Skip to main content
Enterprise AI Analysis: Smell with Genji: Rediscovering Human Perception through an Olfactory Game with AI

AI & Sensory Perception

Smell with Genji: Rediscovering Human Perception through an Olfactory Game with AI

Olfaction plays an important role in human perception, yet its subjective and ephemeral nature makes it difficult to articulate, compare, and share across individuals. This work presents 'Smell with Genji,' an AI-mediated olfactory interaction system that reinterprets the traditional Japanese incense game Genji-kō as a collaborative human-AI sensory experience. By integrating a game setup, a mobile application, and an AI co-smelling partner equipped with olfactory sensing and large language model (LLM)-based conversational capabilities, the system invites participants to compare scents and construct Genji-mon patterns, fostering reflection through a dialogue that highlights the alignment and discrepancies between human and machine perception. This illustrates how sensing-enabled AI can participate in olfactory experience alongside users, pointing toward new possibilities for AI-supported sensory interaction and reflection in human-computer interaction (HCI).

Transformative Impact on Sensory AI & HCI

This research opens new frontiers in human-AI collaboration for sensory experiences, enhancing our understanding and interaction with subtle perceptions like smell.

0 Increase in Olfactory Articulation
0 AI Scent Classification Accuracy
0 New HCI Interaction Paradigms

Deep Analysis & Enterprise Applications

Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.

Genji-kō System Workflow

The 'Smell with Genji' system guides users through a structured olfactory experience, combining traditional ritual with AI-mediated interaction.

Entering the Game
Iterative Comparison and Dialogue (5 Rounds)
Revelation and Debrief

AI Co-smelling Partner Architecture

The AI's ability to participate in olfactory interaction is enabled by an integrated system of sensing, classification, and conversational capabilities.

Component Functionality
Olfactory Sensing Hardware
  • Three gas sensors (BME680, SGP30, Multichannel V2) for environmental and gas composition data.
  • Captures time-series data (temp, humidity, pressure, TVOC, eCO2, NO2, ethanol, CO).
Scent Classification Model
  • Transformer encoder backbone coupled with MLP classifier for 5-class categorization.
  • Employs windowed prediction with accumulative voting for real-time inference (40% accuracy).
LLM-based Conversational Interface
  • Retrieval-Augmented Generation (RAG) using static knowledge (incense, AI principles, templates) and dynamic memory (sensor signals, classification, history).
  • Facilitates context-aware dialogue and reflective comparison.

Bridging the Olfactory-Verbal Gap with AI

AI-mediated dialogue helps users articulate subtle scent differences, overcoming a common challenge in olfactory perception.

Enhanced Communication of Olfactory Experiences

Future Potential in Human-AI Sensory Interaction

This work opens avenues for AI to support broader sensory discovery and well-being. Future studies will explore nuanced interaction design, improved sensor configurations for higher sensitivity, and alternative AI personas to shape sensory awareness and reflection, contributing to a deeper understanding of AI’s role in augmenting human sensory experience beyond traditional modalities.

Calculate Your Potential AI Integration ROI

Estimate the efficiency gains and cost savings for your enterprise by integrating AI-mediated sensory systems. Adjust the parameters below to see the potential impact.

Annual Cost Savings $0
Annual Hours Reclaimed 0

Phased Implementation Roadmap

A structured approach to integrating AI-mediated sensory systems, ensuring smooth deployment and maximum impact.

Phase 1: Discovery & Strategy

Conduct workshops to identify specific use cases, define sensory data requirements, and outline integration points for AI perception within your enterprise. This phase establishes the strategic foundation.

Phase 2: Pilot Development & Testing

Develop a prototype AI co-smelling system tailored to a specific department or process. Deploy sensors and the classification model, then run user trials to gather feedback and refine AI interpretations.

Phase 3: Scaled Deployment & Integration

Expand the system across relevant enterprise functions, integrate with existing platforms, and train employees on new AI-supported sensory workflows. Establish monitoring for continuous performance optimization.

Unlock New Sensory Insights for Your Enterprise

Ready to explore how AI can enhance sensory perception and analysis in your organization? Schedule a personalized consultation to discuss tailored solutions.

Ready to Get Started?

Book Your Free Consultation.

Let's Discuss Your AI Strategy!

Lets Discuss Your Needs


AI Consultation Booking