Despite significant advancements in object detection technology, most existing detection networks fail to investigate global aspects while extracting features from the inputs and cannot automatically adjust based on the characteristics of the inputs. The present study addresses this problem by proposing a detection network consisting of three stages: preattention, attention, and prediction. In the preattention stage, the network framework is automatically selected based on the features of the images’ objects. In the attention stage, the transformer structure is introduced. Taking into account the global features of the target, this study combines a self-attention module in the transformer model and convolution operation to integrate image features from global to local and for detection, thus improving the ship target accuracy. This model uses mathematical methods to obtain results of predictive testing in the prediction stage. The above improvements are based on the You Only Look Once version 4 (YOLOv4) framework, named “Auto-T-YOLO”. The model achieves the highest accuracy of 96.3% on the SAR Ship Detection dataset (SSDD) compared to the other state-of-the-art (SOTA) model. It achieves 98.33% and 91.78% accuracy in the offshore and inshore scenes, respectively. The experimental results verify the practicality, validity, and robustness of the proposed model.

With the increasing popularity of automatic identification system AIS devices, mining latent vessel motion patterns from AIS data has become a hot topic in water transportation research. Trajectory similarity computation is a fundamental issue to many maritime applications such as trajectory clustering, prediction, and anomaly detection. However, current non-learning-based methods face performance and efficiency issues, while learning-based methods are limited by the lack of labeled sample and explicit spatial modeling, making it difficult to achieve optimal performance. To address the above issues, we propose CLAIS, a contrastive learning framework for graph-based vessel trajectory similarity computation. A combined parameterized trajectory augmentation scheme is proposed to generate similar trajectory sample pairs and a constructed spatial graph of the study region is pretrained to help model the input trajectory graph. A graph neural network encoder is used to extract spatial dependency from the trajectory graph to learn better trajectory representations. Finally, a contrastive loss function is used to train the model in an unsupervised manner. We also propose an improved experiment and three related metrics and conduct extensive experiments to evaluate the performance of the proposed framework. The results validate the efficacy of the proposed framework in trajectory similarity calculation.

Abamectin is used in several countries as a type of macrocyclic lactone insecticide to control nematodes and other pests in livestock and agriculture. This medicine, used for animals and crops, would be highly toxic to human if a person has intentional poisoning. We report a case of a 47-year old man who was admitted to the hospital after ingestion of a large dose of abamectin on purpose, and who rapidly recovered consciousness after administration of flumazenil. Although flumazenil is not the antidote of abamectin, we may hypothesize that it could reduce recovery time and shorten expenditures in hospital. This is the first report that focusses on a specific treatment which could possibly accelerate recovery of consciousness for patients with abamectin intoxication.

Prompt engineering provides an efficient way to adapt large language models (LLMs) to downstream tasks without retraining model parameters. However, designing effective prompts can be challenging, especially when model gradients are unavailable and human expertise is required. Existing automated methods based on gradient optimization or heuristic search exhibit inherent limitations under black box or limited-query conditions. We propose Domain-Aware Reinforcement Learning for Prompt Optimization (DA-RLPO), which treats prompt editing as a sequential decision process and leverages structured domain knowledge to constrain candidate edits. Our experimental results show that DA-RLPO achieves higher accuracy than baselines on text classification tasks and maintains robust performance with limited API calls, while also demonstrating effectiveness on text-to-image and reasoning tasks.

Mild cognitive impairment (MCI), a transitional stage between normal aging and Alzheimer’s disease (AD), comprises three potential trajectories: reversion, stability, or progression. Accurate prediction of these trajectories is crucial for disease modeling and early intervention. We propose a novel analytical framework that integrates a healthy control–AD difference template (HAD) with a large-scale Granger causality algorithm based on long short-term memory networks (LSTM-lsGC) to construct effective connectivity (EC) networks. By applying principal component analysis for dimensionality reduction, modeling dynamic sequences with LSTM, and estimating EC matrices through Granger causality, the framework captures both symmetrical and asymmetrical connectivity, providing a refined characterization of the network alterations underlying MCI progression and reversion. Leveraging graph-theoretical features, our method achieved an MCI subtype classification accuracy of 84.92% (AUC = 0.84) across three subgroups and 90.86% when distinguishing rMCI from pMCI. Moreover, key brain regions, including the precentral gyrus, hippocampus, and cerebellum, were identified as being associated with MCI progression. Overall, by developing a symmetry-aware effective connectivity framework that simultaneously investigates both MCI progression and reversion, this study bridges a critical gap and offers a promising tool for early detection and dynamic disease characterization.