Computer Science Learning Research Articles

DEVELOPMENT OF A DECISION SUPPORT SYSTEMFOR LEGAL CASE ANALYSIS AND DECISION MAKING USING RECURRENT NEURAL NETWORK

Over the last few decades, there have been substantial developments in a variety of domains, including computer science, artificial intelligence, and machine learning, which has accelerated the evolution of intelligent systems such as decision support systems with applications in fields such as healthcare, finance, manufacturing, transportation and legal systems. Decision Support Systems (DSS) in legal systems also known as Judicial Decision Support Systems (JDSS) are designed to assist judges and other legal professionals in making legal decisions. JDSS can be used in various areas of law, such as criminal law, civil law, and family law. JDSS can be helpful in various ways, such as reducing the time and effort required to make legal decisions, increasing consistency and fairness in legal decisions, and providing judges and legal professionals with access to relevant legal information and expertise. However, JDSS also have limitations and challenges, such as the need for accurate and up-to-date legal data and the potential for bias in the data or algorithms used in the system. This research work developed a system to assist legal practitioners and it is also designed to enhance the efficiency, transparency, and accessibility of the judicial process. The performance of the developed system was evaluated using some metrics and the following results were obtained: accuracy of 80%, 87% precision, 87% sensitivity/recall and an F1-score of 87%.

Enhancing Children's Academic Learning Experience: Natural Language Interface Designs in Educational Application

User Interaction (UI) designs, a crucial part of the modern internet industry, have been envolving and becoming more and more sophisticated and advanced. Recently, with the development of Machine Learning in Computer Science, Natural Language Interface (NLI) designs, a new division of the UI designs, appears into public’s view. With its special focus on using Natural Language Processing (NLP) to enable applications respond and execute useful actions in response to users’ input, UI designers are able to implement an array of new functions into the application, allowing children (12 to 18 years old) to better interact with the applications. This research primarily focuses on how NLI designs in educational settings are able to enhance their learning experience and academic performance. In particular, with a deep literary analysis, this research incorporates several important findings about NLI designs’ positive effects on children’s academic learning experience and performance. Through thorough investigations, this research concludes that while there are several technical limitations on NLI designs due to the limited level of technology, they can still facilitate children’s learning experience and academic performance by satisfying children, letting them stay longer in the application, and providing them a better guide, which enables them to have a better navigation in the application’s learning environment.

Advancing Equity and Access: Addressing the Side Effects of Broadening Participation in Computer Science K–12 Education

Over the past 20 years, there has been a concentrated effort on expanding K–12 pathways, experiences, and access in computer science education (CSEd). Computer science (CS) is a multifaceted discipline within education, and the current emphasis in education policy has focused on how to expand access for K–12 students in CSEd that will lead to increased innovation and bring new participants into the United States labor economy. Industry partners have advocated for policies and incentives to increase pathways to CS opportunities. This chapter interrogates the side effects of CSEd and offers a framework for considering how side effects impact CS teaching and learning. We highlight the barriers that exist within CS and CSEd and how broadening participation in computing efforts could address longstanding equity and disparity issues.

Creative learning in final year students in computer engineering: A case study of the University of Matanzas

The training of creative computer professionals is considered a strategic process in different countries because it is essential for the computerization of society. This paper proposes an approach to the study of creative computer science learning for the digital transformation of modern society. The aim of the research was to evaluate the creative learning of computer science during the training of computer science professionals. An instrument derived from previous research and metrics was applied to evaluate creative learning in the two groups of terminal years of the computer engineering course at the University of Matanzas with a mixed paradigm. The quantitative analysis diagnosed that more than sixty-five percent of the students are evaluated as poor and fair in both years. The qualitative analysis revealed the inadequacies of the teaching staff in the use of computer science teaching approaches, and the four stages of formation of creative learning in computer science in the degree course: pre-university stage, basic stage, professional stage and research stage. They also revealed three key factors in the formation of creative learning in computer science: the integration of subjects, the solution of real projects, and the mainly emotional support provided by teachers and other professionals to students during their integration into the computerization of organizations.

