Mobile phones as assistive technology

Abstract

Background

Modern assistive technologies use mobile devices, such as smartphones, to increase accessibility for people with special needs. These devices integrate a variety of technological solutions to provide real-time assistance with communication, navigation, and daily activities.

Objective

Demonstrating the leading role of smartphones as portable universal assistive technologies.

Methods

Overview of solutions integrated into mobile devices, implemented in their software and connected as peripherals.

Results

The very high usability of mobile assistive technologies has been shown for people with various disabilities.

Conclusions

The rapid development of AI is contributing to the increased use of mobile devices as assistive technology. As AI becomes more advanced, mobile devices will play an even greater role in providing accessibility for people with disabilities.

Keywords

mobile devices smartphones assistive technology accessibility

Introduction

Mobile technology has been changing the way people communicate, work, and live for a long time. With the development of smartphones and other mobile devices, technology has begun to play a key role in supporting people with different types of disabilities and older people. Mobile phones, originally designed simply for communication, have evolved into universal devices that offer a wide range of functions that can be customized to meet the needs of the individual user.

From the first pagers and simple mobile devices to current highly sophisticated smartphones with their software, the history of mobile phones as assistive technologies reflects the evolution of thinking about inclusivity and accessibility. This article looks at how these technologies have evolved over the years, what innovations they have introduced, and the impact they have had on the lives of people with disabilities and those around them.

The aim of the article, which takes the form of a narrative literature review, is not only to present the historical aspects of mobile technologies but also to outline their potential as assistive tools that contribute to building a more accessible world.

The beginnings of wireless phones

Mobile telephony has come a long way from its beginnings in the 1980s to the smartphone era in the first decade of the 21st century. During this period, technology has evolved from large analog devices designed primarily for voice calls to more advanced digital phones that offer text messaging, basic internet functions, and the first mobile applications.

The 1980s were the era of analog telephony (1G). The first commercial mobile telephone networks were launched in the early 1980s in the USA, Scandinavia, and Great Britain. 1G systems (first generation) were based on analog voice transmission and did not offer data transmission. The phones were large, heavy, and expensive. Due to the high costs, this technology was available mainly to businessmen and emergency services. However, even then it was possible to indicate some basic assistance functions offered by 1G phones. First, it was mobility, allowing for contact outside of a landline phone. A major advantage from the point of view of accessibility were also large physical keys and LED screens, making it easier to use for people with vision problems.

The 1990s were a time of digital revolution and the development of mobile telephony (2G). At that time, second-generation (2G) networks based on the Global System for Mobile Communications (GSM) standard were introduced. Digital transmission improved the quality of calls, increased network capacity, and introduced the ability to use Short Message Service (SMS). SMS has become a key assistive function for deaf and hard-of-hearing people, enabling them to communicate without the mediation of voice calls. The miniaturization of technology made phones smaller, lighter, and more affordable. In addition, their configurations already allowed for simple personalization, such as the ability to change the fonts and contrast of the screens and to associate polyphonic ringtones with contacts. As an alternative to ringtones for the deaf, the device could be set to vibrate.

The early 2000s was the time of ‘semi-intelligent’ mobile phones. 2.5 G networks: General Packet Radio Service (GPRS) and Enhanced Data rates for GSM Evolution (EDGE), were introduced, allowing faster data transmission. In 2001, 3G networks were developed, allowing video calls and mobile internet in a more advanced form. Phones began to resemble primitive smartphones, as devices with color screens and more advanced operating systems (Symbian, Windows Mobile) were produced. The potential in the area of assistive technology has already been seen in mobile phones.¹ Assistive features such as hearing aid compatibility or simple speech synthesizers and primitive speech recognition functions have been incorporated into some of them. Then came the era of smartphones.

Key mobile technologies supporting accessibility in smartphones

Speech recognition and voice assistants

Speech recognition technology enables computers and smartphones to convert spoken language into text, allowing hands-free interactions. Voice assistants such as Siri, Google Assistant, and Alexa leverage advanced Automatic Speech Recognition (ASR) and Natural Language Processing (NLP) to understand user commands. Rapid improvements in machine learning (ML), deep learning, and artificial intelligence (AI)-driven voice models have made voice assistants an integral part of smartphones, smart homes, healthcare applications, and assistive technology for people with disabilities. In smartphones, it is implemented in assistants such as Siri (Apple), Google Assistant, Alexa (Amazon), or Cortana (Microsoft).² The voice assistant mechanism works in the following steps:

(1) Audio capture: The microphone records the user’s voice.

(2) Signal processing: AI and ML algorithms process speech.

(3) Speech-to-text conversion: ASR models transcribe spoken words into text.

(4) Intent recognition: NLP determines the user’s request.

(5) Execution of the command: The assistant answers or performs an action.

Voice assistant applications find applications for people with disabilities primarily as interaction aids.³ This interaction can be related to voice control for the Internet of Things (IoT) systems in smart homes,^4,5 automating daily tasks such as setting alarms, remindings, and searching for information or healthcare.⁶ Smartphone voice assistants are a key component of modern assistive technology and continue to evolve rapidly. Certain issues in speech recognition still present challenges. These include, for example, the correct recognition of accents, dialects, dysphonic voices,^7,8 or the ensuring privacy and the secure storage of user voice data.⁹

Future research directions include improving personalization in voice assistants,¹⁰ enhancing AI algorithms for more accurate transcription,^11,12 and developing advanced biometric voice authentication.^13,14

Image recognition and visual translation

Image recognition and visual translation technologies in smartphones have advanced significantly in recent years, driven by AI, ML, and optical character recognition (OCR). These technologies allow smartphones to analyze images, identify objects, extract text, and translate visual content into different languages or formats in real time. The rise of mobile computing, cloud-based AI, and edge processing has enabled smartphones to perform complex image analysis and translation tasks with remarkable accuracy. ML models trained on large datasets can now recognize objects, detect text, and interpret scenes with human-like precision. A key technology used in this area is AI and neural networks. Image recognition is based on convolutional neural networks (CNNs), which are specifically designed for image analysis. These networks learn to recognize patterns in pixels and classify images based on previous data. Smartphone software uses dedicated algorithms for fast real-time object detection. The base You Only Look Once (YOLO)¹⁵ model processes images at a speed of 45 frames per second, while its smaller variant, Fast YOLO, reaches up to 155 frames per second, outperforming other real-time object detection systems. Another algorithm—MobileNet¹⁶—uses the technique of depth-wise separable convolutions to significantly reduce the number of parameters and computational operations compared to standard convolutions, resulting in lighter and faster models. The recognition of text in images can be used with Tesseract OCR, which compared to other OCR solutions, Tesseract offers high recognition accuracy due to its advanced methods of character segmentation and classification.¹⁷

Main application areas include assisting the blind (applications convert images into sound, voice description, or Braille text), real-time translation of texts from foreign languages using smartphone cameras, object and face recognition used in security (Face ID), e-commerce and health applications, augmented reality (AR), and improving interaction with the environment using smartphone cameras.

