Recognition Skills Research Articles

Exploring the integration of artificial intelligence in math education: Preservice Teachers’ experiences and reflections on problem‐posing activities with ChatGPT

AbstractThis study addresses the need for research that incorporates educational perspectives and theories to understand the impact of Artificial Intelligence (AI) on learning and teaching. Utilizing AI‐integrated mathematical problem‐posing (AIM) activities and the AI‐powered scaffolding (AIS) strategy, the research investigated preservice teachers’ (PTs’) experiences with AI and their capacity for error recognition and correction in problems posed by ChatGPT. The findings reveal that while the PTs excelled at verifying error‐free problems, they struggled significantly with identifying and correcting errors, indicating a gap in their instructional preparedness. The study demonstrates that AIM activities are effective tools for assessing and developing PTs’ error recognition and correction skills. Additionally, AIM activities support the transfer of mathematical knowledge to pedagogical and instructional practices, contributing to PTs’ growth as adaptable educators. The research highlights the need to integrate AI‐based activities into PT training to build robust mathematical knowledge and teaching skills. Focusing on learning, pedagogy, and the human aspects of technology use, AIM activities and the AIS strategy enable PTs to engage critically with AI outputs and enhance their metacognitive skills. These insights emphasize the importance of incorporating AI‐integrated methods into teacher preparation programs to better equip future educators for an AI‐driven educational landscape.

The role of patterning skills in early mathematical development: an analysis of all dimensions of visual perception

ABSTRACT In the early stages of mathematical development, the primary objective is to develop pattern recognition skills by mastering fundamental techniques like sorting and comparison. Numerous pattern structures, such as visual, auditory and spatial patterns, can be created. In this study, we examined the effects of PO-MEP, a pattern-focused mathematics education program for preschool children, on children’s visual perception. The “Pattern-Oriented Mathematics Education Program (PO-MEP)” was developed, and compatible original materials were designed. The program is structured around repeating and growing patterns. Its impact was assessed using a quasi-experimental design, including a pretest, posttest and follow-up test, and a control group. The results show that it had a statistically significant impact on the development of all sub-dimensions of visual perception: hand-eye coordination, figure-ground perception, form constancy, position in space, and spatial relationships. In sum, the program developed the children’s visual perception. Further research may be conducted using different methodologies and age groups to strengthen these findings.

SAILOR: perceptual anchoring for robotic cognitive architectures

Symbolic anchoring is an important topic in robotics, as it enables robots to obtain symbolic knowledge from the perceptual information acquired through their sensors and maintain the link between that knowledge and the sensory data. In cognitive-based robots, this process of transforming sub-symbolic data generated by sensors to obtain and maintain symbolic knowledge is still an open problem. To address this issue, this paper presents SAILOR, a framework for symbolic anchoring integrated into ROS 2. SAILOR aims to maintain the link between symbolic data and perceptual data in real robots over time. It provides a semantic world modeling approach using two deep learning-based sub-symbolic robotic skills: object recognition and matching function. The object recognition skill allows the robot to recognize and identify objects in its environment, while the matching function enables the robot to decide if new perceptual data corresponds to existing symbolic data. This paper describes the proposed method and the development of the framework, as well as its integration in MERLIN2 (a hybrid cognitive architecture fully functional in robots running ROS 2) and the validation of SAILOR using public datasets and a real-world scenario.

Slit Lamp Report Generation and Question Answering: Development and Validation of a Multimodal Transformer Model with Large Language Model Integration.

