Search

Your search keyword '"Li, Xinglin"' showing total 179 results
Start Over Author "Li, Xinglin" Search Limiters Available in Library Collection
179 results on '"Li, Xinglin"'

1. Benchmarking Sub-Genre Classification For Mainstage Dance Music

Author

Shu, Hongzhi, Li, Xinglin, Jiang, Hongyu, Fu, Minghao, and Li, Xinyu

Subjects
Computer Science - Sound, Computer Science - Artificial Intelligence, Computer Science - Multimedia, I.2.1
Abstract

Music classification, with a wide range of applications, is one of the most prominent tasks in music information retrieval. To address the absence of comprehensive datasets and high-performing methods in the classification of mainstage dance music, this work introduces a novel benchmark comprising a new dataset and a baseline. Our dataset extends the number of sub-genres to cover most recent mainstage live sets by top DJs worldwide in music festivals. A continuous soft labeling approach is employed to account for tracks that span multiple sub-genres, preserving the inherent sophistication. For the baseline, we developed deep learning models that outperform current state-of-the-art multimodel language models, which struggle to identify house music sub-genres, emphasizing the need for specialized models trained on fine-grained datasets. Our benchmark is applicable to serve for application scenarios such as music recommendation, DJ set curation, and interactive multimedia, where we also provide video demos. Our code is on \url{https://anonymous.4open.science/r/Mainstage-EDM-Benchmark/}., Comment: Submitted to ICASSP 2025

Published
2024

2. Defense Against Syntactic Textual Backdoor Attacks with Token Substitution

Author

Li, Xinglin, He, Xianwen, Li, Yao, and Cheng, Minhao

Subjects
Computer Science - Computation and Language
Abstract

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same triggers as a certain class. Prior backdoor defense methods primarily target special token-based triggers, leaving syntax-based triggers insufficiently addressed. To fill this gap, this paper proposes a novel online defense algorithm that effectively counters syntax-based as well as special token-based backdoor attacks. The algorithm replaces semantically meaningful words in sentences with entirely different ones but preserves the syntactic templates or special tokens, and then compares the predicted labels before and after the substitution to determine whether a sentence contains triggers. Experimental results confirm the algorithm's performance against these two types of triggers, offering a comprehensive defense strategy for model integrity.

Published
2024

3. BRIEDGE: EEG-Adaptive Edge AI for Multi-Brain to Multi-Robot Interaction

Author

Ouyang, Jinhui, Wu, Mingzhu, Li, Xinglin, Deng, Hanhui, and Wu, Di

Subjects
Electrical Engineering and Systems Science - Signal Processing, Computer Science - Artificial Intelligence, Computer Science - Human-Computer Interaction, Computer Science - Machine Learning, Computer Science - Robotics
Abstract

Recent advances in EEG-based BCI technologies have revealed the potential of brain-to-robot collaboration through the integration of sensing, computing, communication, and control. In this paper, we present BRIEDGE as an end-to-end system for multi-brain to multi-robot interaction through an EEG-adaptive neural network and an encoding-decoding communication framework, as illustrated in Fig.1. As depicted, the edge mobile server or edge portable server will collect EEG data from the users and utilize the EEG-adaptive neural network to identify the users' intentions. The encoding-decoding communication framework then encodes the EEG-based semantic information and decodes it into commands in the process of data transmission. To better extract the joint features of heterogeneous EEG data as well as enhance classification accuracy, BRIEDGE introduces an informer-based ProbSparse self-attention mechanism. Meanwhile, parallel and secure transmissions for multi-user multi-task scenarios under physical channels are addressed by dynamic autoencoder and autodecoder communications. From mobile computing and edge AI perspectives, model compression schemes composed of pruning, weight sharing, and quantization are also used to deploy lightweight EEG-adaptive models running on both transmitter and receiver sides. Based on the effectiveness of these components, a code map representing various commands enables multiple users to control multiple intelligent agents concurrently. Our experiments in comparison with state-of-the-art works show that BRIEDGE achieves the best classification accuracy of heterogeneous EEG data, and more stable performance under noisy environments.

