entropy-logo

Journal Browser

Journal Browser

Swarms and Network Intelligence

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Information Theory, Probability and Statistics".

Deadline for manuscript submissions: closed (1 September 2022) | Viewed by 33816

Printed Edition Available!
A printed edition of this Special Issue is available here.

Special Issue Editors


E-Mail Website
Guest Editor
MIT Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139-4307, USA
Interests: federated learning; machine learning; network theory; social physics; swarm robotics

E-Mail Website
Guest Editor
Department of Technology, Management and Economics, Technical University of Denmark, DTU, Kgs. 2800 Lyngby, Denmark
Interests: intelligent transportation systems; machine learning and pattern recognition; transport modeling; computational creativity

E-Mail Website
Guest Editor
Department of Computer Science, Bar-Ilan University, Ramat-Gan 5290002, Israel
Interests: deep learning; evolutionary computation

Special Issue Information

Dear Colleagues,

The last decade has seen a transformative change in the paradigms, tools and processes utilized for the analysis, modeling and design of data-driven systems. A macrolevel-oriented design is gradually being replaced by bottom–up design methodologies, that emphasize micro-level interactions and efficient composability for the emergence of an optimal macroscopic result. Spanning from rapid penetration of autonomous vehicles and decentralized intelligent ride-sharing systems, through the increasing dominance of autonomous trading machines in the equities, currencies and commodities markets, to the growing appetite of decentralized autonomous scalable big-data dependent mechanisms in the intelligence and defense spaces.

This Special Issue aims to be a forum for the presentation of new and improved techniques for the modeling and analysis of swarm architectures and network-driven system designs. In particular, the analysis and interpretation of such approaches in real-world natural and engineered environments falls within the scope of this Special Issue.

We particularly welcome original research works that focus on information-driven theoretic analysis or modeling approach.

  • Information diffusion in real-world networks: temporal influence analysis and mutual information dynamics among nodes in real-life
  • Collective and swarm intelligence: decentralized information processing and decision making
  • Urban computing and smart cities: theoretical aspects of large-scale dynamic metropolitan multi-layered networks
  • Autonomous collaborative security: self-organization and resilient information processing
  • Intelligence transportation systems: information flow in geographically-embedded networks
  • Smart contracts and cryptocurrencies: computation limitation, convergence and information leakage
  • Decentralized finance (DeFi): effects of composability of information processing units on the future of economy

Dr. Yaniv Altshuler
Prof. Francisco Camara Pereira
Dr. Eli David
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. Entropy 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 2600 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.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (11 papers)

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

Editorial

Jump to: Research

12 pages, 262 KiB  
Editorial
Recent Developments in the Theory and Applicability of Swarm Search
by Yaniv Altshuler
Entropy 2023, 25(5), 710; https://doi.org/10.3390/e25050710 - 25 Apr 2023
Cited by 2 | Viewed by 1838
Abstract
Swarm intelligence (SI) is a collective behaviour exhibited by groups of simple agents, such as ants, bees, and birds, which can achieve complex tasks that would be difficult or impossible for a single individual [...] Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)

