In contemporary education, ensuring classroom accessibility is fundamental to fostering equitable learning opportunities for all students. Despite advancements in inclusive education, students with disabilities continue to encounter substantial barriers that hinder their academic progress. According to the Centers for Disease Control and Prevention (CDC), 24.8% of U.S. adults have a disability, with 12% of graduate students reporting similar challenges [1]. In 2022, approximately 15% of college students disclosed having ADD or ADHD; however, a significant proportion (15-43%) of students who disclose disabilities do not receive necessary accommodations [1][2][3][4]. These statistics underscore the urgent need for a systematic approach to assessing and improving classroom accessibility. To address this challenge, researchers developed a mobile application to audit classroom accessibility. The application incorporates structured questionnaires that evaluate physical classroom accessibility, generating a quantitative accessibility score based on user responses. This score provides data-driven insights into the inclusivity of classroom environments, enabling educational institutions to identify and address accessibility barriers. The application, compatible with both iOS and Android platforms, facilitates real-time feedback collection from students, educators, and staff. This study involves the collection and analysis of real-world physical classroom accessibility data at a Midwestern university using our developed mobile application. Analysis of the accessibility scores reveals significant trends and identifies key areas requiring improvement. The findings indicate that accessible and user-friendly evaluation tools can effectively identify and address physical barriers in classroom environments. Future developments will be directed at incorporating Explainable Artificial Intelligence (XAI) to generate comprehensive reports, providing deeper insights into accessibility challenges for a diverse array of individuals with impairments. This research highlights the potential of technology-driven approaches in capturing firsthand experiences and facilitating substantial improvements in classroom accessibility, ultimately fostering a more inclusive learning environment.

Wheelchair and mobility aid users often face challenges in navigating the built environment due to uneven sidewalks, temporary barriers, steep inclines, and narrow lanes. To assist these users, accessible routing systems have been introduced that generate wheelchair-accessible paths to facilitate navigation in unfamiliar environments. In general, accessible routing systems rely on surface and path characteristics like surface type, incline, width, etc., and crowd-sourced information about barriers to provide the optimal route. Emerging routing systems even provide personalized routing to users that are catered to the user's specific needs and requirements. However, these types of systems collect crowd-sourced personal/identifiable information which introduces privacy and data heterogeneity concerns that are not addressed by them or elsewhere in the concerned domain. To address these two issues specifically, we propose the novel FedAccess system for accessible routing that utilizes the federated learning paradigm for surface recognition using vibration data. The surface-induced vibrations are captured through smartphone-embedded motion sensors (accelerometers and gyroscopes) from 23 manual wheelchair users during their regular navigation. We have covered 10 distinct surfaces from the USA. As a result, the distribution of the data is naturally non-IID. Empirical evaluation shows that the FedAccess system can protect user data and identity while dealing with non-IID data and still recognize heterogeneous surfaces with higher accuracy than the state-of-the-art.

Rehabilitation and disability researchers are increasingly considering utlizing machine learning (ML) algorithms to enhance accessibility for people with disabilities (PwD) as they interact with their environments. PwD often experience environmental barriers in the community and private buildings due to a lack of accessible infrastructure design and prior accessibility information. Such environmental barriers may inhibit PwD from full participation and impede in one’s overall independence and quality of life. The availability of healthcare services and information are essential for increased participation in occupations and optimal independence. In the current era of connected health, information has the ability to be accessed anywhere and providing accessibility content for PwD to use can enhance occupational performance factors. The purpose of this study was to 1) identify existing accessibility measurement challenges and barriers and 2) propose an intelligent accessibility evaluation and assessment for buildings, and 3) leverage mobile applications to address major challenges of accessibility measurement. This research aims to improve the accuracy and reliability of the accessibility measurement using a smarter system.

The nature of the surface has a significant effect on how wheelchair users experience locomotion. The preferred surfaces for wheeled mobility must be even, firm and smooth while generating adequate friction. The development of accessible road maps that include ground conditions is therefore of utmost importance. Our prior work has shown how such maps can be created using surface-induced vibration data collected by motion sensors embedded in smartphones and then classifying them with machine learning algorithms. To make data collection scalable, participatory crowd-sensing can be used, where users collect and transmit sensor data while traveling on wheelchairs. The complexity here is that wheelchairs widely vary in type (manual, power-assist, power), weight, number and nature of wheels, therefore the sensor data generated by different wheelchairs varies greatly. Collecting training data on each individual wheelchair type to develop classification models is not feasible. To address this problem, in this paper we explore the possibility of transferring knowledge from known wheelchairs to unknown types. We develop a transfer learning algorithm to classify 15 surfaces with minimal training data from different wheelchairs. Our experiments with 47 subjects show that surface classification knowledge, learned from sensor data generated by manual wheelchairs, can be transferred to a power wheelchair with up to 90.02% accuracy. This allows crowd-sensing to be used effectively for data collection for generating accessible route maps. We integrate our transfer learning approach into our system for accessible routing, which we developed in previous work.