Despite the increasing miniaturization and computing power of smartphones, image recognition and visual translation systems encounter several challenges. OCR technology in mobile applications still faces limitations related to complex fonts, poor image quality, and varying lighting conditions. Enhancing OCR accuracy requires models based on deep learning, improved pre-processing techniques, and optimized hardware processing.¹⁸ It should not be forgotten that certain hardware requirements, including powerful mobile processors, dedicated AI accelerators (NPUs), high-resolution image sensors, and optimized power management systems, are required to ensure effective real-time image recognition on smartphones.¹⁹ Furthermore, the growing use of smartphone cameras for image recognition, biometric authentication, and AI-powered analysis raises concerns about data privacy, security risks, and unauthorized data collection.²⁰ The authors pay particular attention to the fact that many applications request access to features such as cameras, microphones, or biometric data, which can lead to unauthorized data collection and privacy breaches.

Advances in the area of edge computing and the increase in data transfer speeds with the reduction in latency with 5G technology will allow for even faster and more accurate image processing. In the future, we can expect advances in the fields of better integration of AR with visual translation, automatic creation of image descriptions for blind people, and advanced chatbots translating multimedia content in real time.

Haptic interfaces and tactile feedback

One of the key components of haptic feedback in a smartphone is the linear resonant actuator (LRA) or eccentric rotating mass (ERM) motor, which generates vibrations in response to touch interactions. Advanced haptic systems, such as those found in flagship smartphones, can produce multi-level, localized vibration feedback, allowing users to distinguish between different interactions based on the feel of the vibration.

The built-in vibration function allows for the design of haptic interfaces on smartphones for various applications. Adaptive haptic feedback in smartphones can be used in medical and therapeutic applications. For example, a smartphone-based haptic system can provide personalized vibration in real time to help people with hand tremor. This system adapts to the severity of the tremor, offering personalized feedback to improve motor control.²¹ Another study focuses on haptic systems for the blind. This technology enables the recognition of the environment using haptic feedback sent by smartphones. It can be used for an indoor Moat navigation system in buildings.²² The Moat system achieved high accuracy (up to 95.6%) in four different homes by monitoring 21 commercial IoT devices. Thanks to its adaptive mechanism, the Moat maintains high effectiveness even after changes in the home environment, such as rearranging furniture.

Built-in sensors

Smartphones have evolved from simple communication devices to sophisticated personalized analytical tools equipped with numerous sensors. From basic accelerometers used for screen orientation to the most advanced biomedical sensors to monitor a user’s health, the development of these technologies has had a key impact on human interaction with mobile phones.

Touch sensor

The primary sensor of any smartphone is the touch sensor in the form of a touchscreen. Touch screens have revolutionized the accessibility of smartphones, serving as the main interface for interaction. As a multimodal sensor, the touchscreen detects touch pressure, gestures, and multiple points of contact, enabling various assistive technologies. Using capacitive touch technology, smartphones dynamically adapt interfaces, augment content, and enable alternative methods of interaction, making them versatile assistive tools for people with disabilities. For visually impaired users who use the screen reader function, the touchscreen enables gesture navigation in the device’s graphical user environment via voice feedback.²³ Adaptable gestures and adaptive interfaces support users with motor dysfunction with one-handed mode, sliding gestures, and voice commands.²⁴ The study presented an approach called TGSB (Touch Gestures for Soft Biometrics), which achieved high accuracy: up to 94% in gender recognition and up to 99% in age group recognition. Scroll gestures proved particularly effective, enabling gender recognition with 81% accuracy and age group recognition with 96% accuracy on their own. By being able to define different gestures and assign actions to specific areas of its surface, it is possible to develop many virtual keyboards.²⁵ Such keyboards can have different modes of interaction, facilitating text-based communication for users with physical or visual disabilities. In the conclusions, the authors emphasize the need for more research and the development of more personalized and flexible solutions that take into account the individual preferences and abilities of users with different impairments.

Motion sensors

The sensor that most effectively collects information about the movement of the mobile device, and often its owner, is the accelerometer. It is a critical sensor in smartphones that enables motion-based interactions and accessibility features. Measure linear acceleration in multiple axes (X, Y, Z) and has been extensively used in assistive applications for people with disabilities. Key applications for people with disabilities include mobile apps that use accelerometers in smartphones to detect sudden movements or falls,²⁶ automatically alerting caregivers or emergency services. The authors in their conclusions highlight that the use of widely available devices, such as smartphones, eliminates the need for specialized equipment, making the system more cost-effective and easier to implement on a large scale.

The built-in accelerometer can also be used for activity monitoring and gait analysis.²⁷ In this way, it helps people with movement disorders by tracking movement patterns and helping rehabilitation. It is also possible to develop gesture-based controls to convert hand gestures into commands for people with motor impairments. The results of the experiments show that this approach achieves high accuracy in pattern identification while minimizing the number of false alarms, which is crucial in applications that require precise analysis of human behavior.

Currently, all smartphones have one more sensor related to movement. This is the proximity sensor, which detects nearby objects without physical contact. It is usually located near the front camera and works by emitting infrared light and measuring its reflection to determine the distance of the object from the phone. Typically, it is used to turn off the screen during calls.

Orientation sensors

Sensors related to orientation in space include gyroscope, magnetometer, and GPS receiver. The gyroscope measures changes in the orientation of the device in space, making it useful for gesture control, balance monitoring, and adaptive interfaces. The article²⁸ demonstrated that teaching the Tait–Bryan convention and the interpretation of the three components of angular velocity using a smartphone is practical and effective, encouraging the widespread adoption of such exercises in secondary schools and in engineering and physics programs. For people with physical, visual, and cognitive disabilities, gyroscope-based applications can improve mobility, accessibility, and independence. In assistive applications, the gyroscope is often used in conjunction with the accelerometer. The algorithm developed,²⁹ which combines accelerometer and gyroscope thresholds and was optimized using ROC analysis, achieved both high sensitivity (96.3%) and high specificity (96. 2%) simultaneously, surpassing previous methods that were able to achieve only one of these metrics at a high level.

If the user wants to determine the cardinal directions, they must use an application that provides readings from the built-in magnetometer (compass). It detects the magnetic field of Earth to determine the smartphone’s orientation relative to the north. It can help visually impaired people to move around outside their homes and support wheelchair users to maintain their orientation. This sensor is often used together with a receiver of one of the positioning signals, for example, Global Positioning System (GPS), the European satellite navigation system (Galileo), or others.³⁰ It receives satellite signals to determine the exact geographical location. The results of this study show that blind people and users with limited vision can effectively use the wayfinding application without help. The evaluation also confirms the usefulness of extending the vibration feedback to convey distance information and direction information.

