Learning about Artificial Intelligence (AI) is becoming increasingly important for everyone as technology becomes an increasingly integral part of our everyday lives. When people understand how AI works, they’re better equipped to think critically, solve problems, and feel more comfortable using the tools that are shaping our world. This review paper discusses and compares various existing block-based tools, approaches, and extensions for AI education, making it accessible to all students, regardless of their background or prior experience. Whether students are training a robot, building an AI model, or experimenting with how an agent makes decisions, these platforms give them the tools and freedom to learn by doing.

This paper introduces TalentVision AI, a comprehensive framework that addresses the limitations of traditional football scouting by integrating advanced data preprocessing, unsupervised clustering algorithms, and interactive visual analytics. Leveraging detailed performance metrics and refined positional data, we employ domain-aware clustering—primarily DBSCAN—to identify coherent tactical archetypes across player roles. Our interactive dashboard further enhances interpretability by transforming complex data into intuitive visual narratives, supporting scouts in evidence-based decision-making. Validated through real-world scenarios, TalentVision AI represents a reproducible, scientifically rigorous platform for modern player evaluation and team-specific talent discovery.

Interpreting chest X-rays remains a complex as well as expertise-dependent task, particularly in settings where radiological resources are limited. A new explainable AI (XAI) framework is introduced in this paper. The framework aims to improve diagnostic transparency through a combination of deep learning and natural language explanations. The proposed system integrates segmentation models for localizing anatomical regions. It also integrates classification networks for classification that detect any abnormalities using Grad-CAM for visual model focus interpretation. These visual outputs get contextualized and synthesized via a large language model (LLM) to generate clear, clinically meaningful diagnostic reports. This results in a multimodal pipeline that not only detects and localizes pulmonary infections such as pneumonia and tuberculosis but also translates the findings into accessible natural language. Experimental results show that this framework improves diagnostic clarity and interpretability, which in turn fosters trust among all clinicians while it increases accessibility even for non-experts. Through precisely visualizing and transparently narrating, this work contributes toward new AI tools that responsibly and human-centeredly support medical decisions.

Large Language Models (LLMs) have revolutionized the fields of Artificial Intelligence and Data Science, holding great potential in a variety of domains such as E-Learning, Business, and Data Analytics. However, the challenge of relying on the output generated by LLMs still persists, specifically in sensitive domains such as healthcare and finance. This paper presents an enhanced framework for generating explainable visualizations using LLMs as well as introducing an approach to make the LLM outputs more interpretable to users, enhancing their trust in the validity of the output. The work presented in this paper builds upon the capabilities of the existing tool: LIDA [7]. The paper proposes modifications to its core components as well as the addition of new components. The goal is to enhance the explainability and reliability of the produced outputs. The proposed system refines how goals are identified and explored as well as how visualizations are assessed. The aim is to address limitations in explainability. Key contributions of this work include the integration of a new scoring mechanism that ensures transparency for the LLM-generated evaluations across multiple dimensions, enforcing user trust in the outputs generated. This study contributes by merging the growing field of explainable Artificial Intelligence with the domain of data exploration and analytics by offering a modular and extensible approach to visualization generation, emphasizing user-centric design and interpretability. The findings have implications for researchers, data analysts, and developers looking to bridge the gap between complex data and actionable insights.

This paper introduces AUTOVI, a data exploration platform that changes how individuals interact with and understand datasets. Autovi's contribution comes from its simplicity and focus on making the experience of the user both simple and informative. Autovi achieves its goals by preprocessing real-world data comprehensively, ensuring thorough analysis of different datasets. The modular design of Autovi empowers users, making data exploration supportive and engaging. What sets Autovi apart is its transparent Multi-Layer Perceptron (MLP) classifier and dynamic user feedback mechanisms, which prioritize clarity in training processes for better user understanding. Autovi demonstrates efficiency in data exploration tasks compared to traditional coding approaches. Autovi also automates insights, making data exploration accessible to users of all proficiency levels.

