Classification of the Condition of Cancer Patients Receiving Home Health Care with Machine Learning Methods by Mürsel Kahveci

“…The ANN classifier achieved 88.6% accuracy for all cancer types.The use of machine learning algorithms may provide a more sensitive and objective way to evaluate patients' response to treatment. The machine learning model allows determining the type of cancer using the feature space based on VAS, Karnofsky performance scale, ECOG, Katz and Bartel scores. …”
Get full text

LSD-Det: A Lightweight Detector for Small Ship Targets in SAR Images by Zhen Wang, Bin Qin, Shang Gao

“…However, ship targets in SAR images are often small, have blurred edges, and suffer from strong background interference, making it difficult for traditional detection algorithms to balance accuracy and real-time performance. To address these challenges, this paper proposes LSD-Det, a lightweight SAR ship detection model improved from YOLOv8n. …”
Get full text

Shape-Aware Adversarial Learning for Scribble-Supervised Medical Image Segmentation with a MaskMix Siamese Network: A Case Study of Cardiac MRI Segmentation by Chen Li, Zhong Zheng, Di Wu

“…A case study on public cardiac MRI datasets demonstrated that the proposed MaskMixAdv outperformed the state-of-the-art methods and narrowed the performance gap between scribble-supervised and mask-supervised segmentation. …”
Get full text

Advancing smart communities with a deep learning framework for sustainable resource management. by Yongyan Zhao

“…., cleaning and normalization and feature engineering steps, before model training and testing phases. …”
Get full text

How do family firms balance economic and non-economic goals: from symbiosis to competition by Wei Zhang, Bingde Wu, Ling Chen, Jian-an Zhu, Shihui Chen

“…Our research addresses this question by exploring the symbiotic or competitive relationship between non-economic goals and economic goals in Chinese family firms, and the moderating effect of firm size and firm age.MethodsBased on 2877 firm-year observations of Chinese listed family firms from year 2009 to 2019, this paper examines the relationship between non-economic goals (measured by family management) and economic goals (measured by firm performance). A panel data fixed-effects regression model was employed for the primary analysis. …”
Get full text

Estimating canopy height in tropical forests: Integrating airborne LiDAR and multi-spectral optical data with machine learning by Brianna J. Pickstone, Hugh A. Graham, Andrew M. Cunliffe

“…We suggest using RF due to its ease in model building, computational time, and efficient feature selection for predicting canopy height. …”
Get full text

A Multimodal Deep Learning Approach for Legal English Learning in Intelligent Educational Systems by Yanlin Chen, Chenjia Huang, Shumiao Gao, Yifan Lyu, Xinyuan Chen, Shen Liu, Dat Bao, Chunli Lv

“…The experimental results fully demonstrate that the proposed cross-modal legal English question-answering system not only exhibits significant advantages in multimodal feature alignment and deep reasoning modeling but also shows substantial potential in enhancing learners’ comprehensive capabilities and learning experiences.…”
Get full text

BCDCNN: breast cancer deep convolutional neural network for breast cancer detection using MRI images by D. E. Martina Jaincy, V. Pattabiraman

“…It improves the overall performance by dynamically emphasizing samples with ambiguous predictions, enabling the model to focus more on diagnostically challenging cases and enhancing its discriminative capability. …”
Get full text

Assessing the transferability of BERT to patient safety: classifying multiple types of incident reports by Ying Wang, Farah Magrabi

“…Transferability was evaluated using three datasets: a balanced dataset (type/severity: n_benchmark=286/116); a real-world imbalanced dataset (n_original=444/4837, rare types/severity<=1%); and an independent hospital-level reporting system (n_independent=6000/5950, imbalanced). Model performance was evaluated by F-score, precision and recall, then compared with convolutional neural networks (CNNs) using BERT embeddings and local embeddings from incident reports.Results Fine-tuned BERT outperformed small CNNs trained with BERT embedding and static word embeddings developed from scratch. …”
Get full text

Thrombolytic Therapy in Treatment in Patients with Pulmonary Embolism not High-risk: SIRENA Registry Data by N. A. Cherepanova, I. S. Mullova, T. V. Pavlova, A. D. Erlikh, O. L. Barbarash, S. A. Berns, E. A. Schmidt, D. V. Duplyakov

“…The other 46 (45.5%) non-high-risk patients had no clear indication of the reasons for TLT in their medical history. To study the features of management of patients with not high-risk PE who received TLT (group 1), a selection of pairs of patients from the "SIRENA” registry, comparable in gender and age, in a ratio of 1:1 of patients with not high-risk PE who did not perform TLT (group 2). …”
Get full text

Investigation of the Influence of Atmospheric Scattering on Photolysis Rates Using the Cloud-J Module by Anastasia Imanova, Eugene Rozanov, Sergei Smyshlyaev, Vladimir Zubov, Tatiana Egorova

“…The results show that the calculations performed using Cloud-J v.8.0 are in agreement with the data obtained using the high-resolution LibRadtran model. …”
Get full text

