Article
Forestry
Xiangsuo Fan, Lin Chen, Xinggui Xu, Chuan Yan, Jinlong Fan, Xuyang Li
Summary: This paper proposes a hierarchical convolutional recurrent neural network (HCRNN) model that combines CNN and RNN modules for pixel-level classification of multispectral remote sensing images. The experimental results show that the HCRNN model achieves an overall accuracy of 97.62% on the Sentinel-2 dataset, improving the performance by 1.78% compared to the RNN model. Furthermore, the study focuses on the changes in forest cover in the study area of Laibin City, Guangxi Zhuang Autonomous Region.
Article
Environmental Sciences
Wei Huang, Zeping Liu, Hong Tang, Jiayi Ge
Summary: This paper introduces a novel method for sequentially delineating exterior and interior contours of rooftops with holes from VHR aerial images, integrating semantic segmentation and polygon delineation. By using a convolutional recurrent neural network, this method effectively delineates rooftops with both one and multiple polygons, outperforming existing methods in terms of visual results and six statistical indicators.
Article
Remote Sensing
Wei Zhang, Ping Tang, Lijun Zhao
Summary: Traditional CNN methods for land-cover classification have issues with high computation cost and low efficiency, while methods based on FCN have opened up new possibilities for efficient land-cover classification.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2021)
Article
Computer Science, Artificial Intelligence
Lei Bi, Jinman Kim, Tingwei Su, Michael Fulham, David Dagan Feng, Guang Ning
Summary: In this study, a deep multi-scale resemblance network (DMRN) was developed for the classification of adrenal masses in CT images. By leveraging paired convolutional neural networks (CNNs) to evaluate intra-class similarities, inter-class separability was improved and the influence of imbalanced training data was reduced through the augmentation of training data. The results demonstrated that the DMRN method outperformed the state-of-the-art approaches in the classification of adrenal masses.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2022)
Article
Geochemistry & Geophysics
Guoqing Zhou, Weiguang Liu, Qiang Zhu, Yanling Lu, Yu Liu
Summary: In recent years, models based on fully convolutional neural networks have been proposed to improve accuracy but ignored computational efficiency. This research presents an innovative deep learning model, ECA-MobileNetV3(large)+SegNet, which simultaneously considers both aspects. By modifying the encoder and decoder structures, the proposed model achieves significant improvement in performance and reduces the number of parameters.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Wei Huang, Hong Tang, Penglei Xu
Summary: In this article, a multitask learning approach is proposed to predict rooftop corners by using attention learned from boundaries. The approach simulates the process of manual delineation of rooftops' outline and achieves accurate boundaries with sharp corners and straight lines. Its performance surpasses state-of-the-art methods for instance segmentation.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Biology
Olaide N. Oyelade, Absalom E. Ezugwu, Hein S. Venter, Seyedali Mirjalili, Amir H. Gandomi
Summary: The task of classifying and localizing abnormalities in medical images is challenging. This study proposes a dual branch deep learning framework that combines two different convolutional neural network architectures to achieve classification and localization of abnormalities. Experimental results validate the performance of this method in achieving both classification and localization.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Information Systems
Harmandeep Singh Gill, Ganpathy Murugesan, Baljit Singh Khehra, Guna Sekhar Sajja, Gaurav Gupta, Abhishek Bhatt
Summary: Smart imaging devices have been widely used in agriculture, especially in fruit recognition and classification. Deep learning models, such as CNN, RNN, and LSTM, have been proposed to enhance the accuracy and quantitative analysis of fruit classification. This paper introduces a method combining Type-II Fuzzy, TLBO, and deep learning models to improve fruit image recognition and classification.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Biochemical Research Methods
Yuan Li, Xu Shi, Liping Yang, Chunyu Pu, Qijuan Tan, Zhengchun Yang, Hong Huang
Summary: This paper proposes a multi-layer collaborative generative adversarial transformer (MC-GAT) for cholangiocarcinoma (CCA) classification from hyperspectral pathological images. MC-GAT consists of a generator and a discriminator, which improve the model's generalization and discriminating power. Experimental results show that MC-GAT achieves better classification results compared to other methods.
BIOMEDICAL OPTICS EXPRESS
(2022)
Article
Computer Science, Information Systems
Anik Sen, Kaushik Deb
Summary: Knowledge extraction from soccer videos has diverse applications such as context-based advertisement, content-based video retrieval, match summarization, and highlight extraction. Challenging factors including overlapping soccer actions and uncontrolled video capturing conditions require accurate action detection. This study combines Convolutional Neural Network and Recurrent Neural Network to classify soccer actions of different lengths.
Article
Geochemistry & Geophysics
Zeping Liu, Hong Tang, Wei Huang
Summary: Recently, a novel network called LSI-RNN is introduced to directly detect line segments and solve the issue of local ambiguity in building outline recognition. Experimental results show that LSI-RNN consistently outperforms other methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Jiaqing Zhang, Jie Lei, Weiying Xie, Daixun Li
Summary: The fusion of hyperspectral and LiDAR images is crucial for accurate classification and recognition in remote sensing. This study proposes a method that combines a binary convolutional neural network and a graph convolutional network with invariant attributes to overcome the challenges of constructing effective graph structures. The method utilizes a joint detection framework to simultaneously learn features from regular and irregular regions, resulting in an enhanced structural representation of the images. Experimental results demonstrate the superior performance of the proposed method in hyperspectral image analysis tasks.
