Hybrid WebRTC Signalling for Conferencing

 

Design and Implement A Hybrid WebRTC Signalling Mechanism for Unidirectional & Bi-directional Video Conferencing

International Journal of Computer Science & Network Security

• Volume 24 Issue 9
 
• /
 
• Pages.186-194
 
• /
 
• 2024
 
• /
 
• 1738-7906(pISSN)
• • 
    
  • • doi: 10.22937/IJCSNS.2024.24.9.21

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)

WebRTC (Web Real-Time Communication) is a technology that enables browser-to-browser communication. Therefore, a signalling mechanism must be negotiated to create a connection between peers. The main aim of this paper is to create and implement a WebRTC hybrid signalling mechanism named (WebNSM) for video conferencing based on the Socket.io (API) mechanism. WebNSM was designed over different topologies such as simplex, star and mesh. Therefore it offers several communications at the same time such as one-to-one (unidirectional/bidirectional), one-to-many (unidirectional) and many-to-many (bi-directional) without any downloading or installation. In this paper, WebRTC video conferencing was accomplished via LAN and WAN networks, including the evaluation of resources in WebRTC like bandwidth consumption, CPU performance, memory usage, Quality of Experience (QoE) and maximum links and RTPs calculation. This paper presents a novel signalling mechanism among different users, devices and networks to offer video conferencing using various topologies at the same time, as well as other typical features such as using the same server, determining room initiator, keeping the communication active even if the initiator or another peer leaves, etc. This scenario highlights the limitations of CPU performance, bandwidth consumption and the use of different topologies for WebRTC video conferencing

Cited: Edan, N., Al-Sherbaz, A. and Turner, S. (2024) “Design and Implement A Hybrid WebRTC Signalling Mechanism for Unidirectional & Bi-directional Video Conferencing,” International Journal of Computer Science and Network Security. International Journal of Computer Science and Network Security, 24(9), pp. 186–194. doi: 10.22937/IJCSNS.2024.24.9.21

 Unveiling Pollution Peaks: Comparing Swarm Intelligence with Drone Hill Climber

• September 2024

• DOI: 
• 10.1109/SISY62279.2024.10737602

• Conference: 2024 IEEE 22nd Jubilee International Symposium on Intelligent Systems and Informatics (SISY)

Produce using ChatGPT

Abstract:

Climate Change has become an accelerating problem in recent years due to pollutants like greenhouse gases, with carbon dioxide being the most prominent. Similarly in time, works on the application and development of swarm intelligence using drones, along with the use of drones to monitor air pollution/ source discovery, have been carried out in isolation to date. This paper presents an investigation to discover multiple pollution sources using a variety of existing swarm intelligence algorithms, through simulated drones. This paper also presents a bespoke Drone Hill Climber (DHC) algorithm that introduces the novel of multiple drones each flying on their own set paths, with the aim of finding multiple pollution peaks at efficient speeds.

O. J. Prior, M. A. Hannan Bin Azhar, V. Sahota and S. Turner, "Unveiling Pollution Peaks: Comparing Swarm Intelligence with Drone Hill Climber," 2024 IEEE 22nd Jubilee International Symposium on Intelligent Systems and Informatics (SISY), Pula, Croatia, 2024, pp. 399-404, doi: 10.1109/SISY62279.2024.10737602.
keywords: {Climate change;Pollution;Carbon dioxide;Particle swarm optimization;Intelligent systems;Informatics;Greenhouse gases;Monitoring;Drones;Swarm Intelligence;Drones;Air Pollution Monitoring;Climate Change;Particle Swarm Optimisation;Firefly Algorithm;Artificial Bee Colony;Simulations},

Trustworthy Insights: A Novel Multi-Tier Explainable framework for ambient assisted living

 

Trustworthy Insights: A Novel Multi-Tier Explainable framework for ambient assisted living