Creative Learning of Computer Science of Computer Science Professionals: Case University of Matanzas

Research on creativity is a common topic today, with a strong psychological component influencing its definition. This research takes the definition of creative learning from the theory of subjectivity, which is a strand of the cultural-historical approach. However, few studies have defined creativity in the field of computer science and even fewer have addressed learning in this field. This paper aims to diagnose creative learning in computer science in a computer engineering course at the University of Matanzas. In order to achieve this objective, creative learning is first established as an expression of creativity in learning. Then, it is described as a fundamental form of computer activity and, finally, creative learning in computer science is defined. A questionnaire was used to diagnose creative learning in computing. The questionnaire will be administered to 66 final year students enrolled in the academic year 2022. The indicators obtained in the theoretical section will be measured on a scale from 0 to 1. The study will first compare the data obtained through qualitative state inference, followed by the application of inferential statistical methods to further analyse the results. From the results, creative learning in computer science will be assessed and it will be found that it is generally poor. Based on the data, the hypothesis is rejected and the level of development of creative learning in computing is found to be low.

TinyML: Adopting tiny machine learning in smart cities

<div><p>Since Tiny machine learning (TinyML) is a quickly evolving subject, it is crucial that internet of things (IoT) devices be able to communicate with one another for the sake of stability and future development. TinyML is a rapidly growing subfield at the intersection of computer science, software engineering, and machine learning. Building deep learning (DL) networks that are a few hundred KBs in size has been the focus of recent research in this area. Deploying TinyML into small devices makes them smart. Reduced computation, power usage, and response time are just a few of the many advantages of TinyML. In this work, we provide an introduction to TinyML and demonstrate its benefits and architecture. Then, we investigate the meaning of quantization as a standard compression method for TinyML-related applications. There are two methods used to obtain the quantized weights of the deep learning models are quantization-aware training (QAT) and post-training quantization (PTQ), we described them in details. Next, TinyML-based solutions to improve the role of IoT devices in Smart Cities are highlighted as: lightweight training of deep learning models, inference of lightweight deep learning models in IoT devices, low power consumption, and inference of deep learning models in restricted resources of IoT devices. Finally, presenting some use cases for TinyML studies, with these studies applied to several cases in a variety of fields. To the best of the author’s knowledge, few studies have investigated TinyML as it is an emerging field.</p></div>

Scaling Carbon Footprinting: Challenges and Opportunities

Rapid and continuous increase in greenhouse gas (GHG) emissions is warming our planet at unprecedented rates. Consumer products and services, including all aspects of the corresponding supply chain, contribute to more than 75% of these emissions. Attribution of GHG emissions to each product will drive awareness and change from individual consumers to large corporations that produce and own these products. However, accurate and standards-compliant accounting of carbon emissions for millions of products is challenging as it requires detailed manufacturing and supply chain data, and subject expertise in life cycle assessment (LCA). We posit that ideas from computer science and machine learning can alleviate bottlenecks in LCA, and that research contributions from this community will accelerate solutions for accurate carbon-footprint estimation as well as carbon-abatement strategies at scale. We present the principal components of an LCA study with a step-by-step walk-through. We elaborate upon the challenges to scale LCA, and identify the opportunities to innovate in this space with techniques such as information extraction, personalized recommendations, and decision-making under uncertainty.

Electric Signals in Machine Learning Using AppInventor and Arduino

Recent developments in Artificial Intelligence (AI) have introduced machine learning and its applications into everyday life. As technology becomes increasingly integrated into the educational system, researchers are focused on developing tools that allow students to interact with machine learning in a way that sparks their curiosity and teaches them essential concepts. Our instructional proposal, titled “Electric Signals in Machine Learning Using App Inventor,” focuses on applying learning, transfer, and classification models of audio spectrograms to teach students in the first year of high Secondary school (A’ Lyceum) fundamental concepts of machine learning. This is accomplished using MIT App Inventor and Arduino’s visual programming environments. Students will use the website “Personal Audio Classifier” to train an audio model and App Inventor to connect computer science and machine learning. In addition, with the aid of the Arduino microcontroller, students will engage in visualising Morse code signals and investigating Physical Computing, allowing them to create digital solutions that connect to the real world.

In-school and/or out-of-school computer science learning influence on CS career interests, mediated by having role-models

ABSTRACT Background and Context Both in- and out-of-school computer science (CS) learning opportunities are expanding, but their influences on CS career interests are unclear. Method To investigate, we applied multinomial propensity score weighting analysis on a 2021 U.S. nationally representative sample of 4,116 5th-to-12th-grade students. Findings The odds of expressing CS career interest increase by 171%, 94%, and 40%, respectively, when students pursue CS learning both in and out-of-school, out-of-school only, and in-school only. These effects were similar across race/ethnicity but stronger for girls. Out-of-school learning was the strongest predictor of having CS role-models, though each experience was positive. One third of the effect of both and about half of the effect of each separately were mediated by having CS role models. Implications Our findings suggest that domain-focused learning experiences are generally effective in shaping career interests, and out-of-school learning, specifically, may enhance exposure to role models.

