Article
Engineering, Electrical & Electronic
Mahnoosh Tajmirriahi, Rahele Kafieh, Zahra Amini, Hossein Rabbani
Summary: The study implemented a lightweight convolutional AE network for mimicking the latest OCT image denoising method. The performance of the network was evaluated on various test data sets using visual inspection and quantitative metrics, confirming its good performance in removing speckle noise in OCT scans. The proposed network demonstrated generality, computational efficiency, and device independence, making it suitable for real-time, mobile applications.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Automation & Control Systems
Dingliang Chen, Yi Qin, Yi Wang, Jianghong Zhou
Summary: A novel quadratic function-based deep convolutional auto-encoder is proposed for constructing health indicators from raw bearing vibration signals, showing better performance than traditional data-driven health indicators through comparative experiments.
Article
Engineering, Electrical & Electronic
Yifei Ding, Peng Ding, Minping Jia
Summary: This article presents an RUL prediction method for rolling bearings based on a deep transfer auto-encoder. The method utilizes parameter transfer and feature representation transfer to fully utilize historical model and rapidly adapt to new operating conditions. A case study confirms the effectiveness of the proposed method in precision and accuracy compared to other machine learning models.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Computer Science, Artificial Intelligence
Mallikarjuna Reddy Ayaluri, Sudheer K. Reddy, Srinivasa Reddy Konda, Sudharshan Reddy Chidirala
Summary: Steganalysis is the process of analyzing and predicting the presence of hidden information in images. The current research method uses deep learning to effectively perform steganalysis tasks, but does not focus on the noises present in the images. The proposed research technique introduces Non-Gaussian Noise Aware Auto Encoder Convolutional Neural Network to improve the efficiency of steganalysis.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Hardware & Architecture
Yaonan Guan, Yunwen Xu, Yugeng Xi, Dewei Li
Summary: This paper proposes a method to enhance data feature extraction capabilities by introducing a feedback channel between the Variational Auto Encoder and the Gaussian process. The model addresses common mislabeling issues in unsupervised settings by selecting representative data and constructing a full-data Gaussian process model. By employing a Bayesian framework to guide data point displacement in the latent space, the model effectively discriminates between normal and abnormal data.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Kanae Oda, Ryota Kawamata, Shinji Wakao, Noboru Murata
Summary: The proposed approach combines gradient calculations in both high-dimensional design space and a low-dimensional latent space to search for more global pareto solution group in multi-objective optimization, using optimization results in the low-dimensional space as the initial value of the gradient calculation in the actual design space.
IEEE TRANSACTIONS ON MAGNETICS
(2021)
Article
Computer Science, Artificial Intelligence
B. A. Manjunatha, K. Aditya Shastry, E. Naresh, Piyush Kumar Pareek, Kadiri Thirupal Reddy
Summary: This research focuses on enhancing network intrusion detection by evaluating different auto-encoders. The proposed sparse deep denoising auto-encoder achieved an accuracy of over 96% based on reconstruction error, showing great potential for improved detection accuracy compared to existing methods.
Article
Environmental Sciences
Wei-Tao Zhang, Min Wang, Jiao Guo, Shun-Tian Lou
Summary: Accurate crop classification information is essential for agricultural monitoring and food security evaluation research. This study utilized multi-temporal PolSAR data and neural network techniques to enhance classification performance, showing promising results for practical application in agricultural monitoring and food security evaluation.
Article
Computer Science, Information Systems
Wenjuan Wang, Xuehui Du, Dibin Shan, Ruoxi Qin, Na Wang
Summary: This study utilizes deep learning to automatically extract essential feature representations in the cloud computing environment and designs a novel cloud intrusion detection system. By integrating deep learning and shallow learning techniques, it effectively reduces analytical overhead and achieves higher detection performance on intrusion detection evaluation datasets.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2022)
Article
Multidisciplinary Sciences
Mohsen Ghaderi Goran Abad, Mohammad Mahmoudi
Summary: The study successfully generated a vector beam with spatially-dependent polarization using Laguerre-Gaussian beams through nonlinear magneto-optical rotation. The polarization and intensity distributions of the vector beam can be controlled by changing the orbital angular momentum and radial index of the LG control field. Higher values of the radial index of the LG control field contribute to the generation of vector beams with highly spatially distributed polarization.
