Yasmine Arafa

Followers

Following

Co-author

Public Views

Interests

Uploads

Papers by Yasmine Arafa

Communicating Affect in a Mulit-Agent System

We describe an operational approach to enabling the computational perception required for automat... more We describe an operational approach to enabling the computational perception required for automated generation of affective behaviour through inter-agent communication in multi-agent real-time environments. The research is investigating the potential of extending current agent communication languages so as they not only convey the content of knowledge exchange but also so they can communicate affective attitudes about the shared knowledge. Providing a necessary component of the framework required for autonomous agent, with affective behaviour, development with which we may bridge the gap between current research in psychological theory and practical implementation of social multi-agent systems.

Download

Multi-Scale Attention Network for Diabetic Retinopathy Classification

IEEE Access, 2021

Diabetic Retinopathy (DR) is a highly prevalent complication of diabetes mellitus, which causes l... more Diabetic Retinopathy (DR) is a highly prevalent complication of diabetes mellitus, which causes lesions on the retina that affect vision which may lead to blindness if it is not detected and diagnosed early. Convolutional neural networks (CNN) are becoming the state-of-the-art approach for automatic detection of DR by using fundus images. The high-level features extracted by CNN are mostly utilised for the detection and classification of lesions on the retina. This high-level representation is capable of classifying different DR classes; however, more effective features for detecting the damages are needed. This paper proposes the multi-scale attention network (MSA-Net) for DR classification. The proposed approach applies the encoder network to embed the retina image in a high-level representational space, where the combination of mid and high-level features is used to enrich the representation. Then a multi-scale feature pyramid is included to describe the retinal structure in a different locality. Furthermore, to enhance the discriminative power of the feature representation a multi-scale attention mechanism is used on top of the high-level representation. The model is trained in a standard way using the cross-entropy loss to classify the DR severity level. In parallel as an auxiliary task, the model is trained using the weakly annotated data to detect healthy and non-healthy retina images. This surrogate task helps the model to enrich its discriminative power for distinguishing the non-healthy retina images. The proposed method when implemented has achieved outstanding results on two public datasets: EyePACS and APTOS.

Download

Virtual Social Robot Enhances the Social Skills of Children with HFA

Cognitive Resource Analyzer for Cellular Network Ecosystems

IEEE Transactions on Cognitive Communications and Networking, 2022

Training Social Skills of Children with ASD Through Social Virtual Robot

2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), 2021

In this paper, the researchers presenting an ongoing study that aims to evaluate the effectivenes... more In this paper, the researchers presenting an ongoing study that aims to evaluate the effectiveness of combing Virtual Reality (VR) and social robot as a novel approach to enhance the social skills of children with autism spectrum disorders (ASD). Using Unity 3D, a desktop Virtual environment that employs a virtual robot to interact with the participants through social skill training programme has been developed. 15 children with ASD are participating in the study to evaluate the effectiveness of the developed tool. The initial results show improvement in the skills of the participants.

Deep Learning Prediction of Response to Anti-VEGF among Diabetic Macular Edema Patients: Treatment Response Analyzer System (TRAS)

Diagnostics, 2022

Diabetic macular edema (DME) is the most common cause of visual impairment among patients with di... more Diabetic macular edema (DME) is the most common cause of visual impairment among patients with diabetes mellitus. Anti-vascular endothelial growth factors (Anti-VEGFs) are considered the first line in its management. The aim of this research has been to develop a deep learning (DL) model for predicting response to intravitreal anti-VEGF injections among DME patients. The research included treatment naive DME patients who were treated with anti-VEGF. Patient’s pre-treatment and post-treatment clinical and macular optical coherence tomography (OCT) were assessed by retina specialists, who annotated pre-treatment images for five prognostic features. Patients were also classified based on their response to treatment in their post-treatment OCT into either good responder, defined as a reduction of thickness by >25% or 50 µm by 3 months, or poor responder. A novel modified U-net DL model for image segmentation, and another DL EfficientNet-B3 model for response classification were devel...

Download

Modelling interface agents for personality-based behaviour

IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028)

Visually synthesising the metaphor of life-like visual Personal Service Assistants (PSAs) is the ... more Visually synthesising the metaphor of life-like visual Personal Service Assistants (PSAs) is the focus of much current research. Often the complex visual requirements of the PSA means that little attention is given to the underlying infrastructure necessary to support the reasoning requirements of such a metaphor. This lack of support, from a software engineering perspective, means that many designs and implementations are application specific thus re-use of the designs and implementations are limited. To address this problem our research goes behind the scenes of visual stage representation to provide a technical infrastructure enabling the creation of more believable life-like interface characters based on a structured meta-representation called the Asset Description Language (ADL). The language is extended to enable agents to communicate emotions with other agents (software or human). Hence this explicit representation of emotions within the communication means that an agent can reason about these emotions and respond in an appropriate manner either visually to a human or through communication with another agent. This response permits an agent to exhibit personality. Through the provision of a structured metarepresentation we aim to evaluate the effect personality-based behaviour on interactive user interfaces as well as on other service agents in a multi-agent environment. As the representation provides some basic general design primitives which are not application specific means that re-use of our infrastructure by other developers is possible.