Recently, programming methodologies are being increasingly introduced into children's education. For example, Scratch11https://scratch.mit.edu/ and The Hour of Code22https://hourofcode.com platforms have been adopted in many schools worldwide. However, the daunting problem remains: prolonged use of mobile phones increases the risk of smartphone addiction. This rising incorporation of program-ming alongside the aforementioned negative aspect of traditional serious games have demanded a healthier and more effective platform for programming education to enhance the learning experience of children. As a result, this paper introduces a serious game that incorporates Augmented Reality environments and optical character recognition technology (OCR) to limit screen time and visualize the written code in an efficient and more immersive manner. An experiment was conducted measuring the proposed system's effect on student's learning gain, player's experience, and usability relative to desktop environments. The results show a correlation between the use of the Kode- Arsystem and an increase in learning gain and a positive player experience. The results of system usability were inconclusive.

Integration between Quality Control and Industry 4.0 was explored seeking to obtain the best quality of the final product. This project aims to create an algorithm that creates a large data set that will train the Machine Learning model to achieve Automated Quality Control in Industry 4.0. The Methodology applied started with Data Acquisition by capturing a video of the fruits on the conveyor, afterwards applying Video Processing by cutting this video into frames to obtain raw data, then applying Image Processing on the raw data to clean it using Color Detection and Contour and Size Detection approaches, these methods resulted in the creation of two datasets of fresh and rotten oranges, with a total of 1700+ images of oranges. This paper presents the collection of a large dataset in addition to cleaning this data and make it ready for training and testing, Also to create an algorithm that creates large datasets of crops automatically

Throughout the past centuries technologies have evolved, and we are always looking for ways to make every persons' life easier. Analysing datasets consumes so much time, so interacting with real-life data visualisations is an innovative way to analyse any dataset. Augmented Reality is a new technology that have unlimited ideas, also collaborating over an augmented reality experience is adding a new way of implementing augmented reality to increase humans interaction with the data. This paper is about integrating a collaboration augmented reality experience over dataset visualisation. This paper scope includes the design, implementation and evaluation of the augmented reality experience. This AR experience includes 3 main modules which are Image tracking, data-set visualisation and collaboration. After implementing the AR experience surveys where taken from participants to measure experience usability and participants' task load.

Good collaboration is about clearance between all the team members to let everyone work transparently towards one goal. Augmented Reality was one of the technologies used for data visualization for an immersive and better understanding and analysis of the data. Hence, the collaboration between users on the visualized data in extended reality can combine the analytic power of multiple individuals, and potentially leading to increased quality of solutions and discoveries. The work presented in this paper discusses a remote collaboration technique for enhancing collaboration on visualized data in Augmented Reality. This was done through allowing the user to be immersed to a certain extent, but not completely replacing their reality. The Microsoft Hololens was used to create an Augmented Reality application that transfers the movements of the remote users in real-time using Microsoft Kinect v2 in the form of a hologram of an avatar. This allowed multiple participants to see each other (embodied as avatars), collaborate and interact with 3-Dimension visualized data as shareable holograms between the remote users. An experiment was conducted on 14 participants. The results indicated that the application was useful and fulfills the requirement. We found that the application successfully provided a rich, interesting, and immersive collaborative experience for the students regarding remote collaboration on data visualization in extended reality.

With the increasing popularity of e-commerce and the coronavirus situation, an increasing number of shoppers are opting for online shopping because of store closures and their fear of contracting the coronavirus in public. While conventional retail provides consumers with a full spectrum of interaction, online shopping has been deficient in these types of experiences. Therefore, the virtual reality technology is used to bridge the gap between the two shopping techniques and create a more natural and intuitive shopping environment. The aim of this research is to investigate how, in a virtual store environment, consumers’ interaction affect their shopping experience. A virtual supermarket with the interaction facility was designed. An experiment was conducted to track the effect of the social interaction on the consumers using different metrics. The results showed that consumers’ social interaction in the form of avatar- mediated communication has a beneficial impact on their social presence. It also demonstrates that consumers felt more immersed and socially engaged to the shopping environment via the social interaction among avatars.

