King Abdulaziz University

Qi Kang

Yusuf Abdulaziz Al-Turki

Mengchu Zhou

Abdullah Abusorrah

Siya Yao

Kai Zhang

XuDong Shi

In the field of computer vision, without sufficient labeled images, it is challenging to train an accurate model. But through visual adaptation from source to target domains, a relevant labeled dataset can help solve such problem. Many methods apply adversarial learning to diminish cross-domain distribution difference. They are able to greatly enhance the performance on target classification tasks. GAN (Generative Adversarial Networks) loss is widely used in adversarial adaptation learning methods to reduce a across-domain distribution difference. However, it becomes difficult to decline such distribution difference if generator or discriminator in GAN fails to work as expected and degrades its performance. To solve such cross-domain classification problems, an adaptation algorithm and system called as Generative Adversarial Distribution Matching (GADM) is implemented. In GADM, the objective function is improved by taking cross-domain discrepancy distance into consideration, and further minimize the difference through the competition between the generator and discriminator, thereby greatly decreasing the cross-domain distribution difference. Even when the performance of its generator or discriminator degrades, GADM is capable of decreasing the cross-domain distribution difference. The GADM algorithm and system employs a single GAN framework so as to achieve faster domain adaption with less computation resource. Specially, GADM transfers target data distribution to source one to keep accurate label dependence information, which ensures high accuracy and stability of source classifier and thus achieves better classification performance on target data.

System for fast and accurate visual domain adaptation

To ensure photovoltaic (PV) panels at a PV plant constantly operate in an ideal state, an unsupervised system and method of intelligent performance evaluation and data-driven fault detection is used. The system and method enables engineers to check PV panels in time and implement timely maintenance. Monitored data are classified into three subsets: ideal period A, transition period S, and downturn period B. Based on A and B data, two regression prediction models are built which are tree-based and fit the non-continuous PV data well. Real-time measured power is compared with upper and lower reference baselines derived from the two predictive models, respectively. Using threshold ranges, the system and method achieves the instantaneous performance monitoring of PV power generation, and provides failure identification and operation and maintenance (O&M) suggestions to engineers.

Monitoring and fault detection method and system for photovoltaic plants

Soft sensing of nonlinear and multimode industrial processes given a limited number of labeled data samples is disclosed. Methods include a semi-supervised probabilistic density-based regression approach, called Semi-supervised Weighted Gaussian Regression (SWGR). In SWGR, different weights are assigned to each training sample based on their similarities to a query sample. Then a local weighted Gaussian density is built for capturing the joint probability of historical samples around the query sample. The training process of parameters in SWGR incorporates both labeled and unlabeled data samples via a maximum likelihood estimation algorithm. In this way, the soft sensor model is able to approximate the nonlinear mechanics of input and output variables and remedy the insufficiency of labeled samples. At last, the output prediction as well as the uncertainty of prediction can be obtained by the conditional distribution.

Growing community of inventors

Shanghai, China

Qi Kang