Qiang ZHAO

Dr. Qiang ZHAO

Shandong University, Jinan, Shandong, China
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 March 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZQZhenzhen Quan
Zhenzhen Quan
QCQingshan Chen
Qingshan Chen
MZMoyan Zhang
Moyan Zhang
WHWeifeng Hu
Weifeng Hu
QZQiang ZHAO
Qiang ZHAO
Zhi LiuZhi Liu
Zhi Liu
The recognition prerformance of existing vision-based human action recognition (HAR) methods is greatly reduced in the case of low camera resolution or occlusion. Wearable sensors can provide complementary information to alleviate this problem. It is challenging to construct a robust HAR model using multimodal wearable-sensor data. In this paper, we propose a cross-Attention-based Multimodal fusion Wavelet Knowledge Distillation Network (MAWKDN) method to guide recognition from video data by acquiring complementary information from wearable sensors and reduce the noise effects through wavelet knowledge distillation, which improves the robustness of the model. A multi-attention dilated convolution kernel residual network including dilated convolution and an attention mechanism is constructed to extract features from various sensor modalities and fuse the various modal data through the cross-view attention method to acquire additional information from different modalities. To reduce the modal differences between different modalities of the teacher and student networks and acquire similar semantic knowledge, we learn the information between different modalities by constructing a graph structure of convolutional layer features, and computing the semantic preservation loss between the teacher and student networks. To reduce the influence of noise in the input data, we construct the loss of wavelet knowledge distillation, which transforms the image through the discrete wavelet transform and only retains the low frequency features to extract the useful information. The top-1 accuracy achieved on the UTD-MHAD (99.31%), Berkeley-MHAD (99.40%) and the F1-score on the MMAct (85.26% based on cross-session) dataset prove the superior performance of MAWKDN compared with the state-of-the-art HAR methods. Moreover, we demonstrate the robustness of the MAWKDN approach on the noise-added UTD-MHAD dataset.

30 April 2022 in Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
WHWeifeng Hu
Weifeng Hu
SZSiwen Zhao
Siwen Zhao
QZQiang ZHAO
Qiang ZHAO
HSHao Sun
Hao Sun
XHXifeng Hu
Xifeng Hu
LMLong Ma
Long Ma
With the development of smart justice in China, the Supreme People’s Court implements the system of compulsory retrieval for similar cases continuously and comprehensively, more and more judicial big data has been continuously disclosed, and the application of case retrieval is more extensive, and then, the accuracy of similar case search results needs to be urgently improved. Legal case retrieval is a special search task; for a given query case, it refers to the searching for similar cases. Different from traditional text search, legal case retrieval has different characteristics and greater challenges, for its query case is longer and more complex than common keyword queries and short article queries. In addition, the definition of dependencies between query cases and candidate cases differs from general dependencies based on text or topic. In order to solve these problems, we propose a method for similarity case retrieval based on the legal facts, and our model combine the topic distribution and legal entity facts to make the document representation vector more suitable for legal scenarios. At the same time, the method of paragraph aggregation based on BERT is used to encode context semantic information and solve the problem of long text. The experimental results show that our method is superior to the existing method.

18 January 2025 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
WWWei Wang
Wei Wang
YLYujie Lin
Yujie Lin
Pengjie RenPengjie Ren
Pengjie Ren
ZCZhumin Chen
Zhumin Chen
TSUNENORI MINETSUNENORI MINE
TSUNENORI MINE
YLYujun Li
Yujun Li
Sequential recommendation has attracted a lot of attention from both academia and industry, however the privacy risks associated with gathering and transferring users’ personal interaction data are often underestimated or ignored. Existing privacy-preserving studies are mainly applied to traditional collaborative filtering or matrix factorization rather than sequential recommendation. Moreover, these studies are mostly based on differential privacy or federated learning, which often lead to significant performance degradation, or have high requirements for communication. In this work, we address privacy-preserving from a different perspective. Unlike existing research, we capture collaborative signals of neighbor interaction sequences and directly inject indistinguishable items into the target sequence before the recommendation process begins, thereby increasing the perplexity of the target sequence. Even if the target interaction sequence is obtained by attackers, it is difficult to discern which ones are the actual user interaction records. To achieve this goal, we introduce a novel sequential recommender system called CoLlaborative-cOnfusion seqUential recommenDer (CLOUD) , which incorporates a collaborative confusion mechanism to modify the raw interaction sequences before conducting recommendation. Specifically, CLOUD first calculates the similarity between the target interaction sequence and other neighbor sequences to find similar sequences. Then, CLOUD considers the shared representation of the target sequence and similar sequences to determine the operation to be performed: keep, delete, or insert. A copy mechanism is designed to make items from similar sequences have a higher probability to be inserted into the target sequence. Finally, the modified sequence is used to train the recommender and predict the next item. We conduct extensive experiments on three benchmark datasets. The experimental results show that CLOUD achieves a maximum modification rate of 66.57% on interaction sequences and obtains over 99% recommendation accuracy compared to the state-of-the-art sequential recommendation methods. This proves that CLOUD can effectively protect user privacy at minimal recommendation performance cost, which provides a new solution for privacy-preserving for sequential recommendation. Our implementation is available at https://github.com/weiwang0927/CLOUD .

