Special Issue "Ambient Intelligence in IoT Environments"

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: 30 April 2021.

Special Issue Editors

Prof. Dr. Dmitry Korzun
E-Mail Website
Guest Editor
Department of Computer Science, Institute of Mathematics and Information Technology, University of Petrozavodsk, Petrozavodsk, Russia
Interests: ambient intelligence; smart spaces; Internet of Things; networking; mathematical modeling; performance evaluation; data mining; information services; industrial internet; socio-cyber-physical systems; software engineering
Special Issues and Collections in MDPI journals
Prof. Dr. Ilya Shegelman
E-Mail Website
Co-Guest Editor
Department of End-to-End Technologies and Economic Security, Petrozavodsk State University, Russia
Interests: Innovation; Industrial Systems; System Engineering; Mathematical Modelling; Patents
Prof. Dr. Anatoly Voronin
E-Mail Website
Co-Guest Editor
Department of Applied Mathematics and Cybernetics, Petrozavodsk State University, Petrozavodsk, Russia
Interests: mathematical programming; control systems; industrial automation; enterprise planning; digital economy; digital society; digital education
Special Issues and Collections in MDPI journals

Special Issue Information

Dear Colleagues,

The Internet of Things (IoT) paradigm is essentially supported by the rapid progress in microelectronics. Many digital devices (mobile or embedded) appear near people, and each device can be utilized to serve humans. Devices are connected, and they enable cooperative service construction. Based on this type of cooperation, various IoT environments can be developed. Any IoT environment can be considered as a smart or intelligent environment, since the goal is to produce smart services for its users. A smart service is characterized by such properties as context-awareness, personalization, information assistance, ubiquitous access, adaptation, pro-active delivery, and others.

Service intelligence can be created based on Ambient Intelligence (AmI) methods. The environment provides multisource data and sensing possibilities. Data sources are people, information systems, Internet services, smart IoT objects, and embedded and mobile sensors. The data are fused and analyzed to derive the proper information to assist the user. First, the analysis is almost in real-time, when shared data are dynamically updated. Advanced solutions are needed to access up-to-date information. Second, the top relevant information facts are found among many appropriate ones. Advanced solutions to the information ranking problem are needed to efficiently assist the user. Plenty of different multimedia and mobile equipment are used to effectively deliver services as assistance information to users.

With this Special Issue, we invite authors to submit original research or review articles mainly focused on the Ambient Intelligence and Internet of Things environments. Research and development topics for this Special Issue include but are not limited to:

  • Smart IoT technologies, platforms, and systems;
  • Digital devices and network components for creating AmI in an IoT environment;
  • Multisource data sensing and information exchange in an IoT environment;
  • Fusing data from physical, cyber, and social worlds;
  • Edge and Fog computing for IoT environments;
  • Data mining by interaction of many IoT devices;
  • Data analytics based on semantic relations discovered in multisource data;
  • AmI implementation as a service of information assistance;
  • Testbeds, applications, case studies, and social issues around creating AmI in an IoT environment.

Adj.Prof. Dmitry Korzun
Prof. Ilya Shegelman
Prof. Anatoly Voronin
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Internet of Things
  • Ambient Intelligence
  • smart environments
  • multisource data
  • data mining
  • data fusing
  • information assistance
  • socio-cyber-physical systems
  • industrial internet
  • multi-device cooperation
  • digital innovation

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Open AccessArticle
Data Collection Technology for Ambient Intelligence Systems in Internet of Things
Electronics 2020, 9(11), 1846; https://doi.org/10.3390/electronics9111846 - 04 Nov 2020
Viewed by 512
Abstract
Ambient Intelligence System (AmIS) can be constructed using data collected from Internet of Things (IoT). In this paper, the IoT data collection problem is studied for AmIS with dynamic structure and dynamic behavior of participants (devices), where constraints on resources consumption and performance [...] Read more.
Ambient Intelligence System (AmIS) can be constructed using data collected from Internet of Things (IoT). In this paper, the IoT data collection problem is studied for AmIS with dynamic structure and dynamic behavior of participants (devices), where constraints on resources consumption and performance are essential. A novel technology is proposed, which includes the following steps: (1) definition of the data collection (DC) problem (considering the model of the observed system, DC conditions, etc.); (2) DC policy assignment; (3) construction of DC models; (4) evaluation and presentation of the data processing results. The proposed DC technology supports the development of data collecting subsystems in AmIS. Such subsystems provide data that reflect the changes in structure, state, situation, and behavior of participants in their IoT environment in time. Therefore, we show how this “cognitive” function of the DC process increases the intelligence level of IoT environment. Full article
(This article belongs to the Special Issue Ambient Intelligence in IoT Environments)
Show Figures

