Article
Engineering, Marine
Fan Yin, Chao Li, Haibin Wang, Leixin Nie, Yonglin Zhang, Chaonan Liu, Fan Yang
Summary: This paper proposes a new algorithm framework, BM-SEED, to enhance the resolution and improve the weak target detection capability of BTRs. By using an improved sub-band peak energy detection algorithm, it extracts the peak features of target trajectories in CBF-based BTRs and enhances weak targets through time-spatial autocorrelation analysis. Simulations and sea-trial data evaluations show that this method can improve the resolution of BTR targets to 1 degree with a signal-to-noise ratio of -20 dB.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Information Systems
Soo-Chang Pei, Chia-Yi Chen
Summary: This paper proposed an efficient technique for enhancing underwater images, addressing common issues such as haze, color distortion, and low contrast. By utilizing a precise model and methods like illumination fusion, the detailed and visual effects of underwater images are significantly improved, showing potential for underwater detection and exploration.
Article
Engineering, Electrical & Electronic
Abigail Lee-Leon, Chau Yuen, Dorien Herremans
Summary: In this paper, a novel receiver system utilizing Deep Belief Network (DBN) to combat signal distortion in underwater environments caused by Doppler effect and multi-path propagation is proposed. Results show that the DBN based receiver system outperforms traditional methods in handling received signals affected by the Doppler effect and multi-path propagation.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Yafen Dong, Xiaohong Shen, Haiyan Wang
Summary: This article proposes a bidirectional denoising autoencoder (BDAE) for robust representation learning of underwater acoustic target signal denoising. The results show that the BDAE can effectively learn robust representations for denoising underwater acoustic target signals.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Computer Science, Artificial Intelligence
Zhenyu Peng, Qingzhao Kong, Cheng Yuan, Rongyan Li, Hung-Lin Chi
Summary: This paper presents a novel denoising approach based on deep learning and signal processing to improve communication efficiency. The proposed algorithm achieved significant improvements over the traditional method in reducing the side effect of several common noises in construction sites.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Chemistry, Analytical
Heewon You, Sung-Hoon Byun, Youngmin Choo
Summary: This study proposes a method for detecting signals of interest (SOIs) using a hidden Markov model (HMM) without the need for separate training data. The accuracy of the detection is improved by optimizing the initial parameters using a genetic algorithm (GA). Furthermore, the use of multiple measurements from arrays contributes to further improvement in the detection results.
Article
Environmental Sciences
Yuehai Zhou, Feng Tong, Xiaoyu Yang
Summary: This paper proposes a new framework for underwater acoustic MIMO communication, which enhances communication performance through CoI cancellation. The effectiveness and merits of the proposed method are demonstrated in a sea trial experiment, showing higher output SNR and lower parameter sensitivity compared to traditional methods.
Article
Acoustics
Liu Biao, Jia Ning, Huang Jianchun, Guo Shengming, Xiao Dong, Ma Li
Summary: This paper proposes a method for describing underwater acoustic channels using an autoregressive model, which requires only a few parameters for characterization and can effectively simplify the establishment of channel models.
Article
Geochemistry & Geophysics
Itzhak Lior, Anthony Sladen, Diane Rivet, Jean-Paul Ampuero, Yann Hello, Carlos Becerril, Hugo F. Martins, Patrick Lamare, Camille Jestin, Stavroula Tsagkli, Christos Markou
Summary: The novel technique of distributed acoustic sensing (DAS) has great potential for underwater seismology by transforming standard telecommunication cables into dense arrays of seismo-acoustic sensors. Recording transient ground deformations by analyzing ambient noise, earthquakes, and phase velocities on DAS records is crucial for seismic monitoring. The apparent velocities play a significant role in detecting seismic deformations and phases, with DAS capabilities found to be similar to nearby broadband sensors underwater.
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH
(2021)
Article
Engineering, Multidisciplinary
Hong Yang, Wen-shuai Shi, Guo-hui Li
Summary: In this study, a new denoising method for underwater acoustic signals is proposed. The method utilizes optimized variational mode decomposition, fluctuation-based dispersion entropy threshold improvement, cosine similarity stationary threshold, and other techniques to effectively remove noise from the signals. Experimental results show that the proposed method achieves a significant improvement in denoising effect and has practical value.
DEFENCE TECHNOLOGY
(2023)
Article
Engineering, Marine
Yuzhi Zhang, Shumin Zhang, Bin Wang, Yang Liu, Weigang Bai, Xiaohong Shen
Summary: This paper proposes a deep learning-based signal detection method for underwater acoustic (UWA) OTFS communication, and compares it with conventional methods, showing that the proposed method achieves a lower bit error rate (BER).
