Interactive Experience Research Articles

Evaluation of food pattern behaviours following nutritional education for health professionals

Abstract Background The “Work Programme - UN Decade of action on nutrition 2016-2025” highlights the importance of implementing Recommendation 19 of the Second International Conference on Nutrition of FAO and WHO related to nutrition education interventions (NEI) for health professionals (HP), in order to develop nutritional skills based on national dietary guidelines and coherent policies relating to food. The Local Health Agency integrated with Trieste University (ASUGI), since 2009, has performed 25 NEI with the formation of 910 HP. Post pandemic, the content of ASUGI’s last 5 NEI, programmed by the prevention plan of the Autonomous Region of Friuli Venezia Giulia, was aligned with the principles of the European Farm to Fork Strategy linked to Sustainable Healthy Diets (SHD). Objectives The objectives of the training programme (TP), approved for Continuing Medical Education, was to change and evaluate food pattern behaviour (FPB) of HP (n = 200) to adhere to the SHD. TP was characterized by a systemic view on complex interconnections between nutritional and sensorial food value, sustainability of food chain systems, evolution of urban food environments, as contexts into which SHD choices can be applied. The 2 days training, spread over 14 hours with 40 participants, concluded with interactive work and experiences to applied knowledge and beginning to make informed healthy dietary choices in practice. Results 6 months after the conclusion of TP it was reported that the percentage of HP who consumed the recommended portions of fruits and vegetables had increased from 62% to 70% and from 28% to 35% respectively, while those who consumed no cured meats, red meats or legumes, changed from 24% to 35%, from 19% to 25%, from 6% to 3% respectively. Conclusions The evaluation of the TP systemic structure has shown its effectiveness in improving some healthy FPB of HP and the importance of applying a continuous improvement process of the program to better adhere to the whole SHD. Key messages • The systemic and integrated structure of nutritional education intervention programs for health professionals contributes to improving their healthy food pattern behaviour. • The relationships between complex policies of food systems and the 17 SDGs included in the training programs on nutrition education are useful for promoting adherence to healthy and sustainable diets.

Enhancing English as a Foreign Language (EFL) learning in Saudi Arabia: the academic contribution of YouTube in EFL learning and cultural awareness

The incorporation of technology in English as a Foreign Language (EFL) classroom has drastically transformed conventional learning models by offering innovative ways to boost students’ engagement and improve learning outcomes. This study investigates the impact of using YouTube as an educational tool to enhance EFL instruction in Saudi Arabia. A total of 200 EFL students were divided into two groups: An experimental group which used You Tube as a source of learning and another group which used normal curriculum. A mixed-methods approach was employed, combining quantitative data from a paired-sample t-test with qualitative feedback from students. The results for paired-sample t-test computations revealed a statistically significant difference (p = 0. 003) across the proficiency level indicating improvement in students’ speaking and listening skills at higher proficiency levels. Of the qualitative answers, motivational and participation enhancement were overemphasized. The research points that the integration of YouTube in EFL classrooms can lead to a remarkable increase in language learning especially in the learning area of listening and speaking abilities among the students. These results offer practical implications for educators seeking to integrate multimedia tools into their teaching strategies to promote more interactive and effective learning experiences.

A process evaluation of a LifeLab Dublin; an interactive health literacy intervention

