Article
Engineering, Multidisciplinary
Nuha H. Abdulghafoor, Hadeel N. Abdullah
Summary: This research presents a robust algorithm for real-time detection and tracking of objects in natural scenes captured by cameras. The algorithm combines principal component analysis and deep learning networks to adaptively handle various challenges and limited resources, achieving an intelligent real-time detection and tracking system.
ALEXANDRIA ENGINEERING JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Shengyang Li, Xian Sun, Yanfeng Gu, Yixuan Lv, Manqi Zhao, Zhuang Zhou, Weilong Guo, Yuhan Sun, Han Wang, Jian Yang
Summary: Intelligent processing of satellite video focuses on extracting specific information of ground objects and scenes from earth observation videos through intelligent image/video processing technology. This article presents a systematic review and quantitative analysis of the results published over the last decade, intending to further promote the development of various intelligent processing tasks for satellite video. It analyzes the current difficulties, challenges, and methodological systems for each task, and also provides in-depth analysis and summary of publicly available datasets, algorithm performance, and application scenarios.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Chemistry, Multidisciplinary
Francesco Mercaldo, Luca Brunese, Fabio Martinelli, Antonella Santone, Mario Cesarelli
Summary: This article introduces an automated method for detecting and localizing brain cancer using magnetic resonance imaging analysis. The proposed method aims to improve the prognosis and treatment outcomes for patients by enhancing the detection and precise localization of brain cancer.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Polychronis Charitidis, Sotirios Moschos, Archontis Pipertzis, Ioakeim James Theologou, Michael Michailidis, Stavros Doropoulos, Christos Diou, Stavros Vologiannidis
Summary: StreetScouting is a platform that automates the process of detecting, visualizing, and exporting urban features in a particular region. It utilizes various computer vision approaches to detect and geotag urban features from visual data.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Chemical
Min-Fan Ricky Lee, Ying-Chu Chen
Summary: Object recognition and tracking in underwater vehicles pose challenges. Traditional algorithms with clear feature definitions suffer from uncertainties caused by occlusions, illumination changes, seasonal variations, and different viewpoints. Deep learning approaches require extensive training data but face computation challenges. To overcome these drawbacks, the proposed method utilizes the Siamese Region Proposal Network tracking algorithm with weight sharing to track moving targets. The key challenge is the one-shot detection task for unidentified objects. The proposed system is evaluated using complex and uncertain environmental scenarios, with deep learning model metrics such as accuracy, precision, recall, P-R curve, and F1 score. The tracking rate based on the Siamese Region Proposal Network Algorithm can reach up to 180 FPS.
Article
Plant Sciences
Faiza Khan, Noureen Zafar, Muhammad Naveed Tahir, Muhammad Aqib, Hamna Waheed, Zainab Haroon
Summary: This paper presents an application using deep learning models for the detection and classification of diseases in maize crop, providing segmented images of affected leaves and accurate localization of disease spots. The YOLOv8n model achieved the highest prediction accuracy of 99.04% among the tested models.
FRONTIERS IN PLANT SCIENCE
(2023)
Article
Computer Science, Interdisciplinary Applications
Won-Jae Lee, Myung-Il Roh, Hye-Won Lee, Jisang Ha, Yeong-Min Cho, Sung-Jun Lee, Nam-Sun Son
Summary: In this study, ship awareness was achieved through ship detection using YOLO(v3), constructing a virtual image dataset using Unity, calculating the position of the horizon in ship images, tracking target ships' positions and speeds, and proposing a deep learning model to determine ship headings. The proposed method for ship awareness based on camera images was successfully validated in various scenarios, demonstrating good detection, localization, and tracking performance.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
V. P. Manikandan, U. Rahamathunnisa
Summary: This article introduces an Attuned Object Detection Scheme (AODS) for harmful object detection from CCTV inputs. The proposed scheme relies on a convolutional neural network (CNN) for object detection and classification, and achieves accurate detection of hazardous objects through feature attenuation and dimensional representation comparison. Training with external datasets can improve the scheme's performance.