Environmental sensors

Only a few modern mobile phones are equipped with environmental sensors that allow them to measure and respond to various external conditions. These sensors improve the user experience, provide health and safety monitoring, and even support assistive applications for people with disabilities. Here we can list:

• Ambient light sensor: Measures the intensity of the ambient light to automatically adjust the screen brightness for better visibility.

• Barometer: Measures atmospheric pressure to improve the accuracy of GPS altitude and weather forecasts.

• Thermometer: In which most phones use internal thermometers to monitor the device for overheating. Only some phones have external temperature sensors for environmental readings.

• UV sensor: Measures the level of ultraviolet radiation to provide warnings about sun exposure.

• Hygrometer: Measures air humidity levels, which can be helpful for detecting concentrated water vapor in the air (e.g., boiling water in the kitchen), but can also be used for weather forecasting and health monitoring.

Biomedical sensors

Biomedical sensors are more common in smartphones. These include:

• Heart rate sensor: Measures heart rate (HR) and heart rate variability (HRV) and uses light reflection to measure blood flow and estimate heart rate.³¹

• SpO2 sensor: Measures oxygen levels in the blood and uses light absorption through the skin to estimate blood oxygen levels.³²

• Electrocardiogram (ECG) sensor: Records electrical activity of the heart to detect heart abnormalities and uses metal electrodes.³³

• Blood pressure sensor: Measures systolic and diastolic blood pressure and uses optical sensors.³⁴

Smartphones, which have such sensors built-in, always have the appropriate software already installed to monitor their readings.

Communication with external devices

Modern smartphones support a variety of external assistive devices to enhance accessibility and usability for people with disabilities. These devices can be connected in multiple ways, depending on the user’s needs.

Bluetooth

The most popular way to connect an external device is wireless technology using the Bluetooth standard or its variant known as Bluetooth Low Energy (BLE). Through Bluetooth, it is possible to physically control the movement of mobility aids. An example is smart wheelchairs, which can be controlled via corresponding smartphone applications.³⁵ This IoT-based wheelchair exhibited low voice-control latency (0.5 s, rising to 1 s under a load of 17 kg) and near-zero joystick latency, with maximum speed decreasing proportionally to added weight; obstacle detection was 100% accurate within 20 cm with no false positives beyond that range, fall alerts averaged a notification delay of 3.6 s, and usability testing showed that young children adapted quickly to simplified voice commands while older adults experienced more recognition errors with longer phrases. Wirelessly, it is also possible to control a robotic arm to help users perform everyday tasks. There is a robotic support arm solution for wheelchairs that enables people with limited upper body mobility to interact with objects using smartphone controls.³⁶ The robotic armchair represents a remarkable advancement in robotics, integrating modern and smart technology with everyday furniture to increase convenience and automation. By associating sensors and advanced algorithms or methods, the system makes certain precision and safety measures that prevent collisions and provide smooth navigation in different environments.

In addition to motion assistance, external devices provide navigation and awareness of the surroundings via tactile or audible feedback. An example is Bluetooth-enabled smart shoes that help visually impaired people by sending location-based haptic feedback in real time.³⁷ The authors obtained results that demonstrate that the smart shoes developed based on IoT, equipped with ultrasonic sensors, an ESP32 microcontroller, and a mobile notification system, allows visually impaired individuals to navigate independently by effectively detecting obstacles and delivering immediate alerts, thus significantly improving their mobility and autonomy. A similar solution is the Ashirase device, a shoe-based wearable sensor. This sensor provides non-visual navigation aids through the underfoot vibrations.³⁸ It has an accurate position estimation as the sensor is strongly attached to the shoe. The proposed method obtained a low estimation error <0.2% walking in straight lines and <1.2% walking in circles.

The second innovative solution is a robot that detects steps in the form of a dog to help visually impaired pedestrians get around safely.³⁹ The system adaptively responds to changes in the user’s walking pace and to various spatial challenges, demonstrating strong potential as an assistive navigation aid for visually impaired individuals moving indoors. Another project uses a wristband with vibration feedback to help users navigate in real time and recognize gestures. The system relies on a single inertial measurement unit (IMU) that records wrist movements and provides haptic feedback to indicate direction to follow specific paths, which is particularly beneficial for the visually impaired.⁴⁰ In particular, the proposed artificial intelligence models achieve impressive results: accuracy 95% for hand gesture recognition and an angle error of only 15° for arm motion tracking.

BLE technology, used in conjunction with beacon devices, offers an effective solution for indoor navigation, particularly in environments where GPS is unreliable. BLE beacons transmit unique identifiers that can be detected by mobile applications to estimate a user’s position and provide real-time context-aware audio instructions. This approach has proven especially beneficial for supporting independent mobility of visually impaired individuals.⁴¹ An example of a BLE-based navigation solution is the Wayfindr system,⁴² which uses beacon transmitters installed in public spaces, such as metro stations, to support audio navigation for visually impaired users. The mobile application receives signals from nearby beacons and provides step-by-step voice instructions, allowing greater independence in complex indoor environments.

A separate category of devices that can be connected to a mobile phone via Bluetooth is hearing aids and speech-assist devices. Modern hearing aids use Bluetooth Low Energy (BLE) technology to connect to smartphones, allowing users to adjust settings, amplify specific frequencies, and stream phone calls, which allows for high sound clarity. An interesting solution is the gesture-to-speech system, in which smart gloves are specially adapted for people with speech impairments. These gloves use built-in systems to interpret hand movements and convert them into spoken words or text, facilitating seamless communication. Furthermore, using IoT connectivity, users can seamlessly interact with other smart devices, expanding the range of communication options available to them.⁴³

Bluetooth technology is widely used in assistive solutions based on IoT, enabling seamless interaction between a wide variety of devices and smartphones. An example is the system that enables users to remotely monitor and control home appliances via a smartphone app, integrating voice commands and automation features to assist those with mobility impairments. Research⁴⁴ highlights how smart homes can improve the independence of disabled users, allowing them to control lighting, temperature, security, and other essential home functions. Another type of Bluetooth-connected device is Google Glasses. The glasses can allow real-time magnification of the smartphone screen the user is looking at.⁴⁵ In the pilot evaluation, the calculation task performed with Google Glass was about 28% faster than when using the built-in zoom function of the smartphone.

Another type of external device that uses wireless connectivity to communicate is wearable medical devices. These include smartwatches and heart rate monitors that use Bluetooth to send health data to smartphone apps for real-time monitoring. Diabetes monitoring systems allow users to track glucose levels and receive alerts on their smartphones.⁴⁶ Smartphone-based portable electrochemical and colorimetric methods showed detection limits of 0.467 µM and 10 µM, respectively, indicating good selectivity, stability, and reproducibility. The ease of operation, short detection time, compact and portable design, and good applicability make the system an attractive option for point-of-care body fluid analysis in mobile health.

