教学课程资源库 更多>>

关键词： Large language models   Co-authorship networks   Computer science   Gender   Ethnicity   Biases in network representation  

摘要： Large Language Models (LLMs) have significantly advanced prompt-based information retrieval, yet their potential to reproduce or amplify social biases remains insufficiently understood. In this study, we investigate this issue through the concrete task of reconstructing real-world co-authorship networks of computer science (CS) researchers using two widely used LLMs-GPT-3.5 Turbo and Mixtral 8x7B. This task offers a structured and quantifiable way to evaluate whether LLM-generated scholarly relationships reflect demographic disparities, as co-authorship is a key proxy for collaboration and recognition in academia. We compare the LLM-generated networks to baseline networks derived from DBLP and Google Scholar, employing both statistical and network science approaches to assess biases related to gender and ethnicity. Our findings show that both LLMs tend to produce more accurate co-authorship links for individuals with Asian or White names, particularly among researchers with lower visibility or limited academic impact. While we find no significant gender disparities in accuracy, the models systematically favor generating co-authorship links that overrepresent Asian and White individuals. Additionally, the structural properties of the LLM-generated networks differ from those of the baseline networks. These results highlight the importance of examining how LLMs represent social and scientific relationships, particularly in contexts where they are increasingly used for knowledge discovery and scholarly search.

关键词： Drugs   Chemistry   Computer science  

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.

关键词： Computer science   Physics  

摘要： The research disciplines of computer-generated holography (CGH) and machine learning have evolved in parallel for decades and experienced booming growth due to breakthroughs in mathematical optimization and computing hardware. Over the past few years, deep learning has been applied to CGH and achieved remarkable success, accustoming a great step toward high-quality and real-time holographic display. This review introduces the fundamental concepts of CGH and deep learning, examines the development of deep-learning-based computer-generated holography (DLCGH), and explores cutting-edge research frontiers including data-driven models, physics-driven models, and jointly optimized models. Finally, we summarize with an outlook on the challenges and prospects of DLCGH.

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： Convolutional neural networks   Microphones   Computer science   Vibrometers   Vibrations   Audio recording   Vibration measurement   Support vector machines   Substrates   Mel frequency cepstral coefficient   Apiology   sensor applications (AAPL)   convolutional neural network (CNN)   sensor data processing (DATP)   digital signal processing  

摘要： Audio recordings from inside honey beehives can provide significant information about the health and build-up status of the hives. Bees emit important bioacoustic indicators, such as auditory piping signals, which can play a significant role in determining the growth and health status of the hive. As part of the Appalachian Multipurpose Apiary Informatics System (AppMAIS) project, we have installed microphones inside 28 beehives in the Western region of North Carolina. Several of these hives have swarmed over the past two years, allowing us to collect a multitude of recordings containing piping. Using this data, we have trained a piping detector convolutional neural network (CNN), which can function with high accuracy across three unique hives. This article provides details regarding the acoustic properties of the relevant subclasses of piping signals and the design and implementation of a piping classifier.

关键词： Location awareness   Wireless fidelity   Fingerprint recognition   Accuracy   Hardware   MIMO   Indoor environment   Computer science   Line-of-sight propagation   Internet of Things   Indoor localization   mobile single site   pervasive localization   wireless sensing  

摘要： Leveraging the widespread deployment of existing WiFi sites, WiFi-based techniques offer substantial potential for achieving pervasive indoor localization among various indoor localization techniques. Conventional WiFi-based indoor localization techniques primarily focus on providing fine-grained accuracy. However, previous techniques are not pervasive due to the following constraints: 1) they can hardly be implemented in environments with limited resources of WiFi sites and 2) they are constrained by high-hardware requirements, such as the need for multiple antennas. In this article, we propose a novel technique called mobile single-site localization (MS-Loc), which leverages a mobile single site to perform indoor localization. Specifically, MS-Loc utilizes existing hardware at off-the-shelf mobile WiFi sites to achieve pervasive localization rather than relying on multiple sites or multiple antennas. Moreover, in MS-Loc, a tailor-designed path planning algorithm guides the movement of the mobile single site to locate targets quickly and accurately. We conducted extensive experiments using a real-world testbed. The experimental results demonstrate that MS-Loc presents a competitive localization accuracy compared to previous techniques but is pervasive.

