Analyzing the future behaviors of currency pairs represents a priority for governments, financial institutions, and investors, who use this type of analysis to understand the economic situation of a country and determine when to sell and buy goods or services from a particular location. Several models are used to forecast this type of time series with reasonable accuracy. However, due to the random behavior of these time series, achieving good forecasting performance represents a significant challenge. In this paper, we compare forecasting models to evaluate their accuracy in the short term using data on the EUR/USD exchange rate. For this purpose, we used three methods: Autoregressive Integrated Moving Average (ARIMA), Recurrent Neural Network (RNN) of the Elman type, and Long Short-Term Memory (LSTM). The analyzed period spanned from 2 January 1998, to 31 December 2019, and was divided into training and validation datasets. We performed forecasting calculations to predict windows with six different forecasting horizons. We found that the window of one month with 22 observations better matched the validation dataset in the short term compared to the other windows. Theil’s U coefficients calculated for this window were 0.04743, 0.002625, and 0.001808 for the ARIMA, Elman, and LSTM networks, respectively. LSTM provided the best forecast in the short term, while Elman provided the best forecast in the long term.

We demonstrate an integrated optical pressure sensing platform for multiplexed optofluidics applications. The sensing platform consists in an array of elastomeric on-side nanostructured membranes -effectively 2D photonic crystal- which present colour shifts in response to mechanical stress that alter their nanostructure characteristical dimensions, pitch or orientation. The photonic membranes are prepared by a simple and cost-effective method based on the infiltration of a 2D colloidal photonic crystal (CPC) with PDMS and their integration with a microfluidic system. We explore the changes in the white light diffraction produced by the nanostructured membranes when varying the pneumatic pressure in the microfluidics channels as a way to achieve a power-free array of pressure sensors that change their reflective colour depending on the bending produced on each sensor. The structural characterization of these membranes was performed by SEM, while the optical properties and the pressure-colour relation were evaluated via UV-Vis reflection spectrometry. Maximum sensitivities of 0.17 kPa⁻¹ is obtained when measuring at Littrow configuration (θ_in = −θ_out), and close to the border of the membranes. The reflected colour change with pressure is as well monitorized by using a smartphone camera.

New multi-stimuli responsive materials are required in smart systems applications to overcome current limitations in remote actuation and to achieve versatile operation in inaccessible environments. The incorporation of detection mechanisms to quantify in real time the response to external stimuli is crucial for the development of automated systems. Here, we present the first wireless opto-magnetic actuator with mechanochromic response. The device, based on a nanostructured-iron (Fe) layer transferred onto suspended elastomer structures with a periodically corrugated backside, can be actuated both optically (in a broadband spectral range) and magnetically. The combined opto-magnetic stimulus can accurately modulate the mechanical response (strength and direction) of the device. The structural coloration generated at the corrugated back surface enables to easily map and quantify, in 2D, the mechanical deflections by analyzing in real time the hue changes of images taken using a conventional RGB smartphone camera, with a precision of 0.05°. We demonstrate the independent and synergetic optical and magnetic actuation and detection with a detection limit of 1.8 mW·cm^–2 and 0.34 mT, respectively. The simple operation, versatility, and cost-effectiveness of the wireless multiactuated device with highly sensitive mechanochromic mapping paves the way to a new generation of wirelessly controlled smart systems.

The combination of micro- or nanofluidics and strong light–matter coupling has gained much interest in the past decade, which has led to the development of advanced systems and devices with numerous potential applications in different fields, such as chemistry, biosensing, and material science. Strong light–matter coupling is achieved by placing a dipole (e.g., an atom or a molecule) into a confined electromagnetic field, with molecular transitions being in resonance with the field and the coupling strength exceeding the average dissipation rate. Despite intense research and encouraging results in this field, some challenges still need to be overcome, related to the fabrication of nano- and microscale optical cavities, stability, scaling up and production, sensitivity, signal-to-noise ratio, and real-time control and monitoring. The goal of this paper is to summarize recent developments in micro- and nanofluidic systems employing strong light–matter coupling. An overview of various methods and techniques used to achieve strong light–matter coupling in micro- or nanofluidic systems is presented, preceded by a brief outline of the fundamentals of strong light–matter coupling and optofluidics operating in the strong coupling regime. The potential applications of these integrated systems in sensing, optofluidics, and quantum technologies are explored. The challenges and prospects in this rapidly developing field are discussed.

The production of Explorer roses has historically been attractive due to the acceptance of the product around the world. This species of roses presents high sensitivity to physical contact and manipulation, creating a challenge to keep the final product quality after cultivation. In this work, we present a system that combines the capabilities of intelligent computer vision and unmanned aerial vehicles (UAVs) to identify the state of roses ready for cultivation. The system uses a deep learning-based approach to estimate Explorer rose crop yields by identifying open and closed rosebuds in the field using videos captured by UAVs. The methodology employs YOLO version 5, along with DeepSORT algorithms and a Kalman filter, to enhance counting precision. The evaluation of the system gave a mean average precision (mAP) of 94.1% on the test dataset, and the rosebud counting results obtained through this technique exhibited a strong correlation (R² = 0.998) with manual counting. This high accuracy allows one to minimize the manipulation and times used for the tracking and cultivation process.