Other communication technologies

For individuals with disabilities, external cameras integrated with smartphones play a crucial role in navigation, object recognition, and assistive vision technologies. The choice of connectivity type (USB cable and Bluetooth wireless) significantly impacts latency, image quality, and usability. The study⁴⁷ evaluates external camera solutions for visually impaired individuals, comparing USB and Bluetooth solutions. The authors emphasize that USB-based cameras provide superior image quality and real-time performance, which are crucial for object detection and recognition (a key feature for visually impaired users, requiring fast and high-resolution imaging), scene processing and navigation (where real-time feedback is essential to avoid obstacles), and AI-powered vision assistance (demanding a high-bandwidth connection for effective deep-learning-based recognition).

Many smartphones are now equipped with a Near Field Communication (NFC) contactless interface, which is an advanced form of Radio Frequency Identification (RFID). It is a short-range communication technology that is used for quick and secure data exchange. It is widely used in contactless payments, access control, and automation, but it also has significant assistive applications for people with disabilities. NFC can be used to provide audio guidance and object recognition, allowing visually impaired users to navigate their surroundings more effectively.^48,49 NFC can be used in an indoor blind navigation system. This system⁵⁰ uses passive RFID tags placed in the environment, a specially designed glove, a smartphone worn by the user, and a back-end server to handle the information. When the user, equipped with the glove and smartphone, enters the building, they scan the destination at a kiosk located at the entrance to the building, and the system then guides the user to the destination using landmarks. Examples of applications also include NFC tags for everyday items. Users can attach NFC tags to food containers, medicine bottles and household items and program them to read the labels when scanned with a smartphone.⁵¹ NFC technology can be helpful not only for people with vision problems, but also for people with cognitive disabilities (provides seamless control over household appliances, reduces physical effort in daily tasks),⁵² hearing disabilities (improves the functionality of hearing aids and helps users access speech-to-text services in real-world environments), and motor disabilities (facilitating control in a smart home).⁵³

In this part, we must also indicate the widely used analog audio connection for external audio devices, using the 3.5 mm audio jack connector. Its primary applications are related to devices that assist hearing by amplifying sound for people with hearing loss, and to the use of a microphone to help users with speech impairments communicate more effectively. A final mention should also be made of the wireless network connection (Wi-Fi), which allows devices to communicate at a higher data rate than Bluetooth, enabling the use of the Internet and all the assistive services available on it.

Access facilitation in mobile systems

Modern mobile devices offer a wide range of features to support people with disabilities. iOS and Android are constantly developing their accessibility technologies with innovative solutions such as voice control, screen readers, live captioning, and integration with assistive devices. As a result, people with a variety of limitations can use mobile devices freely and enjoy the full functionality of smartphones.

Accessibility for visually impaired users

Smartphones have become essential tools for everyday communication, navigation, and productivity. However, for visually impaired users, interacting with these devices can be challenging. Fortunately, various accessibility technologies allow blind and low-vision users to use smartphones efficiently. These technologies leverage audio feedback, haptic responses, AI, and ML to enhance user experience. Screen readers are essential for visually impaired users, as they provide audio descriptions of on-screen content, enabling non-visual interaction. They convert text and interface elements into speech or Braille output. The most commonly used screen readers include:

• VoiceOver (iOS): Apple’s built-in screen reader, which uses gestures and voice commands to facilitate navigation.

• TalkBack (Android): Google’s equivalent, offering touch gestures and voice feedback to assist with smartphone use.

• NVDA (cross-platform): Third-party screen readers providing advanced interaction methods for visually impaired users.

Tactile and audio hints help visually impaired users navigate the smartphone interface. Vibrating feedback for typing and gestures provides an additional layer of interaction.

For visually impaired users, it is possible to adjust the display to improve readability. Built-in applications such as Zoom and Magnifier magnify text and interface elements,⁵⁴ while dark mode and high contrast themes reduce visual strain. Color reconfiguration allows colors that are not perceived by the visually impaired to be replaced by colors that are visible to the visually impaired.⁵⁵ Writing interfaces for blind users also often include improvements for text input. The default virtual keyboards can be replaced by more accessible keyboards, for example, allowing predictive gestures.⁵⁶ For users who are fluent in Braille, there are a number of assistive technologies available to enable its use. Braille input methods, such as Apple Braille Screen Input⁵⁷ or external Braille keyboards, enable efficient text input. External refreshable braille displays convert text from a smartphone into tactile braille.

Accessibility mechanisms for people with visual impairments also include command recognition related to the already discussed earlier, voice recognition technologies, and AI assistants. These allow users to control a mobile device without touch.

Technology for people with hearing disabilities

For deaf or hard-of-hearing (DHH) using smartphones, Video Relay Services (VRS) have become an essential tool for communication. These services allow users to communicate through sign language via video calls, offering accessibility and convenience. Research on video-based sign language communication highlights the critical role of video quality in ensuring effective comprehension among DHH users. The study⁵⁸ demonstrates that both screen size and visual distortion significantly affect the intelligibility of sign language, identifying medium-sized displays as optimal for clear communication. Another article⁵⁹ describes how video quality affects real-time sign language comprehension. The study focuses on the relationship between objective measures of video quality, such as Peak Signal-to-Noise Ratio (PSNR), and actual comprehension by deaf users. The results suggest that traditional video quality metrics may not accurately reflect the perceptions of sign language users, highlighting the need to consider perceptual factors when designing video communication systems for DHH communities.

For those with hearing difficulties, technology has been implemented to allow live captioning and transcription. Mechanisms such as Live Captions allow real-time display of subtitles while also providing transcription of conversations and multimedia. Smartphones very often provide compatibility with hearing aids (Hearing Aid Support). Devices can wirelessly connect to hearing aids via Bluetooth or MFi technology (Made for iPhone).

Environmental Sound Recognition (ESR) on smartphones is an advanced accessibility feature designed to assist users, particularly those with hearing impairments. This technology enables smartphones to detect and identify important sounds in the environment, such as doorbells, sirens, alarms, or a crying baby.⁶⁰ Once recognized, the smartphone provides visual, haptic, or text-based notifications to alert the user. Modern ESR systems take advantage of ML and AI to continuously improve sound detection accuracy. Both iOS and Android offer built-in features as Sound Recognition on iPhones and Live Transcribe and Sound Notifications on Android, which help users stay aware of their environment. This technology improves safety, independence, and situational awareness for people with hearing disabilities. The latest mobile devices have adaptive sound profiles. This allows the user to personalize the sounds on a smartphone depending on the type of hearing loss.⁶¹ Setting up these systems might involve the temporary help of non-disabled persons.