SCIENTIFIC REPORTS
(2021)
Article
Engineering, Multidisciplinary
Zilong Wang, Young-Jin Cha
Summary: This article proposes an unsupervised deep learning-based approach for structural damage detection, which utilizes a carefully designed deep auto-encoder and one-class support vector machine for extracting damage-sensitive features and detecting future damage. Experimental and numerical studies confirm the high accuracy and stability of the method in detecting structural damage.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Yan-Lin He, Lei Chen, Yuan Xu, Qun-Xiong Zhu, Shan Lu
Summary: In this article, a new distributed ESN model integrated with auto-encoder is proposed to solve the dimension disaster problem and collinearity issue in ESNs. The experimental results show that the proposed model achieves higher accuracy in soft sensor modeling for dynamic industrial processes.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Information Systems
Jyostna Devi Bodapati
Summary: This paper proposes a convolutional neural network architecture based on spatial attention for recognizing the severity level of diabetic retinopathy. The experimental results show that combining end-to-end training with attention mechanism can improve the performance of the model.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Construction & Building Technology
Zhandong Yuan, Shengyang Zhu, Chao Chang, Xuancheng Yuan, Qinglai Zhang, Wanming Zhai
Summary: An automatic detection algorithm for rail squats via vehicle axle box acceleration signal is proposed in this article. The validity and reliability of the method are verified through simulations and experiments. Comparative studies show that the elliptic envelope method is a better option for squat detection.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Geography, Physical
Xiaolong Wang, Haowen Yan, Liming Zhang, Xingang Zhang, Pengbo Li
Summary: This paper proposes an encryption algorithm for vector maps based on Gaussian random and Haar transform, which ensures the security of the maps and improves decryption efficiency.
JOURNAL OF SPATIAL SCIENCE
(2023)
Article
Automation & Control Systems
Zekui Lyu, Qingsong Xu, Limin Zhu
Summary: In this paper, a new piezoelectric-actuated biaxial compliant microgripper with long strokes is proposed for automatically gripping and rolling tiny rigid objects. The microgripper has been optimized structurally and its performance has been simulated using finite element analysis. Experimental results show that the developed microgripper has the capability to grasp and roll tiny rigid objects, making it promising for precision micromanipulation tasks such as optical fiber alignment.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Statistics & Probability
Runze Li, Kai Xu, Yeqing Zhou, Liping Zhu
Summary: In this article, we propose a novel test based on an aggregation of the marginal cumulative covariances to accommodate heteroscedasticity and high dimensionality in high-dimensional data. Our proposed test statistic is scale-invariance, tuning-free, and easy to implement, with established asymptotic normality under the null hypothesis. We find that our proposed test is much more powerful than existing competitors for covariates with heterogeneous variances, even under high-dimensional linear models, while maintaining high efficiency for homoscedastic covariates.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
Article
Psychology, Multidisciplinary
Sicheng Xiong, Yi Xu, Bin Zhang, Lihui Zhu, Jianhui Xie
Summary: This study identified three patterns of restrained eating in adolescents and found that these patterns were associated with interpersonal factors such as parental monitoring, deviant peer affiliation, and peer relationships. The results can inform targeted prevention and intervention strategies.
CURRENT PSYCHOLOGY
(2023)
Editorial Material
Multidisciplinary Sciences
Zenghui Xie, Fugui Xie, Limin Zhu, Xin-Jun Liu
Summary: Robotization, miniaturization, and portability are the new development trends in milling equipment for large-scale complex structures. The robotic mobile and mirror milling technology has made remarkable progress in practical production.
NATIONAL SCIENCE REVIEW
(2023)
Article
Automation & Control Systems
Peng Guo, Yang Zhang, Weiwei Huang, Nuodi Huang, Long Zhang, Limin Zhu
Summary: In this paper, a generalized reaching-law-based discrete-time integral sliding-mode controller is designed to achieve high output tracking accuracy and avoid significant control efforts for both matched and mismatched disturbances. By synthesizing a disturbance-related integral term based on disturbance decomposition, the proposed sliding surface differs from existing integral sliding surfaces and is crucial for disturbance attenuation. The proposed reaching law introduces an adaptive exponential term into the control gains, which allows for the integration of conventional RL-based DISMC and EC-based DISMC.
ASIAN JOURNAL OF CONTROL
(2023)
Article
Plant Sciences
Meiyu Sun, Li Zhu, Yanan Zhang, Ningning Liu, Jinzheng Zhang, Hui Li, Hongtong Bai, Lei Shi
Summary: This study created new germplasm resources of thyme through hybridization, developed SSR markers based on the whole-genome sequence of T. quinquecostatus, and screened the expression of monoterpene synthase genes in thyme. The results provide a strong foundation for the creation of new germplasm resources, construction of genetic linkage maps, and identification of quantitative trait loci (QTLs), and also help gain insight into the mechanism of monoterpenoid biosynthesis in thyme.
Article
Cell Biology
Ya-Lan Wei, Yu-Qing Lei, Zhou-Jie Ye, Xu-Dong Zhuang, Li-Ping Zhu, Xin-Rui Wang, Hua Cao
Summary: Bepridil, a commonly used medication for arrhythmia and heart failure, has been found to have toxic effects on rat myocardial cells and zebrafish embryos. The treatment with bepridil resulted in calcium overload, morphological abnormalities, and developmental abnormalities. RNA-seq analysis provided insights into the gene expression profiles and metabolic responses. This study evaluates the use of antiarrhythmic agents in prenatal heart patients.
