Article
Engineering, Electrical & Electronic
Tiecheng Song, Jie Feng, Lin Luo, Chenqiang Gao, Hongliang Li
Summary: In this paper, two novel operators, local grouped order pattern (LGOP) and non-local binary pattern (NLBP), are proposed for texture description. Experimental results demonstrate that combining LGOP and NLBP to construct discriminative histogram features as texture descriptor LGONBP shows superiority over state-of-the-art LBP variants for texture classification.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Zeng Qiang, Adu Jianhua, Sun Xiaoya, Hong Sunyan
Summary: An extended complete LBP (ELBP) method is proposed for texture classification in this paper, which provides a detailed description and analysis of the composition of local feature vectors. Experimental results show that the algorithm has good scalability and robustness.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Nuh Alpaslan
Summary: This paper presents novel hybrid methods based on neutrosophic set and LBP features. By transforming the input image into a neutrosophic domain and combining with grayscale images, the proposed methods can extract more robust features. The methods contribute to the classification performance with reasonable computational cost and achieve satisfactory results in experiments.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Qiwu Luo, Jiaojiao Su, Chunhua Yang, Olli Silven, Li Liu
Summary: In this paper, a novel image descriptor, called SNELBP, is proposed to address scale transformation and noise interference simultaneously. It achieves competitive results compared to classical LBP variants and typical deep learning methods.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Yijie Luo, Jiming Sa, Yuyan Song, He Jiang, Chi Zhang, Zhushanying Zhang
Summary: This paper proposes an improved LBP operator by using a local binary pattern operator based on magnitude ranking and a global threshold segmentation operator, to further improve the performance. This improved LBP achieves excellent texture classification accuracy across six common datasets, with an average of 1% lower than the best LBP variants. Meanwhile, the computational complexity of the proposed improved LBP is several times lower than that of the best LBP variants.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Xin Shu, Zhigang Song, Jinlong Shi, Shucheng Huang, Xiao-Jun Wu
Summary: The paper introduces a novel method, multiple channels local binary pattern (MCLBP), which combines single-channel texture characteristics with multi-channel color information for color texture representation and classification. Results from comprehensive experiments on benchmark databases show that this method outperforms most existing color texture features in terms of classification accuracy.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2021)
Article
Engineering, Electrical & Electronic
Shaokun Lan, Xuewen Liao, Hongcheng Fan, Shiqi Hu, Zhibin Pan
Summary: This paper presents the use of Local binary pattern (LBP) in texture classification and proposes improved algorithms to address the existing issues. First, a completed cross-scale Local binary pattern (ccsLBP) operator is introduced to extract cross-scale texture features. Second, a mean-filtered Local binary pattern (LBPmf) operator is proposed to highlight low-frequency texture information. Third, a high-performing multi-channel framework based on Local binary pattern (MC-LBP) is built by combining features extracted by LBP, ccsLBP, and LBPmf hybridly to form the final feature vector of texture images. Experimental results demonstrate the state-of-art texture classification performance of the proposed MC-LBP framework.
DIGITAL SIGNAL PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Turker Tuncer, Sengul Dogan, U. Rajendra Acharya
Summary: The study developed a model using chaotic feature generation function for EEG signal classification, achieving high classification performance by using chaotic one-dimensional local binary pattern and wavelet packet decomposition techniques for abnormal EEG detection.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Xin Shu, Hui Pan, Jinlong Shi, Xiaoning Song, Xiao-Jun Wu
Summary: This paper proposes a novel global refined local binary pattern (GRLBP) for texture feature extraction. By analyzing the nature of pixel intensity distribution in local neighborhoods, GRLBP can effectively describe and distinguish local neighborhoods with similar structures but different contrasts or grayscales. Experimental results demonstrate that GRLBP can represent detailed information of texture images and outperforms state-of-the-art LBP variants in terms of classification accuracy, feature dimension, and computational complexity.
PATTERN RECOGNITION
(2022)
Article
Mathematics, Interdisciplinary Applications
Maria-Alexandra Paun, Paraschiva Postolache, Mihai-Virgil Nichita, Vladimir-Alexandru Paun, Viorel-Puiu Paun
Summary: In this paper, we propose to quantitatively compare the loss of human lung health under the influence of COVID-19 using fractal-analysis interpretation of chest-pulmonary CT pictures. This method is effective for small datasets commonly encountered in medical applications. Fractal analysis characteristics, such as fractal dimension and lacunarity measured values, provide valuable insights for interpreting pulmonary CT picture texture.
