Surface defect detection model of laser cutting polycrystalline cubic boron nitride tool based on asymptotic fusion strategy by Anfu Zhu, Jiaxiao Xie, Heng Guo, Jie Wang, Zilong Guo, Lei Xu, SiXin Zhu, Zhanping Yang, Bin Wang

“…In the backbone network, the C3SE module is constructed by modeling the correlation between feature channels to improve the model’s focus on key features in order to enhance the feature extraction and processing capability of the backbone network; In the neck network, adaptive spatial fusion operation and direct interaction of non-adjacent layers are utilized for multi-scale information fusion, and the asymptotic feature pyramid network for object detection (AFPN) is used instead of the FPN structure to improve the detection performance; In the head network, a soft suppression mechanism is introduced to reduce the overlapping frame score using a decay function, thus improving the detection accuracy. …”
Get full text

WCS-YOLOv8s: an improved YOLOv8s model for target identification and localization throughout the strawberry growth process by Sheng Gao, Sheng Gao, Gongpei Cui, Qiaohua Wang

“…The self- developed SE-MSDWA module is integrated into the backbone network to improve the model’s feature extraction capability while suppressing redundant information, thereby achieving efficient feature extraction. …”
Get full text

KERF: a knowledge-enhanced relearning framework for tailings pond detection from high-resolution remote sensing images by Bingjie Liu, Wei Wu, Hao Wu, Ailong Ma, Shaohua Hu, Nianchun Du, Xuan Cui, Junyang Xie

“…The multi-dimensional features are fused in an adaptive feature bundling strategy, thus achieving a discriminative multi-level description for recognition and false alarm elimination. …”
Get full text

Enhanced intrusion detection model based on principal component analysis and variable ensemble machine learning algorithm by Ayuba John, Ismail Fauzi Bin Isnin, Syed Hamid Hussain Madni, Farkhana Binti Muchtar

“…Principal Component Analysis (PCA) has proven to be a helpful feature selection technique for dimensionality reduction. …”
Get full text

Image Characteristic-Guided Learning Method for Remote-Sensing Image Inpainting by Ying Zhou, Xiang Gao, Xinrong Wu, Fan Wang, Weipeng Jing, Xiaopeng Hu

“…Compared with existing works, FFSM improves the fineness of feature matching. To avoid the problem of local-smoothness in the results, both the generator and discriminator utilize the structure priors and learnable edges to regularize large concentrated missing regions. …”
Get full text

GaitCSF: Multi-Modal Gait Recognition Network Based on Channel Shuffle Regulation and Spatial-Frequency Joint Learning by Siwei Wei, Xiangyuan Xu, Dewen Liu, Chunzhi Wang, Lingyu Yan, Wangyu Wu

“…However, existing gait recognition methods predominantly rely on single-modal data, which demonstrates insufficient feature expression capabilities when confronted with complex factors in real-world environments, including viewpoint variations, clothing differences, occlusion problems, and illumination changes. …”
Get full text

Network-based intrusion detection using deep learning technique by Muhammad Farhan, Hafiz Waheed ud din, Saadat Ullah, Muhammad Sajjad Hussain, Muhammad Amir Khan, Tehseen Mazhar, Umar Farooq Khattak, Ines Hilali Jaghdam

“…The interesting novelty of this study is the tactical use of ReLU-based DNN combined with feature optimization through the Extra Tree Classifier, which not only overcomes general problems like vanishing gradients and overfitting but also greatly increases the interpretability of the model and the efficiency of its computation. …”
Get full text

Sleeping sound with autism spectrum disorder (ASD): study protocol for an efficacy randomised controlled trial of a tailored brief behavioural sleep intervention for ASD by Harriet Hiscock, Cathrine Mihalopoulos, Nicole Papadopoulos, Emma Sciberras, Jane McGillivray, Lidia Engel, Matthew Fuller-Tyszkiewicz, Susannah T Bellows, Deborah Marks, Patricia Howlin, Nicole Rinehart

“…Introduction Sleep problems are a characteristic feature of children with autism spectrum disorder (ASD) with 40% to 80% of children experiencing sleep difficulties. …”
Get full text

