Assistive Technology Applications Research Articles

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

Supplementation of SkQ1 Increases Mouse In Vitro Oocyte Maturation and Subsequent Embryonic Development by Reducing Oxidative Stress.

In vitro oocyte maturation (IVM) technology is important for assisted animal and human reproduction. However, the maturation rates and developmental potential of in vitro-matured oocytes are usually lower than those of in vivo-matured oocytes. Oxidative stress is a main factor that causes the lower maturation rates and quality of in vitro-matured oocytes. The purpose of this study was to investigate the effects of treatment with SkQ1, a mitochondria-targeted antioxidant, on mouse IVM and subsequent embryonic development. The results demonstrated that the supplementation of SkQ1 during IVM improves the maturation rates of mouse oocytes and the subsequent developmental competence of in vitro-fertilized embryos. The addition of SkQ1 to the IVM medium also decreased oxidative stress and apoptosis, and increased mitochondrial membrane potential in matured mouse oocytes. This study provides a new method through which to enhance the maturation rates and the quality of in vitro-matured mouse oocytes, thus promoting the application and development of assisted animal and human reproductive technology.

A Comprehensive Framework for Face age Synthesis, Voice Transformation, and Cartoon Generation

This paper presents a comprehensive framework addressing age-invariant face recognition (AIFR), face age synthesis (FAS), voice transformation, and avatar generation. Traditional AIFR techniques focus on minimizing age-related variations in face recognition but lack visual interpretability, while FAS methods aim to synthesize faces of different ages but often compromise recognition due to artifacts. To address these limitations, we propose MTLFace, a multi-task learning framework that simultaneously handles AIFR and FAS tasks. MTLFace employs attention-based feature decomposition to separate identity and age-related features spatially, improving interpretability. Additionally, we introduce an identity conditional module for fine-grained face age synthesis, enhancing the naturalness of synthesized faces. Unlike conventional methods that achieve age group-level synthesis, our identity conditional module enables identity-level synthesis, resulting in smoother age transitions and preserving individual facial characteristics. Leveraging high-quality synthesized faces, we enhance AIFR performance via selective fine-tuning, where synthesized faces are used to augment training data, leading to improved robustness against age variations. Furthermore, we contribute a large cross-age face dataset with annotations, facilitating research in age-related tasks. In addition to AIFR and FAS, we explore limitations in existing methodologies for voice transformation and propose advancements to improve speech quality and address current challenges. Lastly, we introduce a novel approach for cartoon face generation, utilizing component-based facial feature extraction and template matching to produce diverse and stylistic cartoon faces. Experimental results across various benchmarks demonstrate the effectiveness of our approaches in achieving superior performance in face recognition, voice transformation, and cartoon face generation, thereby contributing to the advancement of multimodal synthesis technologies with potential applications in entertainment, virtual communication, and assistive technologies

Tecnologia Assistiva na Educação

This article proposes a contemporary analysis of Assistive Technology in Education and its direct relationship with the promotion of a culture of inclusion in schools. The methodological paths followed were those of the bibliographic review analysis; analysis of the contemporary social fact and also, with interviews with experts who work in innovation projects and assistive technology. We sought to bring up a contextualization of the social fact related to the Brazilian school context about the use and application of Assistive Technology in Specialized Educational Assistance (AEE) in Brazilian public schools, as well as to analyze data and information from the Brazilian Institute of Geography and Statistics (IBGE) which, through the census, analyzes the social context of people with disabilities, high abilities/giftedness and singularities. In this eagerness, the article discusses through academic analyzes in order to try to understand some paradoxes that are installed in the convergence of information. Through an academic perspective, the investigations were of the most elementary concepts about Assistive Technology, as well as brought up social and pedagogical issues and also presents the technology called Colibri, which presents itself as an alternative to break with existing obstacles to a digital and social inclusion of people with disabilities in Brazil.

TECNOLOGIA ASSISTIVA NA EDUCAÇÃO

This article proposes a contemporary analysis of Assistive Technology in Education and its direct relationship with the promotion of a culture of inclusion in schools. The methodological paths followed were those of the bibliographic review analysis; analysis of the contemporary social fact and also, with interviews with experts who work in innovation projects and assistive technology. We sought to bring up a contextualization of the social fact related to the Brazilian school context about the use and application of Assistive Technology in Specialized Educational Assistance (AEE) in Brazilian public schools, as well as to analyze data and information from the Brazilian Institute of Geography and Statistics (IBGE) which, through the census, analyzes the social context of people with disabilities, high abilities/giftedness and singularities. In this eagerness, the article discusses through academic analyzes in order to try to understand some paradoxes that are installed in the convergence of information. Through an academic perspective, the investigations were of the most elementary concepts about Assistive Technology, as well as brought up social and pedagogical issues and also presents the technology called Colibri, which presents itself as an alternative to break with existing obstacles to a digital and social inclusion of people with disabilities in Brazil.

