FAMHE-Net: Multi-Scale Feature Augmentation and Mixture of Heterogeneous Experts for Oriented Object Detection by Yixin Chen, Weilai Jiang, Yaonan Wang

“…Furthermore, a detector head that lacks a meticulous design may face limitations in fully understanding and accurately predicting based on the enriched feature representations. …”
Get full text

Mapping global distributions, environmental controls, and uncertainties of apparent topsoil and subsoil organic carbon turnover times by L. Zhang, L. Zhang, L. Yang, T. W. Crowther, C. M. Zohner, S. Doetterl, G. B. M. Heuvelink, G. B. M. Heuvelink, A. M. J.-C. Wadoux, A.-X. Zhu, Y. Pu, F. Shen, H. Ma, Y. Zou, C. Zhou, C. Zhou

“…The prediction uncertainties of the <span class="inline-formula"><i>τ</i></span> maps were quantified for better user applications. …”
Get full text

A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment by Polina Pilyugina, Timofey Chernikov, Maria Smirnova, Alexey Zaytsev, Alexander Bulkin, Evgeny Burnaev, Ilya S. Belalov, Nazar Sotiriadi, Albert Efimov, Yury Maximov, Oleg Anisimov

“…Purely data-driven models also face limitations due to the spatial and temporal sparsity of observational data. …”
Get full text

Multi-Scale Self-Attention-Based Convolutional-Neural-Network Post-Filtering for AV1 Codec: Towards Enhanced Visual Quality and Overall Coding Performance by Woowoen Gwun, Kiho Choi, Gwang Hoon Park

“…The objective is to address two persistent artifact issues observed in our previous MTSA model: visible seams at patch boundaries and grid-like distortions from upsampling. …”
Get full text

Geospatial SHAP interpretability for urban road collapse susceptibility assessment: a case study in Hangzhou, China by Bofan Yu, Hui Li, Huaixue Xing, Weiya Ge, Liling Zhou, Jinrui Zhang, Meijun Xu, Cheng Yu

“…In addition to interpreting the contributions of evaluation factors through traditional SHAP summaries and bar plots, we displayed the SHAP values for each evaluation factor using map visualizations, and discussed the model’s sensitivity to different values. To validate the alignment between model predictions and physical collapse mechanisms, our study selected typical collapse cases, interpreted these cases combining map visualizations, SHAP force plots at collapse points, and the physical mechanisms of collapse. …”
Get full text

Development and validation of a deep learning system for detection of small bowel pathologies in capsule endoscopy: a pilot study in a Singapore institution by Bochao Jiang, Michael Dorosan, Justin Wen Hao Leong, Marcus Eng Hock Ong, Sean Shao Wei Lam, Tiing Leong Ang

“…They serve as a decision support system, partially automating the diagnosis process by providing probability predictions for abnormalities. Methods: We demonstrated the use of deep learning models in CE image analysis, specifically by piloting a bowel preparation model (BPM) and an abnormality detection model (ADM) to determine frame-level view quality and the presence of abnormal findings, respectively. …”
Get full text

Accurate and Efficient Fluid Flow Regime Classification Using Localized Texture Descriptors and Machine Learning by Manimaran Renganathan, Palani Thanaraj Krishnan, C. Christopher Columbus, T. Sunil Kumar

“…This paper presents an image-based framework for classifying fluid flow regimes into low and high-speed states by utilizing spatially localized texture features combined with machine learning techniques. …”
Get full text

APPLICATION OF THE GENERALIZED SPACE TIME AUTOREGRESSIVE (GSTAR) METHOD IN FORECASTING THE CONSUMER PRICE INDEX IN FIVE CITIES OF SOUTH SULAWESI PROVINCE by Ahmad Zaki, Lutfiah Shafruddin, Irwan Thaha

“…CPI forecasting is one way to predict future inflation values. This study aims to develop the best GSTAR model for forecasting CPI data for five cities in South Sulawesi, a topic that has not been extensively covered in previous research. …”
Get full text

A Difference-In-Differences Study of the Effects of a New Abandoned Building Remediation Strategy on Safety. by Michelle C Kondo, Danya Keene, Bernadette C Hohl, John M MacDonald, Charles C Branas

“…Building remediations were also significantly associated with reductions in violent gun crimes in one city section (p < 0.01). …”
Get full text

The radial spreading of volcanic umbrella clouds deduced from satellite measurements by Fred Prata, Andrew T. Prata, Rebecca Tanner, Roy G. Grainger, Michael Borgas, Thomas J. Aubry

