相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Automation & Control Systems
Han Li et al.
Summary: In this paper, a novel multidisciplinary design optimisation (MDO) algorithm called the decomposition-based switching multi-objective whale optimiser (SMWO/D) is proposed. It utilizes a penalty-Tchebycheff value-based decomposition framework to decouple strongly correlated conflicting objectives and considers different disciplinary demands comprehensively. Two adaptively switchable evolutionary modes are defined to overcome the shortcoming of premature convergence in the complicated multi-modal non-linear decision space and promote a thorough global search with rich learning strategies. The proposed SMWO/D is evaluated on benchmark functions and compared with four popular decomposition-based multi-objective optimisation algorithms (MOAs), demonstrating its competitiveness in terms of comprehensive performance. Additionally, a sensitivity analysis is conducted to determine the best parameter configuration of SMWO/D. Finally, a case study of a real-world turbine disk structural optimisation validates the practicality of SMWO/D in handling multidisciplinary properties and provides valuable experiences in the aero-engine MDO domain.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2023)
Article
Agricultural Engineering
Daoliang Li et al.
Summary: The acquisition of fish stress information is crucial for monitoring water quality, preventing diseases, and improving welfare. Traditional manual methods for monitoring fish stress are time-consuming and unreliable, while new intelligent methods provide opportunities for automatic recognition. The latest technologies are categorized into machine vision-based, sensor-based, and acoustic-based methods. Advanced sensors and machine learning techniques play a key role in accelerating the automation and intelligence of fish welfare monitoring technology.
AQUACULTURAL ENGINEERING
(2022)
Article
Fisheries
Yonghui Chai et al.
Summary: The study investigated the toxicity effects of ammonia nitrogen on cuttlefish Sepia pharaonis, finding significant impacts on blood cell immunity, respiratory burst activities, phagocytosis rate, and antioxidant function. Exposure to low or high concentrations of ammonia nitrogen led to increased apoptotic blood cells, respiratory burst activities, and MDA content, while decreasing phagocytosis, SOD, and CAT activity. These results suggest that ammonia nitrogen stress can disrupt immune and antioxidant systems in cuttlefish.
Article
Fisheries
Taravat Molayemraftar et al.
Summary: Exposure to ammonia and nitrite resulted in elevated white blood cell counts, decreased red blood cell and hemoglobin levels, significant alterations in blood indices, and changes in serum antioxidant enzyme activities. Nitrite exposure led to significantly higher serum malondialdehyde levels, while ammonia exposure resulted in increased serum catalase activity. Overall, the presence of these substances in water can have adverse effects on common carp's hematological parameters, enzyme activities, and antioxidant defenses.
Article
Agriculture, Multidisciplinary
He Wang et al.
Summary: Real-time detection and tracking of fish with abnormal behavior is an effective way to improve the welfare and survival rate of aquaculture. The proposed combined end-to-end neural network achieves accurate detection and tracking of abnormal behavior individuals.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Computer Science, Artificial Intelligence
Peishu Wu et al.
Summary: In this paper, a novel face mask detection framework called FMDYolo is proposed for monitoring whether people wear masks correctly in public. Experimental results demonstrate the superiority of FMDYolo in face mask detection.
IMAGE AND VISION COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Qi Zheng et al.
Summary: This paper proposes a unified B-spline framework for scale-invariant keypoint detection. The framework provides a mathematical interpretation of existing fast detectors based on integral images, and addresses the problem of repeated integration. Two detectors, B-DoH and B-LoG, are developed within the framework and are shown to outperform other methods in terms of repeatability and efficiency. The use of repeated running-sums improves computation efficiency.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2022)
Article
Computer Science, Artificial Intelligence
Zhixue Zhang et al.
Summary: Fish species recognition from noisy large-scale underwater images is challenging. This work presents a novel deep adversarial learning framework, AdvFish, which outperforms existing methods/models on multiple benchmark datasets. AdvFish is a generic learning framework that can train better recognition models from extremely noisy images.
KNOWLEDGE AND INFORMATION SYSTEMS
(2022)
Article
Biology
Nighat Un Nissa et al.