Risk factors of incident in-hospital pulmonary embolism and its outcomes: autopsy study data by O. Ya. Vasiltseva, I. N. Vorozhtsova, A. V. Krestinin, E. V. Stefanova, R. S. Karpov

“…The impact of RFs and treatment on the PTE outcome was assessed in a statistical model. Results. The presence of two or three RFs was associated with a higher risk of fatal in-hospital PTE. …”
Get full text

Machine Learning for Coronary Plaque Characterization: A Multimodal Review of OCT, IVUS, and CCTA by Alessandro Pinna, Alberto Boi, Lorenzo Mannelli, Antonella Balestrieri, Roberto Sanfilippo, Jasjit Suri, Luca Saba

“…Recent ML models achieve expert-level lumen and plaque segmentation, reliably detecting features linked to vulnerability such as a lipid-rich necrotic core, calcification, positive remodelling, and a napkin-ring sign. …”
Get full text

Machine Learning-Based 3D Soil Layer Reconstruction in Foundation Pit Engineering by Chenxi Zhang, Nan Li, Xiuping Dong, Bin Liu, Meilian Liu

“…Finally, 3D meshing is performed on the soil layer generated from real boreholes, and soil model rendering is achieved through a voxel clustering algorithm. …”
Get full text

Ultrashort wave satellite channel classification and recognition algorithm based on mirror filled spectrum and LA-ResNet50 by Shang WU, Lei SHEN, Lijun WANG, Ruxu ZHANG, Xin HU

“…In response to the classification and identification problems of 5 kHz channels, 25 kHz channels, broadband interference channels, narrowband interference channels, and single tone interference channels in the ultrashort wave frequency band, a classification and identification method for ultrashort wave channels based on mirror filled spectrum and LA-ResNet50 (LBP attention ResNet50) was proposed.The problem of difficulty in distinguishing between satellite channels and background noise under low signal-to-noise ratio, as well as the identification of signal channels and interference channels with similar characteristics, has been effectively solved.Firstly, the proposed method performs mirror symmetry on the ultrashort wave spectrum and fills it in, while blackening the edges of the spectrum to construct a mirror-filled spectrum, which improves the discrimination of different types of channel spectra.Then, channel attention was introduced into ResNet50 to focus the attention of the network model on the channel.Finally, a loss function based on cross entropy and local binary pattern (LBP) was proposed to improve the extraction effect of subtle texture features on signal channels and interference channels images.The proposed method based on mirror-filled spectrum and LA-ResNet50 has shown an improvement of 19.8%, 8.2%, 1.8%, and 0.8% in classification accuracy for ultrashort wave channels compared to the traditional method utilizing fast Fourier transform (FFT) spectrum thresholding, the YOLOv5s target detection and classification method based on mirror-filled spectrum, the Attention-ResNet50 method with attention mechanism based on mirror-filled spectrum, and the Transformer network method under a signal-to-noise ratio (SNR) of 10 dB.…”
Get full text

Evaluation of Rural Visual Landscape Quality Based on Multi-Source Affective Computing by Xinyu Zhao, Lin Lin, Xiao Guo, Zhisheng Wang, Ruixuan Li

“…Binary, ternary, and five-category emotion classification models were then developed. Results indicate that the binary and ternary models achieve superior accuracy in emotional valence and arousal, whereas the five-category model performs least effectively. …”
Get full text

Dynamic parameters of lowering loads at gradual tree felling by Tomáš Kotek, Jindřich Neruda

“…The work methodology consists of three operations: (i) the calculation of the coefficient of shear friction for the combination of 4 ropes and 5 lowering devices - altogether 20 combinations; (ii) the mathematical modelling of the maximum forces acting on the lowering loads of known weight; and (iii) the verification of mathematical modelling using a series of measured experiments of lowering loads of known weight. …”
Get full text

Prediction of post-irradiation swelling rate of 316L stainless steel based on Variational Autoencoders and interpretable machine learning by Chengcheng Liu, Hang Su

“…By comparing various machine learning models, it was found that the Extreme Trees Regression (ETR) model performed best on the test set, achieving an R2 of 0.79 and a Root Mean Square Error (RMSE) of 1.65 %. …”
Get full text

An Automatic Measurement Method of Test Beam Response Based on Spliced Images by Dong Liang, Jing Liu, Lida Wang, Chenjing Liu, Jia Liu

“…The cracks’ information is acquired by the dual network model. The simplified AKAZE feature detection algorithm and the modified RANSAC are used to track the natural features of the structures. …”
Get full text

Fish Disease Detection Using Image Based Machine Learning Technique in Aquaculture by Md Shoaib Ahmed, Tanjim Taharat Aurpa, Md. Abul Kalam Azad

“…The results have bought a judgment of our applied SVM performs notably with 91.42 and 94.12 percent of accuracy, respectively, with and without augmentation.…”
Get full text