Published
2024

4. HAIFIT: Human-to-AI Fashion Image Translation

Author

Jiang, Jianan, Li, Xinglin, Yu, Weiren, and Wu, Di

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

In the realm of fashion design, sketches serve as the canvas for expressing an artist's distinctive drawing style and creative vision, capturing intricate details like stroke variations and texture nuances. The advent of sketch-to-image cross-modal translation technology has notably aided designers. However, existing methods often compromise these sketch details during image generation, resulting in images that deviate from the designer's intended concept. This limitation hampers the ability to offer designers a precise preview of the final output. To overcome this challenge, we introduce HAIFIT, a novel approach that transforms sketches into high-fidelity, lifelike clothing images by integrating multi-scale features and capturing extensive feature map dependencies from diverse perspectives. Through extensive qualitative and quantitative evaluations conducted on our self-collected dataset, our method demonstrates superior performance compared to existing methods in generating photorealistic clothing images. Our method excels in preserving the distinctive style and intricate details essential for fashion design applications. In addition, our method also has obvious advantages in model training and inference speed, contributing to reducing designers' time costs and improving design efficiency., Comment: 10 pages,8 figures

Published
2024

5. EXGC: Bridging Efficiency and Explainability in Graph Condensation

Author

Fang, Junfeng, Li, Xinglin, Sui, Yongduo, Gao, Yuan, Zhang, Guibin, Wang, Kun, Wang, Xiang, and He, Xiangnan

Subjects
Computer Science - Machine Learning
Abstract

Graph representation learning on vast datasets, like web data, has made significant strides. However, the associated computational and storage overheads raise concerns. In sight of this, Graph condensation (GCond) has been introduced to distill these large real datasets into a more concise yet information-rich synthetic graph. Despite acceleration efforts, existing GCond methods mainly grapple with efficiency, especially on expansive web data graphs. Hence, in this work, we pinpoint two major inefficiencies of current paradigms: (1) the concurrent updating of a vast parameter set, and (2) pronounced parameter redundancy. To counteract these two limitations correspondingly, we first (1) employ the Mean-Field variational approximation for convergence acceleration, and then (2) propose the objective of Gradient Information Bottleneck (GDIB) to prune redundancy. By incorporating the leading explanation techniques (e.g., GNNExplainer and GSAT) to instantiate the GDIB, our EXGC, the Efficient and eXplainable Graph Condensation method is proposed, which can markedly boost efficiency and inject explainability. Our extensive evaluations across eight datasets underscore EXGC's superiority and relevance. Code is available at https://github.com/MangoKiller/EXGC.

Published
2024

6. Transcription factor ZmNAC59 regulates plant salt resistance in Zea mays L.

Author

ZHANG Yuhan, LI Xinglin, LIU Lijun, FU Jingye, and WANG Qiang

Subjects
maize, transcription factors, salt stress, ion transport, Biology (General), QH301-705.5, Botany, QK1-989
Abstract

[ Objective ] The NAC transcription factor family is a class of transcription factors that is widely studied in plants. It plays an important role in regulating plant growth and development and responding to abiotic stress. Maize is one of the three major food crops , which faces various adverse stresses in growth and development. Salt stress is one of the main environmental factors limiting crop growth and produc- tion. Therefore , it is of great significance to identify maize salt resistance genes and analyze their salt re- sistance mechanism for breeding stress-resistant maize varieties. [ Methods ] This study cloned the maize transcription factor ZmNAC59 and analyzed its conserved domain and phylogenetic relationship using bioinformatics methods. The expression pattern of the gene in leaves under NaCl and MeJA treatments was analyzed using the quantitative real-time PCR method. The stable transgenic system was used to het- erologously express the gene in Arabidopsis thaliana for phenotype observation. At the same time , virus- induced silencing technology was used to silence the gene in maize , followed by phenotype observation un- der salt stress and enzyme activity detection. [ Results ] The qRT-PCR results showed that ZmNAC59 was up-regulated by NaCl and MeJA treatments. After virus-induced silencing of ZmNAC59 , the silenced strains were more sensitive to salt stress and accumulated more ROS. After over expression of ZmNAC59 in A . thaliana , the over expression lines had higher survival rate , less accumulation of ROS , and lower Na + / K + ratios under salt stress , indicating that ZmNAC59 , as a positive regulator of salt stress , can im- prove plant salt resistance by regulating ion homeostasis. qRT-PCR results showed that Na + and K + transport related genes were significantly up-regulated in A . thaliana overexpression lines. After transient expression of ZmNAC59 in maize protoplasts , the expression of ZmSOS1 , ZmNHX1 , and ZmNHX7 were significantly up-regulated after salt treatment. The Dual-LUC experiment showed that ZmSOS1 was the target gene of ZmNAC59. [ Conclusion ] This study finds that ZmNAC59 activates ZmSOS1 promoter and regulates its expression to promote ion transport under salt stress , thereby improving plant salt resist- ance. This provides a basis for the screening of maize stress resistant genes and variety cultivation.

