教学课程资源库 更多>>

关键词： Anomaly detection   Feature extraction   Task analysis   Image edge detection   Decoding   Computer science   Transforms   Anomaly detection   attributed graphs   domain adaptation   graph neural networks (GNNs)  

摘要： Anomaly detection on attributed graphs has received increasing research attention lately due to the broad applications in various high-impact domains, such as cybersecurity, finance, and healthcare. Heretofore, most of the existing efforts are predominately performed in an unsupervised manner due to the expensive cost of acquiring anomaly labels, especially for newly formed domains. How to leverage the invaluable auxiliary information from a labeled attributed graph to facilitate the anomaly detection in the unlabeled attributed graph is seldom investigated. In this study, we aim to tackle the problem of cross-domain graph anomaly detection with domain adaptation. However, this task remains nontrivial mainly due to: 1) the data heterogeneity including both the topological structure and nodal attributes in an attributed graph and 2) the complexity of capturing both invariant and specific anomalies on the target domain graph. To tackle these challenges, we propose a novel framework Commander for cross-domain anomaly detection on attributed graphs. Specifically, Commander first compresses the two attributed graphs from different domains to low-dimensional space via a graph attentive encoder. In addition, we utilize a domain discriminator and an anomaly classifier to detect anomalies that appear across networks from different domains. In order to further detect the anomalies that merely appear in the target network, we develop an attribute decoder to provide additional signals for assessing node abnormality. Extensive experiments on various real-world cross-domain graph datasets demonstrate the efficacy of our approach.

关键词： Cervical cancer   Health disparities   Black   African American women   Cancer prevention and control   Immigrant health  

摘要： Cervical cancer prevention disparities between Black and White women have been researched extensively, but less is known about disparities among Black subpopulations, despite increased risk, distinct cultures, and rapidly increasing numbers of Black immigrant women to the USA. A 74-item survey was used to conduct a cross-sectional descriptive study. Independent samplettests, logistic multiple regressions, and chi-square tests were used to carry out all comparative analyses. The survey was administered via Psychdata from January 2020 to February 2020. The final sample included 450 eligible participants (African American women [AAW] = 335;Black immigrant women [BIW] from either West, Central, East Africa, or the Caribbean = 115). Compared to AAW, BIW demonstrated much lower knowledge of cervical cancer, AAW were more likely to visit a gynecologist, and to have had a well-woman exam every 3 years or less. A greater percentage of BIW reported not getting Pap smear test because they had no symptoms or because they feared bad results while AAW reported not receiving a Pap smear because it was not convenient, they did not trust any doctor/gynecologist, and lacked access to a gynecologist. Doctor and family advising had a much larger effect on cervical screening among BIW compared to AAW. This study provides evidence of crucial differences in CC knowledge, attitudes, and screening behaviors among BIW and AAW. Funding agencies, program planners and evaluators, and health policymakers are encouraged to require disaggregation of Black women in healthcare research to tease out specific way's interventions can be most effective.

关键词： Students with disabilities   universal design for learning   CS instructional coaching  

摘要： Through a mixed-methods approach that utilized teacher surveys and a focus group with computer science (CS) instructional coaches, this study examined elementary teachers' confidence in meeting the needs of students with disabilities, the extent to which the teachers could use the Universal Design for Learning (UDL) framework in CS education, and the strategies that their CS instructional coaches used with them to help meet the needs of all learners, including those with disabilities. Findings from a Wilcoxon signed-rank test and a general linear regression of the teacher surveys revealed that teachers' confidence in teaching CS and in meeting the needs of students with disabilities increased over the 5 month coaching study, but their understanding of UDL remained low throughout the study. A qualitative thematic analysis of open-response survey questions revealed that the teachers could identify instructional strategies that support the inclusion of students with disabilities in CS instruction. These strategies aligned with high leverage practices (HLPs) and included modeling, the use of explicit instruction, and opportunities for repeated instruction. When asked to identify UDL approaches, however, they had more difficulty. The focus group with coaches revealed that the coaches' primary aim related broadly to equity and specifically to access to and the quality of CS instruction. However, although they introduced UDL-based strategies, they struggled to systematically incorporate UDL into coaching activities and did not explicitly label these strategies as part of the UDL framework on a consistent basis. This finding explains, to a large extent, the teachers' limited understanding of UDL in the context of CS education.