Use by persons with motor impairments

The facilities for people with motor disabilities have a lot in common with facilities for people with visual disabilities already described in the chapter. These include controlling the phone without touching the screen, navigation via voice commands, and the use of voice assistants.

For individuals with limited mobility, paralysis, or neuromuscular disorders, alternative navigation methods may be useful. These include the use of built-in physical switches (buttons for volume control) or external switches such as a joystick. The methods are implemented with the function names ‘Switch Control’ (iOS)⁶² and ‘Switch Access’ (Android).⁶³

Another type of facilitation are tools for automating tasks on smartphones, which include Google Routines⁶⁴ and Apple Shortcuts.⁶⁵ These tools vary in functionality and level of sophistication. Google Routines is designed for mobile devices running the Android operating system. Their main function is to automate daily activities through voice commands or scheduled triggers. Google Routines allows users to set a set of actions that are triggered by a single voice command or at a specific time. Apple Shortcuts, on the other hand, offers more extensive capabilities than Google Routines. You can create custom scripts that perform multiple actions in different applications. These tools can be a significant convenience, not only for people with motor disabilities, minimizing the number of interactions with the device, but also for people with cognitive deficits.

Technologies for the cognitively impaired

Smartphones offer many tools to support people with cognitive disabilities. Some of them—such as voice assistants, shortcuts, or switches—have already been described. For people with cognitive disabilities, a special interface option is being introduced in the smartphone software to simplify the appearance and operation of the device. Depending on the producer, the name of the mode may vary: Easy Mode (Samsung),⁶⁶ Simple Mode (Huawei and⁶⁷ Realme)⁶⁸ and Lite Mode (Xiaomi).⁶⁹ The simplified mode introduces, among other features, the following:

• Larger icons and text: The home screen contains fewer applications and their icons and fonts are larger and more readable.

• Simpler interface: Complicated animations and unnecessary functions are eliminated.

• Easier access to contacts: Frequently used numbers are available on the home screen, making it easier to make calls.

• Reduced notifications: The phone does not overwhelm the user with excessive messages.

• Personalized notifications: Setting vibrations, sounds, and colors for different notifications.

• Faster access to basic functions: Many devices allow you to assign shortcuts to key applications such as the camera, phone, messaging, or web browser.

• Blocking unwanted content: Content filtering options and protection against distractions, for example, Focus Mode (iOS) or Digital Wellbeing (Android).

Despite the improvements that continue to be made, several standard phone activities remain challenging. This is due, among other things, to the small screen size and the predefined interaction methods. These challenges can be particularly acute for people with intellectual disabilities.⁷⁰ Research was carried out on the identification of requirements, usage patterns, and expectations of an accessible mobile phone-based remote communication system. These resulted primarily in the need to use a simplified navigation menu with fewer options.⁷¹

Technology trends

Artificial intelligence and machine learning

AI and ML play a key role in improving assistive technologies on smartphones to help people with disabilities in their daily lives. The use of AI has a significant impact on the functioning of voice assistants. It allows them to adapt to the way the user speaks, can recognize the speech of people with disorders, and converts speech to text in real time, which helps the deaf.

To improve the effectiveness of AI in voice assistants, research is being carried out on the various consumer values associated with the use of voice assistants, analyzing user motivations to use the technology.⁷² Work is also being carried out to analyze the development of AI-based voice assistants, comparing the differences between the solutions used in various mobile phones and examining their impact on the daily lives of users.⁷³ The potential of AI-based voice assistants is being considered in the context of both education⁷⁴ and personalized healthcare.^75,76

The power of AI is important for the blind and visually impaired to recognize images coming from a smartphone’s built-in camera. AI analyzes photos, helping to identify objects and people, and then generates detailed descriptions for blind people.^77–79 It is also becoming very useful for these people to be able to recognize in real time the emotions of people in the eye of the camera of the smartphone.^80–82

Using AI to operate smartphones using hand gestures in front of the camera eliminates the need to touch the screen. The AirPen system allows users to interact with smartphones using finger gestures in the air.⁸³ The system uses deep learning models to locate hands and recognize gestures in real time. It is also possible to recognize hand gestures using non-audible sounds emitted from and received by the smartphone’s built-in speakers and microphones. Such a system uses convolutional neural networks to analyze sound signals and achieves a gesture recognition accuracy of 93.58%.⁸⁴ The result is comparable to a system that uses radar to obtain information on the range and speed of hand movements that allows real-time gesture recognition with an accuracy of more than 95%.⁸⁵

Integration with augmented and virtual reality

Augmented reality (AR) and virtual reality (VR) are increasingly being used on smartphones to support people with various disabilities. Thanks to developments in mobile technology, AR and VR can help with communication, education, rehabilitation, and users’ daily functioning.

AR applications using a smartphone camera can analyze the environment and provide the user with audio information about obstacles, signs, or objects, as described in the previous chapter. Research is underway on AR filters for reducing sensory stimuli. People who are hypersensitive to light or sound (people with autism or cognitive disabilities) can use AR to adjust their perception of their surroundings, for example, reducing the brightness of the screen, selectively removing or obscuring distracting objects from the user’s field of vision⁸⁶ or filtering out ambient noise.⁸⁷ There are no barriers to the use of these technologies in smartphones.

Smartphones and virtual reality (VR) are closely related. Today’s phones offer sufficient processing power, high-resolution screens, and advanced sensors to enable VR technology. Here are some key aspects of this combination:

• Smartphones as screens for VR goggles: Many VR devices use smartphones with high-resolution, 90 Hz + OLED screens as the screens for the headset. Examples are Google Cardboard and Samsung Gear VR.

• VR applications for smartphones that work without the need for additional devices: Watching 360° films and videos in virtual reality (YouTube VR); virtual tours of museums, planets, or historical sites (Google Expeditions); and social applications that allow interaction in a virtual world (VRChat and AltspaceVR).

• Smartphones as VR controllers: Some VR systems allow you to use your smartphone as a gesture controller allowing you to transfer VR images to your phone and use it as a controller in a PC VR environment (SteamVR and ALVR).

In this area of technology development, researchers are working on adaptive augmented and virtual reality (AR/VR) systems designed for people with various disabilities. The authors examine how personalization of user interfaces can improve accessibility to these technologies for people with mobility and sensory limitations.⁸⁸ For example, some research in this area focuses on the possibility of mapping single-handed gestures to two-handed interactions in VR environments, which may be particularly useful for people with limited mobility.⁸⁹ Another issue in development is the design of the upper body gesture interaction in VR for people with spinal muscular atrophy (SMA).⁹⁰

Biofeedback and neural interfaces

Biofeedback is a technique for monitoring physiological processes (e.g., heart rate, brain activity, and muscle tension), allowing users to consciously control certain functions of their body. The following examples of biofeedback applications can be identified in smartphones:

• Rehabilitation apps: For example, monitoring muscle tension to improve motor skills in people after strokes.

