The early detection of digestive problems is essential for lowering the chance of acquiring any form of gastrointestinal cancer, including esophageal cancer. Endoscopy is the method that is used the majority of the time for the purpose of examining and taking photos of this sort of illness. The application of artificial intelligence is now proving to be very efficient in enhancing the identification of gastrointestinal polyps and other abnormal features located inside the gastrointestinal system. As a direct consequence of this development, the use of AI within this sector has seen substantial growth. In the framework of artificial intelligence, this research investigates how well various types of algorithms perform in terms of polyp and abnormal feature recognition accuracy, efficiency, and detection. And introduced a model in this work that is GastroNet. It is developed by doing hyperparameter fine-tuning on YOLOv5 in order to find specific polyps and abnormal characteristics, particularly esophagitis. In this method, a single neural network is used to do an analysis on the whole picture before it is disassembled into its component parts and the bounding boxes and probabilities for each one are calculated independently. The goal of the hyperparameter fine-tuning is to further enhance the overall optimization of the model. Two different methods of annotation were used on a collection of data that consisted of one thousand separate images that needed to be labelled. In addition to implementing the fine-tuned SSD model, this study used three distinct backbone networks: MobileNet v2, MobileNet v2 FPN Lite, and Resnet50 v1 FPN. Additionally, this study has used CSPdarknet53 to create the improved YOLOv4 model. The results of the studies demonstrate that the proposed model, GastroNet was effective in correctly recognizing polyps and aberrant characteristics, reaching a high mAP (mean Average Precision), F1 score, and precision with a value of 0.99 and recall with a value of 1.00. The findings of this research will be a great help to physicians in the proper identification and diagnosis of abnormal features and gastrointestinal polyps.

The increase in car ownership has improved the convenience of people’s travel, but it has also increased the potential risk of pedestrian-vehicle conflicts. In complex traffic scenarios, pedestrian crossing behavior may lead to frequent traffic accidents. It is crucial to accurately and timely anticipate pedestrian crossing intentions to avoid pedestrian-vehicle conflicts, improve driving safety and ensure pedestrian safety. We propose a novel dual-channel pedestrian crossing intention anticipation network (DPCIAN) to anticipate pedestrian crossing intentions. DPCIAN comprises the pedestrian action encoding module and the scene traffic object interaction relation module (STOIRM). Initially, the pedestrian action encoding module resorts to channel-refined Graph Convolutional networks (GCNs) to extract spatio-temporal action features from pedestrians’ skeletons, which improves the inflexible feature extraction of the adaptive GCN and the information redundancy of the multi-channel GCN. Afterward, the STOIRM introduces an interaction relation network to excavate scene object interaction features related to the target pedestrian’s crossing intention with better scene understanding. Finally, the adaptive average pooling layer is used to fuse the spatio-temporal and interaction features to achieve robust anticipation of pedestrian crossing intention. DPCIAN is evaluated on two public datasets, JAAD and PIE, with an accuracy of 89% and 91%, respectively. Both qualitative and quantitative evaluations indicate that DPCIAN can precisely anticipate pedestrians’ crossing intentions in complex traffic scenarios. Code is available at: https://github.com/wrysmile99/DPCIAN.

Depression is a common mental disorder that requires objective and valid assessment tools. However, purely data-driven methods cannot satisfy the clinical diagnostic criteria for automatic depression detection (ADD), and the instability and heterogeneity of multimodal data have not been fully resolved. Therefore, we propose a novel auxiliary tool for ADD based on multimodal purification fusion (MMPF). Initially, a prior constraint gating (PCG) strategy is used to inject doctors’ constraints into depression data to guide and constrain the learning process. Then, we introduce text and audio encoders to extract unpurified features from preprocessed depression data. Afterward, multimodal purification refinement is proposed to extract unintersected common and specific features from unpurified features, generating purified features. Meanwhile, we leverage a multiperspective contrastive learning (MCL) strategy to enhance unpurified and purified features. Finally, modality interaction (MI) based on the transformer is proposed to conduct multimodal fusion. A dynamic corrective learning (DCL) strategy is introduced to tackle modality imbalances and inconsistent sentiment. MMPF is evaluated on the Distress Analysis Interview Corpus Wizard of Oz and performs promisingly in unimodal and multimodal depression detection, indicating its significant role in ADD.

