Article
Public, Environmental & Occupational Health
Rong Zhang, Hao Ji, Yu Pang, Lingling Suo
Summary: This study explores the impact of COVID-19 on cultural industries from the perspective of stock market returns. The findings show that the pandemic has a significant negative impact on the stock market returns of cultural industries, but the degrees of impact vary across different creative sub-sectors. Digitalization can effectively reduce the negative impact of COVID-19 on cultural companies, and the epidemic has larger negative impacts on small and newly-established cultural companies.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Computer Science, Information Systems
Jie Yu, Chao Zhang, Junmei Wang, Mingzhi Zhang, Xingguo Zhang, Xiaoqin Li
Summary: In recent years, there have been frequent flooding incidents in northern provinces of China, affecting asparagus cultivation. To improve production efficiency in facility agriculture, this paper proposes a YOLO-based asparagus recognition scheme that enables fast and accurate target detection with enhanced interference resistance.
Article
Computer Science, Interdisciplinary Applications
Xinghai Guo, Mingjun Ji, Weidan Zhang
Summary: This paper proposes a two-level scheduling method to improve the operational efficiency of automated terminals by using unmanned surface vehicles (USVs) for container transportation in seaports. An upper-level mission planning model is established to minimize the total operation costs by considering USVs deployment, carrying capacity, berthing time intervals, etc. A lower-level collaboration control model is developed to design a predictive controller for path tracking of USVs, considering rudder and motion constraints. Experimental results demonstrate that the proposed approach can achieve cost-effective transportation scheme and satisfactory path tracking results for USVs scheduling, outperforming selected well-known algorithms in terms of solving accuracy and speed.
COMPUTERS & INDUSTRIAL ENGINEERING
(2023)
Article
Computer Science, Information Systems
Wenxuan Liu, Huayi Wu, Kai Hu, Qing Luo, Xiaoqiang Cheng
Summary: Image captioning, a challenging task in artificial intelligence, has seen significant advancements with the help of deep neural networks. While China leads in the number of publications, the United States has the most influence in this research area. Current research trends include evaluation methods, datasets, and the development of new image captioning models.
Article
Chemistry, Multidisciplinary
Yinggang Xie, Quan Wang, Yuanxiong Chang, Xueyuan Zhang
Summary: This study proposes a novel fast target recognition algorithm for dynamic scene moving target recognition. By combining adaptive histogram equalization with the ORB algorithm, the algorithm improves the matching effect under illumination challenges. Experimental results demonstrate its superiority in matching, robustness, and real-time performance.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Ming Guo, Biao Li, Zhaoqun Shao, Ning Guo, Mohan Wang
Summary: A novel objective evaluation method for image fusion based on target quality factor is proposed, which can quantitatively and reasonably evaluate the image fusion for target recognition. The evaluation results are in accordance with the visual effect of the fusion images.
MULTIMEDIA SYSTEMS
(2022)
Article
Optics
Bin Liang, Dongdong Weng, Ziqi Tu, Le Luo, Jie Hao
Summary: This study addresses the issue of specular components in face images by introducing a high-resolution Asian face dataset based on polarization characteristics, and developing a multi-task GAN approach for joint specular removal and intrinsic decomposition. Experimental results demonstrate the significant performance advantage of our method in face image processing.
Review
Management
Angela Acocella, Chris Caplice
Summary: The literature on truckload transportation procurement decisions is driven by real-world challenges and has attracted researchers' attention. However, the dispersed and uncoordinated nature of the literature makes it difficult to identify new research streams, slows progress, and limits the exposure to wider supply chain audiences.
JOURNAL OF BUSINESS LOGISTICS
(2023)
Review
Environmental Sciences
Ting Wen, Jian-Hong Li, Qi Wang, Yang-Yang Gao, Ge-Fei Hao, Bao-An Song
Summary: Plant phenotyping is crucial for plants to adapt to environmental changes and maintain their health. Imaging techniques, especially thermal imaging, are regarded as the most critical and reliable tools for studying plant phenotypes. This review summarizes the progress and future prospects of thermal imaging in assessing plant growth and stress responses.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Engineering, Electrical & Electronic
Lingang Wu, Shengliang Hu, Jianghu Xu, Zhong Liu
Summary: A novel radar target recognition model based on parallel neural networks is proposed for ship HRRP target recognition. The parallel neural network employs CNN and bidirectional LSTM to extract overall envelope features and temporal features, which are then processed by the SE block to enhance critical information. In addition, the GAF method is employed to achieve comparability with existing advanced image recognition models. Experimental results demonstrate that the proposed model outperforms other methods in recognition performance and is robust against small sample sets, high noise, and large amounts of decoy jamming.
