The artificial intelligence (AI) wireless network technology is changing the world of education by bringing intelligent learning systems. This can be achieved through breaking the limitations associated with the classroom and providing learners the chance of accessing educational resources whenever and wherever they wish to. Listening and speaking skills still remain a difficult part of English learning for many students, specifically those who are in junior and senior high schools. The present study focuses on the existing situation regarding English listening and speaking teaching for junior high school students and highlights some of the existing problems related to this topic. An attempt will be made to propose a novel approach by making use of the intelligent voice system for improving phonetic learning. Literature review, questionnaire survey, and quasi-experimental designs have been utilized for assessing the effectiveness of the proposed approach. Integrating knowledge analysis, experimental evaluation, and AI-based intelligent voice system implementation combines speech processing, language analysis, and feedback mechanisms to enhance personalized English listening and speaking learning outcomes. According to the findings, the application of AI-based intelligent voice systems is very helpful in improving the English language speaking and listening abilities of students. The experimental group achieved a higher mean listening and speaking score of 89.16 compared with 83.32 for the conventional teaching approach, demonstrating the effectiveness of the proposed AI-based intelligent voice system in improving English language proficiency. Findings have verified the effectiveness of the adopted strategy and indicate how it can revolutionize English language education through digital means.
Assistive technology (AT) assessment is a person-centred and multidisciplinary process that considers users’ functional needs, goals, preferences, psychosocial experiences, and contextual factors when evaluating the suitability and use of an assistive technology device (ATD). Established approaches provide valuable information about users’ perceived psychosocial experiences; however, they do not themselves provide objective multimodal measurements of affective responses during device interaction. This study presents MERATA, a proof-of-concept multimodal emotion recognition framework designed to explore how objective affective information could complement established AT assessment. MERATA integrates facial, vocal, and physiological signals using deep learning-based modality-specific models and feature-level fusion to estimate valence and arousal and classify selected affective states. An exploratory affect-to-indicator layer associates the model-derived emotional outputs with selected PIADS-aligned items. The framework was evaluated using the K-EmoCon multimodal dataset through unimodal, bimodal, and trimodal experiments. Multimodal fusion demonstrated the technical feasibility of integrating complementary affective modalities, with trimodal configurations providing the strongest performance. However, class imbalance and the use of a dataset not collected in an assistive technology context limit interpretation and generalisability. MERATA demonstrates the feasibility of adding objective affective information to established person-centred assistive technology assessment. It is intended to support, rather than replace, clinical reasoning and user-centred decision-making.
This study examined the independent and combined effects of device type (fixed four-legged walker vs four-wheel rollator) and surface inclination (flat vs 10% incline) on cardiovascular demand and perceived exertion during assisted walking. Twenty-five healthy adults completed four randomized 8-min treadmill trials at a standardized speed of 0.2 m/s. Heart rate (HR) was continuously recorded, cardiovascular load was quantified using relative heart-rate reserve (%HRR), and perceived exertion was assessed with the Borg CR-10 scale. Two-way repeated-measures ANOVA showed significant main effects of both device type and surface inclination on HR and %HRR (all p < .001), with no significant interaction. Walking with the fixed walker and walking on the incline each increased cardiovascular demand, while perceived exertion showed a generally consistent pattern. The highest physiological and perceived demands occurred when the fixed walker was used on the incline. These findings indicate that device configuration and surface inclination contribute independently and approximately additively to the physical demands of assisted walking. Further studies in habitual walker users and clinical populations are needed to determine the clinical relevance of these effects.
Background This article explores the digital practices of young adults with life-shortening conditions (LSCs) and family members during the initial months of the COVID-19 pandemic in the UK. The findings presented are based on qualitative data collected between July and December 2020 by an interdisciplinary research team, including experts by experience who have LSCs. Results Data analysis of the transcripts curated through online interviews with young adults and family members utilised constructivist grounded theory. Through this analysis three themes were highlighted: (1) Social connections, (2) Access to basic goods and employment provision, and (3) Health and wellbeing. Conclusions Digital technologies and practices afforded the young adults and family members to improve their social connections and societal engagement. Without technology, this vulnerable group of people would have been disconnected because of the change in routines and following UK government shielding directives.
Wearable assistive technologies for blind and visually impaired users require discreet feedback channels that do not rely primarily on continuous auditory output. This study presents a simulation-based proof of concept focused on the controller logic of a proposed multimodal vibrotactile navigation belt combining ultrasonic short-range obstacle detection, directional haptic feedback, and a discreet audio channel for high-priority events. The proposed architecture includes three HC-SR04 sensors, a light sensor, and a potentiometer for adjusting the distance threshold. The firmware, implemented in C on an STM32 microcontroller, uses separate threads for data acquisition, distance computation, event handling, and timing. The controller decision logic implemented in the simulation reference model was verified through deterministic unit testing, achieving 100% branch coverage. A Python simulator was then used to assess closed-loop controller–agent behavior in two-dimensional environments with obstacles and light variations. Across 30 base seeds and 30,000 episodes per condition, the mean collision rate was 0.978 ± 0.004 in the no-feedback baseline and 0.101 ± 0.008 in the controller-assisted condition, corresponding to a mean relative reduction of 89.70% ± 0.81%. These findings support controller-level technical feasibility but do not establish real-world usability, user effectiveness, or clinical benefit. Physical prototyping, calibration, and end-user evaluation remain necessary.
