Porosity Characterization of Thermal Barrier Coatings by Ultrasound with Genetic Algorithm Backpropagation Neural Network by Shuxiao Zhang, Gaolong Lv, Shifeng Guo, Yanhui Zhang, Wei Feng

“…The characteristic features f1,f2,Amax,ΔA of the URCAS, which are highly dependent on porosity, are extracted as input data to train the GA_BPNN model for predicting the unknown porosity. …”
Get full text

AI-Driven Ground Points Extraction for Rugged Terrains in Coastal Landscape – A Case Study by N. Manikkavasagam, M. Rajkumar, S. Nagarajan, P. DeWitt

“…To quantify the volumetric loss of sand, the ground and non-ground features should be separated, and erosion could be quantified using the extracted ground features. …”
Get full text

Water Classification Using Convolutional Neural Network by Saira Asghar, Ghulam Gilanie, Mubbashar Saddique, Hafeez Ullah, Heba G. Mohamed, Irshad Ahmed Abbasi, Mohamed Abbas

“…The various image enhancement techniques, i.e., Unsharp Masking (UM), Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Contrast Stretching, were used to highlight the contrast and texture features of water images. The enhanced image samples were then fed to the proposed Convolutional Neural Network (CNN)-based model named WaterNet (WNet) for classification. …”
Get full text

Development and multicenter validation of on-site breast cancer diagnosis using paper spray ionization miniature mass spectrometry by Hou-Chun Huang, Hsin-Hsiang Chung, Jia-Ying Yu, Bo-Rong Chen, Ming-Yang Wang, Cheng-Chih Hsu

“…A machine learning model was trained to differentiate benign and malignant samples based on molecular profiles. …”
Get full text

Enhancing market trend prediction using convolutional neural networks on Japanese candlestick patterns by Edrees Ramadan Mersal, Kürşat Mustafa Karaoğlan, Hakan Kutucu

“…This study aimed to predict the following candle-trend-based JC charts using convolutional neural networks (CNNs). …”
Get full text

When Two are Better Than One: Synthesizing Heavily Unbalanced Data by Francisco Ferreira, Nuno Lourenco, Bruno Cabral, Joao Paulo Fernandes

“…With this approach, we observed, at most, a 5% disparity in F1 scores between classifiers trained and tested with actual data and the ones trained with synthetic data and tested with actual data.…”
Get full text

AI-Powered Mobile App for Nuclear Cataract Detection by Alicja Anna Ignatowicz, Tomasz Marciniak, Elżbieta Marciniak

“…The process involves identifying pathological features and assessing the severity of the detected condition, enabling comprehensive characterization of the NC (nuclear cataract) of cataract progression based on the LOCS III scale classification. …”
Get full text

CELM: An Ensemble Deep Learning Model for Early Cardiomegaly Diagnosis in Chest Radiography by Erdem Yanar, Fırat Hardalaç, Kubilay Ayturan

“…In addition, we introduced a novel stacking-based ensemble model—Combined Ensemble Learning Model (CELM)—that integrates complementary CNN features via a meta-classifier. …”
Get full text

Intelligent resource allocation in internet of things using random forest and clustering techniques by Nahideh Derakhshanfard, Lida Hosseinzadeh, Fahimeh Rashid Jafari, Ali Ghaffari

“…Initially, IoT devices are grouped using the K-Means algorithm based on features such as energy consumption and bandwidth requirements. …”
Get full text

Enhanced and Interpretable Prediction of Multiple Cancer Types Using a Stacking Ensemble Approach with SHAP Analysis by Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Zhongming Zhao

“…This study aimed to develop and evaluate ensemble learning models, specifically stacking, for the accurate prediction of lung, breast, and cervical cancers using lifestyle and clinical data. <b>Methods</b>: 12 base learners were trained on datasets for lung, breast, and cervical cancer. …”
Get full text

Classification of Dyslexia Among School Students Using Deep Learning by Alia Hussein, Ahmed Talib Abdulameer, Ali Abdulkarim, Husniza Husni, Dalia Al-Ubaidi

“…The CNN accurately identified dyslexic individuals based on the spectrogram features, outperforming traditional diagnostic methods. …”
Get full text

