Assistive Applications Research Articles

A comparative study of technological pedagogical content knowledge between special education and general education in China

ABSTRACT This study examined the technological pedagogical content knowledge (TPACK) profiles of teachers at special education schools for the blind and at general elementary schools in China. A total of 113 teachers in special schools and 193 teachers in general elementary schools were enrolled. A questionnaire was used as a quantitative method of data collection and analysis. The modified scale is appropriate for this investigation and has great reliability and validity. The results revealed that, regarding each dimension of TPACK, the competence of the general school teachers was significantly superior to that of the teachers in special schools. Data showed that most pathways to TPACK as proposed were supported, but there were some differences between the two groups of teachers. This study hopes to contribute some insight regarding the assistive technology application in curriculum teaching and design for teachers both at special schools and at general schools.

A Comprehensive Survey on Emerging Assistive Technologies for Visually Impaired Persons: Lighting the Path with Visible Light Communications and Artificial Intelligence Innovations.

In the context in which severe visual impairment significantly affects human life, this article emphasizes the potential of Artificial Intelligence (AI) and Visible Light Communications (VLC) in developing future assistive technologies. Toward this path, the article summarizes the features of some commercial assistance solutions, and debates the characteristics of VLC and AI, emphasizing their compatibility with blind individuals' needs. Additionally, this work highlights the AI potential in the efficient early detection of eye diseases. This article also reviews the existing work oriented toward VLC integration in blind persons' assistive applications, showing the existing progress and emphasizing the high potential associated with VLC use. In the end, this work provides a roadmap toward the development of an integrated AI-based VLC assistance solution for visually impaired people, pointing out the high potential and some of the steps to follow. As far as we know, this is the first comprehensive work which focuses on the integration of AI and VLC technologies in visually impaired persons' assistance domain.

The Dynamic Evolution of College or University Roles in Aesthetic Education Assistance Projects in China: From Implementers to Co-Creators

The role of colleges and universities as transmitters of knowledge and active participants in aesthetic education assistance projects is pivotal. This study aims to investigate how the roles of these institutions in aesthetic education assistance projects have evolved in China. Through interviews with 10 college educators, students who endorse the project, and local teachers engaged in such initiatives, the research seeks to trace the dynamic shifts in the involvement of higher education institutions in fostering aesthetic education. The findings reveal that colleges and universities have transitioned from being mere implementers to assuming four key roles: resource providers, talent developers, knowledge advocates, and leaders in model practices within aesthetic education. A significant innovation of this research is the application of actor-network theory, which illustrates how these institutions have shifted from implementers to collaborators, creating a flexible network that enhances stakeholder engagement, attracts more participants, and encourages sustained active involvement. Ultimately, this study offers fresh insights into improving the initiative and co-innovation capacities of educational institutions and their networks, providing valuable experiences for future research and practical applications of aesthetic education assistance in developing areas to further aesthetic education's growth.

Improving communication and promoting social inclusion for hearing-impaired users: Usability evaluation and design recommendations for assistive mobile applications.

This study examines the usability of communication-assistive applications for hearing-impaired users, with a focus on enhancing user experience and promoting social inclusion. Although such applications have been developed and evaluated previously, interface designs that consider the intimacy needs of hearing-impaired users remain under-explored. We performed a comprehensive usability evaluation employing a mixed-method approach, which involved hearing-impaired individuals as well as field experts. The findings revealed areas for improvement in the design, validated the feasibility of implementing these applications, and emphasized the importance of incorporating the unique needs and preferences of hearing-impaired users. Furthermore, this paper discusses the importance of introducing guidelines and evaluation scales for the "Design for Emotion and Life Knowledge" levels to facilitate smooth and effective human-computer interactions. Such measures will promote the development of intelligent assistive technologies that reflect the qualitative needs of people with disabilities and contribute to social rights for hearing-impaired users. With the growing demands of artificial-intelligence-powered assistive technologies, the inclusion of individuals with disabilities in the design and research process is anticipated to increase. In future, studies should be conducted to blend the culturally shared experiences and emotional bonds expressed by users (having mild-to-severe hearing impairment) with the design and development process of assistive devices or services.

