教学课程资源库 更多>>

关键词： Systems biology   Computer science   Bioengineering  

摘要： Gene regulatory networks (GRNs) are critically important for efforts in biomedicine and biotechnology. Here, we introduce the Regulatory Network Machine (RNM) framework, demonstrating how GRNs behave as analog computers capable of sophisticated information processing. Our RNM framework encapsulates: (1) a dissipative dynamic system with a focus on GRNs, (2) a set of inputs to the system, (3) system output states with identifiable relevance to biotechnological or biomedical objectives, and (4) Network Finite State Machines (NFSMs), which are maps detailing how the system changes equilibrium state in response to patterns of applied inputs. As an extension to attractor landscape analysis, the NFSMs map the sequential logic inherent in the GRN and, therefore, embody the "software-like" nature of the system, providing easy identification of specific applied interventions necessary to achieve desired, stable biological outcomes. We illustrate the use of our RNM framework in important biological examples, including in cancer renormalization.

关键词： Education   Accreditation   Artificial intelligence   Learning systems   Information and communication technology   Focusing   Evaluation models   Data mining   Computer science   Training   Course learning outcome (CLO)   fuzzy evaluation system   outcome-based education (OBE)   program learning outcome (PLO)   student performance assessment  

摘要： Contribution: This research designs a student evaluation framework integrating the fuzzy-logic system that assesses the student's performances in the soft boundary system for outcome-based education (OBE), measuring the course learning outcome (CLO) and program learning outcome (PLO). The framework fills the gap between conventional grading methods and offers insights into learning for course assessment and continuous development. Background: A well-established evaluation technique is a requirement to deliver a productive, skilled, worthy, and compatible student and faculty. Moreover, OBE, with a documented and structured academic curriculum, has to ensure the accreditation of an academic program. Research Questions: What are the drawbacks of traditional student evaluation techniques? Does the proposed system work as a better, more reliable, and meaningful student evaluation method? Methodology: To assess, it considers the final examination paper containing several questions and continuous assessment comprising a few items like class tests, quizzes, viva voce, homework, etc., where the course teachers and moderators assign marks on these questions and items considering the CLOs, learning methods, and Bloom's taxonomy. Then, the framework records and tracks the ratio of earned marks to assigned marks for the fuzzification, while the defuzzification computes the values indicating the CLOs and PLOs earned by a student. Findings: The results study cases for 40 courses of a particular student and analyze statistics for 100 students from the consecutive eight semesters. This fuzzy-logic-based evaluation technique is fairer, reliable, and unbiased to the learners and greatly helps to get accreditation and recognition for the degree worldwide.

摘要： Two-year institutions in the United States, commonly known as Community and Technical Colleges, play a vital role in computing education by offering a range of programs that awards credentials and degrees. These programs address regional workforce needs, support socioeconomic development, and provide pathways for students to transition to four-year institutions. The Computer Science Transfer Associate degree, a widely recognized award, requires alignment with four-year programs through Memoranda of Understanding (MOUs) and adherence to established curriculum guidelines, such as those provided by ACM/IEEE-CS. In 2023, the ACM, IEEE-CS, and AAAI released the CS2023 Curricula, a comprehensive framework defining 17 Knowledge Areas for computer science education. The ACM Committee for Computing Education in Community Colleges (CCECC) builds on this foundation through the "CS202x Transfer" initiative, aiming to map these Knowledge Areas to two-year programs. This initiative involves collaboration with four-year institutions to validate content and refine curriculum models, ensuring their relevance to both academic and workforce needs. Key focus areas include cybersecurity, artificial intelligence (AI), and society, ethics, and the profession (SEP), which are integrated across curricula to address emerging technologies and ethical considerations.

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： Imaging   Medical research   Machine learning   Computer science  

摘要： An accessible and adaptable artificial-intelligence model trained on a diverse set of X-ray images is better than existing models at spotting rare chest diseases.

摘要： The rapid evolution of AI and the increased accessibility of scientific articles through open access marks a pivotal moment in research. AI-driven tools are reshaping how scientists explore, interpret, and contribute to the body of scientific knowledge, offering unprecedented opportunities. Nonetheless, a significant challenge remains: dealing with the overwhelming number of papers published every year. A promising solution is the use of knowledge graphs, which provide structured, interconnected, and formalized frameworks that improve the capabilities of AI systems to integrate information from the literature. This paper presents the last version of the Computer Science Knowledge Graph (CS-KG 2.0), an extensive knowledge base generated from 15 million research papers. CS-KG 2.0 describes 25 million entities linked by 67 million relationships, offering a nuanced representation of the scientific knowledge within the field of computer science. This innovative resource facilitates new research opportunities in key areas such as analysis and forecasting of research trends, hypothesis generation, smart literature search, automatic production of literature review, and scientific question-answering.

关键词： Noise reduction   Recommender systems   Noise   Collaborative filtering   Noise measurement   Training   Contrastive learning   Reinforcement learning   Computer science   Adaptation models   Dynamic denoising   graph learning   implicit feedback   recommender system  

摘要： Due to the inherent challenges in acquiring explicit feedback, graph collaborative filtering (GCF) models often resort to implicit feedback. However, there exists noise in implicit feedback that may not accurately reflect users' preferences. This noise will be amplified by the aggregating and propagating operations of GCF, thereby affecting the performance of GCF. Existing noise mitigation methods attempt to filter noisy samples from implicit feedback data, yet they face limitations such as dependency on side information for sample selection, neglect of false-negative noise, and disregard for the impact of previous selections on current iteration. To overcome these challenges, we propose a dynamic graph learning framework to denoise implicit feedback for GCF (DGLD). DGLD comprises a graph learning module and a reinforcement learning module. The graph learning module evaluates the confidence degrees of interactions by leveraging user-item cosine similarity and global user preferences, updating user-item interaction graph without relying on side information. Meanwhile, the reinforcement learning module employs a policy network to select "false-positive denoising" and "false-negative denoising" actions based on performance of the recommendation model and state of interaction graph obtained from previous iterations. These modules work synergistically to dynamically denoise implicit feedback. Experimental results on three benchmark datasets underscore the superiority of our approach over state-of-the-art general and denoising recommendation models.

关键词： Computing activities   K-12 computing education   computational thinking   emerging technologies   computer science   learning  

摘要： The interest in computing learning activities is continuously increasing, keeping pace with the evolution of educational technologies. This rise in engagement is evident within approaches grounded in constructivism and constructionism, which provide an ideal setting for the spectrum of skills, literacies, and competencies that global initiatives capitalise on in K-12 education. Due to recent advancements in technology and societal changes, we are addressing the need for an updated perspective focussed on designing and implementing computational activities. To achieve this, we have analysed forty-six peer-reviewed empirical studies from the last decade to summarise technology-supported learning strategies' current direction and future potential. The main findings describe programming software and IoT as the preferred digital tools, often presented in novel combinations, extensions, and contextualisations. Implementation primarily occurs within the domain of computer science but exhibits a high degree of interdisciplinarity. Furthermore, there is an increase in activities referring to real-life scenarios, encouraging learners to develop computational skills beyond the classroom and expand their digital awareness through interaction with emerging technologies. We leverage these trends and significant patterns by proposing a summary of focal points for future research and practice, with a focus on activity design.