Prolog is a declarative programming language that is used in different fields including artificial intelligence. This paper introduces a complete visual web-based interface for visual programming using blocks to simulate Prolog programs. The tool also animates the algorithms of the executed program.

Problem solving, analyzing the validity of a solution and spotting patterns in data are all substantial skills needed in the workplace nowadays not only in the programming field. Solving and generating multiple solutions to a problem is quite challenging for children with autism spectrum disorders. As a solution, the work in this paper presents the design, implementation and the evaluation of a serious game that focuses on the sequential programming concepts. The presented game aims to teach problem solving skills to children with autism. A user-study was conducted to evaluate the game with children who have autism. According to the evaluation carried out in this research, the game was proven to be engaging, which indicates that the serious game is promising for teaching sequential programming concepts to children with autism.

This Research to Practice Full Paper presents an application (AutoNotes) that improves the students' learning outcomes by using natural language processing techniques (NLP) such as speech recognition and keywords extraction. AutoNotes is an android application that converts the speech of the instructor to text in real time during the lecture and then it synchronizes this text to the original lecture slides to produce new slides annotated with the explanation of the instructor. These new lecture slides can be displayed in a classroom. Moreover, it can be accessed by the students on their mobile phones. AutoNotes also provides a feature for the students who like to write their notes with their own way. A focus group was conducted to gather target audience opinions. The results have shown that students liked the idea of AutoNotes. They saw it beneficial for them especially if the original lecture slides are not detailed. They also like the idea of putting the notes with its corresponding slide. To evaluate AutoNotes, a between group design setup of two identical lectures with different groups of participants was conducted. In the first lecture, the lecturer used the original lecture slides. However, in the second one the annotated lecture slides was used. The participants were given several tests to compare their overall learning experiences. The results of the tests reveal that the participants that were exposed to the annotated lecture slides had a higher engagement level and learning gain than the other group exposed to the original lecture slides. Additionally, they had a workload level less than the other group. For the system usability test, the average usability scale that AutoNotes got is 78 which can be considered above average. Finally, the results of the accuracy testing reveal that the accuracy of the speech recognition was 83.2%. The precision and recall metrics were used to evaluate the synchronization of the speech with the slides. The average precision score was 75.6%. However, the average recall score was 51.1%.

Autism Spectrum Disorder (ASD) refers to a group of life-long conditions that are characterized by qualitative impairments in social interactions, problem solving and constructive skills. Children with learning disabilities such as autism face challenges in generating suitable and optimal solutions to problems. Those challenges can severely affect their interactions with others. Thus, teaching children with ASD problem solving and computational thinking skills could help them resolve conflicts that may happen in their everyday life. Effective problem solving is critical for their academic and social success and since one of the most effective tools for teaching children with autism is through using visual aids, the work in this paper reports the design and implementation of a serious game that aims at cultivating problem solving skills and teaching programming concepts to children with ASD. The presented game is suitable for children 7 to 14 years of age diagnosed with ASD to learn programming concepts. The preliminary prototype for the game gained positive responses from experts and 12 children with ASD from Caritas Egypt association and Hope Academy.

The work in this paper introduces a platform that is able to visualize eye gaze data. The platform introduces two different directions or algorithms. The first is for videos with heat-map to convert the heat map data into raw numbers. The algorithm takes the video containing the heat map and cuts it into frames. In each frame, it locates the position of the heat-map by searching for the specific colour values and then displaying the position of heat-map in each frame. The algorithm also calculates the fixation points and how long each fixation was for the entirety of the video. The second algorithm is to do the opposite of the first and that is by converting the raw data of eye-movement to a heat map. We are also providing visualization platform for eye-tracking data.

