教学课程资源库 更多>>

关键词： 3D segmentation   computed tomography   computer science   graphical user interface  

摘要： The contact surface area (CSA) quantifies the interface between a tumor and an organ and is a key predictor of perioperative outcomes in kidney cancer. However, existing CSA computation methods rely on shape assumptions and manual annotation. We propose a novel approach using 3D reconstructions from computed tomography (CT) scans to provide an accurate CSA estimate. Our method includes a segmentation protocol and an algorithm that processes reconstructed meshes. We also provide an open-source implementation with a graphical user interface. Tested on synthetic data, the algorithm showed minimal error and was evaluated on data from 82 patients. We computed the CSA using both our approach and Hsieh's method, which relies on subjective CT scan measurements, in a double-blind study with two radiologists of different experience levels. We assessed the correlation between our approach and the expert radiologist's measurements, as well as the deviation of both our method and the less experienced radiologist from the expert's values. While the mean and variance of the differences between the less experienced radiologist and the expert were lower, our method exhibited a slight deviation from the expert's, demonstrating its reliability and consistency. These findings are further supported by the results obtained from synthetic data testing.

关键词： Computer science   Machine learning   Policy   Public health  

摘要： As the European Union’s Artificial Intelligence Act takes effect, AI systems that mimic how human teams collaborate can improve trust in high-risk situations, such as clinical medicine.

关键词： Machine learning   Computer science   Sustainability   Energy  

摘要： Researchers want firms to be more transparent about the electricity demands of artificial intelligence.

关键词： Bidirectional multiscale degradation indicator   Multimodal Interactive attention   Spatial-temporal network   Deep ensembles   Remaining useful life prediction  

摘要： Remaining useful life (RUL) prediction is essential for the health management of rotating machinery systems (RMSs). Because of the complex and variable service conditions of RMSs, degraded data over the entire service cycle frequently feature strong noise and data imbalance, which increase the difficulty and instability of RUL prediction. Therefore, an RUL prediction method based on a multimodal interactive attention spatial-temporal network (MIASTN) with a deep ensemble is proposed to improve the reliability and generalizability of intelligent models. First, the MIASTN is constructed as a deep base learner (DBL), and multiple DBLs are integrated to construct a deep ensemble prediction system. Second, a bidirectional multiscale degradation indicator space is constructed using signal processing decomposition theory to transform the original vibration data into a more interpretable form to improve model interpretability. Finally, a learning method ensemble strategy is employed to achieve the final decision using a DBL as a deep integrator. The proposed RUL prediction method is validated through two case studies. The experimental analysis results show that the proposed method offers significant advantages.

关键词： Neck pain   Disability   Telerehabilitation   Exercise   Telemedicine  

摘要： Objectives Despite the widespread use of TENS in the treatment of chronic nonspecific neck pain (CNNP), there are few studies on Telerehabilitation (TR), and no studies comparing their effectiveness compared to each other in this field. It was planned to investigate and compare the effectiveness of TENS and TR, which is an online rehabilitation tool. Methods Forty-eight (female 45, male 3) patients with CNNP, aged 36.31 + 12.54 years, were randomized into TENS, TR or control groups. Pain severity was determined by Visual Analog Scale (VAS), Bournemouth Neck Questionnaire (NBQ), Neck Disability Index (NDI), Copenhagen Neck Functional Disability Scale (CNFDS), and World Health Organization Quality of Life Module (WHOQOL-BREF). Results VAS, NBQ, NBI, CNFDS Time*Group interaction showed a significant positive change after treatment (p = 0.013, p = 0.007, p = 0.022, p = 0.005, respectively). The effect size of this difference over time was large (p eta 2 = 0.177, p eta 2 = 0.198, p eta 2 = 0.156, p eta 2 = 0.208, respectively). Post-treatment, the highest mean difference was found in VAS and NDI values in the TENS (MD:2.656, MD:7.000, p < 0.001), NBQ, CNFDS, WHOQOL-Bref in the TR (MD:13.187, MD:5.312, MD:-9.660, p < 0.001, respectively). Conclusion VAS and NBQ in the TENS and NDI, CNFS, WHOQOL-Bref in the TR group were more effective after treatment than before treatment in patients with CNNP.