Large language models have shown remarkable efficacy in various medical research and clinical applications. However, their skills in medical image recognition and subsequent report generation or question answering (QA) remain limited. We aim to finetune a multimodal, transformer-based model for generating medical reports from slit lamp images and develop a QA system using Llama2. We term this entire process slit lamp-GPT. Our research used a dataset of 25,051 slit lamp images from 3409 participants, paired with their corresponding physician-created medical reports. We used these data, split into training, validation, and test sets, to finetune the Bootstrapping Language-Image Pre-training framework toward report generation. The generated text reports and human-posed questions were then input into Llama2 for subsequent QA. We evaluated performance using qualitative metrics (including BLEU [bilingual evaluation understudy], CIDEr [consensus-based image description evaluation], ROUGE-L [Recall-Oriented Understudy for Gisting Evaluation-Longest Common Subsequence], SPICE [Semantic Propositional Image Caption Evaluation], accuracy, sensitivity, specificity, precision, and F1-score) and the subjective assessments of two experienced ophthalmologists on a 1-3 scale (1 referring to high quality). We identified 50 conditions related to diseases or postoperative complications through keyword matching in initial reports. The refined slit lamp-GPT model demonstrated BLEU scores (1-4) of 0.67, 0.66, 0.65, and 0.65, respectively, with a CIDEr score of 3.24, a ROUGE (Recall-Oriented Understudy for Gisting Evaluation) score of 0.61, and a Semantic Propositional Image Caption Evaluation score of 0.37. The most frequently identified conditions were cataracts (22.95%), age-related cataracts (22.03%), and conjunctival concretion (13.13%). Disease classification metrics demonstrated an overall accuracy of 0.82 and an F1-score of 0.64, with high accuracies (≥0.9) observed for intraocular lens, conjunctivitis, and chronic conjunctivitis, and high F1-scores (≥0.9) observed for cataract and age-related cataract. For both report generation and QA components, the two evaluating ophthalmologists reached substantial agreement, with κ scores between 0.71 and 0.84. In assessing 100 generated reports, they awarded scores of 1.36 for both completeness and correctness; 64% (64/100) were considered "entirely good," and 93% (93/100) were "acceptable." In the evaluation of 300 generated answers to questions, the scores were 1.33 for completeness, 1.14 for correctness, and 1.15 for possible harm, with 66.3% (199/300) rated as "entirely good" and 91.3% (274/300) as "acceptable." This study introduces the slit lamp-GPT model for report generation and subsequent QA, highlighting the potential of large language models to assist ophthalmologists and patients.

Using Artificial Intelligence to Strengthen the Interaction between Humans and Computers and Biosensor Cooperation

This article examines the application of artificial intelligence (AI) technologies to improve human-computer interaction (HCI) and foster cooperation in graphic design. Comprehensive study and practical use reveal that AI integration significantly enhances HCI's effectiveness and precision while introducing unique collaborative models in graphic design. The research employs natural language processing (NLP) and deep learning technologies in HCI to provide natural dialogue and intelligent responses between humans and machines by developing intelligent question-answering systems and automated task-processing capabilities. Data research indicates that with the implementation of AI, user-computer interface efficiency has increased by 21%, and the mistake rate has decreased by 12%. This accomplishment substantially enhances user experience and facilitates computers in comprehending and addressing user requirements more effectively. The biocompatibility and comfort of users of these substances are of concern. Investigating novel flexible biosensors is imperative to enhance these devices' adaptability, comfort, and interaction. In visual design, the research employs AI's picture recognition and analysis skills to facilitate intelligent recommendations and automatic modifications of design aspects. AI can autonomously produce visual components that align with the designer's goal and approach by analyzing several design scenarios using machine learning algorithms. Data analysis indicates that the design effectiveness of AI-assisted design projects has increased by 30%, and the caliber of the outputs has substantially enhanced.

THE PIGGY SYLLABLE BANK STRATEGY IN IMPROVING THE SYLLABLE RECOGNITION OF KINDERGARTEN LEARNERS

This study aimed to evaluate the effectiveness of the Piggy Syllable Bank Strategy in improving the syllable recognition skills of kindergarten learners at Englandad Primary School, Paoay, Atok, Benguet. Employing a pre-experimental one-group pretest-post-test design, the study involved a total enumeration of eight (8) kindergarten pupils as its participants. The research addressed the following questions: (1) What is the level of syllable recognition skills of kindergarten learners before the use of the Piggy Syllable Bank Strategy? (2) What is the level of recognition skills after the use of the Piggy Syllable Bank Strategy? (3) Is there a significant difference in the syllable recognition skills of the kindergarten learners before and after the intervention? The results revealed that prior to the intervention, the learners’ mean score was 5.88, categorized as "Developing." Post-intervention, the mean score significantly increased to 11.88, corresponding to a "Proficient" level. Statistical analysis using a dependent t-test yielded a computed t-value of 7.895, which exceeded the critical t-value of 1.895 at a 0.05 significance level, indicating a significant improvement in learners' syllable recognition skills. The findings of the study conclude that the Piggy Syllable Bank Strategy is an effective intervention for enhancing syllable recognition skills among kindergarten learners. The study concludes that the kindergarten learners possessed minimum syllable recognition skills before the integration of the syllable bank strategy. The kindergarten learners have developed their syllable recognition skills after the integration of the piggy syllable bank strategy. The use of piggy syllable bank strategy is effective in improving the syllable recognition skills of the kindergarten learners.

