About
65
Publications
19,708
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
652
Citations
Publications
Publications (65)
Herding behavior has become a familiar phenomenon to investors, with potential dangers of both undervaluing and overvaluing assets, while also threatening market stability. This study contributes to the literature on herding behavior by using a recent dataset, covering the most impactful events of recent years. To our knowledge, this is the first s...
For general insurance pricing, aligning losses with accurate premiums is crucial for insurance companies’ competitiveness. Traditional actuarial models often face challenges like data heterogeneity and mismeasured covariates, leading to misspecification bias. This paper addresses these issues from a Bayesian perspective, exploring connections betwe...
Background/Objectives: Predicting patient readmission is an important task for healthcare risk management, as it can help prevent adverse events, reduce costs, and improve patient outcomes. In this paper, we compare various conventional machine learning models and deep learning models on a multimodal dataset of electronic discharge records from an...
Predicting patient readmission is an important task for healthcare risk management, as it can help prevent adverse events, reduce costs, and improve patient outcomes. In this paper, we compare various conventional machine learning models on a multimodal dataset of electronic discharge records from an Irish acute hospital. We \khoi{evaluate the effe...
Innovative approaches are needed for managing risk and system change in healthcare. This paper presents a case study of a project that took place over two years, taking a systems approach to managing the risk of healthcare acquired infection in an acute hospital setting, supported by an Access Risk Knowledge Platform which brings together Human Fac...
Herding behavior has become a familiar phenomenon to investors, carrying the potential danger of both undervaluing and overvaluing assets, while also threatening market stability. This study contributes to the literature on herding behavior by using a more recent dataset to cover the most impactful events of recent years. To our knowledge, this is...
Similarly to the majority of deep learning applications, diagnosing skin diseases using computer vision and deep learning often requires a large volume of data. However, obtaining sufficient data for particular types of facial skin conditions can be difficult, due to privacy concerns. As a result, conditions like rosacea are often understudied in c...
In actuarial practice, the modeling of total losses tied to a certain policy is a nontrivial task due to complex distributional features. In the recent literature, the application of the Dirichlet process mixture for insurance loss has been proposed to eliminate the risk of model misspecification biases. However, the effect of covariates as well as...
We employ graph-based methods to examine the connectedness between cryptocurrencies of different market caps over time. By applying denoising and detrending techniques inherited from Random Matrix Theory and the concept of the so-called Market Component, we are able to extract new insights from historical return and volatility time series. Notably,...
The high dropout rates in programming courses emphasise the need for monitoring and understanding student engagement, enabling early interventions. This activity can be supported by insights into students’ learning behaviours and their relationship with academic performance, derived from student learning log data in learning management systems. How...
In actuarial practice, the modeling of total losses tied to a certain policy is a non-trivial task. Traditional parametric models to predict total losses have limitations due to complex distributional features such as extreme skewness, zero inflation, multi-modality, etc., and the lack of explicit solutions for log-normal convolution. In the recent...
Similar to the majority of deep learning applications, diagnosing skin diseases using computer vision and deep learning often requires a large volume of data. However, obtaining sufficient data for particular types of facial skin conditions can be difficult due to privacy concerns. As a result, conditions like Rosacea are often understudied in comp...
Channel Integration is a crucial task for retailers in order to generate a seamless customer experience. This is particularly the case for assortments. Customers expect an identical assortment along all channels or customer confusion can occur, potentially leading to purchase abandonment or postponement and thus to losses in sales. Mental models ca...
The concept of Enterprise Architecture is suitable for managing the complexity of heterogeneous systems and technologies in Smart Cities. However, many cities and their urban governance processes still face the challenges of digitalizing public services. This paper aims to assess the applicability of TOGAF in a real-world Smart City following a cas...
We analyze the correlation between different assets in the cryptocurrency market throughout different phases, specifically bearish and bullish periods. Taking advantage of a fine-grained dataset comprising 34 historical cryptocurrency price time series collected tick-by-tick on the HitBTC exchange, we observe the changes in interactions among these...
We analyze tick-by-tick data representing major cryptocurrencies traded on some different cryptocurrency trading platforms. We focus on such quantities like the inter-transaction times, the number of transactions in time unit, the traded volume, and volatility. We show that the inter-transaction times show long-range power-law autocorrelations. The...