IMAGE AND VISION COMPUTING
(2022)
Article
Biotechnology & Applied Microbiology
Huchao Yan, Xinggan Peng, Cheng Chen, Ao Xia, Yun Huang, Xianqing Zhu, Xun Zhu, Qiang Liao
Summary: A YOLOx-s-based microalgae detection method was proposed in this study, which utilized a multi-scale and multi-morphology microalgae image dataset as model input. The classification imbalance problem in microalgal detection was solved by selecting Focal Loss for the classification loss. By employing DIoU Loss in regression loss, tiny-scale microalgae were well detected with a shortened processing time. The overall model performance was improved by the ASFF module through feature fusion, and the Precision and Recall of the improved YOLOx-s in detecting microalgae achieved 95.93% and 93.48%, respectively, with a 3.33% improvement in mAP compared to the original YOLOx-s.
ALGAL RESEARCH-BIOMASS BIOFUELS AND BIOPRODUCTS
(2023)
Article
Computer Science, Artificial Intelligence
Abraham Montoya Obeso, Jenny Benois-Pineau, Mireya Sarai Garcia Vazquez, Alejandro Alvaro Ramirez Acosta
Summary: This paper investigates attention mechanisms in Deep Neural Networks (DNNs) and proposes a method that incorporates human visual attention. The proposed approach achieves faster convergence and better performance in image classification tasks compared to global and local automatic attention mechanisms.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Interdisciplinary Applications
Bo Xiao, Shih-Chung Kang
Summary: A vision-based method called construction machine tracker (CMT) is proposed to track multiple construction machines in videos, achieving high accuracy in multiple object tracking. CMT consists of detection, association, and assignment modules, using the YOLOv3 algorithm for construction machine detection. Testing showed a processing speed of 20.8 frames per second and 93.2% accuracy in multiple object tracking.
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
(2021)
Article
Chemistry, Analytical
Li-Yu Lo, Chi Hao Yiu, Yu Tang, An-Shik Yang, Boyang Li, Chih-Yung Wen
Summary: This paper presents a learning-based UAV system for autonomous surveillance, utilizing the YOLOv4-Tiny algorithm and integrating 3D object pose estimation and Kalman filter to enhance perception performance. The fully autonomous system includes UAV path planning and is validated through flight experiments, demonstrating robustness, effectiveness, and reliability in performing surveillance tasks.
Article
Computer Science, Artificial Intelligence
Jose D. Fernandez-Rodriguez, Jorge Garcia-Gonzalez, Rafaela Benitez-Rochel, Miguel A. Molina-Cabello, Gonzalo Ramos-Jimenez, Ezequiel Lopez-Rubio
Summary: This study proposes a model for automatically detecting anomalous vehicle trajectories using video sequences from traffic cameras. The model detects vehicles frame by frame, tracks their trajectories, estimates velocity vectors, and compares them to neighboring trajectories. Vehicles in wrong-way trajectories can be detected with this strategy.
INTEGRATED COMPUTER-AIDED ENGINEERING
(2023)
Article
Biochemical Research Methods
Boyuan Ma, Yuting Xu, Jiahao Chen, Pan Puquan, Xiaojuan Ban, Hao Wang, Weihua Xue
Summary: This paper proposes a deep learning tracking method for reconstructing 3D microstructures, which shows promising performance compared to traditional methods.
Article
Mathematics
Maged Faihan Alotaibi, Mohamed Omri, Sayed Abdel-Khalek, Eied Khalil, Romany F. Mansour
Summary: This study introduces a novel computational intelligence-based harmony search algorithm for real-time object detection and tracking on video surveillance systems, which incorporates an improved RefineDet-based object detection module and HSA with TWSVM model for object classification. Experimental analyses on an open access dataset demonstrate the superiority of the CIHSA-RTODT technique in detecting and tracking multiple objects in video frames.
Article
Chemistry, Applied
Qiang Wei, Wenbin Huang, Xiaodong Liu, Anqi Li, Pengfei Zhang, Zhusong Xu, Zhiqing Yu, Xiaohan Wang, Haoran Liu, Yasong Zhou
Summary: A series of Re modified NiMo/Al2O3 hydrodesulfurization (HDS) catalysts with different contents of Re2O7 were synthesized using stepwise impregnation and co-impregnation methods. The effects of Re modification and impregnation methods on the catalysts' physical-chemical properties were characterized. The results revealed that Re modification improved the crystal morphologies, pore structures, and acid sites of the catalysts. Furthermore, the HDS evaluation showed that Re modification effectively enhanced the conversions, route selectivity, and even selectivity towards 3,3'-DMCHB of 4,6DMDBT, with the stepwise impregnation method exhibiting a more significant effect compared to co-impregnation.