Figure 1

Open AccessArticle
Predictors of Ambient Intelligence: An Empirical Study in Enterprises in Slovakia
Electronics 2020, 9(10), 1655; https://doi.org/10.3390/electronics9101655 - 11 Oct 2020
Viewed by 579
Abstract
Integration of innovative pervasive technologies into the surrounding environment creates ambient intelligence which has become the subject of several scientific and academic considerations. In particular, the pervasive technology is based on Internet of Things (IoT) and Industrial Internet of Things (IIoT). Ambient intelligence [...] Read more.
Integration of innovative pervasive technologies into the surrounding environment creates ambient intelligence which has become the subject of several scientific and academic considerations. In particular, the pervasive technology is based on Internet of Things (IoT) and Industrial Internet of Things (IIoT). Ambient intelligence may be viewed from several perspectives: a technological, multi-aspect and visionary point of view. Several predictors influence the level of ambient intelligence. The aim is to identify significant predictors influencing ambient intelligence and simultaneously determine their impact on the achieved level of ambient intelligence of the company. In the research methodology, we acknowledge the research presumptions, the research question and research hypotheses, the measurement instrument, obtained data and methods used in accordance with the research model. The scientific article presents the results of an empirical study conducted on 206 enterprises, focusing on the examining of the influence of selected predictors on the level of ambient intelligence in enterprises in the Slovak Republic. It examines not only the influence of selected predictors on the level of ambient intelligence, but also their mutual interaction. We found that these activities even build ambient intelligence on their own, although in interaction with each other, their effect on the level of ambient intelligence begins to fade. Therefore, it is necessary to opt for their combination appropriately. Finally, we present the limits of the research and suggestions on further directions of research in this field. Full article
(This article belongs to the Special Issue Ambient Intelligence in IoT Environments)
Show Figures

Figure 1

Open AccessArticle
IoT-Oriented Design of an Associative Memory Based on Impulsive Hopfield Neural Network with Rate Coding of LIF Oscillators
Electronics 2020, 9(9), 1468; https://doi.org/10.3390/electronics9091468 - 08 Sep 2020
Cited by 2 | Viewed by 663
Abstract
The smart devices in Internet of Things (IoT) need more effective data storage opportunities, as well as support for Artificial Intelligence (AI) methods such as neural networks (NNs). This study presents a design of new associative memory in the form of impulsive Hopfield [...] Read more.
The smart devices in Internet of Things (IoT) need more effective data storage opportunities, as well as support for Artificial Intelligence (AI) methods such as neural networks (NNs). This study presents a design of new associative memory in the form of impulsive Hopfield network based on leaky integrated-and-fire (LIF) RC oscillators with frequency control and hybrid analog–digital coding. Two variants of the network schemes have been developed, where spiking frequencies of oscillators are controlled either by supply currents or by variable resistances. The principle of operation of impulsive networks based on these schemes is presented and the recognition dynamics using simple two-dimensional images in gray gradation as an example is analyzed. A fast digital recognition method is proposed that uses the thresholds of zero crossing of output voltages of neurons. The time scale of this method is compared with the execution time of some network algorithms on IoT devices for moderate data amounts. The proposed Hopfield algorithm uses rate coding to expand the capabilities of neuromorphic engineering, including the design of new hardware circuits of IoT. Full article
(This article belongs to the Special Issue Ambient Intelligence in IoT Environments)
Show Figures

