Article
Computer Science, Artificial Intelligence
Xiaojun Yang, Siyuan Li, Ke Liang, Feiping Nie, Liang Lin
Summary: Spectral Clustering (SC) is an important method in various fields, but it has poor performance in high-dimensional data. This paper proposes a new approach called JSEGO, which combines spectral embedding and clustering with structured graph optimization. The new approach improves the performance and addresses the limitations of traditional methods through iterative processes. Experimental results demonstrate the advantage of this new approach.
Article
Computer Science, Artificial Intelligence
Xiaotong Zhang, Han Liu, Xiao-Ming Wu, Xianchao Zhang, Xinyue Liu
Summary: This paper proposes a spectral embedding network named SENet for attributed graph clustering, which improves graph structure and learns node embeddings to address issues in traditional methods, achieving superior performance over state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Mingyu Zhao, Weidong Yang, Feiping Nie
Summary: Graph-based methods have achieved great success in multi-view clustering but suffer from shallow and linear embedding functions and simple weighted-sum rule for fusion similarity graphs. To address these issues, we propose a novel deep multi-view spectral clustering via ensemble model (DMCE) that applies ensemble clustering to fuse similarity graphs and employs graph auto-encoder to learn the common spectral embedding directly. We also design a unified optimization framework with three loss functions for updating variables in DMCE. Experimental results on six real-world datasets demonstrate the effectiveness of our model compared to state-of-the-art methods in multi-view clustering.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Jie Chen, Hua Mao, Dezhong Peng, Changqing Zhang, Xi Peng
Summary: In this paper, a consensus spectral rotation fusion (CSRF) method is proposed for multiview clustering (MVC). The CSRF method learns a fused affinity matrix at the spectral embedding feature level and solves the CSRF optimization problem using an alternating iterative optimization algorithm. Experimental results demonstrate the effectiveness and efficiency of the CSRF method on multiview datasets.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Genetics & Heredity
Rongquan Wang, Huimin Ma, Caixia Wang
Summary: This study proposes an Ensemble Learning Framework (ELF-DPC) for detecting protein complexes within protein-protein interaction networks. The framework constructs a weighted PPI network by combining topological and biological information, mines protein complex cores using a designed strategy, and obtains an ensemble learning model by integrating structural modularity and a trained voting regressor model. Experimental results show that ELF-DPC outperforms state-of-the-art approaches and can detect biologically meaningful protein complexes.
FRONTIERS IN GENETICS
(2022)
Article
Computer Science, Artificial Intelligence
Hongwei Yin, Wenjun Hu, Zhao Zhang, Jungang Lou, Minmin Miao
Summary: This paper proposes an efficient incremental multi-view spectral clustering method SCGL, which only stores one consensus similarity matrix to represent the structural information of all historical views, and integrates sparse graph learning and connected graph learning. Experimental results demonstrate that the method outperforms traditional methods in clustering accuracy.
Article
Computer Science, Artificial Intelligence
S. El Hajjar, F. Dornaika, F. Abdallah
Summary: A constrained version of Multiview Spectral Clustering integrating Nonnegative Embedding and Spectral Embedding is proposed in this paper. The method integrates two types of constraints and shows superiority in experimental results.
INFORMATION FUSION
(2022)
Article
Computer Science, Artificial Intelligence
Wenyu Hao, Shanmin Pang, Zhikai Chen
Summary: The paper proposes a dynamic strategy to construct a common local representation and designs a fusion term to maximize the common structure of local and global representations for mutual reinforcement. By integrating local and global representation learning in a unified framework and utilizing an alternative iteration based optimization procedure, the algorithm demonstrates superiority over state-of-the-art methods through extensive experiments on benchmark datasets.