Abstract The argument for targeting adolescent health has been made strongly, with poor lifestyle behaviours often emerging during this life stage. Furthermore, there is consistent evidence of a widening socioeconomic gap in health indicators. Developing health literacy (HL) in youth populations to improve lifelong health behaviours has garnered increased interest in recent years. This process evaluation examines the acceptability, fidelity and dose delivered of the pilot of LifeLab Dublin: a nine-week, school-based HL intervention for low socioeconomic adolescents. The intervention, which comprised of two out-of-school, interactive HL experiences in conjunction with seven school-based lessons, took place between September and December in 2021 and involved students aged 11 - 13. The health issues targeted were previously identified by the teachers and students of the target population, and the learning activities within the out-of-school experiences were co-designed by adolescents of a similar demographic. Overall, the intervention was perceived positively by the students and teachers, particularly the two interactive out-of-school experiences. The teachers, however, highlighted issues with the volume and content of the school-based lessons, resulting in a reduced number of lessons being delivered. The fidelity of the two LifeLab experiences was high, demonstrating that the students engaged well with the learning activities and that the experience aligned with LifeLab’s core principles and underpinning theoretical constructs. The findings from this study highlight the value in implementing experiential style learning in school-based HL education and the benefit of involving participants in the design of intervention. The evaluation provided valuable insight into the refinements required to enhance the efficacy of the intervention, as well as providing an evidence-base to inform future school-based HL interventions for low socioeconomic adolescents. Key messages • The benefit of adopting experiential style health literacy education with young people. • The benefit of including young people in the design of a health literacy intervention.

Highly sensitive and stretchable CB/GNPs-TPU strain sensor with porous microstructure for multifunctional strain sensing

Multifunctional flexible strain sensors have garnered significant attention in recent years, particularly in the fields of smart wearable devices and human health monitoring. However, the trade-off between high sensitivity and a wide strain range limits their practical applications. This study presents a porous TPU/CB framework prepared using a water vapor-induced phase separation method, which can deform like a spring when stretched, thereby providing the sensor with a greater strain range. The graphene nanoplatelets (GNPs) were subsequently incorporated into the pores of the porous framework through ultrasonic treatment, which enhanced the sensor's sensitivity while preventing increased brittleness caused by the aggregation of conductive fillers. This structure establishes a stable conductive network, enabling the sensor to achieve high sensitivity (GF = 5902.4) across a wide strain range (327 %) while also demonstrating excellent stability and durability (over 7000 stretching/releasing cycles). The sensor can detect not only simple limb movements, such as bending of the arms and knees but also subtle muscle activities, including facial expressions and throat vocalization, thus bringing excellent human-computer interaction experience. These remarkable features position the sensor for promising applications in smart wearables and human health monitoring.

A Review of Tiktok Livestreaming Commerce

In recent years, live-streaming commerce has witnessed remarkable global growth, catalyzed in part by the COVID-19 pandemic. TikTok, originally a video-sharing app, has undergone rapid expansion and now offers livestreaming capabilities. This review aims to explore how TikTok livestreaming is reshaping the marketing landscape. The objective is to uncover the advantages of TikTok livestreaming for various stakeholders, shedding light on its potential implications for marketers, customers, and content creators. A comprehensive examination of existing literature was conducted, analyzing studies, reports, and academic papers. The analysis focused on the multifaceted benefits of TikTok live streaming for marketers, customers, and content creators. It also considered practical implications for businesses utilizing this platform. TikTok livestreaming fosters real-time engagement between marketers and customers, leading to enhanced trust and more effective product demonstrations. It appeals to younger demographics, offering a valuable marketing avenue. For customers, it facilitates interactive, informative, and emotionally engaging shopping experiences. Content creators can leverage TikTok live streaming to monetize their content and deepen connections with their audience, enhancing brand exposure. In conclusion, TikTok livestreaming is reshaping e-commerce by facilitating immersive, interactive, and trust-building experiences for marketers, customers, and content creators. Marketers should focus on quality interaction, product presentation, and partnering with suitable content creators. Collaborations with influencers should consider credibility and alignment with brand values. Leveraging TikTok's livestreaming capabilities offers the potential to cultivate customer loyalty and retention, transforming conventional marketing paradigms in the process

What do we mean by “agency”? A framework and tools for supporting visitors' agency in museums and science centers

AbstractAgency is a central value within museums and science centers, but it has not been defined and operationalized in ways that can guide museum practice or support inclusion for new audiences. In this project, an interdepartmental group of science center staff co‐created a conceptual framework for noticing and supporting visitors' agency. The framework includes four interconnected aspects of agency: physical environment, social engagement, choice and autonomy, and relevance and empowerment. Conceptualizing agency as multifaceted led to more expansive approaches for supporting it, allowing staff to move beyond open‐endedness to consider a wider range of supports and structures that can make museum experiences more inviting and inclusive. The framework informed the development of practical tools for use by exhibit/program developers and facilitators. Tools are freely available and guide museum staff in questioning current practices and integrating the four facets of agency into planning, prototyping, and observation of interactive experiences.

