The management of knowledge-driven artificial intelligence technologies is essential in order to evaluate their impact on human life and society. Social networks and tech use can have a negative impact on us physically, emotionally, socially and mentally. On the other hand, intelligent systems can have a positive effect on people's lives. Currently, we are witnessing the power of large language models (LLMs) like chatGPT and its influence towards the society. The objective of the workshop is to contribute to the advancement of intelligent technologies designed to address the human condition. This could include precise and personalized medicine, better care for elderly people, reducing private data leaks, using AI to manage resources better, using AI to predict risks, augmenting human capabilities, and more. The workshop's objective is to present research findings and perspectives that demonstrate how knowledge-enabled technologies and applications improve human well-being. This workshop indeed focuses on the impacts at different granularity levels made by Artificial Intelligence (AI) research on the micro granular level, where the daily or regular functioning of human life is affected, and also the macro granulate level, where the long-term or far-future effects of artificial intelligence on people's lives and the human society could be pretty high. In conclusion, this workshop explores how AI research can potentially address the most pressing challenges facing modern societies, and how knowledge management can potentially contribute to these solutions.

We aim to build an effective automated single-lead Electrocardiogram (ECG) classification system to enable remote and timely screening of critical cardio-vascular diseases like Heart attack. However, the expenses associated with cardiologist-intervened ECG annotation limits the number of training instances. While conventional deep learning models require large set of training examples for accurate classification, we propose Priv-Aug-Shap-ECGResNet which demonstrates that deep learning algorithm (for e.g., residual network or ResNet) with ablation of unimportant features from the given training dataset can ensure consistently better classification performance over relevant state-of-the-art algorithms. Additively perturbed training augmentation with Shapley attribution finds out the right feature subset with the assistance of the axioms of transferable utility, namely "efficiency" and "null player" on which Shapley value game is defined. Priv-Aug-Shap-ECGResNet is enabled with novel data privacy preservation feature through differential privacy technique to provide measured obfuscation to render ZeroR classification equivalent knowledge gain to the adversary.

Practical time series datasets in classification tasks often suffer from scarcity in number of training instances owing to the expenses associated with the annotation exercise. Deep learning algorithms generally demand sufficiency in the seen examples for its learning purposes. In this paper, we consider adversarial perturbation as the set of invariants such that a robust model can be constructed under the practical constraints of training sample scarcity. We propose ADV-ResNet that augments the learning ability of a Residual Network (ResNet) through adversarial regularization, where adversarial training is transformed to robust form of data augmentation. We propose novel algorithm for adversarial regularization factor computation that estimates the amount of regularization for controlled perturbation in the learning process. The intentional yet measured introduction of perturbations in the ResNet training process enables it to learn better under crafted and controlled perturbations that constitute unseen but important input space. Our empirical investigation on publicly available time series classification datasets (UCR time series archive) demonstrates the utility of ADV-ResNet through ablation study. The empirical evidence clearly indicates the superiority of ADV-ResNet over the baseline ResNet, as well as ADV-ResNet significantly outperforms the state-of-the-art time series classification models.

With the proliferation of Internet of Things (IoT), sensor technologies and advancement in the analytics systems mainly in the form of deep learning algorithms, the long quest for developing human-centric applications like automated disease diagnosis, privacy-enabled analytics is becoming a reality. Knowledge-Driven Analytics and Systems Impacting Human Quality of Life (KDAH) is indeed an attractive proposition. For example, Phonocardiogram or heart sound-based detection of heart abnormality or Myocardial Infarction (MI) prediction using single lead Electrocardiogram (ECG) signals are signifying the capability of analytics algorithm to directly solve human-centric problems. We have proposed privacy-preserved analytics with phonocardiogram-based heart condition detection, established benchmark performance of MI detection using single lead ECG signals as well as demonstrated deep residual learning based algorithm to help carbon footprint management.

