Mathematical Biosciences and Engineering最新文献

Infrared and visible image fusion (IVIF) is devoted to extracting and integrating useful complementary information from muti-modal source images. Current fusion methods usually require a large number of paired images to train the models in supervised or unsupervised way. In this paper, we propose CTFusion, a convolutional neural network (CNN)-Transformer-based IVIF framework that uses self-supervised learning. The whole framework is based on an encoder-decoder network, where encoders are endowed with strong local and global dependency modeling ability via the CNN-Transformer-based feature extraction (CTFE) module design. Thanks to the development of self-supervised learning, the model training does not require ground truth fusion images with simple pretext task. We designed a mask reconstruction task according to the characteristics of IVIF, through which the network can learn the characteristics of both infrared and visible images and extract more generalized features. We evaluated our method and compared it to five competitive traditional and deep learning-based methods on three IVIF benchmark datasets. Extensive experimental results demonstrate that our CTFusion can achieve the best performance compared to the state-of-the-art methods in both subjective and objective evaluations.

In recent years, significant progress has been made in video-based person re-identification (Re-ID). The key challenge in video person Re-ID lies in effectively constructing discriminative and robust person feature representations. Methods based on local regions utilize spatial and temporal attention to extract representative local features. However, prior approaches often overlook the correlations between local regions. To leverage relationships among different local regions, we have proposed a novel video person Re-ID representation learning approach based on a graph transformer, which facilitates contextual interactions between relevant region features. Specifically, we construct a local relation graph to model intrinsic relationships between nodes representing local regions. This graph employs the architecture of a transformer for feature propagation, iteratively refining region features and considering information from adjacent nodes to obtain partial feature representations. To learn compact and discriminative representations, we have further proposed a global feature learning branch based on a vision transformer to capture the relationships between different frames in a sequence. Additionally, we designed a dual-branch interaction network based on multi-head fusion attention to integrate frame-level features extracted by both local and global branches. Finally, the concatenated global and local features, after interaction, are used for testing. We evaluated the proposed method on three datasets, namely iLIDS-VID, MARS, and DukeMTMC-VideoReID. Experimental results demonstrate competitive performance, validating the effectiveness of our proposed approach.

Tumor growth dynamics serve as a critical aspect of understanding cancer progression and treatment response to mitigate one of the most pressing challenges in healthcare. The in silico approach to understanding tumor behavior computationally provides an efficient, cost-effective alternative to wet-lab examinations and are adaptable to different environmental conditions, time scales, and unique patient parameters. As a result, this paper explored modeling of free tumor growth in cancer, surveying contemporary literature on continuum, discrete, and hybrid approaches. Factors like predictive power and high-resolution simulation competed against drawbacks like simulation load and parameter feasibility in these models. Understanding tumor behavior in different scenarios and contexts became the first step in advancing cancer research and revolutionizing clinical outcomes.

Facial emotion recognition (FER) is largely utilized to analyze human emotion in order to address the needs of many real-time applications such as computer-human interfaces, emotion detection, forensics, biometrics, and human-robot collaboration. Nonetheless, existing methods are mostly unable to offer correct predictions with a minimum error rate. In this paper, an innovative facial emotion recognition framework, termed extended walrus-based deep learning with Botox feature selection network (EWDL-BFSN), was designed to accurately detect facial emotions. The main goals of the EWDL-BFSN are to identify facial emotions automatically and effectively by choosing the optimal features and adjusting the hyperparameters of the classifier. The gradient wavelet anisotropic filter (GWAF) can be used for image pre-processing in the EWDL-BFSN model. Additionally, SqueezeNet is used to extract significant features. The improved Botox optimization algorithm (IBoA) is then used to choose the best features. Lastly, FER and classification are accomplished through the use of an enhanced optimization-based kernel residual 50 (EK-ResNet50) network. Meanwhile, a nature-inspired metaheuristic, walrus optimization algorithm (WOA) is utilized to pick the hyperparameters of EK-ResNet50 network model. The EWDL-BFSN model was trained and tested with publicly available CK+ and FER-2013 datasets. The Python platform was applied for implementation, and various performance metrics such as accuracy, sensitivity, specificity, and F1-score were analyzed with state-of-the-art methods. The proposed EWDL-BFSN model acquired an overall accuracy of 99.37 and 99.25% for both CK+ and FER-2013 datasets and proved its superiority in predicting facial emotions over state-of-the-art methods.

