vital skill in computer science and engineering-related disciplines. However, developing source code an error-prone task. Logical errors are particularly hard to identify for both students professionals, single error unexpected end-users. At present, conventional compilers have difficulty identifying many of the (especially logical errors) that can occur code. To mitigate this problem, we propose language model evaluating codes using bidirectional long short-term memory...

Computer programming has attracted a lot of attention in the development information and communication technologies real world. Meeting growing demand for highly skilled programmers ICT industry is one major challenges. In this point, online judge (OJ) systems enhance learning practice opportunities addition to classroom-based learning. Consequently, OJ have created large number problem-solving data (solution codes, logs, scores) archives that can be valuable raw materials education...

The rate of software development has increased dramatically. Conventional compilers cannot assess and detect all source code errors. Software may thus contain errors, negatively affecting end-users. It is also difficult to logic errors using traditional compilers, resulting in that contains A method utilizes artificial intelligence for assessing detecting classifying as correct (error-free) or incorrect required. Here, we propose a sequential language model uses an attention-mechanism-based...

Clustering is the process of grouping similar data into a set clusters. Cluster analysis one major techniques and k-means most popular partitioning clustering algorithm that widely used. But original computationally expensive resulting clusters strongly depends on selection initial centroids. Several methods have been proposed to improve performance algorithm. In this paper we propose heuristic method find better centroids as well more accurate with less computational time. Experimental...

Most academic courses in information and communication technology (ICT) or engineering disciplines are designed to improve practical skills; however, skills theoretical knowledge equally important achieve high performance. This research aims explore how influential improving students' performance by collecting real-world data from a computer programming course the ICT discipline. Today, has become an indispensable skill for its wide range of applications significance across world. In this...

The development and operation of Online Judge System (OJS), which is used to evaluate the correctness programs, a nontrivial difficult task due various functional non-functional requirements. However, although many OJSs have been developed operated, their usefulness reported, theory for constructing has not sufficiently discussed. In this paper, we present nonfunctional requirements oriented OJS as well demonstrate internal components software architecture an OJS, in over decade evaluated...

In recent years, millions of source codes are generated in different languages on a daily basis all over the world. A deep neural network-based intelligent support model for code completion would be great advantage software engineering and programming education fields. Vast numbers syntax, logical, other critical errors that cannot detected by normal compilers continue to exist codes, development an evaluation methodology does not rely manual compilation has become essential. Even...

Abstract In software, an algorithm is a well-organized sequence of actions that provides the optimal way to complete task. Algorithmic thinking also essential break-down problem and conceptualize solutions in some steps. The proper selection pivotal improve computational performance software productivity as well programming learning. That is, determining suitable from given code widely relevant engineering education. However, both humans machines find it difficult identify algorithms without...

Programming is an essential skill in computer science and across a wide range of engineering disciplines. However, errors, often referred to as 'bugs' code, can be challenging identify rectify for both students learning program experienced professionals. Understanding, identifying, effectively addressing these errors are critical aspects programming education software development. To aid understanding classifying we propose multi-label error classification approach source code using...

This research tackles the critical challenge of achieving precise and efficient feature selection in machine learning-based classification, particularly for smart agriculture, where existing methods often fail to balance exploration exploitation complex, high-dimensional datasets. While current approaches, such as standalone nature-inspired optimization algorithms, leverage biological behaviors selection, they are limited by their inability synergize diverse strategies, resulting suboptimal...

Inter-robot communication and high computational power are challenging issues for deploying indoor mobile robot applications with sensor data processing. Thus, this paper presents an efficient cloud-based multirobot framework inter-robot to deploy autonomous robots applications. Deployment of usable service requires uninterrupted movement enhanced vision a robust classification objects obstacles using in the environment. However, state-of-the-art methods face degraded object obstacle...

As the educational landscape evolves, understanding and fostering student adaptability has become increasingly critical. This study presents a comparative analysis of (XAI) techniques to interpret machine learning models aimed at classifying levels. Leveraging robust dataset, we employed several algorithms with particular focus on Random Forest, which demonstrated 91% accuracy. Our utilizes (SHAP), (LIME), Anchors, (ALE), counterfactual explanations reveal specific contributions various...

Effectively analyzing the comments to uncover latent intentions holds immense value in making strategic decisions across various domains. However, several challenges hinder process of sentiment analysis including lexical diversity exhibited comments, presence long dependencies within text, encountering unknown symbols and words, dealing with imbalanced datasets. Moreover, existing tasks mostly leveraged sequential models encode dependent texts it requires longer execution time as processes...

As the educational landscape evolves, understanding and fostering student adaptability has become increasingly critical. This study presents a comparative analysis of XAI techniques to interpret machine learning models aimed at classifying levels. Leveraging robust dataset 1205 instances, we employed several algorithms with particular focus on Random Forest, which demonstrated highest accuracy 91%. The models’ precision, recall F1-score were also evaluated, Forest achieving precision 0.93,...

Programmers often struggle to identify and fix bugs in their programs. In recent years, many language models (LMs) have been proposed fixe rroneous programs support error recovery. However, the LMs tend generate solutions that differ from original input This leads potential comprehension difficulties for users.In this paper, we propose an approach suggest a correct program with minimal repair edits using CodeT5. We fine-tune pre-trained CodeT5 on code pairs consisting of wrong evaluate its...

In recent times, e-learning has become indispensable for both technical and general education. Among all the subjects, programming education drawn attention because of its importance continuous development in ICT sector. Finding errors a solution code is laborious task novice programmers, teachers instructors. Novice programmers are spending lot valuable time to search codes. this paper, method categorization frequent codes presented. proposed method, differences between wrong solutions...

Programmers are allowed to solve problems using multiple programming languages, resulting in the accumulation of a huge number multilingual solution codes. Consequently, identifying codes from this vast archive is challenging and non-trivial task. Considering codes' complexity compared natural conventional language models have had limited success. Deep neural network achieved state-of-the-art performance programming-related tasks. However, code classification based on problem name or...

In this modern era of the internet and information technology, a mentionable amount data is generated from different sources consistently which refers to big data. This huge not only draws great attention for further research but also helps extract knowledge infor-mation in various areas. The Information Communication Technology (ICT) area apart that, as enhancing opportunities development. ICT, most courses especially programming-related are designed improve practical skills. With...

Nowadays, computer programming is a core skill in science with software and computing-related disciplines. Thus, the demand for skilled programmers around world increasing. Programmers are writing codes to meet needs of world. Debugging source search errors time-consuming task, especially logical both novices experienced programmers. We propose language model using bidirectional long short-term memory (BiLSTM) neural network code error evaluation. The BiLSTM considers past future context...

An adaptive user interface for smart programming exercise and its platform is presented. The proposed oriented to repetitive exercises with many pro-gramming tasks through different learning phases. phases include searching, reading, coding, testing, debugging, refactoring, the learner can receive assistance in each phase. content of be adjusted by modes predefined configuration contents are controlled system according transition learner's state activities. realized types materials automatic...