The typical problem like insufficient training instances in time series classification task demands novel deep neural network architecture to warrant consistent and accurate performance. Deep Residual Network (ResNet) learns through ℋ(x) = ℱ(x) + x, where ℱ(x) is a nonlinear function. We propose Blend-Res2Net that blends two different representation spaces: ℋ1(x) = ℱ(x) + Trans(x) and ℋ2(x) = ℱ(Trans(x)) + x with the intention of learning over richer representation by capturing the temporal as well as the spectral signatures (Trans(∙) represents the transformation function). The sophistication of richer representation for better understanding of the complex structure of time series signals, may result in higher generalization loss. Hence, the deep network complexity is adapted by proposed novel restrained learning, which introduces dynamic estimation of the network depth. The efficacy of Blend-Res2Net is demonstrated by a series of ablation experiments over publicly available benchmark time series archive- UCR. We further establish the superior performance of Blend-Res2Net over baselines and state-of-the-art algorithms including 1-NN-DTW, HIVE-COTE, ResNet, InceptionTime, ROCKET, DMS-CNN, TS-Chief.

The average life expectancy of the world’s population is increasing and the healthcare systems sooner than later will be compromised by its reduced capacity and its highly economic cost; in addition, the age distribution of the population is leading towards the older spectrum. This trend will lead to immeasurable and unexpected economic problems and social changes. In order to face up this challenge and complex economic and social problem, it is necessary to rely on the appropriate digital tools and technological infrastructures for ensuring that the elderly are properly cared in their everyday living environments and they can live independently for longer. This article presents ACTIVAGE IoT Ecosystem Suite (AIoTES), a concrete reference architecture and its implementation process that addresses these issues and that was designed within the first European Large Scale Pilot, ACTIVAGE, a H2020 funded project by the European Commission with the objective of creating sustainable ecosystems for Active and Healthy Ageing (AHA) based on Internet of Things and big data technologies. AIoTES offers platform level semantic interoperability, with security and privacy, as well as Big Data and Ecosystem tools. AIoTES enables and promotes the creation, exchange and adoption of cross-platform services and applications for AHA. The number of existing AHA services and solutions are quite large, especially when state-of-the-art technology is introduced, however a concrete architecture such as AIoTES gains more importance and relevance by providing a vision for establishing a complete ecosystem, that looks for supporting a larger variety of AHA services, rather than claiming to be a unique solution for all the AHA domain problems. AIoTES has been successfully validated by testing all of its components, individually, integrated, and in real-world environments with 4345 direct users. Each validation is contextualized in 11 Deployment Sites (DS) with 13 Validation Scenarios covering the heterogeneity of the AHA-IoT needs. These results also show a clear path for improvement, as well as the importance for standardization efforts in the ever-evolving AHA-IoT domain.

The present scenario of Covid-19 pandemic has disrupted the human life to a larger extent. In such context, human-centric applications and systems that endeavor to positively impact the human quality of life is of utmost importance. Knowledge-driven analytics that help to build such intelligent systems play important role to construct the required eco-system on the macro-scale. It is worth mentioning that Knowledge-Driven Analytics and Systems Impacting Human Quality of Life (KDAH) workshop in ACM International Conference on Information and Knowledge Management (CIKM), attempts to bring out the intricate research direction for enabling a sustainable human society through the positive co-existence of human beings and intelligent systems.

This special issue (SI) aims to present recent advances in the design and analysis of communication interfaces for Industry 4.0. The Industry 4.0 paradigm aims to integrate advanced manufacturing techniques with Industrial Internet-of-Things (IIoT) to create an agile digital manufacturing ecosystem. The main goal is to instrument production processes by embedding sensors, actuators and other control devices which autonomously communicate with each other throughout the value-chain[1].

