<![CDATA[Developments in light sensor technology have made it possible to achieve better measurement accuracy. The GY1750BH sensor, for example, is known for its ability to detect changes in light with high sensitivity. While this sensor has many advantages, the accuracy of the results depends highly on the calibration method. Without proper calibration, measurement data can suffer from biases detrimental to the applications that rely on it. Linear regression methods can extract the mathematical relationship between the sensor output and light intensity in light sensors. In light sensor calibration, linear regression helps determine the relationship between the sensor-generated signal (e.g., voltage or current) and the measured light intensity. Thus, we can mathematically map the sensor's response to changes in light intensity, which is used for measurement correction to get closer to the actual value. Implementing linear regression in the GY1750BH sensor is expected to contribute significantly to improving the measurement accuracy of this sensor. By modeling the sensor's response to the actual light intensity, the data generated is expected to be more consistent and accurate so that it can be used in applications that require high accuracy. The results of this study are light intensity measurement with the application of linear regression on the GY 1750 BH sensor, which is more stable, and the resulting comparison is close to the measurement results using measuring instruments. The error produced before using linear regression is 1.2%, and when using linear regression on the GY 1750 BH sensor, it becomes 0.54%.]]>
