教学课程资源库 更多>>

关键词： Industries   Artificial intelligence   Data models   Software   Agile software development   Training   Standards   Computer science   Systematic literature review   Data engineering   computer science education   computer science   course design   design process   instruction   machine learning (ML)   software engineering (SE)  

摘要： Contribution: A novel undergraduate course design at the intersection of software engineering (SE) and machine learning (ML) based on industry-reported challenges. Background: ML professionals report that building ML systems is different enough that one needs new knowledge about how to infuse ML into software production. For instance, various experts need to be deeply involved with these SE projects, such as business analysts, data scientists, statisticians, and software engineers. Intended Outcomes: The creation of a table detailing and matching industry challenges with course learning objectives, course topics, instructional units, and other related activities. Application Design: Course content was derived from interviewing industry professionals with related experience as well as surveying undergraduate computer science and engineering students. The proposed course style is designed to emulate real-world ML-based SE. Findings: Experienced IT professionals testify that the synergy between ML and agile SE is maturing and now becoming the standard practice. Thus, industry-derived content for a pilot undergraduate course has been successfully crafted at the intersection of SE and ML.

关键词： Clustering algorithms   Heuristic algorithms   Encoding   Graph neural networks   Detection algorithms   Clustering methods   Image edge detection   Electronic learning   Computer science   Vectors   Community detection   deep graph clustering   e-learning   user clustering  

摘要： Deep graph clustering is a highly significant tool for community detection, enabling the identification of strongly connected groups of nodes within a graph. This technology is crucial in various fields such as education and E-learning. However, deep graph clustering can be more misled by the graph topology, disregarding node information. For example, an excessive number of intercommunity edges or insufficient intracommunity edges can lead to inaccurate community distinction by the model. In this article, we propose a novel model, deep Graph Clustering with Triple Fusion Autoencoder (GC-TriFA) for community detection, which utilizes a triple encoding fusion mechanism to balance the incorporation of node and topological information, thereby mitigating this issue. Specifically, GC-TriFA employs a shallow linear coding fusion and a deep coding fusion method within an autoencoder structure. This approach enables the model to simultaneously learn and capture the embedding of cross-modality information and later utilizes weight fusion to equalize the two modalities. Furthermore, GC-TriFA also reconstructs the graph structure, learns relaxed $k$-means, and undergoes self-supervised training to enhance the quality of the graph embedding. The experimental results of GC-TriFA, when evaluated as an end-to-end model on publicly available datasets, demonstrate its superiority compared to the baseline models.

关键词： Data collection   Mobile handsets   Trajectory   Electronic mail   Smart phones   Roads   Data analysis   Computer science   Base stations   Sensors   Mobile contact detection   cellular signaling trace   user correlation sensing  

摘要： Mobile contact exhibits user co-traveling events within the same transportation tool, which is crucial for resident profiling, face-to-face interaction detection, etc. In this paper, we investigate urban user mobile contact detection with cellular signaling traces, which is cost-efficient to enable large-scale detection. Specifically, we develop a data collection platform to collect substantial user signaling traces, covering different types of road scenarios within a city. With the collected traces, we perform systematic data analysis to reveal several technical challenges, which are sparsity of signaling trajectory, remote base station noise, and fuzzy matching difficulties. To address challenges, we propose a mobile contact detection method named MoCo. In MoCo framework, we first conduct data denoising to remove the noise from remote base stations. Then, we devise a spatio-temporal filter to eliminate unlikely mobile contact traces in both spatial and temporal domains, reducing the computational overhead. Finally, we design a detection network that integrates the submodules of data alignment, feature encoder, spatio-temporal representation learner, and user mobile contact detector. Extensive evaluation results demonstrate the superiority of MoCo in comparison with state-of-the-art baselines. Robust experiments show that MoCo can work efficiently in different transportation modes and urban densities.

关键词： Training   Noise measurement   Noise reduction   Noise   Optimization   Graph neural networks   Robustness   Computational modeling   Data models   Computer science   Graph condensation   graph structure learning  

摘要： The increasing prevalence of large-scale graphs presents a significant challenge for Graph neural networks (GNNs) training due to their computational demands, limiting the applicability of GNNs in various scenarios. In response to this challenge, graph condensation (GC) is proposed as a promising acceleration solution, focusing on generating an informative compact graph that enables efficient training of GNNs while retaining performance. Despite the potential to accelerate GNN training, existing GC methods overlook the quality of large training graphs during both the training and inference stages. They indiscriminately emulate the training graph distributions, making the condensed graphs susceptible to noises within the training graph and significantly impeding the application of GC in intricate real-world scenarios. To address this issue, we propose robust graph condensation (RobGC), a plug-and-play approach for GC to extend the robustness and applicability of condensed graphs in noisy graph structure environments. Specifically, RobGC leverages the condensed graph as a feedback signal to guide the denoising process on the original training graph. A label propagation-based alternating optimization strategy is in place for the condensation and denoising processes, contributing to the mutual purification of the condensed graph and training graph. Additionally, as a GC method designed for inductive graph inference, RobGC facilitates test-time graph denoising by leveraging the noise-free condensed graph to calibrate the structure of the test graph. Extensive experiments show that RobGC is compatible with various GC methods, significantly boosting their robustness.

