Related Experiment Video
Updated: Aug 2, 2026
07:14
Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
Published on: December 23, 2025
Per-service supervised learning for identifying desired WoT apps from user requests in natural language.
1Department of Computer Engineering, Hongik University, Seoul, South Korea.
Plos One
|November 18, 2017
Summary
This study introduces a new system for natural language Web of Things (WoT) app creation. It uses parallel learning engines to improve accuracy and efficiency in identifying WoT functions.
Area of Science:
- Computer Science
- Artificial Intelligence
- Software Engineering
Background:
- Web of Things (WoT) platforms are rapidly expanding, increasing the demand for efficient WoT application composition.
- Current methods for identifying relevant WoT functions from natural language requests suffer from sub-par accuracy and long training times.
- Previous work utilized a supervised learning system based on conditional random fields (CRF) for this task.
Purpose of the Study:
- To develop a novel system for composing Web of Things (WoT) applications using natural language.
- To improve the accuracy and efficiency of identifying relevant WoT functions that fulfill user requests.
- To enable parallel and incremental learning for WoT application composition.
Main Methods:
- A novel solution is presented, creating a separate learning engine for each trigger service.
- An information retrieval technique is used to identify the most relevant trigger service for a user request.
- A two-phase inference method employs dedicated learning engines to predict trigger and action functions.
Main Results:
- The proposed approach enables parallel and incremental learning, addressing limitations of previous methods.
- Empirical evaluation using refined IFTTT app recipes demonstrates the effectiveness of the new solution.
- The two-phase inference method with parallel learning engines is expected to enhance accuracy in identifying WoT functions.
Conclusions:
- The novel system offers a more accurate and efficient way to compose Web of Things (WoT) applications from natural language.
- The parallel learning engine approach facilitates scalability and adaptability in WoT platform development.
- Future research directions are identified through meticulous analysis of IFTTT app recipe characteristics.
Related Concept Videos
01:15Real-World Application of Classical Conditioning
1.6K
Classical conditioning not only includes the initial pairing of stimuli but also extends to more complex forms, such as higher-order conditioning. Higher-order conditioning involves creating associations beyond the primary conditioned stimulus, resulting in a chain of conditioned responses.
Higher-order, or second-order, conditioning occurs when a neutral stimulus becomes associated with an already established conditioned stimulus through repeated pairings. For instance, if a dog has been...
Higher-order, or second-order, conditioning occurs when a neutral stimulus becomes associated with an already established conditioned stimulus through repeated pairings. For instance, if a dog has been...
1.6K
01:22Purposive Learning
535
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
535