Article
Engineering, Electrical & Electronic
Jiun-Yu Sung
Summary: This study focuses on real-time localization in infrared optical wireless communication (IR-OWC) and proposes a testbed for hybrid communications. Two-stage processes are introduced to increase the localization speed, and comprehensive discussions on time relevant issues are performed. The testbed is implemented under complex environmental conditions to accurately assess its practical performance.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
A. N. Omara, Nouf Saeed Alotaibi
Summary: This paper presents a compressed sensing method for image representation, which represents the image using coefficients of few bases. Efforts have been made to enhance the perceptual levels of this technique by recalculating the coefficients based on SSIM criteria. The paper proposes a backward enhancement technique based on SSIM criteria, which selects bases with good perceptual effects and removes unnecessary bases that may distort the image perceptually.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Engineering, Mechanical
Xingyuan Wang, Qi Ren, Donghua Jiang
Summary: This paper proposes an efficient and adjustable visual image encryption scheme combining a 6D hyperchaotic system, compressive sensing, and Bezier curve embedding. The scheme shows high decryption quality, visual security, robustness, and operating efficiency, outperforming existing related schemes.
NONLINEAR DYNAMICS
(2021)
Article
Computer Science, Software Engineering
Kushin Mukherjee, Brian Yin, Brianne E. Sherman, Laurent Lessard, Karen B. Schloss
Summary: People's associations between colors and concepts influence their ability to interpret color meanings. Even if a concept is not strongly associated with any colors, it can be disambiguated through comparison with other concepts. The semantic discriminability theory explains how people infer meaning from visual features and suggests that the capacity for semantic discriminability is limited by the difference in color-concept associations. Two experiments supported this theory, showing that the ability to produce semantically discriminable colors is constrained by statistical distance, and colors can communicate meaning even for concepts previously considered non-colorable. These results emphasize the importance of colors in visual communication.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2022)
Article
Computer Science, Artificial Intelligence
Yue Pan, Dechang Pi, Junfu Chen, Han Meng
Summary: A novel deep perceptual patch generative adversarial network (FDPPGAN) was proposed to solve the pan-sharpening problem in remote sensing images fusion. The algorithm utilized a perception generator and a patch discriminator to generate high-resolution multispectral images, which outperformed state-of-the-art algorithms in both subjective and objective evaluations based on experiments on QuickBird and WorldView datasets.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Shuming Xiao, Shaoju Wang, Lin Chang
Summary: Compressive sensing (CS) technology is utilized in space optical remote sensing image acquisition to achieve quick and accurate image retrieval for wireless sensor networks. The FFPL-EDRNet, featuring fused features and perceptual loss encoder-decoder residual network, enhances image reconstruction quality by combining features and utilizing perceptual loss functions for more accurate results.
Article
Engineering, Electrical & Electronic
Lihao Zhuang, Liquan Shen, Zhengyong Wang, Yinyi Li
Summary: This paper proposes a novel priors guided adaptive underwater compressive sensing framework, dubbed UCSNet, which can effectively sample and reconstruct underwater images under a fixed low sampling ratio. The framework consists of three sub-networks: underwater priors extraction and guidance network, sampling matrix generation network, and channel-wise reconstruction network. Experimental results demonstrate that our framework outperforms other state-of-the-art methods in terms of underwater image reconstruction quality.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Remote Sensing
Chunyu Zhu, Rongyuan Dai, Liwei Gong, Liangbo Gao, Na Ta, Qiong Wu
Summary: This study proposes a new deep learning algorithm, AMGSGAN, that improves the fusion of hyperspectral and multispectral remote sensing images. The algorithm utilizes an adaptive multi-perceptual field implicit guided sampling approach to enhance the long-range perception of the sampling process. Comparison experiments demonstrate the effectiveness of the proposed algorithm.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)
Article
Computer Science, Information Systems
Xiuli Chai, Haiyang Wu, Zhihua Gan, Daojun Han, Yushu Zhang, Yiran Chen
Summary: A novel double color image encryption algorithm combining 2D compressive sensing with an embedding technique is proposed in this paper, achieving compression and encryption simultaneously and obtaining visually meaningful cipher images. Confusion of the compressed cipher images is done by index sequences generated from a 6D hyperchaotic system, while the relationship of the algorithm with plain images is enhanced by embedding feature parameters into the carrier image.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Sidi Lu, Xin Yuan, Aggelos K. Katsaggelos, Weisong Shi
