Leveraging the power of multimodal large language models (LLMs) offers a promising approach to enhancing the accuracy and interpretability of morphing attack detection (MAD), especially in real-world biometric applications. This work introduces the use of LLMs for differential morphing attack detection (D-MAD). To the best of our knowledge, this is the first study to employ multimodal LLMs to D-MAD using real biometric data. To effectively utilize these models, we design Chain-of-Thought (CoT)-based prompts to reduce failure-to-answer rates and enhance the reasoning behind decisions. Our contributions include: (1) the first application of multimodal LLMs for D-MAD using real data subjects, (2) CoT-based prompt engineering to improve response reliability and explainability, (3) comprehensive qualitative and quantitative benchmarking of LLM performance using data from 54 individuals captured in passport enrollment scenarios, and (4) comparative analysis of two multimodal LLMs: ChatGPT-4o and Gemini providing insights into their morphing attack detection accuracy and decision transparency. Experimental results show that ChatGPT-4o outperforms Gemini in detection accuracy, especially against GAN-based morphs, though both models struggle under challenging conditions. While Gemini offers more consistent explanations, ChatGPT-4o is more resilient but prone to a higher failure-to-answer rate.

Presentation attack detection (PAD) remains a key challenge in contactless fingerprint recognition, especially with the rise of fingerphoto based authentication using smartphones. This work introduces a novel PAD approach using multimodal Large Language Models (LLMs) such as GPT-4o and Gemini 2.0 for interpretable and data-efficient spoof detection. We assess these models under zero-shot, few-shot, and chain-of-thought (CoT) prompting to evaluate their reasoning ability, generalization to unseen attacks, and multi-class classification of presentation attack instruments (PAIs). Experiments on a newly collected dataset (300 bona fide and 1200 spoof samples across four PAIs) show that GPT-4o, especially with CoT and few-shot prompting, outperforms Gemini 2.0 in both detection accuracy and interpretability. These results highlight the potential of LLMs as generalizable and explainable PAD solutions, minimizing the need for large annotated datasets and domain-specific models.

Prognostic assessment remains a critical challenge in medical research, often limited by the lack of well-labeled data. In this work, we introduce ContraSurv, a weakly-supervised learning framework based on contrastive learning, designed to enhance prognostic predictions in 3D medical images. ContraSurv utilizes both the self-supervised information inherent in unlabeled data and the weakly-supervised cues present in censored data, refining its capacity to extract prognostic representations. For this purpose, we establish a Vision Transformer architecture optimized for our medical image datasets and introduce novel methodologies for both self-supervised and supervised contrastive learning for prognostic assessment. Additionally, we propose a specialized supervised contrastive loss function and introduce SurvMix, a novel data augmentation technique for survival analysis. Evaluations were conducted across three cancer types and two imaging modalities on three real-world datasets. The results confirmed the enhanced performance of ContraSurv over competing methods, particularly in data with a high censoring rate.

Smartphone-based contactless fingerphoto authentication has become a reliable alternative to traditional contact-based fingerprint biometric systems owing to rapid advances in smartphone camera technology. Despite its convenience, fingerprint authentication through fingerphotos is more vulnerable to presentation attacks, which has motivated recent research efforts towards developing fingerphoto Presentation Attack Detection (PAD) techniques. However, prior PAD approaches utilized supervised learning methods that require labeled training data for both bona fide and attack samples. This can suffer from two key issues, namely (i) generalization—the detection of novel presentation attack instruments (PAIs) unseen in the training data, and (ii) scalability—the collection of a large dataset of attack samples using different PAIs. To address these challenges, we propose a novel unsupervised approach based on a state-of-the-art deep-learning-based diffusion model, the Denoising Diffusion Probabilistic Model (DDPM), which is trained solely on bona fide samples. The proposed approach detects Presentation Attacks (PA) by calculating the reconstruction similarity between the input and output pairs of the DDPM. We present extensive experiments across three PAI datasets to test the accuracy and generalization capability of our approach. The results show that the proposed DDPM-based PAD method achieves significantly better detection error rates on several PAI classes compared to other baseline unsupervised approaches.