Published
2024
Full Text
View/download PDF

18. Status and Influencing Factors of HIV/AIDS Patients Co-infected with Hepatitis C Virus in Guizhou

Author

Xiucheng YANG, Zhangping HONG, Qing LIU, Yong HU, Jie LI, Xinglin YANG

Subjects
hiv infections, acquired immunodeficiency syndrome, hepatitis c virus, hepatitis c, root cause analysis, guizhou, Medicine
Abstract

Background The status of patients with HIV/AIDS co-infected with HCV considerably varies in different parts of China. The co-infection of HIV and HCV accelerates the clinical progress of the disease, thereby reducing the patients' quality of life and exacerbating the occurrence of death. Currently, there are relatively few studies on patients with HIV/AIDS co-infected with HCV in Guizhou. Objective To analyze the status of patients with HIV/AIDS co-infected with HCV in Guizhou and its influencing factors and consequently provide basis for its early detection, diagnosis, and treatment. Methods The cases included in this study were a cohort of HIV/AIDS patients who received antiviral therapy (ART) in the public health rescue center of Guangzhou from March 2006 to December 2020. Finally, 3 084 patients who met the study requirements were included. Patients' sex, age, ethnicity, education level, occupation, marital status, route of infection, year of diagnosis, and CD4+ T-lymphocytes before ART and anti HCV levels were collected. Multivariate Logistic regression model were used to identify influencing factors of patients with HIV/AIDS co-infected with HCV. Results Among the 3 084 patients with HIV/AIDS, 202 were co-infected with HCV, and the co-infection rate was 6.55%. There were significant differences in HCV infection rates among patients with HIV/AIDS of different age groups, education levels, occupations, route of infection (P0.05) . The prevalence of HCV infection among HIV/AIDS patients tended to decrease with increasing year of diagnosis and increasing levels of CD4+ T lymphocytes (P

Published
2022
Full Text
View/download PDF

22. HAIFIT: Human-Centered AI for Fashion Image Translation

Author

Jiang, Jianan, Li, Xinglin, Yu, Weiren, Wu, Di, Jiang, Jianan, Li, Xinglin, Yu, Weiren, and Wu, Di

Abstract

In the realm of fashion design, sketches serve as the canvas for expressing an artist's distinctive drawing style and creative vision, capturing intricate details like stroke variations and texture nuances. The advent of sketch-to-image cross-modal translation technology has notably aided designers. However, existing methods often compromise these sketch details during image generation, resulting in images that deviate from the designer's intended concept. This limitation hampers the ability to offer designers a precise preview of the final output. To overcome this challenge, we introduce HAIFIT, a novel approach that transforms sketches into high-fidelity, lifelike clothing images by integrating multi-scale features and capturing extensive feature map dependencies from diverse perspectives. Through extensive qualitative and quantitative evaluations conducted on our self-collected dataset, our method demonstrates superior performance compared to existing methods in generating photorealistic clothing images. Our method excels in preserving the distinctive style and intricate details essential for fashion design applications., Comment: 8 pages,8 figures

Published
2024

25. A Linearized Model of FID Signal for Increasing Proton Magnetometer Precision

Author

Tan Chao, Fu Ruijie, Wu Chenguang, and Li Xinglin

Subjects
proton magnetometer, fid signal, frequency measurement, trigger time error, least square, Mathematics, QA1-939
Abstract