Research

Jump to: Editorial

23 pages, 2524 KiB  
Article
A Locust-Inspired Model of Collective Marching on Rings
by Michael Amir, Noa Agmon and Alfred M. Bruckstein
Entropy 2022, 24(7), 918; https://doi.org/10.3390/e24070918 - 30 Jun 2022
Cited by 1 | Viewed by 1707
Abstract
We study the collective motion of autonomous mobile agents in a ringlike environment. The agents’ dynamics are inspired by known laboratory experiments on the dynamics of locust swarms. In these experiments, locusts placed at arbitrary locations and initial orientations on a ring-shaped arena [...] Read more.
We study the collective motion of autonomous mobile agents in a ringlike environment. The agents’ dynamics are inspired by known laboratory experiments on the dynamics of locust swarms. In these experiments, locusts placed at arbitrary locations and initial orientations on a ring-shaped arena are observed to eventually all march in the same direction. In this work we ask whether, and how fast, a similar phenomenon occurs in a stochastic swarm of simple locust-inspired agents. The agents are randomly initiated as marching either clockwise or counterclockwise on a discretized, wide ring-shaped region, which we subdivide into k concentric tracks of length n. Collisions cause agents to change their direction of motion. To avoid this, agents may decide to switch tracks to merge with platoons of agents marching in their direction. We prove that such agents must eventually converge to a local consensus about their direction of motion, meaning that all agents on each narrow track must eventually march in the same direction. We give asymptotic bounds for the expected time it takes for such convergence or “stabilization” to occur, which depends on the number of agents, the length of the tracks, and the number of tracks. We show that when agents also have a small probability of “erratic”, random track-jumping behavior, a global consensus on the direction of motion across all tracks will eventually be reached. Finally, we verify our theoretical findings in numerical simulations. Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)
Show Figures

Figure 1

20 pages, 1734 KiB  
Article
Space-Air-Ground Integrated Mobile Crowdsensing for Partially Observable Data Collection by Multi-Scale Convolutional Graph Reinforcement Learning
by Yixiang Ren, Zhenhui Ye, Guanghua Song and Xiaohong Jiang
Entropy 2022, 24(5), 638; https://doi.org/10.3390/e24050638 - 1 May 2022
Cited by 5 | Viewed by 2427
Abstract
Mobile crowdsensing (MCS) is attracting considerable attention in the past few years as a new paradigm for large-scale information sensing. Unmanned aerial vehicles (UAVs) have played a significant role in MCS tasks and served as crucial nodes in the newly-proposed space-air-ground integrated network [...] Read more.
Mobile crowdsensing (MCS) is attracting considerable attention in the past few years as a new paradigm for large-scale information sensing. Unmanned aerial vehicles (UAVs) have played a significant role in MCS tasks and served as crucial nodes in the newly-proposed space-air-ground integrated network (SAGIN). In this paper, we incorporate SAGIN into MCS task and present a Space-Air-Ground integrated Mobile CrowdSensing (SAG-MCS) problem. Based on multi-source observations from embedded sensors and satellites, an aerial UAV swarm is required to carry out energy-efficient data collection and recharging tasks. Up to date, few studies have explored such multi-task MCS problem with the cooperation of UAV swarm and satellites. To address this multi-agent problem, we propose a novel deep reinforcement learning (DRL) based method called Multi-Scale Soft Deep Recurrent Graph Network (ms-SDRGN). Our ms-SDRGN approach incorporates a multi-scale convolutional encoder to process multi-source raw observations for better feature exploitation. We also use a graph attention mechanism to model inter-UAV communications and aggregate extra neighboring information, and utilize a gated recurrent unit for long-term performance. In addition, a stochastic policy can be learned through a maximum-entropy method with an adjustable temperature parameter. Specifically, we design a heuristic reward function to encourage the agents to achieve global cooperation under partial observability. We train the model to convergence and conduct a series of case studies. Evaluation results show statistical significance and that ms-SDRGN outperforms three state-of-the-art DRL baselines in SAG-MCS. Compared with the best-performing baseline, ms-SDRGN improves 29.0% reward and 3.8% CFE score. We also investigate the scalability and robustness of ms-SDRGN towards DRL environments with diverse observation scales or demanding communication conditions. Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)
Show Figures