Analysis of the Use of Educational Game Media for Science Subjects on Digestive System Material

Educational games are games that are used in the learning process, as a form of technology adaptation in the world of education to help teachers improve the learning process in the classroom. Researchers conducted research with the aim of analyzing the use of educational game media during learning; analyze the impact of using educational game media; how important educational game media is in class V science and science learning at Japeledok State Elementary School. This research uses descriptive qualitative research methods. This research was carried out at SDN Japeledok, Pancur District, Rembang Regency. SDN Japeledok has a total of 11 class V students consisting of 7 boys and 4 girls. The data taken from this research are observations, questionnaires, interviews and documentation using triangulation techniques. The results obtained from this research are the use of educational game media in Japeledok Elementary School that have been implemented by class teachers are Wordwall and Quizizz; The impact given after implementing educational game media is an interactive and fun learning experience, training students' thinking skills, increasing interest and motivation to learn, and making students more active in the learning process in class. Overall, educational games have had a lot of positive impacts on students and teachers. Judging from the impact this educational game has, it has an important role in implementing learning. Educational game media not only provides an interesting alternative in education, but also opens up new opportunities to improve the quality of learning and learning experiences for various types of learners.

Using drama to enrich a genre-based pedagogy for teaching academic writing across content areas

Drama has the potential to enrich and enliven established approaches to literacy learning, engaging students and expanding their possibilities for meaning-making. Drama-rich pedagogy is well-established as an effective tool in supporting language and literacy development. However, research to date has not explored the possibilities of using drama to enrich established genre-based approaches to teaching writing. This article reports on findings from an interventionist case study in an Australian primary school examining how a Year Three/Four teacher used drama-rich pedagogy to support students’ academic writing of a scientific explanation text. The findings indicate three key pedagogical benefits of employing drama to build conceptual understandings of the field of study and relevant academic language as part of a genre-based pedagogy for teaching writing. Firstly, drama experiences can make visible students’ prior knowledge of a topic, allowing teachers to identify, interrogate and transform students’ misconceptions through reflective dialogue on embodied experience. These embodied and interactive experiences also support the development of shared understandings of key concepts and language. Finally, drama experiences provide embodied and interactive contexts in which students can move from common sense to more abstract/technical understandings of the topic of study which they can apply in writing their own texts. In sharing these findings, this article aims to illustrate how drama can be used to develop the conceptual and linguistic understandings required by genre pedagogy in engaging, embodied ways that draw productively on the diverse resources that students bring to their learning.

Advancing Electric Engineering Education through Immersive Virtual Reality: Deep Learning and Evolutionary Algorithms for Image Stitching and Rectification in Virtual Lab Environments

Virtual Reality (VR) technology has emerged as a transformative tool in education, offering immersive and interactive experiences that enhance learning outcomes. This paper delves into the application of image stitching and rectification techniques to create a VR lab environment, specifically tailored for electrical engineering education. The importance of VR technology in education is explored, highlighting its role in promoting active learning and providing experiential learning opportunities. The primary emphasis of this Paper lies in the smooth incorporation of image stitching algorithms for the creation of panoramic perspectives, along with the implementation of rectification techniques to correct irregular borders within the stitched images. By utilizing Convolutional Neural Networks (CNNs) and Genetic Algorithms (GAs), the proposed approach optimizes the rectification process, resulting in visually cohesive representations. Demonstrating the utilization of the VR lab across a range of situations, such as examining power transfer and creating control panels for water pumps in irrigation initiatives, the immersive setting enables students to delve into intricate systems. The performance of the proposed method was evaluated using various metrics, including mean squared error, peak signal to noise ratio (PSNR), structural similarity index (SSIM), and Fréchet inception distance (FID). the combination of deep learning algorithm specifically (CNN) and optimization algorithm specifically (Genetic algorithm (GA)) led to an increase in the accuracy of the rectified images where the average PSNR reached 23.98, SSIM was 0.8066, and FID was 18.72. Regarding the users’ opinion about the generated environment by stitching and rectifying images, participants demonstrated consistent positive sentiments, with mean scores ranging from 3.65 to 4.03, all above the scale midpoint, and moderate variability indicated by standard deviation values ranging from 1.070 to 1.251, suggesting general favorability with some variation in responses. This experience empowers the users to gain insights and cultivate essential problemsolving abilities at a heightened level. Collaborative learning is facilitated, enabling students to engage in collaborative projects regardless of their physical location. Through the synthesis of image processing techniques and VR technology, this research contributes to the enrichment of educational experiences and the advancement of electrical engineering education.