The advent of artificial intelligence (AI), Internet of Things (IoT), powerful computational hardwares like graphics processing units, affordable sensing devices like smart bands, wearables, smartphones pave ways for large number of useful and intelligent applications hitherto never commonly envisaged. However, it is felt that applications, which positively influence human life and society, need distinct attention from the perspective of the researchers, application developers as well as industry. It is understood that knowledge-driven initiatives in terms of technology, application and practical deployment have strong capability to enable long term human-centric convergence of cyber-physical systems. Our endeavor is to discuss those finer details, research directions and application development aspects of analytics and systems intended for impacting human quality of life.

The RPL routing protocol is designed to respond to the requirements of a large range of Low-power and Lossy Networks (LLNs). RPL uses an objective function (OF) to build the route toward a destination based on routing metrics. Considering only a single metric, some network performances can be improved while others may be degraded. In this paper, we present a flexible Objective Function based on Expected Transmission Count (ETX), Consumed Energy and Forwarding Delay (OF-ECF) built on a combination of metrics using an additive method. The main goal of this proposed solution is to balance energy consumption and minimize the average delay. To improve the reliability of the network, a flexible routing scheme that provides the diversity of paths and a higher availability is presented. Simulations results show that the new objective function OF-ECF outperforms the OF-FUZZY, and the standards OF0 and MRHOF. In terms of network lifetime and reliability.

In this work, we demonstrate the feasibility and the main functionalities of a low-cost, nomadic platform for Smart District services. The goal of the platform is to enable the extension of Smart City services to smaller cities, to towns and into the countryside, bypassing the natural barriers through the use of services and vectors which are naturally cross-domain, such as public transportation vehicles, and moving people. the platform is based on mobile and opportunistic sensing, on crowdsensing, and on strategies for community engagement and co-creation mediated by a map-based crowdsourcing application. The demo will showcase the main components of the system, as well as a sample set of Smart District services supported by the platform.

In this paper, we are visualizing a military health service (MHS) platform which is based on hierarchical IoT architecture. We propose a semantic Edge based network model which plays a significant role for communicating tactical and non-tactical piece of information over the network. Further, the exchange of information and subsequent data analysis on the MHS makes the system intelligent and smart. In any standard battlefield scenario, there is a command and control center that correlates the events happening in real time. We have made this command and control center as semantic edge component. This center is entrusted with making vital decisions on the tactical arena of the battlefield. The main aim of the proposed architecture is to provide secured zone to monitor soldiers health and their weapons conditions, respectively. We have also introduced the semantic edge computing mechanism to deal with the large amount of health data in terms of processing, storing and sharing information.

Due to their rapid evolution, mobile devices demand for more dynamic and flexible networking services. A major challenges of future mobile networks is the increased mobile traffic. With the recent upcoming technologies of network programmability like Software-Defined Network (SDN), it may be integrated to create a new communication platform for Internet of Things (IoT). In this work, we present how to determine the effectiveness of an approach to build a new secured network architecture based on SDN and clusters. Our proposed scheme is a starting point for some experiments providing perspective over SDN deployment in a cluster environment. With this aim in mind, we suggest a routing protocol that manages routing tasks over Cluster-SDN. By using network virtualization and OpenFlow technologies to generate virtual nodes, we simulate a prototype system controlled by SDN. With our testbed, we are able to manage 500 things. We can analyze every OpenFlow messages and we have discovered that with a particular flow, the things can exchange information unlike the routing principle.

Securing Internet of Things is currently one of the most challenging tasks standing before the research community. Finding adequate combination of strong cryptography, lightweight computation and minimalistic data transmission with scarce energy resources and no maintenance times is very hard. This paper introduces new mechanism for IEEE 802.1X authentication scheme that has been previously extended for the IEEE 802.15.4 networks. The new solution has been designed to minimize the number of transmitted packets during the authentication process through maximization of the Extensible Authentication Protocol Maximum Transfer Unit. The results have been promising for the certificate based EAP Methods with reduction of around 10% of transferred packets for the EAP-TLS-RSA based methods and around 7% for the EAP-TLS-ECDSA based methods.

