Papers by Ioannis Chatzigiannakis
Journal of Ambient Intelligence and Humanized Computing
The retailing market has undergone a paradigm-shift in the last decades, departing from its tradi... more The retailing market has undergone a paradigm-shift in the last decades, departing from its traditional form of shopping in brick-and-mortar stores towards online shopping and the establishment of shopping malls. As a result, "small" independent retailers operating in urban environments have suffered a substantial reduction of their turnover. This situation could be presumably reversed if retailers were to establish business "alliances" targeting economies of scale and engage themselves in providing innovative digital services. The SMARTBUY ecosystem realizes the concept of a "distributed shopping mall", which allows retailers to join forces and unite in a large commercial coalition that generates added value for both retailers and customers. Along this line, the SMARTBUY ecosystem offers several novel features: (i) inventory management of centralized products and services, (ii) geo-located marketing of products and services, (iii) location-based search for products offered by neighboring retailers, and (iv) personalized recommendations for purchasing products derived by an innovative recommendation system. SMARTBUY materializes a blended retailing paradigm which combines the benefits of online shopping with the attractiveness of traditional shopping in brick-and-mortar stores. This article provides an overview of the main architectural components and functional aspects of the SMARTBUY ecosystem. Then, it reports the main findings derived from a 12 months-long pilot execution of SMARTBUY across four European cities and discusses the key technology acceptance factors when deploying alike business alliances.
Sensors
Machine learning techniques combined with wearable electronics can deliver accurate short-term bl... more Machine learning techniques combined with wearable electronics can deliver accurate short-term blood glucose level prediction models. These models can learn personalized glucose–insulin dynamics based on the sensor data collected by monitoring several aspects of the physiological condition and daily activity of an individual. Until now, the prevalent approach for developing data-driven prediction models was to collect as much data as possible to help physicians and patients optimally adjust therapy. The objective of this work was to investigate the minimum data variety, volume, and velocity required to create accurate person-centric short-term prediction models. We developed a series of these models using different machine learning time series forecasting techniques suitable for execution within a wearable processor. We conducted an extensive passive patient monitoring study in real-world conditions to build an appropriate data set. The study involved a subset of type 1 diabetic sub...
Algorithms
Designing advanced health monitoring systems is still an active research topic. Wearable and remo... more Designing advanced health monitoring systems is still an active research topic. Wearable and remote monitoring devices enable monitoring of physiological and clinical parameters (heart rate, respiration rate, temperature, etc.) and analysis using cloud-centric machine-learning applications and decision-support systems to predict critical clinical states. This paper moves from a totally cloud-centric concept to a more distributed one, by transferring sensor data processing and analysis tasks to the edges of the network. The resulting solution enables the analysis and interpretation of sensor-data traces within the wearable device to provide actionable alerts without any dependence on cloud services. In this paper, we use a supervised-learning approach to detect heartbeats and classify arrhythmias. The system uses a window-based feature definition that is suitable for execution within an asymmetric multicore embedded processor that provides a dedicated core for hardware assisted patte...
Lecture Notes in Computer Science
Recent technologies for low-rate, long-range transmission in unlicensed sub-GHz frequency bands e... more Recent technologies for low-rate, long-range transmission in unlicensed sub-GHz frequency bands enables the realization of Long-range Wide Area Network. Despite the rapid uptake of LPWANs, security concerns arising from the open architecture and usage of the unlicensed band are also growing. While the current LPWAN deployments include basic techniques to deal with end-to-end encryption there are specific security issues that arise due to the overall architecture and protocol layer design. In this paper, a new scheme to establish end-to-end secure communication in long-range IoT deployments is introduced. The advantages over the existing approaches and architectural design are presented in the context of typical smart cities application scenarios.
Electronic Notes in Theoretical Computer Science
Electronic Notes in Theoretical Computer Science
Sensors (Basel, Switzerland), Jan 10, 2017
Raising awareness among young people and changing their behaviour and habits concerning energy us... more Raising awareness among young people and changing their behaviour and habits concerning energy usage is key to achieving sustained energy saving. Additionally, young people are very sensitive to environmental protection so raising awareness among children is much easier than with any other group of citizens. This work examines ways to create an innovative Information & Communication Technologies (ICT) ecosystem (including web-based, mobile, social and sensing elements) tailored specifically for school environments, taking into account both the users (faculty, staff, students, parents) and school buildings, thus motivating and supporting young citizens' behavioural change to achieve greater energy efficiency. A mixture of open-source IoT hardware and proprietary platforms on the infrastructure level, are currently being utilized for monitoring a fleet of 18 educational buildings across 3 countries, comprising over 700 IoT monitoring points. Hereon presented is the system's hi...