Exploring the Psychological Advantages of Early Computer Education in Early phases of Development

The present work aims to explore the significance that teachers attribute to psychological approaches in the process of teaching and learning computer science in early formative years in a Public Educational Institution located in Bawana, Delhi. The research methodology employed is descriptive, using a field design. The study sample consisted of fifteen early formative years teachers. Data collection was conducted through interviews and a Likert scale questionnaire. Quantitative analysis of the data was performed using descriptive statistics. Results reveal that 40% of teachers always consider the basics of computers, while 60% consistently base their planning on the programming relevance in the teaching-learning process. Furthermore, 80% of teachers always prioritize lab activities to promote logical or operational thinking in students, while 20% always utilize recreational activities as a strategy for teaching and learning computer science in their classrooms. However, no respondents indicated consistent use of psychological approaches to enhance the teaching and learning of computer science in a world marked by constant transformation. To summarize, this study highlights the importance of shaping a positive outlook on computer science from an early age to develop students' abstract thinking, logic, and critical reasoning abilities. It emphasizes the need for incorporating psychological approaches to effectively teach and learn computer science among early formative years. By fostering a supportive environment, students can better navigate the challenges of Computer science and embrace its potential as they progress through their educational journey.

Opinion evolution and dynamic trust-driven consensus model in large-scale group decision-making under incomplete information

The shift to a new era of dealing with big data has driven continuous progress and development in computer science, artificial intelligence and machine learning. This change has led to the application of advanced techniques in the realm of decision science, particularly in the area of large-scale group decision-making (LSGDM). However, although these existing techniques have become the core of LSGDM methods, they are still limited in solving problems facing incomplete data. In addition, due to the rise of social media platforms such as Weibo, WeChat and Twitter, which build bridges for communication between decision makers (DMs), this brings new opportunities and challenges for consensus research. To address this set of issues, this study develops a consensus architecture that combines dynamic social network and opinion evolution in the context of an incomplete multi-attribute LSGDM. It is worth mentioning that the proposed consensus framework is a novel decision-making system that can be used to complete the estimation of the missing values and the consensus reaching process (CRP) by simulating the realistic decision-making scenarios. Firstly, considering the size of the trust value and the length of the path, a new trust propagation method is designed to achieve a more reliable estimation of the unknown trust value. Secondly, this paper establishes a missing value estimation method by virtue of the improved DeGroot model, which is able to obtain complete evaluation information by simulating the opinion formation process of DMs. Next, a hierarchical clustering algorithm with stronger robustness is constructed, which not only can adaptively complete the clustering process, but also integrally considers two attributes of trust and opinion similarity. In light of the above research, this study designs an opinion evolution and dynamic trust-driven consensus model, referred to as the DSN-DG-LSGDM model. Finally, the sensitivity analysis and experiments on a real dataset verify the significant superiority of the constructed DSN-DG-LSGDM model compared with the extant LSGDM consensus models.

Development of UI / UX Design in Web-Based Artificial Intelligence Learning on Student Learning Motivation with a User-centered Design Approach

Artificial Intelligence (AI) is a study of intelligent machines. Starting from elementary school, children should have the opportunity to learn computer science, both from computational thinking and programming. Based on that case, an e-learning platform that discusses AI with block-based programming was created, namely eCraft2Learn. Based on the results of field studies, the measurement of user experience and user interface shows the "bad" category on each scale. Whereas in e-learning, UI/UX is the point of interaction as the key in achieving educational goals. It is necessary to develop UI/UX both in terms of structure and content presentation, collaboration, and interaction so that it can influence student learning and motivation. Thus, the UI/UX development is carried out by applying the four stages of the user-centered design method. After all stages of the method are carried out, it produces a UI/UX design whose value can be measured based on the measurement of user experience and the development of student learning motivation is also measured through four indicators, namely intrinsic motivation, identified regulation, external regulation, and amotivation. From these results, it can be concluded that the UI/UX design that has been developed produces an increased value and has a positive effect on the intrinsic motivation scale and identified regulation. However, the results of this UI/UX design have no influence on the scale of external regulation and motivation