Figure 1

21 pages, 3354 KiB  
Article
Experimental Validation of Entropy-Driven Swarm Exploration under Sparsity Constraints with Sparse Bayesian Learning
by Christoph Manss, Isabel Kuehner and Dmitriy Shutin
Entropy 2022, 24(5), 580; https://doi.org/10.3390/e24050580 - 20 Apr 2022
Viewed by 1672
Abstract
Increasing the autonomy of multi-agent systems or swarms for exploration missions requires tools for efficient information gathering. This work studies this problem from theoretical and experimental perspectives and evaluates an exploration system for multiple ground robots that cooperatively explore a stationary spatial process. [...] Read more.
Increasing the autonomy of multi-agent systems or swarms for exploration missions requires tools for efficient information gathering. This work studies this problem from theoretical and experimental perspectives and evaluates an exploration system for multiple ground robots that cooperatively explore a stationary spatial process. For the distributed model, two conceptually different distribution paradigms are considered. The exploration is based on fusing distributively gathered information using Sparse Bayesian Learning (SBL), which permits representing the spatial process in a compressed manner and thus reduces the model complexity and communication load required for the exploration. An entropy-based exploration criterion is formulated to guide the agents. This criterion uses an estimation of a covariance matrix of the model parameters, which is then quantitatively characterized using a D-optimality criterion. The new sampling locations for the agents are then selected to minimize this criterion. To this end, a distributed optimization of the D-optimality criterion is derived. The proposed entropy-driven exploration is then presented from a system perspective and validated in laboratory experiments with two ground robots. The experiments show that SBL together with the distributed entropy-driven exploration is real-time capable and leads to a better performance with respect to time and accuracy compared with similar state-of-the-art algorithms. Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)
Show Figures

Figure 1

16 pages, 633 KiB  
Article
Scalable and Transferable Reinforcement Learning for Multi-Agent Mixed Cooperative–Competitive Environments Based on Hierarchical Graph Attention
by Yining Chen, Guanghua Song, Zhenhui Ye and Xiaohong Jiang
Entropy 2022, 24(4), 563; https://doi.org/10.3390/e24040563 - 18 Apr 2022
Cited by 8 | Viewed by 3192
Abstract
Most previous studies on multi-agent systems aim to coordinate agents to achieve a common goal, but the lack of scalability and transferability prevents them from being applied to large-scale multi-agent tasks. To deal with these limitations, we propose a deep reinforcement learning (DRL) [...] Read more.
Most previous studies on multi-agent systems aim to coordinate agents to achieve a common goal, but the lack of scalability and transferability prevents them from being applied to large-scale multi-agent tasks. To deal with these limitations, we propose a deep reinforcement learning (DRL) based multi-agent coordination control method for mixed cooperative–competitive environments. To improve scalability and transferability when applying in large-scale multi-agent systems, we construct inter-agent communication and use hierarchical graph attention networks (HGAT) to process the local observations of agents and received messages from neighbors. We also adopt the gated recurrent units (GRU) to address the partial observability issue by recording historical information. The simulation results based on a cooperative task and a competitive task not only show the superiority of our method, but also indicate the scalability and transferability of our method in various scale tasks. Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)
Show Figures

Figure 1

17 pages, 2385 KiB  
Article
DNN Intellectual Property Extraction Using Composite Data
by Itay Mosafi, Eli (Omid) David, Yaniv Altshuler and Nathan S. Netanyahu
Entropy 2022, 24(3), 349; https://doi.org/10.3390/e24030349 - 28 Feb 2022
Cited by 2 | Viewed by 2478
Abstract
As state-of-the-art deep neural networks are being deployed at the core level of increasingly large numbers of AI-based products and services, the incentive for “copying them” (i.e., their intellectual property, manifested through the knowledge that is encapsulated in them) either by adversaries or [...] Read more.
As state-of-the-art deep neural networks are being deployed at the core level of increasingly large numbers of AI-based products and services, the incentive for “copying them” (i.e., their intellectual property, manifested through the knowledge that is encapsulated in them) either by adversaries or commercial competitors is expected to considerably increase over time. The most efficient way to extract or steal knowledge from such networks is by querying them using a large dataset of random samples and recording their output, which is followed by the training of a student network, aiming to eventually mimic these outputs, without making any assumption about the original networks. The most effective way to protect against such a mimicking attack is to answer queries with the classification result only, omitting confidence values associated with the softmax layer. In this paper, we present a novel method for generating composite images for attacking a mentor neural network using a student model. Our method assumes no information regarding the mentor’s training dataset, architecture, or weights. Furthermore, assuming no information regarding the mentor’s softmax output values, our method successfully mimics the given neural network and is capable of stealing large portions (and sometimes all) of its encapsulated knowledge. Our student model achieved 99% relative accuracy to the protected mentor model on the Cifar-10 test set. In addition, we demonstrate that our student network (which copies the mentor) is impervious to watermarking protection methods and thus would evade being detected as a stolen model by existing dedicated techniques. Our results imply that all current neural networks are vulnerable to mimicking attacks, even if they do not divulge anything but the most basic required output, and that the student model that mimics them cannot be easily detected using currently available techniques. Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)
Show Figures