We are witnessing the emergence of a new technology paradigm, one which focuses on the large scale integration and simplification of distributed technologies along with their fundamental realignment around the needs of people and society. The new Human Centric Intelligent Society results from these changes is connecting information from many different sources across the physical and virtual worlds, using the power of integration to achieve new insights and to enact change in ways which are quicker and more context aware than ever before. The Human Centric integration will lead to safer, more comfortable and more prosperous societies, but before arriving to this status, we have several challenges for the existing platforms to be migrated and digitalized into a common Cloud Computing ecosystem, and enable the common things with a Web of Things capabilities that can enable new forms of social infrastructure that react to the needs of people in real time. In this work, we present the contributions and extensions to the EENA Public Safety Answering Points standards and data structure (PIDFLO), in order to enable it with the capabilities to be integrated with data coming from personal and wearable sensors (Internet of Things). In details, we have extended PIDF-LO with the support of OMA LwM2M Web Objects, in order to offer a scalable and interoperable integration of the Internet of Things and the European Emergencies Services based on Open Standards.

Due to the high impact that energy consumption of buildings has at global scale, it has been stated the need of achieving energy-efficient buildings to reduce CO2emissions and energy consumption at global scale. In this work we propose to model the energy consumption associated with services provided in buildings to help select the best strategies to save energy. To verify the feasibility of the proposed approach using measurements of relevant parameters affecting, we carry out some analysis in a reference building of which we have contextual data. Firstly, we provide a complete characterization of this building in term of its energy consumption and generate accurate building models able to predict its energy consumption given a concrete set of inputs. Finally, considering the generated energy usage profile of the building, we propose some concrete control actions and strategies to save energy.

RPL (IPv6 Routing Protocol for Low Power and Lossy Networks) is proposed by the ROLL working group at IETF. This protocol used in the Internet of Things is optimal for Low power and Lossy Networks (LLNs). However, the RPL network has some limits when the network is dense. In this paper we evaluate the performance of RPL in three different scenarios. We first, evaluate the characteristics of RPL with fixed nodes, (one sink and others are senders). Then we add mobility, and we compare mobile nodes to fixed nodes in order to show how mobility can influence protocol parameters. Finally, we study the behavior of RPL when the network is dense in order to assess the protocol performances. In this study, we use Contiki OS and Cooja software for all simulations. The results show that RPL performances are greatly influenced by the number of nodes, type of mobility and the topology of the network. When the number of nodes increases, all metrics increase too, especially the power consumption which arrives until an augmentation of 52,85%. Furthermore, Random Waypoint Mobility Model (RWP) gives better metrics than Random Walk (RWK) Mobility Model in terms of number of hops and Expected Transmission (ETX) value. Also, in RWP model, nodes consume 10,73% of power than RWK. Our simulations show clearly that the power consumption is directly related to the number of sink nodes in the network. The more this type of node is present in the network the less power is consumed. The power reduction may occur till 5%.

The Internet of Things (IoT) represents the current technology revolution that is intended to transform the current environment into a more pervasive and ubiquitous world. In this emerging ecosystem, the application of standard security technologies has to cope with the inherent nature of constrained physical devices, which are seamlessly integrated into the Internet infrastructure. This work proposes a set of lightweight authentication and authorization mechanisms in order to support smart objects during their life cycle. Furthermore, such mechanisms are framed within a proposed security framework, which is compliant with the Architectural Reference Model, recently presented by the EU FP7 IoT-A project. The resulting architecture is intended to provide a holistic security approach to be leveraged in the design of novel and lightweight security protocols for IoT constrained environments.

