DATA RECOVERY Web Results

IRTF: A new tensor factorization for irregular multidimensional data ... By integrating the proposed IRTF and TV-CST, we establish an irregular multidimensional data recovery model. From (d), we can observe that our method preserves the color and the edge of the spatial-irregular multidimensional data as compared with traditional tensor factorization with preprocessing.

The Missing Data Recovery Method Based on Improved GAN Most existing data recovery methods require complete datasets for training, leading to substantial data and computational demands and limited generalization. To address these limitations, this study proposes a missing data imputation model based on an improved Generative Adversarial Network (BAC-GAN).

FAST: A battery data recovery method for missing information due to ... The method effectively captures degradation trends and capacity fluctuations, including regeneration effects, with minimal data. In the satellite battery dataset with approximately 70 % missing data, the proposed model reduces recovery errors by more than 50 % compared with existing methods.

Air quality index prediction through TimeGAN data recovery and PSO ... TimeGAN is employed to learn the structure and distribution of air quality data, facilitating the generation of synthetic data through adversarial networks. Subsequently, the missing values in the real data are replaced with the generated data.

Waste heat recoveries in data centers: A review - ScienceDirect Waste heat recovery technology is considered as a promising approach to improve energy efficiency, achieve energy and energy cost savings, and mitigate environmental impacts (caused by both carbon emission and waste heat discharge) at the same time.

Dynamic performance of an integrated heat pump system coupled free ... Recovering and reusing this waste heat for district heating is an effective strategy to enhance energy efficiency in data centers. To align data center waste heat recovery with heat consumer demand and improve energy utilization, a transient mathematical model of a data center-integrated heat pump district heating system was developed and ...

Trustworthy data recovery for incomplete multi-view learning Therefore, in this paper, we aim to develop a trustworthy data recovery framework for incomplete multi-view learning (TDR-IML), which ensures reliable imputed data with an uncertainty-aware scheme.

Long-term missing wind data recovery using free access databases and ... The conventional interpolation techniques hardly achieve the desired data recovery. Therefore, a framework was proposed for long-term missing wind data recovery based on a deep neural network (DNN) utilizing a free access database (European Center for Medium-Range Weather Forecasts, ECMWF).

Tensor network decomposition for data recovery: Recent advancements and ... Tensor network (TN) decomposition stands as a pivotal technique for characterizing the essential features of high-dimensional data, attracting significant interest and achieving notable success in high-dimensional data recovery.

Kernel Bayesian tensor ring decomposition for multiway data recovery With the aid of side information, the recovery performance of the methods above is improved. However, all matrix-based methods with side information encounter difficulties when dealing with high-order data because they cannot incorporate specific side information enhancements.