关键词： Synthetic data   Medical services   Generative adversarial networks   Data privacy   Computer security   Training   Data models   Telecommunication traffic   Generators   Computer science   Generative adversarial network (GAN)   healthcare cybersecurity   Internet of Medical Things (IoMT)   multifeature conditional GAN (MF-CGAN)   network traffic analysis   sustainable development goals (SDG)   synthetic data generation  

摘要： Synthetic data generation via generative artificial intelligence (GenAI) is essential for enhancing cybersecurity and safeguarding privacy in the Internet of Medical Things (IoMT) and healthcare. We introduce multifeature conditional generative adversarial network (GAN) (MF-CGAN), a Conditional GAN with multifeature integration, that generates realistic synthetic data using the WUSTL EHMS 2020 dataset of network traffic and health metrics. MF-CGAN's architecture integrates conditional variables such as cyberattack types, traffic direction, and status flags, preserving their intricate interdependencies. The generator employs dense layers with batch normalization and Leaky ReLU activations to produce conditional synthetic data;the discriminator evaluates authenticity using the same conditional inputs. Experimental results show that MF-CGAN produces high-fidelity synthetic data, closely mirroring real data characteristics. In addition, we quantitatively demonstrate (MAE = 0.012, RMSE = 0.035, and classification accuracy up to 99%) that MF-CGAN-generated data effectively supports cybersecurity tasks, indicating its potential to significantly enhance data availability for IoMT.

关键词： Academic student writing   Generative AI   Large language models   Ethics  

摘要： The new version of ACM and IEEE-CS Computer Science Curricula envisages the preparation of a dozen white papers within more than a third of the Body of Knowledge courses. Lack of experience in conducting research, insufficient ability to articulate thoughts, non-observance of defined recommendations, as well as forgotten verification of what has been done are key challenges in the implementation of these recommendations. Large language models (LLMs) can significantly support the creation of anticipated white papers, encouraging initial directions and inspiration for research, as well as a focused presentation of key elements of the work. Unfortunately, they can also hinder the creation of expected academic texts, promoting the superficiality of research and the presentation of unverified information. In order to facilitate progress in acquiring the necessary writing skills without discriminating against those students who have already acquired them and prefer traditional writing, we have defined a series of strict rules and strategies for preparing the briefing reports with complete, partial, or no reliance on the LLM. They were embedded into the faculty learning management system, implemented, and evaluated twice with more than 150 students during the academic year 2023/24. This paper presents a new approach along with the lessons learned from the first attempt and the changes incorporated into the second. Based on these two carefully designed, conducted and analyzed studies, teachers and students gained a very positive opinion about the impact of LLM on the creation of quality student reports. The effectiveness of the new approach is a guarantee that optimization of the integration of AI-generated content can become a benchmark for the successful preparation of student reports that can be recommended to the wider academic community.

摘要： This paper explores the dynamics of international collaborations in Computer Science, focusing on the roles of the three Publishing Superpowers, those are China, the European Union, and the United States. Leveraging a comprehensive literature review, we investigate collaboration patterns, research impact, retraction rates, and the impact of the Development Index on research outcomes. Our analysis reveals that while China, the EU, and the US play central roles in driving global research endeavors, other regions might shorten the distance between them in terms of the number of publications. Notably, collaborations involving these key regions exhibit lower retraction rates, underscoring their adherence to rigorous scientific practices. Furthermore, our findings highlight the influence of a country’s Development Index on research impact, with Very High Developed countries contributing to higher citation rates and lower retraction rates. Overall, our study sheds light on the significance of international collaborations in shaping the global research landscape and underscores the importance of fostering inclusive and ethical research practices for advancing knowledge and innovation in Computer Science. © 2025, CC BY.