The Americans with Disabilities Act (ADA) is a civil rights law that was signed into law in 1992 by President George H.W. Bush. The law requires wheelchair access be made available for buildings built after 1992. Buildings under the law include retail stores, hotels, banks and most other public buildings. However, there are a large percentage of buildings built before 1992 that are not wheelchair accessible. In addition, ADA does not require the location of ramp to be at the front of the building. This is an inconvenience for individuals who use wheelchairs to access a building, as a) the building may not have a ramp or b) they may have to roll around the building to where the ramp may be located. Hence, in this paper, we describe a prototype artificial intelligent system, which takes the input of a building image, and produces the output prediction for whether the building has a ramp. The system uses a deep learning technique, convolution neural network (CNN) to classify building images. We evaluated our method on a sample dataset of building images that we collected and building images from online sources. Training and validation accuracies were very high, 98.9 and 95.6 percentages respectively.

The aim of this paper is to present a multisensory system that studies abnormal walking patterns to prevent a fall. Due to the growing elderly population, scientific research on smartphone-based gait detection systems has recently become an imperative component in decreasing elderly injuries due to falls. To address the issue of smart gait detection, we propose a gait classification system using smartshoe sensor data in this paper. We used shoe-worn pressure sensors on the foot and validated algorithms to extract the gait parameters during walking trials in a lab environment. This smartshoe contains four pressure sensors with a Wi-Fi communication module to unobtrusively collect data. To the best of our knowledge, this is the first system which can automatically detect abnormalities in walking patterns. A unique signal classification approach is presented by recognizing the abnormality in a subject's gait, and modeling the dynamics of a system as they are captured in a reconstructed phase space. Based on our experiments, we have found an 89% walking-based classification accuracy to help prevent falls.

Nowadays with the dispersion of wireless networks, smartphones and diverse related services, different localization techniques have been developed. Global Positioning System (GPS) has a high rate of accuracy for outdoor localization but the signal is not available inside of buildings. Also other existing methods for indoor localization have low accuracy. In addition, they use fixed infrastructure support. In this paper, we present a novel system for indoor localization, which also works well outside. We have developed a mathematical model for estimating location (distance and direction) of a mobile device using wireless technology. Our experimental results on Smartphones (Android and iOS) show good accuracy (an error less than 2.5 meters). We have also used our developed system in asset tracking and complex activity recognition.

The Americans With Disabilities Act (ADA) and other accessibility standards specify the requirements for assessing the architectural barriers for the built environment. And, the ADA -- Compliance Assessment Toolkit (ADACAT)provides simple pass-fail assessments of those requirements. Measurement Kit is the principal component of the ADACAT, which consists of various measuring instruments like, measuring tape, sound-level meter, light-level meter, magic slope block, etc. In this essay, we show that most of the instruments in the Measurement Kit can be effectively implemented as a software application on a smartphone equipped with sensors like, accelerometer, gyroscope, and microphone. Detailed algorithms have been presented and the experimental results show that an iPhone or iPod Touch 4:0 application can serve as measuring tape, sound-level meter, as well as slope meter, making the ADACAT both cheaper and more portable.

Engineers and other designers commonly use specifications to frame a project's objectives and constraints. These are supplemented by standards, codes, and regulations to create the design package. However, typical design practices often inadvertently ignore the usefulness of the product, environment or information system by people for whom the product would benefit. Consequently, an early design does not work and requires additional iterations and phases of redesign. This drives up the design costs, delays the process, or by tradeoff, prevents individuals with various types of abilities and disabilities to use the design. The universal design approach offers an efficient cost-effective method to expand the population of potential consumers of a product design. Quality of life technologies demand designs that consider populations that are often missed. This paper defines the need for and characteristics of good universal design with illustrations of successful universal product design as well as erred designs that neglected significant populations of potential product users. By definition, quality of life technologies are inclusive, such as aging populations who function with impairments in vision, hearing, and motor abilities. Executing universal design strategies create more successful outcomes.