Article
Computer Science, Artificial Intelligence
Hamideh Sadat Fatemighomi, Mousa Golalizadeh, Meisam Amani
Summary: Efficient analysis of hyperspectral datasets using the latent block model (LBM) has been enhanced by replacing finite mixture model (FMM) with hidden Markov random field (HMRF) and developing a new object-based classification algorithm. The proposed algorithm, named LBMHMRF, achieves higher spectral information utilization, lower parameter estimation requirements, and faster computation compared to alternative algorithms. It has shown the highest potential in terms of classification accuracy and computation time.
PATTERN ANALYSIS AND APPLICATIONS
(2022)
Article
Biology
Rui Huo, Liting Zhang, Feifei Liu, Ying Wang, Yesong Liang, Shoushui Wei
Summary: The study proposed a bidirectional hidden semi-Markov model (BI-HSMM) based on the probability distributions of ECG waveform duration for accurate segmentation of ECG waves, achieving excellent performance on the QT database and wearable dynamic electrocardiography (DCG) signals collected by the Shandong Provincial Hospital (SPH). The experimental results and real DCG signal validation confirmed the significant ability of the proposed BI-HSMM method to segment the resting and DCG signals, which is beneficial for detecting and monitoring CVDs.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Hardware & Architecture
Ru Xu
Summary: In this paper, a fuzzy c-means clustering image segmentation algorithm based on Hidden Markov model is proposed to solve the poor anti-jamming effect in traditional methods. Experimental results show that the proposed algorithm achieves a good segmentation effect, with smooth boundaries, little influence of image noise, and strong robustness.
MOBILE NETWORKS & APPLICATIONS
(2022)
Article
Biochemical Research Methods
Eleni Aloupogianni, Takaya Ichimura, Mei Hamada, Masahiro Ishikawa, Takuo Murakami, Atsushi Sasaki, Koichiro Nakamura, Naoki Kobayashi, Takashi Obi
Summary: This study proposes a framework for tumor segmentation of pigmented skin lesions based on hyperspectral imaging (HSI). Pixel-wise processing and simultaneous use of spatio-spectral features are shown to improve segmentation performance and produce more comprehensive tumor masks. A three-dimensional Xception-based network achieves good performance in tumor border detection, but has difficulty detecting margins in some cases of basal cell carcinoma.
JOURNAL OF BIOMEDICAL OPTICS
(2022)
Article
Environmental Sciences
Shuowen Yang, Xiang Yan, Hanlin Qin, Qingjie Zeng, Yi Liang, Henry Arguello, Xin Yuan
Summary: This paper introduces a novel mid-infrared compressive hyperspectral imaging system that combines an improved MIR-DMD with an off-the-shelf infrared spectroradiometer to capture hyperspectral images in the mid-infrared spectral range. The development of a dual-stage image reconstruction method and the use of measurement without coding as side information has improved the quality of reconstruction for infrared hyperspectral images. This system represents a less expensive alternative to conventional mid-infrared hyperspectral imaging systems.
Article
Computer Science, Artificial Intelligence
Bingyuan Liu, Jose Dolz, Adrian Galdran, Riadh Kobbi, Ismail Ben Ayed
Summary: Most segmentation losses, such as CE and Dice, are variants of the Cross-Entropy or Dice losses. This work provides a theoretical analysis that shows a deeper connection between CE and Dice than previously thought. From a constrained-optimization perspective, both CE and Dice decompose into similar ground-truth matching terms and region-size penalty terms. The analysis uncovers hidden region-size biases: Dice has an intrinsic bias towards extremely imbalanced solutions, while CE implicitly encourages the ground-truth region proportions. Based on this analysis, a principled and simple solution is proposed to explicitly control the region-size bias.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Geochemistry & Geophysics
Zhaoxu Li, Qiang Ling, Zaiping Lin, Jing Wu
Summary: The proposed method utilizes image segmentation and a weighting strategy to extract and model background information, improving the performance and robustness of hyperspectral anomaly detection algorithms.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Geochemistry & Geophysics
Limei Wang, Sijie Niu, Xizhan Gao, Kun Liu, Feixia Lu, Qi Diao, Jiwen Dong
Summary: A new fast high-order SSC (FHoSSC) method with cumulative MRF algorithm is proposed to capture high-order information and improve segmentation accuracy in hyperspectral image segmentation.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Agriculture, Multidisciplinary
Di Song, Kithmee De Silva, Matthew D. Brooks, Mohammed Kamruzzaman
Summary: This study aimed to accurately predict shoot and root biomass of Arabidopsis by eliminating irrelevant information from hyperspectral data. Different segmentation techniques were used to remove the background, and comparing the results of image processing, the spectral information-based normalized difference vegetation index (NDVI) segmentation method yielded better results for shoot and root biomass prediction. Three wavelength optimization methods were used to extract useful information, and the bootstrapping soft shrinkage (BOSS) method selected the least number of wavelengths and produced better results for both shoot and root biomass predictions. Only 19 informative wavelengths were selected, and the partial least squares regression (PLSR) models accurately predicted shoot and root biomass. The results indicated the effectiveness of hyperspectral imaging for accurately predicting shoot and root biomass of Arabidopsis.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Geochemistry & Geophysics