Summary: There is a correlation between environmental conditions and fish health. Pollution in aquatic ecosystems directly affects the presence or absence of parasites. Fish living in optimal environmental conditions and well-nourished are more resistant to diseases than those weakened by malnutrition caused by parasite infestation or environmental deterioration due to pollution. Parasites attach to the host through suckers and hooks and enter the host through various means. The presence of parasites can cause changes in fish that serve as indicators of deterioration in the aquatic habitat.
SAUDI JOURNAL OF BIOLOGICAL SCIENCES
(2022)
Article
Fisheries
Abderrazak Chahid et al.
Summary: This paper investigates the problem of fish growth trajectory tracking and proposes a Q-learning algorithm for optimal control. The algorithm is able to achieve good trajectory tracking performance in the complex aquaculture environment and reduce feed waste.
Article
Computer Science, Information Systems
Liangwei Jiang et al.
Summary: This study proposes a fish recognition method based on targeted sample transfer learning. By freezing the feature extraction layer of the pre-training model and fusing it with a new feature extraction layer, a new feature extractor is formed, which improves the accuracy of fish recognition in complex backgrounds.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Agriculture, Multidisciplinary
Ao Du et al.
Summary: This paper introduces a 2D-3D fusion body measurement method that detects keypoints on RGB images using deep learning and projects them onto livestock point clouds. It achieves body measurements of cattle and pig using interpolation and pose normalization methods.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Automation & Control Systems
Han Li et al.
Summary: This paper reviews the use of mathematical tools to enhance LFIA performance, and proposes a novel taxonomy. It also presents the outlook of developing POCT in conjunction with other state-of-the-art techniques, and highlights the importance of applying computational intelligence methods in boosting POCT development.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2022)
Article
Multidisciplinary Sciences
Caili Gong et al.
Summary: In this study, a multicow pose estimation algorithm was proposed for monitoring the health and well-being of dairy cows in precision farming. The algorithm achieved high precision in detecting and estimating the poses of single and multiple cows. This research provides a theoretical reference for animal pose estimation in large-scale precision livestock farming.
Article
Chemistry, Analytical
Nina Volkmann et al.
Summary: The study aims to develop a camera-based system for monitoring turkey flocks and detecting injuries using neural networks. Key point detection model was applied to annotate 244 turkey images and combined with a segmentation model for injury detection. Key point detection showed good results in clearly differentiating individual animals even in crowded situations.
Article
Multidisciplinary Sciences
Zhengyang Xu et al.
Summary: In this study, we propose a symmetry approach and design a convolutional neural network for mouse pose estimation under scale variation. The network employs the UNet structure as the backbone, utilizes residual network for feature extraction, incorporates the ASPP module to expand the perceptual field, and integrates deep and shallow features to capture spatial relationships at multiple scales to optimize recognition accuracy. Experimental results show that our method achieves state-of-the-art performance on our self-built mouse dataset.
Review
Agriculture, Multidisciplinary
Yupeng Mei et al.
Summary: In aquaculture, fish behavioral monitoring is crucial for scientific management and reducing losses from disease and stress. Fish tracking technology, using computer vision, is a powerful tool for monitoring fish movement and detecting abnormal behaviors. However, fish tracking using computer vision models faces challenges like fish deformation, occlusion, and scale changes. This paper reviews the progress of tracking algorithms in fish research and discusses different methods, including deep learning approaches. It also summarizes datasets and evaluation metrics for fish tracking and provides experimental data. Finally, it discusses future directions, such as combining fish tracking methods with Transformer, for accelerating the advancement of smart fishery and precision farming.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Ecology
Xiaoxue Fu et al.
Summary: This paper proposes the YOLOT algorithm, a quantitative detection algorithm based on the improved YOLOv4, for detecting marine benthos. By introducing the Transformer mechanism and probabilistic anchor assignment, the algorithm enhances the feature extraction capability and adaptability in complex environments. Experimental results show that YOLOT achieves higher recognition precision on the marine benthic dataset compared to the original YOLOv4.
ECOLOGICAL INFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Han Li et al.
Summary: In the context of the global COVID-19 pandemic, a computer aided diagnosis model called Cov-Net is proposed for accurate recognition of COVID-19 from chest X-ray images. Experimental results demonstrate the high feasibility and accuracy of the model in identifying COVID-19. Compared to other algorithms, Cov-Net exhibits superior performance and competitiveness in this task.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Environmental Sciences
Cathy Teng et al.