Article
Biochemistry & Molecular Biology
Sara Omranian, Angela Angeleska, Zoran Nikoloski
Summary: GCC-v is an efficient, parameter-free algorithm that accurately predicts protein complexes, outperforming twelve state-of-the-art methods in multiple experimental scenarios. Its robustness to network perturbations is demonstrated in pan-plant PPI networks and Arabidopsis thaliana, highlighting its potential for impact assessment on predicted protein complexes.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2021)
Review
Biochemistry & Molecular Biology
Sara Omranian, Zoran Nikoloski, Dominik G. Grimm
Summary: This article provides a systematic review of state-of-the-art algorithms for protein complex prediction from protein-protein interaction networks. The existing approaches are categorized and compared, and the performance of eighteen methods is analyzed on benchmark networks. The limitations, drawbacks, and potential solutions in the field are discussed, emphasizing future research efforts.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2022)
Article
Computer Science, Information Systems
Bo Zhou, Wenliang Liu, Wenzhen Zhang, Zhengyu Lu, Qianlin Tan
Summary: In this paper, a new method of multi-kernel graph fusion (MKGF-MM) based on min-max optimization is proposed for spectral clustering, which fully utilizes all base kernels to address the bias to power base kernels issue. The proposed method investigates a novel min-max weight strategy to capture the complementary information among all base kernels and designs an iterative optimization method to solve the objective function. The theoretical proof of convergence is provided and experimental results demonstrate the superiority of the proposed method over comparison methods, along with fast convergence of the proposed optimization method.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Information Systems
S. El Hajjar, F. Dornaika, F. Abdallah
Summary: Recently, one-step clustering methods have achieved good performance. However, there is a lack of approaches for handling the multi-view case, where each instance may have multiple representations. In this paper, a novel graph-based multi-view clustering approach is proposed, which introduces cluster label correlation graph and smoothing constraint to improve the clustering performance.
INFORMATION SCIENCES
(2022)
Article
Statistics & Probability
Patrick Rubin-Delanchy, Joshua Cape, Minh Tang, Carey E. Priebe
Summary: This paper proposes a method to estimate latent positions as vector representations of graph nodes using spectral embedding. The method can handle heterophilic connectivity and negative eigenvalues. It provides consistent estimates with asymptotically Gaussian error. The paper suggests using a Gaussian mixture model for spectral clustering in the stochastic block model and fitting the minimum volume enclosing simplex in the mixed membership model, which improves link prediction and uncovers richer latent structure.
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
(2022)
Article
Computer Science, Information Systems
Ting Li, Yiming Zhang, Hao Liu, Guangtao Xue, Ling Liu
Summary: Spectral clustering (SC) is widely used in industrial product analysis as an unsupervised learning method. Compressive spectral clustering (CSC) accelerates clustering effectively but suffers from expensive computation and time-consuming interpolation. The proposed fast compressive spectral clustering (FCSC) method addresses these issues by assuming eigenvalues satisfy local uniform distribution and reconstructing denoised Laplacian matrix with low-dimensional representation. The experimental results show that FCSC significantly reduces computation time while maintaining high clustering accuracy.
IEEE TRANSACTIONS ON BIG DATA
(2022)
Article
Computer Science, Artificial Intelligence
S. El Hajjar, F. Dornaika, F. Abdallah, N. Barrena
Summary: This paper presents a new method called MVCGE for addressing the limitation of decreased clustering result quality in multi-view clustering due to initialization issues. The proposed method learns the consensus affinity matrix, consensus representation, and cluster index matrix simultaneously through consensus graph learning and nonnegative embedding. It integrates interesting constraints to ensure smoothness of cluster indices over the consensus graph and closeness to the graph convolution of the consensus representation. Experimental results demonstrate that the proposed method performs well on real and synthetic datasets.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Information Systems
Elahe Nasiri, Kamal Berahmand, Yuefeng Li
Summary: Link prediction is a widely studied problem in complex network analysis. The existing methods often overlook the potential of nodal attributes and only focus on the network's topological structure. To address this limitation, a novel method called RGNMF-AN was proposed, which models both the topological structure and nodal attributes for link prediction. The method combines network topology and nodal attribute information and calculates high-order proximities using the SARWS method. Empirical findings on real-world complex network datasets show that the combination of attributed and topological information significantly improves prediction performance compared to baseline and other NMF-based algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Zhongyao Cao, Yue Li, Zhijun Zhang, Magdy F. Iskander
Summary: This article proposes a mechanically reconfigurable 1-D reflectarray that is actuated by a single motor. The reflectarray consists of metal tubes lifted by ejectors, and utilizes the discontinuity of the Archimedean spiral to achieve continuous phase growth. A novel drive mechanism, consisting of Archimedean spiral cams and followers, is designed to convert the motor rotation to linear motion of the elements. The reflectarray, supported by low-cost acrylic plates, achieved a beam steering range of -60 degrees to 60 degrees in one dimension at 5 GHz and showed a significant improvement in the received signal level in a multipath environment.