Freezing Damage Control of Railway Subgrade Miniature Shields in Cold Climatic Regions: Construction Technology Optimization via Numerical Simulation by Caolin Qing, Shaolong Jie, Zurun Yue, Liwei Wang, Bingcheng Wang

“…Microshield structure replacement technology is commonly used to control the freezing damage of railway roadbeds, featuring high efficiency and easy operation. However, improper disposal of measures in the construction process will still cause excessive deformation of the line and endanger the safety of train operations. …”
Get full text

A multimodal travel route recommendation system leveraging visual Transformers and self-attention mechanisms by Zhang Juan, Jing Zhang, Ming Gao

“…Based on this fused representation, a classification or regression model is trained using real travel datasets to recommend optimal travel routes.Results and discussionThe algorithm was rigorously evaluated through experiments conducted on real-world travel datasets, and its performance was benchmarked against other route recommendation methods. …”
Get full text

Definition of the Content Core of Synonymic Series of English-Language Terms in the Field of Construction Equipment by V. A. Rodin

“…This article is devoted to the definition of the content core of synonymous series of English-language terms in the field of construction equipment as one of the methods of studying this terminology system from the point of view of its features and structure. The relevance of the work is due to the growing need to study the terminology system “Construction equipment” in order to train specialists with competencies in the field of design, repair, modernization, and operation of construction machines arriving in the territory of the Russian Federation from abroad. …”
Get full text

Extreme Gradient Boosting Regressor Solution for Defy in Drilling of Materials by Sangeetha Elango, Elango Natarajan, Kaviarasan Varadaraju, Ezra Morris Abraham Gnanamuthu, R. Durairaj, Karthikeyan Mohanraj, M. A. Osman

“…Hyperparameters estimated from the k-fold cross validation were then applied to train and test the XGBoost regressor-based machine learning (ML) model. …”
Get full text

Integrated Method of Assessment the Type of Damages, their Localization and Predicting the Destruction of High-Voltage Electrical Equipment Insulators by the Partial Discharges Cha... by Gataullin А.М., Gubaev D.F.

“…At the same time, the breakdown signs of the model discharge gap, the breakdown voltage values for defective and operable porcelain insulators are determined, which can be used to train models of artificial neural networks and recognize the pre-breakdown situation based on them. …”
Get full text

Toward Symmetry in Accessible Restrooms Design: Integrating KE, RST, and SVM for Optimized Emotional-Functional Alignment by Zimo Chen, Jingwen Tian, Hongtao Zhou, Duan Wu

“…The morphological decomposition of 60 restroom samples yielded 41 design attributes, from which RST attribute reduction isolated six critical features. An SVR model with a radial-basis kernel, trained on 90% of the data and validated on the remaining 10%, achieved R² = 0.931 and RMSE = 0.085. …”
Get full text

A Mobile Sperm Analyzer with User-Friendly Microfluidic Chips for Rapid On-Farm Semen Evaluation by Shu-Sheng Lin, Chang-Yu Chen, Cheng-Ming Lin, Tsun-Chao Chiang, Yu-Siang Tang, Chang-Ching Yeh, Wei-Fan Hsu, Andrew M. Wo

“…This study presents a mobile-based sperm analysis system featuring a user-friendly, droplet-loaded microfluidic chip that enables non-specialist users to perform the rapid and accurate quantitative evaluation of boar semen directly on the farm. …”
Get full text

Upper Limb Action Recognition Using Deep Learning and sEMG by XULinsen, ZHANGHengwei, CHENGen, WANGZhihuan, SUIXiang

“…The concatenated spectrum method converts the preprocessed time-domain signal into the corresponding spectrum through STFT. Two fine-tuning pre-trained models VGG16 and Resnet50 are used to extract features from the vertically concatenated spectrum of all channels and concatenate them. …”
Get full text

A novel approach for music genre identification using ZFNet, ELM, and modified electric eel foraging optimizer by Shuang Zhang, Zhiyong Sun, Hasan Jafari

“…The proposed model uses a pre-trained Zeiler and Fergus Network (ZFNet) to extract high-level features from audio signals, while an Extreme Learning Machines (ELM) is utilized for efficient classification. …”
Get full text