Figure 1

Open AccessArticle
Neural Network for Low-Memory IoT Devices and MNIST Image Recognition Using Kernels Based on Logistic Map
Electronics 2020, 9(9), 1432; https://doi.org/10.3390/electronics9091432 - 02 Sep 2020
Cited by 1 | Viewed by 1661
Abstract
This study presents a neural network which uses filters based on logistic mapping (LogNNet). LogNNet has a feedforward network structure, but possesses the properties of reservoir neural networks. The input weight matrix, set by a recurrent logistic mapping, forms the kernels that transform [...] Read more.
This study presents a neural network which uses filters based on logistic mapping (LogNNet). LogNNet has a feedforward network structure, but possesses the properties of reservoir neural networks. The input weight matrix, set by a recurrent logistic mapping, forms the kernels that transform the input space to the higher-dimensional feature space. The most effective recognition of a handwritten digit from MNIST-10 occurs under chaotic behavior of the logistic map. The correlation of classification accuracy with the value of the Lyapunov exponent was obtained. An advantage of LogNNet implementation on IoT devices is the significant savings in memory used. At the same time, LogNNet has a simple algorithm and performance indicators comparable to those of the best resource-efficient algorithms available at the moment. The presented network architecture uses an array of weights with a total memory size from 1 to 29 kB and achieves a classification accuracy of 80.3–96.3%. Memory is saved due to the processor, which sequentially calculates the required weight coefficients during the network operation using the analytical equation of the logistic mapping. The proposed neural network can be used in implementations of artificial intelligence based on constrained devices with limited memory, which are integral blocks for creating ambient intelligence in modern IoT environments. From a research perspective, LogNNet can contribute to the understanding of the fundamental issues of the influence of chaos on the behavior of reservoir-type neural networks. Full article
(This article belongs to the Special Issue Ambient Intelligence in IoT Environments)
Show Figures

Figure 1

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: Ambient Intelligence Technologies for Digital Economy and Society: Selected Areas for Future Applications
Authors: Anatoly V. Voronin
Affiliation: Petrozavodsk State University, Russia
Abstract: Ambient Intelligence can be implemented based on sensing and computing capabilities of local devices in the IoT environment. As a result, the environment enables dynamic construction of digital services, which make the environment smart or intelligent. In this paper, we consider a generic technology for “intellectualization” of an IoT environment. The technology opportunities for future applications are considered based on our research and development experience with pilot prototypes for such areas as Smart Room environments, Industrial Monitoring, mobile Healthcare systems, Smart City services, and Smart Museum.

Title: Industrial Monitoring Systems based on Edge and Fog Computing
Authors: Dmitry G. Korzun; Evgeny I. Maslennikov; Alexey V. Yartsev; Alexey S. Shtykov
Affiliation: Petrozavodsk State University, Russia; GS Nanotech, Russia
Abstract: The monitoring problem of industrial production equipment forms a promising area for applying both IoT technology and AI methods. Any equipment unit is surrounded with various sensors that continuously provide real data on the technical state and operating conditions. In this paper, we consider the multi-flow collection system of heterogeneous sensed data. This data system provides source information for making the equipment unit as “smart”. Edge devices are responsible for processing the data as well as local servers on the network path to the enterprise information system. The result of data processing is services that provide analytics, assistance, and predictive-based recommendations to equipment personnel.

Title: Car Tourist Trajectory Prediction Based on Bidirectional LSTM Neural Network
Authors: Sergey Mikhailov; Alexey Kashevnik
Affiliation: SPIIRAS, Russia
Abstract: According to the UNTWO predictions, the number of international tourist arrivals will be slowly growing by the end of 2021. One of the ways to keep tourists safe while visiting attractions is to use a personal car or drive on a car instead of using the sharing services. The sensor-based information collected from the tourist's smartphone during the trip allows for his/her behavior analysis. Ambient intelligence technologies support analysis of the information using the surrounding devices. The paper describes an approach to the car tourist trajectory prediction, which has been the demanding subject of different research studies in recent years. We presented an approach that is based on the usage of the bidirectional LSTM neural network model. We show the reference model of the tourist support system for card-based attraction visiting trips. The sensor data acquisition process and the bidirectional LSTM model construction, training and evaluation are demonstrated. We proposed the system architecture that use the tourist smartphone for data acquisition as well as more powerful surrounding devices for information processing. The obtained results can be used for the tourist trip behavior.