关键词： NoSQL   Education   Teaching methods   Constructive alignment   Database   Systematic literature review   Software Engineering   Computer science  

摘要： NoSQL databases are essential for managing modern data-intensive applications. While SQL education is a crucial part of the software engineering and computer science curriculum, it is insufficient in addressing the rise of big data and cloud infrastructures. Despite extensive research on SQL education, there is limited exploration of NoSQL education, particularly in teaching methods and data models. This study addresses this gap by conducting a systematic literature review on NoSQL database education, aiming to assess current research, teaching practices, models, tools, scalability, and security mechanisms while offering a framework for integrating NoSQL into academic curricula. Out of 386 articles, 28 were selected for detailed analysis, focusing on NoSQL teaching methods, models, and curriculum development. Findings revealed that document-oriented and graph databases, especially MongoDB, Cassandra, and Neo4j, are the most taught. The project-based learning approach was the most common teaching method. Challenges identified include adapting to technological advancements, addressing diverse student needs, and the shift to online learning. This review contributes valuable insights into NoSQL education and offers recommendations for improving teaching practices in software engineering curricula.

关键词： Multitasking   Hyperspectral imaging   Optimization   Feature extraction   Computer science   Search problems   Image segmentation   Evolutionary multitasking (EMT)   feature selection (FS)   hyperspectral images (HSIs)   superpixel segmentation  

摘要： Feature selection (FS) is a very important technique for hyperspectral image (HSI) classification, as successfully selecting informative features can significantly increase the learning performance while reducing the computational cost. However, most of the existing FS methods tend to treat the HSI as a whole for FS, which does not fully consider the unique characteristics of HSIs and disregards the fact that different feature classes possess varying preferences for features. Thus, this article proposes a superpixel segmentation-based evolutionary multitasking (EMT) algorithm for FS of HSIs, called SS-EMT. First, the superpixel segmentation method is used to partition the original HSI into several superpixel blocks, which can preserve well the information of different classes of the original image. Second, in order to explore each superpixel block efficiently, an EMT algorithm using particle swarm optimization is designed, which treats each superpixel block as a subtask and then optimizes these subtasks collaboratively by transferring useful knowledge among related subtasks. In addition, a new individual evaluation mechanism is devised to obtain multiple high-quality feature subsets with different numbers of features simultaneously in a single run, thus reducing the computational cost. Finally, extensive experimental results on four common HSI datasets under three classifiers validate that our proposed method outperforms several state-of-the-art FS methods.

关键词： Protocols   Proposals   Complexity theory   Voting   Reliability   Scalability   Synchronization   Electronic mail   Leadership   Computer science   Distributed consensus   Byzantine fault tolerance   leader election   score-based mechanism  

摘要： Leader-based BFT systems face potential disruption and performance degradation from malicious leaders, with current solutions often lacking scalability or greatly increasing complexity. In this paper, we introduce ABSE, an Adaptive Baseline Score-based Election approach to mitigate the negative impact of malicious leaders on leader-based BFT systems. ABSE is fully localized and proposes to accumulate scores for processes based on their contribution to consensus advancement, aiming to bypass less reliable participants when electing leaders. We present a formal treatment of ABSE, addressing the primary design and implementation challenges, defining its generic components and rules for adherence to ensure global consistency. We also apply ABSE to two different BFT protocols, demonstrating its scalability and negligible impact on protocol complexity. Finally, by building a system prototype and conducting experiments on it, we demonstrate that ABSE-enhanced protocols can effectively minimize the disruptions caused by malicious leaders, whilst incurring minimal additional resource overhead and maintaining base performance.

关键词： Survival analysis   Computer science education   Supplemental instruction   Diversity in STEM  

摘要： This study examines the success of undergraduate students in computer science supplementary courses offered by a non-profit organization in partnership with colleges and universities across the U.S. Using a novel dataset from the nonprofit organization, we present one of the first descriptive overviews of students enrolled in supplemental computer science programs. Moreover, we conduct a survival analysis finding that racial and gender disparities in traditional computer science programs exist in these supplemental courses. However, the study finds that when supplemental courses are taken for credit, students are much more likely to complete the course, offering an important insight into program design and student motivation.

关键词： Code biology   Mathematics   Computer science   Synthetic biology   Ecological codes   Psychology   Psychoanalysis   Cultural codes   Cyborgism   Transhumanism  

摘要： The concept of "code" connotes different meanings, intentions, and formalizations. From mathematics and computer sciences to psychology and culture, the term becomes less formal, more diverse, and sometimes appears ambiguous. In biology a growing number of codes ignite a debate about their role in evolution, biocomplexity, and agency, to name just a few. Here, a transdisciplinary group of code scientists attempts to capture the big picture of code research across their fields of interest. In this cross-sectional overview commonalities emerge that may pave the way towards a unified theory of life-based-on-codes. Codes underly cellular processes, perception, cognition, and communication. From ecosystems to human language, codes influence how individuals behave in groups, memorize, learn, and take part in cultural practices. Emotions like aggression, fear, anger, frustration, are important motivators of behaviour modulating mutual communication and sculpting individual experience. The inheritance of experience in form of innate release mechanisms, stereotyped behaviour, or archetypes may have phylogenetic and ontogenetic roots that rely on codes and impact our conscious decision making. Unconsciously, even our dreams draw on codes. In the future, conflation of different coding systems, e.g., from synthetic biology and generative artificial intelligence, will merge biological codes with machine logic and computer language to promote next-level transhumanism. Codes emerge as a currency converter between systems of life and between different scientific disciplines.

关键词： Computer science   Machine learning   Scientific community  

摘要： Researchers argue over whether ‘novel’ AI-generated works use others’ ideas without credit.