Integration of Social Media as A Learning Tool in Mamba’ul ‘Ulum Private Ibtidaiyah School

This study focuses on children's developmental progress at Raudhatul Athfal Al-Bashitiyah concerning learning activities in early childhood education RA Al-Basithiyah, specifically in group B, where the children's numerical recognition skills are notably deficient. When requested, numerical figures should be displayed in the corresponding forms of the digits. Furthermore, only 13 youngsters can write the digits 1-10, while only 17 children can sequentially recite the numbers 1-10. The children's incapacity at RA Al-Basithiyah to recognize and recite the numbers 1-10 is due to the suboptimal teaching method employed for number recognition. The introduction of numbers needs to be supported more by modest learning material, which fails to enhance children's number recognition skills. This study seeks to ascertain if using number cards as a medium can improve children's counting abilities at RA Al Bashitiyah. This study constitutes a Classroom Action Research (PTK). This research employs observation and documentation as data-collecting tools. The participants in this study are the offspring of RA Al Bashitiyah. The study's results utilized two cycles: in the first cycle, the MB category comprised 18 children (60%) and the BSH category included 12 children (40%); in the second cycle, the MB category contained two children (7%) while the BSB category encompassed 28 children (93%), indicating the completion of the second cycle. The number card game enhances children's counting abilities

Pengaruh Permainan Papan Cocok Terhadap Kemampuan Mengenal Warna pada Anak Usia 4-5 Tahun di TK Negeri Pembina Ki Hajar Dewantoro Kecamatan Dungingi

This study aimed to determine whether there is an Effect of Matching Board Games on the Color Recognition Skills in Children Aged 4-5 Years at TK Negeri Pembina Ki Hajar Dewantoro, Dungingi Subdistrict. This study used a quantitative experimental method. The research findings involving 15 children revealed that there was an increase in the results of the Pre-test and Post-Test. In this case, it was observable from the Pre-test data obtaining an average value of 16.06 and a standard deviation of 2.604 and the Post-Test data was with an average value of 21 and a standard deviation of 3.461. in reference to these findings, the respondents who were samples in this study obtained an increase in average results from the pre-test to the post-test.

Collaborative use of a 3D anatomy platform to motivate and enhance anatomy learning in first-year online medical sonography students.

Sonography students require a deep understanding of structural anatomy, including where structures sit relative to one another. Additionally, they need to learn the complex task of identifying structures on medical images including X-rays, computed tomography, magnetic resonance imaging and ultrasound imaging. Anatomy can be taught online, but learning can be challenging for students. Online three-dimensional (3D) anatomy platforms aid student learning, but research investigating how to use them effectively when teaching is scarce. This project evaluated the impact of incorporating a three-dimensional (3D) online anatomy platform into teaching relative structural anatomy and assist sonography students when learning how to recognise structures on medical images. Sixty-one first-year sonography students within an articulated undergraduate and postgraduate medical sonography programme in Australia, studying anatomy online participated in this mixed methods study. The impact of using a 3D online anatomy platform on their conceptual 3D anatomy understanding of relative anatomy, development of medical image recognition skills and their learning experience was assessed via a Qualtrics survey. Students who used this platform collaboratively enhanced their relative anatomy understanding and developed the skill of identifying structures from medical images. The scaffolded use of this platform generated enquiry discussions between teachers and students and made learning anatomy online a social and enjoyable experience. Collaborative and interactive scaffolded use of 3D online anatomy platforms can motivate and encourage student questions and discussions, enabling social connections and enhancing their learning experience. Student enquiry skills were developed, and the more complex task of identifying structures from medical images was made achievable.