We analyse tick-by-tick data representing major cryptocurrencies traded on some different cryptocurrency trading platforms. We focus on such quantities like the inter-transaction times, the number of transactions in time unit, the traded volume, and volatility. We show that the inter-transaction times show long-range power-law autocorrelations that...
The rapid increase and adoption of new Information Technologies (IT) in Smart Cities make the provision of public services more efficient. However, various municipalities and cities deal with challenges to transform and digitize city services. Smart Cities have a high degree of complexity where offered city services must respond to the concerns and...
Purpose
The transition to omnichannel retail is the recognized future of retail, which uses digital technologies (e.g. augmented reality shopping assistants) to enhance the customer shopping experience. However, retailers struggle with the implementation of such technologies in brick-and-mortar stores. Against this background, the present study inv...
Due to the COVID19 pandemic, more higher-level education programmes have moved to online channels, raising the issues in monitoring students’ learning progress. Thanks to advances in online learning systems, however, student data can be automatically collected and used for the investigation and prediction of the students’ learning performance. In t...
Experts rely on fraud detection and decision support systems to analyze fraud cases, a growing problem in digital retailing and banking. With the advent of Artificial Intelligence (AI) for decision support, those experts face the black-box problem and lack trust in AI predictions for fraud. Such an issue has been tackled by employing Explainable AI...
Fraud detection (FD) studies supported by Explainable AI (XAI) lack expert's requirements and principles to align explanation methods (EM) to support decision-making. It remains the lack of trust of fraud experts towards AI predictions. On the other hand, information systems (IS) and HCI research discuss the systematic assessment of requirements fo...
Programming education traditionally has been an important part of Information Technology-related degrees but, more recently, it is also becoming essential in many STEM domains as well. Despite this, drop-out rates in programming courses in higher education institutions are considerable and cannot be ignored. At the same time, analysing learning beh...
Sentiment Analysis techniques enable the automatic extraction of sentiment in social media data, including popular platforms as Twitter. For retailers and marketing analysts, such methods can support the understanding of customers' attitudes towards brands, especially to handle crises that cause behavioural changes in customers , including the COVI...
Brick-and-mortar retailers need to stay competitive to the convenience provided by online channels. Technologies, such as personalized shopping assistants on smartphones can empower customers in-store towards a similar experience as in an online scenario. For instance, an augmented reality shopping assistance application with explainable recommenda...
Explainable Artificial Intelligence (XAI) develops technical explanation methods and enable interpretability for human stakeholders on why Artificial Intelligence (AI) and machine learning (ML) models provide certain predictions. However, the trust of those stakeholders into AI models and explanations is still an issue, especially domain experts, w...
Digital retailers are experiencing an increasing number of transactions coming from their consumers online, a consequence of the convenience in buying goods via E-commerce platforms. Such interactions compose complex behavioral patterns which can be analyzed through predictive analytics to enable businesses to understand consumer needs. In this abu...
Probabilistic modeling methods have found increasing importance in recent years, driven by concurrent growth in computing power with applications in the modeling of many fields of science, engineering, and medicine. This has been due not just to method scope and flexibility, but also in no small part to advance in computing capacity and interconnec...
Received total wideband power (RTWP) data is a measurement of the wanted and unwanted power levels received by a 3G radio base station (RBS) and is a concise indicator of uplink network performance. Using a statistical physics approach, we aim to detect periods of unusual activity between cells by assessing a sample of RTWP measurement data from a...
Usage in the software field deals with knowledge about how end-users use the application and how the application responds to the users’ action. Understanding usage data can help developers optimise the application development process by prioritising the resources such as time, cost and man power on features of the application which are critical for...
Digital retailers have experienced a high influx of big data comingfrom their consumers’ interactions online, a consequence of the convenience inbuying goods via E-commerce platforms. Such interactions compose complexbehavioral patterns which, when analyzed, can provide businesses with opportunities to understand their consumer needs and improve th...
Purchasing decisions do not always come from the rational mental processes but are often being driven by emotions. This insight made researchers think of emotions as of an essential contextual variable capable of enhancing personalized services and providing more precise recommendations within e-Commerce. In this paper we explore the studies made t...