Summary Big data techniques are conceived as the powerful tool to exploit all the potential of the Internet of Things and the smart cities. A new dimension of understanding about the human behaviours is expected to be reached through all the gathered data in the emerging smart environment. The described potential, so‐called Human Dynamics, pursues to describe in real‐time the human behaviours and activities. This work presents our experiences for big data analytics in smart cities, in terms of sensors data management, data fusion and knowledge discovery from the data. The data used is from the European Project SmartSantander, where the traffic behaviour has been correlated with respect to the temperature in the Santander City. The evolution of both flows present a similar behaviour, in detail, a fine grain correlation is discovered. On the one hand, the traffic distribution, aggregated by temperature bins, follows up a Poisson distribution model. The Poisson modelling allows to interpolate and predict complex behaviours based on simple measures such as the temperature. At the same time, on the other hand, the isolated traffic density distribution, without taking into account the temperature‐based aggregation has been analysed. The traffic distribution has presented a burst behaviour, which presents a closer model to the human dynamics. Therefore, this work presents as the smart cities data can be modelled as Poisson or Human Dynamics (burst models). Finally, reference data analytics process, data sets and models are offered for the Open Source Data analytics platform Konstanz Information Miner (KNIME). Copyright © 2014 John Wiley & Sons, Ltd.

Continuous and wireless transmission of vital signs for personalized healthcare is gaining a great deal of interest from Ambient Assisted Living solutions. Personalized healthcare capabilities are limited to the patient data available, which is usually dynamic and incomplete. For that reason, regular monitoring of patients with the aim of offering a suitable analysis of patient evolution is required. Continuous monitoring requires the integration of wireless communication technologies and embedded systems into wearable and portable monitoring systems. In addition, a user interface intuitive is also required, which is easy to use and understand by the patients and caregivers. This work proposes a solution such as Near Field Communication (NFC) for personalized healthcare based on the Internet of Things. NFC is a technology integrated in smart phones that provides capabilities for identification of devices/sensors, and presents ubiquitous communication capabilities between the sensor and the device. NFC also presents challenges in terms of the performance and efficiency of data transmission, due to the constrained resources and capabilities of ubiquitous devices and the latency introduced by the NFC technology. These challenges are intrinsic to NFC since it was originally considered only for simple identification and not for continuous data transmission. In this context, this paper presents a novel monitoring system for continuous data transmission from a set of clinical devices based on NFC which has been optimized in order to make communications feasible. This novel monitoring system is also composed by a set of participatory sensing applications to support caregivers and for patients to self-monitor and self-manage their health status wirelessly. A technical evaluation based on latencies associated with use of NFC for continuous monitoring and an evaluation of usability by a group of elderly users and their caregivers, which studies the interactions between the users and the system, are demonstrated.

Mobility management is a desired feature for the emerging Internet of Things (IoT). Mobility aware solutions increase the connectivity and enhance adaptability to changes of the location and infrastructure. IoT is enabling a new generation of dynamic ecosystems in environments such as smart cities and hospitals. Dynamic ecosystems require ubiquitous access to Internet, seamless handover, flexible roaming policies, and an interoperable mobility protocol with existing Internet infrastructure. These features are challenges for IoT devices, which are usually constrained devices with low memory, processing, communication and energy capabilities. This work has, on the one hand, analysed suitability of Mobile IPv6 and IPSec for constrained devices, and on the other hand, analysed, designed, developed and evaluated a lightweight version of Mobile IPv6 and IPSec. The proposed solution of lightweight Mobile IPv6 with IPSec is aware of the requirements of the IoT and presents the best solution for dynamic ecosystems in terms of efficiency and security adapted to IoT-devices capabilities. This presents concerns in terms of higher overhead and memory requirements. But, it is proofed and concluded that even when higher memory is required and major overhead is presented, the integration of Mobile IPv6 and IPSec for constrained devices is feasible.

