Article
Chemistry, Multidisciplinary
Haijiang Zhu, Yinchu Wang, Jiawei Fan
Summary: This paper proposes an improved IA-Mask R-CNN detection method for surface defect detection on automotive engine parts. By establishing an image dataset and analyzing labeled data, suitable anchor scales for surface defect detection are determined to improve the anchor design in Mask R-CNN. The experimental results show that the proposed method outperforms other detection methods in detecting both minor and larger defects.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Multidisciplinary
Yingying Xu, Dawei Li, Qian Xie, Qiaoyun Wu, Jun Wang
Summary: This paper proposes a novel tunnel defect inspection method based on Mask R-CNN, with detailed studies on PAFPN and the edge detection branch, showing their robustness and accuracy in tunnel defect detection and segmentation.
Article
Engineering, Multidisciplinary
Deqiang He, Rui Ma, Zhenzhen Jin, Ruochen Ren, Suiqiu He, Zaiyu Xiang, Yanjun Chen, Weibin Xiang
Summary: An intelligent model based on attention balanced context Mask R-CNN is proposed for welding quality detection, which collects welding defect images using phased array ultrasonic testing and constructs a defect dataset. Attention block, balanced block, and context block are introduced into Mask R-CNN. Experimental results demonstrate that the accuracy of welding quality detection is 98.20%, which is 4.5% higher than Mask R-CNN. This provides theoretical and technical support for intelligent maintenance and accurate welding quality detection.
Article
Computer Science, Artificial Intelligence
Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen, Yanning Zhang
Summary: Neural Architecture Search (NAS) has the potential to reduce manual effort in network design by automatically discovering optimal architectures, yet object detection has been less explored in NAS research; here, we propose an efficient method to obtain better object detectors by searching for feature pyramid networks and prediction heads, demonstrating superior performance compared to traditional models.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Computer Science, Hardware & Architecture
Hao Wang, Mengjiao Li, Zhibo Wan
Summary: This paper proposes a new surface defect detection network based on Mask R-CNN to detect rail defects, achieving high accuracy in defect location through multi-scale fusion, a new evaluation metric, and data augmentation.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Computer Science, Information Systems
Dongjie Li, Wenbo Xie, Baogang Wang, Weifeng Zhong, Hongmin Wang
Summary: In this study, a novel detection method using generative adversarial networks and data augmentation is proposed to address the issues of imbalance in defect categories and difficult access to defective data in wood defect detection. Additionally, a layered deformable mask region-based convolutional neural network is constructed to tackle the challenges of modeling irregular defects and extracting contextual information.
Article
Chemistry, Multidisciplinary
Yang He, Zihan Jin, Jiqiao Zhang, Shuai Teng, Gongfa Chen, Xiaoli Sun, Fangsen Cui
Summary: This study utilizes Mask R-CNN and transfer learning to detect pavement defects in complex backgrounds. The results show that Mask R-CNN performs better in terms of average precision, and models using FPN have shorter testing time. Additionally, the segmentation performance at different learning rates is analyzed, with Mask R-CNN using ResNet101 plus FPN achieving the best results.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Multidisciplinary
Ji-qing Luo, Hu-sheng Fang, Fa-ming Shao, Yue Zhong, Xia Hua
Summary: In this paper, a model based on Faster R-CNN with NAS optimization and feature enrichment is proposed to effectively detect multi-scale vehicle targets in traffic scenes. The model includes an image adaptive correction algorithm to enhance image quality, Neural Architecture Search to optimize backbone network, and object feature enrichment for robust detection of challenging targets. The model demonstrates state-of-the-art detection performance on the UN-DETRAC dataset.
DEFENCE TECHNOLOGY
(2021)
Article
Chemistry, Analytical
Xiangyang Xu, Mian Zhao, Peixin Shi, Ruiqi Ren, Xuhui He, Xiaojun Wei, Hao Yang
Summary: The intelligent crack detection method is of great significance for intelligent operation and maintenance as well as traffic safety. This paper investigates the application of deep learning in intelligently detecting road cracks and compares and analyzes Faster R-CNN and Mask R-CNN. The results show that the joint training strategy is effective, but it degrades the effectiveness of the bounding box detected by Mask R-CNN.
