Article
Computer Science, Information Systems
Ines Brusch
Summary: This paper explores how image data can be automatically analyzed using a combination of image analysis methods and fuzzy cluster algorithms to predict user preferences. Depending on the diversity of the images, either SVM or CNN provide the best basis for preference prediction.
INFORMATION & MANAGEMENT
(2022)
Article
Environmental Sciences
Guanzhou Chen, Xiaoliang Tan, Beibei Guo, Kun Zhu, Puyun Liao, Tong Wang, Qing Wang, Xiaodong Zhang
Summary: Semantic segmentation is a fundamental task in remote sensing image analysis, and our proposed SDFCNv2 framework shows better performance on remote sensing images compared to the SDFCNv1 framework, increasing the mIoU metric by up to 5.22% while using only about half of the parameters.
Article
Automation & Control Systems
Elene Firmeza Ohata, Gabriel Maia Bezerra, Joao Victor Souza das Chagas, Aloisio Vieira Lira Neto, Adriano Bessa Albuquerque, Victor Hugo C. de Albuquerque, Pedro Pedrosa Reboucas Filho
Summary: The new coronavirus has become a global pandemic, infecting over 1 million people and causing more than 50 thousand deaths. A new method for automatically detecting COVID-19 infection based on chest X-ray images has been proposed and shown to be efficient in detecting COVID-19 in X-ray images.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2021)
Article
Engineering, Electrical & Electronic
Okan Bilge Ozdemir, Alper Koz
Summary: In this article, a deep learning-based hyperspectral gas detection method is proposed, which converts radiance data to luminance-temperature data and utilizes a combination of convolutional neural network (CNN), autoencoder-based network, and a fully connected network for detection. The method achieves superior performance in detecting methane and sulfur dioxide gases compared to traditional spectral angle mapper and adaptive cosine estimator methods using LWIR hyperspectral images. The ablation study demonstrates the contribution of the proposed system by evaluating different combinations of direct classification and unmixing methods.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Ruizhi Han, Zhulin Liu, C. L. Philip Chen
Summary: This paper presents a new variant model of the Broad Learning System (BLS) for accurate diagnosis of Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) using MRI images. The proposed model integrates multi-scale convolution features and abstract features to achieve precise diagnosis. Experimental results demonstrate that the proposed model outperforms other methods in AD and MCI diagnostic tasks.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Ines Brusch
Summary: This paper demonstrates how image data can be automatically analyzed using a combination of image analysis methods and fuzzy cluster algorithms to predict user preferences, which can help companies make targeted offers.
INFORMATION & MANAGEMENT
(2022)
Article
Geochemistry & Geophysics
Haiwen Du, Yu An, Qing Ye, Jiulin Guo, Lu Liu, Dongjie Zhu, Conrad Childs, John Walsh, Ruihai Dong
Summary: Seismic interpretation is a fundamental method for obtaining information about subsurface reservoirs. However, deep learning algorithms often underperform on seismic data due to inconsistent noise patterns. To address this issue, a noise pattern transfer framework is proposed to improve the generality of seismic interpretation algorithms. Experimental results demonstrate the effectiveness of this approach.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Kunlong Zheng, Yifan Dong, Wei Xu, Yun Su, Pingping Huang
Summary: In recent years, significant progress has been made in object detection in remote sensing images due to the rapid development of convolutional neural networks (CNNs). However, most existing methods focus on training suitable network models to extract more powerful features, overlooking the importance of embedding knowledge in detection. This study proposes a method to embed knowledge and demonstrates through experiments that it outperforms the baseline method.
Article
Computer Science, Artificial Intelligence
M. Khojaste-Sarakhsi, Seyedhamidreza Shahabi Haghighi, S. M. T. Fatemi Ghomi, Elena Marchiori
Summary: Alzheimer's Disease (AD) is an irreversible neurodegenerative disease that leads to a gradual decline in cognitive abilities. The early detection of AD is challenging due to subtle changes in biomarkers, which are primarily detectable in different neuroimaging techniques. This survey examines approximately 100 published papers since 2019 that utilize deep learning models such as CNN, RNN, and generative models for AD diagnosis. Additionally, it investigates around 60 papers that apply trending topics or architectures for AD research. The challenges in this field are categorized and explained in terms of data, methodology, and clinical adoption. The paper concludes by discussing future perspectives and providing recommendations for further studies in AD diagnosis.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2022)
Article
Engineering, Electrical & Electronic
Jinhe Su, JiaJia Liao, Dujuan Gu, Zongyue Wang, Guorong Cai
Summary: The paper proposes a novel network called MKD-Net for multiscale keypoint detection in aerial imagery, which effectively addresses the limitation of detecting multiscale objects in aerial scenes with keypoint-based detectors. Experimental results show promising performance compared to baseline networks.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Jing Liu, Yang Li, Feng Zhao, Yi Liu
Summary: In this study, a spectral fractional-differentiation (SFD) feature is proposed to extract effective features for the terrain classification of hyperspectral remote-sensing images (HRSIs). A criterion for selecting the fractional-differentiation order based on maximizing data separability is also introduced. The effectiveness of the SFD feature is verified using four traditional classifiers and five network models, and the results show that the SFD feature can effectively improve the accuracy of terrain classification for HRSIs, especially in cases with small-size training samples.
Article
Automation & Control Systems
Chunfeng Lian, Mingxia Liu, Yongsheng Pan, Dinggang Shen
Summary: This article proposes an attention-guided deep-learning framework to extract multilevel discriminative sMRI features for dementia diagnosis, achieving superior performance compared to state-of-the-art methods in both tasks of AD diagnosis and MCI conversion prediction.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Information Systems
Hiba Mzoughi, Ines Njeh, Mohamed Ben Slima, Ahmed Ben Hamida, Chokri Mhiri, Kheireddine Ben Mahfoudh
Summary: This paper investigates a fully automatic Computer-Aided Diagnosis (CAD) tool for brain glioblastomas tumor exploration based on convolutional Deep-Learning algorithms. The CAD tool includes three steps: pre-processing, segmentation, and classification. Experimental results demonstrate the efficiency and accuracy of the CAD tool in diagnosing brain glioblastomas tumors, highlighting its significance in improving diagnostic performance.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Hyunmin Kim, Hyug-Gi Kim, Jang-Hoon Oh, Kyung Mi Lee
Summary: This study proposes an automated deep-learning model for meningioma detection using the dural tail sign. The model achieved a sensitivity of 82.22% and a false positive average of 29.73 on sagittal CE T1WI. The specificity and false positive average on the normal dataset were 17.65% and 3.16, respectively. The model can assist radiologists in identifying meningiomas based on the detection of dural tail signs, thereby facilitating the reading process.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2023)
Article
Computer Science, Interdisciplinary Applications
Batuhan Sariturk, Dursun Zafer Seker, Ozan Ozturk, Bulent Bayram
Summary: This study investigates the performance evaluation of convolutional neural network architectures in building segmentation from high-resolution images. The results show that deeper architectures can provide better results even with limited data, and shallower architectures perform well with lower computational cost, making them useful for geographic applications.
EARTH SCIENCE INFORMATICS
(2022)