SciTePress - Affiliation Profile

Affiliation

Select a Subject
Refine Ontology Subject

Photonics Research - University of Southampton, United Kingdom

Context (please use complete words only)

Field

Sort by

70 Papers

Facial Profile Biometrics: Domain Adaptation and Deep Learning Approaches

Topic: Biometrics, Detection and Identification

Authors: Malak Alamri ^{1

;

2} and Sasan Mahmoodi ²

Affiliations: ¹ College of Computer and Information Science, Computer Science Department, Jouf University, Al jouf, K.S.A. , ² School of Electronic and Computer Science, University of Southampton, Southampton, U.K.

Digital Object Identifier: 10.5220/0013365700003911

Proceedings of BIOSIGNALS 2025, ISBN: 978-989-758-731-3

Quick Abstract

Previous studies indicate that human facial profiles are considered as a biometric modality and there is a bilateral symmetry in facial profile biometrics. This study examines the bilateral symmetry of the human face profiles and presents the analysis of facial profile images for recognition. A method from few-shot learning framework is proposed here to extract facial profile features. Based on domain adaptation and reverse validation, we introduce a technique known as reverse learning (RL) in this paper for the same side profiles to achieve a recognition rate of 85%. In addition, to investigate bilateral symmetry, our reverse learning model is trained and validated on the left side face profiles to measure the cross recognition of 71% for right side face profiles. Also in this paper, we assume that the right face profiles are unlabelled, and we therefore apply our reverse learning method to include the right face profiles in the validation stage to improve the performance of our algorithm for opposite side recognition. Our numerical experiments indicate an accuracy of 84.5% for cross recognition which, to the best of our knowledge, demonstrates higher performance than the state-of-the-art methods for datasets with similar number of subjects. Our algorithm based on few-shot learning can achieve high accuracies for a dataset characterized with as low as four samples per group.

An Algorithmic Approach for Quantitative Motion Artefact Grading in HRpQCT Medical Imaging

Topics: Medical Imaging; Deep Learning and Neural Networks

Authors: Thomas Cox ¹ , Sasan Mahmoodi ¹ , Elizabeth Curtis ² , Nicholas Fuggle ² , Rebecca Moon ^{2

;

3} , Kate Ward ² , Leo Westbury ² and Nicholas Harvey ^{2

;

4}

Affiliations: ¹ Faculty of Engineering and Physical Sciences, Electronics and Computer Science, University of Southampton, University Road, Southampton, U.K. , ² MRC Lifecourse Epidemiology Centre, University of Southampton, Southampton, U.K. , ³ Paediatric Endocrinology, Southampton Children’s Hospital, University Hospital Southampton NHS Foundation Trust, Southampton, U.K. , ⁴ National Institute for Health Research (NIHR) Southampton Biomedical Research Centre, University of Southampton, and University Hospital Southampton NHS Foundation Trust, U.K.

Digital Object Identifier: 10.5220/0012434900003654

Proceedings of ICPRAM 2024, ISBN: 978-989-758-684-2

Quick Abstract

High Resolution Peripheral Quantitative Computed Tomography (HRpQCT) is a modern form of medical imaging that is used to extract detailed internal texture and structure information from non-invasive scans. This greater resolution means HRpQCT images are more vulnerable to motion artefact than other existing bone imaging methods. Current practice is for scan images to be manually reviewed and graded on a one to five scale for movement artefact, where analysis of scans with the most severe grades of movement artefact may not be possible. Various approaches to automatically detecting motion artefact in HRpQCT images have been described, but these typically rely on classifying scans based on the qualitative manual gradings instead of determining the amount of artefact. This paper describes research into quantitatively calculating the degree of motion affecting an HRpQCT. This is approached by analysing the jumps and shifts present in the raw projection data produced by the HRpQCT instrument scanner, rather than using the reconstructed cross-sectional images. The motivation and methods of this approach are described, and results are provided, along with comparisons to existing work.

