教学课程资源库 更多>>

关键词： Computational modeling   Mathematical model   Data models   Numerical models   Social network services   Eigenvalues and eigenfunctions   Computer science   Social network   signed network   scale-free   power-law   balanced indices   network reconstruction  

摘要： We propose modeling signed networks by considering two layers in a social network for generation of positive and negative links where both the layers comprise of identical set of nodes. The growth process is modeled based on preferential attachment, formation of links probabilistically asserting structural balance of local groups, and internal growth which happens without addition of new nodes. We prove that the degree distribution of a generated network follows a power-law whose exponent depends on the largest eigenvalue of a matrix which governs the dynamics of growth of degrees of nodes with respect to positive and negative links. A computable formula for average degree and lower-bounds for the number of balanced and unbalanced triads of modelled networks are also obtained. A method for structural reconstruction of real signed networks is formulated through estimation the values of the model parameters to generate the network that can inherit different structural properties of the corresponding real network. Experimental results show that our model which we term as 2L-SNM can replicate properties of several real world signed networks much more robustly than competitive state-of-the-art techniques.

关键词： 师范院校   计算机研究生   实践能力   科普服务   信息科学  

摘要： 从学科优势、毕业去向、生源质量及学习需求等方面分析师范院校计算机研究生实践能力培养面临的问题,发现计算机研究生具有师范技能提升与计算机专业实践的双重需求。针对该需求,提出借助优质的信息科学科普服务,设计趣味化课程教学,建立助教制度,促使师范院校计算机研究生师范技能及计算机专业实践能力提升。实践证明,深度参与科普服务的计算机研究生,在其师范技能得到充分锻炼的同时,专业创新实践能力也得以有效提升。

关键词： Training   Task analysis   Benchmark testing   Perturbation methods   Knowledge engineering   Cybernetics   Computer science   Fuzzy rules   generalization capability   interpretability   knowledge adversarial training   Takagi-Sugeno-Kang (TSK) fuzzy classifiers  

摘要： While input or output-perturbation-based adversarial training techniques have been exploited to enhance the generalization capability of a variety of nonfuzzy and fuzzy classifiers by means of dynamic regularization, their performance may perhaps be very sensitive to some inappropriate adversarial samples. In order to avoid this weakness and simultaneously ensure enhanced generalization capability, this work attempts to explore a novel knowledge adversarial attack model for the zero-order Tagaki-Sugeno-Kang (TSK) fuzzy classifiers. The proposed model is motivated by exploiting the existence of special knowledge adversarial attacks from the perspective of the human-like thinking process when training an interpretable zero-order TSK fuzzy classifier. Without any direct use of adversarial samples, which is different from input or output perturbation-based adversarial attacks, the proposed model considers adversarial perturbations of interpretable zero-order fuzzy rules in a knowledge-oblivion and/or knowledge-bias or their ensemble to mimic the robust use of knowledge in the human thinking process. Through dynamic regularization, the proposed model is theoretically justified for its strong generalization capability. Accordingly, a novel knowledge adversarial training method called KAT is devised to achieve promising generalization performance, interpretability, and fast training for zero-order TSK fuzzy classifiers. The effectiveness of KAT is manifested by the experimental results on 15 benchmarking UCI and KEEL datasets.

关键词： Semantics   Adversarial machine learning   Correlation   Visualization   Generators   Generative adversarial networks   Computer science  

摘要： The main challenge of cross-modal retrieval is how to efficiently realize cross-modal semantic alignment and reduce the heterogeneity gap. However, existing approaches either ignore the multigrained semantic knowledge learning from different modalities, or fail to learn consistent relation distributions of semantic details in multimodal instances. To this end, this article proposes a novel end-to-end cross-modal representation method, termed as deep multigraph-based hierarchical enhanced semantic representation (MG-HESR). This method is an integration of MG-HESR with cross-modal adversarial learning, which captures multigrained semantic knowledge from cross-modal samples and realizes fine-grained semantic relation distribution alignment, and then generates modalities-invariant representations in a common subspace. To evaluate the performance, extensive experiments are conducted on four benchmarks. The experimental results show that our method is superior than the state-of-the-art methods.

关键词： Optimization   Convergence   Search problems   Acceleration   Computer science   Signal restoration   Prediction algorithms   Change response   dynamic optimization   evolutionary algorithm (EA)   learning   multiobjective optimization  

摘要： Dynamic multiobjective optimization problems are challenging due to their fast convergence and diversity maintenance requirements. Prediction-based evolutionary algorithms currently gain much attention for meeting these requirements. However, it is not always the case that an elaborate predictor is suitable for different problems and the quality of historical solutions is sufficient to support prediction, which limits the availability of prediction-based methods over various problems. Faced with these issues, this article proposes a knowledge learning strategy for change response in the dynamic multiobjective optimization. Unlike prediction approaches that estimate the future optima from previously obtained solutions, in the proposed strategy, we react to changes via learning from the historical search process. We introduce a method to extract the knowledge within the previous search experience. The extracted knowledge can accelerate convergence as well as introduce diversity for the optimization of the future environment. We conduct a comprehensive experiment on comparing the proposed strategy with the state-of-the-art algorithms. Results demonstrate the better performance of the proposed strategy in terms of solution quality and computational efficiency.

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： Digital technology   Interaction design   Interactive products   Life-centred design   More-than-human   Responsible innovation  

摘要： Over the past decades, the field of interaction design has shaped how people interact with digital technology, both through research and practice. Interaction designers adopted human-centred design to ensure that the interactive products they design meet the needs and desires of end consumers. However, there is surmounting evidence that placing the end consumer at the centre of the design process creates unintended consequences, damaging global systems that are essential to human well-being. This article reviews emerging paradigms that provide a more holistic perspective, such as value-sensitive design, more-than-human participation and life-centred design. Based on this review, the article introduces a practical framework for life-centred design consisting of principles, actionable methods and a model for responsible innovation. The article discusses how interaction designers can use the framework to balance human-centred considerations with environmental and ethical concerns when designing interactive products. © 2022

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.