Explore the vast range of titles available.

Automated Guided Vehicles (AGVs) are vital to smart factories, enabling autonomous and efficient material transport. However, precise navigation is challenging because LiDAR provides high-dimensional, dynamic spatial data, while Inertial Measurement Unit (IMU) signals are often intermittent, leading to inconsistencies and navigation drift. This work proposes the Screened Inertial Data Fusion Method (SIDFM), a novel framework that systematically screens LiDAR data using a minimal differential function and fuses it with IMU intervals through linear regression learning. The SIDFM approach ensures that only consistent LiDAR points are integrated with IMU data, reducing mismatches and improving motion estimation. SIDFM was validated using a benchmark AGV dataset and compared against baseline LiDAR-IMU fusion methods under varying acceleration conditions. Results show that SIDFM reduces navigation errors by 12.09% at low acceleration and 11.43% at high acceleration while also significantly decreasing positioning errors. These improvements enhance the stability, precision, and safety of AGVs in dynamic manufacturing environments. The findings establish SIDFM as an effective and practical solution for robust AGV navigation, with potential applications in smart factories, warehouses, and autonomous mobility systems that demand both efficiency and reliability.

Computer vision is becoming increasingly important for industrial unmanned aerial vehicles (UAVs) to do real-time object and obstacle recognition while they are engaged in autonomous navigation. Variable texture features of objects, on the other hand, frequently lead to feature disappearance, which in turn reduces the accuracy of detection. This work proposed a novel Texture-variant Obstacle Object Classification Model (TOOCM) for feature extraction and dynamic texture representation. By capturing small texture fluctuations in real-time situations, the primary goal is to enhance the accuracy of both obstacle detection and object classification. The TOOCM model incorporates an N-layer ResNet architecture designed to address the difficulties of disappearing features in an adaptable Manner through dynamic layer augmentation based on variations in texture and size. Reconstruction of each convolutional layer in the ResNet is performed on an as-needed basis, taking into consideration the amount of texture concentration in incoming picture regions. The emergence of identifiable texture regions will result in the identification of new objects, which will then trigger adaptive categorization and layer restructuring activities. TOOCM, in contrast to traditional fixed-layer deep models, offers layer-wise learning updates during the navigation of UAV, which guarantees constant performance in complicated settings. The results of the experiments show that TOOCM achieves a greater detection accuracy of 14.09%, enhanced precision of 14.53%, and a loss reduction of 14.17%, particularly in high-density obstacle settings. These results demonstrate that the suggested adaptive feature learning approach is effective.

The diagnosis of epilepsy often depends heavily on Magnetic Resonance Imaging (MRI). Unfortunately, the utilization of MRI is constrained, due to its expensive price and lengthy operating times. More significantly, certain people with claustrophobia or cardiac pacemakers are not candidates for MRI owing to the risk of harm. Computed tomography (CT) images, in comparison, are considerably faster, cheaper, and free from the same restrictions. As opposed to conventional medical imaging synthetic techniques, which rely on abundant unpaired data or a minimum number of paired data, the proposed method in this study utilizes unpaired training data to predict an MR picture from a CT scan. This method overcomes tight registration problem in paired training and reduces the challenge of context mismatch in unpaired training. It is possible to convert 2D brain MR pictures from CT scans using the Spatial & Channel Attention Mechanism-Generative Adversarial Network (SCAM-GAN) that includes cycle-consistent and adversarial losses. The superiority of the proposed strategy was established by quantitative comparisons versus separate training approaches which are paired and unpaired.

T cell receptor-engineered T cells (TCR-Ts) have emerged as potent cancer immunotherapies. While most research focused on classical cytotoxic CD8 + T cells, the application of CD4 + T cells in adoptive T cell therapy has gained much interest recently. However, the cytotoxic mechanisms of CD4 + TCR-Ts have not been fully revealed. In this study, we obtained an MHC class I-restricted MART-1 27-35 -specific TCR sequence based on the single-cell V(D)J sequencing technology, and constructed MART-1 27-35 -specific CD4 + TCR-Ts and CD8 + TCR-Ts. The antitumor effects of CD4 + TCR-Ts were comparable to those of CD8 + TCR-Ts in vitro and in vivo . To delineate the killing mechanisms of cytotoxic CD4 + TCR-Ts, we performed single-cell RNA sequencing and found that classical granule-dependent and independent cytolytic pathways were commonly used in CD4 + and CD8 + TCR-Ts, while high expression of LTA and various costimulatory receptors were unique features for cytotoxic CD4 + TCR-Ts. Further signaling pathway analysis revealed that transcription factors Runx3 and Blimp1/Tbx21 were crucial for the development and killing function of cytotoxic CD4 + T cells. Taken together, we report the antitumor effects and multifaceted killing mechanisms of CD4 + TCR-Ts, and also indicate that MHC class I-restricted CD4 + TCR-Ts could serve as potential adoptive T cell therapies.

