MFGC-Net: Bridging and Fusing Multiscale Features and Global Contexts for Multitask Sea Ice Fine Segmentation by Tianen Ma, Xinwei Chen, Linlin Xu, Pengfei Ma, Peilin Yu

“…However, the existing sea ice segmentation algorithms for SAR images often fail to consider long-range contextual dependencies when capturing multiscale features, resulting in an inability to fully exploit multiscale global contextual information. …”
Get full text

Estimation of gas hydrate and free gas saturation using the rock physics model based on constrained least squares and trust region method in the Shenhu Area, South China Sea by Dajiang Meng, Dajiang Meng, Ruwei Zhang, Ruwei Zhang, Yuan Gu, Yuan Gu, Baojin Zhang, Baojin Zhang, Yunqian Lu, Yunqian Lu, Jiangnan Lin, Jiangnan Lin, Lijie Wang, Lijie Wang

“…Additionally, the application results indicate that the trust region algorithm demonstrates favorable global convergence.…”
Get full text

Improved Phase Diversity Wavefront Sensing with a Deep Learning-Driven Hybrid Optimization Approach by Yangchen Wang, Ming Wen, Hongcai Ma

“…However, conventional optimization-based PDWS methods often suffer from high computational costs and sensitivity to initial values. To address these challenges, this paper proposes a hybrid PDWS method that integrates deep learning with nonlinear optimization to improve efficiency and accuracy. …”
Get full text

Research on fault line selection technology of distribution network based on EMD and WVD by Jin Zhang, Dezhi Chen, Siman Han

“…Amplitude and energy values are combined to define correctness weights. …”
Get full text

Enhancing Visitor Forecasting with Target-Concatenated Autoencoder and Ensemble Learning by Ray-I Chang, Chih-Yung Tsai, Yu-Wei Chang

“…Preceding forecasting algorithms primarily focused on time series analysis, often overlooking influential factors such as economic conditions. …”
Get full text

Method for Automatic Path Planning of Underwater Vehicles Considering Ambient Noise Fields by Gengming Zhang, Lihua Zhang, Yitao Wang, Chunyu Kang, Yinfei Zhou, Xiaodong Ma, Zeyuan Dai, Shaxige Wu

“…The method involves constructing a background noise spectrum level model using Automatic Identification System (AIS) data and wind speed data. Then, a Range-Dependent Acoustic Model (RAM) is integrated to generate a statistically significant 10th percentile noise field. …”
Get full text

Empowering Healthcare: TinyML for Precise Lung Disease Classification by Youssef Abadade, Nabil Benamar, Miloud Bagaa, Habiba Chaoui

“…These findings highlight the potential of TinyML to provide accessible, reliable, and real-time diagnostic tools, particularly in remote and underserved areas, demonstrating the transformative impact of integrating advanced AI algorithms into portable medical devices. …”
Get full text

Deep Learning Network Selection and Optimized Information Fusion for Enhanced COVID-19 Detection: A Literature Review by Olga Adriana Caliman Sturdza, Florin Filip, Monica Terteliu Baitan, Mihai Dimian

Get full text

Leveraging machine learning techniques to analyze nutritional content in processed foods by K. A. Muthukumar, Soumya Gupta, Doli Saikia

“…With protein deficiencies being prevalent among Indians, it is crucial to understand the impact of food processing on nutrient retention. This research integrates machine learning with food science to develop a comprehensive AI framework for forecasting the protein content of various plant-based sources following both traditional and non-conventional processing methods. …”
Get full text

Digital Twin and Data-Driven Remaining Useful Life Prediction of Gearbox by Quanbo Lu, Mei Li, Xiaojuan Huang

“…To further improve prediction accuracy, the paper employs the Central Particle Swarm Optimization algorithm to merge both theoretical and actual RUL values. …”
Get full text

CNN-GRU Battery SOC Estimation Method Fused with Attention Mechanism for Electric Multiple Units by WANG Shenghui, TIAN Qin, LIU Lihao, FENG Enlai, YU Tianjian

“…To precisely estimate the SOC of small-sample battery cycling data, this paper transforms the continuous regression model into a classification problem, discretizes the battery SOC ranges, and converts the final prediction result into discrete SOC values. The experimental results show that compared with the CNN-GRU algorithm, the proposed approach improves three key metrics — root mean square error, mean absolute error, and mean relative error by 18.90%, 17.92% and 19.78%, respectively, demonstrating impressive prediction accuracy and stability.…”
Get full text