Humanizing Online Discussions by remixing AI and #DigitalPowerups

This article explores the need to humanize online learning environments while simultaneously developing students' AI literacies and essential academic skills. Fostering meaningful student engagement by integrating AI tools within the #DigitalPowerups strategy for online discussions, educators can enhance both social presence and collaborative knowledge co-construction, creating a more dynamic and interactive learning experience for students. This approach not only supports creativity, critical thinking, and interdependent thinking, but also ensures that students are equipped with the technological competencies required for success in this digital-age. Remixing these elements—humanized learning, AI literacy, and #DigitalPowerups—provides a comprehensive strategy for engaging students more deeply with course content while preparing them to navigate and thrive in modern educational and professional contexts.

Integrating Virtual Reality Tools into Secondary School Classrooms to Address Gender Gap in STEM Education: An Action Plan

This action plan addresses the gender gap in STEM education by integrating Virtual Reality (VR) tools into secondary school classrooms. Despite various strategies to increase female participation in STEM fields, women remain underrepresented in these areas. The action plan proposes the use of immersive and interactive VR experiences to create more engaging learning environments that may attract a diverse student body, particularly female students. By leveraging the potential of VR to simulate science experiments and other STEM-related activities, this project aims to enhance students' interest and confidence in STEM subjects. A pilot will be conducted in a secondary school, with approximately 50-100 students and a dedicated STEM teaching team. Key strategies include virtual reality technology training for teachers, the design of inclusive STEM curricula, and continuous evaluation through both formative and summative assessments. The expected outcome is that female students will show increased willingness to pursue further study and careers in STEM fields, contributing to long-term reductions in the gender gap in STEM education.

58 A hospital paediatrics education curriculum: Quality improvement for inpatient paediatric learner education on CTU

Abstract Background Paediatric learners experience the bulk of their inpatient medicine on the wards. While bedside teaching is invaluable, ward learning can be impacted by seasonal exposure, clinical homogeneity, and volume. Locally our learners requested more formal ward teaching to encourage dialogue around common topics perhaps not encountered on rotation. We queried whether having a database of interactive guideline-based educational experiences would minimize barriers (eg. time, resources) to providing formal inpatient learner education. Objectives We sought to enhance general paediatrics ward teaching by developing a curriculum of guideline-based interactive educational content on common inpatient paediatric topics. Design/Methods This study was conducted at a Canadian tertiary care paediatric hospital with a range of learners (MSI3, MSI4, paediatric residents (R1-R4)) over 12 months. 1) Needs Assessment: We surveyed residents, hospitalist fellows, and CTU physicians regarding a) perceived need for a curriculum, b) content (top 5 CPS guidelines and top 5 non-CPS topics), c) teaching modality, d) need for handouts, and e) curriculum structure. 2) Curriculum generation: Curriculum was developed according to needs assessment results. 3) Quality improvement: Learners were surveyed after each session with four Likert scale questions (5=strongly agree) regarding teaching quality, clinical translatability, enhanced knowledge/understanding, and improved clinical confidence. Results 1) Needs assessment: Needs assessment (N=25) unanimously supported a structured curriculum. Eleven CPS statements and twelve non-CPS guideline-based topics were identified for content. Three preferred teaching formats were highlighted, and handouts were important to 88% of respondents. The curriculum was favoured to be 50-75% standardized. 2) Curriculum generation: We developed a curriculum of 13 topics with different delivery modalities (e.g. case-based powerpoints, whiteboard talks, Jeopardy, simulation). All were guideline-based, interactive, and had fill-in-the-blank learner handouts. The curriculum was standardized with 4/6 CTU teaching sessions per block being derived from the curriculum bank, and the remainder being at educator discretion (e.g. curriculum bank, interesting case). 3) Quality improvement: Likert scales (5=strongly agree) were positive from all learners (MSI3-R4; N=52), with scores of 4.9+/-0.2 for teaching quality, translatability to practice, and improved understanding, and 4.8+/-0.3 for improved clinical confidence. Conclusion Here we present an interactive and guideline-based paediatric inpatient learner education curriculum whose development, from content to delivery modality, was directed by community needs. We are now seeking funding to prepare for national distribution (e.g. peer-review, licensure), and intend to publish on platform where the curriculum would be downloadable for use by all educators (i.e. senior residents, staff).

