Aral, S. & Walker, D. Identifying influential and susceptible members of social networks. Science (New York, N.Y.) 337, 337–341, https://doi.org/10.1126/science.1215842 (2012).
Zhang, Z., Shi, Y., Willson, J., Du, D.-Z. & Tong, G. Viral…
Category: 7. Maths
-
A novel machine learning framework for stroke type identification in resource constrained settings with robustness to missing data
This research aimed to develop a robust machine learning model for distinguishing between ischemic (IS) and hemorrhagic (HS) strokes solely using clinical attributes, without relying on neuroimaging data. We addressed key challenges including…
Continue Reading
-
Flame monitoring and anomaly detection in steel reheating furnaces based on thermal video using a hybrid AI computer vision system
The proposed anomaly detection methodology combines machine learning with traditional computer vision techniques, creating a hybrid approach that consists of three processing phases, as illustrated in Fig. 3.
Fig. 3 High-level overview of the…
Continue Reading
-
Application of artificial intelligence chatbots in interpreting magnetic resonance imaging reports: a comparative study
Data collection
We collected MRI reports from 6,174 tumor patients who underwent scans between January 1, 2019, and December 31, 2024, at three locations. These reports, varying in length and complexity, were authored by radiologists specializing…
Continue Reading
-
A comparative analysis of parametric survival models and machine learning methods in breast cancer prognosis
Theophilus Gyedu Baidoo and Hansapani8 evaluated both survival-specific and machine learning models using performance metrics such as the concordance index (c-index), integrated brier score (IBS), and area under the curve (AUC). The cox…
Continue Reading
-
Deep active optimization for complex systems
Framework of AO
We summarize our key innovations as follows:
-
A data-driven formula that leverages the number of visits and ML from a small initial dataset to effectively manage the exploration–exploitation…
Continue Reading
-
-
Unsupervised disparity-tolerant algorithm for terahertz image stitching
Geometric distortion correction
To obtain high-quality stitched images, geometric distortion correction must be performed on the input images prior to stitching. Considering the characteristics of terahertz images—such as low resolution, limited…
Continue Reading
-
Decision algorithm with fuzzy framework and evaluation of advanced financial management policy
Pavić, Z. & Novoselac, V. Notes on TOPSIS method. Int. J. Res. Eng. Sci. 1, 5–12 (2013).
Wei, J. & Lin, X. The multiple attribute decision-making VIKOR method and its application. in…
Continue Reading
-
Optimal dosing of anti-cancer treatment under drug-induced plasticity
Model of cell proliferation and phenotypic switching
Our baseline model is a multi-type branching process model in continuous time54. In the model, cells switch stochastically between two distinct cell states, a drug-sensitive (type-0) and a…
Continue Reading
-
A deep learning framework for automated early diagnosis and classification of skin cancer lesions in dermoscopy images
This section gives an extensive description of the experimental arrangement and methodology, along with performance measure metrics under which the developed Skin-DeepNet system has been tested. Comparative analysis is also drawn to compare the…
Continue Reading