Tomato Plant Leaf Disease Detection Using Convolutional Neural Network

Our country is growing country, India is mostly depended on the agriculture field, and Agriculture is pillar of our country’s economy. Because of this India has to improve in agriculture filed, in many of situations’ farmer face difficulties to detect crop disease in a case large area farm, or late in detection of crop disease in such cases farmer lose their all crop and face the huge loss, to avoid this, in agricultural field is detection of plant diseases is very important. And it is very difficult tasks. In regular normal procedure it requires a more time period and trained person to detect accurate plant disease. In this paper, we proposed effective way for plant disease detection using computer science and machine learning model. Disease transmission from unhealthy plant to all other healthy plants in farm is one of the major damages to crop farm. And these diseases spread like forest fire and have the possible to impact the whole operation if not identified in early on. Now Plant disease detection methods helps to identify infected plants in a very early stage and also help us to identify plant disease in a wide range of area of crops in a cost-effective manner. The aim of this project model is to implement machine learning models, in our proposed system we take a plant leaf image on that leaf images we predict the plant disease using Convolution Neural Networks (CNN) model, in that we build a such a model to predict the plant disease with maximum accuracy and it is for plant disease detection for tomato plant. This machine learning model is analyzing different image metrics pixels data to determine the best performance of network. For that dataset were used around 7around 8016 images we going to use to train the model. We going to use 14 layers CNN models to get better accuracy results. Model consist various layers like convolution, pooling, flatten and dense. Early two layers that is preprocessing and augmentation of images Finally, we get the result of which disease that plant have.

Can Synchronous Code Editing and Awareness Tools Support Remote Tutoring? Effects on Learning and Teaching

One-on-one tutoring is effective for learning computer science since a tutor can work alongside a student and provide tailored feedback on their code. However, translating this type of instruction to a remote setting is challenging. Traditional methods such as screensharing lack key pedagogical functionality and most available tools are designed for collaboration rather than instruction. To identify tools that can support remote tutoring, we conducted an experiment to assess two resources: synchronous editing and awareness tools. In our study, an instructor teaches a learner introductory programming concepts remotely, collaborating through screensharing alone, a shared notebook with real-time collaborative editing, or a shared notebook with additional awareness tools overlaid. To embed the awareness tools, we designed a Chrome extension that enables real-time sharing of gaze and cursor data. Our results show that synchronous editing combined with awareness tools significantly improved learning. The awareness tools also helped tutors better communicate with the student, track their understanding, and establish a sense of presence. As a final contribution, we also assessed the efficacy of gaze-sharing using a webcam eye-tracker. While the accuracy was not as precise as a dedicated sensor, instructors described instances when the gaze was useful for gauging student attention and establishing presence. We discuss implications for remote tutoring in computer science and scaling awareness technology.

Resolving Misconception Challenges in the Teaching and Learning of Computer Science Amongst First-Year Undergraduate Students

Misconceptions in the field of computer science can lead to confusion and loss of confidence for students. These misconceptions are based on students' concepts that are not scientifically accurate interpretations. One of the major reasons why students find certain computing and scientific concepts so tough to acquire is because they suffer an inequality or gap between their early classification of a concept and the new learning framework. Resolving misconception challenges in the teaching and learning of sciences is not new because according to the past studies, it is believed to manifest throughout the life of individuals where students are greatly involved when it comes to teaching and learning sciences. The study aims to resolve and correct students’ misconceptions using a practical approach and its impact on students’ gender differences. To address these misconceptions, an experimental design study was conducted in order to examine the effects of practical approach correcting misconceptions among students in computing. The study compared students' scores on Pre-Test and Post-Test, comparing their perceptions of computing and the effectiveness of practical methods to address them. The population of the study consisted of all undergraduate students in higher education institutions in Lagos State. Through the use of random sampling method, 75 undergraduate students from Lagos State University of Education were selected. The instrument was subjected to reliability index after it was validated by experts in computing. An index of .887 results showed significant highly reliable instrument. The results of findings established significant differences between the pre-and post-test scores, but only a slight difference between male and female scores observed. The study recommends that students should be given the opportunity to investigate and test their own findings of computer science components and software functions in order to build a deeper understanding without preconceptions from their prior experiences.

Motivationally Appealing Computer Science e-Learning Games: An Inclusive Design Approach