The relationship between peer social support and self-regulated learning in Samarinda Ulu state junior high school students

Purpose: At the age of 2-7 years, based on Piaget's theory, children are in the pre-operational stage. At this stage, children have the ability to understand mathematical concepts concretely through sensory and interactive experiences. Strategies are needed to improve the children's cognitive abilities. This research aims to provide an overview of early childhood cognitive development at the pre-operational stage in the introduction of geometric shapes. Method: Researchers used a descriptive qualitative approach to interpret and explain patterns of behavior of children who are in the pre-operational stage. Data collection techniques included structured interviews and observations with checklists based on Jean Piaget’s cognitive theory. Respondents in this study were selected using a purposive sampling technique. The respondents consisted of five children aged 6-7 years from the Islamic Kindergarten 'Aqila who were not familiar with geometric shapes. Result: The results of this study indicate that children who are the subjects of the study exhibit behavior patterns consistent with Piaget's theory in the pre-operational stage, Children are able to recognize shapes through interactive learning experiences. Conclusion: Based on the results, it is necessary for parents and teachers to pay attention to the child's cognitive development stage when teaching geometric concepts.

A Comprehensive Review of Communicative Language Teaching (CLT) in Modern Classrooms

Communicative Language Teaching (CLT) has become a dominant methodology in language education, emphasizing interaction and practical communication skills over traditional grammar-focused approaches. With the increasing need for language learners to develop real-world communicative competence, CLT has been widely adopted in modern classrooms across various educational contexts. However, its implementation faces challenges such as cultural differences, teacher preparedness, and institutional constraints. This comprehensive review aims to evaluate the effectiveness and challenges of CLT in contemporary language teaching settings. This study uses a systematic review methodology, analyzing research articles, case studies, and reports published in the last two decades. The review focuses on both qualitative and quantitative studies that assess CLT’s impact on language proficiency, learner motivation, and classroom engagement. It also explores barriers to successful CLT implementation, including teacher training and resource limitations. The findings suggest that CLT has a significant positive impact on learners’ communicative competence and motivation, especially in immersive environments. However, the success of CLT varies depending on the classroom context, cultural backgrounds, and teacher expertise. Moreover, while CLT fosters a more interactive learning experience, challenges such as inadequate teacher training and a lack of suitable materials often hinder its full potential. In conclusion, CLT remains an effective approach to language teaching, but its success is contingent on overcoming implementation barriers. Further research is needed to address these challenges and to explore how CLT can be adapted to different learning environments.