Article
Chemistry, Analytical
Yilin Ge, Dapeng Jiang, Liping Sun
Summary: This paper proposes a new deep learning defect detection pipeline, which collects a defect image dataset and designs a detection pipeline based on DETR. The method addresses the issues of small object detection and unstable training. Experimental results demonstrate that the proposed method outperforms in terms of both speed and accuracy.
Article
Environmental Sciences
Rao Fu, Jing He, Gang Liu, Weile Li, Jiaqi Mao, Minhui He, Yuanyang Lin
Summary: The purpose of this study is to quickly determine the extent and size of post-earthquake seismic landslides using a small amount of post-earthquake seismic landslide imagery data. Different backbone networks were used for training and identification, and the performance of the improved model was significantly better in terms of accuracy and recognition in Haiti's post-earthquake images.
Article
Engineering, Electrical & Electronic
P. M. Diaz, P. Tittus
Summary: A fast wind turbine defect detection model is proposed using a Cascade Mask region Convolutional Neural network (Cascade Mask R-CNN) in this paper. A depthwise separable convolution is used to minimize the computation cost in the backbone network of Cascade Mask R-CNN instead of standard convolution. In addition, image augmentation and transfer learning techniques are used to enhance the model's performance. The proposed WTB defect detection and classification model shows better performance with 82.42% MAP, 87.49% MIoU and 97.8% classifier accuracy, as compared to existing techniques.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Forestry
Chunjiang Yu, Yongke Sun, Yong Cao, Jie He, Yixing Fu, Xiaotao Zhou
Summary: Wood logs need to be measured for size when passing through customs. Traditional measurement methods are inefficient and inaccurate. We propose a method that uses a Mask R-CNN model for contour detection and a binocular stereo camera for diameter measurement. Experimental results show good accuracy and precision of the method.
Article
Ecology
Christopher R. Conrady, Sebnem Er, Colin G. Attwood, Leslie A. Roberson, Lauren de Vos
Summary: The availability of affordable, high-resolution digital cameras has led to a significant increase in capturing natural environments and their inhabitants. Video-based surveys, especially in underwater areas, are valuable as human observation can be expensive, dangerous, inaccessible, or damaging to the environment. This study tests the use of a Mask R-CNN object detection framework for automated fish localization, classification, counting, and tracking. The model performs accurately on both training and validation datasets and even on previously unseen footage.
ECOLOGICAL INFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
M. Emin Sahin, Hasan Ulutas, Esra Yuce, Mustafa Fatih Erkoc
Summary: The COVID-19 pandemic has had a devastating impact on daily lives and healthcare systems. This study aims to accurately diagnose COVID-19 using deep learning techniques on CT images. The results show that the models have high accuracy rates and can help with automated COVID-19 severity quantification in CT images.
NEURAL COMPUTING & APPLICATIONS
(2023)
Letter
Rheumatology
Martin Sebastian Winkler, Peter Korsten, Claudia Binder, Bjoern Tampe
ANNALS OF THE RHEUMATIC DISEASES
(2023)
Article
Cell Biology
J. L. Cordeiro, J. D. Neves, F. Nicola, A. F. Vizuete, E. F. Sanches, C. A. Goncalves, C. A. Netto
Summary: In this study, arundic acid (AA) was administered in a collagenase-induced intracerebral hemorrhage (ICH) rodent model, and it was found that AA could prevent motor dysfunction, reduce S100B levels, and decrease astrogliosis and microglial activation, which in turn led to a decrease in the production of proinflammatory cytokines and reactive oxygen species (ROS).
CELLULAR AND MOLECULAR NEUROBIOLOGY
(2022)
Article
Chemistry, Medicinal
Bichismita Sahu, Santosh Kumar Behera, Rudradip Das, Tanay Dalvi, Arnab Chowdhury, Bhaskar Dewangan, Kiran Kalia, Amit Shard
Summary: This study designed scaffolds derived from peptide nucleic acid (PNA) and conducted in-silico screening to identify a compound with similar binding affinity to RdRp. Compound 12 showed comparable pharmacokinetics to remdesivir but with significantly lower toxicity, making it a potential candidate for the treatment of COVID-19.
