Discov. Internet Things

8 papers23 directions
Discov. Internet Things is a research venue established in 2021 that focuses on the technical evolution and practical application of Internet of Things (IoT) technologies. It serves as a forum for research at the intersection of distributed networking, industrial automation, and artificial intelligence. The venue’s scope includes the development of smart buildings, the integration of UAV-enabled wireless communication, and the optimization of IoT frameworks for industrial environments. The venue is characterized by its focus on system resilience and decentralized intelligence. Published research frequently addresses security and scalability through topics such as reputation-enhanced Byzantine fault tolerance, behavioral anomaly detection for insider threats, and cryptographic sortition for decentralized networks. In the context of machine learning, the venue explores edge learning, resource-aware intelligence for autonomous platforms, and the adversarial manipulation of uncertainty quantification. These contributions aim to improve the reliability of decentralized networks and the efficiency of computation at the network edge. Within the machine learning and AI community, Discov. Internet Things provides a specialized outlet for studying uncertainty propagation and Bayesian topology learning within network data. Prolific contributors to the venue include researchers such as Rick S. Blum, Raja Jurdak, and Mohammad Hajimirsadeghi. By focusing on high-mobility environments and the joint optimization of communication and computation, the venue facilitates the study of how AI models can be deployed and maintained in complex, real-world physical systems.

Papers by Year

2025 4
2024 1
2021 3

Top Research Directions

Research directions most represented by papers from this venue.

Learning Latent Graph Topologies Directly from Data 2
Joint Estimation of Graph Topology and Signals 1
Verifiable Random Selection in Decentralized Networks 1
Graph Smoothness Regularization for Signal Processing and Learning 1
Dynamic Network Infrastructure via Mobile Aerial Base Stations 1
Continuous Behavioral Monitoring Against Internal Adversaries 1
Mapping Directed Information Flow in Neural Networks 1
Reputation Weighted Consensus in Decentralized Networks 1
Signal Processing and Learning on Directed Graphs 1
Overcoming the Quadratic Communication Bottleneck in Distributed Systems 1
Adversarial Manipulation of Distributed Reputation Systems 1
Noise Adaptive Regularization for Inverse Problems 1
Adversarial Attacks on Uncertainty Quantification 1
Tuning Regularization Weights for Graph Learning 1
Joint Communication and Computation Resource Allocation 1

Top Authors

AuthorPapers
Xiaowen Dong2
Chang Wen Chen1
Dimity Miller1
Erik Blasch1
Li Zhang1
Peyman Moghadam1
Raja Jurdak1
Volkan Dedeoglu1

Impactful Papers

Papers from this venue that shaped research clusters.

Influential

Papers

TitleYear
Analytical framework for UAV-enabled wireless communication with D2D networks2025
Landscape layout characteristics and evaluation of smart buildings based on deep learning algorithms2025
Realizing the potential of Internet of Things (IoT) in Industrial applications2025
Reputation-Enhanced Practical Byzantine Fault Tolerance Algorithm for Node Capture Attacks on UAV Networks2025
Uncertainty propagation in the internet of things2024
Bayesian Topology Learning and noise removal from network data2021
Correction to: Bayesian Topology Learning and noise removal from network data2021
Drones as internet of video things front-end sensors: challenges and opportunities2021