Summary: The societal demand for plastic goods has led to the prevalence of synthetic materials in the marine environment. To address plastic pollution, a deep learning-based image classifier using YOLOv5 is proposed, capable of classifying and localizing marine debris and marine life in images and videos. By using the region of interest line and centroid tracking counting methods, the classifier accurately counts the quantity of marine debris and fish displayed in video footage, achieving a counting accuracy of 79%. The proposed method also demonstrates a mean average precision of 89.4% when validated on nine object categories.
MARINE POLLUTION BULLETIN
(2022)
Article
Chemistry, Multidisciplinary
Xianyi Zhai et al.
Summary: This study proposes an improved method for sea cucumber recognition and location based on YOLOv5, achieving accurate identification of underwater sea cucumbers by introducing MSRCR algorithm and CBAM module. The experimental results demonstrate that the improved YOLOv5s model performs well in small target recognition, with higher recognition precision and confidence level.
APPLIED SCIENCES-BASEL
(2022)
Article
Automation & Control Systems
Cheng Wang et al.
Summary: This paper presents a pedestrian detection method based on the MDY algorithm, which improves detection accuracy and real-time performance by optimizing the algorithm and fusing LIDAR point cloud data.
SYSTEMS SCIENCE & CONTROL ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Yuepeng Zhou et al.
Summary: This study introduces CDTNet, an image classification model based on convolutional neural networks. CDTNet utilizes two branches with different dilation rates to capture multi-scale features and recovers low-resolution information through transposed convolution. Experimental results demonstrate that CDTNet outperforms state-of-the-art models on multiple benchmark datasets with lower loss, higher accuracy, and faster convergence speed.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Jinliang Lin et al.
Summary: This paper studies the cross-view geo-localization problem and proposes a framework called RK-Net to jointly learn discriminative representation and detect salient keypoints using the USAM module. The integration of USAM enables end-to-end joint learning, simplifies implementation, and enhances overall performance, achieving competitive accuracy on challenging datasets.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Engineering, Electrical & Electronic
Nianyin Zeng et al.
Summary: In this article, a novel enhanced multiscale feature fusion method called ABFPN is proposed to improve the detection performance of small objects. It is evaluated on benchmark datasets and applied to detect surface defects on printed circuit boards. Experimental results demonstrate its reliability and efficiency.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Agriculture, Multidisciplinary
Qixin Sun et al.
Summary: This paper proposes a novel method for detecting branch keypoints in orchards, enabling branch pruning during fruit picking. By constructing a citrus bearing branch dataset, the proposed method achieves high performance with a smaller model size and lower computing power consumption, outperforming several state-of-the-art keypoint detection methods.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Engineering, Electrical & Electronic
Qigao Fan et al.
Summary: The irregular surface of zebrafish larvae presents challenges for fixing their bodies, leading to high requirements for injection target points and posture control. A zebrafish dataset containing key points and posture annotations was established, and a neural network model designed for zebrafish key point recognition. Through three-dimensional coordinate transformation, posture angle information was accurately calculated, demonstrating improved accuracy in zebrafish posture angle determination under changing postures. An operating platform was also designed to fix zebrafish juveniles and precisely adjust their posture, laying the foundation for further experimental operations.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Youssef Wageeh et al.
Summary: This study introduces a method that improves fish detection and tracking under challenging water conditions by using image enhancement and object detection algorithms.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Weibo Liu et al.
Summary: This study employs a deep belief network to address patient attendance disposal in A&E departments, with the hyperparameters selection being automated by a PSO algorithm. The RODDPSO algorithm is utilized to optimize the hyperparameters of the DBN, achieving better classification accuracy compared to standard and modified DBNs in analyzing A&E data from a hospital in west London.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2021)
Article
Ecology
Sebastian Lopez-Marcano et al.
Summary: Animal movement studies are important for monitoring ecosystem health and understanding ecological dynamics. In marine environments, traditional sampling methods are invasive and costly, prompting the need for automated detection and tracking systems. This study successfully utilized an object detection and tracking pipeline to monitor fish movement, demonstrating a noninvasive and reliable approach for future studies.
ECOLOGY AND EVOLUTION
(2021)
Article
Fisheries
Yudong Jia et al.
Summary: The study found that spotted knifejaw reared in an offshore aquaculture net pen system showed high survival rate, growth performance, and maintained good physiological status in short-term culture, opening a new pathway for the culture of this species.
