Yunnan Open University

Intelligent industrial robots rely significantly on accurate vision and autonomous decision-making to do high-performance tasks. Embedded systems, compact, real-time computer units, have become critical for delivering these capabilities, especially in resource-constrained industrial environments. Despite their advantages, embedded systems meet obstacles such as high computational cost, overfitting, and inadequate parameter tuning, which impede real-time performance and generalizability in dynamic industrial environments. The purpose of this research is to develop an embedded neural network framework that has been tuned using metaheuristic algorithms to increase the precision of robotic vision and the effectiveness of decision-making while considering available resources. Multimodal data (vision, force, and proximity) are acquired from industrial environments. Raw data is cleaned and normalized using min-max scaling. Principal Component Analysis (PCA) is used to extract statistical and geographical characteristics, reducing dimensionality. This research proposes an Intelligent Walrus Optimizer Fused Feed-forward Neural Network (IntWO-FFNet) to enhance the accuracy, efficiency, and adaptability of industrial robots by enabling intelligent perception and decision-making on embedded systems. An FFNet is used on the embedded system to identify environmental inputs and forecast task-specific behaviors. The FFNet is fine-tuned with IntWO to improve learning rates, weight initialization, and hidden layer configurations for less error and faster convergence. The proposed method was implemented using Python 3.10.1. The proposed IntWO-FFNet approach performs better than multimodal baseline architectures, achieving superior results, with accuracy ranging from 95% to 99%. Integrating neural networks with optimization approaches into embedded systems dramatically improves real-time robotic perception and decision-making, providing intelligent automation aligned with industrial robots. The dataset contains 10,214 multimodal samples across five task classes (pick, place, weld, idle, interaction) and five industrial object types. All experiments were executed on a simulated embedded environment (Raspberry-Pi–equivalent ARM setup) using Python 3.10.1, with evaluation performed using stratified train–validation–test splits. Performance was benchmarked against the BIIRCS baseline model, where the proposed IntWO-FFNet achieved 96.3% accuracy, 9.8% RMSE, and 97.5% task-coverage rate.

The DAZAP2 (Deleted in Azoospermia-associated Protein 2) gene encodes an azoospermia-related protein that plays key roles in spermatogenesis, cell cycle regulation, and transcriptional regulation. Here, we employed transcriptome sequencing to analyze porcine testis tissues using long-read and short-read sequencing and identified the DAZAP2 transcripts via RT-PCR. Protein interaction analysis, GO and KEGG enrichment, and competing endogenous RNA (ceRNA) regulatory network construction were performed to elucidate its functional pathways. Furthermore, we assessed the multi-tissue expression of DAZAP2 and the subcellular localization of the DAZAP2 protein. We identified two spliceosomes of the DAZAP2 gene in Banna mini-pig inbred line (BMI) testicular tissue, namely DAZAP2_X1 and DAZAP2_X2, with DAZAP2_X2 being the predominant transcript. Functional enrichment analysis revealed that DAZAP2_X2 was associated with ubiquitin-protein ligase binding, positive regulation of protein monoubiquitination and Wnt signaling pathway, indicating its involvement in spermatogenesis. Additionally, we identified nine microRNAs (miRNAs) interacting with DAZAP2_X2, including ssc-miR-490-3p, ssc-miR-150, ssc-miR-107, ssc-miR-193a-3p, ssc-miR-497, ssc-miR-192, ssc-miR-383, ssc-miR-129a-5p, and ssc-miR-181a, most of which were associated with spermatogenesis. We found DAZAP2_X2 was highly expressed in the testis and bulbourethral glands and was mainly localized in the cytoplasm. These findings suggest that DAZAP2_X2 played a significant role in spermatogenesis and provide a reference for further research on spermatogenesis-related genes and regulatory pathways.

Abstract. Ozone (O3), a major tropospheric air pollutant, poses significant threats to public health and ecosystems, especially across Africa, where O3 concentrations have experienced pronounced increases in recent decades. This study employs an interpretable machine learning (ML) model integrated with multi-source data to predict near-surface O3 levels over Africa from 2020 to 2050 driven by climate change under four Shared Socioeconomic Pathways (SSPs). We quantitatively investigate the respective roles of climate-driven changes in meteorological conditions and biogenic isoprene emissions in affecting future O3 variations. Results reveal that as a NOx-limited region, increased biogenic isoprene emissions contribute to a slight reduction in O3 levels (< 0.5 ppb). Conversely, favorable meteorological conditions elevate O3 levels over Africa, with a maximum projected increase of 2.0 ppb in 2050 relative to 2020, dominating the O3 variations driven by climate change. The low-emission SSP scenarios are projected to prompt less increases in O3 levels than the high-emission SSPs. Moreover, elevated air temperatures associated with global warming magnify the health burden across Africa, as O3 pollution acts as an additional stressor in a warming climate. This highlights the urgency for robust air pollution control and climate mitigation strategies to alleviate future health impacts in Africa.

ABSTRACT M-type dwarfs orbiting stars earlier than G-type have been reported to exhibit larger radii than those predicted by stellar models. To explain the inconsistencies between observations and models, more precise mass and radius measurements of M-type stars in such kind of binaries are needed to refine evolutionary models. By using photometric data from Transiting Exoplanet Survey Satellite and spectroscopic observations from Large sky Area Multi-Object fiber Spectroscopic Telescope (LAMOST), we conducted a study on the binary system TIC 431124333, finding TIC 431124333 is a total-eclipsing detached binary where an F0-type primary is accompanied by an M-type secondary (F+M) with a short period of 1.88 d. The photometric analysis with the Wilson–Devinney (W-D) code yields a mass ratio of 0.13$\,\pm\, 0.2$. Meanwhile, the mass ratio derived from single-lined radial velocities based on medium-resolution spectra from LAMOST is approximately 0.15, which demonstrates TIC 431124333, as a totally eclipsing binary, can deliver a reliable mass ratio with photometric data. The companion has a mass of 0.16 (2) ${\rm M}_{\odot }$ and radius of 0.21 (1)$R_{\odot }$. Given the exceptionally low mass ratio, the secondary component of TIC 431124333 is highly likely to be formed via disc fragmentation and currently in the pre-main-sequence stage. Collective samples of F+M binaries suggest their M-type companions may still be undergoing gravitational contraction towards the main sequence, in contrast to single M-type stars or low-mass binaries exhibiting radius inflation. Further testing of this hypothesis requires additional systems with precisely determined masses and radii.