Toward parallel intelligence: An interdisciplinary solution for complex systems

Zhao, Yong; Zhu, Zhengqiu; Chen, Bin; Qiu, Sihang; Huang, Jincai; Lu, Xin; Yang, Weiyi; Ai, Chuan; Huang, Kuihua; He, Cheng; Jin, Yucheng; Liu, Zhong; Wang, Fei-Yue

doi:10.1016/j.xinn.2023.100521

Cited by 6 publications

(2 citation statements)

References 150 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventional grid‐based numerical methods, including the finite difference method (FDM) (Jalghaf et al., 2021), finite volume method (FVM) (Xia & Liang, 2018), and finite element method (FEM) (Jiang & Ma, 2011), have indeed yielded significant successes in the realm of PDE solving. However, their precision remains intrinsically tethered to the resolution of the computational mesh, necessitating iterative procedures and paralleling skills to attain numerical solutions (Kochkov et al., 2021; Zhao et al., 2023). Although refining the mesh resolution can enhance accuracy, it concurrently engenders exponential increments in computational demands.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Method for Dynamic Process Modeling of Real Landslides Based on Fourier Neural Operator

Chen,

Ouyang,

et al. 2024

Earth and Space Science

View full text Add to dashboard Cite

The conventional numerical solvers for partial differential equations encounter a formidable challenge, as their computational efficiency and accuracy are heavily contingent on grid size. Recently, machine learning (ML) has exhibited substantial promise in addressing partial differential equations. Nevertheless, substantial hurdles persist in practical applications. In this work, we endeavor to establish a deep learning framework founded on the Fourier neural operator (FNO) for resolving the intricacies of simulating real landslide dynamic processes. Our findings demonstrate that the current FNO approach adeptly replicates landslide dynamic processes and boasts exceptional computational efficiency. Additionally, it is noteworthy that this data‐driven ML methodology can seamlessly incorporate data from other experimental sources or numerical simulation techniques. Consequently, this work underscores the significant potential of utilizing ML methodologies to supplant conventional numerical simulation methods.

show abstract

Section: Introductionmentioning

confidence: 99%

A Deep Learning Method for Dynamic Process Modeling of Real Landslides Based on Fourier Neural Operator

Chen,

Ouyang,

et al. 2024

Earth and Space Science

View full text Add to dashboard Cite

show abstract

“…Pelangi pembelajaran Abad 21 menggambarkan keterampilan yang paling dibutuhkan siswa pada saat ini. Kerangka tersebut menambah mata pelajaran interdisipliner dengan tema abad ke-21 yang relevan dengan beberapa isu dan masalah utama zaman ini (D'Este & Robinson-García, 2023;Sevilla et al, 2023;Zhao et al, 2023), seperti kesadaran global (multicultural awareness and understanding) (Barcena-Vazquez et al, 2023); literasi lingkungan (kesadaran dan pemahaman ekologi energi dan keberlanjutan sumber daya) (Law et al, 2023); literasi keuangan (pengetahuan ekonomi, bisnis, dan kewirausahaan); literasi kesehatan (pelayanan kesehatan, nutrisi, dan pengobatan pencegahan) (Mathias et al, 2023) (Keegan, 2021); dan literasi kewarganegaraan (keterlibatan masyarakat, pengabdian masyarakat, etika, dan keadilan sosial). Mata pelajaran inti dan interdisipliner pada pembelajaran abad ke-21 dilingkupi dengan tiga set keterampilan yang paling diminati saat ini, yaitu keterampilan belajar dan inovasi, keterampilan informasi, media, dan teknologi, serta keterampilan hidup dan karir (Trilling dan Fadel, 2009).…”

unclassified

Pelatihan Pembelajaran Berbasis 21st Century Skills di Sekolah Indonesia Johor Bahru Malaysia

Wulan,

Putri,

Rahayu

et al. 2023

bce

View full text Add to dashboard Cite

The 21st-century skills are skills that students must master to survive and compete in this 4.0 industrial revolution era. Teachers need to have good professional competence in order to facilitate students to develop 21st-century skills. This also applies to elementary school teachers. Therefore, the teacher needs training that can provide knowledge and skills for teachers to present such learning. The training program participant is an elementary school teacher at the Indonesian School of Johor Bahru Malaysia. The problem identified is that not all SIJB's primary school teachers have diverse educational backgrounds, and the learning presented is not based on 21st-century skills. The participants of this training are 19 teachers. The program is web-based training using the ADDIE model. This training is conducted in three stages, namely the pre-implementation, implementation, and post-implementation stages. At the implementation stage, there are eight meetings containing materials on 21st Century Skills-based learning in Indonesian Language, Mathematics, Science, Social Studies and Civics, English, Arts, ICT, innovative learning models and learning life skills. Participants were given a pretest and posttest understanding of 21st Century learning. The pretest results showed an average value of 60.8, which means that participants' understanding of 21st Century learning is still quite good and the posttest average score of 84.5, which means that understanding participants is good. The result shows that the participants' understanding increased after attending the training. Based on the questionnaire results, the participant's response was quite good, and hoped that the training activities could be carried out on an ongoing basis. Keywords: 21st Century Skills Training Program, Professional Competency of Elementary Teacher

show abstract

Parallel intelligence in three decades: a historical review and future perspective on ACP and cyber-physical-social systems

Wang,

Yang,

Liu

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Recent advances in human-in-the-loop or human-centric research have sparked a new wave of scientific exploration. These studies have enhanced the understanding of complex social systems and contributed to more sustainable artificial intelligence (AI) ecosystems. However, the incorporation of human or social factors increases system complexity, making traditional approaches inadequate for managing these complex systems and necessitating a novel operational paradigm. Over decades of work, a mature and comprehensive theory of parallel intelligence (PI) has been established. Rooted in cyber-physical-social systems (CPSS), PI adapts flexibly to various situations within complex systems through the ACP framework (Artificial systems, Computational experiments, and Parallel execution), ensuring system reliability. This paper provides a detailed review and a novel perspective on PI, beginning with the historical and philosophical origins of CPSS and proceeding to present both the fundamental framework and technological implementations of PI. PI-based Industry 5.0 is highlighted, where three pillars are adopted to help realize the supposed vision. Additionally, the paper outlines applications of PI in multiple fields, such as transportation, healthcare, manufacturing, and agriculture, and discusses the opportunities and challenges for imaginative intelligence. The continuous exploration of PI is expected to eventually facilitate the realization of “6S”-based (safe, secure, sustainable, sensitive, service, and smart) parallel ecosystems.

show abstract

Toward parallel intelligence: An interdisciplinary solution for complex systems

Cited by 6 publications

References 150 publications

A Deep Learning Method for Dynamic Process Modeling of Real Landslides Based on Fourier Neural Operator

A Deep Learning Method for Dynamic Process Modeling of Real Landslides Based on Fourier Neural Operator

Pelatihan Pembelajaran Berbasis 21st Century Skills di Sekolah Indonesia Johor Bahru Malaysia

Parallel intelligence in three decades: a historical review and future perspective on ACP and cyber-physical-social systems

Contact Info

Product

Resources

About