Search

Your search keyword '"LIU Hanzhou"' showing total 214 results
Start Over Author "LIU Hanzhou"
214 results on '"LIU Hanzhou"'

2. Progress in the application of water distillation for tritiated water separation

Author

ZHANG Shuya, YANG Qian, JIN Aiping, LIU Hanzhou, and WANG Shuao

Subjects
tritiated water, water distillation, hydrogen isotope separation, packing, height equivalent theoretical plate, Nuclear engineering. Atomic power, TK9001-9401
Abstract

Large volumes of water containing tritium are generated during the operation, decommissioning, and incident-management of nuclear installations and related facilities, and are expected to increase with the ongoing expansion of nuclear power generation. If released into the environment, this water could pose a substantial environmental threat to living organisms. However, conventional isotope separation techniques, such as cryogenic distillation and catalytic exchange, are inadequate for efficiently isolating significant quantities of low-level tritiated water because of the complex machinery and excessive energy required, and the potential for hydrogen-gas detonation. In contrast, water distillation (WD), as a traditional technology, has the unique advantages of simple operation, no corrosive and toxic substances, and no hydrogen explosion risk, but problems of small separation coefficient and low efficiency always exist in this technique. However, the separation effect of WD can be effectively improved by improving the process variables in the process of WD, such as temperature, distillation column diameter, and packing dimensions, so as to adapt WD to the separation of industrial tritiated water. This study provides a thorough exposition of the basic principles and distinctive features of water distillation and examines the effect of various operational parameters on separation efficiency to adapt the process for the industrial separation of tritiated water. The impact of various process variables on the separation efficiency of tritiated water via distillation was investigated, and results show that optimizing these variables can markedly improve the separation efficiency of water distillation. In particular, decreasing the dimensions of the packing material or altering its properties can lead to higher separation factors and lower residual tritiated water concentration. These findings suggest that water distillation can be used for the separation of tritiated water. By optimizing its operational parameters, water distillation can become a viable method for the industrial separation of tritiated water and is expected to play a significant role in this field in the future.

Published
2023
Full Text
View/download PDF

3. Behavior-Dependent Linear Recurrent Units for Efficient Sequential Recommendation

Author

Liu, Chengkai, Lin, Jianghao, Liu, Hanzhou, Wang, Jianling, and Caverlee, James

Subjects
Computer Science - Information Retrieval
Abstract

Sequential recommender systems aims to predict the users' next interaction through user behavior modeling with various operators like RNNs and attentions. However, existing models generally fail to achieve the three golden principles for sequential recommendation simultaneously, i.e., training efficiency, low-cost inference, and strong performance. To this end, we propose RecBLR, an Efficient Sequential Recommendation Model based on Behavior-Dependent Linear Recurrent Units to accomplish the impossible triangle of the three principles. By incorporating gating mechanisms and behavior-dependent designs into linear recurrent units, our model significantly enhances user behavior modeling and recommendation performance. Furthermore, we unlock the parallelizable training as well as inference efficiency for our model by designing a hardware-aware scanning acceleration algorithm with a customized CUDA kernel. Extensive experiments on real-world datasets with varying lengths of user behavior sequences demonstrate RecBLR's remarkable effectiveness in simultaneously achieving all three golden principles - strong recommendation performance, training efficiency, and low-cost inference, while exhibiting excellent scalability to datasets with long user interaction histories., Comment: Accepted to CIKM 2024

Published
2024

4. DeblurDiNAT: A Generalizable Transformer for Perceptual Image Deblurring

Author

Liu, Hanzhou, Li, Binghan, Liu, Chengkai, and Lu, Mi

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Although prior state-of-the-art (SOTA) deblurring networks achieve high metric scores on synthetic datasets, there are two challenges which prevent them from perceptual image deblurring. First, a deblurring model overtrained on synthetic datasets may collapse in a broad range of unseen real-world scenarios. Second, the conventional metrics PSNR and SSIM may not correctly reflect the perceptual quality observed by human eyes. To this end, we propose DeblurDiNAT, a generalizable and efficient encoder-decoder Transformer which restores clean images visually close to the ground truth. We adopt an alternating dilation factor structure to capture local and global blur patterns. We propose a local cross-channel learner to assist self-attention layers to learn short-range cross-channel relationships. In addition, we present a linear feed-forward network and a non-linear dual-stage feature fusion module for faster feature propagation across the network. Compared to nearest competitors, our model demonstrates the strongest generalization ability and achieves the best perceptual quality on mainstream image deblurring datasets with 3%-68% fewer parameters.

