A Feedback-corrected Collaborative Filtering for Personalized Real-world Service Recommendation

Zhao, Shuai; Zhang, Yang; Cheng, Bo; Chen, Junliang

doi:10.15837/ijccc.2014.3.1085

Cited by 7 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, the authors in Zheng et al (2010) improve activity recommendations, by pulling many users' data together and by applying CF to find like-minded users and likepatterned activities at different locations. There are a few approaches that exploit CF in real-world recommendations within ubiquitous scenarios (Zhao et al 2014;Zhang et al 2013). However, they aimed at improving IoT service provision and not at using real world data to improve user similarity.…”

Section: Adaptation Based On User Datamentioning

confidence: 99%

“…Examples of items with low complexity and value are: news, books and movies, whereas examples of more complex and higher value items can range from laptops to financial services, jobs and travel itineraries. With RWUM items can also be goals to be achieve, activities to be performed, services to be used Zhao et al (2014), Zhang et al (2013).…”

Section: Adaptation Based On User Datamentioning

confidence: 99%

See 1 more Smart Citation

Real World User Model: Evolution of User Modeling Triggered by Advances in Wearable and Ubiquitous Computing

2018

View full text Add to dashboard Cite

Over the last few years, user modeling scenery is changing. With the recent advancements in ubiquitous and wearables technologies, the amount and type of data that can be gathered about users and used to build user models is expanding. User Model can now be enriched with data regarding different aspects of people's everyday lives. All these changes bring forth new research questions about the kinds of services which could be provided, the ways for effectively conveying new forms of personalisation and recommendation, and how traditional user modeling should change to exploit ubiquitous and wearable technology to provide these services. In this paper we follow the evolution of user modeling process, starting from the traditional User Model and progressing to RWUM -Real World User Model, which contains data from a person's everyday life. We tried to answer the above questions and to present a conceptual framework that represents the RWUM process, which might be used as a reference model for designing RWUM-based systems. Finally, we propose some inspiring usage scenarios and design directions that can guide researchers in designing novel, robust and versatile services based on RWUM.

show abstract

Section: Adaptation Based On User Datamentioning

confidence: 99%

Section: Adaptation Based On User Datamentioning

confidence: 99%

Real World User Model: Evolution of User Modeling Triggered by Advances in Wearable and Ubiquitous Computing

2018

View full text Add to dashboard Cite

show abstract

“…Ao propor alguma estratégia de busca deve-se, primeiramente, delinear a estratégia de seleção, ranqueamento e recomendação. Várias abordagens são propostas [24,36,19,38,18,23,39,27,37], inclusive algumas considerando atributos de qualidade de produtores de dados, no entanto, diversas delas são complexas demais e demandam muito processamento. Assim, deseja-se que o mecanismo de busca seja rápido e exija o mínimo, ou nenhuma interação explícita.…”

Section: Requisitosunclassified

Ranqueamento de Produtores de Dados na Internet das Coisas

Silva

Gama

Lóscio

2017

Anais Do Simpósio Brasileiro De Sistemas De Informação (SBSI)

View full text Add to dashboard Cite

RESUMOCom a ascensão da Internet das Coisas (Internet of Things -IoT ), bilhões de dispositivos estarão conectadosà internet do futuro produzindo, consumindo e processando dados e se comunicando uns com os outros. Descobrir e selecionar de forma eficiente os dispositivos que melhor respondem a uma determinada necessidade se mostram como problemas relevantes a serem investigados no paradigma IoT. Face a este problema, o presente trabalho propôs: (i) o uso e o monitoramento dinâmico de métricas de qualidade na descrição dos produtores de dados, (ii) proposta de uma técnica de ranqueamento de produtores de dados que utilize atributos de qualidade diversos, (iii) a proposta do conceito de fila dinâmica de resultados no mecanismo de busca, visando economia de processamento e ganho de desempenho e (iv) uso do estilo arquitetural REST para a oferta dos produtores de dados como recursos. Por fim, foi considerado um cenário de uso do aplicativo móvel Bike Cidadão com o objetivo de avaliar a performance das contribuições propostas. ABSTRACTWith the rise of the Internet of Things (IoT) billion devices will be connected to the internet of the future producing, consuming and processing data and communicating with each other. Discover and select e ciently the devices best suited to a particular need, appear as relevant issues to be investigated in the IoT. In view of this problem, the present work proposes: (i) using and monitoring quality metrics in the description of the data producers, (ii) the propose of a ranking of data producers technique that makes use of quality attributes, (iii) the suggestion of dynamic queue results by the search engine and (iv) the use of REST style for providing

show abstract

“…This recent transformation is mostly leaded by the Information and Communication Technologies [1], where hot research fields such as Big Data [2,3], Artificial Intelligence [4], or Internet of Things (IoT) [5,6] are already heading this new paradigm in which physical world (land, sea, air, and space) merges with cyberspace producing a hybrid environment where physical and cyber entities are linked together [7] (Figure 1).…”

Section: Introductionmentioning

confidence: 99%

HYBINT: A Hybrid Intelligence System for Critical Infrastructures Protection

Hingant

Zambrano

Pérez

et al. 2018

Security and Communication Networks

View full text Add to dashboard Cite

Cyberattacks, which consist of exploiting security vulnerabilities of computer networks and systems for any kind of malicious purpose (e.g., extortion, data steal, assets hijacking), have been continuously increasing worldwide in recent years. Cyberspace appears today as a new battlefield, along with physical world scenarios (land, sea, air, and space), for the organizations defence and security. Besides, by the fact that attacks from the physical world may have significant implications in the cyber world and vice versa, these dimensions cannot be understood independently. However, the most common intelligence systems offer an insufficient situational awareness exclusively focused on one of these decision spaces. This article introduces HYBINT, an enhanced intelligence system that provides the necessary decision-making support for an efficient critical infrastructures protection by combining the real-time situation of the physical and cyber domains in a single visualization space. HYBINT is a real cross-platform solution which supplies, through Big Data analytical methods and advanced representation techniques, hybrid intelligence information from significant data of both physical and cyber data sources in order to bring an adequate hybrid situational awareness (HSA) of the cyber-physical environment. The proposal will be validated in a detailed scenario in which HYBINT system will be evaluated.

show abstract

A Feedback-corrected Collaborative Filtering for Personalized Real-world Service Recommendation

Cited by 7 publications

References 20 publications

Real World User Model: Evolution of User Modeling Triggered by Advances in Wearable and Ubiquitous Computing

Real World User Model: Evolution of User Modeling Triggered by Advances in Wearable and Ubiquitous Computing

Ranqueamento de Produtores de Dados na Internet das Coisas

HYBINT: A Hybrid Intelligence System for Critical Infrastructures Protection

Contact Info

Product

Resources

About