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2022)
Article
Acoustics
Yuji Liu, Huixiu Chen, Biao Wang
Summary: This paper proposes a method for estimating the arrival direction of underwater acoustic signals, using two-channel real and imaginary covariance matrices as input signals for a convolutional neural network. Compared to the traditional MUSIC algorithm, the CNN algorithm shows higher accuracy and shorter estimation time in low SNR environments.
Article
Engineering, Marine
Zeju Wu, Yang Ji, Lijun Song, Jianyuan Sun
Summary: An algorithm combining color correction and detail enhancement is proposed to address underwater image issues. By improving nonlocal means denoising algorithm and U-Net, the algorithm effectively enhances underwater images while retaining edge features and texture information. The proposed algorithm demonstrates remarkable results in enhancing underwater images.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Xuefeng Zhong, Zilong Jiang, Fangjiong Chen, Xiaowu Zhu, Ming Tao
Summary: In this article, the throughput performance of time-slotted underwater acoustic sensor networks (UASNs) with guard time is investigated. The probability distributions of the arrival time of interfering packets and the packet overlap duration are derived based on the geographical node distribution. The expressions of the probability density functions (pdfs) of the signal-to-interference-plus-noise ratio (SINR), as well as the outage probability and normalized throughput for a typical link between two nodes, are obtained. The results show that properly selected guard time length can increase the throughput of time-slotted networks compared to those without guard time. Simulation results validate the theoretical findings and illustrate the interference characteristics in underwater networks.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Multidisciplinary
Tinggui Chen, Junrui Jiao, Dejie Yu
Summary: The study proposes a method based on the gradient acoustic-grating metamaterial (GAGM) for detecting harmonic and periodic impulse signals more easily. Numerical and experimental investigations demonstrate that GAGM achieves acoustic rainbow trapping to spatially separate different frequency components. This work opens up new vistas for weak signals detection in various areas.
Article
Engineering, Electrical & Electronic
Fei Yuan, Lihui Zhan, Panwang Pan, En Cheng
Summary: This paper discusses the compression techniques for underwater image communication, introducing the concept of Human Visual System to optimize image compression methods according to human eye characteristics. Experimental results validate the effectiveness of the proposed approach in maximizing the visual redundancy of underwater images while maintaining visual perception quality.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2021)
Article
Engineering, Electrical & Electronic
Yifan Huang, Manyu Liu, Fei Yuan
Summary: Underwater image processing is important in various fields, but challenges such as color degradation and blurred details exist. By combining color correction method and multi-scale recursive convolutional neural network, the quality of underwater images can be improved.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2021)
Article
Engineering, Electrical & Electronic
Rongxin Zhang, Xiaoli Ma, Deqing Wang, Fei Yuan, En Cheng
Summary: The paper introduces an adaptive design for OFDM transmission systems to combat the fast time-varying characteristics of underwater acoustic channels by utilizing the second-order statistics of channel state information. By proposing a new adaptive coding and bit-power loading algorithm, it aims to achieve the highest achievable bit rate with fixed error rate.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2021)
Article
Engineering, Civil
Jianxiang Lu, Fei Yuan, Weidi Yang, En Cheng
Summary: Computer vision is crucial in scientific research, resource exploration, and underwater applications, but faces color distortion issues. The proposed underwater image color restoration network (UICRN) estimates parameters of the underwater imaging model to achieve real color. By generating a dataset combining optical properties, the UICRN method competes in color restoration and robustness.
IEEE JOURNAL OF OCEANIC ENGINEERING
(2021)
Article
Engineering, Electrical & Electronic
Yifan Huang, Fei Yuan, Fengqi Xiao, En Cheng
Summary: This paper presents a two-step strategy based on deep learning and conventional image enhancement technologies to improve the visual performance of underwater images. The method combines color restoration and image fusion to address issues such as low contrast and detail blurring, achieving significantly better results in both qualitative and quantitative qualities.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2022)
Article
Computer Science, Information Systems
Hongbin Chen, Yi Zhu, Wenwen Zhang, Kefei Wu, Fei Yuan
Summary: This paper presents a low-cost, low-power consuming micromodem for underwater Internet of Things (IoT) applications. The micromodem utilizes the STM32F767 processor for fast digital signal processing and employs a convolutional code-block interleaving-frequency hopping-MFSK communication scheme to ensure communication quality. Experimental results show that the micromodem can achieve reliable underwater acoustic communication transmission at 200 to 300 bits per second over a distance of 500 meters.