FRACTAL AND FRACTIONAL
(2023)
Article
Computer Science, Information Systems
Abadhan Ranganath, Manas Ranjan Senapati, Pradip Kumar Sahu
Summary: In this article, a fractal-based texture descriptor method is proposed to find the similarity of local patterns and discriminate different patterns of images. Experimental results show that this method outperforms other two methods in terms of classification accuracy and has lower computational complexity.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Software Engineering
Shaokun Lan, Jie Li, Shiqi Hu, Hongcheng Fan, Zhibin Pan
Summary: In this paper, a neighbourhood feature-based local binary pattern (NF-LBP) is proposed to improve the classification performance of the local binary pattern (LBP) in texture feature analysis. The NF-LBP method combines the neighbourhood feature, local sign component, and centre pixel component to provide better texture information and is robust to noise.
Article
Mathematics, Interdisciplinary Applications
Zbigniew Omiotek, Roza Dzierzak, Andrzej Kepa
Summary: Fractal analysis was utilized to extract feature descriptors for diagnosing bone damage caused by osteoporosis from CT images of vertebrae, resulting in three descriptors. The K-NN classifier demonstrated the highest overall classification accuracy among the supervised classification methods, showing promise for diagnosing osteoporotic bone defects.
FRACTALS-COMPLEX GEOMETRY PATTERNS AND SCALING IN NATURE AND SOCIETY
(2021)
Article
Computer Science, Artificial Intelligence
Zhibin Pan, Shiqi Hu, Xiuquan Wu, Ping Wang
Summary: This study introduces a novel adaptive center pixel selection (ACPS) strategy to improve the robustness and discrimination capability of Local Binary Pattern(LBP) in texture classification. By applying interpolation method and edge detection, ACPS helps recover lost texture information and accurately extract complicated texture microstructures, leading to significantly improved texture classification performance on various texture databases.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Debjit Das, Ruchira Naskar, Rajat Subhra Chakraborty
Summary: Due to the availability of image tampering software tools, image manipulation has become widespread. Image splicing, which involves combining parts from different images, is a common form of manipulation. Detecting image splicing is important in digital forensics, and this paper proposes a technique using a feature set of optimal dimensions for successful detection. Experimental results using the Columbia Image Splicing Detection Evaluation Dataset show that a feature set comprising of Local Binary Pattern features with a dimension as low as 31 achieves state-of-the-art spliced image classification result using the Support Vector Machine classifier.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Genetics & Heredity
Guobo Xie, Cuiming Wu, Yuping Sun, Zhiliang Fan, Jianghui Liu
FRONTIERS IN GENETICS
(2019)
Article
Biochemistry & Molecular Biology
Guobo Xie, Shuhuang Huang, Yu Luo, Lei Ma, Zhiyi Lin, Yuping Sun
MOLECULAR GENETICS AND GENOMICS
(2019)
Article
Medicine, Research & Experimental
Guobo Xie, Zhiliang Fan, Yuping Sun, Cuiming Wu, Lei Ma
JOURNAL OF TRANSLATIONAL MEDICINE
(2019)
Review
Biochemistry & Molecular Biology
Guobo Xie, Bin Huang, Yuping Sun, Changhai Wu, Yuqiong Han
Summary: Long noncoding RNAs (lncRNAs) have a significant impact on biological processes and predicting potential lncRNA-disease associations can aid in disease diagnosis and treatment. The proposed model RWSF-BLP shows reliable AUC values and outperforms other canonical methods, with case studies demonstrating its effectiveness in predicting lncRNA-disease associations for diseases like lung cancer and leukemia.
MOLECULAR GENETICS AND GENOMICS
(2021)
Article
Mathematical & Computational Biology
Guobo Xie, Hui Chen, Yuping Sun, Guosheng Gu, Zhiyi Lin, Weiming Wang, Jianming Li
Summary: In this paper, a computational approach based on deep matrix factorization with multi-source fusion (DMFMSF) is proposed to predict circRNA-disease associations. By selecting and combining several useful circRNA and disease similarities through similarity kernel fusion, linear and non-linear characteristics are mined to infer potential associations. The performance of DMFMSF is rigorously validated on two benchmark datasets through cross-validation, showing superiority over existing computational approaches in predicting circRNA-disease associations.
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
(2021)
Article
Computer Science, Information Systems
Tianrong Chen, Jie Ling, Yuping Sun
Summary: This paper examines content camouflage attacks on preprocessing modules in deep learning systems and formulates them as an optimization problem using a multi-scale discriminator. Experimental results demonstrate the effectiveness of the proposed attacks against deep learning systems.