Kasirajan, M., Azhar, H. and Turner, S. 2023. Trustworthy Insights: A Novel Multi-Tier Explainable framework for ambient assisted living . https://doi.org/10.1109/TrustCom60117.2023.00357

More details available at https://repository.canterbury.ac.uk/item/9683y/trustworthy-insights-a-novel-multi-tier-explainable-framework-for-ambient-assisted-living 

Integrating transparency, interpretability, and accountability into the design of Artificial Intelligence (AI) tools for Ambient Assisted Living (AAL) enhances user trust and acceptance. Clear explanations of the AI system's operations and decision-making process are vital, enabling users to comprehend the factors influencing predictions and recommendations. This paper introduces a novel explainable framework tailored for AAL, representing a structured approach to comprehensively understand feature importance in the decision-making process of machine learning models. The framework adopts a hierarchical approach, commencing with an overview of feature importance for the entire AAL system (Tier 0) and subsequently organising explanations into smaller subsets (Tiers 1, 2 and 3) based on user-defined measures, such as accuracy, activity types in AAL, and specific time periods. By facilitating metadata exploration and offering in-depth insights, the proposed framework augments model interpretability and user trust, ultimately empowering informed decision-making within AAL contexts.

Effect of Gait Speed on Trajectory Prediction Using Deep Learning Models for Exoskeleton Applications

 New paper

Kolaghassi, Rania, Gianluca Marcelli, and Konstantinos Sirlantzis. 2023. "Effect of Gait Speed on Trajectory Prediction Using Deep Learning Models for Exoskeleton Applications" Sensors 23, no. 12: 5687. https://doi.org/10.3390/s23125687

Effect of Gait Speed on Trajectory Prediction Using Deep Learning 

 Effect of Gait Speed on Trajectory Prediction Using Deep Learning Models for Exoskeleton Applications

Sensors

DOI https://doi.org/10.3390/s23125687

Abstract

Gait speed is an important biomechanical determinant of gait patterns, with joint kinematics being influenced by it. This study aims to explore the effectiveness of fully connected neural networks (FCNNs), with a potential application for exoskeleton control, in predicting gait trajectories at varying speeds (specifically, hip, knee, and ankle angles in the sagittal plane for both limbs). This study is based on a dataset from 22 healthy adults walking at 28 different speeds ranging from 0.5 to 1.85 m/s. Four FCNNs (a generalised-speed model, a low-speed model, a high-speed model, and a low-high-speed model) are evaluated to assess their predictive performance on gait speeds included in the training speed range and on speeds that have been excluded from it. The evaluation involves short-term (one-step-ahead) predictions and long-term (200-time-step) recursive predictions. The results show that the performance of the low- and high-speed models, measured using the mean absolute error (MAE), decreased by approximately 43.7% to 90.7% when tested on the excluded speeds. Meanwhile, when tested on the excluded medium speeds, the performance of the low-high-speed model improved by 2.8% for short-term predictions and 9.8% for long-term predictions. These findings suggest that FCNNs are capable of interpolating to speeds within the maximum and minimum training speed ranges, even if not explicitly trained on those speeds. However, their predictive performance decreases for gaits at speeds beyond or below the maximum and minimum training speed ranges.

For more details go to https://researchspace.canterbury.ac.uk/94z04/effect-of-gait-speed-on-trajecto 

Practical ways to analyse Twitter data - the new challenges

 Practical ways to analyse Twitter data - the new challenges

Invited Talk at The British Academy: Early Career Researcher Network, University of Birmingham, 12th June 2023

The focus of the talk was on using tools for Twitter analysis and some of the problems.

Exoskeleton using AI and Assistive Robotic Technology aims to help children with cerebral palsy

 Researchers from Canterbury Christ Church University has presented the UK's first lower limb Exoskeleton aimed at helping children with neurological disorders at London Tech Week 2023.

