Multimodal sentiment analysis has a wide range of applications due to its information complementarity in multimodal interactions. Previous works focus more on investigating efficient joint representations, but they rarely consider the insufficient unimodal features extraction and data redundancy of multimodal fusion. In this paper, a Video-based Cross-modal Auxiliary Network (VCAN) is proposed, which is comprised of an audio features map module and a cross-modal selection module. The first module is designed to substantially increase feature diversity in audio feature extraction, aiming to improve classification accuracy by providing more comprehensive acoustic representations. To empower the model to handle redundant visual features, the second module is addressed to efficiently filter the redundant visual frames during integrating audiovisual data. Moreover, a classifier group consisting of several image classification networks is introduced to predict sentiment polarities and emotion categories. Extensive experimental results on RAVDESS, CMU-MOSI, and CMU-MOSEI benchmarks indicate that VCAN is significantly superior to the state-of-the-art methods for improving the classification accuracy of multimodal sentiment analysis.

In this paper, we propose a novel wavelet convolution unit for the image-oriented neural network to integrate wavelet analysis with a vanilla convolution operator to extract deep abstract features more efficiently. On one hand, in order to acquire non-local receptive fields and avoid information loss, we define a new convolution operation by composing a traditional convolution function and approximate and detailed representations after single-scale wavelet decomposition of source images. On the other hand, multi-scale wavelet decomposition is introduced to obtain more comprehensive multi-scale feature information. Then, we fuse all these cross-scale features to improve the problem of inaccurate localization of singular points. Given the novel wavelet convolution unit, we further design a network based on it for fine-grained Alzheimer's disease classifications (i.e., Alzheimer's disease, Normal controls, early mild cognitive impairment, late mild cognitive impairment). Up to now, only a few methods have studied one or several fine-grained classifications, and even fewer methods can achieve both fine-grained and multi-class classifications. We adopt the novel network and diffuse tensor images to achieve fine-grained classifications, which achieved state-of-the-art accuracy for all eight kinds of fine-grained classifications, up to 97.30%, 95.78%, 95.00%, 94.00%, 97.89%, 95.71%, 95.07%, 93.79%. In order to build a reference standard for Alzheimer's disease classifications, we actually implemented all twelve coarse-grained and fine-grained classifications. The results show that the proposed method achieves solidly high accuracy for them. Its classification ability greatly exceeds any kind of existing Alzheimer's disease classification method.

With the development of society, deep learning has been widely used in object detection, face recognition, speech recognition, and other fields. Among them, object detection is a popular direction in computer vision and digital image processing, and face detection is a focus of this hot direction. Although face detection technology has gone through a long research stage, it is still considered as one of the more difficult subjects in human feature detection technology. In addition, the face detection technology itself has two sides, imperceptibility and complexity of the environment, and other defects cause the existing technology to be unable to accurately recognize faces of different proportions, obscured and different postures. Therefore, this paper adopts an advanced deep learning method based on machine vision to detect human faces automatically. In order to accurately detect a variety of human faces, a multiscale fast RCNN method based on upper and lower layers (UPL‐RCNN) is proposed. The network is composed of spatial affine transformation components and feature region components (ROI). This method plays a vital role in face detection. First of all, multiscale information can be grouped in detection, so as to deal with small areas of the face. Then, the method can use the inspiration of the human visual system to perform contextual reasoning and spatial transformation, including zooming, cutting, and rotating. Through comparative experiments, the analysis results show that this method can not only accurately detect human faces but also has better performance than fast RCNN. Compared with some advanced methods, this method has the advantages of high accuracy, less time consumption, and no correlation mark.

Clustering is a concept in data mining, which divides a data set into different classes or clusters according to a specific standard, making the similarity of data objects in the same cluster as large as possible. Clustering by fast search and find of density peaks (DPC) is a novel clustering algorithm based on density. It is simple and novel, only requiring fewer parameters to achieve better clustering effect, without the requirement for iterative solution. And it has expandability and can detect the clustering of any shape. However, DPC algorithm still has some defects, such as it employs the clear neighborhood relations to calculate local density, so it cannot identify the neighborhood membership of different values of points from the distance of points and It is impossible to accurately cluster the data of the multi-density peak. The fuzzy neighborhood density peak clustering algorithm is proposed for this shortcoming (F-DPC): novel local density is defined by the fuzzy neighborhood relationship. The fuzzy set theory can be used to make the fuzzy neighborhood function of local density more sensitive, so that the clustering for data set of various shapes and densities is more robust. Experiments show that the algorithm has high accuracy and robustness.

With the rapid development of big data, big data research in the security protection industry has been increasingly regarded as a hot spot. This article mainly aims at solving the problem of predicting the tendency of juvenile delinquency based on the experimental data of juvenile blindly following psychological crime. To solve this problem, this paper proposes a rough ant colony classification algorithm, referred to as RoughAC, which first uses the concept of upper and lower approximate sets in rough sets to determine the degree of membership. In addition, in the ant colony algorithm, we use the membership value to update the pheromone. Experiments show that the algorithm can not only solve the premature convergence problem caused by stagnation near the local optimal solution but also solve the continuous domain and combinatorial optimization problems and achieve better classification results. Moreover, the algorithm has a good effect on predicting classification and can provide guidance for predicting the tendency of juvenile delinquency.

Pulmonary embolism is a life-threatening condition where early diagnosis and precise localization are crucial for improving patient outcomes. While CT pulmonary angiography (CTPA) is the primary method for detecting pulmonary embolism, existing segmentation algorithms struggle to effectively distinguish thrombi from vascular structures in complex 3D CTPA images, often leading to both false positives and false negatives. To address these challenges, the Threshold Adjustment Segmentation Network (TSNet) is proposed to enhance segmentation performance in 3D CTPA images. TSNet incorporates two core modules: the Threshold Adjustment Module (TAD) and the Geometric-Topological Axial Feature Module (GT-AFM). TAD utilizes logarithmic scaling, adaptive adjustments, and nonlinear transformations to optimize the probability distributions of thrombi and vessels, reducing false positives while improving the sensitivity of thrombus detection. GT-AFM integrates geometric features and topological information to enhance the recognition of complex vascular and thrombotic structures, improving spatial feature processing. Experimental results show that TSNet achieves a sensitivity of 0.761 and a false positives per scan of 1.273 at ε = 0 mm. With an increased tolerance of ε = 5 mm, sensitivity improves to 0.878 and false positives per scan decreases to 0.515, significantly reducing false positives. These results indicate that TSNet demonstrates superior segmentation performance under various tolerance levels, showing robustness and a well-balanced trade-off between sensitivity and false positives, making it highly promising for clinical applications.