“…This model also predicts the observed radial velocities. …”
Get full text

On the Brink: Mapping the Last Strongholds of the Critically Endangered Flapper Skate (Dipturus intermedius) by Sophie L. Loca, Patrick C. Collins, Amy Garbett, Ryan McGeady, James Thorburn, Chris McGonigle

“…Location The NE Atlantic shelf region. A Bayesian spatial binomial GAMM was used to model the distribution of flapper skate across the NE Atlantic shelf. …”
Get full text

Kernel density change: A new bitemporal lidar metric for directly mapping wildland fire fuel consumption by Michael J. Campbell, Andrew T. Hudak, T. Ryan McCarley, Benjamin C. Bright, Philip E. Dennison

“…In this study, we compared MFLC to a new modeling approach that directly predicts consumption from a suite of bitemporal point cloud structural change metrics. …”
Get full text

An Ensemble of Convolutional Neural Networks for Sound Event Detection by Abdinabi Mukhamadiyev, Ilyos Khujayarov, Dilorom Nabieva, Jinsoo Cho

“…An ensemble approach combines predictions from three models, achieving F1 scores of 71.5% for segment-based metrics and 46% for event-based metrics. …”
Get full text

ENHANCING WEIGHTED FUZZY TIME SERIES FORECASTING THROUGH PARTICLE SWARM OPTIMIZATION by Armando Jacquis Federal Zamelina, Suci Astutik, Rahma Fitriani, Adji Achmad Rinaldo Fernandes, Lucius Ramifidisoa

“…Furthermore, the length of the interval and the extent to which previous values (Order length) are utilized in predicting the subsequent value are pivotal factors in WFTS modelization and its forecasting accuracy. …”
Get full text

Novel transfer learning based bone fracture detection using radiographic images by Aneeza Alam, Ahmad Sami Al-Shamayleh, Nisrean Thalji, Ali Raza, Edgar Anibal Morales Barajas, Ernesto Bautista Thompson, Isabel de la Torre Diez, Imran Ashraf

“…In this study, we propose a novel transfer learning-based approach called MobLG-Net for feature engineering purposes. Initially, the spatial features are extracted from bone X-ray images using a transfer model, MobileNet, and then input into a tree-based light gradient boosting machine (LGBM) model for the generation of class probability features. …”
Get full text

Observation and Numerical Simulation of Cross-Mountain Airflow at the Hong Kong International Airport from Range Height Indicator Scans of Radar and LIDAR by Ying Wa Chan, Kai Wai Lo, Ping Cheung, Pak Wai Chan, Kai Kwong Lai

“…In order to study the feasibility of predicting such disturbed airflow, a mesoscale meteorological model and a computational fluid dynamics model with high spatial resolution are used in this paper. …”
Get full text

Deep Learning-Based MRI Brain Tumor Segmentation With EfficientNet-Enhanced UNet by Pradeep Kumar Tiwary, Prashant Johri, Alok Katiyar, Mayur Kumar Chhipa

“…Precisely delineating brain tumor areas from multimodal MRI scans is crucial for clinical diagnosis and predicting patient outcomes. However, challenges arise from similar intensity patterns, varying tumor shapes, and indistinct boundaries, which complicate brain tumor segmentation. …”
Get full text

Real-Time Fire Risk Classification Using Sensor Data and Digital-Twin-Enabled Deep Learning by In-Seop Na, Vani Rajasekar, Velliangiri Sarveshwaran

“…A key innovation is the use of digital twin technology, which dynamically integrates real-time data from IoT sensors and simulation models to predict fire disaster scenarios accurately. …”
Get full text

Estimating corn leaf chlorophyll content using airborne multispectral imagery and machine learning by Fengkai Tian, Jianfeng Zhou, Curtis J. Ransom, Noel Aloysius, Kenneth A. Sudduth

“…A UAV-based multispectral camera collected imagery at the same time as manual readings. Machine learning models developed based on image features derived from UAV images were used to predict leaf chlorophyll content. …”
Get full text

Estimates of Lake Nitrogen, Phosphorus, and Chlorophyll‐a Concentrations to Characterize Harmful Algal Bloom Risk Across the United States by Meredith M. Brehob, Michael J. Pennino, Amalia M. Handler, Jana E. Compton, Sylvia S. Lee, Robert D. Sabo

“…We then used these RF models to extrapolate lake TN and TP predictions to lakes without nutrient observations and predict chlorophyll‐a for ∼112,000 lakes across the CONUS. …”
Get full text