Hasil untuk "math.DS"

Patrizia Delpiano

Stefania Cherubini, Andrea Ciolli

Controlled studies of new oral anticoagulants (NOACs) in patients with atrial fibrillation have included above all patients at high risk of stroke, providing solid evidence on the benefits of anticoagulant therapy with such drugs in male patients with CHA2DS2-VASc score ≥2 and in women with a score of ≥3. Although estimates of stroke risk in patients with lower scores predominantly come from studies in patients not receiving NOAC, in many of these subjects anticoagulant therapy still seems able to provide clinical benefit. The current guidelines therefore recommend oral anticoagulant therapy in patients with CHA2DS2-VASc ≥1 in men and ≥2 in women. However, the use of this therapy must be carefully weighted with the expected reduction in the risk of stroke, the risk of bleeding and the patient's preferences. The paradygmatic case of a patient with CHA2DS2-VASc score 1 is reported in which acetylsalicylic acid therapy is substituted with dabigatran 150 mg / day in order to guarantee the patient maximum protection against the risk of stroke, without exposing him to an excessive risk of bleeding (Cardiology).

Jerry L. Harbour

Tri Luu, Thinh Tong, Tuong Dang et al.

This study addresses the problem of automatic object classification by leveraging the strengths of both deep learning and traditional machine learning. The main goal of this project is to develop a prototype application capable of efficiently and accurately recognizing and classifying objects in images. To tackle this, the YOLOv10 model for object detection was used, then extracted features such as bounding-box size [3] and average color. If an image is of poor quality or YOLOv10 fails to detect any object, this study applies PCA to enhance image quality. These extracted features are then used to train a Random Forest classifier from the scikit-learn library. The performance of the Random Forest classifier is optimized using GridSearchCV [2] and evaluated using StratifiedKFold [5]. The results showed that the YOLO + Random Forest combination system achieved an overall accuracy of 93%, with a higher average Precision and F1-score than using YOLOv10 alone. The combined model significantly improves the ability to classify glass and organic objects, although the number of samples of these two types is limited. The study concluded that the combination of YOLOv10 and Random Forest is an effective approach to building an automated object classification system, taking advantage of the detection speed of deep learning and the characterization-based classification capabilities of traditional machine learning, contributing to intelligent object management.

Bala Shanmukha Sowmya Javvadhi, Manas Kumar Yogi

Robert Faußner

Dhriti Banerjee, Atanu Naskar, Jayita Sengupta et al.

Okeowo Idowu Adeniyi

Arosocohi Yosua Daeli, Dewi Agushinta R, Emirul Bahar et al.

Santhosh Kumar, Sath ish, Kaar thika

Ali Inalegwu Michael, David I J, Obiabo Adikwu

Astrid Adler

Hristo Velkov

Hans-Werner Eroms

Simon B. N. Thompson

Maria Thurmair