WIRELESS COMMUNICATIONS & MOBILE COMPUTING
(2022)
Article
Chemistry, Multidisciplinary
Tingzhuang Liu, Yi Zhu, Kefei Wu, Fei Yuan
Summary: This study improves the accuracy and practicality of underwater robots by designing an interactive gesture recognition method. The algorithm is trained and tested using self-labeled underwater datasets, and combined with target tracking to continuously track underwater human bodies. The experiments demonstrate that this approach significantly enhances gesture recognition accuracy and achieves good performance in practical applications.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Civil
Fengqi Xiao, Fei Yuan, Yifan Huang, En Cheng
Summary: This article proposes a turbid underwater image enhancement method based on parameter-tuned stochastic resonance (SR). By constructing an algorithm framework, analyzing the relationship between image quality evaluation metrics and system parameters, and proposing an adaptive parameter tuning strategy, the proposed method effectively enhances turbid underwater images.
IEEE JOURNAL OF OCEANIC ENGINEERING
(2023)
Article
Computer Science, Information Systems
Zhenyu Jia, Wenjun Zheng, Fei Yuan
Summary: This article introduces the consideration of multipath and noise in low-power long-range modulation systems for underwater IoT applications, proposing a two-dimensional modulation method that can effectively suppress multipath effects and obtain a larger processing gain.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Tingzhuang Liu, Xinyu He, Linglu He, Fei Yuan
Summary: Drowning is a significant health concern, and there are challenges in detecting drowning victims due to lack of data, subtle traits, and real-time requirements. This paper proposes an underwater computer vision based drowning detection device to address these challenges.
IET IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Xinyu He, Fei Yuan, Tingzhuang Liu, Yi Zhu
Summary: In this paper, a drowning detection video system that combines computer vision and deep learning technologies is proposed. It can detect drowning events in swimming pools in real time, solving the problem of inaccurate drowning detection in traditional methods. By proposing strategies for underwater near-vertical human detection and a lightweight drowning detection convolutional autoencoder, the lack of drowning videos and the inauthenticity of simulative videos are addressed. Experimental results demonstrate that the proposed method has good comprehensive performance.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Engineering, Civil
Jiahui Liu, Fei Yuan, Chang Xue, Zhenyu Jia, En Cheng
Summary: This article proposes an effective and robust underwater image compression scheme, utilizing an autoencoder for extreme bit rate compression and a multistep training strategy to improve decoder robustness. Experimental results show that the content of the reconstructed image can still be recognized under high compression ratios and average bit error rates.
IEEE JOURNAL OF OCEANIC ENGINEERING
(2023)
Article
Engineering, Civil
Yifan Huang, Fei Yuan, Fengqi Xiao, Jianxiang Lu, En Cheng
Summary: A novel Zero-Reference Deep Network for Underwater Image Enhancement is proposed in this paper, which transforms the enhancement of an underwater image into a specific parameter map estimation by using a deep network. The method utilizes a lightweight deep network to estimate the dynamic adjustment parameters of the underwater curve model and adjusts the dynamic range of the given image pixels accordingly. The significant contribution of the proposed method is zero reference, as it does not require any paired or unpaired reference data for training.
IEEE JOURNAL OF OCEANIC ENGINEERING
(2023)
Article
Chemistry, Analytical
Jinwang Yi, Jie Tang, Fei Yuan, Guanhao Qiao, Dongping Dai
Summary: Underwater sensor nodes are randomly deployed in the underwater environment, resulting in uneven distribution and energy consumption. To address this issue, a non-uniform clustering algorithm is proposed, considering node energy, density, and coverage redundancy. The algorithm selects cluster heads and designs cluster sizes to equalize energy consumption. Simulation results show that the algorithm prolongs network lifetime, balances energy consumption, and maintains network coverage better than other algorithms.
Article
Telecommunications
Jinwang Yi, Guanhao Qiao, Fei Yuan, Yue Tian, Xianling Wang
Summary: Due to the dynamic characteristics of the underwater environment, the distribution of underwater targets often exhibit irregularities, making node deployment challenging. This letter proposes an improved greedy strategy combined with a depth-first search mechanism to solve the coverage problem of underwater targets. By selecting optimal deployment locations and implementing a flexible search process, the global solution problem is transformed into multiple local optimal solution problems, improving solution efficiency. Simulation results demonstrate the superiority of the proposed algorithm in terms of node deployment cost and coverage efficiency in underwater acoustic sensor networks (UASNs).
IEEE COMMUNICATIONS LETTERS
(2023)