Color regeneration from reflective color sensor using an artificial intelligent technique

A deep learning-based real-time hypothermia and hyperthermia monitoring system with a simple body sensor

A real-time hypothermia and hyperthermia monitoring system with a simple body sensor based on a Convolutional Neural Network (CNN) is presented. The sensor is produced with 3D-printed thermochromic material. Due to the color change feature of thermochromic materials with temperature, 3D-printed thermochromic Polylactic Acid (PLA) material was used to monitor temperature changes visually. In this paper, we have used the transfer learning technique and fine-tuned the AlexNet CNN. Thirty images for each temperature class between 28-44°C and 510 image data were used in the algorithm. We used 80% and 20% of the data for training and validation. We achieved 96.1% accuracy of validation with a fine-tuned AlexNet CNN. The material's characteristics suggest that it could be employed in delicate temperature sensing and monitoring applications, particularly for hypothermia and hyperthermia.

A low-cost real color picker based on Arduino

Color measurements have traditionally been linked to expensive and difficult to handle equipment. The set of mathematical transformations that are needed to transfer a color that we observe in any object that doesn't emit its own light (which is usually called a color-object) so that it can be displayed on a computer screen or printed on paper is not at all trivial. This usually requires a thorough knowledge of color spaces, colorimetric transformations and color management systems. The TCS3414CS color sensor (I2C Sensor Color Grove), a system for capturing, processing and color management that allows the colors of any non-self-luminous object using a low-cost hardware based on Arduino, is presented in this paper. Specific software has been developed in Matlab and a study of the linearity of chromatic channels and accuracy of color measurements for this device has been undertaken. All used scripts (Arduino and Matlab) are attached as supplementary material. The results show acceptable accuracy values that, although obviously do not reach the levels obtained with the other scientific instruments, for the price difference they present a good low cost option.

A neural network based intelligent predictive sensor for cloudiness, solar radiation and air temperature

Accurate measurements of global solar radiation and atmospheric temperature, as well as the availability of the predictions of their evolution over time, are important for different areas of applications, such as agriculture, renewable energy and energy management, or thermal comfort in buildings. For this reason, an intelligent, light-weight and portable sensor was developed, using artificial neural network models as the time-series predictor mechanisms. These have been identified with the aid of a procedure based on the multi-objective genetic algorithm. As cloudiness is the most significant factor affecting the solar radiation reaching a particular location on the Earth surface, it has great impact on the performance of predictive solar radiation models for that location. This work also represents one step towards the improvement of such models by using ground-to-sky hemispherical colour digital images as a means to estimate cloudiness by the fraction of visible sky corresponding to clouds and to clear sky. The implementation of predictive models in the prototype has been validated and the system is able to function reliably, providing measurements and four-hour forecasts of cloudiness, solar radiation and air temperature.

Noniterative algorithm for improving the accuracy of a multicolor-light-emitting-diode-based colorimeter

We present a noniterative algorithm to reliably reconstruct the spectral reflectance from discrete reflectance values measured by using multicolor light emitting diodes (LEDs) as probing light sources. The proposed algorithm estimates the spectral reflectance by a linear combination of product functions of the detector's responsivity function and the LEDs' line-shape functions. After introducing suitable correction, the resulting spectral reflectance was found to be free from the spectral-broadening effect due to the finite bandwidth of LED. We analyzed the data for a real sample and found that spectral reflectance with enhanced resolution gives a more accurate prediction in the color measurement.