Feature representations with rich topic information can greatly improve the performance of story segmentation tasks. VAEGAN offers distinct advantages in feature learning by combining variational autoencoder (VAE) and generative adversarial network (GAN), which not only captures intricate data representations through VAE's probabilistic encoding and decoding mechanism but also enhances feature diversity and quality via GAN's adversarial training. To better learn topical domain representation, we used a topical classifier to supervise the training process of VAEGAN. Based on the learned feature, a segmentor splits the document into shorter ones with different topics. Hidden Markov model (HMM) is a popular approach for story segmentation, in which stories are viewed as instances of topics (hidden states). The number of states has to be set manually but it is often unknown in real scenarios. To solve this problem, we proposed an infinite HMM (IHMM) approach which utilized an HDP prior on transition matrices over countably infinite state spaces to automatically infer the state's number from the data. Given a running text, a Blocked Gibbis sampler labeled the states with topic classes. The position where the topic changes was a story boundary. Experimental results on the TDT2 corpus demonstrated that the proposed topical VAEGAN-IHMM approach was significantly better than the traditional HMM method in story segmentation tasks and achieved state-of-the-art performance.

As a result of recent research, a new stochastic methodology of assessing causality was developed. Its application to instrumental measurements of temperature (T) and atmospheric carbon dioxide concentration ([CO₂]) over the last seven decades provided evidence for a unidirectional, potentially causal link between T as the cause and [CO₂] as the effect. Here, I refine and extend this methodology and apply it to both paleoclimatic proxy data and instrumental data of T and [CO₂]. Several proxy series, extending over the Phanerozoic or parts of it, gradually improving in accuracy and temporal resolution up to the modern period of accurate records, are compiled, paired, and analyzed. The extensive analyses made converge to the single inference that change in temperature leads, and that in carbon dioxide concentration lags. This conclusion is valid for both proxy and instrumental data in all time scales and time spans. The time scales examined begin from annual and decadal for the modern period (instrumental data) and the last two millennia (proxy data), and reach one million years for the most sparse time series for the Phanerozoic. The type of causality appears to be unidirectional, T→[CO₂], as in earlier studies. The time lags found depend on the time span and time scale and are of the same order of magnitude as the latter. These results contradict the conventional wisdom, according to which the temperature rise is caused by [CO₂] increase.

We modeled the impact of local vaccine mandates on the spread of vaccine-preventable infectious diseases, which in the absence of vaccines will mainly affect children. Examples of such diseases are measles, rubella, mumps, and pertussis. To model the spread of the pathogen, we used a stochastic SIR (susceptible, infectious, recovered) model with two levels of mixing in a closed population, often referred to as the household model. In this model, individuals make local contacts within a specific small subgroup of the population (e.g., within a household or a school class), while they also make global contacts with random people in the population at a much lower rate than the rate of local contacts. We considered what would happen if schools were given freedom to impose vaccine mandates on all of their pupils, except for the pupils that were exempt from vaccination because of medical reasons. We investigated first how such a mandate affected the probability of an outbreak of a disease. Furthermore, we focused on the probability that a pupil that was medically exempt from vaccination, would get infected during an outbreak. We showed that if the population vaccine coverage was close to the herd-immunity level, then both probabilities may increase if local vaccine mandates were implemented. This was caused by unvaccinated pupils possibly being moved to schools without mandates.