Time series forecasting faces significant challenges due to non-stationary components that obscure underlying patterns. While Transformer-based models are effective at capturing stationary components, they struggle with non-stationary dynamics and multivariate dependencies. In this paper, we proposeFreqEvo, a lightweight Frequency Domain Feature Enhancement module for time series forecasting.FreqEvoprogressively filters frequency components from high to low amplitude, ensuring the preservation of informative features while reducing noise. By integrating recursive Fourier-based residual modeling and cross-domain attention,FreqEvoeffectively refines low-amplitude frequency features and stabilizes the embeddings, outperforming traditional low-pass filtering and random frequency selection methods in capturing both short-term and long-term dependencies. Experimental results on benchmark datasets demonstrate thatFreqEvooutperforms state-of-the-art (SOTA) models and serves as a plug-and-play module to enhance existing Long-Term Sequence Forecasting (LSTF) models.

Radar false target jamming can be used to cover the actions of real targets, posing a great challenge to radar target detection. Most traditional recognition methods are almost ineffective in recognizing real-false targets in the case of missing false target samples, and their effectiveness may decrease with pulse compression processing. This letter proposes a recognition method based on fast-slow time frequency response features and positive-unlabeled (PU) learning algorithm to overcome the above problems. The novel method utilizes pulse compression and coherent accumulation processing to improve the stability of frequency response features, then employs a PU learning algorithm for real-false target recognition in the case of missing false target label information. The proposed method obtain a recognition rate of 97.8% on the measured data.

AI City is the direction of urban construction and development in the future, Qiqihar has put forward the grand strategy of building AI City in Qiqihar, as one of the first batch of national AI City construction pilots. There are not only a series of favorable factors and rare opportunities, but also a series of thorny problems and severe challenges in construction of AI City in Qiqihar. Through the in-depth analysis and judgment of these conditions, we should make good use of all favorable factors, and have the courage to face various problems and challenges in the construction of AI City in Qiqihar, actively seek effective solutions and methods, make great efforts to overcome difficulties, promote the construction of AI City in Qiqihar to make greater progress and development continuously.