Depression is one of the most common mental illnesses, affecting people’s quality of life and posing a risk to their health. Low-cost and objective automatic depression detection (ADD) is becoming increasingly critical. However, existing ADD methods usually treat depression detection as a regression problem for predicting patient health questionnaire-8 (PHQ-8) scores, ignoring the scores’ ambiguity caused by multiple questionnaire issues. To effectively leverage the score labels, we propose an uncertainty-aware label contrastive and distribution learning (ULCDL) method to estimate PHQ-8 scores, thus detecting depression automatically. ULCDL first simulates the ambiguity within PHQ-8 scores by converting single-valued scores into discrete label distributions. Afterward, it learns to predict the PHQ-8 score distribution by minimizing the Kullback–Leibler (KL) divergence between the score distribution and the discrete label distribution. Finally, the predicted PHQ-8 score distribution outperforms the PHQ-8 score in ADD. Moreover, label-based contrastive learning (LBCL) is introduced to facilitate the model for learning common features related to depression in multimodal data. A multibranch fusion module is proposed to align and fuse multimodal data for better exploring the uncertainty of PHQ-8 labels. The proposed method is evaluated on the publicly available DAIC-WOZ dataset. Experiment results show that ULCDL outperforms regression-based depression detection methods and achieves state-of-the-art performance. The code will be released after acceptance.

In the blockchain system, mining pools are popular for miners to work collectively and obtain more revenue. Nowadays, there are consensus attacks that threaten the efficiency and security of mining pools. As a new type of consensus attack, the Fork After Withholding (FAW) attack can cause huge economic losses to mining pools. Currently, there are a few evaluation tools for FAW attacks, but it is still difficult to evaluate the FAW attack protection capability of target mining pools. To address the above problem, this paper proposes a novel evaluation framework for FAW attack protection of the target mining pools in blockchain systems. In this framework, we establish the revenue model for mining pools, including honest consensus revenue, block withholding revenue, successful fork revenue, and consensus cost. We also establish the revenue functions of target mining pools and other mining pools, respectively. In particular, we propose an efficient computing power allocation optimization algorithm (CPAOA) for FAW attacks against multiple target mining pools. We propose a model-solving algorithm based on improved Aquila optimization by improving the selection mechanism in different optimization stages, which can increase the convergence speed of the model solution and help find the optimal solution in computing power allocation. Furthermore, to greatly reduce the possibility of falling into local optimal solutions, we propose a solution update mechanism that combines the idea of scout bees in an artificial bee colony optimization algorithm and the constraint of allocating computing power. The experimental results show that the framework can effectively evaluate the revenue of various mining pools. CPAOA can quickly and accurately allocate the computing power of FAW attacks according to the computing power of the target mining pool. Thus, the proposed evaluation framework can effectively help evaluate the FAW attack protection capability of multiple target mining pools and ensure the security of the blockchain system.

Accurate long-term water demand forecasting is beneficial to the sustainable development and management of cities. However, the randomness and nonlinear nature of water demand bring great challenges to accurate long-term water demand forecasting. For accurate long-term water demand forecasting, the models currently in use demand the input of extensive datasets, leading to increased costs for data gathering and higher barriers to entry for predictive projects. This situation underscores the pressing need for an effective forecasting method that can operate with a smaller dataset, making long-term water demand predictions more feasible and economically sensible. This study proposes a framework to delineate and analyze long-term water demand patterns. A forecasting model based on generative adversarial networks and multivariate feature fusion (the water demand forecast-mixer, WDF-mixer) is designed to generate synthetic data, and a gradient constraint is introduced to overcome the problem of overfitting. A multi-feature fusion method based on temporal and channel features is then derived, where a multi-layer perceptron is used to capture temporal dependencies and non-negative matrix decomposition is applied to obtain channel dependencies. After that, an attention layer receives all those features associated with the water demand forecasting, guiding the model to focus on important features and representing correlations across them. Finally, a fully connected network is constructed to improve the modeling efficiency and output the forecasting results. This approach was applied to real-world datasets. Our experimental results on four water demand datasets show that the proposed WDF-mixer model can achieve high forecasting accuracy and robustness. In comparison to the suboptimal models, the method introduced in this study demonstrated a notable enhancement, with a 62.61% reduction in the MSE, a 46.85% decrease in the MAE, and a 69.15% improve in the $R^2$ score. This research could support decision makers in reducing uncertainty and increasing the quality of water resource planning and management.