I-Hsien Ting

I-Hsien Ting, Kazunori Minetaki, Dario Liberona et al.

The rapid evolution of large language model based multiagent systems has transformed digital communication, with platforms like MoltBook emerging as essential agent native environments for observing autonomous social behaviors. While existing literature has documented the structural topology of these networks, there remains a critical gap in understanding the semantic content and emotional undercurrents of agent discourse. In this study, we propose a multi-dimensional analytical framework, utilizing human AI collaboration leveraging the Hermes agent powered by the Minimax 2.7 LLM to facilitate data collection and preliminary analysis. Our methodology synthesizes Social Network Analysis with sentiment analysis and thematic visualization to decode inter-agent interactions. We argue that benchmarking agent social dynamics against human social networks is inherently limited; thus, this study focuses exclusively on the intrinsic mechanics of agent-native communication. By integrating structural network metrics with qualitative diagnostics, we provide a holistic view of interaction quality within the MoltBook ecosystem. This collaborative approach not only addresses the need for semantic depth in agent network analysis but also offers valuable insights into the emergent dynamics of decentralized autonomous digital networks.

I-Hsien Ting, Yi-Jun Tseng, Yu-Sheng Lin

Pulmonary embolism is a life-threatening disease, early detection and treatment can significantly reduce mortality. In recent years, many studies have been using deep learning in the diagnosis of pulmonary embolism with contrast medium computed tomography pulmonary angiography, but the contrast medium is likely to cause acute kidney injury in patients with pulmonary embolism and chronic kidney disease, and the contrast medium takes time to work, patients with acute pulmonary embolism may miss the golden treatment time. This study aims to use deep learning techniques to automatically classify pulmonary embolism in CT images without contrast medium by using a 3D convolutional neural network model. The deep learning model used in this study had a significant impact on the pulmonary embolism classification of computed tomography images without contrast with 85\% accuracy and 0.84 AUC, which confirms the feasibility of the model in the diagnosis of pulmonary embolism.