Xue Shi, Yu Li
Summary: Accurately modeling the distributions of spectral intensities is crucial for obtaining accurate image segmentation results. In this research, a hierarchical gamma mixture model (HGaMM) is proposed for high-resolution SAR image segmentation. By building a statistical model using HGaMM and effectively utilizing spectral intensity information, the proposed algorithm outperforms traditional algorithms and achieves accurate segmentation results.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Automation & Control Systems
Renhai Chen, Shimin Yuan, Chenlin Ma, Huihui Zhao, Zhiyong Feng
Summary: This article discusses the advantages and disadvantages of GPS and cellular-based positioning. It highlights the challenges of cellular-based positioning and proposes a novel algorithm called THMM to improve its accuracy. The algorithm is optimized based on the characteristics of cellular-based data and the experimental results demonstrate its effectiveness.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Computer Science, Artificial Intelligence
Xiaohong Liu, Kangdi Shi, Zhe Wang, Jun Chen
Summary: Current deep-learning-based Video Super-Resolution methods using videos generated by the camera ISP as inputs are suboptimal due to information loss and inconsistency. This study proposes a new VSR method that utilizes camera sensor data directly, with a carefully built Raw Video Dataset. Through Successive Deep Inference and reconstruction modules, the proposed method achieves superior VSR results compared to the state-of-the-art by leveraging the informativeness of camera raw data and separation of super-resolution and color correction processes.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Shujun Yang, Junhui Hou, Yuheng Jia, Shaohui Mei, Qian Du
Summary: The novel classification scheme SP-DLRR demonstrates superior performance in hyperspectral image classification by utilizing classification-guided superpixel segmentation and discriminative low-rank representation.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Geochemistry & Geophysics
Kai Ren, Weiwei Sun, Xiangchao Meng, Gang Yang, Jiangtao Peng, Jingfeng Huang
Summary: This article presents a locally optimized image segmentation fusion (LOISF) framework for HS super-resolution reconstruction, which preserves spatial details and texture while improving image quality in LR HS and HR MS images through the construction of a joint fusion model and a convex optimization solution.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Mathematics, Interdisciplinary Applications
Abdessatar Souissi, El Gheteb Soueidi
Summary: This paper aims to expand on previous research on quantum hidden Markov processes by introducing the concept of entangled hidden Markov processes. These are hidden Markov processes in which the hidden processes themselves are entangled Markov processes. The paper provides an explicit expression for the joint expectation of these processes and demonstrates that the approach also applies to the classical case.
CHAOS SOLITONS & FRACTALS
(2023)
Article
Multidisciplinary Sciences
Qian Wang, Qingli Li, Mei Zhou, Zhen Sun, Hongying Liu, Yiting Wang
Article
Optics
Xi Liu, Mei Zhou, Song Qiu, Li Sun, Hongying Liu, Qingli Li, Yiting Wang
Article
Biochemical Research Methods
Qian Wang, Jianbiao Wang, Mei Zhou, Qingli Li, Yiting Wang
BIOMEDICAL OPTICS EXPRESS
(2017)
Article
Instruments & Instrumentation
Qian Wang, Qingli Li, Mei Zhou, Li Sun, Song Qiu, Yiting Wang
APPLIED SPECTROSCOPY
(2018)
Article
Instruments & Instrumentation
Jing Song, Menghan Hu, Jiansheng Wang, Mei Zhou, Li Sun, Song Qiu, Qingli Li, Zhen Sun, Yiting Wang
INFRARED PHYSICS & TECHNOLOGY
(2019)
Article
Biochemical Research Methods
Jiansheng Wang, Qingli Li
JOURNAL OF BIOMEDICAL OPTICS
(2018)
Article
Optics
Yifan Duan, Jiansheng Wang, Menghan Hu, Mei Zhou, Qingli Li, Li Sun, Song Qiu, Yiting Wang
OPTICS AND LASER TECHNOLOGY
(2019)
Article
Instruments & Instrumentation
Menghan Hu, Qingli Li
INFRARED PHYSICS & TECHNOLOGY
(2019)
Article
Engineering, Electrical & Electronic
Menghan Hu, Guangtao Zhai, Rong Xie, Xiongkuo Min, Qingli Li, Xiaokang Yang, Wenjun Zhang
IEEE TRANSACTIONS ON BROADCASTING
(2020)
Article
Environmental Sciences
Xi Chen, Jiaxu Huang, Sheng Wang, Gongjian Zhou, Hongkai Gao, Min Liu, Ye Yuan, Laiwen Zheng, Qingli Li, Honggang Qi
Summary: This study improves the performance of rainfall-runoff models by utilizing short lag-times, and proposes a model with long and short lag-time attention mechanism to enhance accuracy. The results indicate that the proposed model outperforms the state-of-the-art counterparts at mesoscale stations with humid climates.
Proceedings Paper
Computer Science, Artificial Intelligence
Li Sun, Song Qiu, Qingli Li, Hongying Liu, Mei Zhou
ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2017, PT I
(2018)
Proceedings Paper
Computer Science, Information Systems
Kaixuan Zhang, Yang Xu, Li Sun, Song Qiu, Qingli Li
MULTIMEDIA MODELING, MMM 2018, PT II
(2018)
Proceedings Paper
Optics
JianSheng Wang, Mei Zhou, Qingli Li, Li Sun, Song Qiu
TENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2018)
(2018)
Article
Optics
Luo Xu, Tian Wang-Xiao, Huang Yi, Wu Xiu-Ling, Li Lin-Hui, Chen Peng, Zhu Xin-Guo, Li Qing-Li, Chu Jun-Hao
JOURNAL OF INFRARED AND MILLIMETER WAVES
(2018)
Proceedings Paper
Acoustics
Zhonglin Sun, Li Sun, Qingli Li
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2018)