教学课程资源库 更多>>

关键词： Chemistry   Computer science   Drugs  

摘要： Gastric cancer (GC) is a prevalent malignancy with a high mortality rate and limited treatment options. Aging significantly contributes to tumor progression, and GC was confirmed as an aging-related heterogeneous disease. This study established an aging-associated index (AAI) using a machine learning-derived gene panel to stratify GC patients. High AAI scores associated with poor prognosis and indicated potential benefits from adjuvant chemotherapy, while showing resistance to immunotherapy. Single-cell transcriptome analysis revealed that AAI was enriched in monocyte cells within the tumor microenvironment. Two distinct molecular subtypes of GC were identified through unsupervised clustering, leading to the development of a subtype-specific regulatory network highlighting SOX7 and ELK3 as potential therapeutic targets. Drug sensitivity analyses indicated that patients with high ELK3 expression may respond to FDA-approved drugs (axitinib, dacarbazine, crizotinib, and vincristine). Finally, a user-friendly Shiny application was created to facilitate access to the prognostic model and molecular subtype classifier for GC. © 2025 The Author(s)

关键词： Applied sciences   Computer science   Navigation System  

摘要： Traditional Zenith Tropospheric Delay (ZTD) models often face difficulties in maintaining prediction accuracy under complex meteorological conditions and data loss. To address this, we propose the transformer-xLSTM (TransXLT) model, which integrates spatial-temporal information from global navigation satellite system (GNSS) stations, ERA5 (global atmospheric reanalysis), and GPT3 (empirical ZTD estimation). Missing data are reconstructed using a sparse attention-based time series reconstruction (SASR) method. Experimental results show: (1) under a 120-h data loss, SASR reduces mean absolute error (MAE) by 24.5% compared to cubic Hermite interpolation; (2) SASR lowers training root mean square error (RMSE) by 15.1% versus direct data deletion; and (3) TransXLT achieves an average RMSE of 8.13 mm across six sites, reducing RMSE by up to 76.54% compared to benchmarks like CNN-LSTM and ERA5. Demonstrating robustness across varying latitudes, altitudes, and seasons, the model significantly advances ZTD estimation accuracy for GNSS applications.

关键词： Electromagnetics   Computer science   Electrical engineering  

摘要： The contemporary mobile communication has undergone a significant shift toward a novel phase characterized by the emergence of beyond 5G (B5G) and 6G technologies. These advancements underscore a focus on enhanced spectral efficiency, minimized latency, and expansive connectivity. This paper thoroughly examines 6G wireless communication networks, including their architectural framework, key technologies, application scenarios, use cases, and challenges. The architectural blueprint of 6G networks integrates space, terrestrial, aerial, and undersea communications to facilitate deep connectivity across various scenarios, which is to meet the increasing future communication requisites. Toward this end, the paper proposes 15 key technologies such as terahertz communication, visible light communication, dynamic spectrum sharing, ultra-massive multiple-input multiple-output (MIMO), and in-band full-duplex. Furthermore, typical scenarios and emerging use cases of 6G are detailed. Conclusively, this paper expounds upon potential challenges in developing and suggests the corresponding solutions, fostering a global dialogue on this transformative technological frontier.

关键词： Human action recognition   Machine operation analysis   Artificial intelligence   Deep learning   Wavelet transformation   Convolutional neural network (CNN)   Long short-term memory (LSTM)   Industrial machinery   Video-based sensing   Operation process analysis   Value stream mapping  

摘要： Automating work process analysis is crucial in manufacturing to improve efficiency and productivity. However, traditional deep learning methods often fail to capture subtle temporal changes in machine operations, such as varying speeds. We propose a cost-effective approach called pseudo-sensing, which simulates sensor data by measuring machine speeds directly from video using wavelet transformation, a mathematical tool for time-frequency analysis. This approach eliminates the need for physical sensors. We evaluated pseudo-sensing by integrating it into two task classification models. The first is a convolutional neural network-long short-term memory (CNN-LSTM) model, which extracts spatial features via a CNN and learns temporal patterns using an LSTM. The second is a three-dimensional residual network (3D ResNet, R3D), designed to process spatiotemporal data simultaneously. With pseudo-sensing, the CNN-LSTM's micro-F1 score-an accuracy metric averaging precision and recall across all classes-improved from 0.712 to 0.736 (+2.4 points), while R3D's score rose from 0.675 to 0.701 (+2.7 points). To assess general applicability, we tested pseudo-sensing on another dataset featuring diverse machine motions: unidirectional movements (e.g., conveyor belts), oscillatory movements (e.g., pendulum-like motions), rotational movements (e.g., rotary presses), and intermittent movements (e.g., blinking or toggling mechanisms). The method achieved an 83% success rate in identifying machine dynamics. By leveraging deep learning, this method integrates video-based machine operation sensing with task recognition, considering both human actions and machine states. Eliminating additional sensors while enhancing accuracy and efficiency, pseudo-sensing offers broad potential for advancing manufacturing process analysis.