Download

Development and deployment of a multi-agent system for public service access

Proceedings of the third annual conference on Autonomous Agents - AGENTS '99, 1999

In this paper we summarise the technology developments and results of a large-scale hardware and ... more In this paper we summarise the technology developments and results of a large-scale hardware and software technology development that required both multimedia and multi-agents. The KIMSAC project (a European acts project -Kiosk-based Integrated Multimedia System Access to Citizens) started in September 95 with the vision of using the Personal Service Assistant Metaphor to provide public services to a variety of users. The project anticipated that the users would be of varying ages, education and technology awareness as the application to be supported included social services (e.g. income support) and employment services (e.g. finding jobs and training courses). Hence any solution would have to support a diverse set of users and be able to support distributed information and service access. The distributed solution was required as the two user organisations supporting the domain requirements were independent government organisations, the hardware and location requirements, the development partners themselves were distributed over five major European countries and the end-user was the public. The KIMSAC solution was tested on two sets of real user trials based in Ireland. Trial 1 completed in June 97 and the second trial started July 98. As the project nears completion, we summarise in this paper an analysis of the software design and development.

Download

Conversational Sales Assistants

believable embodied agents requires an awareness of context and the capability to communicate wit... more believable embodied agents requires an awareness of context and the capability to communicate with speech and gestures. We are concerned with developing such agents for use as sales assistants in a virtual marketplace. We employ a communication model which takes a public perspective on the meaning of communicative acts to enhance the agent's social awareness. Additionally the agent draws private inferences to build a model of the user. The agent uses a BDI model to reason about its contextual information and plan communicative acts. The speech and gestures generated by the agent are integrated using a script language. We contend that the integration of these components will help us to achieve contextual embodied agents.

Download

Improving the performance of the Proof-of-Work Consensus Protocol Using Machine learning

Blockchain technology has proven to be secured and reliable technology by bringing security, trus... more Blockchain technology has proven to be secured and reliable technology by bringing security, trust and data integrity to distributed systems. It brought a new paradigm that helps in the existence of the cryptocurrency and eliminating the third party in a financial transaction. It has the potential of optimising, enhancing streamlining many processes outside the cryptocurrency and financial sector but the adoption of the technology is limited by the hindering performance issues. These issues are mostly around the Proof-of-Work (PoW) consensus protocol that is used by Bitcoin and Ethereum and referred to as the most secured and decentralised protocol thus, the most reliable. Unfortunately, the protocol suffers a performance degrade with the increasing size and number of transactions because of its complexity. Many industries, researchers and organisation have been working on addressing these issues but most of the attempts result in facing another issue referred to as the scalability ...

Download

Sustaining entrepreneurial ecosystems with ebarts

ebarts is a global, digital currency, based on the provision of a better means of bartering. It i... more ebarts is a global, digital currency, based on the provision of a better means of bartering. It is a social currency that is neither bought nor issued, but is created by users in trusted exchanges. All transactions are facilitated through a multi-platform app. The service is cross-border to support entrepreneurs and facilitate the creation of ecosystems of complementary social economies. Many entrepreneurs have great ideas, energy and skills, but lack cash. Expertise, spare capacity, and goods/services procurement can be financed with ebarts. New networks created through trusted exchange will sustain and promote businesses, and in communities. The goal of ebarts is democratisation of money.

Blockchain and IoT-based Secure Multimedia Retrieval System for a Massive Crowd

Proceedings of the 2019 on International Conference on Multimedia Retrieval, 2019

Blockchain's properties in addressing trust in highly decentralized environments can make it an e... more Blockchain's properties in addressing trust in highly decentralized environments can make it an enabler for novel sharing economy services. In this paper, we demonstrate the practicality of blockchain-based Secure IoT as a Service (SIoTaaS), where an IoT device can be rented from a service provider, securely and in a privacy-preserving fashion. Our framework allows the simultaneous operations of distinct providers of IoT-based sharing economy services at a large scale. Multiple parties can securely share text and multimedia in the context of location and point-ofinterest sharing, perform financial transactions by hiding true identity of parties involved in various online transactions, perform user and IoT registration, transfer value transactions via Ethereum tokens between providers and consumers, as well as raw IoT data payload. This can turn smart room IoT devices, such as smart locks, light bulbs, air conditioning and fans into rentable business entities within a secure sharing economy platform. We will demonstrate such a proof of concept IoT sharing economy framework, which is specifically designed to support the temporary IoT needs of very large numbers of users, such as Hajj pilgrims concentrating for a short period of time at a single area in Saudi Arabia.