Latency Reduction in Immersive Systems through Request Scheduling with Digital Twin Networks in Collaborative Edge Computing

Immersive systems, which offer immersive interactive experiences by tightly coupling the real and virtual worlds, encompassing Augmented Reality (AR) and Virtual Reality (VR), have undergone rapid development in recent years. The inherent latency issue of immersive systems poses considerable challenges for AR/VR applications that are highly sensitive to delay. To address this challenge, we propose utilizing edge collaboration as an efficient means to schedule AR/VR requests, owing to the inherent ability of edge nodes to seamlessly coordinate within the same geographical region and optimally allocate request resources to minimize latency. However, when it comes to edge nodes across different regions, a significant hurdle emerges. These nodes often lack real-time knowledge about cached resources across other regions, making cross-regional edge collaboration for AR/VR request scheduling an extremely challenging problem. We formally define and prove the NP-hardness of this problem. To tackle this complexity, we introduce a Federated Digital Twin Model Construction (FedDT), which establishes a global digital twin network connecting different edge nodes. This network simulates and reflects the resource status and availability of each edge node in real time. Subsequently, we devise an extended Dijkstra algorithm to determine the shortest path between AR/VR requests and edge nodes, taking into account current network conditions to optimize service delay. Both theoretical analysis and experimental results confirm that compared with baseline methods, our proposed solution consistently achieves an average delay reduction of 36.78% across various scenarios, effectively demonstrating its superior performance.

Influence of Avatar Identification on the Attraction of Virtual Reality Games: Survey Study.

In gaming, the embodied interaction experience of avatars serves as a key to emotional sublimation in artistic creation. This presents the emotional expression of art in a more vivid form, which is a critical factor in the high attractiveness of virtual reality (VR) games to players. Intertwined with players' physiological and psychological responses, immersion is an essential element for enhancing gaming attractiveness. This study aims to explore how to help players establish a sense of identity with their embodied avatars in VR game environments and enhance the attractiveness of games to players through the mediating effect of immersion. We conducted a structured questionnaire survey refined through repeated validation. A total of 402 VR users were publicly recruited through the internet from March 22, 2024, to April 13, 2024. Statistical analysis was conducted using the SPSS and Amos tools, including correlation analysis, regression analysis, and mediation effect verification. We divided the self-differentiation theory into 4 dimensions to validate their impact on avatar identification. Subsequently, we correlated the effects of avatar identification, game immersion, and game attractiveness and proposed a hypothetical mediating model. Regression analysis of the predictor variables and the dependent variable indicated a significant positive predictive effect (P<.001); the variance inflation factor values for each independent variable were all <5. In the hypothesis testing of the mediating effect, the total mediating effect was significant (P<.001). Regarding the direct impact, both the effect of avatar identification on immersion and the effect of immersion on game attractiveness were significant (P<.001). However, the direct effect of avatar identification on game attractiveness was not significant (P=.28). Regarding the indirect impact, the effect of avatar identification on game attractiveness was significant (P<.001). The results indicate a significant positive correlation between different dimensions of the self-differentiation theory and identification with avatars. Moreover, immersion in the game fully mediated the relationship between identification with avatars and game attractiveness. This study underscores that the embodiment of avatar identification is influenced by dimensions of self-differentiation, and the impact of identification with avatars on game attractiveness is contingent upon full mediation by immersion. These findings deepen our understanding of the role of avatar identification in VR gaming.

Research on the Interactive Effects of Parenting Advertising Under the Sustainable Development Goals (SDGS)

Objective: The objective of this study is to investigate the different effects of advertising interactive experiences, and explore effective advertising interactive methods, to provide effective parenting advertising training for abusive parents. Theoretical Framework: Refers to the multi-sensory advertising interaction model based on the studies before, such as the AIEDA tourism advertising effects model, schema congruence theory, and a spiral brand experience concept. Method: This study conducted the distinct "Systematic Literature Review Synthesis Process", a stand-alone literature review typology that helps make sense of a chosen body of current literature and helps determine the theoretical framework at the early stages of research ideation. Results and Discussion: The results revealed that visual, auditory, and multi-sensory interactions all have different elements and characteristics and could cause different levels of attention, memory, and emotions for audiences. Research Implications: The results are expected to guide the development of a theoretical framework for combining advertising and user experience interaction. Originality/Value: The research helps to identify interactive sensory experience characteristics in advertisements, guide the effective dissemination of parenting public service advertisements, and create a happier family atmosphere for children, to promote SDG 3 on ensuring healthy lifestyles and promoting the well-being of people of all ages.