关键词： Fraud   Credit cards   Logic gates   Data models   Predictive models   Graph neural networks   Feature extraction   Finance   Computer science   Training   Fraud detection   semi-supervised learning   graph neural network  

摘要： Credit card fraud is a severe issue that causes significant losses for both cardholders and issuing banks. Existing methods utilize machine learning-based classifiers to identify fraudulent transactions from labeled transaction records. However, labeled data are often scarce compared to the billions of real transactions due to the high cost of annotation, which means that previous methods do not fully utilize the rich features of unlabeled data. What's more, contemporary methods succumb to a fallacy of unawareness of the local risk structure and the inability to capture certain risk patterns. Therefore, we propose the Risk-aware Gated Temporal Attention Network (RGTAN) for fraud detection in this work. Specifically, we first build a temporal transaction graph based on the transaction records, which consists of temporal transactions (nodes) and their interactions (edges). Then we leverage a Gated Temporal Graph Attention (GTGA) Mechanism to propagate messages among the nodes and learn adaptive representations of transactions. We also model the fraud patterns through risk propagation, taking advantage of the relations among transactions. More importantly, we devise a neighbor risk-aware representation learning layer to enhance our method's perception of multi-hop risk structures. We conduct extensive experiments on a real-world credit card transaction dataset and two public fraud detection datasets. The results show that our proposed method, RGTAN, outperforms other state-of-the-art methods on three fraud detection datasets. The risk-aware semi-supervised experiments also demonstrate the excellent performance of our model with only a small fraction of manually labeled data. Moreover, RGTAN has been deployed in a world-leading credit card issuer for credit card fraud detection, and the case study results show the effectiveness of our method in uncovering real-world fraud patterns.

关键词： Lower bound   Heuristic algorithms   Data mining   Computer science   Euclidean distance   Electronic mail   Training   Time measurement   Standards   Costs   Time series analysis   data mining   dynamic time warping  

摘要： Motif discovery is a critical operation for analyzing series data in many applications. Recent works demonstrate the importance of finding motifs with Dynamic Time Warping. However, existing algorithms spend most of their time in computing lower bounds of Dynamic Time Warping to filter out the unpromising candidates. Specifically, the time complexity for computing these lower bounds is O(L) for each pair of subsequences, where L is the length of the motif (subsequences). This paper proposes two new lower bounds, called LBf and LBM, both of them only cost amortized O(1) time for each pair of subsequences. On real datasets, the proposed lower bounds are at least one magnitude faster than the state-of-the-art lower bounds used in motif discovery while still keeping satisfying effectiveness. Based on these faster lower bounds, this paper designs an efficient motif discovery algorithm that significantly reduces the cost of lower bounds. The experiments conducted on real datasets show the proposed algorithm is 5.6 times faster than the state-of-the-art algorithms on average.

关键词： Ensemble learning   Estimation   Accuracy   Heuristic algorithms   Bagging   Training data   Synthetic data   Hands   Computer science   Training   Class imbalance problems   oversampling   multiclass imbalance   ensemble learning   dynamic ensemble  

