5 hasil untuk "Prosenjit Roy"
Menampilkan 1–5 · 0,53 detik · RSS
-
Artikel Jurnal
A Study of Serum C-Reactive Protein and Interleukin-6 in Patients with Type 2 Diabetes Mellitus and Their Correlation with Diabetic Nephropathy
Background: Type 2 diabetes mellitus (T2DM) represents the predominant form of diabetes globally and is a major contributor to chronic kidney disease (CKD) through diabetic nephropathy (DN). DN is associated with both hyperglycemia-induced microvascular damage and low-grade systemic inflammation…
-
Artikel Jurnal
Evaluating Pretrained Deep Learning Models for Image Classification Against Individual and Ensemble Adversarial Attacks
The robustness of Deep Neural Networks (DNNs) against adversarial attacks is an important topic in the area of deep learning. To fully investigate the robustness of DNNs, this study examines four frequently used white box adversarial attack techniques, namely, the Fast Gradient Sign Method (FGSM)…
-
Artikel Jurnal Teks lengkap
Optimizing Circular Supply Chains for Live-Streaming E-Commerce: Managing Reverse Logistics and Environmental Impacts Using Life Cycle Assessment
Background: Live-streaming e-commerce has emerged as a significant retail channel, especially in the apparel industry, characterized by high impulse-driven purchase rates and elevated product returns. Reverse logistics processes associated with these returns generate considerable environmental…
-
Artikel Jurnal Teks lengkap
Echocardiographic Evidence of Left Ventricular Dysfunction in COPD: Relationship with Disease Severity
Background and Objectives: Chronic obstructive pulmonary disease (COPD) significantly impacts morbidity and mortality, often due to cardiovascular comorbidities that are frequently overlooked. This study examines the prevalence of left ventricular dysfunction in COPD patients and its association…
-
Artikel Jurnal Teks lengkap
U-SAMNet: Uncertainty-Aware Self-Attention Multi-Task Network for Pore Detection in Additive Manufacturing
Reliable pore detection in in situ monitoring is essential for quality control in additive manufacturing, particularly in safety-critical applications. However, existing automated approaches often struggle with low-quality images, computational inefficiency, and the lack of reliable uncertainty…