• Stress and anxiety management: Respiratory biofeedback can help people on the autism spectrum or with PTSD.

• Device control using brainwave or EMG signals: Facilitates smartphone use for people with tetraplegia.

Neural interfaces, otherwise known as brain-computer interfaces (BCIs), allow people with disabilities to control smartphones or other devices with their thoughts. They are particularly useful for people with complete paralysis (e.g., ALS—amyotrophic lateral sclerosis) or very limited mobility. Sensors (electrodes) responsible for recording brain signals can be non-invasive—most commonly used, used in EEG headbands and helmets, semi-invasive—electrodes are placed under the skull, but on the surface of the brain, and invasive—implanted directly into the cerebral cortex, used, for example, in Neuralink.⁹¹

The development of brain-computer interfaces in medicine has been underway for many years now, with a focus on their potential to improve communication and device control for people with severe disabilities. A special feature of development in this field is the need for long-term research.⁹² Another very important issue is the individual, social, and commercial aspects of neural interface technologies, including their potential for use in conjunction with smartphones for people with disabilities. This highlights the need to consider ethical issues as these technologies develop.^93,94

Conclusions

Mobile phones are no longer just communication tools, they are lifelines for accessibility. With AI-powered image recognition and visual translation, smartphones empower blind users, non-native speakers, and people with learning disabilities to navigate the world independently and confidently. The key advantages of these devices, which confirm their significant role for people with disabilities, include:

• Portability and affordability: Smartphones are replacing expensive assistive devices, making accessibility tools widely available.

• AI-based performance: ML improves the accuracy of text, object, and environment recognition.

• Multifunctionality: Mobile device combines image recognition, speech synthesis, and object detection in a single device.

• Cloud computing and edge AI: Many functions use the cloud, but many also work offline, increasing usability without an internet connection.

The main developments in mobile technology are mainly focused on the role of AI-supported voice assistants, which is very useful for a large part of the disability community. Also of note is the increasing integration with AR, IoT and healthcare, which is a field for further research and innovation.

In summary, it can be concluded that the strongest aspect of smartphones as assistive technology is their ability to be highly personalized, allowing them to meet the specific needs of each user. Such personalization enables people with disabilities to customize their devices to better suit their unique requirements and preferences. As a result, smartphones are becoming more than just tools, they are transforming into indispensable companions that enhance independence and improve quality of life.

Footnotes

ORCID iD

Krzysztof Dobosz

Funding

The authors received no financial support for the research, authorship, and/or publication of this article.

Declaration of conflicting interests

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

References

Mueller

Jones

Broderick

, et al. Assessment of user needs in wireless technologies. Assist Technol 2005; 17(1): 57–71.

Hoy

. Alexa, Siri, Cortana, and more: an introduction to voice assistants. Med Ref Serv Q 2018; 37(1): 81–88.

Bhalerao

Bhilare

Bondade

, et al. Smart Voice Assistant: a universal voice control solution for non-visual access to the Android operating system. Inter Res J Engine Tech (IRJET) 2017; 4(1): 1713–1720.

Mofrad

Mosse

. Speech recognition and voice separation for the internet of things. In: Proceedings of the 8th International Conference on the Internet of Things, 2018, pp. 1–8.

Tiwari

Hashmi

Keskar

, et al. Virtual home assistant for voice based controlling and scheduling with short speech speaker identification. Multimed Tool Appl 2020; 79(7): 5243–5268.

Sezgin

Huang

Ramtekkar

, et al. Readiness for voice assistants to support healthcare delivery during a health crisis and pandemic. npj Digit Med 2020; 3(1): 122.

Rohlfing

Buckley

Piraquive

, et al.

Hey Siri: how effective are common voice recognition systems at recognizing dysphonic voices?

Laryngoscope 2021; 131(7): 1599–1607.

Cave

Bloch

. The use of speech recognition technology by people living with amyotrophic lateral sclerosis: a scoping review. Disabil Rehabil Assist Technol 2023; 18(7): 1043–1055.

Sun

Chen

Zhang

. “Alexa, stop spying on me!” speech privacy protection against voice assistants. In: Proceedings of the 18th conference on embedded networked sensor systems, 2020, pp. 298–311.

10.

Cheng

, et al. Scoring metrics of assessing voiceprint distinctiveness based on speech content and rate. IEEE Trans Dependable Secure Comput 2024; 21(6): 5582–5599.

11.

Gokcimen

Das

. Evaluating the performance of Turkish automatic speech recognition using the generative AI-based whisper model. In: 2024 9th International Conference on Computer Science and Engineering. UBMK, 2024, pp. 121–125.

12.

Nasr-Esfahani

Bekrani

Rajabi

. Robust recognition of Persian isolated digits in speech using deep neural network. 2024. Available from: https://arxiv.org/abs/2412.10857

13.

Khot

Sreenivas

, et al. Multifactor authentication using blockchain in 6G. In: 2024 8th International Conference on Computational System and Information Technology for Sustainable Solutions (CSITSS), 2024, pp. 1–6.

14.

Uchida

Kawabata

Hamasaki

, et al. Improving biometric accuracy using ear canal images: removing overexposed and underexposed images through a lightweight algorithm. In: 2024 IEEE International Symposium on Consumer Technology (ISCT), 2024, pp. 81–85.

15.

Redmon

Divvala

Girshick

, et al. You only look once: unified, real-time object detection. 2016. Available from: https://arxiv.org/abs/1506.02640

16.

Howard

Zhu

Chen

, et al. MobileNets: efficient convolutional neural networks for mobile vision applications. 2017. Available from: https://arxiv.org/abs/1704.04861

17.

Smith

. An overview of the Tesseract OCR engine. In: Ninth international conference on document analysis and recognition (ICDAR 2007). IEEE, 2007, vol 2, pp. 629–633.

18.

Pujari

Madnal

Premchandran

. Mobile app for enhancing accessibility among the visually impaired. In: 2024 2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry (IDICAIEI), 2024, pp. 1–6.

19.

Huda

Nogami

Rahayu

, et al. IoT-enabled plant monitoring system with power optimization and secure authentication. Comput Mater Continua (CMC) 2024; 81(2): 3165–3187.

20.

Sipior

Ward

Volonino

. Privacy concerns associated with smartphone use. J Internet Commer 2014; 13(3-4): 177–193.

21.

Lei

. Ergonomic hand motion assistance and AR rehabilitation: bridging the gap in tremor disorder therapies through mixed reality. In: 2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW). IEEE, 2024, pp. 322–325.

22.

Wang

Pierson

, et al. Moat: adaptive inside/outside detection system for smart homes. Proc ACM Interact Mob Wearable Ubiquitous Technol 2024; 8(4): 1–31.

23.

