Abstract. Traditional commercial and retail banks are under great pressure from new competitors. They must rise to the challenges of understanding their customer actions and behaviors, and be ready to meet their expectations even before they explicitly express them. But the ability to know customers' demands in nearly real-time requires the evolution of existing architectures to support the detection, notification, and processing of business events to manage business information streams. This paper describes a practical experience in evolving a core banking enterprise architecture by leveraging business event exploitation, and includes the definition of business events; the design of a reference architecture and its integration points with the legacy architecture, as well as the description of an initial governance approach. Furthermore, as the core banking architecture is a critical infrastructure we have evaluated the performance of the evolved architecture so as to understand whether or not it can meet the banks' quality levels.
Abstract.User privacy has become a hot topic within the identity management arena. However, the field still lacks comprehensive frameworks even though most identity management solutions include built-in privacy features. This study explores how best to set up a single control point for users to manage privacy policies for their personal information, which may be distributed (scattered) across a set of network-centric identity management systems. Our goal is a user-centric approach to privacy management. As the number of schemas and frameworks is very high, we chose to validate our findings with a prototype based on the Liberty Alliance architecture and protocols.
The field of medical coding enables to assign codes of medical classifications such as the international classification of diseases (ICD) to clinical notes, which are medical reports about patients' conditions written by healthcare professionals in natural language. These texts potentially include medical terms that define diagnosis, symptoms, drugs, treatments, etc., and the use of spontaneous language is challenging for automatic processing. Medical coding is usually performed manually by human medical coders becoming time-consuming and prone to errors. This research aims at developing new approaches that combine deep learning elements together with traditional technologies. A semantic-based proposal supported by a proprietary knowledge graph (KG), neural network implementations, and an ensemble model to resolve the medical coding are presented. A comparative discussion between the proposals where the advantages and disadvantages of each one is analysed. To evaluate approaches, two main corpus have been used: MIMIC-III and private de-identified clinical notes.
Fujitsu HIKARI is an artificial intelligence solution to assist clinicians in medical decision making, developed in the context of a joint collaboration project between Fujitsu Laboratories of Europe and Hospital Clínico San Carlos. This decision support system leverages on data analytics combined with healthcare semantic information to provide health estimations for patients, improving care quality and personalized treatment. Fujitsu HIKARI stands on the shoulders of biomedical knowledge, which includes (i) theoretical knowledge extracted from scientific literature, domain expert knowledge, and health standards; and (ii) empirical knowledge extracted from real patient electronic health records. The theoretical knowledge combines a theoretical knowledge graph (TKG) and a biomedical document repository (BDR). The empirical knowledge is encoded in an empirical knowledge graph (EKG). One of the main functionalities of Fujitsu HIKARI is the patient mental health risks assessment, which is based on the exploitation of its underlying Biomedical Knowledge.
Business information has become a critical asset for companies and it has even more value when obtained and exploited in real time. This paper analyses how to integrate this information into an existing banking Enterprise Architecture, following an event-driven approach, and entails the study of three main issues: the definition of business events, the specification of a reference architecture, which identifies the specific integration points, and the description of a governance approach to manage the new elements. All the proposed solutions have been validated with a proof-of-concept test bed in an open source environment. It is based on a case study of the banking sector that allows an operational validation to be carried out, as well as ensuring compliance with non-functional requirements. We have focused these requirements on performance.
Abstract. The banking industry is observing how new competitors threaten its millennial business model by targeting unbanked people, offering new financial services to their customer base, and even enabling new channels for existing services and customers. The knowledge on users, their behaviour, and expectations become a key asset in this new context. Well aware of this situation, the Center for Open Middleware, a joint technology center created by Santander Bank and Universidad Politécnica de Madrid, has launched a set of initiatives to allow the experimental analysis and management of socio-economic information. PosdataP2P service is one of them, which seeks to model the economic ties between the holders of university smart cards, leveraging on the social networks the holders are subscribed to. In this paper we describe the design principles guiding the development of the system, its architecture and some implementation details.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.