A linearized model of frequency measurement for the Free Induction Decay (FID) signal is proposed to increase the Proton Magnetometer (PM) precision. First, the nonlinear model of frequency measurement is set up according to the characteristic of the FID signal. Then, according to the error analysis of the MCFM method, the model is linearized on the condition of precision requirement. Furthermore, to reduce the nonlinear error caused by approximate treatment and the trigger time error caused by the random noise, the Least Squares (LS) method is adopted to estimate the slope of the linearized model, and the frequency to be measured is the inverse of the slope. Finally, a PM Prototype is made to verify the effectiveness of the proposed method. Experimental results show that the precision of frequency measurement is obviously increased if the proposed method is adopted for the noised sine signal. Moreover, the RMSD and the NPSD of magnetic-field measurement are about 0.13 nT and 80 pT/Hz1/2, respectively if the proposed method is adopted by PM, which is better than the comparison method.

Published
2020
Full Text
View/download PDF

26. S-Trimer, a COVID-19 subunit vaccine candidate, induces protective immunity in nonhuman primates

Author

Liang, Joshua G., Su, Danmei, Song, Tian-Zhang, Zeng, Yilan, Huang, Weijin, Wu, Jinhua, Xu, Rong, Luo, Peiwen, Yang, Xiaofang, Zhang, Xiaodong, Luo, Shuangru, Liang, Ying, Li, Xinglin, Huang, Jiaju, Wang, Qiang, Huang, Xueqin, Xu, Qingsong, Luo, Mei, Huang, Anliang, Luo, Dongxia, Zhao, Chenyan, Yang, Fan, Han, Jian-Bao, Zheng, Yong-Tang, and Liang, Peng

Published
2021
Full Text
View/download PDF

28. Characterization of CCoV-HuPn-2018 spike protein-mediated viral entry

Author

Liu, Yongmei, primary, Chen, Danying, additional, Wang, Yuanyuan, additional, Li, Xinglin, additional, Qiu, Yaruo, additional, Zheng, Mei, additional, Song, Yanjun, additional, Li, Guoli, additional, Song, Chuan, additional, Liu, Tingting, additional, Zhang, Yuanyuan, additional, Guo, Ju-Tao, additional, Lin, Hanxin, additional, and Zhao, Xuesen, additional

Published
2023
Full Text
View/download PDF

33. Efficient catalytic reduction of dyes by single or agglomerated nano‑silver functionalized wood and hydrodynamic simulation of wood channels

Author

Zheng, Guanfeng, Li, Xinglin, Song, Chaoyun, Wang, Lei, Li, Zhiyu, Zhang, Yuchun, Fu, Peng, Zheng, Guanfeng, Li, Xinglin, Song, Chaoyun, Wang, Lei, Li, Zhiyu, Zhang, Yuchun, and Fu, Peng

Abstract

Wood has a multi-scale pore structure, creating conditions for the development of new water purification materials. However, the adsorption capacity of wood for dyes is always limited, so this study combines the unique structure of wood with Ag nanoparticles (NPs) to achieve efficient catalytic reduction of dyes, harnessing the advantages of both. Ag/wood composite filtration materials with different Ag contents were prepared by hydrothermal method and vacuum impregnation. The results showed that with the increase of Ag content, the interaction between metal and wood channels and the degradation performance of Ag/wood composite materials exhibited a volcano-shaped trend. The contact area between Ag NPs and dye molecules plays a key role in the degradation of dye. The load phenomenon and internal flow state were discussed in detail by means of hydrodynamic simulation. Ag0.05/wood composite made silver nanoparticles and dye molecules reach a high balance and reduction degree. Therefore, Ag0.05/wood composites showed the highest catalytic reduction efficiency and great stability during the degradation of dyes, with a degradation efficiency of up to 96.9 %. The novelty of this study lies in the detailed description of the electron transfer process and mechanism of Ag NPs as a relay during MB degradation.