Title: Industrial Sensing Systems with Strain Gauges: Opportunities for Smart Monitoring
Authors: Vladimir S. Ignakhin, Igor V. Sekirin, Vasiliy V. Melentyev, Sergey A. Marchenkov
Affiliation: Petrozavodsk State University, Russia
Abstract: The paper reviews recent research and applications of both laboratory prototypes and commercially fabricated mechanical strain gauges. Basic operational principles as well as advantageous points of each type of sensors are considered. The applicability of strain sensing is discussed for the needs of emerging smart monitoring application in such fields as Industrial Internet of Things, manufacturing, building construction, and vehicle operation. Our study focuses on magnetoelastic sensors based on new developed amorphous and nanocrystalline magnetic microwires and ribbons with advanced magnetoelastic properties as well as latest achievements in design of capacitive transducers of mechanical stress. The opportunity of integrating a set of mechanical strain sensors into a smart material monitoring system is discussed. The concept model and support algorithms of such a system are proposed, including the use of wireless bonding of the sensors network and the processing controller.

Title: Fine Grained Memory Inspection Techniques and Tools for Smart Devices Performance Tuning 
Authors: Kirill Krinkin, Valeriya Dopira, Olga Kochneva, Sergey Petrov and Maxim Kopylov
Affiliation: Saint-Petersburg Electrotechnical University “LETI”, Russia 
Abstract: Smart mobile devices are key citizens in Internet of Things (IoT) environments. On the one hand, a smart device needs to run complicated algorithms to implement Ambient Intelligence (AmI) in cooperation with other devices. On the other hand, each device has limited individual resources (hardware, computing capacity). In this paper, we study the problem of fine tuning the device operation, including power consumption. The goal is to achieve a sufficient performance level with minimal battery drain, especially in the case of autonomous operation. The crucial problem is memory management when a memory management algorithm avoids a memory competing state and synchronizes the availability of RAM regions with processes’ CPU-bursts. Many IoT devices use the software stack based on Linux operating system with many existing performance evaluation tools. We introduce performance criteria for IoT devices in Ambient Intelligence Systems are introduced. Existing tools are evaluated in respect to the applicability for tuning the memory performance of limited IoT devices. We present a fine grain memory analysis technique on RAM page level and its implementation apagescan as a novel evaluation tool. In particular, if the smart device software stack contains several micro-services with different QoS requirements then the apagescan tool investigates smart services' mutual impact and perform whole device service optimization, which increases device response time and potentially reduces the cost.

Title: Semantic Reference Model of Information Process Individualization in Internet of Things
Authors: Dmitry Mouromtsev
Affiliation: ITMO University, Russia
Abstract: The individualization of information processes employs Artificial Intelligence (AI), especially in the context of digital economy needs, such as Industrial Internet of Things (IIoT, IoT), data integration and fusion or scholarly communication. AI-based implementation requires hybrid approaches to process modelling that apply advanced methods of semantic knowledge representation and machine learning. The approaches have already proved their effectiveness through the development Graph Neural Networks (GNN) and Graph Deep Learning (GDL), including applications with process modeling. Nevertheless, the combination of machine learning and semantic modeling methods imposes a number of requirements and restrictions to the data types and object properties as well as to the structure of ontologies for information process representation. In this paper, we focus on concept modelling for IoT-oriented information process individualization. A novel semantic reference model is proposed for effective individualization of information processes. The model takes into account requirements and restrictions of the AI hybrid approaches in IoT settings. To show the effectiveness, we consider a use case of information exchange in an IoT environment where data integration is required for unstructured data in soft and heterogeneous domains such as technical specification analysis and learning analytics.

Back to TopTop