Published
2024

5. Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models

Author

Liu, Chengkai, Lin, Jianghao, Wang, Jianling, Liu, Hanzhou, and Caverlee, James

Subjects
Computer Science - Information Retrieval
Abstract

Sequential recommendation aims to estimate the dynamic user preferences and sequential dependencies among historical user behaviors. Although Transformer-based models have proven to be effective for sequential recommendation, they suffer from the inference inefficiency problem stemming from the quadratic computational complexity of attention operators, especially for long behavior sequences. Inspired by the recent success of state space models (SSMs), we propose Mamba4Rec, which is the first work to explore the potential of selective SSMs for efficient sequential recommendation. Built upon the basic Mamba block which is a selective SSM with an efficient hardware-aware parallel algorithm, we design a series of sequential modeling techniques to further promote model performance while maintaining inference efficiency. Through experiments on public datasets, we demonstrate how Mamba4Rec effectively tackles the effectiveness-efficiency dilemma, outperforming both RNN- and attention-based baselines in terms of both effectiveness and efficiency. The code is available at https://github.com/chengkai-liu/Mamba4Rec.

Published
2024

13. Real-World Image Deblurring via Unsupervised Domain Adaptation

Author

Liu, Hanzhou, Li, Binghan, Lu, Mi, Wu, Yucheng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Bebis, George, editor, Ghiasi, Golnaz, editor, Fang, Yi, editor, Sharf, Andrei, editor, Dong, Yue, editor, Weaver, Chris, editor, Leo, Zhicheng, editor, LaViola Jr., Joseph J., editor, and Kohli, Luv, editor

Published
2023
Full Text
View/download PDF

38. DeblurDiNAT: A Lightweight and Effective Transformer for Image Deblurring

Author

Liu, Hanzhou, Li, Binghan, Liu, Chengkai, Lu, Mi, Liu, Hanzhou, Li, Binghan, Liu, Chengkai, and Lu, Mi

Abstract

Blurry images may contain local and global non-uniform artifacts, which complicate the deblurring process and make it more challenging to achieve satisfactory results. Recently, Transformers generate improved deblurring outcomes than existing CNN architectures. However, the large model size and long inference time are still two bothersome issues which have not been fully explored. To this end, we propose DeblurDiNAT, a compact encoder-decoder Transformer which efficiently restores clean images from real-world blurry ones. We adopt an alternating dilation factor structure with the aim of global-local feature learning. Also, we observe that simply using self-attention layers in networks does not always produce good deblurred results. To solve this problem, we propose a channel modulation self-attention (CMSA) block, where a cross-channel learner (CCL) is utilized to capture channel relationships. In addition, we present a divide and multiply feed-forward network (DMFN) allowing fast feature propagation. Moreover, we design a lightweight gated feature fusion (LGFF) module, which performs controlled feature merging. Comprehensive experimental results show that the proposed model, named DeblurDiNAT, provides a favorable performance boost without introducing noticeable computational costs over the baseline, and achieves state-of-the-art (SOTA) performance on several image deblurring datasets. Compared to nearest competitors, our space-efficient and time-saving method demonstrates a stronger generalization ability with 3%-68% fewer parameters and produces deblurred images that are visually closer to the ground truth.

Published
2024

50. Metal–Organic Framework Based Thermoluminescence Dosimeter

Author

Yang, Qian, primary, Qin, Haoming, additional, Chen, Lixi, additional, Zhang, Shuya, additional, Mei, Sen, additional, Wu, Deli, additional, Yin, Yuchen, additional, Dai, Xing, additional, Shen, Nannan, additional, Tao, Ye, additional, Luan, Ni, additional, Jin, Aiping, additional, Wang, Yanlong, additional, Chai, Zhifang, additional, Sun, Liang, additional, Liu, Hanzhou, additional, and Wang, Shuao, additional

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results