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
(2023)
Article
Engineering, Electrical & Electronic
Weiquan Zhang, Yue Li, Kunpeng Wei, Zhijun Zhang
Summary: This paper presents two dual-band back-to-back planar inverted-F antennas (PIFAs) for WLAN applications, which can simultaneously radiate at the 2.4 GHz and 5 GHz bands by etching a slot on the PIFA. A decoupling process using long and short slots on the ground is discussed to reduce mutual coupling. The fabricated and measured antennas show good coverage of the 2.4 and 5 GHz WLAN bands with isolation improved to higher than 20 dB at both bands.
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
(2023)
Article
Computer Science, Artificial Intelligence
Razieh Sheikhpour, Kamal Berahmand, Saman Forouzandeh
Summary: Feature selection aims to eliminate redundant features and choose informative ones. Semi-supervised feature selection becomes important as it utilizes labeled and unlabeled data. We propose two frameworks, one based on Hessian matrix and the other on Hessian-Laplacian combination, for semi-supervised feature selection. Our frameworks utilize regularization and constraint techniques to select informative features and maintain the topological structure of data. Experimental results demonstrate the effectiveness of our frameworks in selecting informative features.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Optics
Wendi Yan, Ziheng Zhou, Hao Li, Wangyu Sun, Qihao Lv, Yue Li
Summary: Different from classical periodic-resonator-based metamaterials, epsilon-near-zero (ENZ) metamaterials achieve equivalent electromagnetic characteristics in deep subwavelength scales. By substituting dielectric dopants with metal-layer dopants, a dielectric-free approach is used to construct a low-loss resonant cavity, enabling the largest tuning range of the effective permeability mu(eff). The low-loss benefits of layer-type ENZ metamaterials are demonstrated in integrated microfluidic switches and high-sensitivity sensors, showing universal significance for wide-range applications in extreme-small-volume devices and systems.
LASER & PHOTONICS REVIEWS
(2023)
Article
Engineering, Electrical & Electronic
Weiquan Zhang, Yue Li, Kunpeng Wei, Zhijun Zhang
Summary: This article presents a compact multiple-input-multiple-output (MIMO) microstrip antenna system that covers the 2.4 and 5 GHz wireless local area network (WLAN) bands. The dual-band characteristics are achieved by exciting the TM01 and TM03 modes of a microstrip antenna, using a rectangular slot to improve the radiation capability of the TM03 mode, and utilizing two probes to tune the resonant frequency of the TM01 mode. High interport isolation at the two WLAN bands is achieved through isolation enhancement at the lower and upper-frequency bands, introducing split loops to reduce mutual coupling at the 2.4 GHz band, and adding dipole elements in the rectangular slot for high isolation at the 5 GHz band. The proposed antenna system operates at 2.25-2.63 and at 5.14-6.06 GHz, with measured maximum mutual coupling of less than -15.3 dB at both operating frequency bands.
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
(2023)
Article
Engineering, Electrical & Electronic
Zhongyao Cao, Jiadong Hu, Yue Li, Kunpeng Wei, Zhijun Zhang, Magdy F. Iskander
Summary: A compact reconfigurable element-based 360 degrees azimuth scanning array is proposed for aviation applications. The reconfigurable Yagi-Uda element is constructed by combining a driven element and two switchable parasitic elements. The array can switch the radiation pattern to two broadside states in two directions and an endfire state. The measured results of the prototype indicate a wide scanning range and high gain with a small cross-sectional area. This work provides a compact reconfigurable antenna with full 360 degrees coverage for aviation applications and has the potential to promote future anti-interference array designs.