Summary: In this work, reinforcement learning is applied to video compressive sensing to adapt the compression ratio. The gap in previous studies of how to adapt B in the video SCI system is filled using RL. An RL model and various convolutional neural networks are employed to achieve adaptive sensing of video SCI systems. Additionally, the performance of an object detection network is utilized for RL-based adaptive video compressive sensing. This proposed adaptive SCI method can be implemented in low cost and real time, and takes the technology one step further towards real applications of video SCI.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2023)
Article
Computer Science, Hardware & Architecture
Rang Liu, Ming Li, Honghao Luo, Qian Liu, A. Lee Swindlehurst
Summary: Integrated sensing and communication (ISAC) is a key solution for addressing spectrum congestion and increasing demands. By sharing resources and using reconfigurable intelligent surface (RIS) technology, ISAC achieves higher efficiencies. This article analyzes the potential of deploying RIS in ISAC systems to improve communication and sensing performance, discusses existing explorations, presents a case study, and outlines open challenges and research directions.
IEEE WIRELESS COMMUNICATIONS
(2023)
Article
Physics, Fluids & Plasmas
Emiliano Perez Ipina, Brian A. Camley
Summary: In a cluster of cells, individual cells can sense chemical gradients more accurately by integrating concentration measurements. However, when cells have limited positional information within the cluster, the accuracy of collective gradient sensing is reduced.
Article
Engineering, Electrical & Electronic
Sheng-Jie Wang, Po-Ning Chen, Shin-Lin Shieh, Yu-Chih Huang
Summary: The paper revisits the problem of probabilistic caching and proposes a novel algorithm based on Lagrange multipliers and simulated annealing to improve the content delivery success probability. The enhanced algorithm shows significant improvement in CDSP and is less sensitive to initial values when dealing with hundreds of contents. Additionally, an alternative metric of maximizing weighted CDSP is introduced to increase overall system throughput, showing similar conclusions to the original algorithm.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Zhongxiang Wei, Fan Liu, Christos Masouros, Nanchi Su, Athina P. Petropulu
Summary: Integrated sensing and communication (ISAC) is a candidate 6G technology that aims to unify the operations of future networks. While information security challenges arise from including information signaling in the waveform, the sensing capability in ISAC transmission offers opportunities for secure techniques. This article discusses the challenges, opportunities, and approaches to securing ISAC transmission, as well as the potential of using sensing capability for obtaining target information.
IEEE COMMUNICATIONS MAGAZINE
(2022)
Article
Materials Science, Multidisciplinary
Xiang Wan, Zi Ai Huang, Jia Wei Wang, Wen Hao Wang, Bai Yang Li, Qiang Xiao, Xu Jie Wang, Jia Chen Wan, Tie Jun Cui
Summary: This article proposes the idea of using a single information metasurface to achieve electromagnetic sensing and wireless communication. The metasurface can function as a remote sensor for imaging and locating targets, as well as transmitting sensing information to local users by modulating the radiation phase of directional beams. This concept has significant implications for the future information society.
ADVANCED MATERIALS TECHNOLOGIES
(2023)
Article
Engineering, Electrical & Electronic
Yan Wang, Shiying Yin, Shuyuan Zhu, Zhan Ma, Ruiqin Xiong, Bing Zeng
Summary: A new three-stage deep convolutional neural network (NTSDCN) is proposed for image demosaicking, consisting of the LC-LRU and FG-PFU units. The NTSDCN significantly outperforms state-of-the-art methods according to experimental results, achieving better performance in RGB image reconstruction.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Yang Wang, Xiaopeng Fan, Ruiqin Xiong, Debin Zhao, Wen Gao
Summary: In this paper, a neural network based enhancement to inter prediction (NNIP) is proposed for improving the coding performance of inter prediction. Experimental results show that NNIP achieves higher BD-rate reduction compared to traditional HEVC coding.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Jing Zhao, Ruiqin Xiong, Jiyu Xie, Boxin Shi, Zhaofei Yu, Wen Gao, Tiejun Huang
Summary: Conventional digital cameras require still scenes for clear images, while spike cameras can record continuous variations in dynamic light intensity, making them highly suitable for high-speed motion scenes. This paper proposes an image reconstruction approach for spike cameras, employing adaptive temporal filtering to take advantage of temporal correlation. Experimental results demonstrate that this approach outperforms existing methods, producing high-quality reconstructed images.