An Information Security Model for an IoT-enabled Smart Grid

Topics: Internet of Things; Case Studies; Security, Privacy and Trust ; Smart City Examples and Case Studies; Architecture for secure and interactive IoT; IoT Services and Applications; Firewall, access control, identity management; Intrusion and detection techniques

Authors: Abeer Akkad ^{1

;

2} , Gary Wills ¹ and Abdolbaghi Rezazadeh ¹

Affiliations: ¹ Electronic and Computer Science Dept., University of Southampton, University Road, Southampton, U.K. , ² Information Systems Dept., Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, K.S.A

Digital Object Identifier: 10.5220/0011042200003194

Proceedings of IoTBDS 2022, ISBN: 978-989-758-564-7

Quick Abstract

The evolution of an Internet of Things-enabled Smart Grid affords better automation, communication, monitoring, and control of electricity consumption. It is now essential to supply and transmit the data required, to achieve better sensing, more accurate control, wider information communication and sharing, and more rational decision-making. However, the rapid growth in connected entities, accompanied by the increased demand for electricity, has resulted in several challenges to be addressed. One of these is protecting energy information exchange proactively, before an incident occurs. It is argued that Smart Grid systems were designed without any regard for security, which is considered a serious omission, especially for data security, energy information exchange, and the privacy of both the consumers and utility companies. This research is motivated by the gap identified in the requirements and controls for maintaining cybersecurity in the bi-directional data flow within the IoT-enabled Smart Grid. The initial stages of the research define and explore the challenges and security requirements, through the literature and industrial standards. The Threat Modelling identified nine internet-based threats. The analysis proposes a security model which includes 45 relevant security controls and 7 security requirements.

Hypoxic-Ischaemic Encephalopathy Prognosis using Susceptibility Weighted Image Analysis based on Histogram Orientation Gradient

Topics: Medical Signal Acquisition, Analysis and Processing; Medical Image Acquisition, Processing, Analysis, and Detection

Authors: Zhen Tang ¹ , Sasan Mahmoodi ¹ , Angela Darekar ² and Brigitte Vollmer ³

Affiliations: ¹ School of Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, U.K. , ² Department of Medical Physics, University Hospital Southampton NHS Foundation Trust, Southampton So16 6YD, U.K. , ³ Clinical Neurosciences and Clinical and Experimental Sciences, Faculty of Medicine, University of Southampton, SO17 1BJ, U.K.

Digital Object Identifier: 10.5220/0010856800003123

Proceedings of BIOSIGNALS 2022/BIOSTEC, ISBN: 978-989-758-552-4

Quick Abstract

The aim of this study is to analyse the susceptibility-weighted magnetic resonance images (SWI) by using Histogram of Oriented Gradients (HOG) as a global feature to identify areas of the neonatal brain affected by Hypoxic-ischaemic encephalopathy (HIE). 42 infants with neonatal HIE have undergone under SW imaging in the neonatal period and have been investigated through neurodevelopmental assessment at 24 months of age. HOG features are used to represent the whole brain SW images and the region of interest separated from the brain image registration algorithm. We use k-nearest neighbours (kNN) and random forest to classify the SWI images into normal and abnormal groups, and then we compare our results to our previous work. The result shows an effective classification, which achieved an accuracy of 76.25±10.9. Our research suggests that automated analysis of neonatal SWI images can identify brain regions affected by HIE on SWI images and predict motor and cognitive outcomes.

Provisioning Security in a Next Generation Mobility as a Service System

Topics: Security, Privacy and Trust ; Smart City Examples and Case Studies; Architecture for secure and interactive IoT; Transport Safety and Mobility

Authors: Tope Omitola ¹ , Ben Waterson ² , Niko Tsakalakis ³ , Richard Gomer ¹ , Sophie Stalla-Bourdillon ⁴ , Tom Cherrett ⁵ and Gary Wills ¹

Affiliations: ¹ Electronics & Computer Science, University of Southampton, Southampton, U.K. , ² Maritime & Environmental Engineering, University of Southampton, Southampton, U.K. , ³ School of Law, University of Southampton, Southampton, U.K. , ⁴ Immuta Inc., U.S.A. , ⁵ Transportation Research Group, University of Southampton, Southampton, U.K.

Digital Object Identifier: 10.5220/0011043900003194

Proceedings of IoTBDS 2022, ISBN: 978-989-758-564-7

Quick Abstract

The urban mobility landscape is evolving at an amazing rate, with the number of mobility services growing rapidly around the world. This evolution has brought about the concept of Mobility-as-a-Service (MaaS) in providing transportation services. MaaS capitalises on the Internet of Things to provide access to seamless multi- and inter-modal mobility to the end-user. A well implemented MaaS scheme involves many stakeholders, including passengers, producing, sharing, and consuming (personal) data. In order to encourage MaaS uptake in the general population, participating stakeholders must be confident of the ensuing data privacy and security, as part of their interactions with the system. In this paper, we use STRIDE Threat Modeling framework to analyse the threats that may arise in a MaaS ecosystem. From these threats, we develop mitigations that can be used to eliminate and/or reduce such threats. This threat elicitation and their accompanying mitigations can be used as springboards to establish the necessary security to engender trust in MaaS usage.