COMPUTERS & SECURITY
(2022)
Article
Computer Science, Interdisciplinary Applications
Guobo Xie, Haojie Xu, Jianming Li, Guosheng Gu, Yuping Sun, Zhiyi Lin, Yinting Zhu, Weiming Wang, Youfu Wang, Jiang Shao
Summary: Due to the time and funding constraints of developing new COVID-19 vaccines or drugs, drug repositioning has emerged as a promising therapeutic strategy. We propose a method called DRPADC that effectively predicts novel drug-disease associations. Experimental results show that DRPADC outperforms other methods in terms of AUC values and case studies.
COMPUTERS & CHEMICAL ENGINEERING
(2022)
Article
Biochemistry & Molecular Biology
Guobo Xie, Yinting Zhu, Zhiyi Lin, Yuping Sun, Guosheng Gu, Jianming Li, Weiming Wang
Summary: The study proposed a computational method called HBRWRLDA, which efficiently predicts lncRNA-disease associations, reducing the time needed for biological experiments. Experimental results demonstrated that HBRWRLDA has high predictive accuracy and can play a significant role in disease research.
MOLECULAR GENETICS AND GENOMICS
(2022)
Article
Biochemical Research Methods
Guobo Xie, Zelin Jiang, Zhiyi Lin, Guosheng Gu, Yuping Sun, Qing Su, Ji Cui, Huizhe Zhang
Summary: Long non-coding RNAs (lncRNAs) play a vital role in biological regulation and understanding human diseases. In order to improve prediction performance, we developed a computational method that incorporates higher-order similarity information into the similarity network, achieving better results through a decay function designed by random walk with restart.
CURRENT BIOINFORMATICS
(2023)
Article
Computer Science, Information Systems
Haonan Huang, Yuping Sun, Meijing Lan, Huizhe Zhang, Guobo Xie
Summary: The importance of microbe-drug associations (MDA) prediction is highlighted in research, as traditional wet-lab experiments are costly and time-consuming. Therefore, we have developed two novel computational approaches, GNAEMDA and VGNAEMDA, to provide efficient solutions for well-annotated cases and cold-start scenarios. These models utilize multi-modal attribute graphs and graph normalized convolutional network to accurately infer potential MDA, especially for new microbes or drugs. Experimental results demonstrate the strong prediction performances of GNAEMDA and VGNAEMDA, with over 75% of the predicted associations being validated in PubMed.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Information Systems
Qing Su, Enhai Ou, Yuping Sun, Chunyan Lv, Guobo Xie, Haoqing Wang, Honglin Huang
Summary: This article introduces a novel representation learning model called SimH for COVID-19 knowledge graphs. The model enhances the modeling capability for low-connected star-like structures and complex nonlinear relationships through the addition of activation operation and hyperplane projection technique. A negative triplet sampling method is also introduced to generate reliable negative triplets. Experimental results demonstrate significant improvements in prediction and classification accuracy compared to existing knowledge representation learning models.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Biochemical Research Methods
Huizhe Zhang, Juntao Fang, Yuping Sun, Guobo Xie, Zhiyi Lin, Guosheng Gu
Summary: This study proposes a novel method called AGAEMD to predict potential miRNA disease associations. It utilizes a node-level attention graph auto-encoder to represent nodes and calculate association scores. Experimental results demonstrate the excellent performance of AGAEMD compared to other methods, and case studies confirm its reliable predictive performance.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Biology
Guoquan Ning, Yuping Sun, Jie Ling, Jijia Chen, Jiaxi He
Summary: Drug-drug interactions (DDIs) refer to the potential effects of simultaneous interactions between two or more drugs, which may result in adverse reactions or reduced drug efficacy. Accurate prediction of DDIs is crucial and a novel framework called BDN-DDI has been proposed to infer potential DDIs with high accuracy and outperforming previous methods.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biochemistry & Molecular Biology
Guobo Xie, Jianming Li, Guosheng Gu, Yuping Sun, Zhiyi Lin, Yinting Zhu, Weiming Wang
Summary: Drug repositioning is a valuable method for identifying new indications for existing drugs and can greatly reduce the cost and time of drug development. The BGMSDDA algorithm, which integrates multiple similarity measures, has shown excellent performance in predicting drug-disease associations and has been validated on various datasets.
Article
Biochemistry & Molecular Biology
Guobo Xie, Yinting Zhu, Zhiyi Lin, Yuping Sun, Guosheng Gu, Weiming Wang, Hui Chen
Summary: A computational prediction method, HOPMCLDA, based on high-order proximity and matrix completion was proposed to predict lncRNA-disease associations. Through experiments, it was demonstrated that HOPMCLDA outperforms other methods in predicting these associations.