HardwareX
One oft-cited strategy towards sustainability is improving energy efficiency inside public buildi... more One oft-cited strategy towards sustainability is improving energy efficiency inside public buildings. In this context, the educational buildings sector presents a very interesting and important case for the monitoring and management of buildings, since it addresses both energy and educational issues. In this work, we present and discuss the hardware IoT infrastructure substrate that provides real-time monitoring in multiple school buildings. We believe that such a system needs to follow an open design approach: rely on hardware-agnostic components that communicate over well-defined open interfaces. We present in detail the design of our hardware components, while also providing insights to the overall system design and a first set of results on their operation. The presented hardware components are utilized as the core hardware devices for GAIA, an EU research project aimed at the educational community. As our system has been deployed and tested in several public school buildings in Greece, we also report on its validation.
Proceedings of the Seventeenth Annual Acm Symposium on Parallelism in Algorithms and Architectures, Jul 18, 2005
Wireless sensor networks are comprised of a vast number ofultra-small fully autonomous computing,... more Wireless sensor networks are comprised of a vast number ofultra-small fully autonomous computing, communication and sensingdevices, with very restricted energy and computing capabilities,which co-operate to accomplish a large sensing task. Such networkscan be very useful in practice in applications that requirefine-grain monitoring of physical environment subjected to criticalconditions (such as inaccessible terrains or disaster places).Features including the huge number of
Proceedings of the 17th International Symposium on Parallel and Distributed Processing, 2003
Smart Dust is a set of a vast number of ultra-small fully autonomous computing and communication ... more Smart Dust is a set of a vast number of ultra-small fully autonomous computing and communication devices, with very restricted energy and computing capabilities, that cooperate to quickly and efficiently accomplish a large sensing task. Smart Dust can be very useful in practice i.e. in the local detection of a remote crucial event and the propagation of data reporting its realization. In this work we continue (see [4]) our effort towards the research on smart dust from a basic algorithmic point of view. Under a simple but realistic model for smart dust we present an interesting problem, which is how to propagate efficiently information on an event detected locally. Then we present a new smart dust protocol, which we call the "Sleep-Awake" protocol, for information propagation that explicitly uses the energy saving features (i.e. the alteration of sleeping and awake time periods) of the smart dust particles. By using both some simple probabilistic analysis and extensive experiments, we provide some first concrete results for the success probability and the time and energy efficiency of the protocol, in terms of parameters of the smart dust network. We note that the study of the interplay of these parameters allows us to program the smart dust network characteristics accordingly.
An ad-hoc mobile network is a collection of mobile hosts, with wireless communication capabilitie... more An ad-hoc mobile network is a collection of mobile hosts, with wireless communication capabilities, forming a temporary network without the aid of any established fixed infrastructure. In such networks, topological connectivity is subject to frequent, unpredictable change. Our work focuses on networks with high rate of such changes to connectivity. For such dynamic changing networks we propose protocols which exploit the coordinated (by the protocol) motion of a small part of the network. We show that such protocols can be designed to work correctly and efficiently even in the case of arbitrary (but not malicious) movements of the hosts not affected by the protocol. We also propose a methodology for the analysis of the expected behaviour of protocols for such networks, based on the assumption that mobile hosts (whose motion is not guided by the protocol) conduct concurrent random walks in their motion space. Our work examines some fundamental problems such as pair-wise communication, election of a leader and counting, and proposes distributed algorithms for each of them. We provide their proofs of correctness, and also give rigorous analysis by combinatorial tools and also via experiments.
Computer Science Review, Feb 1, 2011
In this work, we study the propagation of influence and computation in dynamic distributed system... more In this work, we study the propagation of influence and computation in dynamic distributed systems. We focus on broadcasting models under a worst-case dynamicity assumption which have received much attention recently. We drop for the first time in worst-case dynamic networks the common instantaneous connectivity assumption and require a minimal temporal connectivity. Our temporal connectivity constraint only requires that another causal influence occurs within every time-window of some given length. We establish that there are dynamic graphs with always disconnected instances with equivalent temporal connectivity to those with always connected instances. We present a termination criterion and also establish the computational equivalence with instantaneous connectivity networks. We then consider another model of dynamic networks in which each node has an underlying communication neighborhood and the requirement is that each node covers its local neighborhood within any time-window of some given length. We discuss several properties and provide a protocol for counting, that is for determining the number of nodes in the network.
Computer Science Review, Feb 1, 2011
Computer Science Review, Feb 1, 2011
2015 IEEE Symposium on Computers and Communication (ISCC), 2015
Short lived chest pain episodes of post PCI patients represent the most common clinical scenario ... more Short lived chest pain episodes of post PCI patients represent the most common clinical scenario treated in the Accidents and Emergency Room. Continuous ECG monitoring could substantially diminish such hospital admissions and related ambulance calls. Delivering community based, easy-to-handle, easy to wear, real time electrocardiography systems is still a quest, despite the existence of electronic electrocardiography systems for several decades. The PATRIOT system serves this challenge via a 12-channel, easy to wear, easy to carry, mobile linked, miniaturized automatic ECG device and a Cloud platform. The system may deliver high quality electrocardiograms of a patient to medical personnel either on the spot or remotely both in a synchronous or asynchronous mode, enhancing autonomy, mobility, quality of life and safety or recently treated coronary artery disease patients.
Uploads
Papers by Ioannis Chatzigiannakis