关键词： Computer science   Ethics   Mathematics and computing   Scientific community  

摘要： A survey finds that most respondents are sceptical that the technology underpinning large-language models is sufficient for artificial general intelligence.

关键词： Tweets  

摘要： Context: X, formerly known as Twitter, is one of the largest social media platforms and has been widely used for communication during research conferences. While previous studies have examined how users engage with X during these events, limited research has focused on analyzing the content posted by computer science conferences. Objective: This study investigates how conferences from different areas of computer science perform on social media by analyzing their activity, follower engagement, and the content posted on X. Method: We collect posts from 22 computer science conferences and conduct statistical experiments to identify variations in content. Additionally, we perform a manual analysis of the top five posts for each engagement metric. Results: Our findings indicate statistically significant differences in category, sentiment, and post length across computer science conference posts. Among all engagement metrics, likes were the most common way users interacted with conference content. Conclusion: This study provides insights into the social media presence of computer science conferences, highlighting key differences in content, sentiment, and engagement patterns across different venues. Copyright © 2025, The Authors. All rights reserved.

关键词： Avatars   Authentication   Metaverse   Costs   Protocols   Manipulators   Cryptography   Internet of Things   Tail   Computer science   avatar   metaverse   traceability  

摘要： Metaverse allows users to immersively interact with millions of partners, breaking through the constraints of the physical world. To ensure the traceability of malicious avatars, provers in large-scale commercial activities need to periodically submit identity parameters to the verifier as interaction evidence, imposing a disastrous communication and storage burden on both parties. In this article, we propose a traceable and efficient continuous authentication scheme for large-scale avatars. First, we construct a continuous authentication framework, where the prover's device locally checks its manipulator to submit the starting and ending identities as interaction evidence. Second, we propose a transitive signature scheme with path verifiability to ensure the relevance and unforgeability of the starting and ending identities. Finally, we design a traceable authentication protocol based on the proposed signature scheme to reduce communication and storage costs while guaranteeing traceability. Security analysis shows that the protocol not only defends against the attacks of device hijacking and false accusations but also supports virtual-to-physical tracking. Extensive evaluations show that the communication cost and storage costs are reduced by 95.97% and 98.35%, respectively, which can be used for avatar authentication and tracking in large-scale commercial activities.

关键词： 不插电的计算机科学   计算思维   教育帮扶   西南乡村  

摘要： 人工智能时代学生的计算思维能力培养是全世界普遍关注的教育议题,乡村学生的计算思维能力培养更是关乎我国高质量教育体系建设。在西南乡村教育帮扶活动中,面对计算思维教育理念缺乏支持、计算思维教育师资薄弱等困境,文章阐述了面向计算思维的不插电计算机科学活动的框架和示例,为改善西南乡村计算思维教育落后面貌提供了有益的思路和实践经验。

关键词： Servers   Privacy   Mobile applications   Security   Public key   Encryption   Computer science   Nickel   Internet of Things   Costs   Attribute-based encryption   location sharing   mobile applications   privacy-preserving  

摘要： Location sharing, as an essential component of mobile applications, helps mobile users share location information and enhance their community connections. However, users may be reluctant to share their locations with personal privacy concerns, as anyone including location server who knows these locations can infer much sensitive information about users through analyzing these locations' information plus their background knowledge. Therefore, it poses a natural question for mobile location-sharing applications how to share users' locations without any breach of their privacy. To answer this question, in this article, we describe two practical attribute-based encryption schemes served privacy-preserving mobile location-sharing applications. Our proposals are quite suitable for such a mobile application-location sharing with common interests since in our designs users' interests are also taken into consideration as well as location information. In particular, our two schemes have a higher performance in the sense that in our first construction both ciphertexts and private keys are of constant size simultaneously, and our second construction is an extension of the first that provides a tradeoff between ciphertext size and public-key size. Therefore, the two schemes we designed in this work are quite practical in mobile applications which are often equipped with limited transmission or storage resources. Finally, we offer a formal security proof under a well-defined security model, followed by an experimental evaluation and a theoretical performance comparison.