EEG-based motor imagery channel selection and classification using hybrid optimization and two-tier deep learning

Brain–computer interface (BCI) technology holds promise for individuals with profound motor impairments, offering the potential for communication and control. Motor imagery (MI)-based BCI systems are particularly relevant in this context. Despite their potential, achieving accurate and robust classification of MI tasks using electroencephalography (EEG) data remains a significant challenge. In this paper, we employed the Minimum Redundancy Maximum Relevance (MRMR) algorithm to optimize channel selection. Furthermore, we introduced a hybrid optimization approach that combines the War Strategy Optimization (WSO) and Chimp Optimization Algorithm (ChOA). This hybridization significantly enhances the classification model’s overall performance and adaptability. A two-tier deep learning architecture is proposed for classification, consisting of a Convolutional Neural Network (CNN) and a modified Deep Neural Network (M-DNN). The CNN focuses on capturing temporal correlations within EEG data, while the M-DNN is designed to extract high-level spatial characteristics from selected EEG channels. Integrating optimal channel selection, hybrid optimization, and the two-tier deep learning methodology in our BCI framework presents an enhanced approach for precise and effective BCI control. Our model got 95.06% accuracy with high precision. This advancement has the potential to significantly impact neurorehabilitation and assistive technology applications, facilitating improved communication and control for individuals with motor impairments

Personalized prediction of intradialytic hypotension in clinical practice: Development and evaluation of a novel AI dashboard incorporating risk factors from previous and current dialysis sessions

BackgroundIntradialytic hypotension (IDH) is one of the most common and critical complications of hemodialysis. Despite many proven factors associated with IDH, accurately predicting it before it occurs for individual patients during dialysis sessions remains a challenge. PurposeTo establish artificial intelligence (AI) predictive models for IDH, which consider risk factors from previous and ongoing dialysis to optimize model performance. We then implement a novel digital dashboard with the best model for continuous monitoring of patients’ status undergoing hemodialysis. The AI dashboard can display the real-time probability of IDH for each patient in the hemodialysis center providing an objective reference for care members for monitoring IDH and treating it in advance. MethodsEight machine learning (ML) algorithms, including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), K Nearest Neighbor (KNN), Light Gradient Boosting Machine (LightGBM), Multilayer Perception (MLP), eXtreme Gradient Boosting (XGBoost), and NaiveBayes, were used to establish the predictive model of IDH to determine if the patient will acquire IDH within 60 min. In addition to real-time features, we incorporated several features sourced from previous dialysis sessions to improve the model’s performance. The electronic medical records of patients who had undergone hemodialysis at Chi Mei Medical Center between September 1, 2020 and December 31, 2020 were included in this research. Impact evaluation of AI assistance was conducted by IDH rate. ResultsThe results showed that the XGBoost model had the best performance (accuracy: 0.858, sensitivity: 0.858, specificity: 0.858, area under the curve: 0.936) and was chosen for AI dashboard implementation. The care members were delighted with the dashboard providing real-time scientific probabilities for IDH risk and historic predictive records in a graphic style. Other valuable functions were appended in the dashboard as well. Impact evaluation indicated a significant decrease in IDH rate after the application of AI assistance. ConclusionThis AI dashboard provides high-quality results in IDH risk prediction during hemodialysis. High-risk patients for IDH will be recognized 60 min earlier, promoting individualized preventive interventions as part of the treatment plan. Our approachis believed to promise an excellent way for IDH management.