Download

Payments as We Know Them Are Changing––ebarts the Social eCurrency: Tomorrow’s Cash

The Book of Payments, 2016

ebarts is a mutual exchange digital currency, which enables people to buy and sell without money.... more ebarts is a mutual exchange digital currency, which enables people to buy and sell without money. It has been created with a strong social purpose to unlock idle skills and resources within communities, and to encourage the growth of a social economy. ebarts are used in a secure, mobile-based marketplace for trading goods and services, and generate value from exchange. In this paper, we discuss the user-centred design process we have employed to build an ebarts marketplace platform, focusing on people’s expectations for creating and using ebarts. Our design reflects our findings that people are geared by a want to reduce waste and generate value from possessions, skills and time that would otherwise be wasted. Correlating people’s responses from focus groups indicates that social entrepreneurship can be nurtured by such marketplaces, and that there is need for a space to be created in society for individuals to engage their entrepreneurial creativity for their own benefit as well as directly affecting their communities. Finally, based on our development of ebarts we present a framework with which to understand the varieties of outcomes an ebarts-based marketplace can achieve and how it can strategically exploit the changes such marketplaces may bring.

The BCS Appathon Challenge at Greenwich

Compass: Journal of Learning and Teaching, 2016

The BCS Appathon set out to engage as many people as possible in the UK during one hour in progra... more The BCS Appathon set out to engage as many people as possible in the UK during one hour in programming an app for their mobile phones. Just over 50 people took part at Greenwich: students, staff, families and members of the general public. The Appathon's aim was to get participants to develop their own simple app during a one hour highly interactive workshop. The workshop continued on allowing Appathon attendees to work developing apps of their own design. In the concluding session, participants had an opportunity to present their apps in a “show and tell” activity.The success of the Appathon has encouraged staff in the department to think of how it could be employed with first year students who are active smart phone users but find programming difficult and lack confident when starting to learn programming. By putting first year students through the Appathon experience, we hope to create a large pool of student ambassadors who can work with us in taking the Appathon to local sc...

Download

A High Level Service-Based Approach to Software Component Integration

2012 Sixth International Conference on Complex, Intelligent, and Software Intensive Systems, 2012

This paper motivates and sets out a framework for a high-level approach to software component int... more This paper motivates and sets out a framework for a high-level approach to software component integration. The framework builds on the concept of SaaS (Software as a Service) and uses a service ontology for the annotation of software components with formal specifications. The ontology is used to instruct interoperability between software components through a unified API interface. The impetus for this approach is to provision for smooth integration, management and scalability in a collaborative and distributed development environment.

Download

Ebarts - Democratic Money

Conventional money depends upon scarcity to maintain its value and for this reason there will nev... more Conventional money depends upon scarcity to maintain its value and for this reason there will never be enough CM to do all the things that we need to do, for example provide education, care and opportunities. To do this, a new kind of money is needed. ebarts is a multiplatform, global digital currency. ebarts is based on barter, and is created by the users as they buy and sell from one another. It is a system of transferrable IOUs. Because ebarts is created by the users, there will always be enough currency to facilitate exchange, potentially opening up a new social economy. ebarts is the basis of democratic money.

Download

Indicators to the Effect of Agent Technology on Consumer Loyalty

A Framework for Supporting Multimodal Conversational Characters in a Multi-agent System

Lecture Notes in Computer Science, 2000

It is generally argued that one of the problems with such interface characters today is their ina... more It is generally argued that one of the problems with such interface characters today is their inability to respond believably or adequately to the context of an interaction and the surrounding environment. Affective behaviour is used to better express responses to interaction context and provide more believable visual expressive responses. We describe an operational approach to enabling the computational perception required for the automated generation of affective behaviour through inter-agent communication in multi-agent real-time environments. The research is investigating the potential of extending current agent communication languages so as they not only convey the semantic content of knowledge exchange but also they can communicate affective attitudes about the shared knowledge. Providing a necessary component of the framework required for autonomous agent development with which we may bridge the gap between current research in psychological theory and practical implementation of social multi-agent systems.

Download

Virtual personal service assistants: real-time characters with artificial hearts

IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028)

Over the last years there has been a growing consensus that new generation interfaces turn their ... more Over the last years there has been a growing consensus that new generation interfaces turn their focus on the human element by enriching Human-Computer Communication with an Affective dimension. Affective generation of autonomous agent behaviour aspires to give computer interfaces emotional states that relate and take into account user as well as system environment considerations. Internally, through computational models of artificial hearts (emotion and personality), and externally through believable multi-modal expression augmented with quasi-human characteristics. Computational models of affect are addressing problems of how agents arrive at a given affective state and how these states are expressed through natural multimodal communicative interaction. Much of this work is targeting the entertainment environment and generally does not address the real-time requirements of multi-agent systems, where behaviour is dynamically changing based on agent goals as well as the shared data and knowledge. This paper discusses one of the requirements for real-time realisation of Personal Service Assistant interface characters. We describe an operational approach to enabling the computational perception required for the automated generation of affective behaviour through inter-agent communication in multi-agent real-time environments. The research is investigating the potential of extending current agent communication languages so as they not only convey the semantic content of knowledge exchange but also they can communicate affective attitudes about the shared knowledge. Providing a necessary component of the framework required for real-time autonomous agent development with which we may bridge the gap between current research in psychological theory and practical implementation of social multi-agent systems.

Download

Building Multi-modal Personal Sales Agents as Interfaces to E-commerce Applications

Lecture Notes in Computer Science, 2001

... paper addresses three distinct components of an overall framework for developing lifelike, mu... more

Yasmine Arafa

Uploads

Papers by Yasmine Arafa

Log In