This review explores the evolution of indoor perovskite solar cells driven by recent advances in material optimization and machine learning, fostering sustainable indoor energy solutions for interconnected smart technologies.

To realize the purpose of energy saving, materials with high weight are replaced by low-weight materials with eligible mechanical properties in all kinds of fields. Therefore, conducting research works on lightweight materials under specified work conditions is extremely important and profound. To understand the relationship of aluminum alloy AA5005 among flow stress, true strain, strain rate, and deformation temperature, hot isothermal tensile tests were conducted within the strain rate range 0.0003–0.03 s⁻¹ and temperature range 633–773 K. Based on the true stress-true strain curves obtained from the experiment, a traditional constitutive regression Arrhenius-type equation was utilized to regress flow behaviors. Meanwhile, the Arrhenius-type equation was optimized by a sixth-order polynomial function for compensating strain. Thereafter, a back propagation artificial neural network (BP-ANN) model based on supervised machine learning was also employed to regress and predict flow stress in diverse deform conditions. Ultimately, by introducing statistical analyses correlation coefficient (R²), average absolute relative error (AARE), and relative error ($\delta$) to the comparative study, it was found that the Arrhenius-type equation will lose accuracy in cases of high stress. Additionally, owning higher R², lower AARE, and more concentrative $\delta$ value distribution, the BP-ANN model is superior in regressing and predicting than the Arrhenius-type constitutive equation.

Tensile tests on AA5005 alloy were conducted on model MTS-810 tensile test machine during temperature 633-773 K and strain rate 0.0003-0.03 s^-1. The flow stress–true strain curves were obtained. In order to analyze the flow stress behavior of aluminum AA5005 alloy, the phenomenological Fields-Backofen equation based on the fitting regression analysis was developed. The flow stress values calculated by the obtained model keep coincidence with experimental values. Eventually, the statistical analysis methods (correlation coefficient (R), average absolute relative error (AARE)) were adopted to examine the credibility of the established model. Results show that the R-value is 0.99592 and the AARE is 3.3128 %, which indicates the high fitting accuracy of the Fields-Backofen equation. Consequently, the Fields-Backofen model can describe the constitutive relationship of AA5005 alloy credibly.

A reverse-offset printed temperature sensor based on interdigitated electrodes (IDTs) has been investigated in this study. Silver nanoparticles (AgNPs) were printed on a glass slide in an IDT pattern by reverse-offset printer. The sensing layer consisted of a sucrose film obtained by spin coating the sucrose solution on the IDTs. The temperature sensor demonstrated a negative temperature coefficient (NTC) with an exponential decrease in resistance as the temperature increased. This trend is the characteristic of a NTC thermistor. There is an overall change of ~2800 kΩ for the temperature change of 0 °C to 100 °C. The thermistor is based on a unique temperature sensor using a naturally occurring biocompatible material, i.e., sucrose. The active sensing material of the thermistor, i.e., sucrose used in the experiments was obtained from extract of Muscovado. Our temperature sensor has potential in the biomedical and food industries where environmentally friendly and biocompatible materials are more suitable for sensing accurately and reliably.