In the paper, a novel color image encryption scheme is proposed by use of the three-dimensional chaotic maps and some data reconstruction techniques. In the diffusion process of the encryption algorithm, the three-dimensional chaotic Logistic map is introduced to changes the pixel value of the plain image. Meanwhile, in the confusion process, the three-dimensional chaotic Cat map is applied to deal with the position of the image pixels. Moreover, some data reconstruction techniques are employed for the better encryption result. Furthermore, the corresponding decryption algorithm is also given. The significant advantages of our method are the effectiveness and simplicity, and our proposed method breaks the correlation between image pixel layers, offers a large key space and against differential and statistical attacks effectively. Finally, the superiority of the proposed algorithm will be shown by the experimental results, security analysis, and the corresponding comparisons with literature.

Chronic diseases are increasingly major threats to older persons, seriously affecting their physical health and well-being. Hospitals have accumulated a wealth of health-related data, including patients’ test reports, treatment histories, and diagnostic records, to better understand patients’ health, safety, and disease progression. Extracting relevant information from this data enables physicians to provide personalized patient-treatment recommendations. While collaborative filtering techniques and classical algorithms such as naive Bayes, logistic regression, and decision trees have had notable success in health-recommendation systems, most current systems primarily inform users of their likely preferences without providing explanations. This paper proposes an approach of deep learning with a local interpretable model–agnostic explanations (LIME)-based interpretable recommendation system to solve this problem. Specifically, we apply the proposed approach to two chronic diseases common in older adults: heart disease and diabetes. After data preprocessing, we use six deep-learning algorithms to form interpretations. In the heart-disease data set, the actual model recommendation of multi-layer perceptron and gradient-boosting algorithm differs from the local model’s recommendation of LIME, which can be used as its approximate prediction. From the feature importance of these two algorithms, it can be seen that the CholCheck, GenHith, and HighBP features are the most important for predicting heart disease. In the diabetes data set, the actual model predictions of the multi-layer perceptron and logistic-regression algorithm were little different from the local model’s prediction of LIME, which can be used as its approximate recommendation. Moreover, from the feature importance of the two algorithms, it can be seen that the three features of glucose, BMI, and age were the most important for predicting heart disease. Next, LIME is used to determine the importance of each feature that affected the results of the calculated model. Subsequently, we present the contribution coefficients of these features to the final recommendation. By analyzing the impact of different patient characteristics on the recommendations, our proposed system elucidates the underlying reasons behind these recommendations and enhances patient trust. This approach has important implications for medical recommendation systems and encourages informed decision-making in healthcare.

This study presents three deidentified large medical text datasets, named DISCHARGE, ECHO and RADIOLOGY, which contain 50K, 16K and 378K pairs of report and summary that are derived from MIMIC-III, respectively. We implement convincing baselines of automated abstractive summarization on the created datasets with pre-trained encoder-decoder language models, including BERT2BERT, BERTShare, RoBERTaShare, Pegasus, ProphetNet, T5-large, BART and GSUM. Further, based on the BART model, we leverage the sampled summaries from the training set as prior knowledge guidance, for encoding additional contextual representations of the guidance with the encoder and enhancing the decoding representations in the decoder. The experimental results confirm the improvement of ROUGE scores and BERTScore made by the proposed method.

Undesired jamming launched by malicious jammers can attack authorized communications, which is viewed as one of the critical challenges in vehicular networks. In this paper, in order to handle the problem, anti-jamming communication driven by reinforcement learning is studied in intelligent reflecting surface (IRS)-aided vehicular networks. The system sum transmission rate is optimized by joint designing the transmit beamforming at the roadside unit (RSU) and the reflection coefficients at the IRS. An anti-jamming strategy based on combining annealing bias-priority experience replay method and twin delayed deep deterministic policy gradient (TD3) technique is developed to handle the formulated challenging non-convex problem. The proposed strategy is employed to train the replay buffer in TD3, which can eliminate the deviation under the distribution change and has the advantages of fast convergence and is not easy to fall into local optima. Numerical results confirm that our proposed strategy can enhance the sum rate of multiple vehicular users and ensure radar sensing capability of RSU compared with the existing methods.