Figure 1

36 pages, 5115 KiB  
Article
Organisational Structure and Created Values. Review of Methods of Studying Collective Intelligence in Policymaking
by Rafał Olszowski, Piotr Pięta, Sebastian Baran and Marcin Chmielowski
Entropy 2021, 23(11), 1391; https://doi.org/10.3390/e23111391 - 24 Oct 2021
Cited by 2 | Viewed by 2567
Abstract
The domain of policymaking, which used to be limited to small groups of specialists, is now increasingly opening up to the participation of wide collectives, which are not only influencing government decisions, but also enhancing citizen engagement and transparency, improving service delivery and [...] Read more.
The domain of policymaking, which used to be limited to small groups of specialists, is now increasingly opening up to the participation of wide collectives, which are not only influencing government decisions, but also enhancing citizen engagement and transparency, improving service delivery and gathering the distributed wisdom of diverse participants. Although collective intelligence has become a more common approach to policymaking, the studies on this subject have not been conducted in a systematic way. Nevertheless, we hypothesized that methods and strategies specific to different types of studies in this field could be identified and analyzed. Based on a systematic literature review, as well as qualitative and statistical analyses, we identified 15 methods and revealed the dependencies between them. The review indicated the most popular approaches, and the underrepresented ones that can inspire future research. Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)
Show Figures

Figure 1

17 pages, 2542 KiB  
Article
Leadership Hijacking in Docker Swarm and Its Consequences
by Adi Farshteindiker and Rami Puzis
Entropy 2021, 23(7), 914; https://doi.org/10.3390/e23070914 - 19 Jul 2021
Cited by 4 | Viewed by 3459
Abstract
With the advent of microservice-based software architectures, an increasing number of modern cloud environments and enterprises use operating system level virtualization, which is often referred to as container infrastructures. Docker Swarm is one of the most popular container orchestration infrastructures, providing high availability [...] Read more.
With the advent of microservice-based software architectures, an increasing number of modern cloud environments and enterprises use operating system level virtualization, which is often referred to as container infrastructures. Docker Swarm is one of the most popular container orchestration infrastructures, providing high availability and fault tolerance. Occasionally, discovered container escape vulnerabilities allow adversaries to execute code on the host operating system and operate within the cloud infrastructure. We show that Docker Swarm is currently not secured against misbehaving manager nodes. This allows a high impact, high probability privilege escalation attack, which we refer to as leadership hijacking, the possibility of which is neglected by the current cloud security literature. Cloud lateral movement and defense evasion payloads allow an adversary to leverage the Docker Swarm functionality to control each and every host in the underlying cluster. We demonstrate an end-to-end attack, in which an adversary with access to an application running on the cluster achieves full control of the cluster. To reduce the probability of a successful high impact attack, container orchestration infrastructures must reduce the trust level of participating nodes and, in particular, incorporate adversary immune leader election algorithms. Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)
Show Figures