Article
Computer Science, Artificial Intelligence
Jing Zhang et al.
Summary: This paper proposes a comprehensive solution for human keypoint detection from a single image, addressing challenges such as occlusion, blur, illumination, and scale variance. By optimizing network structure, training strategies, and postprocessing techniques, the proposed method shows superior performance on the MS COCO keypoint detection benchmark compared to state-of-the-art methods.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Environmental Sciences
Pengfei Shi et al.
Summary: The paper proposes an underwater biological detection algorithm based on improved Faster-RCNN, utilizing ResNet as the backbone feature extraction network and BiFPN structure for enhanced feature extraction and multi-scale feature fusion. The algorithm also incorporates EIoU and K-means++ to reduce redundant bounding boxes and generate more suitable anchor boxes, resulting in improved detection accuracy in experiments.
Article
Computer Science, Information Systems
Zongsheng Wang et al.
Summary: Traditional tracking algorithms rely on manually extracted features, while deep learning algorithms can automatically extract features which are important for single target tracking in complex underwater environments. The SiamRPN++ algorithm, incorporating the NewNet-62 backbone network structure, achieves fast and accurate tracking underwater, with improved performance compared to traditional algorithms.
Article
Automation & Control Systems
Wendong Gai et al.
Summary: The improved Tiny YOLOv3 algorithm leverages K-means clustering, pooling, convolution layers, and upsampling/downsampling techniques to enhance feature fusion and multi-scale fusion, ultimately incorporating complete intersection over union in the loss function for improved detection results. It is lightweight and can be trained on a CPU, meeting the requirements of detection speed and accuracy.
SYSTEMS SCIENCE & CONTROL ENGINEERING
(2021)
Article
Fisheries
Ahmad Salman et al.
ICES JOURNAL OF MARINE SCIENCE
(2020)
Article
Chemistry, Analytical
Antoine Mauri et al.
Article
Marine & Freshwater Biology
Lu Cai et al.
Article
Chemistry, Analytical
Zhengjun Qiu et al.
Article
Chemistry, Analytical
Wenkai Xu et al.
Article
Computer Science, Artificial Intelligence
Zitong Wan et al.
Article
Geochemistry & Geophysics
Zhiqiang He et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2020)
Article
Agricultural Engineering
Kewei Cai et al.
AQUACULTURAL ENGINEERING
(2020)
Article
Computer Science, Information Systems
Juan Li et al.
Article
Fisheries
Lucas C. Maltez et al.
JOURNAL OF THE WORLD AQUACULTURE SOCIETY
(2019)
Article
Engineering, Ocean
Junhui Wang et al.
MARINE TECHNOLOGY SOCIETY JOURNAL
(2019)
Article
Automation & Control Systems
Houssem Eddine Rouabhia et al.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2019)
Article
Fisheries
Muzi Zhang et al.
FISH & SHELLFISH IMMUNOLOGY
(2018)
Article
Cell Biology
Yuen K. Ip et al.
Article
Fisheries
Alessandro Lucchetti et al.
CANADIAN JOURNAL OF FISHERIES AND AQUATIC SCIENCES
(2018)
Article
Automation & Control Systems
Fan Feng et al.
SYSTEMS SCIENCE & CONTROL ENGINEERING
(2018)
Article
Computer Science, Artificial Intelligence
Weibo Liu et al.
Article
Fisheries
Xiangli Dong et al.
FISH & SHELLFISH IMMUNOLOGY
(2016)
Article
Statistics & Probability
Ludwig Bothmann et al.
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS
(2016)
Article
Biochemistry & Molecular Biology
Zhi-Hua Li et al.
CHEMICO-BIOLOGICAL INTERACTIONS
(2015)
Article
Fisheries
B. Sadoul et al.
Article
Psychology, Mathematical
B. W. Patullo et al.
BEHAVIOR RESEARCH METHODS
(2007)
Article
Physiology
David J. Randall et al.
RESPIRATORY PHYSIOLOGY & NEUROBIOLOGY
(2006)
Article
Biochemical Research Methods
S Kato et al.
JOURNAL OF NEUROSCIENCE METHODS
(2004)
Article
Optics
W Gong et al.
APPLIED PHYSICS B-LASERS AND OPTICS
(2004)