Enhancing stock index prediction: A hybrid LSTM-PSO model for improved forecasting accuracy. by Xiaohua Zeng, Changzhou Liang, Qian Yang, Fei Wang, Jieping Cai

“…The experimental results on six global stock indices demonstrate that PSO-LSTM effectively fits real data, achieving high prediction accuracy. Moreover, increasing PSO iterations lead to gradual loss reduction, which indicates PSO-LSTM's good convergence. …”
Get full text

Modeling of Distorted Degradation Data Based on Oil Analysis by Yue Chen, Jian Shi

“…The main contributions are as follows: First, we developed a degradation correction model that automatically identifies oil top-up events while globally rectifying distorted data, achieving an accurate reconstruction of physical degradation curves. …”
Get full text

Research on Spam Filters Based on NB Algorithm by Su Shengyue

“…The algorithm demonstrated high accuracy and efficiency in classifying large-scale text data, achieving an accuracy of 97.74%, a recall rate of 96.60%, and a precision rate of 96.8%, with an F1 score of 0.97. …”
Get full text

Pseudo Multi-Modal Approach to LiDAR Semantic Segmentation by Kyungmin Kim

“…Extensive experiments on two benchmark datasets demonstrate that the proposed method improves performance by 2.2–3.5 mIoU over the baseline using only LiDAR data, achieving performance comparable to that of real multi-modal approaches.…”
Get full text

Bootstrap for finite N lattice Yang-Mills theory by Vladimir Kazakov, Zechuan Zheng

“…The exact upper and lower margins for the free energy per plaquette, derived from our bootstrap method, demonstrate good agreement with Monte Carlo data, achieving precision within 0.1% for the physically relevant range of couplings in both three and four dimensions. …”
Get full text

Detection of surges of SARS-Cov-2 using nonparametric Hawkes models by Sophie Phillips, George Mohler, Frederic Schoenberg

“…At false alarm rates below 5%, the forecasts based on Rt are correct more often than forecasts based on smoothing the raw case count data, achieving a maximum accuracy of 90% with Rt>1.39. …”
Get full text

Framework for investigating structure cracking using real engineering data combined with physics constraints by Han Si, Qidi Wang, Xin Ruan, Xingpo Fang

“…This paper proposes a data-driven analysis framework that combines physical principles, dimensionality reduction techniques and ensemble learning models to trace back the deep-seated connections between data, achieving multi-factor analysis of structural defects. …”
Get full text

An object-based spectral and elevation feature fusion framework for landslide mapping using time-series Landsat-8 imagery by Tsung-Han Wen, Tee-Ann Teo

“…The experimental results demonstrated that the fused model outperformed models that used only spectral data, achieving higher accuracy and reducing commission and omission errors. …”
Get full text

Multi-Dimensional Anomaly Detection and Fault Localization in Microservice Architectures: A Dual-Channel Deep Learning Approach with Causal Inference for Intelligent Sensing by Suchuan Xing, Yihan Wang, Wenhe Liu

“…We evaluated our framework using a semi-supervised learning approach that leveraged both labeled anomalies and abundant normal data, achieving 95.4% detection accuracy, 93.8% F1-score, and 87.6% precision in fault component localization. …”
Get full text

Advancements in the Application of Convolutional Neural Networks in Ultrasound Imaging for Breast Cancer Diagnosis and Treatment by An Zichen, Li Fan

“…Deep learning (DL), as one of the most powerful machine learning techniques in the field of artificial intelligence (AI), has the ability to automatically select features from raw data, achieving remarkable advancements in breast US imaging. …”
Get full text

The Dynamic Response of Aluminum Alloy Plates Subjected to Multiple-Fragment Impacts Under Pre-Tensile Loading: A Numerical Study by Yitao Wang, Teng Zhang, Hanzhe Zhang, Yuting He, Liying Ma, Antai Ren

“…Utilizing an advanced finite element framework with stress dynamic relaxation preloading, the established model was rigorously validated against experimental gas-gun impact data, achieving less than 11% deviation in residual velocity. …”
Get full text