CURRENT COMPUTER-AIDED DRUG DESIGN
(2022)
Article
Oncology
Yi Liao, Senmao Li, Hao Chen, Chunyu Chen, Jintuan Huang, Feng Lin, Jianping Wang, Zuli Yang
Summary: A risk prediction system combining FIT and risk factors was developed to improve the sensitivity of colonoscopy screening. The system effectively stratified participants into high risk and low risk groups, with better predictive ability for colorectal neoplasia compared to using FIT alone.
EUROPEAN JOURNAL OF CANCER PREVENTION
(2023)
Article
Oncology
Luca Giraldi, Jovana Stojanovic, Dario Arzani, Roberto Persiani, Jinfu Hu, Kenneth C. Johnson, Zuo-Feng Zhang, Monica Ferraroni, Domenico Palli, Guo-Pei Yu, Carlo La Vecchia, Claudio Pelucchi, Nuno Lunet, Ana Ferro, Reza Malekzadeh, Joshua Muscat, David Zaridze, Dmitry Maximovich, Nuria Aragones, Vicente Martin, Jesus Vioque, Eva M. Navarrete-Munoz, Mohammadreza Pakseresht, Eva Negri, Matteo Rota, Farhad Pourfarzi, Lina Mu, Robert C. Kurtz, Areti Lagiou, Pagona Lagiou, Roberta Pastorino, Stefania Boccia
Summary: This study aimed to examine the association between height and risk of gastric cancer. Through a large pooled analysis of case-control studies, the study found no significant association between adult height and gastric cancer.
EUROPEAN JOURNAL OF CANCER PREVENTION
(2023)
Article
Oncology
Maria A. Karalexi, Marina Servitzoglou, Vassilios Papadakis, Denis Kachanov, Maja Cesen Mazic, Margaret Baka, Maria Moschovi, Maria Kourti, Sofia Polychronopoulou, Eftichia Stiakaki, Emmanuel Hatzipantelis, Helen Dana, Kalliopi Stefanaki, Astero Malama, Marios S. Themistocleous, Katerina Strantzia, Tatyana Shamanskaya, Panagiota Bouka, Paraskevi Panagopoulou, Maria Kantzanou, Evangelia Ntzani, Nick Dessypris, Eleni Th. Petridou
Summary: The prognosis of children with neuroblastoma varies depending on the stage and biology of the tumor, and early-stage neuroblastoma has a better prognosis. Treatment with anti-GD2 antibody can improve the prognosis of high-risk patients.
EUROPEAN JOURNAL OF CANCER PREVENTION
(2023)
Article
Ophthalmology
Massimiliano Serafino, Andrea Lembo, Matteo Scaramuzzi, Andrea Dellavalle, Paolo Nucci
Summary: Pulled-in-two syndrome is a serious complication of strabismus surgery, where an extraocular muscle is ruptured. Transposition of the inferior oblique muscle can be a potential technique for treatment if the muscle cannot be retrieved.
EUROPEAN JOURNAL OF OPHTHALMOLOGY
(2022)
Article
Ophthalmology
Jin Kyun Oh, Yan Nuzbrokh, Winston Lee, Jose Ronaldo Lima de Carvalho, Nan Kai Wong, Janet Sparrow, Rando Alliikmets, Stephen H. Tsang
Summary: This case report describes two brothers with progressive vision loss and night blindness, showing typical symptoms of pigmented paravenous retinochoroidal atrophy. Genetic analysis revealed a mutation in the CRX gene in both individuals.