Figure 1

18 pages, 1363 KiB  
Article
Accuracy-Risk Trade-Off Due to Social Learning in Crowd-Sourced Financial Predictions
by Dhaval Adjodah, Yan Leng, Shi Kai Chong, P. M. Krafft, Esteban Moro and Alex Pentland
Entropy 2021, 23(7), 801; https://doi.org/10.3390/e23070801 - 24 Jun 2021
Cited by 2 | Viewed by 5445
Abstract
A critical question relevant to the increasing importance of crowd-sourced-based finance is how to optimize collective information processing and decision-making. Here, we investigate an often under-studied aspect of the performance of online traders: beyond focusing on just accuracy, what gives rise to the [...] Read more.
A critical question relevant to the increasing importance of crowd-sourced-based finance is how to optimize collective information processing and decision-making. Here, we investigate an often under-studied aspect of the performance of online traders: beyond focusing on just accuracy, what gives rise to the trade-off between risk and accuracy at the collective level? Answers to this question will lead to designing and deploying more effective crowd-sourced financial platforms and to minimizing issues stemming from risk such as implied volatility. To investigate this trade-off, we conducted a large online Wisdom of the Crowd study where 2037 participants predicted the prices of real financial assets (S&P 500, WTI Oil and Gold prices). Using the data collected, we modeled the belief update process of participants using models inspired by Bayesian models of cognition. We show that subsets of predictions chosen based on their belief update strategies lie on a Pareto frontier between accuracy and risk, mediated by social learning. We also observe that social learning led to superior accuracy during one of our rounds that occurred during the high market uncertainty of the Brexit vote. Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)
Show Figures

Figure 1

13 pages, 2132 KiB  
Article
Socioeconomic Patterns of Twitter User Activity
by Jacob Levy Abitbol and Alfredo J. Morales
Entropy 2021, 23(6), 780; https://doi.org/10.3390/e23060780 - 19 Jun 2021
Cited by 5 | Viewed by 2807
Abstract
Stratifying behaviors based on demographics and socioeconomic status is crucial for political and economic planning. Traditional methods to gather income and demographic information, like national censuses, require costly large-scale surveys both in terms of the financial and the organizational resources needed for their [...] Read more.
Stratifying behaviors based on demographics and socioeconomic status is crucial for political and economic planning. Traditional methods to gather income and demographic information, like national censuses, require costly large-scale surveys both in terms of the financial and the organizational resources needed for their successful collection. In this study, we use data from social media to expose how behavioral patterns in different socioeconomic groups can be used to infer an individual’s income. In particular, we look at the way people explore cities and use topics of conversation online as a means of inferring individual socioeconomic status. Privacy is preserved by using anonymized data, and abstracting human mobility and online conversation topics as aggregated high-dimensional vectors. We show that mobility and hashtag activity are good predictors of income and that the highest and lowest socioeconomic quantiles have the most differentiated behavior across groups. Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)
Show Figures

Figure 1

26 pages, 2622 KiB  
Article
Towards Generative Design of Computationally Efficient Mathematical Models with Evolutionary Learning
by Anna V. Kalyuzhnaya, Nikolay O. Nikitin, Alexander Hvatov, Mikhail Maslyaev, Mikhail Yachmenkov and Alexander Boukhanovsky
Entropy 2021, 23(1), 28; https://doi.org/10.3390/e23010028 - 27 Dec 2020
Cited by 13 | Viewed by 4434
Abstract
In this paper, we describe the concept of generative design approach applied to the automated evolutionary learning of mathematical models in a computationally efficient way. To formalize the problems of models’ design and co-design, the generalized formulation of the modeling workflow is proposed. [...] Read more.
In this paper, we describe the concept of generative design approach applied to the automated evolutionary learning of mathematical models in a computationally efficient way. To formalize the problems of models’ design and co-design, the generalized formulation of the modeling workflow is proposed. A parallelized evolutionary learning approach for the identification of model structure is described for the equation-based model and composite machine learning models. Moreover, the involvement of the performance models in the design process is analyzed. A set of experiments with various models and computational resources is conducted to verify different aspects of the proposed approach. Full article
(This article belongs to the Special Issue Swarms and Network Intelligence)
Show Figures

Figure 1

Back to TopTop