Service delivery in smart environments by implicit organizations

Busetta, Paolo; Kuflik, Tsvi; Merzi, Mattia; Rossi, Silvia

doi:10.1109/mobiq.2004.1331742

Cited by 14 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These techniques are primarily based on architectures for communication among the agents that model the environment and the devices. Such architectures include, for example, the tuple space communication of da Silva and Vasconcelos [2007], the role-based communication of Busetta et al [2003Busetta et al [ , 2004, the goal-based organization and interaction of Encarnacao and Kirste [2005], and the use of JINI in Amigone et al [2005]. All these architectures have the primary aim of allowing agents to enter and leave the system, and for the goals of the system to be achieved by organizations of agents that form dynamically.…”

Section: Resultsmentioning

confidence: 99%

“…The work described in Busetta et al [2003Busetta et al [ , 2004 concerns responsive/active environments, and in particular interactive museums. The work is part of the project Peach (Personal Experience with Active Cultural Heritage 11 which is funded by a national body in Trento, Italy, and involves collaboration between academics in Italy, Germany, USA, and Canada, and heritage organizations in Italy (Castello del Buonconsiglio, Pompei Excavations) and Germany (Volklinger Huette Museum).…”

Section: Busetta Et Al [2003 2004] Penserini Et Al [2005] Museumsmentioning

confidence: 99%

See 1 more Smart Citation

Ambient intelligence

2011

View full text Add to dashboard Cite

In this article we survey ambient intelligence (AmI), including its applications, some of the technologies it uses, and its social and ethical implications. The applications include AmI at home, care of the elderly, healthcare, commerce, and business, recommender systems, museums and tourist scenarios, and group decision making. Among technologies, we focus on ambient data management and artificial intelligence; for example planning, learning, event-condition-action rules, temporal reasoning, and agent-oriented technologies. The survey is not intended to be exhaustive, but to convey a broad range of applications, technologies, and technical, social, and ethical challenges.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Busetta Et Al [2003 2004] Penserini Et Al [2005] Museumsmentioning

confidence: 99%

Ambient intelligence

2011

View full text Add to dashboard Cite

show abstract

“…Every considered limb is constituted by three joints each. For example, in the case of the left arm, the three joints are the left shoulder (a l [0]), the left elbow (a l [1]) and the left hand (a l [2]). In the case of the left leg, the three joints are the left hip (l l [0]), the left knee (l l [1]) and the left foot (l l [2]).…”

Section: The Proposed Approachmentioning

confidence: 99%

Combining CNN and LSTM for activity of daily living recognition with a 3D matrix skeleton representation

Ercolano

Rossi

2021

Intel Serv Robotics

View full text Add to dashboard Cite

In socially assistive robotics, human activity recognition plays a central role when the adaptation of the robot behavior to the human one is required. In this paper, we present an activity recognition approach for activities of daily living based on deep learning and skeleton data. In the literature, ad hoc features extraction/selection algorithms with supervised classification methods have been deployed, reaching an excellent classification performance. Here, we propose a deep learning approach, combining CNN and LSTM, that exploits both the learning of spatial dependencies correlating the limbs in a skeleton 3D grid representation and the learning of temporal dependencies from instances with a periodic pattern that works on raw data and so without requiring an explicit feature extraction process. These models are proposed for real-time activity recognition, and they are tested on the CAD-60 dataset. Results show that the proposed model behaves better than an LSTM model thanks to the automatic features extraction of the limbs’ correlation. “New Person” results show that the CNN-LSTM model achieves $$95.4\%$$ 95.4 % of precision and $$94.4\%$$ 94.4 % of recall, while the “Have Seen” results are $$96.1\%$$ 96.1 % of precision and $$94.7\%$$ 94.7 % of recall.

show abstract

“…In our case, the services themselves are generated as agents in a multi-agent system that has been developed as part of the PIL project [13], a multi-agent museum visitor's guide system. This system uses LoudVoice agents' communication infrastructure [39,40] and contains five components (see Figure 2): 1) a Spatial Information Broker that reports the visitor's position periodically, integrating positioning information from different sources (currently Infrared and WiFi); 2) a Presentation Composer that provides presentations to the visitor, based on the current location and taking into account the visitors' inferred preferences; 3) a User Modeler agent that keeps track of the visitors' preferences based on their behavior; 4) a Communication Services Agent that provides communication services to the visitors; and 5) a User Assistant (Device Interface) agent which is installed on the user's PDA and provides the user interface to the system (information presentation/user actions).…”

Section: Implementation Of the Generic Framework In Active Museumsmentioning

confidence: 99%