EUROPEAN JOURNAL OF OPHTHALMOLOGY
(2022)
Article
Psychology, Clinical
L. A. Rescorla, M. Y. Ivanova, T. M. Achenbach, Vera Almeida, Meltem Anafarta-Sendag, Ieva Bite, J. Carlos Caldas, John William Capps, Yi-Chuen Chen, Paola Colombo, Margareth da Silva Oliveira, Anca Dobrean, Nese Erol, Alessandra Frigerio, Yasuko Funabiki, Reda Gedutiene, Halldor S. Guomundsson, Min Quan Heo, Young Ah Kim, Tih-Shih Lee, Manuela Leite, Jianghong Liu, Jasminka Markovic, Monika Misiec, Marcus Mueller, Kyung Ja Oh, Veronica Portillo-Reyes, Wolfgang Retz, Sandra B. Sebre, Shupeng Shi, Sigurveig H. Siguroardottir, Roma Simulioniene, Elvisa Sokoli, Dragana Milijasevic, Ewa Zasepa
Summary: This study compares self-reports and collateral reports of older adults' mental health across 19 societies, finding that the OASR and OABCL are efficient assessments that can be used internationally to screen for various problems and strengths.
INTERNATIONAL PSYCHOGERIATRICS
(2022)
Article
Biochemistry & Molecular Biology
Nikhil Maroli, Balu Bhasuran, Jeyakumar Natarajan, Ponmalai Kolandaivel
Summary: This study utilized text mining and named entity recognition methods to identify the co-occurrence of important COVID 19 genes/proteins in the interaction network. Molecular docking and molecular dynamics simulation revealed the inhibition mechanism of key proteins and confirmed the affinity of procyanidin towards critical receptors.
JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS
(2022)
Article
Public, Environmental & Occupational Health
Anya P. G. F. Vieira-Meyer, Maira B. Coutinho, Helena P. G. Santos, Maria Saintrain, George T. de M. Candeiro
Summary: This study investigated the knowledge and practice of Brazilian public primary and secondary health care dentists during the COVID-19 pandemic. The majority of these dentists believed in the transmission of COVID-19 through dental procedures, but had a fair level of knowledge about COVID-19 symptoms. There was skepticism about the effectiveness of personal protective equipment and biosafety procedures in preventing COVID-19 transmission. Factors such as country region, social distancing, dental specialty, and the use of protective measures influenced the likelihood of dentists performing dental treatment during the pandemic. The study concludes that additional preventive measures and internationally accepted guidelines are needed to address the challenges brought by COVID-19.
DISASTER MEDICINE AND PUBLIC HEALTH PREPAREDNESS
(2022)
Article
Public, Environmental & Occupational Health
Eugenia O'Kelly, Anmol Arora, Charlotte Pearson, James R. Ward, P. John Clarkson
Summary: This study evaluates alternatives and replacement methods for qualitative fit testing. It found that aroma diffusers and smaller enclosures can perform the testing quickly and accurately.
DISASTER MEDICINE AND PUBLIC HEALTH PREPAREDNESS
(2022)
Review
Clinical Neurology
Christoph Eckhard Heyde, Ulrich Josef Albert Spiegl, Anna Voelker, Nicolas von der Hoeh, Jeanette Henkelmann
Summary: The prevalence of nonspecific pyogenic spondylodiskitis has increased, causing high morbidity and mortality. The diagnosis is often delayed due to nonspecific clinical manifestations at the early stage. CT can assess the bony condition, while MRI is still the gold standard for diagnosis.
JOURNAL OF NEUROLOGICAL SURGERY PART A-CENTRAL EUROPEAN NEUROSURGERY
(2023)
Article
Rehabilitation
Danielle Brasil-Barros-da-Silva, Emerson Fachin-Martins
Summary: This study aimed to explore the association between the usage of forearm crutches and pain complaints and health conditions. The study found different patterns of pain complaints between permanent and temporary users, with temporary female users more likely to be injured due to external causes. Additionally, both types of users reported varying levels of pain, with only permanent users reporting mild pain.
ASSISTIVE TECHNOLOGY
(2022)
Article
Psychology, Multidisciplinary
Lia Ring, Lee Greenblatt-Kimron, Yuval Palgi
Summary: This study aimed to examine whether subjective nearness-to-death moderated the association between health worries and death anxiety due to the COVID-19 outbreak among older adults in Israel. The findings revealed that subjective nearness-to-death moderated the association between health worries and death anxiety. The importance and significance of subjective perceptions concerning the distance from death as a resilient resource is discussed.