Increasing comprehensiveness and reducing workload in a systematic review of complex interventions using automated machine learning by Olalekan A Uthman, Rachel Court, Jodie Enderby, Lena Al-Khudairy, Chidozie Nduka, Hema Mistry, GJ Melendez-Torres, Sian Taylor-Phillips, Aileen Clarke

“…After that, we examined the performance of the classifiers in correctly labelling the papers. We evaluated the performance of the five deep-learning models [i.e. parallel convolutional neural network (CNN), stacked CNN, parallel-stacked CNN, recurrent neural network (RNN) and CNN–RNN]. …”
Get full text

A Transformer-LSTM-SVR hybrid model for AI-driven emotional optimization in NEV embedded interior systems by Zongming Liu, Xuhui Chen, Xinan Liang, Zhicheng Sun, Fengqi Yang, Wenwen Ou, Linwei Li, Xiayan Qin

“…Furthermore, interpretability analysis reveals key design feature differences among user groups. The proposed method combines a Transformer module, which captures higher-order interactions among multidimensional design parameters (e.g., sentiment evaluation coefficients and task completion time), and a Long Short-Term Memory (LSTM) network, configured to enhance time-series feature capture through adjustments to hidden unit count and sequence length. …”
Get full text

A Follow-Up Risk Identification Model Based on Multi-Source Information Fusion by Shuwei Guo, Yunyu Bo, Jie Chen, Yanan Liu, Jiajia Chen, Huimin Ge

“…In Stage 1, a deep feedforward neural network autoencoder reconstructs preprocessed multi-source heterogeneous indicators of human-vehicle-road-environment. …”
Get full text

Exploratory and Interpretable Approach to Estimating Latent Health Risk Factors Without Using Domain Knowledge by Ruichen Cong, Shoji Nishimura, Atsushi Ogihara, Qun Jin

“…In recent years, health analyses based on neural network models have been applied widely. However, such analysis processes are blackbox and the results lack explainability. …”
Get full text

Perceived Information Revisited II by Akira Ito, Rei Ueno, Naofumi Homma

“…LPI is defined as the mutual information between the output of the feature extractor of a neural network (NN) model and the intermediate value, representing the potential attack performance of the trained model. …”
Get full text

Length Requirements for Urban Expressway Work Zones’ Warning and Transition Areas Based on Driving Safety and Comfort by Aixiu Hu, Ruiyun Huang, Yanqun Yang, Ibrahim El-Dimeery, Said M. Easa

“…We employed a combination of the analytic network process and entropy weighting method to calculate the comprehensive weights of the eight evaluation indicators. …”
Get full text

Advancing Progressive Web Applications to Leverage Medical Imaging for Visualization of Digital Imaging and Communications in Medicine and Multiplanar Reconstruction: Software Deve... by Mohammed A. AboArab, Vassiliki T. Potsika, Alexis Theodorou, Sylvia Vagena, Miltiadis Gravanis, Fragiska Sigala, Dimitrios I. Fotiadis

“…This study uses a dataset comprising 22 CT scans of peripheral artery patients to demonstrate the application’s robust performance, with Google Chrome outperforming other browsers in both the local area network and wide area network settings. In addition, the application’s accuracy in MPR reconstructions was validated with an error margin of <0.05 mm and outperformed the state-of-the-art methods by 84% to 98% in loading and volume rendering time. …”
Get full text

Time Series Remote Sensing Image Classification with a Data-Driven Active Deep Learning Approach by Gaoliang Xie, Peng Liu, Zugang Chen, Lajiao Chen, Yan Ma, Lingjun Zhao

“…For uncertainty, we construct an auxiliary deep network to evaluate the uncertainty of unlabeled data. …”
Get full text

Optimal eukaryotic 18S and universal 16S/18S ribosomal RNA primers and their application in a study of symbiosis. by Yong Wang, Ren Mao Tian, Zhao Ming Gao, Salim Bougouffa, Pei-Yuan Qian

“…Eukaryotic 18S ribosomal RNA (rRNA) gene primers that feature a wide coverage are critical in detecting the composition of eukaryotic microscopic organisms in ecosystems. …”
Get full text

COMMENTARY: OPEN ACCESS TO RESEARCH AND THE INDIVIDUAL RESPONSIBILITY OF RESEARCHERS by Thierry Chanier

“…Citation is becoming an important feature of the research evaluation process of individuals as well as of institutions, and OA offers an impact advantage (OpCit, 2006)…”
Get full text

Using U-Net models in deep learning for brain tumor detection from MRI scans by Minh Khiem Nguyen, Phuoc Huy Tran, Tan Tai Phan

“…We propose a method employing two U-Net models: ResNeXt-50 and EfficientNet architectures, integrated with a Feature Pyramid Network (FPN) for segmenting brain tumor. …”
Get full text

Freight production and attraction of industrial, agricultural and livestock, food, and fruit and vegetable commodities by Seyed Ali Ghaemi, Mansour Hadji Hoseinlo