Research has shown that e-learning games do not have the same level of appeal to girls, as they do to boys; particularly in the crucial 11-14 age group. In the United Kingdom, this is typically when they start to make subject choices that impact their future studies and careers. Given the shortage of females who choose computer science as a career, this study explores how e-learning games can be designed to be motivationally appealing to young learners. It further explores the role of game representations and its appeal to this age group. This empirical study addresses the research question: “Can we develop e-learning games which appeal and motivate girls of age 11-14 to study computer science concepts?” Two e-learning games were developed: one included game representations such as game colour, graphics, character, age appropriateness, storyline, number of players, violence, identified as appealing to young females and the other game included antithetical or neutral representations. The two developed prototypes were used to explore key e-learning game representations as used to teach computer science concepts. A total of 304 participants, comprising of 152 girls and 152 boys from a combination of same sex and mixed secondary schools in Southeast England, engaged with both experimental games. The experiment also elicited information on how learners interact with these games and the resulting game appeal, motivation and learning. The insight gained from the analysis of data captured during the experiments, provide the evidence to demonstrate that inclusive e-learning games which motivate and appeal to girls of age 11-14 can be developed. This can have a positive influence on their willingness to use such games to learn computer science concepts. This implies that the study found positive outcomes related to e-learning game appeal, motivation and the learning of girls of this age group. A follow-up longitudinal study could investigate the impact of significant e-learning game representations that appeal to the target group. This could provide additional evidence on the changes in the appeal of the investigated significant game representations over time, due to the influence of other factors such as socio-economic and socio-cultural differences. This understanding can further enhance inclusive e-learning strategies to improve diversity in computer science education and consequently the career pipeline.

Problem Decomposition Skills, Mathematical Maturity, and Their Relation to Mathematics Problem-Solving in A Computer Science Learning Class

Problem Decomposition Skills, Mathematical Maturity, and Their Relation to Mathematics Problem-Solving in A Computer Science Learning Class

CISing Up Service Learning: A Systematic Review of Service Learning Experiences in Computer and Information Science

The benefits of service learning in computer and information science (CIS) are believed to be significant, ranging from providing students with real-world experiences to retaining students to positively impacting community partners. Although there are many benefits of service learning, the CIS domain does impose unique costs for integrating service learning into the curriculum. Yet there is little systematic research to help the CIS community understand best practices for maximizing benefits while minimizing costs. Experience reports about service learning courses in CIS have appeared in the literature annually since 2000, and thus we address this gap in knowledge by conducting a systematic review and content analysis of 84 experience reports from the The ACM Guide to Computing Literature . We synthesize the current state of service learning in CIS as well as derive recommendations for best practices and future research directions.

Achieving Effective Learning Outcomes through the Use of Analogies in Teaching Computer Science

Analogy-based learning methods map the concept being learned to a concept well understood by the learner. An analogy is primarily useful when learners do not know the topic being studied. Computer science is an area where the concepts exhibit a high level of abstraction and, hence, are hard for students to comprehend. The use of analogies in instruction can significantly reduce the cognitive load a student faces in learning abstract computer science concepts. The role of analogies in helping students learn computer science topics has not been explored adequately. This paper presents our efforts related to using analogy-based teaching in computer science. Over the last several years, we have developed extensive analogies for many advanced computer science concepts. We have used these analogies extensively in classroom teaching at our institution. We list the analogies that we have developed and used in our classroom teaching and, as illustration, discuss two analogies: one from the field of operating systems and another one in modular software design. We have also conducted experiments to evaluate the impact of using these two analogies on student learning outcomes. Our results confirm our hypothesis that analogy-based instruction techniques are effective and result in improved student learning outcomes.

Connecting beliefs, mindsets, anxiety and self-efficacy in computer science learning: an instrument for capturing secondary school students’ self-beliefs

ABSTRACT Background and Context Few instruments exist to measure students’ CS engagement and learning especially in areas where coding happens with creative, project-based learning and in regard to students’ self-beliefs about computing. Objective We introduce the CS Interests and Beliefs Inventory (CSIBI), an instrument designed for novice secondary students learning by designing projects (particularly with physical computing). The inventory contains subscales on beliefs on problem solving competency, fascination in design, value of CS, creative expression, and beliefs about context-specific CS abilities alongside programming mindsets and outcomes. We explain the creation of the instrument and attend to the role of mindsets as mediators of self-beliefs and how CSIBI may be adapted to other K-12 project-based learning settings. Method We administered the instrument to 303 novice CS secondary students who largely came from historically marginalized backgrounds (gender, ethnicity, and socioeconomic status). We assessed the nine-factor structure for the 32-item instrument using confirmatory factor analysis and tested the hypothesized model of mindsets as mediators with structural equation modeling. Findings We confirmed the nine-factor structure of CSIBI and found significant positive correlations across factors. The structural model results showed that problem solving competency beliefs and CS creative expression promoted programming growth mindset, which subsequently fostered students’ programming self-concept. Implications We validated an instrument to measure secondary students’ self-beliefs in CS that fills several gaps in K-12 CS measurement tools by focusing on contexts of learning by designing. CSIBI can be easily adapted to other learning by designing computing education contexts.