Published
2023

34. Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Training

Author

Li, Xinglin, Wang, Kun, Deng, Hanhui, Liang, Yuxuan, Wu, Di, Li, Xinglin, Wang, Kun, Deng, Hanhui, Liang, Yuxuan, and Wu, Di

Abstract

In this paper, we study the \textit{graph condensation} problem by compressing the large, complex graph into a concise, synthetic representation that preserves the most essential and discriminative information of structure and features. We seminally propose the concept of Shock Absorber (a type of perturbation) that enhances the robustness and stability of the original graphs against changes in an adversarial training fashion. Concretely, (I) we forcibly match the gradients between pre-selected graph neural networks (GNNs) trained on a synthetic, simplified graph and the original training graph at regularly spaced intervals. (II) Before each update synthetic graph point, a Shock Absorber serves as a gradient attacker to maximize the distance between the synthetic dataset and the original graph by selectively perturbing the parts that are underrepresented or insufficiently informative. We iteratively repeat the above two processes (I and II) in an adversarial training fashion to maintain the highly-informative context without losing correlation with the original dataset. More importantly, our shock absorber and the synthesized graph parallelly share the backward process in a free training manner. Compared to the original adversarial training, it introduces almost no additional time overhead. We validate our framework across 8 datasets (3 graph and 5 node classification datasets) and achieve prominent results: for example, on Cora, Citeseer and Ogbn-Arxiv, we can gain nearly 1.13% to 5.03% improvements compare with SOTA models. Moreover, our algorithm adds only about 0.2% to 2.2% additional time overhead over Flicker, Citeseer and Ogbn-Arxiv. Compared to the general adversarial training, our approach improves time efficiency by nearly 4-fold.

Published
2023

35. A Comparative Study on the Examination System of CPA in the AI Evelopment Background Take China, Australia, the United States, the United Kingdom, Japan, and Germany as examples

Author

Zhang Chao, Li Xinglin, Qi Yuzhu, He Yitong, Niu Jingwei, Xu Yiyi, and Zhang Jiaying

Subjects
Environmental sciences, GE1-350
Abstract

At present, the globalization of the world economy continues to intensify, and the pace of technological modernization is accelerating. Artificial intelligence methods such as big data and financial sharing are gradually replacing traditional working methods in all walks of life, and the accounting industry is no exception. Under the dual impact of globalization and the development of artificial intelligence, the demand for training international compound accounting professionals is large and increasing, "CPA examination system" as one of the most authoritative examinations in the field of accounting, its matching with the current environment is particularly important. Starting from the current status of CPA examination, the author has made an in-depth investigation and study on the CPA examination systems in many countries including China, the United States, Britain, Japan, Germany and Australia by consulting a large number of relevant literature. Meanwhile, they systematically analyzed the CPA examination systems in various countries from four dimensions: examination organization, examination threshold, examination cycle and examination subjects, explored the similarities and differences of CPA examination systems in the world's mainstream countries, and summarized the common problems and the advantages that can be used for reference, which has practical significance for the design and update of the CPA examination system in China. At the same time, it provides reference significance for improving the professional quality of accounting personnel and accelerating the pace of changing the functions of accounting personnel.

Published
2021
Full Text
View/download PDF

36. Brave the Wind and the Waves: Discovering Robust and Generalizable Graph Lottery Tickets

Author

Wang, Kun, Liang, Yuxuan, Li, Xinglin, Li, Guohao, Ghanem, Bernard, Zimmermann, Roger, Zhou, Zhengyang, Yi, Huahui, Zhang, Yudong, and Wang, Yang

Abstract

The training and inference of Graph Neural Networks (GNNs) are costly when scaling up to large-scale graphs. Graph Lottery Ticket (GLT) has presented the first attempt to accelerate GNN inference on large-scale graphs by jointly pruning the graph structure and the model weights. Though promising, GLT encounters robustness and generalization issues when deployed in real-world scenarios, which are also long-standing and critical problems in deep learning ideology. In real-world scenarios, the distribution of unseen test data is typically diverse. We attribute the failures on out-of-distribution (OOD) data to the incapability of discerning causal patterns, which remain stable amidst distribution shifts. In traditional spase graph learning, the model performance deteriorates dramatically as the graph/network sparsity exceeds a certain high level. Worse still, the pruned GNNs are hard to generalize to unseen graph data due to limited training set at hand. To tackle these issues, we propose the Resilient Graph Lottery Ticket (RGLT) to find more robust and generalizable GLT in GNNs. Concretely, we reactivate a fraction of weights/edges by instantaneous gradient information at each pruning point. After sufficient pruning, we conduct environmental interventions to extrapolate potential test distribution. Finally, we perform last several rounds of model averages to further improve generalization. We provide multiple examples and theoretical analyses that underpin the universality and reliability of our proposal. Further, RGLT has been experimentally verified across various independent identically distributed (IID) and out-of-distribution (OOD) graph benchmarks.