Article
Engineering, Industrial
Jingru Wang, Kuanyun Zhu, Jiawu Peng, Wenyan Zhuo
Summary: This study considers a two-echelon supply chain with partial cross ownership (PCO) and explores the strategy of the retailer to share private demand information with the supplier via cheap talk. We find that when the proportion of partial cross holding shares is moderate, the retailer can truthfully disclose private demand information, benefiting both the retailer and the supplier.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Psychology, Developmental
Jiaqi Zhao, Yuanyuan An, Xiaohui Li, Jiali Huang
Summary: This study investigates the trajectories of posttraumatic growth (PTG) among adolescents who survived the Yancheng tornado in China and examines the effects of posttraumatic stress symptoms (PTSS) on these trajectories. The results reveal differentiated PTG trajectories and highlight the importance of PTSS in shaping these trajectories for improving post-disaster psychological interventions.
CHILD PSYCHIATRY & HUMAN DEVELOPMENT
(2023)
Article
Peripheral Vascular Disease
Ting Wang, Fangfang Fan, Yanjun Gong, Lan Gao, Zhihao Liu, Jia Jia, Mengyuan Liu, Yimeng Jiang, Yan Zhang, Jianping Li
Summary: This study investigated the association between albuminuria and brachial-ankle pulse wave velocity (baPWV) and carotid-femoral pulse wave velocity (cfPWV) in a community-based population in Beijing. The results showed that baPWV was significantly associated with albuminuria, and it could be considered for community health screening.
JOURNAL OF HUMAN HYPERTENSION
(2023)
Article
Business
Jiebing Wu, Yan Yuan, Bin Guo
Summary: This study examines the impact of cognitive proximity and technological regime on knowledge accumulation in industrial clusters. The results indicate that cognitive proximity and cumulativeness condition jointly have a significant effect on a cluster's knowledge accumulation. Moreover, large firm clusters perform best under high levels of knowledge cumulativeness.
ASIAN JOURNAL OF TECHNOLOGY INNOVATION
(2023)
Article
Otorhinolaryngology
Xiaofan Jing, Ming Yang, Yuan Liu, Yan Wang, Jingjing Li, Wen Hu
Summary: This study investigated the possible associations of chest CT-determined trunk muscle mass and quality with dysphagia in older inpatients. The results demonstrated that muscle mass was negatively associated with dysphagia, while intermuscular adipose tissue and its percentage were positively associated with dysphagia. However, muscle density was not significantly associated with dysphagia.
Article
Chemistry, Physical
Ge Yang, Yali Xie, Yaru Wang, Ying Tang, Leng Leng Chng, Fuyi Jiang, Fanglin Du, Xianfeng Zhou, Jackie Y. Ying, Xun Yuan
Summary: This paper reports on the design of a novel Cu-based nanocatalyst, watersoluble thiolated Cu-30 nanoclusters (NCs), for living cell labeling via CuAAC. The Cu-30 NCs exhibit good biocompatibility, excellent stability, and scalable synthesis, making them a promising catalyst for potential commercial applications. Furthermore, the Cu-30 NCs demonstrate superior catalytic activities for a series of Huisgen cycloaddition reactions with good recyclability, making them suitable for intracellular bioorthogonal applications.
Article
Chemistry, Multidisciplinary
Yugang Zhang, Linwei He, Tingting Pan, Jian Xie, Fuqi Wu, Xinglong Dong, Xia Wang, Lixi Chen, Shicheng Gong, Wei Liu, Litao Kang, Junchang Chen, Lanhua Chen, Long Chen, Yu Han, Shuao Wang
Summary: SCU-SnS, an open metal-sulfide framework with three different types of active sites, exhibits superior iodine adsorption capacity through mechanisms such as charge balancing and strong binding affinity.
Article
Materials Science, Ceramics
Chaoyu Li, Fafeng Xia, Liming Yao, Huaxing Li, Xin Jia
Summary: In this study, Ni and Ni-BN-TiC layers were fabricated using laser cladding technique (LCT). The microstructure, phase structure, mechanical properties, thermal stability, and corrosion behaviors of Ni-BN-TiC layers were investigated. The results showed that Ni-BN-TiC layers had a fine and compact microstructure with improved mechanical properties and outstanding corrosion resistance.
