Discrete Wavelet Transform (DWT) has been widely explored to enhance the performance of image superresolution (SR). Despite some DWT-based methods improving SR by capturing fine-grained frequency signals, most existing approaches neglect the interrelations among multiscale frequency sub-bands, resulting in inconsistencies and unnatural artifacts in the reconstructed images. To address this challenge, we propose a Diffusion Transformer model based on image Wavelet spectra for SR (DTWSR). DTWSR incorporates the superiority of diffusion models and transformers to capture the interrelations among multiscale frequency sub-bands, leading to a more consistence and realistic SR image. Specifically, we use a Multi-level Discrete Wavelet Transform to decompose images into wavelet spectra. A pyramid tokenization method is proposed which embeds the spectra into a sequence of tokens for transformer model, facilitating to capture features from both spatial and frequency domain. A dual-decoder is designed elaborately to handle the distinct variances in low-frequency and high-frequency sub-bands, without omitting their alignment in image generation. Extensive experiments on multiple benchmark datasets demonstrate the effectiveness of our method, with high performance on both perception quality and fidelity.

Incorporation of data from multiple resources and various structures is necessary for accurate estimation of the driving range for electric vehicles. In addition to the parameters of the vehicle model, states of the battery, weather information, and road grade, the driving behavior of the driver in different regions is a critical factor in predicting the speed/acceleration profile of the vehicle. Following our previously proposed big data analysis framework for range estimation, in this paper we implement and compare different techniques for speed profile generation. Moreover we add the big data analysis classification results to especially improve the performance of the Markov Chain approach. The quantitative results show the significant influence of considering the big data analysis results on range estimation.

In this paper, we propose a Context Aware Intelligent Mobile Platform (IMP) for the use of various surrounding local services with minimal user intervention in the forthcoming ubiquitous environment. Through the use of proposed platform, a user can easily discover available surrounding local services and utilize the best service appropriate for one's situation and device's constraints. The user situation and the corresponding service are automatically grasped by the embedded context aware engine and selected by the semantic machine to machine manager.