Leveraging Graph Neural Networks for IoT Attack Detection by Mevlüt Uysal, Erdal Özdoğan, Onur Ceran

“…To address this challenge, researchers propose a novel hybrid approach combining Graph Neural Networks and XGBoost algorithm for robust intrusion detection in IoT ecosystems. …”
Get full text

N-Bipolar Soft Expert Sets and Their Applications in Robust Multi-Attribute Group Decision-Making by Sagvan Y. Musa, Amlak I. Alajlan, Baravan A. Asaad, Zanyar A. Ameen

“…Existing MAGDM approaches often lack the ability to simultaneously integrate positive and negative assessments, especially in nuanced, multi-valued evaluation spaces. …”
Get full text

Machine Learning Framework for Early Detection of Chronic Kidney Disease Stages Using Optimized Estimated Glomerular Filtration Rate by Samit Kumar Ghosh, Namareq Widatalla, Ahsan H. Khandoker

“…Once the model fine-tunes the eGFR estimations, it feeds them into various algorithms for CKD stage classification, including Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). …”
Get full text

METHOD OF QUALIFICATION ESTIMATION AND OPTIMIZATION OF PROFESSIONAL TEAMS OF PROGRAMMERS by A. A. Prihozhy, A. M. Zhdanouski

“…The qualification of a group of programmers is evaluated taking into account the requirements for a particular project, which integrates three components: the average qualification of programmers included in the group; the qualification of the group with respect to the best representatives for each of the technologies; threshold values of the levels of programmer qualification and group qualification for each of the technologies, as well as threshold values of the integrated qualification, reflecting the specifics of the given project. …”
Get full text

Reducing the dynamic range of infrared images based on block-priority equalization and compression of histograms by S. I. Rudikov, V. Yu. Tsviatkou, A. P. Shkadarevich

“…When interpolating pixel values, high-priority blocks use local alignment values, and low-priority blocks use global alignment values. …”
Get full text

A Study on Spatial and Temporal Changes and Synergies/Trade-Offs of the Production-Living-Ecological Functions in Mountainous Areas Based on the Niche Width Model by Yaling Li, Ruoying Song, Ping Ren

“…Based on this, spatial clustering patterns were further analyzed using Maxwell’s triangle and K-means algorithms to delineate functional zones. Key findings include: (1) Production function (PF) and living function (LF) exhibit a “core-periphery” spatial pattern (high-value clusters in the south, low-value contiguous areas in the north), while ecological function (EF) displays a “high-low-high” ring-shaped pattern (high values in the northwest and southeast, declining in the central region due to development pressure); (2) synergy and trade-off relationships coexist in the study area. …”
Get full text

Machine learning-based prognostic prediction for acute ischemic stroke using whole-brain and infarct multi-PLD ASL radiomics by Zhenyu Wang, Chaojun Jiang, Xianxian Zhang, Tianchi Mu, Qingqing Li, Shu Wang, Congsong Dong, Yuan Shen, Zhenyu Dai, Fei Chen

“…Methods Radiomics features were extracted from the whole-brain and infarct regions based on multi-PLD ASL CBF images of 110 AIS patients. Five machine learning algorithms were used to construct radiomics models (whole-brain, infarct, and combined), clinical models, and comprehensive models integrating radiomics and clinical data. …”
Get full text

Predicting neoadjuvant chemotherapy response in locally advanced gastric cancer using a machine learning model combining radiomics and clinical biomarkers by Tong Ling, Zhichao Zuo, Liucheng Wu, Jie Ma, Tingan Wang, Mingwei Huang

“…A variety of ML algorithms were applied to integrate the rad score with clinical biomarkers, resulting in the construction of a hybrid model. …”
Get full text

Bayesian Q-learning in multi-objective reward model for homophobic and transphobic text classification in low-resource languages: A hypothesis testing framework in multi-objective... by Vivek Suresh Raj, Ruba Priyadharshini, Saranya Rajiakodi, Bharathi Raja Chakravarthi

“…The policy outputs action logits, integrated with Q-value estimates sampled via Thompson Sampling from a Gaussian posterior. …”
Get full text