IET RADAR SONAR AND NAVIGATION
(2023)
Article
Computer Science, Artificial Intelligence
Ganggang Dong, Hongwei Liu
Summary: In recent years, there has been a resurgence in neural networks for learning high-level representations. However, the limited availability of radar images with label information restricts the fitting power of deep architectures. Moreover, the presence of speckles, which are multiplicative noise with statistical specificity, makes image interpretation difficult. To address these issues, this paper proposes a new hierarchical receptive neural network that encodes and refines features using signal-wise receptive modules and patch-wise receptive units.
PATTERN RECOGNITION
(2022)
Article
Environmental Sciences
Aiqi Zhong, Qiang Fu, Danfei Huang, Jingping Zhu, Huilin Jiang
Summary: To enhance marine target recognition in challenging conditions, a polarization-intensity joint imaging method and corresponding processing method are proposed. The method combines fine imaging of polarization in a small field of view and wide-field imaging of visible light intensity. High-resolution polarization cameras are used for detailed inspection after locking onto areas of interest. A processing method is utilized to enhance and fuse the information from these areas. In order to address issues in the marine environment, details are extracted from a polarization camera and combined with the RealSR algorithm for super-resolution of the intensity image.
GEOCARTO INTERNATIONAL
(2023)
Review
Computer Science, Artificial Intelligence
Wouter M. Kouw, Marco Loog
Summary: This review categorizes approaches in domain adaptation into sample-based, feature-based, and inference-based methods, highlighting the importance of conditions for formulating bounds on cross-domain generalization error.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Geochemistry & Geophysics
Zhuo Chen, Lingjun Zhao, Qishan He, Gangyao Kuang
Summary: This paper proposes a pixel-level and feature-level domain adaptation approach to enhance the performance of target recognition in heterogeneous SAR situations.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Review
Microbiology
Neha Sharma, Meeta Lavania, Banwari Lal
Summary: This review examines the potential and advantages of biosurfactants in the petroleum sector, such as sustainability, environmental friendliness, and biodegradability. Biosurfactants can be used to enhance oil recovery and remediate oil spills, providing the petroleum industry with more viable and cost-effective alternatives.
FRONTIERS IN MICROBIOLOGY
(2023)
Article
Chemistry, Analytical
Stefan Postolache, Pedro Sebastiao, Vitor Viegas, Octavian Postolache, Francisco Cercas
Summary: Soil nutrients assessment is important in horticulture, but implementing an information system for horticulture faces challenges such as spatial variability, different soil properties for different plants, varying nutrient uptake, small size of monoculture, and diversity in farm components and socio-economic factors. However, advances in technology allow for the creation of low-cost, efficient information systems to improve resource management and increase productivity and sustainability in horticultural farms.
Article
Engineering, Marine
Chao Mi, Shifeng Huang, Yujie Zhang, Zhiwei Zhang, Octavian Postolache
Summary: This paper presents a visual non-contact measurement method for real-time positioning of the three-dimensional attitude of containers in automatic container terminal operations. The method achieves accurate measurement using a combination of deep learning networks and traditional image processing algorithms, meeting the requirements of automated loading and unloading.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2022)
Article
Robotics
Haobo Zuo, Changhong Fu, Sihang Li, Kunhan Lu, Yiming Li, Chen Feng
Summary: This work proposes an adversarial blur-deblur network (ABDNet) for UAV tracking, which includes a deblurrer to recover the visual appearance of the tracked object and a blur generator to produce realistic blurry images for adversarial training. ABDNet is trained with blurring-deblurring loss and tracking loss, and during inference, the blur generator is removed while the deblurrer and the tracker work together for UAV tracking.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Robotics
Sihang Li, Changhong Fu, Kunhan Lu, Haobo Zuo, Yiming Li, Chen Feng
Summary: This research presents TRTrack, a comprehensive framework that fully utilizes stereoscopic representation for UAV tracking. Through trajectory-aware reconstruction training (TRT) and spatial correlation refinement (SCR), the framework improves the performance of UAV tracking.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Chemistry, Analytical
Antonio Raimundo, Joao Pedro Pavia, Pedro Sebastiao, Octavian Postolache
Summary: Industrial inspection is crucial for quality and safety; this paper proposes YOLOX-Ray, an efficient deep learning architecture for industrial inspection; through combining SimAM attention mechanism and Alpha-IoU loss function, YOLOX-Ray outperforms other configurations in three case studies.