An intelligent energy management strategy (EMS) based on an improved Reinforcement Learning (RL) algorithm is developed to enhance the adaptability of the EMS and to further improve the fuel efficiency of a Plug-in Parallel Hybrid Electric Vehicle (PHEV). Both the numerical model and the energy management strategy of a plug-in PHEV are described. The improved RL with Q-learning algorithm is implemented to acquire the optimal control strategies for improving fuel economy. The Markov Chain is employed to calculate the Transition Probability Matrix of the required power. A Kullback-Leibler (KL) divergence rate is designed to activate the update of EMS, when a new corresponding driving cycle is expected. An Exploration Factor (EF) is proposed to overcome the disadvantages of the normal RL algorithm in convergence rate and reward cost evaluation. The diverse KL divergence rates are examined to seek optimal solutions. The normal-RL strategy, rule-based strategy, and dynamic programming strategy are implemented as benchmark strategies to verify the effectiveness of the proposed strategy. The validation results indicate that the improved RL algorithm with EF makes it possible to promote the EMS capable of significantly improving the energy efficiency of a plug-in PHEV.

OBJECTIVE: Coronavirus disease 2019 (COVID-19) has caused considerable morbidity and mortality, especially in patients with underlying health conditions. A precise prognostic tool to identify poor outcomes among such cases is desperately needed. METHODS: Total 400 COVID-19 patients with underlying health conditions were retrospectively recruited from 4 centers, including 54 dead cases (labeled as poor outcomes) and 346 patients discharged or hospitalized for at least 7 days since initial CT scan. Patients were allocated to a training set (n = 271), a test set (n = 68), and an external test set (n = 61). We proposed an initial CT-derived hybrid model by combining a 3D-ResNet10 based deep learning model and a quantitative 3D radiomics model to predict the probability of COVID-19 patients reaching poor outcome. The model performance was assessed by area under the receiver operating characteristic curve (AUC), survival analysis, and subgroup analysis. RESULTS: The hybrid model achieved AUCs of 0.876 (95% confidence interval: 0.752-0.999) and 0.864 (0.766-0.962) in test and external test sets, outperforming other models. The survival analysis verified the hybrid model as a significant risk factor for mortality (hazard ratio, 2.049 [1.462-2.871], P < 0.001) that could well stratify patients into high-risk and low-risk of reaching poor outcomes (P < 0.001). CONCLUSION: The hybrid model that combined deep learning and radiomics could accurately identify poor outcomes in COVID-19 patients with underlying health conditions from initial CT scans. The great risk stratification ability could help alert risk of death and allow for timely surveillance plans.

Simultaneous feature selection and clustering is a major challenge in unsupervised learning. In particular, there has been significant research into saliency measures for features that result in good clustering. However, as datasets become larger and more complex, there is a need to adopt a finer-grained approach to saliency by measuring it in relation to a part of a model. Another issue is learning the feature saliency and advanced model parameters. We address the first by presenting a novel Gaussian mixture model, which explicitly models the dependency of individual mixture components on each feature giving a new component-based feature saliency measure. For the second, we use Markov Chain Monte Carlo sampling to estimate the model and hidden variables. Using a synthetic dataset, we demonstrate the superiority of our approach, in terms of clustering accuracy and model parameter estimation, over an approach using a model-based feature saliency with expectation maximisation. We performed an evaluation of our approach with six synthetic trajectory datasets obtaining an average clustering accuracy of 97 percent. To demonstrate the generality of our approach, we applied it to a network traffic flow dataset obtaining an accuracy of 93 percent for intrusion detection. Finally, we performed a comparison with state-of-the-art clustering techniques using three real-world trajectory datasets of vehicle traffic. Our approach achieved an average clustering accuracy of 96 percent compared to 77-95 percent for the other techniques. In conclusion, for the datasets considered, component based feature saliency measures gave improved clustering over those based on whole models.

