Nec corporation (20240104430). INFORMATION PROCESSING APPARATUS, FEATURE QUANTITY SELECTION METHOD, TRAINING DATA GENERATION METHOD, ESTIMATION MODEL GENERATION METHOD, STRESS LEVEL ESTIMATION METHOD, AND STORAGE MEDIUM simplified abstract
Contents
- 1 INFORMATION PROCESSING APPARATUS, FEATURE QUANTITY SELECTION METHOD, TRAINING DATA GENERATION METHOD, ESTIMATION MODEL GENERATION METHOD, STRESS LEVEL ESTIMATION METHOD, AND STORAGE MEDIUM
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 INFORMATION PROCESSING APPARATUS, FEATURE QUANTITY SELECTION METHOD, TRAINING DATA GENERATION METHOD, ESTIMATION MODEL GENERATION METHOD, STRESS LEVEL ESTIMATION METHOD, AND STORAGE MEDIUM - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
INFORMATION PROCESSING APPARATUS, FEATURE QUANTITY SELECTION METHOD, TRAINING DATA GENERATION METHOD, ESTIMATION MODEL GENERATION METHOD, STRESS LEVEL ESTIMATION METHOD, AND STORAGE MEDIUM
Organization Name
Inventor(s)
Yoshiki Nakashima of Tokyo (JP)
Masanori Tsujikawa of Tokyo (JP)
INFORMATION PROCESSING APPARATUS, FEATURE QUANTITY SELECTION METHOD, TRAINING DATA GENERATION METHOD, ESTIMATION MODEL GENERATION METHOD, STRESS LEVEL ESTIMATION METHOD, AND STORAGE MEDIUM - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240104430 titled 'INFORMATION PROCESSING APPARATUS, FEATURE QUANTITY SELECTION METHOD, TRAINING DATA GENERATION METHOD, ESTIMATION MODEL GENERATION METHOD, STRESS LEVEL ESTIMATION METHOD, AND STORAGE MEDIUM
Simplified Explanation
The patent application describes an information processing apparatus designed to improve feature quantity selection for machine learning of a stress level estimation model. The apparatus includes a first selection section that generates a feature set by selecting feature quantities from multiple modalities, and a second selection section that chooses a combination of feature quantities based on verification of estimation accuracy through machine learning.
- Explanation of the patent/innovation:
- First selection section generates a feature set by selecting feature quantities from different modalities.
- Second selection section selects a combination of feature quantities based on verification of estimation accuracy through machine learning.
Potential Applications
The technology can be applied in various fields such as healthcare, mental health, human resources, and wearable technology for stress monitoring.
Problems Solved
1. Improved accuracy in stress level estimation through optimized feature selection. 2. Enhanced efficiency in machine learning processes by selecting the most relevant feature quantities.
Benefits
1. More accurate stress level estimation models. 2. Increased efficiency in machine learning tasks. 3. Enhanced performance of stress monitoring systems.
Potential Commercial Applications
Optimized stress monitoring apps, mental health assessment tools, wearable devices for stress management, and HR software for employee well-being.
Possible Prior Art
Prior art may include similar feature selection methods for machine learning models in various domains, such as healthcare, finance, and marketing.
Unanswered Questions
How does the apparatus handle feature quantities from different modalities during the selection process?
The apparatus uses the first selection section to generate a feature set by selecting feature quantities from various modalities. It is essential to understand how these different modalities are considered and weighted during the selection process to ensure optimal feature quantity selection.
What specific machine learning algorithms are used in the verification of estimation accuracy?
The abstract mentions that the verification of estimation accuracy is carried out by applying combinations of feature quantities to the machine learning of the estimation model. It would be beneficial to know which machine learning algorithms are utilized in this process to understand the effectiveness and reliability of the verification method.
Original Abstract Submitted
in order to improve a feature quantity selection method for machine learning of a stress level estimation model, an information processing apparatus () includes: a first selection section () that generates a feature set by selecting a feature quantity corresponding to each of a plurality of modalities from among a plurality of feature quantities; and a second selection section () that selects, based on a result of verifying estimation accuracy, a combination of feature quantities for use in the machine learning, the verification being carried out by applying combinations of feature quantities included in the feature set to the machine learning of the estimation model.