The Role of ChatGPT in Teaching Speaking Skills for English Majored Students: A Research Perspective

With the rapid advancement of artificial intelligence and its integration into education, the potential for enhancing English-speaking instruction has grown significantly. Traditional methods of teaching speaking to English-majored students often face challenges such as time constraints, limited access to native speakers, and varying levels of student proficiency. This study explores the auxiliary role of ChatGPT, a large language model, in assisting the development of speaking skills among English majors. By leveraging its natural language processing capabilities, the study aims to innovate teaching methods and provide learners with personalized, real-time practice opportunities. The article first outlines the technical features of ChatGPT and its applications in speaking instruction, including customized conversation practice, real-time interaction, and intelligent feedback. It also examines the current challenges of traditional speaking instruction, such as limited classroom time and the need for individualized feedback. Furthermore, the study discusses how ChatGPT can support teachers in providing scalable, interactive learning experiences. Finally, the article evaluates the effectiveness and feasibility of ChatGPT in enhancing speaking proficiency and highlights the potential future applications of AI tools in English language education. This research offers valuable insights into how AI can be integrated into language learning to address existing challenges and improve the overall teaching of speaking skills.

A lightweight network-based sign language robot with facial mirroring and speech system

Human–robot interaction is an essential capability for humanoid robots to enter the physical world and become companions in people’s lives, learning, and work. While the majority of current research focuses on the voice-based interactions of robots, yet over 60% of communication occurs through nonverbal behaviors, such as facial expressions and hand gestures. Endowing robots with the ability to communicate through nonverbal behavior not only enhances the interactive experience with robots but also provides a potential communication tool for individuals with hearing or speech impairments. Here, we develop a humanoid robot capable of adjusting facial movements by driving servos, and design a novel framework for the robot to integrate sign language recognition and facial landmark detection algorithms. This framework facilitates the robot recognize sign language and translate it into spoken language, while also imitating the facial expressions of the signers. To achieve this, we also propose a lightweight deep learning network called RealTimeSignNet for real-time sign language recognition. Leveraging lightweight 3D convolution modules and time-dependent constraints, this model adapts to various time scales, ensuring efficient processing of sign language recognition tasks. Experimental results demonstrate the outstanding performance of the RealTimeSignNet model on mainstream sign language datasets, achieving an accuracy of 88.1% on the large continuous sign language dataset (continuous SLR), 98.2% on the isolated sign language dataset (SLR 500), and 91.50% on the English sign language dataset (WLAS). The overall assessment demonstrates that our humanoid robot is capable of recognizing sign language and translating it into spoken language, while imitating the facial emotions, providing a comprehensive solution to the communication challenges faced by individuals with hearing and speech impairments.

CodelessML: A Beginner's Web Application for Getting Started with Machine Learning

Building machine learning models requires intensive coding and installation of certain software. This is frequently a barrier for beginners learning about machine learning. To overcome this situation, we present CodelessML, a reproducible web-based application designed for Machine Learning beginners due to its coding-free and installation-free design, published under Code Ocean capsule. It provides a common workflow that eases the process of building Machine Learning models and using the model for predictions. Using the Agile method, CodelessML was successfully built using Python, Anaconda, and Streamlit It. By using CodelessML, users can get a walkthrough and interactive experience of building machine learning through a simplified machine learning process: exploratory data analytics (EDA), modelling, and prediction. The impact of the software was evaluated based on feedback from 79 respondents, which showed that based on a 5-scale Likert, CodelessML received average ratings of 4.4 in accessibility, 4.3 in content, and 4.4 in functionality. CodelessML serves as an accessible entry point for learning machine learning, offering online, free, and reproducible features.