The academics were part of a three-year EU Interreg 2 Seas (European Regional Development Fund) project called MOTION. It included researchers from across four countries with the aim to develop Assistive Robotic Technology in the form of a wearable, lower limb exoskeleton to help children with cerebral palsy and other neurological conditions stand and walk as part of their rehabilitation therapy.

Professor Konstantinos Sirlantzis who leads the Artificial Intelligence and Assistive Robotics research team at the University, said: "We’re delighted to be able to have this opportunity to demonstrate the innovative design and AI-based personalised predictive control for the Exoskeleton, which was developed specifically with the consideration of the physicality and movement of children with cerebral palsy."

To read more this extract was taken from

https://www.canterbury.ac.uk/news/exoskeleton-using-ai-and-assistive-robotic-technology-aims-to-help-children-with-cerebral-palsy 

Importance of Transparency in Artificial Intelligence

 A  new paper recently published by Dr Leishi Zhang as co-author on transparency in Artificial Intelligence systems raises some interesting questions.

https://researchspace.canterbury.ac.uk/94734/the-impact-of-system-transparenc 

The Impact of System Transparency on Analytical Reasoning

CHI EA '23: Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems

April 2023

Article No.: 274Pages 1–6

https://doi.org/10.1145/3544549.3585786

Abstract

In this paper, we present the hypothesis that system transparency is critical for tasks that involve expert sensemaking. Artificial Intelligence (AI) systems can aid criminal intelligence analysts, however, they are typically opaque, obscuring the underlying processes that inform outputs, and this has implications for sensemaking. We report on an initial study with 10 intelligence analysts who performed a realistic investigation exercise using the Pan natural language system [10, 11], in which only half were provided with system transparency. Differences between conditions are analysed and the results demonstrate that transparency improved the ability of analysts to reason about the data and form hypotheses.

References

1. Ashraf Abdul, Christian von der Weth, Mohan Kankanhalli, and Brian Y. Lim. 2020. COGAM: Measuring and Moderating Cognitive Load in Machine Learning Model Explanations. Association for Computing Machinery, New York, NY, USA, 1-14. https://doi.org/10.1145/3313831.3376615

   Sule Anjomshoae, Amro Najjar, Davide Calvaresi, and Kary Främling. 2019. Explainable Agents and Robots: Results from a Systematic Literature Review. In Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (Montreal QC, Canada) (AAMAS '19). International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC, 1078-1088.

   Jessie Chen, Katelyn Procci, Michael Boyce, Julia Wright, Andre Garcia, and Michael Barnes. 2014. Situation Awareness-Based Agent Transparency.Google  https://doi.org/10.21236/ADA600351

   Karl de Fine Licht and Jenny de Fine Licht. 2020. Artificial Intelligence, Transparency, and Public Decision-Making. AI and Society 35, 4 (2020), 917-926.  https://doi.org/10.1007/s00146-020-00960-w

   D. Delmolino and M. Whitehouse. 2018. Responsible AI: A framework for building trust in your AI solutions.Google Scholar

   Penny Duquenoy, Donald Gotterbarn, Kai Kimppa, Norberto Patrignani, and B.L.William Wong. 2018. Addressing Ethical Challenges of Creating New Technology for Criminal Investigation: The VALCRI Project. 31-38.  https://doi.org/10.1007/978-3-319-89297-9_4

   Heike Felzmann, Eduard Fosch Villaronga, Christoph Lutz, and Aurelia Tamò-Larrieux. 2019. Transparency you can trust: Transparency requirements for artificial intelligence between legal norms and contextual concerns. Big Data & Society 6, 1 (2019), 2053951719860542. https://doi.org/10.1177/2053951719860542

   Sam Hepenstal, Neesha Kodagoda, Leishi Zhang, Pragya Paudyal, and B. L. William Wong. 2019. Algorithmic Transparency of Conversational Agents. In IUI Workshops.