A new type of adjustable nozzle with an annulus clearance between the surfaces of a revolved solid and the matched hole was analyzed, which contained matching parts, regulating parts, guiding elements, and sealing part. The general regulating function of the adjustable nozzle was derived and the regulating and matching characteristics were also analyzed. Through the analysis, it was concluded that the matching-profile curve of either the revolved body or matched hole should be chosen as a straight line in order to keep the linear regulating feature. Moreover, the multi-annulus-clearance nozzle was designed, and some experiments were carried out on preparing budesonide particles with the nozzle. According to the experimental results, it was proved that the annulus nozzles is practical in preparing micro-particles by supercritical fluid precipitation method.

To improve the accuracy of tool wear detection, this paper proposes a tool wear detection method based on genetic neural network. Firstly, the vibration signals during tool processing are collected, and these signals are preprocessed to eliminate background noise. Then, in addition to the time-frequency analysis, the Ensemble Empirical Mode Decomposition which is more suitable for the processing of non-stationary random signals is also applied to extract tool wear sensitive features from signals. To reduce the computational complexity of the neural network, some minor components in the sensitive features can be omitted by kernel principal component analysis, leaving the principal components as the input of the neural network. Finally, aiming at the shortcomings of the BP neural network, the genetic algorithm is optimized in terms of chromosome coding, setting of control parameters and genetic operation, so that it can obtain better weights and thresholds to improve the BP neural network. The experimental result proves that the accuracy of BP neural network is 86.7% and that of genetic neural network is 96%. The tool wear detection method based on genetic neural network is more suitable for practical use.

Gold immunochromatographic assay (GICA) is a widely used immunological detection technology with high sensitivity and high efficiency as well as simple operation. Traditional GICA is mainly based on instrument for qualitative detection. In response to the above questions, this paper aims to develop an automated detection framework for immunochromatographic strips that can adaptively improve the detection performance of the gold immunochromatographic strip (GICS) system. As a research hotspot of machine learning (ML), reinforcement learning (RL) has made many progresses in the field of image segmentation. In this paper, the RL method is applied to the GICS system for the first time. The RL agent provides an adaptive segmentation model for the newly obtained GICS images by learning the state features of the preprocessed images. It is worth noting that our method does not require a large training data set and simultaneously can effectively reduce the grayscale-based image feature space. The experimental results show that the proposed method has a good segmentation effect, and provides a reliable solution for the quantitative analysis of the GICS system.

Spatial cognition enables adaptive goal-directed behavior through structured internal models of space. Robust biological systems consolidate spatial knowledge into three interconnected forms: landmarks for salient cues, route knowledge for movement trajectories, and survey knowledge for map-like representations. While recent advances in multi-modal large language models (MLLMs) have enabled visual-language reasoning in embodied agents, these efforts lack structured spatial memory and instead operate reactively, limiting their generalization and adaptability in complex real-world environments. Here we present Brain-inspired Spatial Cognition for Navigation (BSC-Nav), a unified framework for constructing and leveraging structured spatial memory in embodied agents. BSC-Nav builds allocentric cognitive maps from egocentric trajectories and contextual cues, and dynamically retrieves spatial knowledge aligned with semantic goals. Integrated with powerful MLLMs, BSC-Nav achieves state-of-the-art efficacy and efficiency across diverse embodied navigation tasks (e.g., improving success weighted by path length from 17.6% to 44.9% in instance-level navigation and from 42.7% to 53.1% in zero-shot long-horizon instruction-following), while also supporting versatile embodied behaviors in the real physical world. These results highlight a scalable path toward general-purpose spatial intelligence.

This study was aimed at investigating the mutations in colorectal cancer (CRC) for recurrent neoantigen identification. A total of 1779 samples with whole exome sequencing (WES) data were obtained from 7 published CRC cohorts. Common HLA genotypes were used to predict the probability of neoantigens at high-frequency mutants in the dataset. Based on the WES data, we not only obtained the most comprehensive CRC mutation landscape so far but also found 1550 mutations which could be identified in at least 5 patients, including KRAS G12D (8%), KRAS G12V (5.8%), PIK3CA E545K (3.5%), PIK3CA H1047R (2.5%), and BMPR2 N583Tfs∗44 (2.8%). These mutations can also be recognized by multiple common HLA molecules in Chinese and TCGA cohort as potential “public” neoantigens. Many of these mutations also have high mutation rates in metastatic pan-cancers, suggesting their value as therapeutic targets in different cancer types. Overall, our analysis provides recurrent neoantigens as potential cancer immunotherapy targets.