关键词： AP Computer Science A course/exam   AP Computer Science Principles course/exam   gender and race/ethnicity  

摘要： The Advanced Placement Computer Science Principles (APCSP) course was introduced in 2016 to address long-standing gender and racial/ethnic disparities in the United States among students taking Advanced Placement Computer Science (APCS) in high school, as well as among those who pursued computing majors in college. Although APCSP has drawn a more diverse population of course takers than the traditional Advanced Placement Computer Science A (APCSA) course, questions remain about whether the new course portends students' longer-term interest in computing and technology. This study used data from more than 120,000 first-year college students in the United States to understand the relationship between taking APCSA, APCSP, or both APCS courses and students' aspirations to major in computing or to pursue a computing or technology career. Our results indicated that taking APCSA or taking both APCS courses positively predicted students'major or career aspirations in computing and technology, but that taking only APCSP did not predict long-term computing interest (although positive associations were identified for women). The findings identify a possible tension in the function of APCSP, as it appears to broaden access to computing knowledge, but may not necessarily encourage longer-term computing aspirations for all groups of underrepresented students.

关键词： Robustness   Convolutional neural networks   Receivers   Forestry   Computer science   Information technology   Elbow   Coverless image steganography   camouflage image   CNN features   image clustering   image retrieval  

摘要： Recently, most coverless image steganography (CIS) methods are based on robust mapping rules. However, due to the limited mapping expression relationship between secret information and hash sequence, it is a challenge to further improve the hiding ability of coverless information hiding. Towards this goal, this paper proposes a robust coverless steganography scheme using camouflage image(CI-CIS). For the sender, CI-CIS introduces an camouflage image as the transmission carrier and establishes the correlation between them by Convolutional Neural Network(CNN) features. For the receiver, the camouflage image can retrieve the corresponding stego-image to recover the secret information. To this end, we designed a reversible retrieval scheme between stego-image and camouflage image by using image clustering. At the same time, since the semantic features represented by CNN are robust to image attacks, our method can increase the capability of the CIS effectively. Besides, we also build an inverted index to improve retrieval efficiency. Experimental results and analysis show that the CI-CIS has higher robustness and more flexible capacity setting compared with the existing CIS methods.

关键词： Containers   Data centers   Load management   Costs   IP networks   Computer science   Microservice architectures   Container placement   traffic-aware   load balancing   data centers   cloud computing  

摘要： Instantiated containers of an application are distributed across multiple Physical Machines (PMs) to achieve high parallel performance. Container placement plays a vital role in network traffic and the performance of containerized data centers. Existing container placement techniques are inadequate due to the ignorance of container traffic patterns. To solve this issue, we first investigate the network traffic between containers and observe that it exhibits a Zipf-like distribution. Motivated by this finding, we propose a novel container placement approach-Blender-by taking into account the Zipf-like distribution. Blender employs two algorithms called RefineAlg and SplitAlg to divide containers of applications into blocks, and place these blocks across Virtual Machines (VMs). Blender exhibits two salient features: (i) it minimizes inter-block traffic by arranging the containers that communicate frequently in the same block. (ii) it achieves good load balancing by combining complementary blocks that request different resource types (e.g., CPU-intensive and memory-intensive blocks) and distributing these blocks across multiple VMs. The experimental results show that Blender significantly reduces communication traffic and network latency. In particular, Blender reduces the traffic of SBP and CA-WFD by 22% and 32%, respectively. Blender decreases network latency by 16% and 26% compared to SBP and CA-WFD. Furthermore, with Blender in place, the physical resources of hosting PMs are well balanced and utilized.