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
(2023)
Article
Engineering, Electrical & Electronic
Shan Gao, Le Chang, Anxue Zhang, Yue Li, Zhijun Zhang
Summary: This article addresses the issue of exact coverage problem of unbalanced Wi-Fi 6 bands by engineering the TM0.5,0 and TM0.5,1 modes of the half-mode patch while maintaining small volume. The design guideline includes selecting proper patch size, optimizing feeding positions, and using lumped components. The proposed half-mode patch with the smallest volume among reported Wi-Fi 6 dual-band patch antennas fully covers the Wi-Fi 6 bands and suits the optimal Wi-Fi 6 RF front-end architecture.
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
(2023)
Article
Engineering, Electrical & Electronic
Mingzhe Hu, Yue Li
Summary: This paper proposes a wideband and low-profile microstrip antenna for MIMO applications, which simultaneously excites three modes to achieve wideband radiation. The proposed antenna has a compact size and low profile, making it suitable for 5G mobile MIMO applications.
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
(2023)
Article
Engineering, Electrical & Electronic
Xiaopeng Zhang, Dawei Zhou, Shichao Li, Yue Li, Zhijun Zhang
Summary: A simple approach is proposed to reshape the radiation patterns of the third mode of dipole and slot antennas by adding short parasitic strips or slots to both sides of the antennas. The reversed current or E-field in the third mode is canceled out by the induced current or E-field on the added parasitic elements, resulting in reshaped omnidirectional or bidirectional radiation patterns. The effects of parasitic element length, spacing, and position on radiation patterns have also been studied. Two prototypes with parasitic elements were fabricated and tested, validating the concept with good agreement between measured and simulated results.
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
(2023)
Article
Engineering, Electrical & Electronic
Weiquan Zhang, Yue Li, Kunpeng Wei, Zhijun Zhang
Summary: A compact dual-band multibeam antenna system with high gain is proposed for MIMO Wi-Fi application. The system consists of four rotationally symmetric antenna panels and two series-fed microstrip patch antenna arrays operating at the 5GHz band. Two dual-function metasurfaces are placed between the antenna arrays to improve the gain and provide 2.4GHz antenna functionality. The antenna system demonstrates 360 degrees pattern coverage in azimuth and high gain characteristics.
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
(2023)
Article
Computer Science, Artificial Intelligence
Kamal Berahmand, Yuefeng Li, Yue Xu
Summary: DAC-HPP is a novel method for attributed graph clustering that utilizes high-order proximities and deep clustering framework to achieve efficient node grouping. Extensive experiments on synthetic and real networks demonstrate its superiority.
NEURAL COMPUTING & APPLICATIONS
(2023)
Review
Computer Science, Information Systems
Mehrdad Rostami, Mourad Oussalah, Kamal Berahmand, Vahid Farrahi
Summary: In recent years, the healthcare databases have seen a significant increase in both the number and volume of data sources. Analyzing these extensive medical data presents both opportunities and challenges for knowledge discovery in health informatics. This paper provides a comprehensive review of the applications of social network analysis and community detection algorithms in healthcare, filling the existing gap and offering up-to-date literature research. It also categorizes existing community detection algorithms and examines publicly available healthcare datasets, key challenges, and knowledge gaps in the field.
Article
Nanoscience & Nanotechnology
Xu Qin, Yijing He, Wangyu Sun, Pengyu Fu, Shuyu Wang, Ziheng Zhou, Yue Li
Summary: This study investigates the concept of stepped waveguide metamaterials as low-loss effective replicas of surface plasmon polaritons (SPPs). The proposed structure maintains the same field configuration as regular SPPs but avoids inherent losses, outperforming regular low-loss SPP designs with natural plasmonic materials in terms of propagation lengths. Furthermore, the stepped waveguide metamaterial exhibits excellent compatibility in direct interconnections with arbitrary regular SPPs, potentially leading to new SPP devices with low-loss advantages.