The Use of English Language Speech Assistant (ELSA) Speak Application to Improve Pronunciation

This research aimed to investigate the effectiveness of English Language Speech Assistant (ELSA) speak application is effective in improving students’ pronunciation at SMP Negeri 1 Sirenja. The primary research question is whether or not the use of English Language Speech Assistant (Elsa) speak application is effective in improving students’ pronunciation. The research used a quasi-experimental design with an applied non-equivalent control group design. The research used a purposive sampling technique and took a sample of 57 students. The subject of this research was the eighth-grade students at SMP Negeri 1 Sirenja class A and B. B class was an experimental group while A class was a control group. The research instrument was a pronunciation test that was given as a pre-test and post-test. The data collected was analyzed by using descriptive statistics and inferential analysis using SPSS 22 version program. Based on the result of the hypothesis test (t-test), the value from the data analysis that has been conducted shows a significance value of 0.000<0,05. In addition, the alternative hypothesis (Ha) is accepted while the null hypothesis (Ho) is rejected. In conclusion, the use of English Language Speech Assistant (ELSA) speak application is effective in improving students’ pronunciation.

Sighpost Assistant Prototype Design: A Wayfinding Application to Assist The Independence of The Visually Impaired in Mobility Through Understanding The Concept of Space

This research presents a study related to the creation and design of direction applications to help blind independence in mobility through understanding the concept of space. This research aims to help blind independence in carrying out daily activities by understanding the concept of space in their environment. This research uses a development method, namely the prototype development model. However, this research is limited only to the development of the Signpost Assistant application design. It is hoped that this research will be continued and will produce a finished product. Based on the results of data collection and prototype development carried out, it can be concluded that Signpost Assistant is an application that is quite easy to use and is needed by blind people.

Application of Robotic Stereotactic Assistance (ROSA) for spontaneous intracerebral hematoma aspiration and thrombolytic catheter placement

BackgroundSpontaneous intracerebral hemorrhage (ICH) accounts for up to 20% of all strokes and results in 40% mortality at 30 days. Although conservative medical management is still the standard treatment for ICH patients with small hematoma, patients with residual hematoma ≤15 mL after surgery are associated with better functional outcomes and survival rates. This study reported our clinical experience with using Robotic Stereotactic Assistance (ROSA) as a safe and effective approach for stereotactic ICH aspiration and intra-clot catheter placement. MethodsA retrospective analysis was conducted of patients with spontaneous ICH who underwent ROSA-guided ICH aspiration surgery. ROSA-guided ICH surgical techniques, an aspiration and intra-clot catheter placement protocol, and a specific operative workflow (pre-operative protocol, intraoperative procedure and postoperative management) were employed to aspirate ICH using the ROSA One Brain, and appropriate follow-up care was provided. ResultsFrom September 14, 2021 to May 4, 2022, a total of 7 patients were included in the study. Based on our workflow design, ROSA-guided stereotactic ICH aspiration effectively aspirated more than 50% of hematoma volume (or more than 30 mL for massive hematomas), thereby reducing the residual hematoma to less than 15 mL. The mean operative time of entire surgical procedure was 1.3 ± 0.3 h, with very little perioperative blood loss and no perioperative complications. No patients required catheter replacement and all patients’ functional status improved. ConclusionsWithin our clinical practice ROSA-guided ICH aspiration, using our established protocol and workflow, was safe and effective for reducing hematoma volume, with positive functional outcomes.

Leveraging temporal dependency for cross-subject-MI BCIs by contrastive learning and self-attention

Brain-computer interfaces (BCIs) built based on motor imagery paradigm have found extensive utilization in motor rehabilitation and the control of assistive applications. However, traditional MI-BCI systems often exhibit suboptimal classification performance and require significant time for new users to collect subject-specific training data. This limitation diminishes the user-friendliness of BCIs and presents significant challenges in developing effective subject-independent models. In response to these challenges, we propose a novel subject-independent framework for learning temporal dependency for motor imagery BCIs by Contrastive Learning and Self-attention (CLS). In CLS model, we incorporate self-attention mechanism and supervised contrastive learning into a deep neural network to extract important information from electroencephalography (EEG) signals as features. We evaluate the CLS model using two large public datasets encompassing numerous subjects in a subject-independent experiment condition. The results demonstrate that CLS outperforms six baseline algorithms, achieving a mean classification accuracy improvement of 1.3 % and 4.71 % than the best algorithm on the Giga dataset and OpenBMI dataset, respectively. Our findings demonstrate that CLS can effectively learn invariant discriminative features from training data obtained from non-target subjects, thus showcasing its potential for building models for new users without the need for calibration.