摘要： Dynamic ensemble has significantly greater potential space to improve the classification of imbalanced data compared to static ensemble. However, dynamic ensemble schemes are far less successful than static ensemble methods in the imbalanced learning field. Through an in-depth analysis on the behavior characteristics of dynamic ensemble, we find that there are some important problems that need to be addressed to release the full potential of dynamic ensemble, including but not limited to, correcting the component classifiers' bias towards the majority classes, increasing the proportions of the positive classifiers (i.e., the component classifiers making correct prediction) for difficult samples, and providing the accurate competence estimations on the hard-to-classify samples w.r.t the classifier pool. Inspired by these, we propose a Dynamic Ensemble Framework for imbalanced data classification (imDEF). imDEF first uses the data generation method OREM$\mathrm{_{G}}$G to generate multiple artificial synthetic datasets, which have diverse class distributions by rebalancing the original imbalanced data. Based on each of such synthetic datasets, imDEF then utilizes a Classification Error-aware Self-Paced Sampling Ensemble (SPSE$\mathrm{_{CE}}$ CE ) method to gradually focus more on difficult samples, to create a low-biased classifier pool and increase the proportions of the positive classifiers for the difficult samples. Finally, imDEF constructs a referee system to achieve the competence estimations by leveraging an Ensemble Margin-aware Self-Paced Sampling Ensemble (SPSE$\mathrm{_{EM}}$ EM ) method. SPSE$\mathrm{_{EM}}$ EM incrementally strengthens the learning of the hard-to-classify samples, so that the competent levels of component classifiers could be estimated accurately. Extensive experiments demonstrate the effectiveness of imDEF. The source codes have been made publicly available on GitHub.

关键词： Computer science   Latent profile analysis   Latent transition analysis   Motivation   Undergraduates  

摘要： Although achievement motivation theories like the Situated Expectancy-Value Theory highlight domain-general and course-specific motivation, few studies have examined students' motivational beliefs at both levels. This study explores domain-general and course-specific motivational profiles in undergraduate computer science (CS) courses, focusing on expectancy for success, values, and belonging. Using latent profile analysis, we identified four domain-level profiles and five course-level profiles, with the profiles representing different combinations of positive motivation and cost. We examined how these profiles evolved during the semester, finding via latent transition analysis that domain-general motivations appear to be more stable over time. Additionally, gender differences in profile membership showed women and other non-men often in higher cost profiles compared to men, and there was more variability in mean grades across course profiles than across CS domain profiles. These findings enhance our understanding of how combinations of motivational beliefs can influence student engagement and performance. Educational Relevance and Implications Statement: Our study explored the motivational profiles of undergraduate computer science (CS) students, revealing that these profiles vary by domain and course and change from the beginning to the end of the semester. We found that domain-general motivational beliefs, which encompass general attitudes toward the field of CS, remain more stable over time compared to course-specific motivational beliefs, which reflect specific attitudes toward individual CS courses. The stability of domain-general motivational beliefs suggest that foundational attitudes formed early could influence long-term engagement with CS, emphasizing the need for early interventions. We also found gender differences in motivational profiles;women and other non-men were more likely to be in high-cost profiles compared to men. The gender disparities in per

关键词： Bioinformatics   Computer science  

摘要： The security of medical information has become a significant challenge with the move from traditional filing systems to electronic records. This study proposes the use of blockchain technology to address these concerns. The system registers patients and medical staff with unique IDs and stores patient diagnoses as immutable records on the blockchain. A central interplanetary file system stores the collected data, which can be accessed by authorized users like nurses, pharmacists, and patients via special access details. Users must log in before accessing medical records through the Electronic Record Management system. This approach can be scaled to multiple hospitals. After testing, the system showed some latency issues with 100 nodes, but performance improved with more nodes (300-500), demonstrating better scalability as the system handles more data and hospitals. Overall, the proposed blockchain-based system offers a secure, scalable solution for managing and accessing medical records.

关键词： Natural sciences   Applied sciences   Computer science  

摘要： This paper constructs three bi-class multi-relational heterogeneous graphs based on real-world data, and proposes a semantic and relation aware neural network model (SRA-BMHN) designed for bi-class multi-relational heterogeneous graphs. SRA-BMHN consists of two core modules: first, the semantic-aware module, which integrates diverse relational semantic information using a non-linear mapping function and attention mechanism tailored to specific relationship semantics;second, the relation-aware module, which employs a hierarchical bipartite subgraph aggregation strategy. This module first divides the bi-class multi-relational heterogeneous graphs into multiple bipartite subgraphs based on different edge relationship types and captures the topological information within them. It then merges these subgraphs into a relation-weighted sub graph and captures the relational features of nodes on the weighted heterogeneous subgraph. Finally, SRABMHN fuses the features from the semantic-aware module and the relation-aware module to generate the final node embeddings. Experimental results on three datasets demonstrate the superiority of the proposed method.