Boolean functions and networks are commonly used in the modeling and analysis of complex biological systems, and this paradigm is highly relevant in other important areas in data science and decision making, such as in the medical field and in the finance industry. In a Boolean model, the truth state of a variable is either 0 or 1 at a given time. Despite its apparent simplicity, Boolean networks are surprisingly relevant in many areas of application such as in bioinformatics to model gene expressions and interactions. In the latter case, a gene is either ``on" or ``off" depending on its expression level. Despite the promising utility of Boolean modeling, in most practical applications the Boolean network is not known. Automated learning of a Boolean network and Boolean functions, from data, is a challenging task due in part to the large number of unknowns (including both the structure of the network and the functions) to be estimated, for which a brute force approach would be exponentially complex. In this paper we develop a new information theoretic methodology that we show to be significantly more efficient than previous approaches. Building on the recently developed optimal causation entropy principle (oCSE), that we proved can correctly infer networks distinguishing between direct versus indirect connections, we develop here an efficient algorithm that furthermore infers a Boolean network (including both its structure and function) based on data observed from the evolving states at nodes. We call this new inference method, Boolean optimal causation entropy (BoCSE), which we will show that our method is both computationally efficient and also resilient to noise. Furthermore, it allows for selection of a set of features that best explains the process, a statement that can be described as a networked Boolean function reduced order model. We highlight our method to the feature selection in several real-world examples: (1) diagnosis of urinary diseases, (2) Cardiac SPECT diagnosis, (3) informative positions in the game Tic-Tac-Toe, and (4) risk causality analysis of loans in default status. Our proposed method is effective and efficient in all examples.

In high-traffic harbor waters, marine radar frequently encounters signal interference stemming from various obstructive elements, thereby presenting formidable obstacles in the precise identification of ships. To achieve precise pixel-level ship identification in the complex environments, a customized neural network-based ship segmentation algorithm named MrisNet is proposed. MrisNet employs a lightweight and efficient FasterYOLO network to extract features from radar images at different levels, capturing fine-grained edge information and deep semantic features of ship pixels. To address the limitation of deep features in the backbone network lacking detailed shape and structured information, an adaptive attention mechanism is introduced after the FasterYOLO network to enhance crucial ship features. To fully utilize the multi-dimensional feature outputs, MrisNet incorporates a Transformer structure to reconstruct the PANet feature fusion network, allowing for the fusion of contextual information and capturing more essential ship information and semantic correlations. In the prediction stage, MrisNet optimizes the target position loss using the EIoU function, enabling the algorithm to adapt to ship position deviations and size variations, thereby improving segmentation accuracy and convergence speed. Experimental results demonstrate that MrisNet achieves high recall and precision rates of 94.8% and 95.2%, respectively, in ship instance segmentation, outperforming various YOLO and other single-stage algorithms. Moreover, MrisNet has a model parameter size of 13.8M and real-time computational cost of 23.5G, demonstrating notable advantages in terms of convolutional efficiency. In conclusion, MrisNet accurately segments ships with different spot features and under diverse environmental conditions in marine radar images. It exhibits outstanding performance, particularly in extreme scenarios and challenging interference conditions, showcasing robustness and applicability.

To solve the problem of deformation and stress in segments when a full-face hard rock tunnel boring machine (TBM) tunnel for an urban subway passes through existing buildings, a three-dimensional mechanical calculation model of TBM tunneling under existing buildings was established based on numerical analysis to comprehensively study the spatial attributes of tunnel segments during TBM tunneling. The Qingdao Metro Line 1 TBM tunnel in the hard rock stratum of Xiaobei District passes through existing buildings. The results indicated that (1) the stress and deformation of the segments were different at different positions. The horizontal and vertical stress and displacement of the segments in front of the building were significantly affected by the building. When the segment was not in the area below the horizontal plane of the building, the vertical stress of the segment was significantly greater than the two stresses in the horizontal direction. (2) The vertical displacements of the vault and the arch bottom were the largest, and the influence of vertical accessories was stronger when the segment was closer to the building.(3) When the tunnel was excavated to approximately one tunnel diameter in front of the building, the building was affected. If the surrounding rock is unstable, the excavation face may collapse and the ground surface may sink, possibly leading to inclination, cracking, and uneven settlement of the building.

The fault diagnosis of the gearbox is primarily based on the analysis of the harmonic response. However, the generation mechanism of the harmonic response of the gear pair is still not distinctly explained in a healthy gearbox. Therefore, this paper is dedicated to establishing a dynamic model of the gearbox for this issue. In this model, the contact force of the bearing and the meshing stiffness of the gear pair are determined by the Hertz theory and the potential energy method, then the shaft motion is used as the connection to establish the coupling relationship between the gear pair and the bearing. After this dynamic model is confirmed by experiments and existing models, the coupling relationship inside the gearbox and the harmonic response of the gear pair are studied using this model. The result demonstrates that a closed control loop is formed due to the vibration transmission between the gear pair, the bearing and the shaft, and there is a strong coupled vibration between the gear pair and the bearing in the gearbox. Due to the generation of the center distance error, misalignment angle and disorganized meshing process of the gear pair, the meshing stiffness is altered, which excites the harmonic response of the gear pair. When the speed of the gearbox is increased, although the vibration amplitude of the gearbox is increased, the system predominantly vibrates at the fundamental frequency, and the harmonic of the gear pair is also shifted to the low frequency band.