瑞萨博客

Software is becoming the new sensor. This shift in thinking opens the door to incorporating more complex, AI-based algorithms, rather than just simple condition thresholds.

Reality AI Tools^® includes functionality to monitor the status of data collection automatically, tracking consistency, quality, and coverage.

To get your machine learning model to the point where it’s ready for field testing, you’ll want to collect several thousand observations that cover a broad a range of the variation expected.

Relying only on high-level descriptive statistics rather than time and frequency domains will miss anomalies, fail to detect signatures and sacrifice value that an implementation could potentially deliver.

Real-time streaming data must be carved into smaller windows for consideration by a machine learning model, how that stream is carved up can have an impact on model performance and power consumption.

With the right features, almost any machine learning algorithm will find what you're looking for. Without good features, none will.

Reality AI Tools focuses on "inherent explainability" — keeping the fundamental functioning of each model conceptually accessible to the design engineer from the first steps of model construction.

Renesas uses a machine learning guided process to explore a huge variety of well-understood mathematical and engineering feature spaces.

As sensor and MCU costs decreased, an ever-increasing number of organizations have attempted to exploit this by adding sensor-driven embedded AI to their products.

The more sophisticated machine learning tools that are optimized for signal problems and embedded deployment can cut months, or even years, from an R&D cycle.