Thermally Driven 3D Seamless Textile Actuators for Soft Robotic Applications

Soft wearable robotic devices have emerged as a promising solution for human mobility assistance and rehabilitation, yet current solutions suffer from issues such as bulkiness, high cost, nonscalability, noise, and limited portability. This study introduces a novel approach to soft robotic assistive devices using untethered, soft actuators with seamlessly integrated sensing, heating, and actuation properties through digital machine knitting and low‐boiling liquid. The proposed soft actuator operates under a voltage of less than 12.5 V, generating a tip force of up to 50 mN. This actuator achieves a bending motion when filled with 2 mL of low‐boiling liquid and supplied with 15 W. The dynamic response of the actuator is examined under consistent parameters, revealing a 60‐second inflation time and a subsequent natural cooling period of 30 s at room temperature. Notably, over 12 cycles, the tip force of the actuator exhibits minimal variation, highlighting its durability for prolonged usage. The proposed approach paves the way for overcoming the limitations of existing technologies, particularly in terms of motion assistance and rehabilitation applications, with an emphasis on at‐home usage during daily activities.

Ecofriendly and high-performance flexible pressure sensor derived from natural plant materials for intelligent audible and silent speech recognition

Flexible pressure sensors (FPSs) are widely used in human–computer interaction (HCI) and medical diagnoses, but their further development faces several challenges. Integrating artificial intelligence (AI) with FPSs is indispensable for advancing the cognitive capabilities of HCI systems, but the FPS must also be ecofriendly, cost-effective, and high-performance to meet the demands of environmental protection and sustainable development. Here, a biodegradable capacitive FPS is presented that is fabricated from natural plant materials (i.e., cornstarch and lignocellulose) while exhibiting remarkable attributes such as high sensitivity (2.427 kPa−1 at 0–2 kPa), rapid response/recovery time (20/24 ms), extremely low detection limit (∼10 Pa), outstanding stability (> 6000 fatigue tests), excellent biocompatibility (survival rate exceeding 99 % in cell viability assays), and prominent biodegradability (complete degradation within 24 h). Prepared sensors were integrated with optimized AI algorithms, embedded systems, and wireless transmission technologies to develop a dual-functional (i.e., audible and silent) speech recognition system that achieved recognition rates exceeding 95 %. The developed sensor is expected to play a crucial role in future HCI and medical assistance applications.

A patterned vibrotactile method using envelope modulation with high resolution and low perceptual frequency

The virtual haptics is a crucial aspect of immersive virtual reality, extending the traditional experiences of sight and hearing. The vibration can provide direct normal vibration and friction reduction, making it a promising method to realize virtual haptics. However, the optimum perceptual threshold of skin for vibration is 100 Hz to 500 Hz, resulting in a too low vibrotactile resolution. The conflict between the low perceptual frequency and high resolution still remains challenges. In this paper, a low-frequency envelope wave methodology is proposed to realize the localized vibrotactile feedback. The high-frequency components are modulated into a low-frequency envelope waveform, which provides low-frequency perception and high resolution at the same time. Due to hardware limitations, the modes must be truncated and minimized as much as possible. This requirement conflicts with achieving localized vibration at arbitrary points and further implementing complex vibration patterns. Therefore, a modal optimization algorithm is proposed to solve the inverse problem. The modal participation coefficients is obtained, basing on the evaluation index that ensures the frequency of the envelope wave and the vibration pattern quality. The localized vibration patterns including multiple points, points of proportional amplitude, bar and circle are achieved with a resolution of 3 cm and a perception frequency of about 200 Hz. This method is expected to be applied to virtual reality, blind assistance, and other potential applications to enhance tactile interaction experiences.

