Cognitive friendship and goal management for the social IoT

Kasnesis, Panagiotis; Patrikakis, Charalampos Z.; ogias, Dimitris; Toumanidis, Lazaros; Venieris, Iakovos S.

doi:10.1016/j.compeleceng.2016.09.024

Cited by 23 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This relates to the 'Social Internet of Things' (SIoT), which integrates people and smart devices interacting within a social structure of IoT, often through IoT platforms [10,11]. The 'Social Collaborative Internet of Things' (SCIoT) represents a more advanced form of SIoT where social objects collaborate, interact and share information, creating cyber-physical ecosystems [12].…”

Section: Social Machines In Digital Health For Pandemic Managementmentioning

confidence: 99%

“…This refers to cognitive reasoning within temporary social structures, combining users, objects and services in the form of a 'Dynamic Social Structure of Things' [15]. Cognitive collaboration between connected devices can be achieved by combining machine learning with middleware technologies [12]. Some studies even suggest the creation of emotional models for human-machine interactions [16,17], as expressed in Table 1.…”

Section: Social Machines In Digital Health For Pandemic Managementmentioning

confidence: 99%

See 1 more Smart Citation

COVID-19 what have we learned? The rise of social machines and connected devices in pandemic management following the concepts of predictive, preventive and personalized medicine

et al. 2020

View full text Add to dashboard Cite

Objectives Review, compare and critically assess digital technology responses to the COVID-19 pandemic around the world. The specific point of interest in this research is on predictive, preventive and personalized interoperable digital healthcare solutions. This point is supported by failures from the past, where the separate design of digital health solutions has led to lack of interoperability. Hence, this review paper investigates the integration of predictive, preventive and personalized interoperable digital healthcare systems. The second point of interest is the use of new mass surveillance technologies to feed personal data from health professionals to governments, without any comprehensive studies that determine if such new technologies and data policies would address the pandemic crisis. Method This is a review paper. Two approaches were used: A comprehensive bibliographic review with R statistical methods of the COVID-19 pandemic in PubMed literature and Web of Science Core Collection, supported with Google Scholar search. In addition, a case study review of emerging new approaches in different regions, using medical literature, academic literature, news articles and other reliable data sources. Results Most countries' digital responses involve big data analytics, integration of national health insurance databases, tracing travel history from individual's location databases, code scanning and individual's online reporting. Public responses of mistrust about privacy data misuse differ across countries, depending on the chosen public communication strategy. We propose predictive, preventive and personalized solutions for pandemic management, based on social machines and connected devices. Solutions The proposed predictive, preventive and personalized solutions are based on the integration of IoT data, wearable device data, mobile apps data and individual data inputs from registered users, operating as a social machine with strong security and privacy protocols. We present solutions that would enable much greater speed in future responses. These solutions are enabled by the social aspect of human-computer interactions (social machines) and the increased connectivity of humans and devices (Internet of Things). Conclusion Inadequate data for risk assessment on speed and urgency of COVID-19, combined with increased globalization of human society, led to the rapid spread of COVID-19. Despite an abundance of digital methods that could be used in slowing or stopping COVID-19 and future pandemics, the world remains unprepared, and lessons have not been learned from previous cases of pandemics. We present a summary of predictive, preventive and personalized digital methods that could be deployed fast to help with the COVID-19 and future pandemics.

show abstract

Section: Social Machines In Digital Health For Pandemic Managementmentioning

confidence: 99%

Section: Social Machines In Digital Health For Pandemic Managementmentioning

confidence: 99%

COVID-19 what have we learned? The rise of social machines and connected devices in pandemic management following the concepts of predictive, preventive and personalized medicine

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Subsequently, another idea of CIoT is proposed through coordinating insight into IoT. A CIoT is an IoT with cognitive capacity which is incorporated to advance execution and accomplish insight is characterized by Kasnesis et al [16].…”

Section: Cognitive Iotmentioning

confidence: 99%

A Survey on Data Perception in Cognitive Internet of Things

Bhajantri¹,

Balugari²

2019

JTIT

View full text Add to dashboard Cite

A Cognitive Internet of Things (CIoT) is a brand of Internet of Things (IoT) with cognitive and agreeable mechanisms, which are incorporated to advance performance and accomplish insights into real world environments. CIoT can perceive present system's conditions, analyze the apparent information, make smart choices, and increase the network performance. In this survey paper, we present classifications of data perception techniques used in CIoT. This paper also compares the data perception works against energy consumption, network lifetime , resource allocation, and throughput, as well as quality of data and delay. In addition, simulation tools for IoT and their performance are discussed. Finally, we provide the model of cognitive agent-based data perception in CIoT for future research and development, which ensures the network performance in terms of reliability, energy efficient, accuracy, scalable, fault tolerant, and quality of data.