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING
(2022)
Article
Engineering, Electrical & Electronic
Jin Wang, Longhua Sun, Ruiqin Xiong, Yunhui Shi, Qing Zhu, Baocai Yin
Summary: This paper proposes a method that uses edge consistency between normal map and depth map as a constraint to guide the restoration of the depth map, and promotes the piece-wise smoothness of the depth map using a reweighted graph Laplacian regularizer. Experimental results demonstrate the superior performance of the proposed method compared to other state-of-the-art methods, especially in edge areas and noisy conditions.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Rui Zhao, Ruiqin Xiong, Ziluo Ding, Xiaopeng Fan, Jian Zhang, Tiejun Huang
Summary: Optical flow estimation is a fundamental task, but unsupervised methods suffer in scenarios with large displacement, small objects, and occlusions. In this study, we propose a novel optical flow network based on a decoder with multi-scale kernels, incorporating innovative ideas to enhance performance, including various motion-related information as input, multi-scale update units, and image-guided up-sampling loss.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Multidisciplinary Sciences
Jon B. Toledo, Tanweer Rashid, Hangfan Liu, Lenore Launer, Leslie M. Shaw, Susan R. Heckbert, Michael Weiner, Sudha Seshadri, Mohamad Habes
Summary: Tau PET tracers have shown strong associations with clinical outcomes in individuals with cognitive impairment and cognitively unremarkable elderly individuals. The machine learning-derived SPARE-Tau index successfully detects pathology in the earliest disease stages and accurately predicts disease progression compared to a priori-based region of interest approaches (ROI).
Article
Computer Science, Interdisciplinary Applications
Zihao Liu, Zhuowei Li, Zhiqiang Hu, Qing Xia, Ruiqin Xiong, Shaoting Zhang, Tingting Jiang
Summary: In this paper, we propose a method that applies contrastive learning (CL) to the task of medical image segmentation, aiming to learn more discriminative representation. Our method achieves state-of-the-art results across multiple domains and demonstrates robustness in the limited-data scenario, by performing patch-level tugging and repulsing, and utilizing an uncertainty-aware feature re-weighting block (UAFR).
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Medicine, General & Internal
Tanweer Rashid, Karl Li, Jon B. Toledo, Ilya Nasrallah, Nicholas M. Pajewski, Sudipto Dolui, John Detre, David A. Wolk, Hangfan Liu, Susan R. Heckbert, R. Nick Bryan, Jeff Williamson, Christos Davatzikos, Sudha Seshadri, Lenore J. Launer, Mohamad Habes
Summary: This study suggests that intensive blood pressure (BP) treatment, compared with standard treatment, was associated with a slower increase of white matter lesions (WMLs) and improved diffusion tensor imaging, fractional anisotropy (FA), and cerebral blood flow (CBF) changes in several vulnerable brain regions.
Article
Medicine, General & Internal
Sokratis Charisis, Tanweer Rashid, Hangfan Liu, Jeffrey B. Ware, Paul N. Jensen, Thomas R. Austin, Karl Li, Elyas Fadaee, Saima Hilal, Christopher Chen, Timothy M. Hughes, Jose Rafael Romero, Jon B. Toledo, Will T. Longstreth, Timothy J. Hohman, Ilya Nasrallah, R. Nick Bryan, Lenore J. Launer, Christos Davatzikos, Sudha Seshadri, Susan R. Heckbert, Mohamad Habes
Summary: This study conducted a whole-brain investigation of enlarged perivascular spaces (ePVSs) and found that increased ePVS burden in the basal ganglia and thalamus is associated with cerebral small vessel disease (cSVD), highlighting the clinical importance of ePVSs in these locations.