关键词： Maintenance engineering   Multicore processing   Prediction algorithms   Software algorithms   Indexes   Computer science   Scalability   Core number maintenance   dense subgraph   dynamic graph   graph analytics  

摘要： This article studies the core maintenance problem in dynamic graphs. The core number is a fundamental index reflecting the cohesiveness of a graph, which is widely used in large-scale graph analytics. The core maintenance problem requires updating the core numbers of vertices after a set of edges and vertices are inserted into or deleted from the graph. Previous works focus on the scenario of single-edge updates and process the edges one by one when multiple edges are inserted/deleted. We initiate the studies of processing multiple edges concurrently to improve the efficiency of core maintenance. Specifically, we discover a structure of inserted/deleted edges, superior edge set, which can be processed together to greatly reduce unnecessarily repeated visits of vertices in the procedure of sequential edge processing. Based on the structure of the superior edge set, efficient algorithms are then devised for incremental and decremental core maintenance, respectively. Compared with single-edge processing algorithms, our algorithms show a significant speedup in the processing time. Furthermore, our algorithms admit parallel implementations, which can further improve the update efficiency. We also conduct extensive experiments on different types of real-world, temporal, and synthetic data sets, and the results illustrate that the proposed algorithms exhibit good efficiency, stability, and scalability.

关键词： Computer science   Approximation algorithms   Iterative algorithms   Optimization   Iterative methods   Systematics   Stability analysis  

摘要： Optimization problems in engineering and applied mathematics are typically solved in an iterative fashion, by systematically adjusting the variables of interest until an adequate solution is found. The iterative algorithms that govern these systematic adjustments can be viewed as a control system. In control systems, the output is measured and the input is adjusted using feedback to drive the error to zero. Similarly, in iterative algorithms, the optimization objective is evaluated and the candidate solution is adjusted to drive it toward the optimal point. Choosing an algorithm that works well for a variety of optimization problems is akin to robust controller design. Just as dissipativity theory can be used to analyze the stability properties of control systems, it can also be used to analyze the convergence properties of iterative algorithms. By defining an appropriate notion of “energy” that dissipates with every iteration of the algorithm, the convergence properties of the algorithm can be characterized. This article formalizes the connection between iterative algorithms and control systems and shows through examples how dissipativity theory can be used to analyze the performance of many classes of optimization algorithms. This control-theoretic viewpoint enables the selection and tuning of optimization algorithms to be performed in an automated and systematic way.

关键词： Citations   Open access   Toll access   Open access journals   Author-pays charges (APC) model   Article processing charge   Springer   Elsevier  

摘要： Purpose Citation is an important measure of quality, and it plays a vital role in evaluating scientific research. However, citation advantage varies from discipline to discipline, subject to subject and topic to topic. This study aims to compare the citation advantage of open access and toll access articles from four subfields of computer science. Design/methodology/approach This research studies the articles published by two prestigious publishers: Springer and Elsevier in the author-pays charges model from 2011 to 2015. For experimentation, four sub-domains of computer science are selected including (a) artificial intelligence, (b) human-computer interaction, (c) computer vision and graphics, and (d) software engineering. The open-access and toll-based citation advantage is studied and analyzed at the micro level within the computer science domain by performing independent sample t-tests. Findings The results of the study highlight that open access articles have a higher citation advantage as compared to toll access articles across years and sub-domains. Further, an increase in open access articles has been observed from 2011 to 2015. The findings of the study show that the citation advantage of open access articles varies among different sub-domains of a subject. The study contributed to the body of knowledge by validating the positive movement toward open access articles in the field of computer science and its sub-domains. Further, this work added the success of the author-pays charges model in terms of citation advantage to the literature of open access. Originality/value To the best of the authors' knowledge, this is the first study to examine the citation advantage of the author-pays charges model at a subject level (computer science) along with four sub-domains of computer science.