show abstract

“…Como se ha indicado anteriormente, Wu propone en [10] una separación de los componentes que determinan las prestaciones en términos de calidad para la IoE en tres capas: calidad de datos (Quality of Data, QoD), calidad de la información (Quality of Información, QoI) y calidad de experiencia de usuario (Quality of user Experience, QoE) como se muestra en la Tabla I. Esta misma clasificación de prestaciones en tres niveles, entiéndase QoD, QoI y QoE, también se emplea en [12]. En este trabajo, los autores intentan fusionar los conceptos de Social Internet of Things (SIoT) y Cognitive Internet of Things (CIoT) dentro del paradigma de IoE, presentando un ejemplo de implementación con smart software agents.…”

Section: Identificación De Métricasunclassified

QoE en el contexto de Internet of Everything

Cano

2017

Proceedings XIII Jornadas De Ingenieria Telematica - JITEL2017

View full text Add to dashboard Cite

Campus Muralla del Mar, Edif. Antigones, s/n 30202 Cartagena (España) mdolores.cano@upct.es Resumen-La investigación y el desarrollo hacia laInternet of Everything (IoE) inteligente es un empeño ambicioso y altamente interdisciplinar que debe abordarse en los diferentes niveles de su arquitectura. Un efecto colateral de esta separación se produce en la medición de la calidad de los servicios proporcionados y en cómo evaluar sus prestaciones. La calidad de experiencia de usuario (Quality of user Experience, QoE) se ha convertido en un marco de referencia de evaluación de prestaciones capaz de acoger los nuevos requisitos y demandas de este nuevo paradigma. En este artículo, proporcionamos una visión actual de la QoE en la IoE. Para ello, realizamos un estudio de las propuestas de medición de QoE, de las métricas que se sugieren para su modelado y sus relaciones. Como resultado, se identifica la necesidad de un nuevo enfoque para la evaluación de prestaciones de los servicios y aplicaciones de la IoE capaz de capturar su idiosincrasia, es decir, las nuevas métricas que definen calidad, nivel de conocimiento, nivel de inteligencia, consumo, etc., así como la carencia de un modelado entre los diferentes componentes de la QoE en IoE.Palabras Clave-IoE, IoT, QoE, QoD, QoI. I. INTRODUCCIÓNNos encontramos en una situación única en la que nuestro universo físico está adquiriendo una nueva existencia digital, donde cualquier ser/objeto va a estar conectado y capacitado para comunicarse y colaborar. En esta nueva realidad, con millones de dispositivos conectándose a la nube para intercambiar, procesar, y almacenar información, paradigma de Internet of Everything (IoE) [1], la arquitectura de red debe adaptar de forma cognitiva tanto sus principales parámetros de capacidad/caudal y latencia, como la calidad de sus servicios, de la forma más ágil, inteligente y eficiente posible. Es decir, como si se tratase de un servicio público básico (utility service) en función de las demandas de sus productores/consumidores de información.En este marco general, el proyecto AIM (Augmenting Intelligence, cognitive capabilities, efficiency and value of coMmunication technologies for the IoE) pretende avanzar en las nuevas tecnologías de red para que permitan crear valor y cubrir efectivamente las necesidades futuras de comunicación y colaboración de una sociedad evolucionada. Durante la última década, se ha realizado un esfuerzo de investigación importante en el ámbito de Internet of Things (IoT), en particular en el avance de las tecnologías habilitadoras [2] (aquéllas que aseguran su correcta operación y permiten el despliegue de aplicaciones elementales y servicios sectoriales). Sin embargo, el trabajo relacionado con la adaptabilidad y las capacidades cognitivas de IoE donde "todas las cosas" deberían mejorar su disposición para aprender, comprender y actuar en el mundo físico, el digital y el social no ha hecho más que comenzar. Desde las TIC, entendemos que el aumento de la inteligencia en IoE debe interpretarse como la capacidad de...

show abstract

Cognitive friendship and goal management for the social IoT

Cited by 23 publications

References 11 publications

COVID-19 what have we learned? The rise of social machines and connected devices in pandemic management following the concepts of predictive, preventive and personalized medicine

COVID-19 what have we learned? The rise of social machines and connected devices in pandemic management following the concepts of predictive, preventive and personalized medicine

A Survey on Data Perception in Cognitive Internet of Things

QoE en el contexto de Internet of Everything

Contact Info

Product

Resources

About