To maintain an effective memory of old knowledge in a dynamically growing knowledge environment, continual knowledge graph embedding (CKGE) focuses on alleviating catastrophic forgetting. However, existing CKGE methods still suffer substantial performance degradation in dynamic knowledge graphs (DKG). We have found this challenge is mainly posed by spurious forgetting, a previously overlooked phenomenon that arises from the inherent interference effects in the continual learning (CL) process. In this paper, we deeply explore spurious forgetting in CKGE. First, we reveal two primary causes of spurious forgetting, knowledge interference and knowledge misalignment, and how to affect knowledge biasing within dynamic learning scenarios. Second, to fill this research gap, we propose a robust and efficient CKGE method (DebiasedKGE) for mitigating spurious forgetting. Specifically, to alleviate knowledge interference, we propose a mutual information-guided disentangled learning mechanism, which identifies latent features of different knowledge types and learns independent semantic representations for each, thereby reducing interference in knowledge embedding. Furthermore, to mitigate the deviation of new knowledge from previously learned knowledge, we design a dual-view regularized knowledge alignment mechanism that jointly constrains both the magnitude and direction of embedding transitions. Finally, we evaluate DebiasedKGE on four public CKGE datasets and two additional datasets constructed to contain knowledge perturbations of different dimensions. The results show that DebiasedKGE effectively alleviates spurious forgetting and achieves significant performance improvements. Our codes and datasets are available at https://anonymous.4open.science/r/DebiasedKGE.

Histopathology Whole-Slide Images (WSIs) provide an important tool to assess cancer prognosis in computational pathology (CPATH). While existing survival analysis (SA) approaches have made exciting progress, they are generally limited to adopting highly-expressive network architectures and only coarse-grained patient-level labels to learn visual prognostic representations from gigapixel WSIs. Such learning paradigm suffers from critical performance bottlenecks, when facing present scarce training data and standard multi-instance learning (MIL) framework in CPATH. To overcome it, this paper, for the first time, proposes a new Vision-Language-based SA (**VLSA**) paradigm. Concretely, (1) VLSA is driven by pathology VL foundation models. It no longer relies on high-capability networks and shows the advantage of *data efficiency*. (2) In vision-end, VLSA encodes textual prognostic prior and then employs it as *auxiliary signals* to guide the aggregating of visual prognostic features at instance level, thereby compensating for the weak supervision in MIL. Moreover, given the characteristics of SA, we propose i) *ordinal survival prompt learning* to transform continuous survival labels into textual prompts; and ii) *ordinal incidence function* as prediction target to make SA compatible with VL-based prediction. Notably, VLSA's predictions can be interpreted intuitively by our Shapley values-based method. The extensive experiments on five datasets confirm the effectiveness of our scheme. Our VLSA could pave a new way for SA in CPATH by offering weakly-supervised MIL an effective means to learn valuable prognostic clues from gigapixel WSIs. Our source code is available at https://github.com/liupei101/VLSA.

X-ray inspection of pipeline welds brings benefits for the industrial quality and safety of production. However, noise and complex texture structure in X-ray images caused by issues such as poor contrast and blurry defects lead to extraordinary obstacles for lightweight and high-precision identification to satisfy almost 100% accuracy requirements, especially in constrained environments. This paper proposes a novel method, named YOLO-Xweld, to detect pipeline welding defects for constrained application scenarios. YOLO-Xweld is derived from YOLO v3-tiny by adding an SPP module to the backbone network to enhance multi-scale feature extraction, and weakening large-scale network detection branch based on characteristics of pipeline weld X-ray images. Depthwise separable convolution is introduced to achieve a lightweight model and reduce the dependence on the high-performance hardware. Experiments show that the number of the model's parameters and floating-point operations have dropped by over 70%, and the model size has been reduced to 1/15 of the original size, while the test accuracy is close to 100%. This is of great significance in reducing the dependence on high-performance hardware and enhancing the convenience and operability during inspections in the constrained pipeline weld detection environment.

Sepsis is a systemic inflammatory response caused by pathogens such as bacteria. Because its pathogenesis is not clear, the clinical manifestations of patients vary greatly, and the alarming incidence and mortality pose a great threat to patients and medical systems, especially in the ICU (Intensive Care Unit). The traditional judgment criteria have the problem of low specificity. Artificial intelligence models could greatly improve the accuracy of sepsis prediction and judgment. Based on the XGBoost machine learning framework taking demographic, vital signs, laboratory tests and medical intervention data as input, this paper proposes a novel model for dynamically predicting sepsis and assessing risk. To realize the model, two methods for feature construction are introduced. For the observed time-series data of vital signs and laboratory tests, the time-dependent method performs to construct the time-dependent characteristics after the statistical screening. For the clinical intervention data, the statistical counting method is applied to construct count-dependent characteristics. Moreover, a new objective function is proposed for the XGBoost framework, and the first-order and second-order gradients of the objective function are also given for model training. Compared with the state-of-the-art methods at present, the proposed model has the best performance, with AUROC improved by 5.4% on the MIMIC-III dataset and 2.1% on PhysioNet Challenge 2019 dataset. The data processing and training methods of this model can be conveniently applied in different electronic health record systems and has a wide application prospect.

A Copula-based joint statistical model is proposed for texture representation on the domain of quaternion wavelet transform (QWT). Both the magnitude and the three phases of QWT are used as the discriminative information for constructing a 2-level Copula model, which consists of inner and outer Copulas. The inner Copula is applied to the intra-scale dependence while the outer Copula to capture the magnitude-phase dependence. Texture retrieval experiments based on Bayesian framework are carried out to evaluate our model. Experimental results show that, based on the multilevel Copula model, the performance of texture representation is improved by taking into account both the magnitude-phase dependence and the intra-scale dependence.

To design an effective and robust fingerprint recognition method is still an open issue. Some texture-based methods such as directional energy method and wavelet method are available nowadays. However, directional energy method is insufficient to capture the detail information of fingerprint and it is also improper to directly use wavelet method to extract the feature since the complex and rich edge information of fingerprint. In this work we propose a texture-based method called DFB-Wavelet for fingerprint recognition via combining directional filter banks (DFB) and wavelet. The region of interest (ROI) composed of nonoverlapping square blocks, is decomposed into eight directions by employing DFB. Wavelet signatures are calculated as the features of a fingerprint image from each directional subband of DFB. The feature matching is performed on the global normalized Euclidean distance between the input fingerprint features and the templates features. Experimental results show that DFB-Wavelet method has the higher accuracy compared to the traditional texture-based methods.

Single biometric cryptosystems were developed to obtain win-win scenarios for security and privacy. They are seriously threatened by spoof attacks, in which a forged biometric copy or artificially recreated biometric data of a legitimate user may be used to spoof a system. Meanwhile, feature alignment and quantization greatly degrade the accuracy of single biometric cryptosystems. In this paper, by trying to bind multiple biometrics to cryptography, a cryptosystem named multibiometric cryptosystem (MBC), is demonstrated from the theoretical point of view. First, an MBC with two fusion levels: fusion at the biometric level, and fusion at the cryptographic level, is formally defined. Then four models, namely biometric fusion model,MN-split model, nonsplit model, and package model, adopted at those two levels for fusion are presented. Shannon entropy analysis shows that even if the biometric ciphertexts and some biometric traits are disclosed, the new constructions still can achieve consistently data security and biometric privacy. In addition, the achievable accuracy is analyzed in terms of false acceptance rate/false rejection rate at each model. Finally, a comparison on the relative advantages and disadvantages of the proposed models is discussed.