Using Big Data Analytics to Combat Retail Fraud

Topics: Strategy ; Business for AI and Deep Learning; Business for Big Data, Internet of Things and Cloud Computing

Authors: Danni Zhang ¹ , Steffen Bayer ¹ , Gary Willis ² , Gina Frei ¹ , Enrico Gerding ² and Pk Senyo ¹

Affiliations: ¹ Southampton Business School, University of Southampton, Southampton, U.K. , ² Electronics & Computer Science, University of Southampton, Southampton, U.K.

Digital Object Identifier: 10.5220/0011042600003206

Proceedings of FEMIB 2022, ISBN: 978-989-758-567-8

Quick Abstract

Fraudulent returns are seen as a misfortune for most retailers because it reduces sales and induce greater costs and challenges in returns management. While extant research suggests one of the causes is retailers’ liberal return policies and that retailers should restrict their policies, there is no study systematically exploring the impacts of various return policies and fraud interventions on reducing different types of fraudulent behaviour and the costs and benefits of associated interventions. In this paper, we first undertook semi-structured interviews with retailers in the UK and North America to gain insights into their fraud intervention strategies, as well as conducted literature review on fraudulent returns to identify the influential factors that lead customers to return products fraudulently. On this basis, we developed a simulation model to help retailers forecast fraudulent returns and explore how different combinations of interventions might affect the cases of fraudulent returns and associated financial impacts on profitability. The background literature on fraudulent returns, the findings of interviews, and the demonstration and implications of the model on reducing fraudulent returns and related financial impacts are discussed. Our model allows retailers to make cost- effective evaluations and adopt their fraud prevention strategies effectively based on their business models.

Success Factors of Business Intelligence and Performance Dashboards to Improve Performance in Higher Education

Topics: Strategic Decision Support Systems; Requirements Analysis And Management

Authors: Asmaa Abduldaem and Andy Gravell

Affiliation: Electronics and Computer Science, Southampton University, Southampton, U.K.

Digital Object Identifier: 10.5220/0010499503920402

Proceedings of ICEIS 2021, ISBN: 978-989-758-509-8

Quick Abstract

The need for more effective communication becomes more important as the size of an organisation increases. This underlines the importance of using tools like Business Intelligence (BI) and dashboards to monitor and improve their output, as well as to improve accuracy and efficiency of the data that is available. However, there is a lack of understanding of applying analytics and strategic insight into analytics in Higher Education (HE), compared to other sectors such as business, government, and healthcare. In addition, the use of BI and dashboards in HE has been studied by a small number of papers, which is particularly limited in investigating the factors to ensure successful application within this context or understanding the metrics that determine this success. This highlights the importance of understanding successful adoption of such technologies to improve performance and decision-making processes, particularly within HE institutions. In this paper, we concentrate on investigating successful adoption of business intelligence and department-related level of tactical dashboards to support performance measurement and decision-making processes in HE. As the research area is complex and multidimensional, the triangulation method has been applied to support a rich set of data and a mixture of a qualitative approach to gather insights into potential factors, and a quantitative approach to confirm these factors. By adapting the concept of Balanced scorecard to measure the success factors, we conjecture that it would enhance successful adoption within this sector.

A Security Framework to Protect Data in Cloud Storage

Topics: Conceptual frameworks and models; Emerging issues and recommendations for organizational security; Surveys and their quantitative analysis; Information systems related issues

Authors: Farashazillah Yahya ¹ , Victor Chang ² , Robert John Walters ³ and Gary Brian Wills ³

Affiliations: ¹ Faculty of Computing and Informatics, Universiti Malaysia Sabah, Kota Kinabalu, Sabah and Malaysia , ² International Business School Suzhou, Xi'an Jiaotong-Liverpool University, Suzhou and China , ³ Electronics and Computer Science, University of Southampton, Southampton and U.K.

