visual exploration of literature datasets, especially in specialized domains like isostatic pressing in materials research, aids scientific understanding and discovery but demands robust natural language processing te...
详细信息
visual exploration of literature datasets, especially in specialized domains like isostatic pressing in materials research, aids scientific understanding and discovery but demands robust natural language processing techniques for semantic representation. Existing methods often rely on complex and time-consuming processes to obtain text embeddings, which are numerical representations of text that capture their semantic information and similarity. The quality of text embeddings is crucial for enabling visual exploration of literature datasets. Our research question is whether visual exploration of literature datasets can benefit from GPT (generative pre-trained transformer) text embeddings. We seek to answer this question by performing case studies and expert interviews. To do this, we curated a unique literature dataset about isostatic pressing, sourced from diverse periods and genres. Utilizing a GPT embedding model, we generated embeddings for textual analysis, visualizing and examining their semantic interrelations. Expert reviews were undertaken to evaluate the utility of these techniques. Our findings show that GPT text embeddings offer significant improvements in visually exploring literature datasets, revealing deep semantic similarities and diversities. We also discuss the implications, limitations of our study, and propose directions for future research.
Understanding the patterns of traffic-related carbon dioxide (CO2) emissions from different trip purposes is of great significance for the development of low-carbon transportation. However, most existing research igno...
详细信息
ISBN:
(纸本)9783031500749;9783031500756
Understanding the patterns of traffic-related carbon dioxide (CO2) emissions from different trip purposes is of great significance for the development of low-carbon transportation. However, most existing research ignores the traffic-related CO2 emissions from daily trip. Accurately inferring trip purposes is a prerequisite for analyzing the patterns of traffic-related CO2 emissions from daily trip. The existing research on inferring trip purposes has been proven effective, but it ignores door-to-door service (DTD) and the time-varying characteristics of the attractiveness of Points of Interest (POIs). In this paper, we propose a Bayesian-based method to infer trip purposes. It identifies DTD through spatial relation operations and constructs the dynamic function of POIs attractiveness using kernel density estimation (KDE). A visual analysis system is also developed to help users explore the spatio-temporal patterns of traffic-related CO2 emissions from daily trip. Finally, the effectiveness of the method and the system is verified through case study based on real data and positive feedback from experts.
As the primary source of carbon dioxide (CO2) emissions, cities are the key to solving climate change. Prior works focus on CO2 emission drivers and CO2 emission city clusters. However, the methods of mining CO2 emiss...
详细信息
ISBN:
(纸本)9798400701405
As the primary source of carbon dioxide (CO2) emissions, cities are the key to solving climate change. Prior works focus on CO2 emission drivers and CO2 emission city clusters. However, the methods of mining CO2 emission drivers include narrow factors affecting CO2 emissions, and ignore the interactions among these factors. The intelligibility of the results of the Geographical Weighted Regression (GWR) that is used to analyze the spatial heterogeneity of drivers is poor. Moreover, the relations between CO2 emission city clusters and economic ties among cities are ignored. The lack of visual analysis tools is also a problem that needs to be fixed. Hence we develop a novel analysis framework. Thereinto, a novel method based on the stepwise regression (SR) is used to mine drivers;the biclustering algorithm is introduced into the traditional GWR to improve the intelligibility of the GWR;the gravity-entropy model is adopted to analyze the relations between CO2 emission city clusters and economic correlation strength among cities. Furthermore, a visualanalytics system is implemented to explore the situation of CO2 emissions. We demonstrate the effectiveness of our approach through case studies conducted with socioeconomic data from 169 Chinese cities and positive feedback from experts and volunteers.
暂无评论