Image Reconstruction Using Novel Two-Dimensional Fourier Transform

Kala, S; Nalesh, S; Jose, Babita R.; Mathew, Jimson

doi:10.1007/978-3-319-63754-9_31

Cited by 2 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Figure 5, assuming the true distribution as shown in Figure 5 MMSE can better constrain the number of predicted density map matrices. 2D-DFT can help to better constrain the distribution of predicted data and even achieve image reconstruction [70]. Cosine similarity can better constrain the similarity of distribution [71] and measure the similarity of different objects to achieve image classification [72].…”

Section: Loss Functionmentioning

confidence: 99%

In-Depth Analysis of Railway and Company Evolution of Yangtze River Delta with Deep Learning

2020

View full text Add to dashboard Cite

The coordinated development of smart cities has become the goal of world urban development, and the railway network plays an important role in this progress. This paper proposes a solution that integrates data acquisition, storage, GIS visualization, deep learning, and statistical correlation analysis to deeply analyze the distribution data of companies collected in the past 40 years in the Yangtze River Delta. Through deep learning, we predict the spatial distribution of the company after the opening of the train stations. Through statistical and correlation analysis of the company’s registered capital and quantity, the urban development relationship under the influence of the opening of the railway is explored. Going forward, the use and application of such analysis can be tested for use and application in the context of other smart cities for specific aspects or scale.

show abstract

Section: Loss Functionmentioning

confidence: 99%