Intelligent Distributed Computing

A special issue of Information (ISSN 2078-2489). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: closed (30 April 2021) | Viewed by 6524

Special Issue Editor


E-Mail Website
Guest Editor
Department of Computer Science, Università di Pisa, 56126 Pisa PI, Italy
Interests: distributed computing; clock synchronization; sensor networks; web applications; serverless applications

Special Issue Information

Dear Colleagues,

In the last few decades, we managed to build the most complex artifact ever made: the Internet. Today, millions of devices are connected, and their number is growing with the introduction of myriads of sensors and actuators. We have conceptual tools such as abstraction layers that help us to understand the complex structure of the global network and to extend it with new functions and capabilities. To this end, new communication media and protocols are introduced, giving new ways to exchange data and control. We use the Internet to find and obtain knowledge, but we need to empower its engine with autonomous capabilities to adapt processes and to synthesize new ones.

The introduction of a centralized controller preserving the consistent operation of autonomous entities seems an appealing shortcut. However, through the years, we have learned that such apparent simplification introduces several hidden problems: a performance bottleneck, a single point of failure, a security weakness, etc. By contrast, distributed systems scale better, are more resilient, and less exposed to intrusion.

However, their design is challenging, since communication latencies jeopardize timing, and the concept of a global state is a dangerous illusion. Distributed control is a powerful conceptual tool, just like abstraction layers, but very difficult to apply. We need research targeting systems of networked entities that use the available information to produce the kind of behaviors that we qualify as intelligent: to use the experience to learn how to cope with unanticipated events. We have several tools that individually pursue this aim, but we need to coordinate them using a multidisciplinary attitude. The range of application fields for such devices has limits that are yet to be defined: from personal assistants to robot swarms, from weather forecasts to sentiment analysis, etc.

The Special Issue on "Intelligent Distributed Computing" welcomes articles about computer systems that produce new, adaptive behaviors of member devices based on their collective experience. Contributions should provide what is needed in order to reproduce their results, i.e., databases, algorithms, program sources, and hardware designs, all of which should be made available to the readers. We will especially appreciate those that show how the results meet the specific demands of human environments, health, and culture.

Topics:

  • Adaptive coordination of distributed agents
  • Swarm intelligence and distributed robotics
  • Distributed problem solving and planning
  • Distributed approaches to machine learning
  • Distributed Intelligence for medical application
  • Distributed Intelligence for environmental control
  • Distributed Intelligence in human–computer interaction
  • Distributed Intelligence for the humanities
  • Time in intelligent distributed systems

Dr. Augusto Ciuffoletti
Guest Editor

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 submissions that pass pre-check are 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. Information is an international peer-reviewed open access monthly 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 1600 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.

Published Papers (2 papers)

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

Research

16 pages, 2409 KiB  
Article
A Quaternion Gated Recurrent Unit Neural Network for Sensor Fusion
by Uche Onyekpe, Vasile Palade, Stratis Kanarachos and Stavros-Richard G. Christopoulos
Information 2021, 12(3), 117; https://0-doi-org.brum.beds.ac.uk/10.3390/info12030117 - 09 Mar 2021
Cited by 13 | Viewed by 3798
Abstract
Recurrent Neural Networks (RNNs) are known for their ability to learn relationships within temporal sequences. Gated Recurrent Unit (GRU) networks have found use in challenging time-dependent applications such as Natural Language Processing (NLP), financial analysis and sensor fusion due to their capability to [...] Read more.
Recurrent Neural Networks (RNNs) are known for their ability to learn relationships within temporal sequences. Gated Recurrent Unit (GRU) networks have found use in challenging time-dependent applications such as Natural Language Processing (NLP), financial analysis and sensor fusion due to their capability to cope with the vanishing gradient problem. GRUs are also known to be more computationally efficient than their variant, the Long Short-Term Memory neural network (LSTM), due to their less complex structure and as such, are more suitable for applications requiring more efficient management of computational resources. Many of such applications require a stronger mapping of their features to further enhance the prediction accuracy. A novel Quaternion Gated Recurrent Unit (QGRU) is proposed in this paper, which leverages the internal and external dependencies within the quaternion algebra to map correlations within and across multidimensional features. The QGRU can be used to efficiently capture the inter- and intra-dependencies within multidimensional features unlike the GRU, which only captures the dependencies within the sequence. Furthermore, the performance of the proposed method is evaluated on a sensor fusion problem involving navigation in Global Navigation Satellite System (GNSS) deprived environments as well as a human activity recognition problem. The results obtained show that the QGRU produces competitive results with almost 3.7 times fewer parameters compared to the GRU.
Full article
(This article belongs to the Special Issue Intelligent Distributed Computing)
Show Figures

Figure 1

23 pages, 7880 KiB  
Article
S.O.V.O.R.A.: A Distributed Wireless Operating System
by Henry Zárate Ceballos and Jorge Eduardo Ortiz Triviño
Information 2020, 11(12), 581; https://0-doi-org.brum.beds.ac.uk/10.3390/info11120581 - 14 Dec 2020
Viewed by 2055
Abstract
Due to the growth of users and linked devices in networks, there is an emerging need for dynamic solutions to control and manage computing and network resources. This document proposes a Distributed Wireless Operative System on a Mobile Ad-hoc Network (MANET) to manage [...] Read more.
Due to the growth of users and linked devices in networks, there is an emerging need for dynamic solutions to control and manage computing and network resources. This document proposes a Distributed Wireless Operative System on a Mobile Ad-hoc Network (MANET) to manage and control computing resources in relation to several virtual resources linked in a wireless network. This prototype has two elements: a local agent that works on each physical node to manage the computing resources (e.g., virtual resources and distributed applications) and an orchestrator agent that monitors, manages, and deploys policies on each physical node. These elements arrange the local and global computing resources to provide a quality service to the users of the Ad-hoc cluster. The proposed S.O.V.O.R.A. model (Operating Virtualized System oriented to Ad-hoc networks) defines primitives, commands, virtual structures, and modules to operate as a distributed wireless operating system. Full article
(This article belongs to the Special Issue Intelligent Distributed Computing)
Show Figures

Figure 1

Back to TopTop