Wenbin Zhang’s research while affiliated with Kunming University and other places

Leading economic indicators are crucial statistics that are based on the economy and have a significant impact on various factors such as policies, stock market trends, etc. However, due to the long release time interval of these indicators, it is challenging to accurately predict their trends in advance. In this paper, we propose an effective framework for forecasting leading economic indicators in the United States by utilizing leading indicators to predict each other and learn their mutual correlation through an attention mechanism. To achieve this, we present a hierarchical, multi-task learning approach that uses textual data to make predictions for four essential leading economic indicators. We first group news articles by topic and then summarize and extract information using a time-series method and attention. Finally, we concatenate news information with historical data to forecast the leading economic indicators. Our experimental results demonstrate that our approach successfully forecasts leading economic indicators, and we are able to predict four indicators one month beforehand. This framework has significant potential for use in the finance industry and can be used to inform important decisions related to investment strategies, policymaking, and other financial aspects.

The content of the watercore in apples plays a decisive role in their taste and selling price, but there is a lack of methods to accurately assess it. Therefore, this paper proposes an OCRNet-based method for apple watercore content evaluation. A total of 720 watercores of apples from Mengzi, Lijiang, and Zhaotong City in Yunnan Province were used as experimental samples. An appropriate watercore extraction model was selected based on different evaluation indicators. The watercore feature images extracted using the optimal model were stacked, and the watercore content of apples in different regions was evaluated by calculating the fitted area of the stacked watercore region. The results show that the OCRNet model is optimal in all evaluation metrics when facing different datasets. The error of OCRNet is also minimized when extracting overexposed as well as underexposed images with 0.15% and 0.38%, respectively, and it can be used to extract the characteristics of the apple watercore. The evaluation result of the watercore content of apples in different regions is that Lijiang apples have the highest watercore content, followed by Mengzi apples, and Zhaotong apples have the least watercore content.

Structured pruning for large language models (LLMs) has garnered significant academic interest due to its ability to efficiently compress and accelerate LLMs by eliminating redundant weight groups at a coarse-grained granularity. Current structured pruning methods for LLMs typically depend on a singular granularity for assessing weight importance, resulting in notable performance degradation in downstream tasks. Intriguingly, our empirical investigations reveal that utilizing unstructured pruning, which achieves better performance retention by pruning weights at a finer granularity, \emph{i.e.}, individual weights, yields significantly varied sparse LLM structures when juxtaposed to structured pruning. This suggests that evaluating both holistic and individual assessments for weight importance are essential for LLM pruning. Building on this insight, we introduce the Hybrid-grained Weight Importance Assessment (HyWIA), a novel method that merges fine-grained and coarse-grained evaluations of weight importance for the pruning of LLMs. Leveraging an attention mechanism, HyWIA adaptively determines the optimal blend of granularity in weight importance assessments in an end-to-end pruning manner. Extensive experiments on LLaMA-V1/V2, Vicuna, Baichuan, and Bloom across various benchmarks demonstrate the effectiveness of HyWIA in pruning LLMs. For example, HyWIA surpasses the cutting-edge LLM-Pruner by an average margin of 2.82% in accuracy across seven downstream tasks when pruning LLaMA-7B by 50%.

Learning high-level representations for graphs is crucial for tasks like node classification, where graph pooling aggregates node features to provide a holistic view that enhances predictive performance. Despite numerous methods that have been proposed in this promising and rapidly developing research field, most efforts to generalize the pooling operation to graphs are primarily performance-driven, with fairness issues largely overlooked: i) the process of graph pooling could exacerbate disparities in distribution among various subgroups; ii) the resultant graph structure augmentation may inadvertently strengthen intra-group connectivity, leading to unintended inter-group isolation. To this end, this paper extends the initial effort on fair graph pooling to the development of fair graph neural networks, while also providing a unified framework to collectively address group and individual graph fairness. Our experimental evaluations on multiple datasets demonstrate that the proposed method not only outperforms state-of-the-art baselines in terms of fairness but also achieves comparable predictive performance.

