Assistive Applications Research Articles

Embedded Machine Learning Using Microcontrollers in Wearable and Ambulatory Systems for Health and Care Applications: A Review

The use of machine learning in medical and assistive applications is receiving significant attention thanks to the unique potential it offers to solve complex healthcare problems for which no other solutions had been found. Particularly promising in this field is the combination of machine learning with novel wearable devices. Machine learning models, however, suffer from being computationally demanding, which typically has resulted on the acquired data having to be transmitted to remote cloud servers for inference. This is not ideal from the system’s requirements point of view. Recently, efforts to replace the cloud servers with an alternative inference device closer to the sensing platform, has given rise to a new area of research Tiny Machine Learning (TinyML). In this work, we investigate the different challenges and specifications trade-offs associated to existing hardware options, as well as recently developed software tools, when trying to use microcontroller units (MCUs) as inference devices for health and care applications. The paper also reviews existing wearable systems incorporating MCUs for monitoring, and management, in the context of different health and care intended uses. Overall, this work can be used as a kick-start for embedding machine learning models on MCUs, focusing on healthcare wearables.

A Deep Learning Based Model to Assist Blind People in Their Navigation

Aim/Purpose: This paper proposes a new approach to developing a deep learning-based prototyping wearable model which can assist blind and visually disabled people to recognize their environments and navigate through them. As a result, visually impaired people will be able to manage day-to-day activities and navigate through the world around them more easily. Background: In recent decades, the development of navigational devices has posed challenges for researchers to design smart guidance systems for visually impaired and blind individuals in navigating through known or unknown environments. Efforts need to be made to analyze the existing research from a historical perspective. Early studies of electronic travel aids should be integrated with the use of assistive technology-based artificial vision models for visually impaired persons. Methodology: This paper is an advancement of our previous research work, where we performed a sensor-based navigation system. In this research, the navigation of the visually disabled person is carried out with a vision-based 3D-designed wearable model and a vision-based smart stick. The wearable model used a neural network-based You Only Look Once (YOLO) algorithm to detect the course of the navigational path which is augmented by a GPS-based smart Stick. Over 100 images of each of the three classes, namely straight path, left path and right path, are being trained using supervised learning. The model accurately predicts a straight path with 79% mean average precision (mAP), the right path with 83% mAP, and the left path with 85% mAP. The average accuracy of the wearable model is 82.33% and that of the smart stick is 96.14% which combined gives an overall accuracy of 89.24%. Contribution: This research contributes to the design of a low-cost navigational standalone system that will be handy to use and help people to navigate safely in real-time scenarios. The challenging self-built dataset of various paths is generated and transfer learning is performed on the YOLO-v5 model after augmentation and manual annotation. To analyze and evaluate the model, various metrics, such as model losses, recall value, precision, and maP, are used. Findings: These were the main findings of the study: • To detect objects, the deep learning model uses a higher version of YOLO, i.e., a YOLOv5 detector, that may help those with visual im-pairments to improve their quality of navigational mobilities in known or unknown environments. • The developed standalone model has an option to be integrated into any other assistive applications like Electronic Travel Aids (ETAs) • It is the single neural network technology that allows the model to achieve high levels of detection accuracy of around 0.823 mAP with a custom dataset as compared to 0.895 with the COCO dataset. Due to its lightning-speed of 45 FPS object detection technology, it has become popular. Recommendations for Practitioners: Practitioners can help the model’s efficiency by increasing the sample size and classes used in training the model. Recommendation for Researchers: To detect objects in an image or live cam, there are various algorithms, e.g., R-CNN, Retina Net, Single Shot Detector (SSD), YOLO. Researchers can choose to use the YOLO version owing to its superior performance. Moreover, one of the YOLO versions, YOLOv5, outperforms its other versions such as YOLOv3 and YOLOv4 in terms of speed and accuracy. Impact on Society: We discuss new low-cost technologies that enable visually impaired people to navigate effectively in indoor environments. Future Research: The future of deep learning could incorporate recurrent neural networks on a larger set of data with special AI-based processors to avoid latency.

A Smartphone Based Application for Medical Assistance of Elderly Patients

The importance of a routine health check-up for elderly patients, as well as the documentation of that check- up, cannot be overstated. Maintaining adequate documentation for a patient by himself or by his attendance, on the other hand, is extremely difficult. This paper primarily focuses on developing a framework that includes a smartphone application and introduces a real-time remote monitoring system for basic medical treatment of an elderly patient. It can keep track of a patient’s emergency contacts. Using the SMS manager API, emergency contacts can receive messages with the patient’s daily health alerts. Furthermore, the system will keep track of the patient’s symptoms, and if anything goes wrong for a continuous period of time, the system will automatically send out reminders to schedule medical appointments. For medical appointments, a patient may be able to search for nearest doctors and schedule an appointment for him via the system. Here, Google map technology is used to search nearby doctors. A reminder is introduced in this system where all of the activities for a patient are notified on a regular basis.

