Dr. Martin Serrano, in collaboration with NIST researchers Eugene Song, Tom Roth, and David Wollman, received a best paper presentation award at the 2024 IEEE IECON international conference for the team’s research paper, titled “Semantics for Enhancing Communications- and Edge-Intelligence-enabled Smart Sensors: A Practical Use Case in Federated Automotive Diagnostics.” In his presentation, Dr. Serrano explained the advantages of semantics and ontology engineering and its relevance for enabling semantic communications in edge AI-enabled smart sensors, and its use in federated automotive systems.
Dr. Serrano introduced the visionary data continuum for IoT data including interpreting, understanding, and visualizing IoT data from various sensor devices to applications, and he addressed the new challenges of IoT for semantic communication to collect, exchange, and share IoT data. Dr. Serrano explained how semantic Web technologies based on linked data and data interoperability principles can be used to enable efficient stream processing, data management, and intelligent applications.
Dr. Serrano then described the paper contributions including extraction of domain knowledge (e.g., dictionary, rules to interpret data, and the use of ontology information) and use of this knowledge in automotive applications. Dr. Serrano explained how linked Open Vocabularies for Internet of Things (LOV4IoT) and the Machine to Machine for Measurement data (M3) framework can be used to combine and infer domain knowledge for applications. He described a practical use case of AI-enabled smart sensors for automotive diagnoses using an audio event dataset classifier (YAMNet) and Tiny Machine Learning (TinyML), and he demonstrated a prototype implementation on edge devices including its practical use for event detection in Automotive Preventive Maintenance.
Dr. Serrano concluded by describing planned future work including the design of an AI-enabled smart sensor architecture, other applications and uses of the introduced work in different domains, AudioSet extensions, and semantic model validation including the need for cross-domain knowledge testing using the presented edge AI approach.
NIST researcher Dr. Eugene Song, Dr. Helbert da Rocha (University of Beira Interior, Portugal), and collaborators demonstrated an online tool called the IEEE 1451 Playground at the 2024 IEEE IECON conference. The tool, which provides interactive forms to experiment with and learn the IEEE 1451 standard for smart sensors, was presented during a special session held for the InterOp Plugfest. The Plugfest showcased reference implementations, validations, conformance testing, and interoperability testing of the IEEE 1451 series of standards from industry, academy, and private sector participants.
The IEEE 1451 Playground was designed to support both learning the IEEE 1451 family of standards and validating user inputs against the standard specifications. It focuses on exploring, testing, and validating the transducer electronics data sheet (TEDS), transducer services messages, and network services messages defined in the IEEE 1451.0-2024 standard. During the event, Dr. Song also demonstrated the IEEE P1451.99 binding implementation enabling smart sensors and devices physically deployed in Portugal, Japan, Italy, and Chile to remotely participate in the same sensor network.
NIST researcher Dr. Eugene Song and Prof. Hiroaki Nishi (Keio University, Japan) presented a research paper titled “Security for IEEE P1451.1.6-based Sensor Networks for IoT Applications” at the 2024 IEEE IECON conference. Their presentation received a best presentation award for its session.
In the presentation, Dr. Song highlighted that the main challenges for Internet of Things (IoT) sensor networks are the lack of robust standards, diverse wireline and wireless connectivity, interoperability between different devices, security, and privacy. IEEE 1451 is a family of standards for smart sensors that addresses these challenges by defining common network services, transducer services, and transducer electronic data sheets (TEDS), with the P1451.1.6 standard focused on IoT devices that communicate using the MQTT (Message Queuing Telemetry Transport) communication protocol.
Prof. Nishi described a security framework for IEEE P1451.1.6 sensor networks including an architecture, a security policy with six security levels, and a format for security TEDS. Prof. Nishi also introduced a new MQTT service to manage access control lists across the sensor network. The framework was implemented and demonstrated with a hardware prototype using two sensors communicating through an MQTT broker.
NIST researcher leaders Edward Griffor, Tao Zhang, and Abdella Battou addressed the 21st International ACS/IEEE International Conference on Computer Systems and Applications (AICCSA 2024) in Sousse, Tunisia, held on 22-26 October 2024. The conference sessions included presentations on Ubiquitous, Parallel and Distributed Computing (including cloud, IoT, network, sensors, and blockchain technologies); Security, Privacy, and Trust; Data Science, Knowledge Engineering, and Ontologies (including Information Retrieval, Big Data, Databases, and Knowledge Systems); Artificial Intelligence & Cognitive Systems; Natural Language Processing; and Multimedia, Computer Vision, and Image Processing.
Dr. Griffor’s keynote on using Artificial Intelligence/Machine Learning (AI/ML) to assess autonomous system performance described current progress on developing performance metrics for these systems. Griffor plotted the evolution of system energy/processing usage as an AI-equipped system reasons, and learns, about its operating environment, and he explained how the system reduces the “informational dimension” of its operating environment, improving its overall performance. Griffor pointed to how the system’s rules emerge and make action progressively more energy/processing efficient. As action patterns emerge, these rules can be “exported” as structure in the environment, resulting in autonomous systems that can manage tradeoffs between the limited resources of time and energy to meet quality objectives.
Dr. Zhang’s keynote on edge AI and 6G discussed the essential roles of edge AI in 6G and beyond networks. Zhang described how edge computing has evolved to edge AI, and how edge AI is further evolving toward an AI continuum that seamlessly spans from the user to the cloud. He discussed how edge AI and the AI continuum are becoming increasingly important for future AI and 6G networks. He further discussed possible initial steps toward an AI-native 6G network architecture that will be enabled by edge AI and the AI continuum.
Dr. Battou’s keynote on quantum networking described current work on the Multiverse platform for quantum networks and experiments management. He explained the choice of microservices for the architecture and the Vert.x framework for its implementation. He then detailed services such as Topology, Configuration, Fault, and Security and how they are currently used in the NIST testbed and the Washington Metropolitan Quantum Network Research Consortium (DC-QNet).
On November 18, 2024, the NIST Industrial Wireless Research Team, led by NIST research leader Rick Candell, met with the National Electrical Manufacturers Association (NEMA) arc welding group to discuss the impacts of welding equipment on the performance of industrial wireless networks operating under 4 GHz. Affected networks include Wi-Fi networks operating at 2.4 GHz and private 5G networks at 3.5 GHz. A NIST publication “On the Impact of TIG Welding Interference on Industrial Wi-Fi Networks: Modeling of Empirical Data and Analytical Studying of Coexistence” drew the attention of the NEMA welding group, who asked for a meeting with the NIST team. The group included representative from Miller Electric, Lincoln Electric, and ESAB, among others, who collectively expressed a positive opinion of NIST’s research and publication. A key discussion point was that understanding the impact of industrial interference is important to controlling their impacts. Welding interference is a radio interference noise source investigated by the IEEE P3388 working group, chaired by Rick Candell. Conclusions from the meeting include that 1) more modern welding generators may potentially produce less interference than prior welding technology; 2) more measurements and study is needed to determine the interference impacts of these more modern welding machines; and 3) a collaboration between NIST and NEMA members could be beneficial to support this effort.