Published
2024
Full Text
View/download PDF

38. Hypoglycaemic effect of coixan from Coix seeds on mice

Author

Yin Yanan, Yang Weiwei, Jiao Yingliang, Yang He, and Li Xinglin

Subjects
Environmental sciences, GE1-350
Abstract

Diabetes is an endocrine system disease characterized by high morbidity, high prevalence, and high mortality. Although the traditional medicine for treating diabetes has a good effect, its side effects are also large. Traditional Chinese medicine has also achieved good therapeutic effects in the treatment of diabetes, and the side effects of Chinese medicine are small. Coix is a medicinal and edible plant. It is used as food and medicine alone or in combination with other herbs in the early days. Its seeds have become one of the most popular Chinese herbal medicines. The coixan was extracted from Coix seed, and it was administered to diabetic mice. After five weeks of treatment, it was found to have some role in hypoglycemic. This study provides a good application prospect for Chinese medicine treatment of diabetes.

Published
2019
Full Text
View/download PDF

43. A Linearized Model of FID Signal for Increasing Proton Magnetometer Precision

Author

Chao Tan, Ruijie Fu, Wu Chenguang, and Li Xinglin

Subjects
Physics, proton magnetometer, trigger time error, 020208 electrical & electronic engineering, Biomedical Engineering, 020206 networking & telecommunications, 02 engineering and technology, Signal, Computational physics, least square, fid signal, Proton magnetometer, Control and Systems Engineering, QA1-939, 0202 electrical engineering, electronic engineering, information engineering, frequency measurement, Instrumentation, Mathematics
Abstract

A linearized model of frequency measurement for the Free Induction Decay (FID) signal is proposed to increase the Proton Magnetometer (PM) precision. First, the nonlinear model of frequency measurement is set up according to the characteristic of the FID signal. Then, according to the error analysis of the MCFM method, the model is linearized on the condition of precision requirement. Furthermore, to reduce the nonlinear error caused by approximate treatment and the trigger time error caused by the random noise, the Least Squares (LS) method is adopted to estimate the slope of the linearized model, and the frequency to be measured is the inverse of the slope. Finally, a PM Prototype is made to verify the effectiveness of the proposed method. Experimental results show that the precision of frequency measurement is obviously increased if the proposed method is adopted for the noised sine signal. Moreover, the RMSD and the NPSD of magnetic-field measurement are about 0.13 nT and 80 pT/Hz1/2, respectively if the proposed method is adopted by PM, which is better than the comparison method.

Published
2020

44. Natural Product Evodiamine with Borate Trigger Unit: Discovery of Potent Antitumor Agents against Colon Cancer

Author

Dan Liu, Li Xinglin, Shanchao Wu, Chunquan Sheng, Guoqiang Dong, Zonglin Ma, and Shuqiang Chen

Subjects
inorganic chemicals, chemistry.chemical_classification, Reactive oxygen species, Natural product, 010405 organic chemistry, Cell growth, Organic Chemistry, 01 natural sciences, Biochemistry, digestive system diseases, 0104 chemical sciences, 010404 medicinal & biomolecular chemistry, chemistry.chemical_compound, chemistry, Apoptosis, In vivo, Evodiamine, Drug Discovery, Cancer cell, Cancer research, Boronic acid
Abstract

[Image: see text] In order to improve the antitumor potency of the natural product evodiamine, novel boron-containing evodiamine derivatives were designed by incorporating boronic acid and boronate as trigger units. Boronate derivative 13a could be triggered by reactive oxygen species (ROS) in the HCT116 colon cancer cell line and showed excellent antitumor activity in vitro and in vivo. It induced apoptosis in HCT116 cancer cells in a dose-dependent manner and cell growth arrest at the G2 phase.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results