Features of the application of protection measures and assistance to victims of violent crimes

Features of the application of protection measures and assistance to victims of violent crimes

The precarisation of daily life in Spain: Austerity, social policy and food insecurity

This article examines the extent to which the 2008 economic crisis has led to a shift in ways of eating among people living in precarious conditions in Spain, and the kinds of strategies they have developed to obtain daily food. Building on a literature review on precarisation in Spain and an analysis of action plans to combat food insecurity, participant-observation ethnography was carried out in Catalonia. Fieldwork was conducted during 2017–2019 in public and private spaces focusing on the food practices of 51 first-time applicants for social assistance. Qualitative data obtained from interviews and direct observation were recorded, transcribed and coded using the ATLAS-ti program to facilitate thematic analysis. Study participants’ oral narratives reveal substantial changes in food procurement and eating practices. Strategies include buying different foods, shopping less often and/or in different stores, seeking out cheaper brands, preparing simpler dishes, growing food and recycling leftovers. Their food itineraries reflect increasing reliance on charities, although a common alternative is meals prepared outside the home by family, neighbourhood, activist organisations or themselves. Eating patterns reveal not only experiences of food deprivation and social suffering, but also alternative ways of food procurement. Although food aid is based mainly on an assistance-oriented model, participatory initiatives have the potential to become political spaces that invite us to rethink the distribution of food resources and the limitations of social policies.

Information system of distribution of material aid for university students

The article discusses the solution of a number of problems related to the distribution of financial assistance for students of universities: late submission of applications, paper submission, changing categories, all this complicates the process of filing and considering applications for financial assistance, thereby increasing the burden on employees of directorates of institutes. The purpose of this work is to increase the efficiency and accessibility of this process through an information system that will allow you to submit applications online, and employees of the directorate or dean’s office to track this process in a timely manner. This article provides an algorithm for the distribution of material assistance, presents design solutions and software implementation. The developed system will allow to exclude personal interaction between the staff of the directorate and students in this process.

IoT-Based Wearable Devices for Patients Suffering from Alzheimer Disease.

The disorder of Alzheimer's (AD) is defined as a gradual deterioration of cognitive functions, such as the failure of spatial cognition and short-term memory. Besides difficulties in memory, a person with this disease encounters visual processing difficulties and even awareness and identifying of their beloved ones. Nowadays, recent technologies made this possible to connect everything that exists around us on Earth through the Internet, this is what the Internet of Things (IoT) made possible which can capture and save a massive amount of data that are considered very important and useful information which then can be valuable in training of the various state-of-the-art machine and deep learning algorithms. Assistive mobile health applications and IoT-based wearable devices are helping and supporting the ongoing health screening of a patient with AD. In the early stages of AD, the wearable devices and IoT approach aim to keep AD patients mentally active in all of life's daily activities, independent from their caregivers or any family member of the patient. These technological solutions have great potential in improving the quality of life of an AD patient as this helps to reduce pressure on healthcare and to minimize the operational cost. The purpose of this study is to explore the State-of-the-Art wearable technologies for people with AD. Significance, challenges, and limitations that arise and what will be the future of these technological solutions and their acceptance. Therefore, this study also provides the challenges and gaps in the current literature review and future directions for other researchers working in the area of developing wearable devices.

Úroveň vedomostí zdravotníkov o možnostiach poskytovania pomoci obetiam domáceho násilia

Aim: The aim of the study was to find out the awareness of healthcare workers about domestic violence and possibilities of help for domestic violence victims. Material and Methods: The method of data collection was anonymous non-standardized questionnaire of own construction. Its distribution was carried out electronically using snowball method and through the social network, in cooperation with administrators of the groups connecting professional healthcare workers, with emphasis on nurses’ community. The data collection took place in August 2022. The data analysis was carried out through the domain for electronic questionnaires construction survio.com. The study results are presented in contingency charts displaying values of absolute frequency (n) and relative frequency (%). The study involved 83 respondents, with most representation of nurses (86,7 %). Results: The results showed relatively good awareness of available possibilities of assistance to domestic violence victims. The existence of free-of-charge Infoline was known to 73,5 % of the questioned, and 72,3 % of the respondents were aware of the mail and mobile application for assistance to children. About the possibility to address non-governmental organizations were informed 92,8 % of the questioned. They were the least informed about the fact that the obligation to announce the domestic violence is implied by the law. This unawareness was presented by 28,9 % of the respondents. Summary: The contact with healthcare workers when providing nursing care to domestic violence victims is an essential part of solving the problem of a violated victim. Only erudite personnel are able to both inform a victim about the current options of help and provide the particular solutions for handling the difficult situation, with emphasis on the security of all the involved.

