Augmented and virtual reality (AR/VR) hold significant potential to transform how we communicate, collaborate, and interact with others. However, there has been a lack of work to date investigating accessibility barriers in relation to immersive technologies for people with disabilities. To address current gaps in knowledge, we led two multidisciplinary sandpits with key stakeholders (including academic researchers, AR/VR industry specialists, people with lived experience of disability, assistive technologists, and representatives from national charities and special needs colleges) to collaboratively explore and identify existing challenges with AR and VR experiences. We present key themes that emerged from sandpit activities and map out the interaction barriers identified across a spectrum of impairments (including physical, cognitive, visual, and auditory disabilities). We conclude with recommendations for future work addressing the challenges highlighted to support the development of more inclusive AR and VR experiences. 

/pdf/inclusive-ar-vr-accessibility-barriers-for-immersive-1in5iarl.pdf

Inclusive AR/VR: Accessibility Barriers for Immersive Technologies

Augmented and virtual reality experiences present significant barriers for disabled people, making it challenging to fully engage with immersive platforms. Whilst researchers have started to explore potential solutions addressing these accessibility issues, we currently lack a comprehensive understanding of research areas requiring further investigation to support the development of inclusive AR/VR systems. To address current gaps in knowledge, we led a series of multidisciplinary sandpits with relevant stakeholders (i.e., academic researchers, industry specialists, people with lived experience of disability, assistive technologists, and representatives from disability organisations, charities, and special needs educational institutions) to collaboratively explore research challenges, opportunities, and solutions. Based on insights shared by participants, we present a research agenda identifying key areas where further work is required in relation to specific forms of disability (i.e., across the spectrum of physical, visual, cognitive, and hearing impairments), including wider considerations associated with the development of more accessible immersive platforms. 

Inclusive Augmented and Virtual Reality: A Research Agenda

PURPOSE
Visually impaired people (VIP) find it challenging to understand and gain awareness of their surroundings. Most activities require the use of the auditory or tactile senses. As such, assistive systems which are capable of aiding visually impaired people to understand, navigate and form a mental representation of their environment are extensively being studied and developed. The aim of this paper is to provide insight regarding the characteristics, as well as the advantages and drawbacks of different types of sonification strategies in assistive systems, to assess their suitability for certain use-cases.


MATERIALS AND METHODS
To this end, we reviewed a sizeable number of assistive solutions for VIP which provide a form of auditory feedback to the user, encountered in different scientific databases (Scopus, IEEE Xplore, ACM and Google Scholar) through direct searches and cross-referencing.


RESULTS
We classified these solutions based on the aural information they provide to the VIP - alerts, guidance and information about their environment, be it spatial or semantic. Our intention is not to provide an exhaustive review, but to select representative implementations from recent literature that highlight the particularities of each sonification approach.


CONCLUSIONS
Thus, anyone who is intent on developing an assistive solution will be able to choose the desired sonification class, being aware of the advantages/disadvantages and at the same time having a fairly wide selection of articles from the representative class.

A review of sonification solutions in assistive systems for visually impaired people.

Human activity recognition (HAR) using wearable sensors enables continuous monitoring for healthcare applications. However, the conventional centralised training of deep learning models on sensor data poses challenges related to privacy, communication costs, and on-device efficiency. This paper proposes a federated learning framework integrating spiking neural networks (SNNs) with long short-term memory (LSTM) networks for energy-efficient and privacy-preserving HAR. The hybrid spiking-LSTM (S-LSTM) model synergistically combines the event-driven efficiency of SNNs and the sequence modelling capability of LSTMs. The model is trained using surrogate gradient learning and backpropagation through time, enabling fully supervised end-to-end learning. Extensive evaluations of two public datasets demonstrate that the proposed approach outperforms LSTM, CNN, and S-CNN models in accuracy and energy efficiency. For instance, the proposed S-LSTM achieved an accuracy of 97.36% and 89.69% for indoor and outdoor scenarios, respectively. Furthermore, the results also showed a significant improvement in energy efficiency of 32.30%, compared to simple LSTM. Additionally, we highlight the significance of personalisation in HAR, where fine-tuning with local data enhances model accuracy by up to 9% for individual users. 