Digital Object Identifier: 10.5220/0007737603070314

Proceedings of IoTBDS 2019, ISBN: 978-989-758-369-8

Quick Abstract

With the success and widespread adoption of Cloud Computing Cloud storage has become the storage option of choice for many computer users wishing to keep their data online. This paper presents a framework to explore and evaluate security threats to data held in Cloud Storage. The Cloud Storage Security Framework (CSSF) has been developed both from consideration of established good practice as described in existing literature and the opinions of cloud storage managers and experts using a questionnaire and separate interviews. The purpose of the framework is to support researchers and managers of Cloud storage to understand the nine identified factors of security in Cloud storage and how to ensure security measures are successful. CSSF can also integrate with another framework to produce a greater impact and strengthens its research contributions.

Recommendations from Cold Starts in Big Data

Topics: Large-scale Information Systems and Applications; Big Data Algorithm, Methodology, Business Models and Challenges

Authors: David Ralph ¹ , Yunjia Li ² , Gary Wills ¹ and Nicolas G. Green ¹

Affiliations: ¹ Electronics and Computer Sciences (ECS), University of Southampton, University Rd, Southampton, SO17 1BJ and U.K , ² Launch International LTD, 3000a Parkway, Whiteley, Fareham, PO15 7FX and U.K

Digital Object Identifier: 10.5220/0007798801850194

Proceedings of IoTBDS 2019, ISBN: 978-989-758-369-8

Quick Abstract

In this paper, we introduce Transitive Semantic Relationships (TSR), a new technique for ranking recommendations from cold-starts in datasets with very sparse, partial labelling, by making use of semantic embeddings of auxiliary information, in this case, textual item descriptions. We also introduce a new dataset on the Isle of Wight Supply Chain (IWSC), which we use to demonstrate the new technique. We achieve a cold start hit rate @10 of 77% on a collection of 630 items with only 376 supply-chain supplier labels, and 67% with only 142 supply-chain consumer labels, demonstrating a high level of performance even with extremely few labels in challenging cold-start scenarios. The TSR technique is generalisable to any dataset where items with similar description text share similar relationships and has applications in speculatively expanding the number of relationships in partially labelled datasets and highlighting potential items of interest for human review. The technique is also appropriate for use as a recommendation algorithm, either standalone or supporting traditional recommender systems in difficult cold-start situations.

The Feasibility of using V2G to Face the Peak Demand in Warm Countries

Topic: Smart Grid and V2G

Authors: Ibrahem A. Almansour , Enrico H. Gerding and Gary Wills

Affiliation: University of Southampton, United Kingdom

Digital Object Identifier: 10.5220/0006661502380242

Proceedings of VEHITS 2018, ISBN: 978-989-758-293-6

Quick Abstract

As a result of the very difficult weather in Saudi Arabia during the summer, there is too high power peak demand in the grid and this is expected to increase in the next decade. To fix this problem, power consumers should participate in the power production. Vehicle-to-grid (V2G), one of the efficient sustainable technologies, can offer this opportunity. It is defined as a concept where electric vehicle (EV) provides electric to the grid when parked. This investigation looks at the feasibility of using V2G to mitigate the problem of highest electricity peak demand in the summer period in one of the warmest countries of the world (Saudi Arabia). We conduct a survey in order to serve this issue and we use information from Saudi Arabia electricity authority. We found that, V2G is a promising solution to the peak demand challenge in the summer in Saudi Arabia since there is about 80% of the sample interested in using V2G technology. Moreover, 90% of the participants used their vehicles less than 4 hours daily. Furthermore, in the summer period, most of the participants park their vehicles for the longest time between 13:00 to 18:00, which is the peak demand period.

Context (please use complete words only)

Field

Sort by

Topic(s):

Filter listed results, by

Publication date

From:

To:

Author

Locate Author in list below

Data pager
Data pager
1 2 3 4 5 6 7 8 9 10 ... Page 1 of 17, items 1 to 10 of 163.

Add Author(s) to filter:

Gary B. Wills (17)

Robert J Walters (12)

Hugh C. Davis (6)

Sasan Mahmoodi (6)

Su White (5)

R. Crowder (4)

D. M. Simpson (4)

Natalia Angarita (3)

David M. Simpson (3)

Lester Gilbert (3)

Conference

Locate Conference in list below

Data pager
Data pager
1 2 3 Page 1 of 3, items 1 to 10 of 25.

Add Conference(s) to filter:

BIOSIGNALS(11)

ICEIS(6)

VISAPP(6)

CSEDU(5)

IoTBDS(5)

WEBIST(4)

ICPRAM(4)

SIMULTECH(3)

CLOSER(3)

BIOINFORMATICS(2)

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject: