Quantitative information on how well a horse clears a jump has great potential to support the rider in improving the horse’s jumping performance. This study investigated the validation of a GPS-based inertial measurement unit, namely Alogo Move Pro, compared with a traditional optical motion capture system. Accuracy and precision of the three jumping characteristics of maximum height (Zmax), stride/jump length (lhorz), and mean horizontal speed (vhorz) were compared. Eleven horse–rider pairs repeated two identical jumps (an upright and an oxer fence) several times (n = 6 to 10) at different heights in a 20 × 60 m tent arena. The ground was a fiber sand surface. The 24 OMC (Oqus 7+, Qualisys) cameras were rigged on aluminum rails suspended 3 m above the ground. The Alogo sensor was placed in a pocket on the protective plate of the saddle girth. Reflective markers placed on and around the Alogo sensor were used to define a rigid body for kinematic analysis. The Alogo sensor data were collected and processed using the Alogo proprietary software; stride-matched OMC data were collected using Qualisys Track Manager and post-processed in Python. Residual analysis and Bland–Altman plots were performed in Python. The Alogo sensor provided measures with relative accuracy in the range of 10.5–20.7% for stride segments and 5.5–29.2% for jump segments. Regarding relative precision, we obtained values in the range of 6.3–14.5% for stride segments and 2.8–18.2% for jump segments. These accuracy differences were deemed good under field study conditions where GPS signal strength might have been suboptimal.

The Foreign Exchange market is a significant market for speculators, characterized by substantial transaction volumes and high volatility. Accurately predicting the directional movement of currency pairs is essential for formulating a sound financial investment strategy. This paper conducts a comparative analysis of various machine learning models for predicting the daily directional movement of the EUR/USD currency pair in the Foreign Exchange market. The analysis includes both decorrelated and non-decorrelated feature sets using Principal Component Analysis. Additionally, this study explores meta-estimators, which involve stacking multiple estimators as input for another estimator, aiming to achieve improved predictive performance. Ultimately, our approach yielded a prediction accuracy of 58.52% for one-day ahead forecasts, coupled with an annual return of 32.48% for the year 2022.

Accurate localization is crucial for numerous applications. While several methods exist for outdoor localization, typically relying on GPS signals, these approaches become unreliable in environments subject to a weak GPS signal or GPS outage. Many researchers have attempted to address this limitation, primarily focusing on real-time solutions. However, for applications that do not require real-time localization, these methods remain suboptimal. This paper presents a novel Transformer-based bidirectional encoder approach to address, in postprocessing, the localization challenges during GPS weak signal phases or GPS outages. Our method predicts the velocity during periods of weak or lost GPS signals and calculates the position through bidirectional velocity integration. Additionally, it incorporates position interpolation to ensure smooth transitions between active GPS and GPS outage phases. Applied to a dataset tracking horse positions—which features velocities up to 10 times those of pedestrians and higher acceleration—our approach achieved an average trajectory error below 3 m, while maintaining stable relative distance errors regardless of the GPS outage duration.

Many applications rely on IMU and GNSS data for localization, typically fused using algorithms such as the Kalman filter or its derivatives. While this approach provides accurate localization without additional infrastructure, it performs poorly in GNSS-denied environments. Although deep learning methods have been proposed to address this issue in real time, they do not exploit future data, resulting in suboptimal reconstructions for applications where real-time processing is not required. To address this limitation, we introduce POSNNET, a postprocessing framework designed to reconstruct position and velocity during prolonged periods of weak or absent GNSS signals. Designed for all non-real-time localization scenarios, POSNNET is applicable across various domains such as sports performance analysis, infrastructure-free road mapping, and wildlife tracking. The framework estimates velocity using state-of-the-art neural networks that leverage both past and future IMU and GNSS data. Position is subsequently recovered through weighted bidirectional integration. To enhance reconstruction accuracy and consistency, outputs from multiple neural networks are combined through averaging. POSNNET was validated on a 100-hour equestrian dataset, characterized by faster and more complex dynamics than typical pedestrian motion. It achieved an average trajectory error of 4.07 meters for GNSS outages lasting 30 seconds to 2 minutes, and 7.06 meters for outages lasting 2 to 5 minutes.

Accurate localization is crucial for numerous applications. While several methods exist for out-door localization, typically relying on GPS signals, these approaches become unreliable in indoor environments due to weak GPS signal or GPS outage. Many researchers have attempted to ad-dress this limitation, primarily focusing on real-time solutions. However, for applications that do not require real-time localization, these methods remain suboptimal. This paper presents a novel Transformer-based bidirectional encoder approach to address indoor localization challenges in postprocessing. Our method predicts velocity during periods of weak or lost GPS signal and calculates position through bidirectional velocity integration. Additionally, it incorporates posi-tion interpolation to ensure smooth transitions between active GPS and GPS outage phases. Applied to a dataset tracking horse positions—which features velocities up to 10 times those of pedestrians and higher acceleration—our approach achieved an average trajectory error below 3 meters, while maintaining stable relative distance errors regardless of GPS outages duration.