A Privacy and Energy-Aware Federated Framework for Human Activity Recognition

The relevance of this research is determined by the need to study the issues of improving data storage technologies for complex telemedicine systems. The objective is to create a multi-layered data storage model for complex telemedicine systems to ensure the most complete use of their capacity and the timely expansion of existing storage. The research is conducted on the basis of an analysis of existing opportunities and problems in the field of data storage technologies. An analysis of the main features of the development of data storage technologies revealed that the existing models have no detailed description of the recording and physical storage of data bits, which is necessary for describing the storage process. Different architectures are reviewed, and their strengths and weaknesses are discussed. Within the framework of a demonstration experiment using the Kohonen neural network apparatus as a tool for solving the problem of placing objects in accordance with the required parameters, it is shown that the proposed storage system resource management model is operable and allows solving the problem of rational use of physical resources. As a result, a multilevel model of data storage is proposed, which combines the levels of storage process organization and technology. The distinguishing feature of this method is the comparison of storage organization levels, data media, and characteristics of physical storage and stored files. Doi: 10.28991/HIJ-2023-04-04-09 Full Text: PDF

Forming the Architecture of a Multi-Layered Model of Physical Data Storage for Complex Telemedicine Systems

With the advances in IoT and edge-computing, Federated Learning is ever more popular as it offers data privacy. Low-power spiking neural networks (SNN) are ideal candidates for local nodes in such federated setup. Most prior works assume that the participating nodes have uniform compute resources, which may not be practical. In this work, we propose a federated SNN learning framework for a realistic heterogeneous environment, consisting of nodes with diverse memory-compute capabilities through activation-checkpointing and time-skipping that offers ~$4\times$ reduction in effective memory requirement for low-memory nodes while improving the accuracy upto 10% for non-independent and identically-distributed data.

Federated Learning with Spiking Neural Networks in Heterogeneous Systems

Video analytics have a wide range of applications and has attracted much interest over the years. While it can be both computationally and energy intensive, video analytics can greatly benefit from in/ near memory compute. The practice of moving compute closer to memory has continued to show improvements to performance and energy consumption and is seeing increasing adoption. Recent advancements in solid state drives (SSDs) have incorporated near memory Field Programmable Gate Arrays (FPGAs) with shared access to the drive’s storage cells. These near memory FPGAs are capable of running operations required by video analytic pipelines such as object detection and template matching. These operations are typically executed using Convolutional Neural Networks (CNNs). A CNN is composed of multiple individually processed layers which perform various image processing tasks. Due to lack of resources, a layer may be partitioned into more manageable sub-layers. These sub-layers are then processed sequentially, however some sub-layers can be processed simultaneously. Moreover, the storage cells within FPGA equipped SSD’s are capable of being augmented with in-storage compute to accelerate CNN workloads and exploit the intra parallelism within a CNN layer. To this end we present our work, which leverages heterogeneous architectures to create an in/near-storage acceleration solution for video analytics. We designed a NAND flash accelerator, and an FPGA accelerator, then mapped and evaluated several CNN benchmarks. We show how to utilize FPGAs, local DRAMs, and in-memory SSD compute to accelerate CNN workloads. Our work also demonstrates how to remove unnecessary memory transfers to save latency and energy.

/pdf/fusing-in-storage-and-near-storage-acceleration-of-305ycenr.pdf

Fusing In-Storage and Near-Storage Acceleration of Convolutional Neural Networks

A Graphical Representation of Sensor Mapping for Machine Tool Fault Monitoring and Prognostics for Smart Manufacturing

An investigation of scheduling policies for multimedia systems

With advancement of recent network and chip technologies, IoT devices are becoming smarter with increasing compute power, bandwidth, and storage available on the device. This enables intelligent decision making and information transferring on the devices and unleashes the power of AIoT (Artificial Intelligence of Things) that supports applications such as smart city/agriculture/manufacturing/health care and self-driving scenarios. The AIoT Workshop is a forum for researchers, scientists, engineers, and practitioners to share and learn AI powered IoT solutions. The AIoT is a multi-disciplinary area, which include but not limited to IoT, AI/ML, embedded systems, networking, and stream analytics. The 5th AIoT workshop will be hosted in person in conjunction with the 28th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2022). The workshop program consists of keynotes, invited talks, accepted technical paper presentations, as well as a digital agriculture hackathon panel

The 5th Artificial Intelligence of Things (AIoT) Workshop

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Vijaykrishnan Narayanan

Author Tools

Chat about Author