Artificial intelligence and assisted reproductive technology: Applying a reproductive justice lens

In recent years, health-data-driven artificial intelligence and machine learning applications have been introduced to many areas of medicine. In the field of assisted reproduction, artificial intelligence and machine learning applications and related technologies have been hailed as (potentially) significant and ground-breaking, not least because they promise standardisation and automation in in-vitro fertilisation clinics – a precondition for scaling up and branching out in the fertility bioindustry. Artificial intelligence data-driven algorithms promise time- and cost-effective selection of ‘high-quality’ reproductive cells and successful personalised treatments. In this essay, we aim to critically discuss artificial intelligence as a technological clinical practice, which is currently moving from bench to bedside internationally. Through an analytic framework of reproductive justice, we propose that introducing artificial intelligence into this already stratified context threatens to black-box health disparities and to generate what we refer to as ‘hyper-stratifications’ of reproduction in the context of rising health and social disparities in the European context. As feminist, social science and bioethics scholars, we are all too aware of how reproductive technologies reinforce normativities rather than unravel them. We cannot presume that artificial intelligence is an ethical technological agent or user of health data but, instead, need to keep a critical eye on the moral ambivalence of emerging and evolving artificial intelligence-assisted reproduction technologies practices and their gendered consequences. Given the current hype around artificial intelligence, but also with concerns around the fast development and deployment of artificial intelligence generally and in artificial intelligence-assisted reproduction technologies particularly in mind, there is an urgent need to engage in critical feminist discussion of such developments.

Enhancement of Students' Writing Skills Through Training in Scientific Article Writing

The aim of this Prodamat activity is to provide scientific article writing training to seventh-semester students majoring in Mathematics Education at Ahmad Dahlan University. The implementation method of this activity includes presentations on various assistant applications in writing scientific articles, practical training in scientific article writing, and evaluation related to the effectiveness of the training on students' motivation in composing scientific articles. The evaluation results indicate that the scientific article writing training is effective, as evidenced by the positive assessments given by participating students. These assessments cover the improvement of scientific article writing skills, better understanding of various assistant applications in scientific article writing, the applicability of the training materials, and the interactive presentation of the content

Mental Health Assistant using Sentiment Analysis through NLP

Given the increasing prevalence of mental health problems and social disruption, quality mental health services are an important issue in today's society. This paper provides a comprehensive understanding of the mental health assistant application proposed. By combining insights from psychology, healthcare, and technology, we identify problems arising from existing systems, including barriers to access, limited affordability, and disparities in supply. The system is an Android platform that allows people seeking mental health care to record and use features such as self-diagnosis, taking mental health tests for various conditions such as Depression, Bipolar Disorder, OCD and Anxiety, analyzing their daily mood , and sharing one-on-one conversations with mental health professionals. This research contributes by providing opportunities for improving mental health services in the future. Key Words: Mental Health, Android, Personality Tests, One-on-one Conversation

Android Legal Assistance Application: Bridging the Gap in Legal Access

The Android Legal Assistance Application represents a significant stride towards democratizing access to legal services through technological innovation. In this paper, we provide a thorough analysis of the application’s function- alities, algorithms, and impact. By leveraging the ubiquity of smartphones and advanced algorithms, our application aims to bridge the gap between individuals and legal resources, empowering users to navigate complex legal land- scapes effectively. Through a comprehensive examination, we elucidate how the application addresses the persistent challenge of unequal access to legal resources, particularly for marginalized communities. By providing tailored legal assistance, recommendations, and access to a vast repository of legal documents, our application strives to promote justice and equality. We delve into the core features of the application, including its legal assistance feature, lawyer recommendation system, and extensive legal document library. Moreover, we discuss the system architecture, tools, and technologies employed in the development process. Through advanced algorithms in natural language processing (NLP) and document analysis, our application delivers accurate and contextually appropriate legal guidance to users. We also present empirical results indicating improved accessibility, enhanced user experience, and positive user feed- back. Finally, we outline future prospects for the application, emphasizing the integration of additional legal services, implementation of robust security measures, and refinement of algorithms. Overall, the Android Legal Assistance Application signifies a paradigm shift in legal access, paving the way for a more inclusive and equitable society.