Researchers in the retail domain today propose that, in particular, complex and non-financial goals such as ‘customer experience’ represent the new imperative and leading management objective in the age of Digital Retail, questioning the role of conventional financial measures such as revenue. However, there is no evidence in research showing the c...
Usage in the software domain refers to the knowledge about how end-users use the application and how the application responds to the user's actions. Usage can be revealed by monitoring the user's interaction with the application. However, in the cloud environment, it is non-trivial to understand the interactions of the users by using only the monit...
Cloud computing monitors applications, virtual and physical resources to ensure performance capacity, workload management, optimize future application updates and so on. Current state-of-the-art monitoring solutions in the cloud focus on monitoring in application/service level, virtual and physical (infrastructure) level. While some of the research...
Cloud computing monitors applications, virtual and physical resources to ensure performance
capacity, workload management, optimize future application updates and so on. Current state-of-the-art monitoring solutions in the cloud focus on monitoring in application/service level, virtual and physical (infrastructure) level. While some of the research...
There is a significant challenge in smart cities implementations. One challenge is to align smart city strategies with the impact on quality of life. Stakeholders’ concerns are multiple and diverse, and there is a high interdependency and heterogeneity of technologies and solutions. To tackle this challenge, researchers have suggested to view citie...
Cloud migration has attracted a lot of attention in both industry and academia due to the on-demand, high availability, dynamic scalable nature. Organizations choose to move their on-premise applications to adapt to the virtualized environment of the cloud where the services are accessed remotely over the internet. These applications need to be re-...
Cloud migration has attracted a lot of attention in both industry and academia due to the on-demand, high availability, dynamically scalable nature. Organizations choose to move their on-premise applications to adapt to the virtualized environment of the cloud where the services are accessed remotely over the internet. These applications need to be...
Identified the research problem where applications migrated and the cloud-native applications deployed on the cloud after some amount of time, their logic or implementation become inadequate and outdated. But, they are too ingrained to be replaced. To tackle this problem, a re-engineering approach called architectural refactoring is proposed, where...
Cellular automata (CA) have been gaining momentum as a promising tool in the field of in silico Drug Dissolution System (DDS) modelling due to their bottom-up approach and the ability to simulate broad range of physico-chemical reactions at small domain level. In pharmaceutical applications, CA models use a combination of discrete-event rules, prob...
Smart city is an urban development vision to integrate multiple Information and Communication Technology (ICT) and Internet of Things (IoT) solutions in a secure fashion to manage a city's assets. IoT devices are heterogeneous and collect large amount of data which need to be collected, processed, stored and shared among various devices, services a...
In pharmaceutical modelling, cellular automata have been used as an established tool to represent molecular changes through discrete structural interactions. The data quality provided by such modelling is found suitable for the early drug design phase where flexibility is paramount. While both synchronous (CA) and asynchronous (ACA) types of automa...
A novel, discrete space-time model of pedestrian behaviour in real urban networks is presented. An agent-based approach is used to define characteristics of individual pedestrians, based on spatial awareness and cognition theories, combined with preferential choices of different social groups. Behaviour patterns are considered incorporating rules o...
The field of pharmaceutical modelling has, in recent years, benefited from using probabilistic methods based on cellular automata, which seek to overcome some of the limitations of differential equation based models. By modelling discrete structural element interactions instead, these are able to provide data quality adequate for the early design p...
One of the main challenges in data analytics is that discovering structures and patterns in complex datasets is a computer-intensive task. Recent advances in high-performance computing provide part of the solution. Multicore systems are now more affordable and more accessible. In this paper, we investigate how this can be used to develop more advan...
Cellular Automata (CA) properties facilitate the detail required for the bottom-up approach to modelling and simulation of a broad range of physico-chemical reactions. In pharmaceutical applications, CA models use a combination of discrete-event rules based on probabilistic distributions and fundamental physical laws to predict the behaviour of act...
Pharmaceutical companies today face a growing demand for more complex drug designs. In the past few decades, a number of probabilistic models have been developed, for the purpose of giving a better insight into the microscopic features of these complex designs. Of particular interest are those models that simulate controlled release systems to prov...
In the last few decades, a number of probabilistic models for drug delivery have been developed. Of particular interest are those that model controlled release systems to provide targeted dose delivery. Controlled release is achieved by using polymers with different dissolution characteristics. We present here a model based on Monte Carlo and Cellu...