Ultrasound evaluation of the cardiovascular system in offspring conceived through assisted reproductive technology.

With the widespread application of assisted reproductive technology, the health issues of offspring conceived through assisted reproductive technology have also received increasing attention. Animal experiments and clinical studies have found subclinical adverse changes in the cardiovascular system of assisted reproductive offspring. Assisted reproductive technology itself may be just one of the many factors contributing to this phenomenon, with epigenetics playing an important role. Ultrasound technology can be used to assess the morphological structure and function of the cardiovascular system in assisted reproductive offspring from the fetal stage, providing the possibility to study the potential cardiovascular damage in this large population. This review aims to explore the effects and mechanisms of assisted reproductive technology on the cardiovascular system of offspring and provide a review of the research progress in ultrasound technology in this area.

Internet of things (IoT)-based assistive system for patients with spinal muscular atrophy (SMA): a case report

Purpose Assistive technologies based on IoT can contribute to improve quality of living of patients with severe motor difficulties by providing partial or total independence. The aim of this work was to analyse the usability and performance of an assistive system based on the IoT when is evaluated by a child patient with spinal muscular atrophy type 1 (SMA-I). Materials and methods The study involved a child with SMA-I and his caregiver. The materials used include an M5Stack Core2 kit, a mobile app, and a smart switch based on the ESP-01S card. The patient sends requests to the caregiver from the app installed on the M5Stack Core2 to a mobile app, and controls smart switches located in the rooms. The system was tested by the participants for a period of 30 days to later evaluate its usability and performance. Results The results show that the control function of smart switches is the most used and there is no decrease in interactions over the days for the system in general. In addition, the scores obtained from both usability tests (patient and caregiver) were 87.5% and 90%, respectively. The average performance of the entire system was 93.33%. Conclusion The application of assistive technologies based on the IoT allows obtaining a practical solution that improves the development of daily activities in a patient with SMA-I.

Advanced Electrode Technologies for Noninvasive Brain-Computer Interfaces.

Brain-computer interfaces (BCIs) have garnered significant attention in recent years due to their potential applications in medical, assistive, and communication technologies. Building on this, noninvasive BCIs stand out as they provide a safe and user-friendly method for interacting with the human brain. In this work, we provide a comprehensive overview of the latest developments and advancements in material, design, and application of noninvasive BCIs electrode technology. We also explore the challenges and limitations currently faced by noninvasive BCI electrode technology and sketch out the technological roadmap from three dimensions: Materials and Design; Performances; Mode and Function. We aim to unite research efforts within the field of noninvasive BCI electrode technology, focusing on the consolidation of shared goals and fostering integrated development strategies among a diverse array of multidisciplinary researchers.

Cognitive Robotics: Integrating Artificial Intelligence and Embodied Intelligence for Advanced Problem Solving

Artificial intelligence (AI) and embodied intelligence are combined in cognitive robotics, which marks a paradigm change in highly developed problem-solving skills. This study offers a comprehensive review of the theoretical underpinnings, practical difficulties, practical applications, and moral implications of cognitive robots. The study explores machine learning methods, natural language processing tools, and computer vision technologies after introducing the fundamental concepts. It clarifies embodied intelligence further by emphasizing the important roles that sensory data fusion, robotic actuation, and adaptive behaviours play in the cognitive capabilities of robots. The study then moves on to discuss cognitive robotics' integration difficulties, including issues in sensory data fusion, cognitive dissonance in AI-driven robotics, and human-robot interaction. Applications in autonomous cars, healthcare, manufacturing, and assistive technologies demonstrate how cognitive robotics is transforming many different industries. The ethical obligations involved in the creation and use of cognitive robotic systems are highlighted, along with ethical issues relating to employment, privacy, and ethical AI practises. In-depth analysis is done of the present and foreseeable difficulties in cognitive robotics. Along with cognitive difficulties like contextual comprehension and moral conundrums, technical obstacles linked to sensor limits and processing restrictions are also studied. The study highlights cutting-edge research projects and multidisciplinary partnerships that provide answers to these problems, paving the path for the development of cognitive robots in the future. The article envisions a future where cognitive robots would play a part in space exploration, disaster response, and personalised robotics. It also surveys integration possibilities with cutting-edge technologies like augmented reality and the Internet of Things. The study summarises the key findings and presents the implications for future research, and emphasises the important part cognitive robotics plays in resolving difficult issues. To ensure that cognitive robots continue to have an impact on a future that is smarter, more connected, and understanding, ethical issues, multidisciplinary collaboration, and responsible development practises are necessary.

Assistive Self-Driving Car Networks to Provide Safe Road Ecosystems for Disabled Road Users

Disabled pedestrians are among the most vulnerable groups in road traffic. Using technology to assist this vulnerable group could be instrumental in reducing the mobility challenges they face daily. On the one hand, the automotive industry is focusing its efforts on car automation. On the other hand, in recent years, assistive technology has been promoted as a tool for consolidating the functional independence of people with disabilities. However, the success of these technologies depends on how well they help self-driving cars interact with disabled pedestrians. This paper proposes an architecture to facilitate interaction between disabled pedestrians and self-driving cars based on deep learning and 802.11p wireless technology. Through the application of assistive technology, we can locate the pedestrian with a disability within the road traffic ecosystem, and we define a set of functionalities for the identification of hand gestures of people with disabilities. These functions enable pedestrians with disabilities to express their intentions, improving their confidence and safety level in tasks within the road ecosystem, such as crossing the street.

Transcriptome analyses reveal transcriptional profiles of horse oocytes before and after in vitro maturation.

Oocyte in vitro maturation is necessary for the study and application of animal-assisted reproduction technology in animal reproduction and breeding. The comprehensive transcriptional profile of equine oocyte maturated in vitro has not been fully mined yet, which makes many key transcriptional events still unidentified. Here, Smart-seq2 was performed to analyse the gene expression pattern and the underlying regulatory mechanism of horse germinal vesicle (GV) and in vitro metaphase II (MII) oocytes. The results showed that 6402 genes (2640 up-regulated and 3762 down-regulated in MII samples compared to GV) and 4021 lncRNA transcripts (1210 up-regulated and 2811 down-regulated in MII samples compared to GV) were differentially expressed in GV and MII oocytes. Further, GO and KEGG analysis found that differentially expressed mRNAs and lncRNAs were mainly enriched in the pathways related to energy and lipid metabolism. In addition, LGALS3 was found a key gene in mediating the regulation of oocyte meiosis recovery and fertilization ability. This study provides novel knowledge about gene expression and energy metabolism during equine oocyte maturation and a reference for the further study and application of assisted reproductive technology in horse reproduction and breeding.

Evaluation of the Effectiveness of Assistive Technology for Executive Function Support for People With Acquired Brain Injury: Protocol for Single-Case Experimental Designs.

Executive function, including prospective memory, initiating, planning, and sequencing everyday activities, is frequently affected by acquired brain injury (ABI). Executive dysfunction necessitates the use of compensatory cognitive strategies and, in more severe cases, human support over time. To compensate for the executive dysfunction experienced, growing options for electronic mainstream and assistive technologies may be used by people with ABI and their supporters. We outline the study protocol for a series of single-case experimental designs (SCEDs) to evaluate the effectiveness of smart home, mobile, and/or wearable technologies in reducing executive function difficulties following ABI. Up to 10 adults with ABI who experience executive dysfunction and have sufficient cognitive capacity to provide informed consent will be recruited across Victoria and New South Wales, Australia. Other key inclusion criteria are that they have substantial support needs for everyday living and reside in community dwellings. On the basis of the participant's identified goal(s) and target behavior(s), a specific electronic assistive technology will be selected for application. Both identification of the target behavior(s) and selection of the assistive technology will be determined via consultation with each participant (and their key support person, if applicable). The choice of SCED will be individualized for each participant based on the type of technology used in the intervention, the difficulty level of the behavior targeted for change, and the anticipated rate of change. For each SCED, repeated measurements of the target behavior(s) during the baseline condition will provide performance data for comparison with the performance data collected during the intervention condition (with technology introduced). Secondary outcome measures will evaluate the impact of the intervention. The protocol includes 2 customizable Microsoft Excel spreadsheets for electronic record keeping. Recruitment period is June 2022 through March 2024. Trial results for the individual participants will be graphed and analyzed separately using structured visual analysis supplemented with statistical analysis. Analysis will focus on important features of the data, including both within- and between-phase comparisons for response level, trend, variability, immediacy, consistency, and overlap. An exploratory economic evaluation will determine the impact on formal and informal support usage, together with quality of life, following the implementation of the new technological intervention. The study has been designed to test the cause-effect functional relationships between the intervention-in this case, electronic assistive technology-and its effect in changing the target behavior(s). The evaluation evidence gained will offer new insights into the application of various electronic assistive technologies for people who experience executive dysfunction following ABI. Furthermore, the results will help increase the capacity of key stakeholders to harness the potential of technology to build independence and reduce the cost of care for this population. Australian New Zealand Clinical Trials Registry (ANZCTR) ACTRN12622000835741, https://www.anzctr.org.au/ACTRN12622000835741.aspx. DERR1-10.2196/48503.

TEKNOLOGI ASISTIF SEBAGAI MEDIA PEMBELAJARAN BAHASA INDONESIA SISWA BERKEBUTUHAN KHUSUS

Assistive technology is a special device that consists of a set of technologies tailored to the individual needs of students. This technology can be used by Indonesian language teachers to provide access for students in inclusive classrooms. The implementation of assistive technology is expected to be beneficial in improving students' abilities in learning Indonesian language. Assistive technology can help students with special needs to actively participate in learning, including receiving materials, engaging in the learning process, and evaluation. Based on the literature review, the application of assistive technology in teaching Indonesian language to students with special needs will be effective if done through a systematic process. Starting from preparation, model, framework, implementation, and evaluation. Assistive technology provides accessibility for students, making it easier for them to acquire knowledge in the Indonesian language. Furthermore, assistive technology can assist students with special needs to work independently, enhance learning motivation, and feel equal rights as regular students.

Real Time Human Body Posture Analysis Using Deep Learning

Abstract: We present a novel approach for accurately estimating the pose of objects in a low-cost and resource-efficient manner, making it suitable for deployment on embedded systems. Our algorithm comprises of two primary stages: object detection and spatial reconstruction. In the first stage, we employ a Convolutional Neural Network (CNN) called PoseNet for object detection. This approach has proven to be effective in detecting and localizing objects in an image. Next, utilizing stereo correspondences, we 3D reconstruct the spatial coordinates of multiple ORB features within the object's bounding box. This enables us to accurately estimate the position of the object in space. To calculate the final position of the object, we compute a weighted average of the stereo-corresponded key points' spatial coordinates. The weights are proportional to the level of ORB stereo matching, which enables us to obtain a more accurate estimate of the object's position in space. Our algorithm was tested in a calibrated environment, and we compared the results with a deep learning-based method using various datasets. The results show that our approach outperforms existing methods in terms of accuracy, while maintaining a low cost and efficient resource utilization. Our proposed method has several applications, including the quantitative and qualitative analysis of human posture. By analyzing all aspects of a person's posture, we can determine if there are any postural deviations, imbalances, or muscle weaknesses that may be causing pain or discomfort. This information can then be used to develop personalized rehabilitation programs, reducing the risk of injury and enhancing athletic performance. Furthermore, our approach can be used in various assistive technology applications, such as the control of robotic arms for pick-andplace tasks. The low-cost and resource-efficient nature of our algorithm make it ideal for deployment in embedded systems, enabling us to develop affordable and accessible assistive technology solutions. In conclusion, our proposed algorithm provides an accurate, low-cost, and resource-efficient solution for pose estimation, with a wide range of potential applications in human posture analysis, assistive technology, and beyond.

A Design of Assistive Technology Application for Visually Disabled Elderly Citizens

A Design of Assistive Technology Application for Visually Disabled Elderly Citizens

3D Printed Energy Return Elements for Upper Limb Sports Prosthetics

Prosthetics are an extension of the human body and must provide functionality similar to that of a non-disabled individual to be effective. Sports prosthetics such as the Flex-Foot Cheetah from Össur have demonstrated the value of creating devices that both provide mechanical support and introduce passive energy return to mimic forces otherwise produced at joints. These energy return mechanisms have not yet been demonstrated for upper limb prosthetics but could improve their effectiveness and provide a greater range of motion and control. Using multi-material 3D printing technology, we extend energy return components to upper limb prosthetics by developing novel force-sensing springs and applying them to a basketball prosthetic. The 3D-printed springs compensate for the forces otherwise generated by wrist and finger flexion while measuring the mechanical deflection. We discuss design guidelines, methods for integrated 3D printed energy return within prosthetics, and broader applications in assistive technologies.