A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental Interaction.

People with blindness and low vision (pBLV) encounter substantial challenges when it comes to comprehensive scene recognition and precise object identification in unfamiliar environments. Additionally, due to the vision loss, pBLV have difficulty in accessing and identifying potential tripping hazards independently. Previous assistive technologies for the visually impaired often struggle in real-world scenarios due to the need for constant training and lack of robustness, which limits their effectiveness, especially in dynamic and unfamiliar environments, where accurate and efficient perception is crucial. Therefore, we frame our research question in this paper as: How can we assist pBLV in recognizing scenes, identifying objects, and detecting potential tripping hazards in unfamiliar environments, where existing assistive technologies often falter due to their lack of robustness? We hypothesize that by leveraging large pretrained foundation models and prompt engineering, we can create a system that effectively addresses the challenges faced by pBLV in unfamiliar environments. Motivated by the prevalence of large pretrained foundation models, particularly in assistive robotics applications, due to their accurate perception and robust contextual understanding in real-world scenarios induced by extensive pretraining, we present a pioneering approach that leverages foundation models to enhance visual perception for pBLV, offering detailed and comprehensive descriptions of the surrounding environment and providing warnings about potential risks. Specifically, our method begins by leveraging a large-image tagging model (i.e., Recognize Anything Model (RAM)) to identify all common objects present in the captured images. The recognition results and user query are then integrated into a prompt, tailored specifically for pBLV, using prompt engineering. By combining the prompt and input image, a vision-language foundation model (i.e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing environmental objects and scenic landmarks, relevant to the prompt. We evaluate our approach through experiments conducted on both indoor and outdoor datasets. Our results demonstrate that our method can recognize objects accurately and provide insightful descriptions and analysis of the environment for pBLV.

Enhancing Voice Assistants with Generative AI Language Models for Interactive Conversations

This paper presents comprehensive research for the development of a voice assistant application using HTML/CSS, JavaScript, Python, SQLite, and the Hugging Face API. The proposed methodology encompasses key steps in data collection, model training, frontend and backend development, integration, testing, and deployment, ensuring the creation of a robust and user-friendly voice assistant system. By leveraging a combination of web technologies and Al tools, the developed voice assistant application offers an interactive and intelligent user experience across its users. Key Words: Voice assistant, HTML/CSS, JavaScript, Python, SQLite, Hugging Face API, LLMs, AI.

Transforming medical assistance fund application management: A business process reengineering approach

The application process for the Medical Assistance Fund (MAF) to help patients receive medical interventions at public hospitals has been plagued with delays due to the increasing number of applications, inefficient management, and manual tasks. This study aims to redesign the current application process through Business Process Reengineering (BPR) and to evaluate the effectiveness of a new process to be carried out by the Medical Social Work Unit (MSWU). A new methodology, B2Lean which is based on a combination of the BPR and Lean Thinking was proposed to help identify the processes requiring improvement and to remove inefficient ones. A new online application system, the Patient Assistance Management System was proposed as an IT enabler for this BPR initiative. This study was based on a qualitative research methodology involving a case study in which interviews and observations were used to collect data. The sample study consisted of seven MSWU officers and several supporting staff selected from a government hospital. In the interviews, the ‘5W 1H’ technique was used to elicit and analyze their feedback on issues relating to the existing processes. The findings of the analysis revealed that several manual tasks were inefficient, which had to be either removed or replaced, effectively helping to reduce the overall processing time by 52%. With the new and efficient processes, practitioners could certainly expedite patients’ applications for medical assistance, thus helping them to receive prompt medical interventions. The B2Lean methodology could be used as a guideline for organizations seeking improvement in their current practices.