“…This paper analyzes freight production and attraction and their relationship with traffic analysis zone (TAZ) features. The effects of some parameters on the production and attraction of industrial, agricultural and livestock, food, and fruit and vegetable freight were evaluated using over 300 explanatory variables, i.e., land-use types, the numbers and areas of businesses, the characteristics of residents and employees, employment, land price, vehicle ownership per capita, and road network, and TAZ descriptors. …”
Get full text

Identification of ulcerative colitis diagnostic markers from differentially expressed genes shared with Hirschsprung disease by Wei Zuo, Zhengguang Wang

“…Pearson correlation analysis evaluated the relationship between immune cell infiltration and feature genes, while a Protein-Protein Interaction (PPI) network examined interactions with related proteins. …”
Get full text

Detección y diagnóstico de fallas en motores mediante el análisis de vibraciones aplicando técnicas de inteligencia artificial. by Jair Elías Araujo Vargas, Dilan Yesid Franklin Coronel, Victor Manuel Arias Ruiz

“…In this specific task, indicators such as the precision, sensitivity and specificity of the algorithms or aspects such as vibration signal conditioning techniques, extraction methods, selection of key features, training of artificial intelligence models, neural networks and support vector machines were taken into account. …”
Get full text

The Property Graph Data Format (PGDF) by Renzo Angles, Sebastian Ferrada, Ignacio Burgos

“…The expressiveness of PGDF is defined by its ability to represent a wide range of property graph features. In this article, we describe the syntax and semantics of PGDF, outline methods for converting property graphs stored in multiple CSV files to PGDF and other graph data formats, and present an experimental evaluation comparing PGDF, YARS-PG, GraphML, and JSON-Neo4j. …”
Get full text

Robust Classification of UWB NLOS/LOS Using Combined FCE and XGBoost Algorithms by Shoude Wang, Nur Syazreen Ahmad

“…The method begins with feature selection using the Pearson Correlation Coefficient to filter less correlated features of the UWB Channel Impulse Response (CIR) data, followed by outlier handling. …”
Get full text

Automated emotion recognition of students in virtual reality classrooms by Michael Shomoye, Richard Zhao

“…However, the rise of online learning platforms and advanced technologies such as virtual reality (VR) challenge the conventional modes of gauging student engagement, especially when certain facial features become obscured or are entirely absent. This research explores the potential of Convolutional Neural Networks (CNNs), specifically a custom-trained model adapted from the ResNet50 architecture, in recognizing and distinguishing subtle facial expressions in real-time, such as neutrality, boredom, happiness, and confusion. …”
Get full text

On the added value of sequential deep learning for the upscaling of evapotranspiration by B. Kraft, B. Kraft, B. Kraft, J. A. Nelson, S. Walther, F. Gans, U. Weber, G. Duveiller, M. Reichstein, W. Zhang, M. Rußwurm, D. Tuia, M. Körner, Z. Hamdi, M. Jung

“…</p> <p>Our findings highlight non-linear model responses to biases in the training data and underscore the need for improved upscaling methodologies, which could be achieved by increasing the amount and quality of training data or by the extraction of more-targeted features representing spatial variability. The neural networks seem to yield more-realistic ensemble uncertainty compared to XGBoost. …”
Get full text

Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism. by Li Bo, Lv Junrui, Luo Xuegang

“…To overcome these limitations, we propose TGMHA (Tensor Decomposition and Gated Neural Network with Multi-Head Self-Attention), a novel hybrid model that integrates three key innovations: 1) Tensor-based Feature Extraction: We combine Standard Delay Embedding Transformation (SDET) with Tucker tensor decomposition to reconstruct raw time series into low-rank tensor representations, capturing latent spatio-temporal patterns while suppressing sensor noise. 2) Multi-Head Self-Attention for Inter-Indicator Dependencies: A multi-head self-attention mechanism explicitly models complex inter-dependencies among diverse water quality indicators (e.g., pH, dissolved oxygen, conductivity) via parallel feature subspace learning. 3) Efficient Long-Term Dependency Modeling: An encoder-decoder architecture with gated recurrent units (GRUs), optimized by adaptive rank selection, ensures efficient modeling of long-term dependencies without compromising computational performance. …”
Get full text

Employing the concept of stacking ensemble learning to generate deep dream images using multiple CNN variants by Lafta Alkhazraji, Ayad R. Abbas, Abeer S. Jamil, Zahraa Saddi Kadhim, Wissam Alkhazraji, Sabah Abdulazeez Jebur, Bassam Noori Shaker, Mohammed Abdallazez Mohammed, Mohanad A. Mohammed, Basim Mohammed Al-Araji, Abdulkareem Z. Mohmmed, Wasiq Khan, Bilal Khan, Abir Jaafar Hussain

“…Performance of the proposed model was evaluated across three octaves to amplify the maximum possible patterns and features of the base image. …”
Get full text