   Sam Hepenstal, B.L. William Wong, Leishi Zhang, and Neesha Kodogoda. 2019. How analysts think: A preliminary study of human needs and demands for AI-based conversational agents. Proceedings of the Human Factors and Ergonomics Society Annual Meeting 63, 1 (2019), 178-182. https://doi.org/10.1177/1071181319631333

   Sam Hepenstal, Leishi Zhang, Neesha Kodagoda, and B. L. William Wong. 2020. Pan: Conversational Agent for Criminal Investigations. In Proceedings of the 25th International Conference on Intelligent User Interfaces Companion (Cagliari, Italy) (IUI '20). Association for Computing Machinery, New York, NY, USA, 134-135.

   Sam Hepenstal, Leishi Zhang, Neesha Kodagoda, and B. L. william Wong. 2021. Developing Conversational Agents for Use in Criminal Investigations. ACM Trans. Interact. Intell. Syst. 11, 3-4, Article 25 (aug 2021), 35 pages. https://doi.org/10.1145/3444369

   Intel.gov. 2022. Principles of artificial intelligence ethics for the intelligence community. https://www.dni.gov/index.php/features/2763-principles-of-artificialintelligence-ethics-for-the-intelligence-community. Accessed: 2022-06-16.

   G.A. Klein. 1993. A recognition-primed decision (RPD) model of rapid decision making. In Decision Making in Action: Models and Methods, G.A. Klein, Judith Orasanu, R. Calderwood, and Caroline E. Zsambok (Eds.). Norwood: Ablex Publishing Corporation, 138-147.

   G.A. Klein, R Calderwood, and D MacGregor. 1989. Critical decision method for eliciting knowledge. Transactions on Systems, Man, and Cybernetics 19, 3 (1989), 462-472. https://doi.org/10.1109/21.31053

   G. Klein, J. K. Phillips, E. L. Rall, and D. A. Peluso. 2007. A data-frame theory of sensemaking. In Expertise out of context: Proceedings of the Sixth International Conference on Naturalistic Decision Making, R. R. Hoffman (Ed.). Lawrence Erlbaum Associates Publishers, 113-155.

   David Leslie. 2019. Understanding artificial intelligence ethics and safety: A guide for the responsible design and implementation of AI systems in the public sector.The Alan Turing Institute (2019). https://doi.org/10.5281/zenodo.3240529

   Arun Rai. 2020. Explainable AI: from black box to glass box. Journal of the Academy of Marketing Science 48, 1 (January 2020), 137-141. https://doi.org/10.1007/s11747-019-00710-5

   R Roovers. 2019. Transparency and responsibility in artificial intelligence. A call for explainable AI.

   Ben Shneiderman. 2020. Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy. International Journal of Human-Computer Interaction 36, 6 (2020), 495-504.  https://doi.org/10.1080/10447318.2020.1741118

   Aaron Springer and Steve Whittaker. 2019. Progressive Disclosure: Empirically Motivated Approaches to Designing Effective Transparency. In Proceedings of the 24th International Conference on Intelligent User Interfaces (Marina del Ray, California) (IUI '19). Association for Computing Machinery, New York, NY, USA, 107-120.Google ScholarDigital Library https://doi.org/10.1145/3301275.3302322

   B.L.William Wong. 2004. Data analysis for the Critical Decision Method. The Handbook of Task Analysis for Human computer Interaction (01 2004).

   B.L.William Wong and Neesha Kodagoda. 2016. How Analysts Think: Anchoring, Laddering and Associations. Proceedings of the Human Factors and Ergonomics Society Annual Meeting 60, 1 (2016), 178-182. https://doi.org/10.1177/1541931213601040

   B.L.William Wong and Margaret Varga. 2012. Black Holes, Keyholes And Brown Worms: Challenges In Sense Making. Proceedings of the Human Factors and Ergonomics Society Annual Meeting 56 (10 2012), 287-291.  https://doi.org/10.1177/1071181312561067

2.