Communication and information access defines the basis to reach a personalized health end-to-end framework. Personalized health capability is limited to the available data from the patient. The data is usually dynamic and incomplete. Therefore, it presents a critical issue for mining, analysis and trending. For that reason, this work presents an interconnection framework for mobile Health (mHealth) based on the Internet of Things. It makes continuous and remote vital sign monitoring feasible and introduces technological innovations for empowering health monitors and patient devices with Internet capabilities. It also allows patient monitoring and supervision by remote centers, and personal platforms such as tablets. In terms of hardware it offers a gateway and a personal clinical device used for the wireless transmission of continuous vital signs through 6LoWPAN, and patient identification through RFID. In terms of software, this interconnection framework presents a novel protocol, called YOAPY, for an efficient, secure, and scalable integration of the sensors deployed in the patient's personal environment. This paper presents the architecture and evaluates its capability to provide continuous monitoring, ubiquitous connectivity, extended device integration, reliability, and security and privacy support. The proposed interconnection framework and the proposed protocol for the sensors have been exhaustively evaluated in the framework of the AIRE project, which is focused on patients with breathing problem. This evaluates for the proposed protocol the data aggregation mechanism level, Round-Trip delay Time, impact of the distance, and the impact of the security. It has been concluded that secure continuous monitoring is feasible with the use of the proposed {YOAPY}} aggregation mechanisms and the capabilities from the proposed interconnection framework.

Personalized health capability is limited to the available data from the patient, which is usually dynamic and incomplete. Therefore, it is presenting a critical issue for knowledge mining, analysis and trending. For that reason, this work presents a knowledge acquisition and management platform based on the Internet of Things (IoT). IoT is presenting the capability to connect any object to Internet. These Smart Objects are providing an enormous quantity of data. This work is focused on the personal and mobile health areas, where the integration of clinical devices in the patient's environment, this will enable new services with capabilities to predict health anomalies in real time, send alerts, reminders and offer an enriched feedback to the patient. This feedback will help and motivate to the patients with the treatments adherence and compliance and to follow a healthy lifestyle. In order to reach these services and feedback capabilities, it is required a full integration of the clinical devices and efficient processing of the collected data. The presented knowledge acquisition and management architecture is composed of, on the one hand, a gateway and a personal clinical device used for the integration of clinical devices, wireless transmission of continuous vital signs through 6LoWPAN, and patient identification through RFID. On the other hand, it is complemented with a data model and pre-processing module called YOAPY, which analyses the data from the sensors at the personal devices level. This offers an enriched data to the knowledge-based systems, and this also aggregate the data acquired in order to improve the performance of the communications to the constrains from the Smart Objects in aspects such as low bandwidth, frame size and power consumption. This architecture is being evaluated with an extended set of sensors required for patients with breathing problem in the framework of the AIRE project, it has evaluated the capabilities to provide knowledge acquisition and management from continuous monitored vital signs, the capabilities for diagnosis and detection of anomalies, and finally the support for security and privacy.

Recently the problem of providing effective and appropriate healthcare to elderly and disable people is an important field in relative to the aging of population problems. The objective of information and communication technologies (ICT) is to focus on the new technologies the medical environments, so that it can provide management to accelerate and improve the clinical process. Our contribution is to introduce an approach based on Internet of things (IoT) in medical environments to achieve a global connectivity with the patient, sensors and everything around it. The main goal of this globality feature is to provide a context awareness to make the patient's life easier and the clinical process more effective. To achieve this approach, firstly has been developed an architecture which has been designed to offer great potential and flexibility of communications, monitoring and control. This architecture includes several advanced communication technologies; among them are 6LoWPAN and RFID/NFC, which are the basis of the IoT. Moreover the research deal with the problems related to the mobility and security that happens when IoT is applied in medical environments. The mobility issue requires developing a protocol over 6LoWPAN network to be carried out in sensor networks with high specification related with low power consumption and capacity. While in the RFID/NFC technologies need to support secure communications, our proposal is to introduce a set of security techniques and cryptographic SIM card to authenticate, encrypt and sign the communications with medical devices. The preliminary results showed a reduction of time in the handover process with the protocol for mobility defined, by omitting the stages of addressing and simplifying the MIPv6 protocol. In addition to increase the security in the communications carried out by NFC devices enhanced with the inclusion of cryptographic SIM card.