Parallel development of object recognition in newborn chicks and deep neural networks.

How do newborns learn to see? We propose that visual systems are space-time fitters, meaning visual development can be understood as a blind fitting process (akin to evolution) in which visual systems gradually adapt to the spatiotemporal data distributions in the newborn's environment. To test whether space-time fitting is a viable theory for learning how to see, we performed parallel controlled-rearing experiments on newborn chicks and deep neural networks (DNNs), including CNNs and transformers. First, we raised newborn chicks in impoverished environments containing a single object, then simulated those environments in a video game engine. Second, we recorded first-person images from agents moving through the virtual animal chambers and used those images to train DNNs. Third, we compared the viewpoint-invariant object recognition performance of the chicks and DNNs. When DNNs received the same visual diet (training data) as chicks, the models developed common object recognition skills as chicks. DNNs that used time as a teaching signal-space-time fitters-also showed common patterns of successes and failures across the test viewpoints as chicks. Thus, DNNs can learn object recognition in the same impoverished environments as newborn animals. We argue that space-time fitters can serve as formal scientific models of newborn visual systems, providing image-computable models for studying how newborns learn to see from raw visual experiences.

Enhancing the Alphabet Recognition Skill by Using Educational Games (HAPCAB Model) of Primary 1 Students at Puyud Community School, Pattani Province, Thailand

The purpose of this research was to investigate the effectiveness of using educational games, specifically the HAPCAB model, in improving students' alphabet recognition skills in primary 1 students at Puyud Community School in Pattani Province, Thailand. The study included 27 students in the first semester of 2022. The students were selected through purposive sampling. The research instruments involved lesson plans, pre-tests and post-tests for alphabet recognition, and a satisfaction measurement scale. The results of the research showed that students' alphabet recognition skills improved after using the HAPCAB model, with a higher achievement score of 11.85 compared to before. Additionally, the students had a very favorable level of satisfaction with the HAPCAB model, with a mean score of 4.70.

Innovative Approaches in English Learning: AI Smart Chatbots As A Model

The current study aims to highlight the role of “artificial intelligence-based conversational bots for learning English” as an innovative tool that provides advanced educational solutions, providing an effective and free learning opportunity for all students at all educational levels. It is also discussed how to benefit from the capabilities of chatbots, including learning about some text and voice chat programmes designed in artificial intelligence applications for learners of English as a second language. These bots have reached a degree of professionalism, as they have transcended imagination and entered the fields of creative vision, self-learning, and greatly simulating the human mind. The current study followed the descriptive method in collecting, classifying, and analyzing information by studying literature and previous scientific research related to artificial intelligence technology and its applications. The results of this study were: AI English language learning applications and chatbots offer numerous benefits, including personalized learning, voice recognition, and writing and reading skills development. They provide instant feedback on grammar and writing style, offer flexibility in accessing resources, and enable students to apply English knowledge in real-life contexts.

Innovative Teaching of AI-Based Text Mining and ChatGPT Applications for Trend Recognition in Tourism and Hospitality

This research applies a model-based teaching approach aimed at scrutinizing trends in the leisure, tourism, hospitality, recreation, and sport (LTHRS) field by integrating artificial intelligence (AI) along with ChatGPT, project-based learning (PBL), systems thinking, and industrial analysis tools to foster trend recognition skills. The study employs a quasi-experimental design to compare the efficacy of two instructional approaches (exploratory vs. confirmatory) concerning AI literacy and learning outcomes. Notably, the exploratory group exhibits marked improvements in AI knowledge, while the confirmatory group demonstrates enhanced trend recognition ability. Additionally, the research delves into the application effects of AI-based text mining and ChatGPT (AITM) as content analysis tools through four distinct projects (5G’s impact on tourism industries, travel trends caused by metaverse, daylily tour in Huatan Township, and Taiwanese elements in spectator sports), underscoring the substantial efficacy of AITM in capturing diverse themes, albeit with challenges in discerning subtle and subjective labels. These findings highlight the effectiveness of the model-based teaching approach and the multifaceted utility of AI and automated text mining in augmenting trend recognition skills.