Article
Engineering, Electrical & Electronic
Peng Wang, Zhongchen He, Ying Zhang, Gong Zhang, Hongchao Liu, Henry Leung
Summary: This study proposes a multispectral pansharpening method based on a multisequence convolutional recurrent neural network (MCRNN). The MCRNN consists of two subnetworks, namely shallow feature extraction and deep feature fusion, which effectively fuse the spatial and spectral information of the PAN and MS images. Experimental results show that the proposed MCRNN outperforms traditional pansharpening methods.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Review
Environmental Sciences
Abhasha Joshi, Biswajeet Pradhan, Shilpa Gite, Subrata Chakraborty
Summary: Reliable and timely crop-yield prediction and mapping are crucial for food security and decision making. Remote sensing data and deep learning algorithms have been effective tools for crop mapping and yield prediction. This study provides a thorough systematic review of the important scientific works related to state-of-the-art deep learning techniques and remote sensing in crop mapping and yield estimation.
Article
Astronomy & Astrophysics
Kai Feng, Long Xu, Dong Zhao, Sixuan Liu, Xin Huang
Summary: Timely solar flare forecasting is hindered by data transmission delay, prompting the need to deploy compression models on satellites. Three compression methods (knowledge distillation, pruning, and quantization) were examined, along with a proposed assembled compression model that demonstrated effective compression and maintained accuracy.
ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES
(2023)
Article
Biochemical Research Methods
Aline Silva da Cruz, Maria Margarida Drehmer, Wagner Baetas-da-Cruz, Joao Carlos Machado
Summary: This study quantified microcirculation cerebral blood flow in a rat model of ischemic stroke using ultrasound biomicroscopy and ultrasound contrast agents. The results showed high sensitivity and specificity of this method, making it a valuable tool for preclinical studies.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Christina Dalla, Ivana Jaric, Pavlina Pavlidi, Georgia E. Hodes, Nikolaos Kokras, Anton Bespalov, Martien J. Kas, Thomas Steckler, Mohamed Kabbaj, Hanno Wuerbel, Jordan Marrocco, Jessica Tollkuhn, Rebecca Shansky, Debra Bangasser, Jill B. Becker, Margaret McCarthy, Chantelle Ferland-Beckham
Summary: Many funding agencies have emphasized the importance of considering sex as a biological variable in experimental design to improve the reproducibility and translational relevance of preclinical research. Omitting the female sex from experimental designs in neuroscience and pharmacology can result in biased or limited understanding of disease mechanisms. This article provides methodological considerations for incorporating sex as a biological variable in in vitro and in vivo experiments, including the influence of age and hormone levels, and proposes strategies to enhance methodological rigor and translational relevance in preclinical research.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Wenyu Gu, Dongxu Li, Jia-Hong Gao
Summary: We developed a precise and rapid method for positioning and labelling triaxial OPMs on a wearable magnetoencephalography (MEG) system, improving the efficiency of OPM positioning and labelling.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Kai Lin, Linhang Zhang, Jing Cai, Jiaqi Sun, Wenjie Cui, Guangda Liu
Summary: The article introduces an EEG feature map processing model for emotion recognition, which achieves significantly improved accuracy by fusing EEG information at different spatial scales and introducing a channel attention mechanism.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
John E. Parker, Asier Aristieta, Aryn H. Gittis, Jonathan E. Rubin
Summary: This work presents a toolbox that implements a methodology for automated classification of neural responses based on spike train recordings. The toolbox provides a user-friendly and efficient approach to detect various types of neuronal responses that may not be identified by traditional methods.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Yun Liang, Ke Bo, Sreenivasan Meyyappan, Mingzhou Ding
Summary: This study compared the performance of SVM and CNN on the same datasets and found that CNN achieved consistently higher classification accuracies. The classification accuracies of SVM and CNN were generally not correlated, and the heatmaps derived from them did not overlap significantly.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Antonino Visalli, Maria Montefinese, Giada Viviani, Livio Finos, Antonino Vallesi, Ettore Ambrosini
Summary: This study introduces an analytical strategy that allows the use of mixed-effects models (LMM) in mass univariate analyses of EEG data. The proposed method overcomes the computational costs and shows excellent performance properties, making it increasingly important in the field of neuroscience.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Xavier Cano-Ferrer, Alexandra Tran -Van -Minh, Ede Rancz
Summary: This study developed a novel rotation platform for studying neural processes and spatial navigation. The platform is modular, affordable, and easy to build, and can be driven by the experimenter or animal movement. The research demonstrated the utility of the platform, which combines the benefits of head fixation and intact vestibular activity.
JOURNAL OF NEUROSCIENCE METHODS
(2024)