CELL AND TISSUE RESEARCH
(2023)
Article
Automation & Control Systems
Li Hua, Nuodi Huang, Bowen Yi, Yanzheng Zhao, Limin Zhu
Summary: B-spline curve approximation with tool tip position adjustment is proposed to reduce the maximum curve curvature and improve machining efficiency without exceeding tolerance in CNC machining. Toolpaths are divided into subdivisions based on discrete curvature, and tool tip positions are adjusted to minimize maximum discrete curvature. The improved ELSPIA method fits the adjusted toolpaths and lowers chord errors by searching appropriate foot point parameters.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Engineering, Manufacturing
Zi-Hui Zhu, Peng Huang, Suet To, Li-Min Zhu, Zhiwei Zhu
Summary: A fast-tool-servo-controlled shear-thickening micropolishing method is proposed for removing undesired surface diffraction on diamond-turned microstructured surfaces. The method allows for controllable material removal by adjusting the gap width and achieves improved surface quality.
INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE
(2023)
Article
Optics
Bingxin Chen, Hong Pan, Liping Zhu, Hongtao Xu, Hengliang Wang, Lijian Zhang, Xiaomi Yan, Chiyuan Ma, Xuguang Xu, Wei Lu, Zhenghua An, Yanru Song
Summary: Superconducting photodetection offers wide spectral coverage and single photon sensitivity, but the detection efficiency is low in the longer wavelength infrared range. By using a superconducting metamaterial, we achieved nearly perfect absorption at dual color infrared wavelengths and enhanced light coupling efficiency. Our infrared detector demonstrated peak responsivity of 1.2 x 106 V/W and 3.2 x 106 V/W at two resonant frequencies, significantly higher than the non-resonant frequency. This work provides a way to improve the sensitivity of superconducting photodetectors in the infrared range.
Article
Computer Science, Artificial Intelligence
Chengyang Li, Liping Zhu, Gangyi Tian, Yi Hou, Heng Zhou
Summary: This paper investigates the localization problem of referring relationships and proposes a mask-level relational reasoning perspective to improve model interpretability. Specific modules and methods are designed for text-to-image and image-to-text reasoning processes, and multimodal relational reasoning is achieved through bi-directional reasoning. Experimental results demonstrate that the proposed method achieves state-of-the-art performance on two datasets.
PATTERN RECOGNITION
(2023)
Article
Engineering, Environmental
Xiao-Bo Yang, Wei Li, Ze-Zhong Lin, Jing-Qi Liu, Hong-Xin Jiang, Hao Jia, Wei-Liang Jin, Xin-Long Hou, Bing-Xuan Du, Li-Na Zhu, De-Ming Kong
Summary: Efficient and selective adsorption/removal of Cs+ is crucial for resource utilization and radioactive pollution control. A PAN/PB aerogel with enhanced PB-loading capacity was prepared by pre-doping Fe3+ in PAN nanofibers. The PAN/PB aerogel exhibited interconnected porous structure, ultralight density, improved water stability, increased thermal stability, robust mechanical elasticity, high hydrophilicity, and excellent Cs+ adsorption selectivity. Its practical application potential was demonstrated by the highly efficient and selective adsorption/removal of Cs+ from simulated seawater and salt lake brine.
CHEMICAL ENGINEERING JOURNAL
(2023)
Article
Computer Science, Interdisciplinary Applications
Jinlong Liu, Yuancheng Shao, Junyang Li, Limin Zhu, Xiaolei Gong, Lianyan Xue, Juanya Shen, Youjin Li
Summary: This study used computer-aided design and computational fluid dynamics to simulate upper airway flow characteristics, providing guidance for surgeons in treating infants with vallecular cyst and coexisting laryngomalacia.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Engineering, Chemical
Dong-xiao Cao, Yan Chen, Wei-liang Jin, Wei Li, Rui Wang, Ke Wang, An-na Tang, Li-na Zhu, De-ming Kong
Summary: Rapid and efficient removal of organic dyes from polluted water is important for environmental protection and water resources management. A new anionic covalent organic polymer (COP), named COPOH+CO, with the fastest dye adsorption kinetics so far, was synthesized. COPOH+CO showed a higher adsorption capacity for the cationic dye methylene blue (MB) compared to other COPs, indicating a synergy between its functional groups.
SEPARATION AND PURIFICATION TECHNOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Shengmiao Sun, Bixuan Wang, Molan Qing, Danbi Tian, Ling Jiang, Liying Zhu
Summary: A modified screen-printed electrode based on ZIF-8, Ag NPs, and ErGO was developed for dopamine detection. The synthesized ErGO/Ag-ZIF-8 composites maintained the structure of ZIF-8. The oxidation current of dopamine increased linearly in the range of 0.1-200 mu M with a detection limit of 0.03 mu M (S/N=3). The sensor exhibited good reproducibility and selectivity, and it was successfully applied for dopamine detection in goat serum with satisfactory recovery range.