Article
Engineering, Electrical & Electronic
Zhenyu Liu, Yijing He, Yue Li
Summary: This paper proposes a general approach to enhance the beamwidth of microstrip antennas for wide beam coverage in both E- and H-planes. By introducing vertical currents brought by capacitive metalized vias, the half-power beamwidth (HPBW) is effectively broadened compared to regular microstrip antennas. In addition, the use of low-loss air medium and two arrays of via fences allows for high radiation efficiency. A fabricated and tested prototype validates the proposed design, showing enhanced HPBWs of 100(degrees) and 90(degrees) in E- and H-planes, respectively. Compared to existing 2.4-GHz antennas, the proposed antenna offers the advantages of wide beamwidth and high radiation efficiency, making it suitable for space-limited mobile devices with wide coverage requirements.
IEEE OPEN JOURNAL OF ANTENNAS AND PROPAGATION
(2023)
Article
Biology
Seyyed Bahram Borgheai, Alyssa Hillary Zisk, John McLinden, James Mcintyre, Reza Sadjadi, Yalda Shahriari
Summary: This study proposed a novel personalized scheme using fNIRS and EEG as the main tools to predict and compensate for the variability in BCI systems, especially for individuals with severe motor deficits. By establishing predictive models, it was found that there were significant associations between the predicted performances and the actual performances.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Hongliang Guo, Hanbo Liu, Ahong Zhu, Mingyang Li, Helong Yu, Yun Zhu, Xiaoxiao Chen, Yujia Xu, Lianxing Gao, Qiongying Zhang, Yangping Shentu
Summary: In this paper, a BDSMA-based image segmentation method is proposed, which improves the limitations of the original algorithm by combining SMA with DE and introducing a cooperative mixing model. The experimental results demonstrate the superiority of this method in terms of convergence speed and precision compared to other methods, and its successful application to brain tumor medical images.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Jingfei Hu, Linwei Qiu, Hua Wang, Jicong Zhang
Summary: This study proposes a novel semi-supervised point consistency network (SPC-Net) for retinal artery/vein (A/V) classification, addressing the challenges of specific tubular structures and limited well-labeled data in CNN-based approaches. The SPC-Net combines an AVC module and an MPC module, and introduces point set representations and consistency regularization to improve the accuracy of A/V classification.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Omair Ali, Muhammad Saif-ur-Rehman, Tobias Glasmachers, Ioannis Iossifidis, Christian Klaes
Summary: This study introduces a novel hybrid model called ConTraNet, which combines the strengths of CNN and Transformer neural networks, and achieves significant improvement in classification performance with limited training data.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Juan Antonio Valera-Calero, Dario Lopez-Zanoni, Sandra Sanchez-Jorge, Cesar Fernandez-de-las-Penas, Marcos Jose Navarro-Santana, Sofia Olivia Calvo-Moreno, Gustavo Plaza-Manzano
Summary: This study developed an easy-to-use application for assessing the diagnostic accuracy of digital pain drawings (PDs) compared to the classic paper-and-pencil method. The results demonstrated that digital PDs have higher reliability and accuracy compared to paper-and-pencil PDs, and there were no significant differences in assessing pain extent between the two methods. The PAIN EXTENT app showed good convergent validity.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Biao Qu, Jialue Zhang, Taishan Kang, Jianzhong Lin, Meijin Lin, Huajun She, Qingxia Wu, Meiyun Wang, Gaofeng Zheng
Summary: This study proposes a deep unrolled neural network, pFISTA-DR, for radial MRI image reconstruction, which successfully preserves image details using a preprocessing module, learnable convolution filters, and adaptive threshold.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Alireza Rafiei, Milad Ghiasi Rad, Andrea Sikora, Rishikesan Kamaleswaran
Summary: This study aimed to improve machine learning model prediction of fluid overload by integrating synthetic data, which could be translated to other clinical outcomes.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Jinlian Ma, Dexing Kong, Fa Wu, Lingyun Bao, Jing Yuan, Yusheng Liu
