教学课程资源库 更多>>

关键词： Computer science   Translational research  

摘要： Much of computer science research can benefit from the Translational Computing Science paradigm, which bridges foundational, use-inspired, and applied research with the delivery and deployment of its outcomes and supports essential bidirectional interplays. However, its wide adoption continues to face multiple challenges and roadblocks. This paper uses the perspectives and experiences of two accidental translationists to illustrate the translation process, it impacts, as well as the challenges and roadblocks faced.

关键词： Conferences   Medical services   Security   Internet of Things   Informatics   Computer security   Computer science  

摘要： TO BUILD a sustainable ecosystem, healthcare reinforced by the Internet of Things (IoT-Health) is a sector that makes a very useful contribution to society. With the aging of the world's population, the ability to monitor and protect people at home reduces costs and increases the quality of life. IoT healthcare has become a market with great potential, and IT giants such as IBM, Microsoft, and GE Healthcare develop products for specialized medical applications. Using IoT-Health for data collection and workflow automation is a great way to reduce waste and minimize human errors. However, the security of healthcare information is a major concern, and cybersecurity has become a significant threat for healthcare providers as well as governments to achieve sustainable city milestones. IT professionals must continually resolve health data security issues to help patients and the damage that healthcare security breaches can have on their lives.

关键词： computer science   COVID-19   engineering   equity   multi-institution   qualitative methods   remote learning   undergraduate  

摘要： Background In Spring 2020, the COVID-19 pandemic sent universities into emergency remote education. The pandemic has been disruptive but offers the opportunity to learn about ways to support students in other situations where abrupt changes to teaching and learning are necessary. Purpose/Hypothesis We described the responses of engineering and computer science students to a series of prompts about their experiences with remote learning. Design/Method Data about students' remote learning experiences were collected from undergraduate engineering and computer science students at four different universities through an end-of-semester survey. Descriptive statistics were calculated, and qualitative responses were analyzed using qualitative content analysis through the lenses of master narrative theory and sociocultural theory. Results Student responses revealed how their individual circumstances combined to reduce motivation, create home environments detrimental to completing schoolwork, and increase stress. Many students described the negative impacts of remote learning, but some students found positive aspects of the situation. The majority of students did not indicate a change in their desire or plans to pursue engineering or computer science majors. Conclusions There was wide variation in how students experienced the disruption to university learning during Spring 2020. Implications of this paper can help not only in cases where emergency remote learning is needed in the future but also as universities seek to return to "normal" operations in 2022 and beyond.

关键词： Proteins   Annotations   Prediction algorithms   Biological processes   Labeling   Computer science   Task analysis   PPI networks   protein function prediction   graph diffusion   semi-supervised learning  

摘要： A method to improve protein function prediction for sparsely annotated PPI networks is introduced. The method extends the DSD majority vote algorithm introduced by Cao et al. to give confidence scores on predicted labels and to use predictions of high confidence to predict the labels of other nodes in subsequent rounds. We call this a majority vote cascade. Several cascade variants are tested in a stringent cross-validation experiment on PPI networks from S. cerevisiae and D. melanogaster, and we show that for many different settings with several alternative confidence functions, cascading improves the accuracy of the predictions. A list of the most confident new label predictions in the two networks is also reported. Code and networks for the cross-validation experiments appear at http://***/cascade.

摘要： No abstract available.

关键词： capital punishment   death row   final statements   last meals   United States  

摘要： Over the past two decades, a growing body of work has emerged in the social sciences that explores various aspects of capital punishment in the contemporary United States. This article reviews one strand of this literature that focuses on the execution ritual itself - specifically on condemned inmates' last meals and the final statements that they make in the execution chamber just prior to their execution. It also discusses some of the limitations of the research and offers some ideas for future scholarship in this area.

关键词： Trajectory   Clustering algorithms   Partitioning algorithms   Gene expression   Diseases   Computer science   Manifolds   Trajectory inference   consensus clustering   gene partition   single-cell transcriptome  

摘要： Cellular programs often exhibit strong heterogeneity and asynchrony in the timing of program execution. Single-cell RNA-seq technology has provided an unprecedented opportunity for characterizing these cellular processes by simultaneously quantifying many parameters at single-cell resolution. Robust trajectory inference is a critical step in the analysis of dynamic temporal gene expression, which can shed light on the mechanisms of normal development and diseases. Here, we present TiC2D, a novel algorithm for cell trajectory inference from single-cell RNA-seq data, which adopts a consensus clustering strategy to precisely cluster cells. To evaluate the power of TiC2D, we compare it with three state-of-the-art methods on four independent single-cell RNA-seq datasets. The results show that TiC2D can accurately infer developmental trajectories from single-cell transcriptome. Furthermore, the reconstructed trajectories enable us to identify key genes involved in cell fate determination and to obtain new insights about their roles at different developmental stages.

关键词： Smoothing methods   Laplace equations   Network topology   Topology   Task analysis   Multimedia Web sites   Computer science   Attributed networks   autoencoder   network representation learning   smoothing  

摘要： Attributed networks are ubiquitous in the real world, such as social networks. Therefore, many researchers take the node attributes into consideration in the network representation learning to improve the downstream task performance. In this article, we mainly focus on an untouched ``oversmoothing'' problem in the research of the attributed network representation learning. Although the Laplacian smoothing has been applied by the state-of-the-art works to learn a more robust node representation, these works cannot adapt to the topological characteristics of different networks, thereby causing the new oversmoothing problem and reducing the performance on some networks. In contrast, we adopt a smoothing parameter that is evaluated from the topological characteristics of a specified network, such as small worldness or node convergency and, thus, can smooth the nodes' attribute and structure information adaptively and derive both robust and distinguishable node features for different networks. Moreover, we develop an integrated autoencoder to learn the node representation by reconstructing the combination of the smoothed structure and attribute information. By observation of extensive experiments, our approach can preserve the intrinsical information of networks more effectively than the state-of-the-art works on a number of benchmark datasets with very different topological characteristics.

关键词： Gold   Feature extraction   Estimation   Face   Deep learning   Computer science   Learning systems   Channel-wise and spatial attention learning   pixel-level relation learning   facial AU detection  

摘要： Attention mechanism has recently attracted increasing attentions in the field of facial action unit (AU) detection. By finding the region of interest of each AU with the attention mechanism, AU-related local features can be captured. Most of the existing attention based AU detection works use prior knowledge to predefine fixed attentions or refine the predefined attentions within a small range, which limits their capacity to model various AUs. In this paper, we propose an end-to-end deep learning based attention and relation learning framework for AU detection with only AU labels, which has not been explored before. In particular, multi-scale features shared by each AU are learned first, and then both channel-wise and spatial attentions are adaptively learned to select and extract AU-related local features. Moreover, pixel-level relations for AUs are further captured to refine spatial attentions so as to extract more relevant local features. Without changing the network architecture, our framework can be easily extended for AU intensity estimation. Extensive experiments show that our framework (i) soundly outperforms the state-of-the-art methods for both AU detection and AU intensity estimation on the challenging BP4D, DISFA, FERA 2015, and BP4D+ benchmarks, (ii) can adaptively capture the correlated regions of each AU, and (iii) also works well under severe occlusions and large poses.

关键词： Computer science   Ethics  

摘要： BLOOM aims to address the biases that machine-learning systems inherit from the texts they train on.