Article
Computer Science, Artificial Intelligence
Hangfan Liu, Michel J. Grothe, Tanweer Rashid, Miguel A. Labrador-Espinosa, Jon B. Toledo, Mohamad Habes
Summary: In this paper, a method is proposed to improve clustering of subjects in neuroimaging applications by exploiting the underlying clusters of features and suppressing noise through nonnegative matrix tri-factorization and adaptive regularization. Experimental results on synthetic data and real magnetic resonance imaging (MRI) data demonstrate the superiority of the proposed method.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Neurosciences
Karl Li, Tanweer Rashid, Jinqi Li, Nicolas Honnorat, Anoop Benet Nirmala, Elyas Fadaee, Di Wang, Sokratis Charisis, Hangfan Liu, Crystal Franklin, Mallory Maybrier, Haritha Katragadda, Leen Abazid, Vinutha Ganapathy, Vijaya Lakshmi Valaparla, Pradeepthi Bagudu, Eliana Vasquez, Leigh Solano, Geoffrey Clarke, Gladys Maestre, Tim Richardson, Jamie Walker, Peter T. Fox, Kevin Bieniek, Sudha Seshadri, Mohamad Habes
Summary: This article introduces a new data repository, the South Texas Alzheimer's Disease research center repository, designed to study and validate the relationship between neuroimaging markers and neurological changes. The repository includes a diverse range of dementia samples, spans a wide age range, and utilizes advanced imaging protocols and MRI-guided histopathological analysis to improve diagnosis and understanding of neurodegenerative disorders.
JOURNAL OF ALZHEIMERS DISEASE
(2023)
Proceedings Paper
Engineering, Electrical & Electronic
Hangfan Liu, Karl Li, Jon B. Toledo, Mohamad Habes
Summary: Aging subjects with neurodegenerative conditions have heterogeneous disease biology and different disease phenotypes. Clinical data play a crucial role in understanding the disease heterogeneity, but they are often affected by noise, leading to errors in clustering. This study introduces an adaptive regularization method based on coefficient distribution modeling to remove noise and enhance clustering effectiveness.
2022 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 22)
(2022)
Article
Clinical Neurology
Jon B. Toledo, Hangfan Liu, Michel J. Grothe, Tanweer Rashid, Lenore Launer, Leslie M. Shaw, Haykel Snoussi, Susan Heckbert, Michael Weiner, John Q. Trojanwoski, Sudha Seshadri, Mohamad Habes
Summary: This study evaluated the associations between magnetic resonance imaging (MRI) atrophy and flortaucipir positron emission tomography (PET) clusters across the Alzheimer's disease (AD) spectrum. The results showed that different clusters were associated with the apolipoprotein E genotype and white matter hyperintensity volumes. Moreover, only the hippocampal sparing atrophy cluster showed a specific association with brain aging imaging index. Tau clusters had stronger clinical associations than atrophy clusters. Tau and atrophy clusters were partially associated.
ALZHEIMERS & DEMENTIA-TRANSLATIONAL RESEARCH & CLINICAL INTERVENTIONS
(2022)
Article
Computer Science, Information Systems
Chong Mou, Jian Zhang, Xiaopeng Fan, Hangfan Liu, Ronggang Wang
Summary: This paper proposes a novel collaborative attention network (COLA-Net) for image restoration, which combines local and non-local attention mechanisms to restore image content in areas with complex textures and highly repetitive details. By developing an effective and robust patch-wise non-local attention model, long-range feature correspondences are captured.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Jing Zhao, Ruiqin Xiong, Hangfan Liu, Jian Zhang, Tiejun Huang
Summary: The paper introduces a spike-to-image neural network for dynamic scene reconstruction from continuous spike streams, utilizing a hierarchical architecture to handle noise and high-speed motion. Experimental results show that the proposed network outperforms existing spike camera reconstruction methods.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
