Optimizing Connectome Reconstruction in Intelligent Management Approach Using DEA

In the filed of connectomics, reconstructing an accurate and complete connectome requires considerable manpower, financial resources, and time. Efficient management of reconstruction projects to conserve resources and enable rapid reconstruction poses a significant challenge. This study views individual annotators as decision-making units from a microlevel perspective and uses data envelopment analysis to establish productivity and performance analysis model of annotators. By introducing advanced Artificial Intelligence (AI) algorithms to empower intelligent management of connectome reconstruction, we can mine users’ effective outputs in a more reliable and robust way. Edge computing performance is improved by embedding intelligent algorithms and data collection systems into user devices. Through the analysis of the inputs and outputs in the production activities of annotators, the effectiveness of the proposed model has been validated, which helps to understand and optimize user performance. The proposed method can be used for efficient management in connectome reconstruction to allocate resources equitably and optimize human resources within the company.