LLC G . Navigate your device with TalkBack, 2025. Available from: https://support.google.com/accessibility/android/answer/6006598?sjid=6116339708814644228-EU

24.

Guarino

Malandrino

Zaccagnino

, et al. Touchscreen gestures as images. A transfer learning approach for soft biometric traits recognition. Expert Syst Appl 2023; 219: 119614.

25.

Shahid

Ali Shah

Dar

, et al. A review of smartphone’s text entry for visually impaired. In: 2018 24th International Conference on Automation and Computing (ICAC), 2018, pp. 1–7.

26.

Dobosz

Wreczycki

. Fall detection of the elderly using a smartphone. Journal of Medical Informatics & Technologies 2016; 25: 19–27.

27.

Mohsin

Abdul Kadeem

Sheel

, et al. Artificial intelligence-assisted pattern discovery for narrow domains of human activity using a heuristic-optimised approach. In: 2024 International Conference on Smart Systems for Electrical, Electronics, Communication and Computer Engineering (ICSSEECC), 2024, pp. 648–653.

28.

de Jesus

VLB

Pérez

CAC

de Oliveira

, et al. Understanding the gyroscope sensor: a quick guide to teaching rotation movements using a smartphone. Phys Educ 2018; 54(1): 015003.

29.

Huynh

Nguyen

Irazabal

, et al. Optimization of an accelerometer and gyroscope-based fall detection algorithm. J Sens 2015; 2015(1): 452078.

30.

Rodriguez-Sanchez

Moreno-Alvarez

Martín

, et al. Accessible smartphones for blind users: a case study for a wayfinding system. Expert Syst Appl 2014; 41(16): 7210–7222.

31.

De Ridder

Van Rompaey

Kampen

, et al. Smartphone apps using photoplethysmography for heart rate monitoring: meta-analysis. JMIR Cardio 2018; 2(1): e4. Available from: https://cardio.jmir.org/2018/1/e4/

32.

Ding

Nassehi

Larson

. Measuring oxygen saturation with smartphone cameras using convolutional neural networks. IEEE J Biomed Health Inform 2018; 23(6): 2603–2610.

33.

Bruining

Caiani

Chronaki

, et al. Acquisition and analysis of cardiovascular signals on smartphones: potential, pitfalls and perspectives: by the Task Force of the e-Cardiology Working Group of European Society of Cardiology. Eur J Prev Cardiol 2014; 21(2_suppl): 4–13.

34.

Frey

Menon

Elgendi

. Blood pressure measurement using only a smartphone. npj Digit Med 2022; 5(1): 86.

35.

Kumar

Kushwaha

Sherawat

, et al. IoT based smart wheelchair for disabled person. In: 2024 International Conference on Electrical Electronics and Computing Technologies (ICEECT), 2024, vol 1, pp. 1–6.

36.

Trinadh

MKD

Reddy

Ram

, et al. Assistive robotic arm for wheelchairs: enhancing daily living for the disabled. In: 2024 8th International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2024, pp. 1181–1185.

37.

Mahalakshmi

Arunbalaji

Dhanushmoorthy

, et al. Smart shoe for visually impaired person based on IoT. In: 2024 International Conference on Computational Intelligence for Green and Sustainable Technologies (ICCIGST), 2024, pp. 1–6.

38.

Kajimoto

Tanaka

Bao

, et al. Shoe-based PDR system for two-dimensional tracking. In: 2025 IEEE International Conference on Consumer Electronics (ICCE). IEEE, 2025, pp. 1–2.

39.

Hamadi

Latoui

. Step-detection-controlled robot dog guide for visually impaired pedestrians. In: 2024 International Conference on Advances in Electrical and Communication Technologies (ICAECOT), 2024, pp. 1–5.

40.

Chang

Han

, et al. Real-time arm motion tracking and hand gesture recognition based on a single inertial measurement unit. In: 2024 11th International Conference on Internet of Things: Systems, Management and Security (IOTSMS), 2024, pp. 44–49.

41.

Real

Araujo

. Navigation systems for the blind and visually impaired: past work, challenges, and open problems. Sensors 2019; 19(15): 3404.

42.

Wayfindr . Understanding audio wayfinding and audio-based navigation, 2018. Accessed: 2025-04-20.https://www.wayfindr.net/wp-content/uploads/2018/08/Understanding-Audio-Wayfinding-and-Audio-Based-Navigation.pdf

43.

Pandey

Kumar

Kaushik

, et al. IoT-assisted gesture-to-audio conversion system for enhancing accessibility in speech-impaired users. In: 2024 IEEE 5th India Council International Subsections Conference (INDISCON). IEEE, 2024, pp. 1–5.

44.

Rajak Das

. Enhancing residential living: an innovative IoT-based home automation system for convenience, security, and accessibility. Int J Eng Sci 2024; 13(12): 17–20.

45.

Pundlik

Liu

, et al. Magnifying smartphone screen using google glass for low-vision users. IEEE Trans Neural Syst Rehabil Eng 2017; 25(1): 52–61.

46.

Shen

Zhang

, et al. Smartphone-based portable electrochemical-colorimetric dual-mode biosensor for glucose detection in a co-reaction system. Electrochim Acta 2024; 481: 143952, Available from: https://www-sciencedirect-com-443.web.bisu.edu.cn/science/article/pii/S0013468624001968

47.

Patel

Parmar

. Assistive device using computer vision and image processing for visually impaired; review and current status. Disabil Rehabil Assist Technol 2022; 17(3): 290–297.

48.

Lim

. NFC label tagging smartphone application for the blind and visually impaired in IoT. In: Information Science and Applications: Proceedings of ICISA 2020. Springer, 2021, pp. 305–315.

49.

AlZuhair

Najjar

Kanjo

. NFC based applications for visually impaired people-A review. In: 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW). IEEE, 2014, pp. 1–6.

50.

Ganz

Schafer

Gandhi

, et al. PERCEPT indoor navigation system for the blind and visually impaired: architecture and experimentation. Int J Telemed Appl 2012; 2012(1): 894869.

51.

Sánchez

Fraile

Mateos

, et al. PharmaFabula. NFC mobile technology and RFID for identification of medicines for the Blind. 2009.

52.

de la Guía

Lozano

Penichet

VMR

, et al. Distributed and tangible user interfaces to design interactive systems for people with cognitive disabilities. In: Lozano

Gallud

Tesoriero

, et al. (eds). Distributed user interfaces: usability and collaboration. Human–computer interaction series. London: Springer London, 2013, pp. 129–140.

53.

Spinsante

Gambi

. NFC-based user interface for smart environments. Advances in Human-Computer Interaction 2015; 2015(1): 854671.

54.

Luo

. How 16,000 people used a smartphone magnifier app in their daily lives. Clin Exp Optom 2020; 103(6): 847–852.

55.