Stavovi, motivacija i kompetencije defektologa za upotrebu asistivne tehnologije u nastavi

People with intellectual disabilities exhibit difficulties in all domains of functioning that can be overcome with the use of assistive technology. The objective was to examine the attitudes of special education teachers towards the use of assistive technology, their motivation for its application and their perception of competence. The sample comprised of 62 special education teachers working in different institutions, and instruments were used to measure attitudes towards the use of assistive technology, motivation for its use and self-percieved level of competencies. Majority of special education teachers have positive attitudes towards the use of assistive technology, a high degree of motivation and consider themselves competent in its use. Special education teachers who use assistive technology every day have more positive attitudes, greater motivation and consider themselves more competent. Those who work in institutions occupied by younger population have more positive attitudes and believe that they are more competent in the application of assistive technology, compared to respondents who work in institutions occupied by older people with intellectual disabilities. With the increase of age, the attitudes toward the use of assistive technology become more negative, but the self-perception of competence decreases. Special education teachers who have more positive attitudes towards the use of assistive technology have a higher degree of motivation for its application and believe they are more competent. After the implementation of trainings that have a direct impact on increasing the competence in the field of assistive technology, attitudes towards its use can be improved and motivation for its daily use can increase.

‘The plural of silo is not ecosystem’: Qualitative study on the role of innovation ecosystems in supporting ‘Internet of Things’ applications in health and care

Background Internet of Things (IoT) innovations such as wearables and sensors promise improved health outcomes and service efficiencies. Yet, most applications remain experimental with little routine use in health and care settings. We sought to examine the multiple interacting influences on IoT implementation, spread and scale-up, including the role of regional innovation ‘ecosystems’ and the impact of the COVID-19 context. Methods Qualitative study involving 20 participants with clinical, entrepreneurial and broader innovation experience in 18 in-depth interviews, focusing primarily on heart monitoring and assistive technology applications. Data analysis was informed by the NASSS (non-adoption, abandonment, scale-up, spread, sustainability) framework. Results Interviewees discussed multiple tensions and trade-offs, including lack of organisational capacity for routine IoT use, limited ability to receive and interpret data, complex procurement and governance processes, and risk of health disparities and inequalities without system support and funding. Although the pandemic highlighted opportunities for IoT use, it was unclear whether these would be sustained, with framings of innovation as ‘disruption’ coming at odds with immediate needs in healthcare settings. Even in an ‘ecosystem’ with strong presence of academic and research institutions, support was viewed as limited, with impressions of siloed working, conflicting agendas, fragmentation and lack of collaboration opportunities. Conclusions IoT development, implementation and roll-out require support from multiple ecosystem actors to be able to articulate a value proposition beyond experimental or small-scale applications. In contexts where clinical, academic and commercial worlds collide, sustained effort is needed to align needs, priorities and motives, and to strengthen potential for good value IoT innovation.

Digital privacy of smartphone camera-based assistive technology for users with visual disabilities

Smartphone users with visual disabilities often use camera-based assistive technology applications such as Seeing AI, BeMyEyes, and TapTapSee apps in identifying people and objects. As personal information could be shared, digital privacy issues are critical to those with visual disabilities. However, little is known about user perspectives on digital privacy issues - e.g., the degree to which those with visual disabilities understand user privacy policies and the degree to which they intend to adopt those apps. To address the knowledge gap, this study conducted interviews with a convenience sample of 30 participants with visual disabilities. The results indicate that those with visual disabilities had a lack of knowledge about privacy policies and potential risks of privacy and security breaches of personal information. The results contributed to forming a conceptual framework that contains a list of facilitators and barriers to user adoption, which could serve as a knowledge foundation for many other researchers and professionals to support and enhance users' privacy awareness, accessible to users with visual disabilities.

Ensino de tecnologia assistiva nos cursos de graduação em terapia ocupacional do Estado de São Paulo

Abstract Introduction Knowledge about assistive technology is related to aspects of the field of occupational therapy, thus, it is questioned whether such knowledge has been addressed in undergraduate courses. Objectives To identify the undergraduate courses in occupational therapy in the state of São Paulo that offer disciplines related to assistive technology, identify the disciplines, their respective workloads and the content present in each of them. Method The sample consisted of eight universities, five public and three private. The search was made in the curricular matrices, teaching plans of specific and non-specific disciplines, objectives and contents available online or requested from the course coordinator. Descriptive data analysis was performed. Results It was found that assistive technology content was offered in the investigated universities, with a difference between the workload and the content offered. The analysis by assistive technology application area showed that the content on orthoses is offered in 100% of the analyzed courses, followed by assistive products for the performance of daily activities and prostheses, both contents found in 75% of the courses; mobility equipment; accessibility and universal design in 62.5%; alternative communication in 50% of the courses. Conclusion The results point to the relevance of greater homogeneity of content between the investigated universities and suggest that this study has the potential to foster discussions about the formation of occupational therapists in the assistive technology area, since the results come from the analysis of undergraduate courses located in the state which has the largest number of occupational therapy courses in Brazil.