Summary: In this study, a new method based on MDenseNet is proposed for automatic segmentation of nodular lesions from ultrasound images. Experimental results demonstrate that the proposed method can accurately extract multiple nodules from thyroid and breast ultrasound images, with good accuracy and reproducibility, and it shows great potential in other clinical segmentation tasks.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Jiabao Sheng, SaiKit Lam, Jiang Zhang, Yuanpeng Zhang, Jing Cai
Summary: Omics fusion is an important preprocessing approach in medical image processing that assists in various studies. This study aims to develop a fusion methodology for predicting distant metastasis in nasopharyngeal carcinoma by mitigating the disparities in omics data and utilizing a label-softening technique and a multi-kernel-based neural network.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Zhenxiang Xiao, Liang He, Boyu Zhao, Mingxin Jiang, Wei Mao, Yuzhong Chen, Tuo Zhang, Xintao Hu, Tianming Liu, Xi Jiang
Summary: This study systematically investigates the functional connectivity characteristics between gyri and sulci in the human brain under naturalistic stimulus, and identifies unique features in these connections. This research provides novel insights into the functional brain mechanism under naturalistic stimulus and lays a solid foundation for accurately mapping the brain anatomy-function relationship.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Qianqian Wang, Mingyu Zhang, Aohan Li, Xiaojun Yao, Yingqing Chen
Summary: The development of PARP-1 inhibitors is crucial for the treatment of various cancers. This study investigates the structural regulation of PARP-1 by different allosteric inhibitors, revealing the basis of allosteric inhibition and providing guidance for the discovery of more innovative PARP-1 inhibitors.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Qing Xu, Wenting Duan
Summary: In this paper, a dual attention supervised module, named DualAttNet, is proposed for multi-label lesion detection in chest radiographs. By efficiently fusing global and local lesion classification information, the module is able to recognize targets with different sizes. Experimental results show that DualAttNet outperforms baselines in terms of mAP and AP50 with different detection architectures.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Kaja Gutowska, Piotr Formanowicz
Summary: The primary aim of this research is to propose algorithms for identifying significant reactions and subprocesses within biological system models constructed using classical Petri nets. These solutions enable two analysis methods: importance analysis for identifying critical individual reactions to the model's functionality and occurrence analysis for finding essential subprocesses. The utility of these methods has been demonstrated through analyses of an example model related to the DNA damage response mechanism. It should be noted that these proposed analyses can be applied to any biological phenomenon represented using the Petri net formalism. The presented analysis methods extend classical Petri net-based analyses, enhancing our comprehension of the investigated biological phenomena and aiding in the identification of potential molecular targets for drugs.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Hansle Gwon, Imjin Ahn, Yunha Kim, Hee Jun Kang, Hyeram Seo, Heejung Choi, Ha Na Cho, Minkyoung Kim, Jiye Han, Gaeun Kee, Seohyun Park, Kye Hwa Lee, Tae Joon Jun, Young-Hak Kim
Summary: Electronic medical records have potential in advancing healthcare technologies, but privacy issues hinder their full utilization. Deep learning-based generative models can mitigate this problem by creating synthetic data similar to real patient data. However, the risk of data leakage due to malicious attacks poses a challenge to traditional generative models. To address this, we propose a method that employs local differential privacy (LDP) to protect the model from attacks and preserve the privacy of training data, while generating medical data with reasonable performance.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Siwei Tao, Zonghan Tian, Ling Bai, Yueshu Xu, Cuifang Kuang, Xu Liu
Summary: This study proposes a transfer learning-based method to address the phase retrieval problem in grating-based X-ray phase contrast imaging. By generating a training dataset and using deep learning techniques, this method improves image quality and can be applied to X-ray 2D and 3D imaging.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)