Panagiotis Kasnesis

Collective domotic intelligence through dynamic injection of semantic rules

Recent advances in IoT and pervasive computing have led to the introduction of a plethora of devices, featuring enhanced intelligence in sensing, understanding context and reacting to situations. In the case of smart home environment, the result is the introduction of smart, connected domotic devices, featuring enhanced intelligence. In combination with enhanced capabilities for sensing, controlling and automatic, the power of these devices can be further exploited by the use of a semantic connection layer that can facilitate a goal-oriented collaboration between devices and a meaningful interaction with humans. This paper proposes an integrated platform, enabling dynamic injection of automation rules based on semantic web technologies, in a collective intelligence environment. The role of the human - end user in this environment is supported through a user friendly IDE enabling the easy discovery, access and operation, through the introduction of automation rules.

A Cooperative Fog Approach for Effective Workload Balancing

Fog Computing is an emerging paradigm, suitable to serve the particular needs of IoT networks. It includes the deployment of computational devices at the edge of the network facilitating faster real-time processing of time-sensitive data. In this article, we present a Fog architecture, which diverges from the traditional hierarchical and centralized Fog model, and adopts a cooperative model, which allows for a federation of Edge networks. In our proposal, the tasks that the nodes are called to complete, are characterized according to their computational nature and are subsequently allocated to the appropriate host. Edge networks communicate through a brokering system with IoT systems in an asynchronous way via the Pub/Sub messaging pattern.

Cognitive friendship and goal management for the social IoT

Use of smart software agents for enabling SIoT in the cloud.Definition of the smart objects profile and life cycle.Use of two ontologies for handling the social relationships of the smart entities.Manifest needs and services of smart objects through an embedded descriptive file.Presentation of an IoT scenario on our SIoT simulator using semantic rules. The concept of an Internet of Things is already mature, enough to start evolving towards an Internet of Everything, over which humans, objects and virtual items can be interconnected. For this to be feasible though, there is the need for a framework which not only supports the interconnection between the entities of this Internet, but also allows the meaningful interaction between them. In this paper, we present an idea on how this can be materialized, based on the use of semantic web technologies and smart software agents. These middleware technologies, combined with machine learning techniques, can lead to cognitive friendship and goal management. The paper includes a presentation of the theoretical framework, a use case scenario, and results over the use of a simulation tool. Display Omitted

ASSIST: An agent-based SIoT simulator

In this paper, a proposal on the evolution of Internet of Things towards a Social Networks inspired environment (Social Internet of Things-SIoT) is presented. An architecture for supporting the SIoT based on the use of agents, which enable device to device and human to device “social” communication, is presented, along with a simulator (ASSIST) which enables the visualization of the way the proposed architecture works. The use of rules in our proposal comes to enable the communication and operation of agents on the basis of needs and services, while a use case is presented, demonstrating the use of the simulator to create links between SIoT Agents that assist them to discover the services they need.

Changing the Game of Mobile Data Analysis with Deep Learning

Situational and context awareness is becoming more and more important on the course towards intelligent machines and devices, offering a comprehensive toolset for improving our quality of life. The increased computational capacity of personal/smart devices, and their constantly increasing capabilities for sensing, allow for a large amount of collected data to be stored, processed and transmitted over mobile devices and networks. As a result, fast processing and analysis of this mobile data is becoming a big challenge. In this article, we start from the presentation of common mobile context-aware applications and a reference to the current practices and approaches on mobile data analysis, and propose the use of deep learning for analyzing sensor data from mobile devices, while we discuss open issues related to this approach.

The Health Avatar: Privacy-Aware Monitoring and Management

The rapidly increasing number of health monitoring devices, mainly wearables, will let users monitor their health and habitual parameters in a simple and easy way. However, the diversity of available platforms calls for simplified, standard solutions that can offer integrated tools to users--that is, patients, professionals, and practitioners. The authors present the idea of a health avatar thats used as the electronic equivalent of a human and features a dynamic life profile corresponding to the human owners physical status, living conditions, and habits. They examine how such avatars can be used to improve the quality of health and life.

Improving Quality of Life with the Internet of Everything

The advent of the Internet of Everything, where things and data providers can connect not only to other things and data providers, but to human entities as well, and are enriched with intelligence, calls for sophisticated data handling, storing, and sharing mechanisms. In this chapter, we present an ecosystem built over the idea of Internet of Everything and featuring a collaborative, intelligent service bus, which gathers information from connected devices and uses it to improve quality of life. All aspects related to data collection, processing, protection of privacy, as well as collaboration between users and interfacing between humans and devices are addressed, while mechanisms supporting decision making towards health related goals are presented.

Changing Mobile Data Analysis through Deep Learning

Situational and context awareness are becoming more and more important on the road toward intelligent machines and devices that can offer a comprehensive toolset for improving quality of life. The increased computational capacity of personal and smart devices, and their constantly increasing capabilities for sensing, allow a large amount of collected data to be stored, processed, and transmitted over mobile devices and networks. Consequently, fast processing and analysis of this mobile data is becoming a big challenge. In this article, the authors present common mobile context-aware applications and reference current mobile data analysis practices and approaches. They then propose using deep learning to analyze sensor data from mobile devices and discuss open issues related to this approach.

A Cloud Platform for classification and resource management of complex electromagnetic problems

Most scientific applications tend to have a very resource demanding nature and the simulation of such scientific problems often requires a prohibitive amount of time to complete. Distributed computing offers a solution by segmenting the application into smaller processes and allocating them to a cluster of workers. This model was widely followed by Grid Computing. However, Cloud Computing emerges as a strong alternative by offering reliable solutions for resource demanding applications and workflows that are of scientific nature. In this paper we propose a Cloud Platform that supports the simulation of complex electromagnetic problems and incorporates classification (SVM) and resource allocation (Ant Colony Optimization) methods for the effective management of these simulations.