Permainan Tradisional Boy-Boyan: Upaya Peningkatan Kemampuan Mengenal Angka dalam Bahasa Madura

The study aims to determine the development of number recognition skills in Madurese language for children aged 5-6 years and to assess the percentage improvement in number recognition skills in Madurese among Group B children at Tanjung Jati Kindergarten through the traditional game "boy-boyan" during the 2022/2023 academic year. The research method used is Classroom Action Research (CAR) based on the Kemmis and McTaggart model. The classroom action research was conducted in four cycles, each consisting of four stages: planning, implementation, observation, and reflection. The subjects and data sources for this study were Group B children at Tanjung Jati Kindergarten, totaling 9 children, consisting of 3 boys and 6 girls. Data collection techniques in this study included observation and documentation. The data analysis techniques used were qualitative and quantitative analysis. The results of the classroom action research show an improvement in the children's ability to recognize numbers in Madurese at each stage. This can be seen from the pre-cycle results, where the children's speaking ability was generally in the "Starting to Develop" category at 38.95%. No children had reached the "Developing as Expected" or "Developing Very Well" categories. However, after the learning process through the traditional game of "boy-boyan," there was an increase in speaking skills. In cycle 1, the children's speaking ability reached the "Developing as Expected" category at 70.4%. In cycle 2, their speaking ability reached the "Developing Very Well" category at 88.9%. Based on the results of this classroom action research, the teacher was able to improve the children's ability to recognize numbers in Madurese in Group B at Tanjung Jati Kindergarten through the traditional game "boy-boyan."

From challenges to competencies: informal female entrepreneurship in emerging economies

PurposeInformal female entrepreneurs in emerging economies operate in challenging business environments. This research examines the competencies of informal female entrepreneurs (IFEs) to explore how they persist because and despite the unique set of challenges they face.Design/methodology/approachWe undertake a qualitative study focusing on IFE in the Indian context. Using the abilities–motivation–opportunity (AMO) framework as a theoretical lens, we interviewed 14 IFEs to gain insights into their entrepreneurial challenges and understand how they address the challenges.FindingsThe results demonstrate that IFEs are prone to various challenges around the individual level, business challenges on an operating and functional level and other challenges rooted in their business environment. Further, the study sheds light on the competencies of IFEs on three fronts, namely, ability-enhancing competencies, including – technical skills, problem solving, communication and adaptability; motivation-enhancing competencies, including – self-motivation, resilience and optimism and lastly, opportunity-enhancing competencies, including – local-centric approach, networking and resourcefulness.Research limitations/implicationsThe study highlights the nuanced settings of informal female entrepreneurship in an emerging economy context. By highlighting the challenges and competency interplay, our study opens novel avenues for the interrelationships to be studied in further detail.Originality/valueOur study provides close insight into the everyday challenges of IFEs operating in informal economies. Their competencies and perseverance-related attributes contribute to the mainstream entrepreneurship literature, as these entrepreneurs exhibit unique competencies that allow them to thrive in challenging contextual settings. Their willingness to learn new skills, opportunity recognition, motivation and adaptability skills contribute to a better understanding of the phenomenon of informal female entrepreneurship.

Exploring the Effects of Augmented Reality on the Emotion Recognition Skills of Autistic Children

Autistic children have significant difficulties in recognizing and labeling emotions, difficulties which may hinder the natural development of their ability to express and regulate further emotions. The purpose of this study was to evaluate the effect of an augmented reality emotion recognition program (ARERP) delivered in a group format on the emotion recognition of young autistic children. This study employed a concurrent multiple probe design across behaviors to evaluate the effects of the training on children’s emotion recognition. The target behavior was recognizing three emotion sets: positive, negative, and complex. The sequence of conditions included pre-test, baseline, training, post-test, and follow-up sessions. Positive results were found across all four children who all achieved 100% accuracy in identifying emotions during the training. Further, the emotion recognition skills were successfully maintained for 4–7 weeks post-training, with observed generalization to untrained still pictures and GIFs. This study provides preliminary evidence supporting the effectiveness of AR-based group training for young autistic children.