Virtual Reality has been one of the interesting topics that have risen in the previous years. It has diverged into many fields including medicine, tourism, and education. On the other hand, new techniques have been used for teaching programming rather than the traditional paper and pen technique. The work presented in this paper proposes a new way of teaching children programming using the Virtual Reality (VR) technology. A game has been implemented with Scratch-like background to test whether the immersive factor of VR would have a positive effect on the learning outcome of the children. A study has been conducted on 10 participants to compare between two techniques for teaching the basic programming concepts: VR game and Desktop game. Results showed that the mean of the learning gain of the VR group was higher than the Desktop mean but with no significant p-value. However, the engagement test results showed that the participants were more engaged to the VR game than the Desktop game with p-value of 0.032.

Programming has become a crucial skill in today’s world. Technology and computers are basically part of anything now. President Obama once referred to the importance of children learning programming: “I do not want our young people to just be consumers, I want them to be producers of this technology and to understand it, to feel like they are controlling it, as opposed to it controlling them.” It is thus an increasing need for an individual to know how to write their own programs. With the increasing dependency on computation, one can anticipate such skills being a requirement for most jobs in the coming years. There is a lot of effort done in this area, however most of them focused on either software or hardware track. The aim of this work is to test if using a hybrid approach for teaching K-12 students programming by combining both software and hardware techniques is more effective than using a singleton approach.

Infographics is a tool for data visualization. It makes data easy to understand and interpret. An infographic is defined as a visual representation for data like a chart or a diagram. Infographics can help in many fields including education. This is due to the fact that information can be easily memorized and understood if was given in a visual form. Infographics are found everywhere and used in many different fields. Facebook timeline is considered as an infographic. On another hand, online journalism is increasingly gaining popularity. It is also considered as a source of big data that is rapidly expanding. Online newspapers and magazines provide a large population with daily important information. The aim of the work is to use data visualization, infographics and Natural Language Processing (NLP) techniques in online journalism. The aim of the work is to automatically visualize the information in an article in the form of infographics.

Computations usually handle excessive amounts of data with different types. The simpler the data is displayed, the faster actions might be performed. With big data, it is important to be able to find out what is really happening through the details of the data. This could be done with visualization through flexible displaying of data with efficient forms using advanced visualization technologies.

This paper discusses a rule-based approach for visualizing proofs using tableaux techniques. Semantic Tableau is usually used to prove by refutation. In addition, tableaux techniques are commonly studied in different courses. Visualization is an effective teaching methodology. The availability of visualization methods that could be used by instructors is thus important.

The aim of the tool provided in the paper is to provide a virtual reality enabled platform for teaching programming. The focus is on the concepts of objects and classes. The platform allows users to customize and see almost everything to see their effects.

The paper introduces an approach that allows for detecting interaction with a graphical display in a rule-based declarative approach. It also introduces the possibility of connecting the interaction to a specific animation step to be performed. The two approaches were embedded into an animation system to aid in teaching algorithms.

Trees and graphs are two data structures that are commonly used in representing different kinds of data. They also have many associated algorithms taught in different courses. It is thus beneficial to have a tool that could be used by students, teachers and programmers to visually trace how their algorithms work. The work in this paper presents, CHR-Graph, an easy-to-use platform for animating trees and graphs and their correlated algorithms using Constraint Handling Rules (CHR).

Over the past years, visualization of programs has been widely applied. Algorithm animation was proven to aid in teaching and learning. It provides a convenient medium for beginners to a programming language by giving them the ability to visually discover how their programs are running. It also provides experts of a language with a means to have a visual trace utility. Lately, a new approach for adding visualization features into Constraint Handling Rules (CHR) programs was proposed. The new methodology was a dynamic one able to animate different types of algorithms. The work in this paper aims at introducing a revised extension that is able to embed visualization features into Java programs. With the new extension, Java algorithms could be animated without the need of doing any modifications to the code. In addition, the provided technique is still a general one able to animate different kinds of algorithms.

Recently, a new approach for embedding visualization features into Constraint Handling Rules (CHR) programs has been proposed. It allows CHR programmers to animate and visualize different algorithms implemented in CHR. Such features have become essential with CHR being a general purpose language. In this paper, a new diagrammatic representation for CHR programs is presented. The representation is also able to account for the newly embedded visual features.