13 January 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
GSGuoqiang Sun
Guoqiang Sun
XQXiaoyan Qi
Xiaoyan Qi
QZQiang ZHAO
Qiang ZHAO
WWWei Wang
Wei Wang
YLYujun Li
Yujun Li
This study proposes an efficient method for computing State Vectors in Sequence-to-Sequence (SVSeq2Seq) architecture to improve the performance of sequence data forecasting, which associates each element with other elements instead of relying only on nearby elements. First, the dependency between two elements is adaptively captured by calculating the relative importance between hidden layers. Second, tensor train decomposition is used to address the issue of dimensionality catastrophe. Third, we further select seven instantiated baseline models for data prediction and compare them with our proposed model on six real-world datasets. The results show that the Mean Square Error (MSE) and Mean Absolute Error (MAE) of our SVSeq2Seq model exhibit significant advantages over the other seven baseline models in predicting the three datasets, i.e., weather, electricity, and PEMS, with MSE/MAE values as low as 0.259/0.260, 0.186/0.285 and 0.113/0.222, respectively. Furthermore, the ablation study demonstrates that the SVSeq2Seq model possesses distinct advantages in sequential forecasting tasks. It is observed that replacing SVSeq2Seq with LPRcode and NMTcode resulted in an increase under an MSE of 18.05 and 10.11 times, and an increase under an MAE of 16.54 and 9.8 times, respectively. In comparative experiments with support vector machines (SVM) and random forest (RF), the performance of the SVSeq2Seq model is improved by 56.88 times in the weather dataset and 73.78 times in the electricity dataset under the MSE metric, respectively. The above experimental results demonstrate both the exceptional rationality and versatility of the SVSeq2Seq model for data forecasting.

29 June 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
QZQiang ZHAO
Qiang ZHAO
RGRundong Guo
Rundong Guo
XFXiaowei Feng
Xiaowei Feng
WHWeifeng Hu
Weifeng Hu
SZSiwen Zhao
Siwen Zhao
YCYewen Cao
Yewen Cao
Legal judgement prediction (LJP) is a crucial part of legal AI, and its goal is to predict the outcome of a case based on the information in the description of criminal facts. This paper proposes a decision prediction method based on causal inference and a multi-expert FTOPJUDGE mechanism. First, a causal inference algorithm was adopted to process unstructured text. This process did not require very much manual intervention to better mine the information in the text. Then, a neural network dedicated to each task was set up, and a neural network that simultaneously served multiple tasks was also set up. Finally, the pre-trained language model Lawformer was used to provide knowledge for downstream tasks. By using the public data set CAIL2018 and comparing it with current mainstream decision prediction models, it was shown that the model significantly improved the performance of downstream tasks and achieved great improvements in multiple indicators. Through ablation experiments, the effectiveness and rationality of each module of the proposed model were verified. The method proposed in this study achieved reasonably good performance in legal judgment prediction, which provides a promising solution for legal judgment prediction.

10 November 2022 in Zhonghua Yi Xue Yi Chuan Xue Za Zhi = Zhonghua Yixue Yichuanxue Zazhi = Chinese Journal of Medical Genetics
Verified
Journal Article
Closed access
QZQiang ZHAO
Qiang ZHAO
Shuxiong ChenShuxiong Chen
Shuxiong Chen
HSHailin Sun
Hailin Sun
WYWanling Yang
Wanling Yang
BBBo Ban
Bo Ban
To develop a multiplex PCR method for a rapid detection of Y chromosome-specific sequences in patients with Turner syndrome. Nine genes were selected from various regions of the Y chromosome for designing the primers, which included SRY, TBL1Y, TSPY on the short arm of the Y chromosome, DDX3Y, HSFY1, RPS4Y2 and CDY1 on the long arm of Y chromosome and SHOX in the short arm and SPRY3 in the long arm of the pseudoautosomal region (PAR) of X and Y chromosomes. A multiplex PCR method for the nine genes in Y chromosome was established and optimized. The sensitivity was tested by using different amounts of genomic DNA. A total of 36 patients with Turner syndrome and a patient with male dwarfism with karyotype of 46, X, +mar were examined by the multiplex PCR method for the existence of materials from the Y chromosome. The optimization results of the multiplex PCR reaction system (50 μL) showed that when the final concentration of upstream and downstream of each pair of primers was 0.1 μM, the multiplex PCR reaction of the 9 pairs of primers clearly amplified the target with the expected band size, and there was no non-specific amplification. The bands were clearly visible when the amount of genomic DNA in the multiple PCR reaction system was as low as 1 ng. By using the method, we have examined the 36 patients with Turner syndrome. One patient with Turner syndrome with karyotype of 45,X[40]/47XYY[21] amplified specific seven genes on Y chromosome, 35 patients with Turner syndrome amplified only two target genes SHOX and SPRY3, but not the other seven specific genes on the Y chromosome, which was in keeping with the clinical manifestations of such patients. This study established a multiplex PCR reaction system with nine genes, which can quickly and accurately screen Y chromosome materials in patients with Turner syndrome. It has the advantages of low cost, simple operation, high specificity and rapid turn-around time, and can be used to detect Turner syndrome patients with Y chromosome material in time. The method has provided a diagnostic basis for preventive gonad resection to prevent malignant gonadal tumors.