Humanoid Robot-Assisted Learning for Level 1 Autistic Children: Developing Test Plans to Enhance Number Recognition Skills

Autism Spectrum Disorder (ASD) impacts the social, communication, and cognitive development of affected individuals. Level 1 autism, the mildest form of ASD, presents unique challenges in the acquisition of crucial skills such as number recognition, which serves as a foundational aspect of children's cognitive development. Recent studies have shown that humanoid robots can offer effective intervention strategies for children with autism, fostering learning in a structured, engaging, and interactive environment. This study aims to develop and evaluate test plans using humanoid robots to enhance number recognition skills in Level 1 children with autism. Based on the findings, a test plan was designed to address the unique learning needs of Level 1 children with autism in number recognition. Participants were selected based on specific criteria, ensuring a diverse and representative sample. The humanoid robot's capabilities and features were detailed, emphasizing its role in facilitating the test plan. The research methodology outlined the test plan components, implementation procedure, data collection, and analysis techniques. Results demonstrated that the humanoid robot-assisted test plan was effective in enhancing number recognition skills among Level 1 children with autism. The participants exhibited significant improvements in their abilities to identify and manipulate numbers, as well as increased engagement and motivation in learning tasks. The study also revealed that the interactive and supportive nature of the humanoid robot fostered a positive learning environment, which contributed to the observed improvements in number recognition skills. The implications of these findings extend to the broader field of autism intervention, highlighting the potential benefits of incorporating humanoid robots into educational programs for children with autism.

Overcoming Reading Difficulties with Reading Fluency Strategies in the Turkish Language: Evidence from a Transparent Orthography

This study employed a single-case design with an AB structure to examine the effect of implementing a Response to Intervention (RTI) model on a fourth-grade elementary school student with reading difficulties. The participant in the study was Deniz, a fourth-grade elementary school student. The pretest measures revealed that Deniz was at the frustration level in both word recognition and reading comprehension skills. Consequently, an eight-week reading intervention program was designed to address and remediate Deniz’s reading difficulties. Through the intervention program, Deniz’s word recognition improved from the frustration level to the instructional level, and her reading comprehension progressed from the frustration level to the independent level, accompanied by a significant decrease in reading miscues.

Poor face recognition predicts social anxiety in autism: A short report.

Research has shown that some autistic people have severe difficulties in recognising other people's faces. However, little is understood about how these difficulties impact the daily life and the mental well-being of autistic people. In this study, we asked 60 autistic adults with varying degrees of face recognition ability to complete two tests of face recognition, a questionnaire about social anxiety and a bespoke survey which asked participants about their experiences of face recognition and social interaction. We found that participants who had poor face recognition reported experiencing higher levels of social anxiety compared to those with average or better face recognition skills. More than half felt that their face recognition difficulties affected their social interactions, and over a third believed it hindered their ability to make friends. These findings suggest that face recognition difficulties may contribute to social anxiety among autistic individuals.

Program to Improve Letter Recognition Skills For Children With Learning Difficulties Using Montessori Reading Techniques

Children with learning difficulties experience obstacles in the learning process, one of which is in the process of learning to read. Based on observations in the field, there is a child with learning difficulties aged 8 years who does not recognize the letters of the alphabet. Beginning reading for children with learning difficulties should use methods that suit their needs. One of the reading methods that can be used in the beginning reading process is the Montessori reading method. For this reason, this research aims to develop a program to improve letter recognition skills for children with learning difficulties using Montessori reading techniques. This program is developed based on the child’s ability analyzed from the results of developmental assessments on cognitive and language aspects. This program is implemented by researchers accompanied by parents of children with learning difficulties so that parents can continue the program later. This research uses mixed methods so that to collect and analyze data using qualitative methods and quantitative methods. The type of this research is Single Subject Research (SSR). The results of this study indicate that the letter recognition program with Montessori techniques can improve the ability to recognize letters for children with learning difficulties.Keywords: Letter recognition, children with learning difficulties, montessori reading techniques