Effective resource utilization is an important problem in the application of array, especially for the new time modulated array. Considering the problem of full utilization of array elements in time modulated array, a sparse optimization algorithm based on discrete variable convex optimization is proposed in this paper. The pattern optimization of equal excitation time modulation array is realized in two stages: In the first stage, the number of working array elements is as low as possible under the condition of suppressing the sidelobe of the central frequency. In the second stage, the sideband is suppressed by iterative convex optimization. The numerical simulation results are compared with other methods to verify the effectiveness of the proposed method in pattern optimization of equal excitation time modulation array. Finally, the optimization performance of the algorithm with different array parameters is verified.

In view of the importance of various components and asynchronous shapes of multivariate time series, a clustering method based on dynamic time warping and affinity propagation is proposed. From the two perspectives of the global and local properties information of multivariate time series, the relationship between the data objects is described. It uses dynamic time warping to measure the similarity between original time series data and obtain the similarity between the corresponding components. Moreover, it also uses the affinity propagation to cluster based on the similarity matrices and, respectively, establishes the correlation matrices for various components and the whole information of multivariate time series. In addition, we further put forward the synthetical correlation matrix to better reflect the relationship between multivariate time series data. Again the affinity propagation algorithm is applied to clustering the synthetical correlation matrix, which realizes the clustering analysis of the original multivariate time series data. Numerical experimental results demonstrate that the efficiency of the proposed method is superior to the traditional ones.

A fast exact nearest neighbor search algorithm over large scale data is proposed based on semi-convex hull tree, where each node represents a semi-convex hull, which is made of a set of hyper planes. When performing the task of nearest neighbor queries, unnecessary distance computations can be greatly reduced by quadratic programming. GPUs are also used to accelerate the query process. Experiments conducted on both Intel(R) HD Graphics 4400 and Nvidia Geforce GTX1050 TI, as well as theoretical analysis show that the proposed algorithm yields significant improvements and outperforms current k-d tree based nearest neighbor query algorithms and others.

This letter studies a new method based on Bayesian variational inference to estimate the sparse channel parameters in large-scale multiple-input-single-output orthogonal frequency division multiplexing (MISO-OFDM) systems. Also, the sparse common support of different channel impulse responses, which results in a block- structured model, is considered. The covariance matrix of the block is introduced in the block-structured model to effectively recover the channel parameters combining with the Bayesian hierarchical structure. Furthermore, variational message-passing (VMP) is applied to slove the problem. The simulation results show that the proposed algorithm outperforms the traditional ones.

A significant amount of work has been done in the area of price series forecasting using soft computing techniques, most of which are based upon supervised learning. Unfortunately, there has been evidence that such models suffer from fundamental drawbacks. Given that the short-term performance of the financial forecasting architecture can be immediately measured, it is possible to integrate reinforcement learning into such applications. In this paper, we present the novel hybrid view for a financial series and critic adaptation stock price forecasting architecture using direct reinforcement. A new utility function called policies-matching ratio is also proposed. The need for the common tweaking work of supervised learning is reduced and the empirical results using real financial data illustrate the effectiveness of such a learning framework.

This paper presents an enhanced least-squares approach for solving reinforcement learning control problems. Model-free least-squares policy iteration (LSPI) method has been successfully used for this learning domain. Although LSPI is a promising algorithm that uses linear approximator architecture to achieve policy optimization in the spirit of Q-learning, it faces challenging issues in terms of the selection of basis functions and training samples. Inspired by orthogonal least-squares regression (OLSR) method for selecting the centers of RBF neural network, we propose a new hybrid learning method. The suggested approach combines LSPI algorithm with OLSR strategy and uses simulation as a tool to guide the "feature processing" procedure. The results on the learning control of cart-pole system illustrate the effectiveness of the presented scheme.