Locke

McRae

Peaty

, et al. Developing accessible technologies for a changing world: understanding how people with vision impairment use smartphones. Disabil Soc 2022; 37(1): 111–128.

56.

Zhang

Ashok

, et al. Accessible gesture typing on smartphones for people with low vision. In: Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology, 2024, pp. 1–11.

57.

Apple . Type braille directly on your iPhone, iPad, or iPod touch, 2024. Available from: https://support.apple.com/en-us/101637

58.

Cavender

Rice

Wilamowska

. SignWave: human perception of sign language video quality as constrained by mobile phone technology. Emergency 2005; 7(12): 16–20.

59.

Tran

Kim

Chon

, et al. Evaluating quality and comprehension of real-time sign language video on mobile phones. In: The proceedings of the 13th international ACM SIGACCESS conference on Computers and accessibility, 2011, pp. 115–122.

60.

Jain

. Sound sensing and feedback techniques for deaf and hard of hearing people. University of Washington, 2022.

61.

Aldaz

Puria

Leifer

. Smartphone-based system for learning and inferring hearing aid settings. J Am Acad Audiol 2016; 27(09): 732–749.

62.

Inc A . Use Switch Control to navigate your iPhone, iPad, or iPod touch, 2025. Available from: https://support.apple.com /en -us/119835

63.

LLC G . Control your Android device with Switch access, 2025. Available from: https://support.google.com/accessibility/android/answer/6122836?hl=en

64.

LLC G . Create and manage Routines in Google Home, 2025. Available from: https://support.google.com/googlenest/answer/7029585?hl=en&co=GENIE.Platform%3DAndroid

65.

Inc A . Shortcuts User Guide, 2025. Available from: https://support.apple.com /guide/shortcuts/welcome/ios

66.

Samsung . Using Easy Mode on my Samsung Phone, 2024. Available from: https://www.samsung.com/au/support/mobile-devices/using-easy-mode/

67.

Huawei Technologies Co L . How to enable and use Simple Mode on your Huawei devices, 2019. Available from: https://consumer.huawei.com/en/community/details/Tutorial-How-to-enable-and-use-Simple-Mode-on-your-Huawei-devices/topicId_4926/

68.

Realme . How to use simple mode, 2024. Available from: https://www.realme.com /in/support/kw/doc/2061160

69.

Xiaomi . Simplify Your Interface with Lite Mode, 2024. Available from: https://new.c.mi.com /global/post/960861

70.

Williams

Shekhar

. People with learning disabilities and smartphones: testing the usability of a touch-screen interface. Educ Sci 2019; 9(4): 263.

71.

Dawe

. Understanding mobile phone requirements for young adults with cognitive disabilities. In: Proceedings of the 9th international ACM SIGACCESS conference on Computers and accessibility, 2007, pp. 179–186.

72.

Malodia

Islam

Kaur

, et al.

Why do people use Artificial Intelligence (AI)-enabled voice assistants?

IEEE Trans Eng Manag 2021; 71: 491–505.

73.

Huang

Research on the development of voice assistants in the era of artificial intelligence. In: SHS Web Conf, SHS Web of Conferences. EDP Sciences, 2023, vol. 155, p. 03019.

74.

Terzopoulos

Satratzemi

. Voice assistants and artificial intelligence in education. Proceedings of the 9th Balkan Conference on Informatics, 2019, pp. 1–6.

75.

Ahanin

Sade

Tat

. Applications of artificial intelligence and voice assistant in healthcare. Int J Acad Res Bus Soc Sci 2022; 12: 2545–2554.

76.

Kocaballi

Berkovsky

Quiroz

, et al. The personalization of conversational agents in health care: systematic review. J Med Internet Res 2019; 21(11): e15360.

77.

Najm

Elferjani

Alariyibi

. Assisting blind people using object detection with vocal feedback. In: 2022 IEEE 2nd International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA). IEEE, 2022, pp. 48–52.

78.

Srinivas Bobba

Krishna Sai Boddu

Mani Surendra Bolla

, et al. Newvision: application for helping blind people using deep learning. arXiv e-prints, 2023, p. 2311.

79.

Khabarlak

. Face detection on mobile: five implementations and analysis, 2022. Available from: https://arxiv.org/abs/2205.05572

80.

Savchenko

. Frame-level prediction of facial expressions, valence, arousal and action units for mobile devices, 2022. Available from: https://arxiv.org/abs/2203.13436

81.

Hewitt

Gunes

. CNN-Based facial affect analysis on mobile devices, 2018. Available from: https://arxiv.org/abs/1807.08775

82.

Banerjee

Washington

Mutlu

, et al. Training and profiling a pediatric emotion recognition classifier on mobile devices, 2021. Available from: https://arxiv.org/abs/2108.11754

83.

Jain

Hebbalaguppe

. AirPen: a touchless fingertip based gestural interface for smartphones and head-mounted devices, 2019. Available from: https://arxiv.org/abs/1904.06122

84.

Ibrahim

El-Refai

Ahmed

, et al. Pervasive hand gesture recognition for smartphones using non-audible sound and deep learning, 2021. Available from: https://arxiv.org/abs/2108.02148

85.

Ren

Beletchi

, et al. Hand gesture recognition using 802.11 ad mmWave sensor in the mobile device, 2021.

86.

Lee

Kim

. Augmenting reality to diminish distractions for cognitive enhancement, 2024. Available from: https://arxiv.org/abs/2403.03875

87.

Grimshaw-Aagaard

Walther-Hansen

. Less-is-more: auditory strategies for reduced reality. Personal Ubiquitous Comput 2024; 28: 1–13.

88.

Biswas

Orero

Swaminathan

, et al. Adaptive accessible AR/VR systems. In: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, 2021, pp. 1–7.

89.

Yamagami

Junuzovic

Gonzalez-Franco

, et al. Two-in-one: a design space for mapping unimanual input into bimanual interactions in VR for users with limited movement. ACM Trans Access Comput 2022; 15(3): 1–25.

90.

Tian

Wang

, et al. Designing upper-body gesture interaction with and for people with spinal muscular atrophy in VR. In: Proceedings of the CHI Conference on Human Factors in Computing Systems, 2024, pp. 1–19.

91.

Musk

Neuralink . An integrated brain-machine interface platform with thousands of channels. J Med Internet Res 2019; 21(10): e16194.

92.

Shih

Krusienski

Wolpaw

. Brain-computer interfaces in medicine. In: Mayo Clin Proc, Mayo clinic proceedings. Elsevier, 2012, vol. 87, p. 268–279.

93.

Burwell

Sample

Racine

. Ethical aspects of brain computer interfaces: a scoping review. BMC Med Ethics 2017; 18: 1–11.

94.

Fontanillo Lopez

Zhang

. Beyond technologies of electroencephalography-based brain-computer interfaces: a systematic review from commercial and ethical aspects. Front Neurosci 2020; 14: 611130.