Enhancing Medical X-Ray Image Classification with Neutrosophic Set Theory and Advanced Deep Learning Models by Walid Abdullah

“…The results indicate that models trained on NS-transformed data, particularly DenseNet and MobileNet, yield superior outcomes compared to those trained on the original data, achieving significantly higher accuracy, precision, and recall. …”
Get full text

Multi-dimensional perceptual recognition of tourist destination using deep learning model and geographic information system. by Shengtian Zhang, Yong Li, Xiaoxia Song, Chenghao Yang, Niusha Shafiabady, Robert M X Wu

“…Then, we adopted the improved Inception V3 model, the bidirectional long short-term memory network (BiLSTM) model with multi-head attention, and geographic information system (GIS) technology to recognize basic tourist feature information from the UGC dataset, such as the content, sentiment, and spatiotemporal perceptual dimensions of the data, achieving a recognition accuracy of over 97%. Finally, a progressive dimension combination method was proposed to visualize and analyze multiple perceptions. …”
Get full text

A lightweight intrusion detection approach for CAN bus using depthwise separable convolutional Kolmogorov Arnold network by Wenwen Zhao, Yikun Yang, Hao Hu, Yanzhan Chen, Fan Yu

“…To address these limitations, we employ spectral normalization GAN to synthesize anomalous data, achieving a balanced distribution across four attack categories and normal traffic. …”
Get full text

A Novel Empirical Fractional Approach for Modeling the Clogging of Membrane Filtration During Protein Microfiltration by Leila Cherifi, Yamina Ammi, Salah Hanini, Mohamed Hentabli, Ouafa Belkacem, Jérôme Harmand

“…The models are validated against experimental data, achieving impressive coefficients of determination (<i>R</i>²) between 0.9896 and 0.9997 and relative root mean squared errors (nRMSE) ranging from 0.8674% to 2.9548%. …”
Get full text

Advances in deep learning and MRI co-assisted genotyping of brain gliomas by CUI Shaoguo, CHEN Junshan

“…Current studies have established a technical framework ranging from supervised to unsupervised learning by integrating multimodal MRI data, achieving high predictive accuracy in single-gene classification through multi-task joint optimization and transfer learning. …”
Get full text

Outdoor RGB and Point Cloud Depth Dataset for Palm Oil Fresh Fruit Bunch Ripeness Classification and Localization by Jin Yu Goh, Mohamed Sultan Mohamed Ali, Yusri Md Yunos, Usman Ullah Sheikh, Muhamad Salman Khan

“…Binary ripeness annotations adhere to Malaysian Palm Oil Board standards, with spatial registration between RGB and depth data achieving a mean error of 1.8 cm at 3 meters. Expert validation resulted in 92.5% inter-rater agreement. …”
Get full text

A Data Cleaning Method for the Identification of Outliers in Fishing Vessel Trajectories Based on a Geocoding Algorithm by Li Zhang, Weifeng Zhou

“…The method proposed in this study is able to effectively identify outliers in trajectory data, achieving efficient and effective trajectory data cleaning and improving the accuracy and reliability of the data.…”
Get full text

Dam Deformation Data Preprocessing with Optimized Variational Mode Decomposition and Kernel Density Estimation by Siyu Chen, Chaoning Lin, Yanchang Gu, Jinbao Sheng, Mohammad Amin Hariri-Ardebili

“…Validation using simulated deformation data and Global Navigation Satellite Systems (GNSS)-based observed horizontal deformation from dam engineering demonstrates the method’s robustness in accurately identifying outliers and denoising data, achieving superior preprocessing performance.…”
Get full text

Lightweight Deep Learning for sEMG-Based Fingers Position Classification and Embedded System Deployment by Victor H. Benitez, Jesus Pacheco, Guillermo Cuamea-Cruz

“…A 1D Convolutional Neural Network was developed and validated using experimental data, achieving a classification accuracy of 97% in controlled scenarios. …”
Get full text