Article
Robotics
Changhong Fu, Teng Li, Junjie Ye, Guangze Zheng, Sihang Li, Peng Lu
Summary: This study proposes a novel scale-aware domain adaptation framework, ScaleAwareDA, to tailor general Siamese trackers for UAV tracking. By constructing the target domain and using training datasets with UAV-specific attributes, this approach can represent objects in UAV scenarios more effectively and maintain robustness. Extensive experiments and real-world tests have demonstrated the superior tracking performance and practicality of ScaleAwareDA.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Robotics
Kunhan Lu, Changhong Fu, Yucheng Wang, Haobo Zuo, Guangze Zheng, Jia Pan
Summary: This paper proposes an efficient plug-and-play cascaded denoising Transformer (CDT) to suppress cluttered and complex real noise in UAV visual tracking, thereby improving tracking performance.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Review
Engineering, Electrical & Electronic
Patricia Silva, Diogo Ribeiro, Joaquim Mendes, Eurico Augusto Rodrigues Seabra, Octavian Postolache
Summary: Railways are widely used and their comfort is crucial for passengers. However, current research lacks sufficient evaluation methods for train passenger comfort, with a lack of experiments in real railway environments and simultaneous application of static and dynamic methods.
Article
Computer Science, Information Systems
Joao Monge, Goncalo Ribeiro, Antonio Raimundo, Octavian Postolache, Joel Santos
Summary: Health monitoring is crucial in healthcare facilities, but challenges such as human error, patient compliance concerns, and limited resources affect the reliability of health data. To address these issues, we propose a non-intrusive smart sensing system using SensFloor smart carpet and an IMU wearable sensor to monitor position and gait characteristics. Machine learning algorithms are utilized to analyze the collected data and generate real-time, cloud-stored information accessible to medical professionals and patients. The system's real-time dashboards provide comprehensive analysis, enabling personalized training plans and better rehabilitation outcomes.
Review
Computer Science, Artificial Intelligence
Changhong Fu, Kunhan Lu, Guangze Zheng, Junjie Ye, Ziang Cao, Bowen Li, Geng Lu
Summary: UAV-based visual object tracking using Siamese networks is versatile and effective, but it faces obstacles due to limited computational resources and complex real-world circumstances. This study provides a comprehensive review and analysis of leading-edge Siamese trackers, evaluates their feasibility and efficacy through onboard tests, identifies limitations, and discusses the prospects for the development of Siamese tracking in UAV-based AI systems.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Automation & Control Systems
Guangze Zheng, Changhong Fu, Junjie Ye, Bowen Li, Geng Lu, Jia Pan
Summary: In many industrial applications, visual approaching the object is crucial to subsequent manipulating in unmanned aerial manipulator (UAM). The key to efficient vision-based UAM object tracking is still limited. To address this problem, a novel model-free scale-aware Siamese tracker (SiamSA) is proposed. Furthermore, two novel UAM tracking benchmarks are first recorded and comprehensive experiments validate the effectiveness of SiamSA. Real-world tests also confirm practicality for industrial UAM approaching tasks with high efficiency and robustness.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Bowen Li, Changhong Fu, Fangqiang Ding, Junjie Ye, Fuling Lin
Summary: This paper proposes a novel discriminative correlation filter-based tracker ADTrack with illumination adaptive and anti-dark capability, and establishes a UAV nighttime tracking benchmark UAVDark135. Extensive experiments validate the superiority and robustness of ADTrack in all-day conditions.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Pediatrics
Joao Rala Cordeiro, Sara Mosca, Ana Correia-Costa, Catia Ferreira, Joana Pimenta, Liane Correia-Costa, Henrique Barros, Octavian Postolache
Summary: This study explores the impact of overweight and obesity during childhood on cardiovascular health using data science techniques. The findings suggest that obesity has subtle effects on cardiovascular health, which can be observed through ECG analysis.
Article
Engineering, Electrical & Electronic
Mariana C. Jacob Rodrigues, Octavian Postolache, Francisco Cercas
Summary: This study examines the effects of sound stimulation, such as music and stress noise, on the balance of the autonomous nervous system. The results showed that ambient music increases parasympathetic activity and comfort levels, while noise stress contributes to the increase of sympathetic activity. Integrating musical stimuli into a smart environment can potentially lower individual's stress levels and improve well-being.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Proceedings Paper
Automation & Control Systems
Guangze Zheng, Changhong Fu, Junjie Ye, Bowen Li, Geng Lu, Jia Pan
Summary: This paper proposes a novel Siamese network for vision-based UAM approaching, addressing the issue of object tracking in the presence of scale variation. It introduces pairwise scale-channel attention and scale-aware anchor proposal to effectively deal with the challenges. A new UAM tracking benchmark, UAMT100, is also provided for evaluation.
2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2022)
