Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Natural and Artificial Concepts01:24

Natural and Artificial Concepts

619
In psychology, concepts can be divided into two categories: natural and artificial. Natural concepts are formed through direct or indirect experiences. For example, consider the concept of snow. If you live in a place with regular snowfall, such as Essex Junction, Vermont, you know snow through direct experiences. You’ve seen it fall, touched it, shoveled it, and played in it. You recognize its texture, appearance, and even its smell. In contrast, if you live on an island like Saint...
619
Tidal Forces01:06

Tidal Forces

3.5K
The origin of Earth's ocean tides has been a subject of continuous investigation for over 2000 years. However, the work of Newton is considered to be the beginning of the proper understanding of the phenomenon. Ocean tides are the result of gravitational tidal forces. These same tidal forces are present in any astronomical body; they are responsible for the internal heat that creates the volcanic activity on Io, one of Jupiter's moons, and the breakup of stars that get too close to...
3.5K
SBAR II: Application of SBAR01:14

SBAR II: Application of SBAR

6.3K
SBAR is an effective communication tool used by healthcare professionals to communicate patient information accurately. SBAR stands for Situation, Background, Assessment, and Recommendation. For a better understanding, an example is given below.
SBAR Report from a Nurse to a Health Care Provider
S: "Hello, Dr. Smith. This is Jane, RN, from the Med Surg unit. I am calling to tell you about Ms. White in Room 210, who is experiencing increased pain and redness at her incision site. Her recent...
6.3K
Mass Analyzers: Common Types01:19

Mass Analyzers: Common Types

1.7K
The quadrupole mass analyzer consists of four cylindrical metal rods arranged in a diamond carrying a DC voltage and a radio-frequency AC voltage. The motion of ions through the quadrupole depends on the field strength, causing only ions of a certain m/z to resonate successfully and strike the detector at a given field strength. Though the transmission rate for these analyzers is high, the exact elemental composition of the sample is not determined because of low resolution; however, they are...
1.7K
Automatic Processing and Automatic Social Behavior01:28

Automatic Processing and Automatic Social Behavior

284
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
284
Mass Analyzers: Overview01:13

Mass Analyzers: Overview

1.9K
The mass analyzer is a crucial component of the mass spectrometer. In the ionization chamber, the vaporized sample is bombarded with a high-energy electron beam to generate a radical cation and further fragment into neutral molecules, radicals, and cations. A series of negatively charged accelerator plates accelerate the cations into the mass analyzer. The mass analyzer separates ions according to their mass-to-charge (m/z) ratios and then directs them to the detector. The common types of mass...
1.9K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Drug-Induced QT Prolongation: Associations Between Risk Classifications in a Swedish Clinical Decision Support System and Clinical Outcomes.

Clinical pharmacology and therapeutics·2025
Same author

Identifying Adverse Drug Events in Clinical Text Using Fine-Tuned Clinical Language Models: Machine Learning Study.

JMIR formative research·2025
Same author

Multicancer analyses of short tandem repeat variations reveal shared gene regulatory mechanisms.

Briefings in bioinformatics·2025
Same author

Potential Adverse Drug Events Identified with Decision Support Algorithms from Janusmed Risk Profile-A Retrospective Population-Based Study in a Swedish Region.

Pharmacy (Basel, Switzerland)·2024
Same author

A comparative study of the 2D- and 3D-based skeleton avatar technology for assessing physical activity and functioning among healthy older adults.

Health informatics journal·2023
Same author

High GC content causes orphan proteins to be intrinsically disordered.

PLoS computational biology·2017
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

Related Experiment Video

Updated: Feb 28, 2026

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

1.6K

Agentic RAG for Maritime AIoT: Natural Language Access to Structured Data.

Oxana Sachenkova1, Melker Andreasson1, Dongzhu Tan1

  • 1Computer Science and Media Technology Department, Linnaeus University, SE-391 31 Kalmar, Sweden.

Sensors (Basel, Switzerland)
|February 27, 2026
PubMed
Summary
This summary is machine-generated.

Lighthouse Bot enhances maritime AIoT by providing secure, natural-language access to sensor data using Agentic Retrieval-Augmented Generation (RAG). This system ensures data privacy and verifiable analysis for critical industrial applications.

Keywords:
GenAIIoTLLMsRAGmaritime industrysensor data

Related Experiment Videos

Last Updated: Feb 28, 2026

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

1.6K

Area of Science:

  • Maritime operations
  • Artificial Intelligence of Things (AIoT)
  • Data Science

Background:

  • Modern maritime operations increasingly depend on sensor data for efficiency and decision-making.
  • Large language models (LLMs) offer advanced capabilities but require secure, constrained data access in industrial settings.
  • Retrieval-Augmented Generation (RAG) is crucial for data minimization, privacy, and regulatory compliance in sensitive applications.

Purpose of the Study:

  • Introduce Lighthouse Bot, a novel Agentic RAG system for natural-language access to maritime sensor data.
  • Address the need for verifiable autonomous data analysis in the AIoT domain, focusing on maritime use cases.
  • Demonstrate secure, limited-context data interaction and numerical accuracy validation for industrial AIoT.

Main Methods:

  • Developed a detailed architecture integrating an LLM with specialized databases and coding agents.
  • Transformed natural language queries into executable tasks, including Python code generation for time-series analysis and SQL queries for relational databases.
  • Implemented secure, limited-context RAG to keep sensitive data outside LLM prompts and ensure auditable tool use.
  • Created a test suite of 24 questions across varying complexity and data interaction types to evaluate system performance.

Main Results:

  • Lighthouse Bot demonstrated robust, controlled data access with high factual fidelity.
  • The proprietary Claude 3.7 model achieved nearly 90% factual correctness.
  • The open-source Qwen 72B model achieved 66% overall correctness, with 99% accuracy on simple retrieval and aggregation queries.
  • The system successfully generated Python code for analysis and executed complex SQL queries.

Conclusions:

  • Secure, limited-context RAG is essential for AIoT in maritime environments.
  • Lighthouse Bot offers a viable solution for verifiable autonomous data analysis in the AIoT domain.
  • The system shows potential for cost-effective automation of exploratory data analyses in industrial settings.