EPR study of interlayer interaction in Gd₂O₃/Fe nanostructure by A. M. Kasumov, A. I. Dmitriev, Yu. M. Bataiev, M. M. Bataiev, V. M. Karavaeva, K. A. Korotkov, A. I. Ievtushenko

Get full text

On the Physical Basis for the Incomparability of NP and BQP by Vivek Kumar, Maheshwari Prasad Singh, Srikanth Radhakrishna

“…We argue that theories $\Theta^{(\mathcal{NP})}$ or $\Theta^{(\mathcal{PSPACE})}$ effectively feature degrees of nonlinearity. Thus, the linearity of quantum theory prevents complete problems in these complexity classes to be efficiently solvable on a quantum computer. …”
Get full text

Discrimination Analysis for Predicting Defect-Prone Software Modules by Ying Ma, Ke Qin, Shunzhi Zhu

“…Based on the analysis, we find that the data sets used in this field have nonlinearly separable and class-imbalanced problems. Unlike the prior works, we try to exploit the kernel method to nonlinearly map the data into a high-dimensional feature space. …”
Get full text

Enhanced YOLOv8-based pavement crack detection: A high-precision approach. by ZuXuan Zhang, HongLi Zhang, TongJia Zhang

“…At present, the repair of cracks is still implemented manually, which has the problems of low identification efficiency and high labor cost. …”
Get full text

Experiment of Image Recognition of Railway Vehicle Brake Shoe Based on Edge Moment Invariants Matching Algorithm by 高向东, 伍世全, 王腾

“…The experimental results show that the proposed method is effective for solving the above problems. The proposed algorithm can recognize the vehicle brake shoe automatically and can provide an effective way to solve the technical problems in long-standing recognition of the moving brake shoes.…”
Get full text

AS-Faster-RCNN: An Improved Object Detection Algorithm for Airport Scene Based on Faster R-CNN by Zhige He, Yuanqing He

“…However, the existing detection models have the problems of degradation, lacking of detection capability for deformed and small objects and single feature extraction, causing low detection accuracy. …”
Get full text

"Wieczór" Edwarda Żebrowskiego - autorska kopia by Andrzej Szpulak

“…He shows that by using the concept of feature of more experienced colleague, Żebrowski at the same time creates the foundations for his own film language and manifests its own perception of the world, as well as interpersonal problems, developed in further work. …”
Get full text

FORMATION OF ENGINEERING ETHICS IN RUSSIA by L. S. Moskovchuk, N. H. Orlova

“…The main periods are emphasized and main problems for each of the periods are identified. The main feature of the first or pre-revolutionary period was the participation of the technical intelligentsia (representatives of well educated people - engineers, scientists) in the formation of ethics of an engineer. …”
Get full text

Active epidemiological surveillance in the program of poliomyelitis eradication in Serbia by Jevremović Ivana, Antonijević Božidar, Lončarević Goranka

“…Along with the achieved results, problems in conducting the active epidemiological surveillance in Serbia, applied measures, and suggestions for improving its quality were presented. …”
Get full text

Deep Learning and Its Application in the Field of Rail Transit by XIONG Qunfang, LIN Jun, LIU Yue, YUAN Hao, YOU Jun

“…Deep learning has shown great potential and advantage in feature extraction and image recognition. In recent years, more and more researches have focused on the application of deep learning in rail transit. …”
Get full text

AN EXISTENCE RESULT FOR SYSTEMS THAT APPEAR IN by Dragoş-Pătru COVEI

“…From thispoint of view and from these reasons such problems shall continue to be characteristic feature ofactivities and tasks taken by scientific research, of major significance in mathematics. …”
Get full text

Development of Refined Electromagnetic Models of Reciprocating Electric Generators with Permanent Magnets by A. B. Menzhinski, A. N. Malashin, P. B. Menzhinski

“…The authors have developed refined electromagnetic models of electric generators of reciprocating motion with permanent magnets, which make it possible to obtain the main parameters of generators at the initial stages of electromagnetic calculation and when solving optimization problems with acceptable accuracy. A distinctive feature of the refined electromagnetic models of generators is the consideration of the scattering and buckling coefficients of the magnetic flux in the magnetic system that change during the simulation.…”
Get full text