Digital forensics plays a pivotal role in modern investigative processes, utilizing specialized methods to systematically collect, analyze, and interpret digital evidence for judicial proceedings. However, traditional digital forensic techniques are primarily based on manual labor-intensive processes, which become increasingly insufficient with the rapid growth and complexity of digital data. To this end, Large Language Models (LLMs) have emerged as powerful tools capable of automating and enhancing various digital forensic tasks, significantly transforming the field. Despite the strides made, general practitioners and forensic experts often lack a comprehensive understanding of the capabilities, principles, and limitations of LLM, which limits the full potential of LLM in forensic applications. To fill this gap, this paper aims to provide an accessible and systematic overview of how LLM has revolutionized the digital forensics approach. Specifically, it takes a look at the basic concepts of digital forensics, as well as the evolution of LLM, and emphasizes the superior capabilities of LLM. To connect theory and practice, relevant examples and real-world scenarios are discussed. We also critically analyze the current limitations of applying LLMs to digital forensics, including issues related to illusion, interpretability, bias, and ethical considerations. In addition, this paper outlines the prospects for future research, highlighting the need for effective use of LLMs for transparency, accountability, and robust standardization in the forensic process.

To address the issues of insufficient rigor in existing methods for quantifying apple watercore severity and the complexity and low accuracy of traditional classification models, this study proposes a method for watercore quantification and a classification model based on a deep convolutional neural network. Initially, visible/near-infrared transmission spectral data of apple samples were collected. The apples were then sliced into 4.5 mm thick sections using a specialized tool, and image data of each slice were captured. Using BiSeNet and RIFE algorithms, a three-dimensional model of the watercore regions was constructed from the apple slices to calculate the watercore severity, which was subsequently categorized into five distinct levels. Next, methods such as the Gramian Angular Summation Field (GASF), Gram Angular Difference Field (GADF), and Markov Transition Field (MTF) were applied to transform the one-dimensional spectral data into two-dimensional images. These images served as input for training and prediction using the ConvNeXt deep convolutional neural network. The results indicated that the GADF method yielded the best performance, achieving a test set accuracy of 98.73%. Furthermore, the study contrasted the classification and prediction of watercore apples using traditional methods with the existing quantification approaches for watercore levels. The comparative results demonstrated that the proposed GADF-ConvNeXt model is more straightforward and efficient, achieving superior performance in classifying watercore grades. Furthermore, the newly proposed quantification method for watercore levels proved to be more effective.

Background Accurately predicting hospital admissions from the emergency department (ED) is essential for improving patient care and resource allocation. This study aimed to predict hospital admissions by integrating both structured clinical data and unstructured text data using machine learning models. Methods Data were obtained from the 2021 National Hospital Ambulatory Medical Care Survey—Emergency Department (NHAMCS-ED), including adult patients aged 18 years and older. Structured data included demographics, visit characteristics, vital signs, and medical history, while unstructured data consisted of free-text chief complaints and injury descriptions. A Gradient Boosting Classifier (GBC) was applied to structured data, while a fine-tuned GPT-2 model processed the unstructured text. A combined model was created by averaging the outputs of both models. Model performance was evaluated using 5-fold cross-validation, assessing accuracy, precision, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). Results Among the 13,115 patients, 2264 (17.3%) were admitted to the hospital. The combined model outperformed the individual structured and unstructured models, achieving an accuracy of 75.8%, precision of 39.5%, sensitivity of 75.8%, and specificity of 75.8%. In comparison, the structured data model achieved 73.8% accuracy, while the unstructured model reached 64.6%. The combined model had the highest AUC, indicating superior performance. Conclusions Combining structured and unstructured data using machine learning significantly improves the prediction of hospital admissions from the ED. This integrated approach can enhance decision-making and optimize ED operations.

Given a question–image input, a visual commonsense reasoning (VCR) model predicts an answer with a corresponding rationale, which requires inference abilities based on real-world knowledge. The VCR task, which calls for exploiting multi-source information as well as learning different levels of understanding and extensive commonsense knowledge, is a cognition-level scene understanding challenge. The VCR task has aroused researchers’ interests due to its wide range of applications, including visual question answering, automated vehicle systems, and clinical decision support. Previous approaches to solving the VCR task have generally relied on pre-training or exploiting memory with long-term dependency relationship-encoded models. However, these approaches suffer from a lack of generalizability and a loss of information in long sequences. In this work, we propose a parallel attention-based cognitive VCR network, termed PAVCR, which fuses visual–textual information efficiently and encodes semantic information in parallel to enable the model to capture rich information for cognition-level inference. Extensive experiments show that the proposed model yields significant improvements over existing methods on the benchmark VCR dataset. Moreover, the proposed model provides an intuitive interpretation of visual commonsense reasoning.