Target image detection algorithm of complex road scene based on improved multi-scale adaptive feature fusion technology by Xu Zhaosheng, Liao Zhongming, Xiao Xiaoyong, Ahmad Suzana, Mat Diah Norizan, Ismail Azlan

“…The simulation outcomes illustrate that the recommended IMSAFFT model increases the accuracy ratio of 98.4%, target image detection ratio of 97.4%, traffic prediction rate of 96.5%, processing speed rate of 10.4% and F1-score ratio of 95.4% compared to other existing models.…”
Get full text

Mapping the internal structures of fault zones of the sedimentary cover: a tectonophysical approach applied to interpret TDEM data (Kovykta gas condensate field) by K. Zh. Seminsky, I. V. Buddo, A. A. Bobrov, N. V. Misyurkeeva, Yu. P. Burzunova, A. S. Smirnov, I. A. Shelokhov

“…Such segments are confined to layers that differ with respect to frac‐ turing. Exploration and development of hydrocarbon deposits can benefit from 3D modeling of large fault zones with the use of the tectonophysical approach for processing and interpretation of the TEM data. …”
Get full text

Using Deep Learning Techniques to Enhance Blood Cell Detection in Patients with Leukemia by Mahwish Ilyas, Muhammad Bilal, Nadia Malik, Hikmat Ullah Khan, Muhammad Ramzan, Anam Naz

“…We have modified its layers combination to include convolutional, pooling, and fully connected layers that are optimized for image characteristics. …”
Get full text

A digital twin-enabled fog-edge-assisted IoAT framework for Oryza Sativa disease identification and classification by Goluguri N.V. Rajareddy, Kaushik Mishra, Satish Kumar Satti, Gurpreet Singh Chhabra, Kshira Sagar Sahoo, Amir H. Gandomi

“…This model is further refined by including Quaternion convolution layers, which enhance colour information processing, and Atrous convolution layers, which improve depth perception, particularly in extracting disease patterns. …”
Get full text

Deep learning-based feature selection for detection of autism spectrum disorder by Ibrahim Nafisah, Nermine Mahmoud, Ahmed A. Ewees, Mohamed G. Khattap, Abdelghani Dahou, Safar M. Alghamdi, Ibrahim A. Fares, Mohammed Azmi Al-Betar, Mohammed Azmi Al-Betar, Mohamed Abd Elaziz, Mohamed Abd Elaziz

“…The enhanced feature selection process, coupled with the hybrid model, addresses limitations in current neuroimaging analyses and offers a promising direction for more accurate and clinically applicable ASD detection models.…”
Get full text

Development of Level 2 aerosol and surface products from cross-track scanning polarimeter POSP on board the GF-5(02) satellite by C. Chen, X. Lei, Z. Liu, H. Gu, O. Dubovik, P. Litvinov, D. Fuertes, Y. Cao, Y. Cao, H. Yu, H. Yu, G. Xiang, B. Meng, Z. Qiu, X. Sun, J. Hong, Z. Li

“…Here, we developed aerosol and surface products from POSP/GF-5(02) based on the Generalized Retrieval of Atmosphere and Surface Properties (GRASP)/Models approach. The detailed retrieval approach and processing scheme are provided. …”
Get full text

Enhancing IoT security and healthcare data protection in the metaverse: A Dynamic Adaptive Security Mechanism by Saima Siraj Qureshi, Jingsha He, Nafei Zhu, Ahsan Nazir, Juan Fang, Xiangjun Ma, Ahsan Wajahat, Faheem Ullah, Sirajuddin Qureshi, Sahroui Dhelim, Muhammad Salman Pathan

“…Although the LSTM model demonstrates strong accuracy, the ensemble approach of Random Forest balances computational efficiency and performance. …”
Get full text

On the drivers of ice nucleating particle diurnal variability in Eastern Mediterranean clouds by Kunfeng Gao, Franziska Vogel, Romanos Foskinis, Stergios Vratolis, Maria I. Gini, Konstantinos Granakis, Olga Zografou, Prodromos Fetfatzis, Alexandros Papayannis, Ottmar Möhler, Konstantinos Eleftheriadis, Athanasios Nenes

Get full text

Calculation of oxidation depth in low-carbon steel under nonstationary conditions by introducing a fictitious time by Marija Riđošić, Branko Pejović, Milorad Tomić, Slavko Smiljanić

“…The exact information about the thickness of the oxidation layer has a great practical importance. The aim of this paper is to take the existing process for calculating the depth of oxidation, which is valid for a stationary area, and use it for a non-stationary area. …”
Get full text