Residential security through the Home Assistant Platform

The etymology of the word safety means: lack of danger; feeling of peace and confidence; shelter from any danger; feeling of security. A security system of goods, values and protection of people can be implemented through an automated platform, under the name of Home Assistant. This server software application can communicate with an easy control system for fast and two-way access, which can be mounted to a restricted main entrance. The automatic opening of the access door is controlled both by stand-alone RFID (Radio-Frequency Identification) modules, which act on an electric closing mechanism, and by an automation system configured in the Home Assistant application. The ultimate goal is the security of the premises through a system that can operate both locally and online via internet connection. The research methodology was based on the study of intelligent applications for residential access, described in the literature, aiming at integration into the open-source HA platform, by developing new code sequences. I come with this paper in support of those who want to bring an improvement in the existing automation system, respectively to encourage those who want an automated residence at a higher level.

Overview of assets 2021

The 23rd International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS 2021) was successfully held between October 18th to 22nd, 2021. The ASSETS conference is the premier computing research conference exploring the design, evaluation, and use of computing and information technologies with and for people with disabilities and older adults. This year, the ASSETS conference continues its tradition of presenting innovative research on mainstream and specialized assistive technologies, accessible computing, and assistive applications of computer, network, and information technologies. 424 attendees from 24 countries and 6 continents (no one from Antarctica yet!) attended the conference, setting a new attendance record for ASSETS.

E-Commerce Assistant Application incorporating Machine Learning Image Classification

E-Commerce Assistant Application incorporating Machine Learning Image Classification

Innovative Interaction Software for Remote Assistance Application

Innovative Interaction Software for Remote Assistance Application

An Assistant Android Application "Help Me" Application

Many people find themselves in a situation where they feel threatened or scared for their lives. Those people sometimes might need assistance in carrying out certain projects or tasks or may require certain documents or would like to share certain helpful documents with other users. In this application we try to integrate all of these aiding functions and mobile technologies into one assistant application to help users who require such services, to obtain it easily in one place without any constraints. This application offers seven main functions: signing in/up, adding contacts, sending location using the panic button, asking for a request, doing a favour for a friend, uploading and downloading documents from the server, and how to use menu. We have used Java and XML for the development on the client-side and the Firebase services to develop and store data on the server-side alongside Node.js for server-side function development.

A Virtual Assistant Design and Application on Industrial Database

The development and advancement of technology allows people to access information in a variety of ways. Whether in commerce, marketing or communication, the amount and variety of data is increasing in every field. Collecting this data in different fields and drawing conclusions based on the data has become very important for the development of individuals, companies, industries, and countries, and especially collecting this data in databases has become popular. In this paper, an industrial database was created, a wireless sensor network was set up using ZigBee protocol for data collection, the collection of data in the database was done quickly and cheaply, and a natural language processing based Virtual Assistant was created to query the data. Unlike other traditional rule-based methods, Virtual Assistant has a non-predetermined structure that allows Virtual Assistant to answer different types of questions from the user. The communication between the created Sensor Network, database and Virtual Assistant is done using XMPP message protocol. Again, with the help of this protocol, a system is presented to communicate with the user. With the method presented in the study, the data in the relational database was made queryable regardless of location and platform. With the virtual help system provided, the distance between natural language and computer language is shortened and people can get information quickly and easily.

Unit Optimalization Using the QM App for Windows on Perumahan Bukit Aradiar Permai Balikpapan

<p><em>Abstract</em></p><p>Housing demand continues to increase along with the increase in economic activity and the number of residents in the city of Balikpapan according to the 2017 Central Statistics Agency as many as 636,012 people to 645,727 people. The increase in housing demand is driven by the community's perspective that home ownership must be met while housing availability is limited. Based on the Balikpapan City Government in the 2012 Regional Spatial Plan, the plan to develop a spatial pattern of cultivation areas is more directed towards the north and east parts of the city so that population growth and development are not concentrated in the city center. This is a challenge for housing providers to meet the needs of long-lived communities and migrant communities by building housing located in the East of Balikpapan City as a place to live. The increase in land prices is so high in Balikpapan due to the movement of the capital from Jakarta to East Kalimantan, making housing prices also higher. The limited land owned by the housing developer must be utilized as well as possible for the construction of housing units, construction of facilities, and the existence of green space in the housing according to government regulations related to Balikpapan City RTRW. Land owned by housing developers that vary in shape is extremely limited with the type of house being built also varies and the price of the unit offered is different for each unit. For this reason, the developer must be able to optimize the production of the type of house that will be built based on government regulations and the National Spatial Plan, optimizing the land to get the optimum profit. This optimization uses the assistive application of QM for Windows and obtained 98 units for type 40/120 and type 45/120 for 102 units with optimum profit yielding Rp 104,292,098,201 for the BEP method.</p><p> </p><p><strong><em>Keywords:</em></strong><em> </em><em>Optimization</em><em>;</em><em> QM For Windows</em><em>;</em><em> Unit.</em></p>

Design and Construction of a Smart-home Automation System (SHAS) using Nodemcu and Google Assistant

This paper presents the design and construction of a smart-home automation system using nodeMCU and Google assistant. The device consist of Enhanced Universal Synchronous Asynchronous Receiver Transmitter (EUSART) module that contains all clock generators, shift registers and data buffers necessary to perform an input or output serial data transfer independently of the device program execution. The NodeMCU (ESP8266) Wi-fi Shield connected the microcontroller to the provided Wi-fi network. The Arduino and MPLAB Programming Interface with the help of PICKit3 were used to run the code on PIC16F877A. Home appliances were controlled via a web page created using IFTTT for the voice command and the Blynk app for controlling hardware remotely and also display sensor data. IFTTT is a simple to use internet service that easily enables IoT devices to GET and POST data. The device was constructed based on low cost and reliable home controlled monitoring system for accessing and controlling electronics appliances remotely using any Smart phone with access to Google assistance or Computer web application. The device was test under different electronics appliances with different voltage capacities and was found efficient. Therefore, this device when used is capable of improving the living standard at home, reduces human effort, save energy and time thus make homes have sufficient automation.

Enhancing mental skills for better Reading-writing abilities using Interactive assistive Technology: A survey-based study for Down Syndrome Students

The aim of present study is to bring Human-Computer Interaction strategy to bridge the reading-writing issues faced by intellectual disabled Down Syndrome Students with the support of Interactive Technology. We have used mixed methodology, wherein an online survey is processed across the Pakistan to evaluate medium of computing technology accessed by Down syndrome students and to identify the problems faced in reading-writing. A practical approach carried out to observe the mental strengths and thinking potential through hands-on practice with desktop, portable devices, smart phones, and specific applications. A proposed Interactive Learning Model compensate the barriers faced in reading- writing through using assistive technology services and applications. The results show that the assistive technology and relative services enhance the thinking and decision-making abilities. Interactive technology and smart solutions provide a continuously support with touch-to-speak technology to develop language skills and expressing their thoughts, communication control and decrease frustration. Tough-type-read-spell oriented custom software to improve reading and spelling skills and to provide paperless advantage.

Dual‐mode linearity enhanced power amplifier with wideband AM‐PM compensation for 5–6‐GHz FeLAA applications

This letter presents a 5–6-GHz dual-mode power amplifier (PA) realized for further enhanced licensed assisted access application of downlink transmission. The output matching network with multiple harmonic traps and the wideband AM-PM compensation technique are used in the design. To achieve high linear output power with less variation in the wide frequency range, different bias voltages of the first stage PA are set for dual-mode operation. In the range 5–6 GHz, the PA delivers > 30 dBm saturated output power and reaches 24.4–24.8 dBm linear power at −35 dBc adjacent channel leakage ratio.

ArmSym: A Virtual Human–Robot Interaction Laboratory for Assistive Robotics

Research in human–robot interaction for assistive robotics usually presents many technical challenges for experimenters, forcing researchers to split their time between solving technical problems and conducting experiments. In addition, previous work in virtual reality setups tends to focus on a single assistive robotics application. In order to alleviate these problems, we present ArmSym, a virtual reality laboratory with a fully simulated and developer-friendly robot arm. The system is intended as a testbed to run many sorts of experiments on human control of a robotic arm in a realistic environment, ranging from an upper limb prosthesis to a wheelchair-mounted robotic manipulator. To highlight the possibilities of this system, we perform a study comparing different sorts of prosthetic control types. Looking at nonimpaired subjects, we study different psychological metrics that evaluate the interaction of the user with the robot under different control conditions. Subjects report a perception of embodiment in the absence of realistic cutaneous touch, supporting previous studies in the topic. We also find interesting correlations between control and perceived ease of use. Overall our results confirm that ArmSym can be used to gather data from immersive experiences prosthetics, opening the door to closer collaboration between device engineers and experience designers in the future.

Innovation of Micro Equity Model for Msme Business Adaptation During Pandemic Covid-19.

Large number of MSMEs have been severely hit during the Covid-19 pandemic. This study examined a micro equity financing model as an innovative answer to conventional micro loan in assisting MSMEs’ bussiness adaptation during the pandemic. The micro equity financing model employs a profit-sharing system with flexible repayment method and without collateral. A qualitative descriptive data processing approach was employed. Due to pandemic situation, interviews were conducted online to respondents of MSME that use the micro equity model in the Equitree project in Yogyakarta. The micro equity model has shown to provide many benefits to MSME business adaptation, especially in financial, marketing and product aspects, such as innovation in product development, online marketing, business assistance, flexible repayment and easier loan application.