CERAMICS INTERNATIONAL
(2023)
Article
Cardiac & Cardiovascular Systems
Junyu Pei, Hao Zhang, Yanan Li, Jiafu Yan, Keyang Zheng, Xiaopu Wang, Xi-Long Zheng, Xinqun Hu
Summary: The study found a U-shaped relationship between orthostatic blood pressure changes and major adverse cardiovascular events (MACE) occurrence. An increase in orthostatic diastolic blood pressure and a decrease in orthostatic systolic blood pressure were associated with an increased MACE risk. The benefits of intensive blood pressure management were consistent across different ranges of orthostatic blood pressure changes.
Proceedings Paper
Engineering, Electrical & Electronic
Qingcheng Zhu, Yongli Zhao, Xiaosong Yu, Jie Zhang
Summary: Cloud services relying on communication, computing, and caching resources are supported by datacenter networks (DCNs). The security of these services is under threat due to the emergence of quantum computers. Quantum key distribution (QKD) technology offers information-theoretically secure secret key sharing between remote users. A quantum cloud, achieved through QKD-secured cloud datacenter networks, provides communication, computing, caching, and cipher resources for data transmission, processing, storing, and encryption. To address the coordination problem of the newly emerged 4C resources, a 4C-oriented control architecture is designed, and innovative heuristic algorithms for securing service function chains are proposed. Simulation results demonstrate that the proposed algorithms outperform the baseline in terms of service success ratio.
2023 INTERNATIONAL CONFERENCE ON OPTICAL NETWORK DESIGN AND MODELING, ONDM
(2023)
Article
Metallurgy & Metallurgical Engineering
Xiong Tianying, Wang Jiqiang
Summary: Cold spray is a rapidly developing solid-material deposition technology that has broad application prospects in areas of metal coating preparation, additive manufacturing, and component repair due to its low spraying temperature and high particle velocity.
ACTA METALLURGICA SINICA
(2023)
Article
Mathematics, Applied
Zimo Yan, Xie Zheng, Jianping Li
Summary: In this paper, the relationships between some vertex-degree-based topological indices (including the general Randic index, the first Zagreb index, and the forgotten index) and the energy of graphs are established by using the concept of the energy of a vertex. Bounds on the energy of graphs containing no isolated vertices are given in terms of the first Zagreb index and the forgotten index. Furthermore, bounds on the normalized Laplacian energy in terms of two particular cases of the general Randic index are obtained.
DISCRETE MATHEMATICS LETTERS
(2023)
Review
Multidisciplinary Sciences
Ke Tian Tan, Samrat Ghosh, Zhiyong Wang, Fuxiang Wen, David Rodriguez-San-Miguel, Jie Feng, Ning Huang, Wei Wang, Felix Zamora, Xinliang Feng, Arne Thomas, Donglin Jiang
Summary: Chemical approaches play a crucial role in the design, synthesis, control and engineering of small molecules, polymers and networks, combining covalent bonds and non-covalent interactions to establish complex structures for specific functions. Covalent organic frameworks (COFs) are crystalline porous polymers that integrate organic units into highly ordered structures through polymerization using covalent bonds for primary order structures and non-covalent interactions for high order structures in a one-pot reaction system. This Primer provides a comprehensive overview of the field of COFs, covering chemistry, physics, materials and applications, aiming to present a concise yet complete picture of the field and addressing key fundamental issues with future directions in mind.
NATURE REVIEWS METHODS PRIMERS
(2023)
Article
Green & Sustainable Science & Technology
Yonggan Yang, Zihao Kang, Binggen Zhan, Peng Gao, Qijun Yu, Yanlai Xiong, Jingfeng Wang, Yunsheng Zhang
Summary: This paper systematically studied the effects of different mineral admixtures and sulfate solution types on the performance of concrete, and explored the changes in the microstructure and corrosion products of concrete using various analysis methods. The results showed that the presence of magnesium ions accelerated concrete deterioration, while an appropriate amount of slag improved the corrosion resistance of concrete.
JOURNAL OF RENEWABLE MATERIALS
(2023)