Defect Detection and Classification on Wind Turbine Blades Using Deep Learning with Fuzzy Voting by Reed Pratt, Clark Allen, Mohammad A. S. Masoum, Abdennour Seibi

“…Three Mask R-CNN models, leveraging different convolutional neural network (CNN) backbones—VGG19, Xception, and ResNet-50—were constructed and trained on a novel dataset of 3000 RGB images (size 300 × 300 pixels) annotated with defects, including cracks, holes, and edge erosion. …”
Get full text

Hyperspectral Imaging and Machine Learning for Diagnosing Rice Bacterial Blight Symptoms Caused by <i>Xanthomonas oryzae</i> pv. <i>oryzae</i>, <i>Pantoea ananatis</i> and <i>Enter... by Meng Zhang, Shuqi Tang, Chenjie Lin, Zichao Lin, Liping Zhang, Wei Dong, Nan Zhong

“…<i>oryzae</i>, yet they differ in drug resistance and management strategies. …”
Get full text

Models, systems, networks in economics, engineering, nature and society by D.V. Mirosh

“…The use of the developed neural networks allows to improve diagnostic studies for asynchronous machines of various capacities, easily adapt them to different dimensional designs, improve the quality of diagnostic services provided and reduce the labor costs of diagnostic specialists in the study of the parameters of the state of an electric machine.…”

Non-intrusive Load Decomposition Model Based on Deep Fusion of Multi-modal Integration by YAO Gang, WANG Yun, WANG Yuanliang, SONG Zihao

Get full text

Quantum AI: A Cognitive Machine Learning Technique based on Nurturing Food Security Sustainability Predictive Analysis for Life Science - Bioengineering in Healthcare by Senthil G.A., Monica K.M., Prabha R., Prinslin L., Elavarasi R.

“…The system's Leveraging (QRL) has high prediction accuracies of 90%, 92%, and 93%, ensuring efficient nutritional analysis in different foods. Integrating quantum computer models will greatly improve predictive performance and scalability. …”
Get full text

Leveraging hybrid 1D-CNN and RNN approach for classification of brain cancer gene expression by Heba M. Afify, Kamel K. Mohammed, Aboul Ella Hassanien

“…Therefore, the classification of brain cancer gene expression according to the hybrid model (BO + 1D-CNN + RNN) provides more accurate and useful assessments for patients with different types of brain cancers. Thus, gene expression data are used to create a DL classification-based- hybrid model that will hold senior promise in the treatment of brain cancer.…”
Get full text

BO-CNN-BiLSTM deep learning model integrating multisource remote sensing data for improving winter wheat yield estimation by Lei Zhang, Changchun Li, Xifang Wu, Hengmao Xiang, Yinghua Jiao, Huabin Chai

“…Furthermore, the BCBL model exhibited strong stability and generalization across different climatic conditions.ConclusionThus, the BCBL model combined with SIF data can offer reliable winter wheat yield estimates, hold significant potential for application, and provide valuable insights for agricultural policymaking and field management.…”
Get full text

Machine Learning-Based Detection of Non-Technical Losses in Power Distribution Networks by Mahmut Türk, Heybet Kılıç, Cem Haydaroglu

“…In order to reduce these losses, we propose an artificial intelligence-based approach that utilizes deep learning architectures in the detection of different types of leakage (voltage leakage, current leakage and voltage-current leakage). …”
Get full text

Electrocardiographic sex index: a continuous representation of sex by Ibrahim Karabayir, Turgay Celik, Luke Patterson, Liam Butler, David Herrington, Oguz Akbilgic

Get full text

PBD-YOLO: Dual-Strategy Integration of Multi-Scale Feature Fusion and Weak Texture Enhancement for Lightweight Particleboard Surface Defect Detection by Haomeng Guo, Zheming Chai, Huize Dai, Lei Yan, Pengle Cheng, Jianhua Yang

“…In order to improve the ability of the algorithm to extract weak texture features, the SPDDEConv (Space to Depth and Difference Enhance Convolution) module was introduced in this study, which reduced the loss of information in the down-sampling process through space-to-depth transformation and enhanced the edge information of weak texture defects through difference convolution. …”
Get full text

Caricature Face Photo Facial Attribute Similarity Generator by Muhammad Irfan Khan, Muhammad Kashif Hanif, Ramzan Talib

“…Furthermore, the ratio between different facial features was computed using different vertical and horizontal distances. …”
Get full text

Pedestrian Detection in Fisheye Images Based on Improved YOLOv8 Algorithm by ZHU Yumin, SUN Guangling, MIAO Fei

“…The feature information of different scales is extracted through DWConv with different convolution kernels, and the CA and SA modules are combined to enhance the model’s feature expression ability. …”
Get full text

Application of Generative Adversarial Nets (GANs) in Active Sound Production System of Electric Automobiles by Kai Liang, Haijun Zhao

“…To demonstrate the quality difference of the generated samples from different input signals, two GAN models with different inputs were constructed. …”
Get full text

Surface morphology segmentation and evaluation of diamond lapping pad based on improved Mask R-CNN by Wenlong SUO, Yanfen LIN, Congfu FANG

“…ConclusionsThe dilated convolution method can effectively expand the receptive field and improve the ability to extract deep semantic features of targets at different scales. …”
Get full text

LBNet: A Lightweight Bilateral Network for Semantic Segmentation of Martian Rock by Pengfei Wei, Zezhou Sun, He Tian

“…In the deep semantic information branch, channel split convolution (CSConv) is adopted to extract features by adopting different convolution kernels on different channel, reducing the similarity between different feature maps and increasing feature maps diversity. …”
Get full text

First-Arrival Picking for Microseismic Monitoring Based on Deep Learning by Xiaolong Guo

“…In microseismic monitoring, achieving an accurate and efficient first-arrival picking is crucial for improving the accuracy and efficiency of microseismic time-difference source location. In the era of big data, the traditional first-arrival picking method cannot meet the real-time processing requirements of microseismic monitoring process. …”
Get full text

Data-driven cultural background fusion for environmental art image classification: Technical support of the dual Kernel squeeze and excitation network. by Chenchen Liu, Haoyue Guo

“…The DKSE module adopts various techniques such as dilated convolution, L2 regularization, Dropout, etc. in the multi-layer convolution process. …”
Get full text

SAD-Net: a full spectral self-attention detail enhancement network for single image dehazing by Qingjun Niu, Kun Wu, Jialu Zhang, Zhenqi Han, Lizhuang Liu

“…SDEC combines wavelet transform and difference convolution(DC) to enhance high-frequency features while preserving low-frequency information. …”
Get full text

Evaluation of Various Free Software Options for Catphan 504 Phantom Analysis by Lorena Cunha Fernandes, Maira Ribeiro dos Santos, Leonardo Peres da Silva, Thiago Viana Miranda Lima, Rafael Figueiredo Pohlmann Simões

“…Purpose: the purpose of this study is to analyse the images reconstructed with different thorax and bone convolution filters using popular free-use software in the field of medical physics, for the Catphan 504 phantom. …”
Get full text

A Crowd Density Detection Algorithm for Tourist Attractions Based on Monitoring Video Dynamic Information Analysis by Lina Li

“…In this paper, novel scale perception module and inverse scale perception module are designed to further facilitate the mining of multiscale information by the counting model; the main function of the third stage is to generate the population distribution density map, which mainly consists of three columns of void convolution with different void rates and generates the final population distribution density map using the feature maps of different branch regressions. …”
Get full text