A Deep Learning Approach for Fault Detection and Localization in MT-VSC-HVDC System Utilizing Wavelet Scattering Transform by Manohar Mishra, Debadatta Amaresh Gadanayak, Abha Pragati, Jai Govind Singh

“…The variable epoch size training enhances convergence speed, leading to more stable and consistent results. A secondary LSTM model with a similar layer architecture is also trained and evaluated on WST-based features to identify the fault location within internal faults. …”
Get full text

Integration of Artificial Neural Network Regression and Principal Component Analysis for Indoor Visible Light Positioning by Negasa Berhanu Fite, Getachew Mamo Wegari, Heidi Steendam

“…Additionally, the pose of the light-emitting diodes is prior unknown, adding another layer of complexity to the positioning process. Dynamic indoor environments further complicate matters due to user mobility and obstacles, which can affect system accuracy. …”
Get full text

Foreign object recognition for mine conveyor belt iron separators based on transfer learning with EfficientNet by Hailong YANG, Yiping YUAN, Panpan FAN, Lu XIAO, Feiyang ZHAO, Shaoke YUAN

“…Comparative experiments were conducted, and results show that the proposed model achieves faster stable iterations and lower loss values, outperforming other existing convolutional neural network models across various performance metrics. …”
Get full text

CALCULATION STUDIES OF SPATIAL DISTRIBUTION OF THE ABSORBED DOSE RATE FOR VARIOUS SEEDS by N. A. Nerozin, A. P. Pyshko, V. V. Shapovalov

“…Microsourse «SEED No. 6711» (model of the company Nicomed Amersham) is hermetically sealed in a titanium capsule silver rod covered with a thin layer of radioactive I‑125. …”
Get full text

GAN-enhanced deep learning for improved Alzheimer's disease classification and longitudinal brain change analysis by Purushottam Pandey, Surbhi Bhatia Khan, Surbhi Bhatia Khan, Surbhi Bhatia Khan, Jyoti Pruthi, Eid Albalawi, Ali Algarni, Ahlam Almusharraf

“…These features are then processed through the LSTM model, which classifies individuals into categories such as cognitively normal (CN), mild cognitive impairment (MCI), and Alzheimer's disease (AD). …”
Get full text

Exploring MediaPipe optimization strategies for real-time sign language recognition by Phuoc Thanh Nguyen, Thanh Hoang Nguyen, Ngoc Xuan Nguyen Hoang, Huynh Thanh Binh Phan, Hoang Son Hai Vu, Hieu Nhan Huynh

“…We introduce an innovative multi-modal methodology, amalgamating four distinct Long Short-Term Memory (LSTM) models dedicated to processing skeletal coordinates ascertained from the MediaPipe framework. …”
Get full text

GMTBLC: a deep learning-based bi-modal network traffic classification method by WEI Debin, JIANG Qinlong, WEN Jinglong, WANG Xinrui

“…Experimental results on ISCX and USTC-TFC2016 datasets demonstrate that the proposed model achieves a classification accuracy of 99.31%, with precision, recall, and F1-score all above 98%, and outperforms the other models in classification effectiveness.…”
Get full text

Influence of subgrade filling types on covering effect in seasonally frozen soil area by FENG Degang, HAO Dongmiao, ZHANG Mingli, YAN Yanfeng, ZHOU Zhixiong, ZHANG Ruiling, LI Guang

“…The water-vapor-heat model of unsaturated soil is established to simulate the formation process and difference of different subgrade filling cover effect in a certain area of Lanzhou. …”
Get full text

AI-Enhanced Detection of Heart Murmurs: Advancing Non-Invasive Cardiovascular Diagnostics by Maria-Alexandra Zolya, Elena-Laura Popa, Cosmin Baltag, Dragoș-Vasile Bratu, Simona Coman, Sorin-Aurel Moraru

“…The model processes heart sound recordings using advanced pre-processing techniques such as z-score normalization, band-pass filtering, and data augmentation (Gaussian noise, time shift, and pitch shift) to enhance robustness. …”
Get full text

Phase diagram from nonlinear interaction between superconducting order and density: toward data-based holographic superconductor by Sejin Kim, Kyung Kiu Kim, Yunseok Seo

“…Consideration of the positional embedding layers is motivated by the transformer model of natural-language processing in the artificial intelligence (AI) field. …”
Get full text

Study on subsidence evolution induced by coal mining under highway based on finite element simulation by Guoxi Cheng, Huibin Liu, Fengli Li, Teng Nie, Qiang Wang, Chuang Peng

“…A comparative study revealed that the mechanical properties of the generalized layers determined by processing the mechanical parameters of dry core samples will be much higher than those of the natural strata under the in situ water-saturated condition, and then the subsidence caused by coal mining will be significantly underestimated. …”
Get full text