BRAC University

Decomposing Apparent Skill in Machine-Learning Event Classification: A Multi-Catalog Study of Label Structure, Feature Coupling, and Operational Generalization

Machine-learning evaluation assumes that a held-out target represents the decision problem of interest. That assumption is difficult to satisfy when labels are constructed retrospectively from the same observational record that supplies the predictors, because a classifier can th...

Topical Finasteride 0.25% Solution for Female Pattern Hair Loss (FPHL) in Postmenopausal Women: A 52‐Week Retrospective Observational Study

BACKGROUND: Female pattern hair loss (FPHL), characterized by progressive follicular miniaturization, is the most common cause of hair thinning in women and increases in prevalence after menopause. While topical minoxidil is approved for FPHL, clinical response is variable. Oral...

Channel decoupling of the memory window in CuInP2S6-gated two-dimensional ferroelectric transistors: conditions, limits, and implications for interface processing

We ask which properties of the channel can change the memory window of a metal-ferroelectric-metal-insulator-semiconductor (MFMIS) ferroelectric transistor gated by CuInP 2 S 6 . For a window read at a constant drain current we derive a conditional expression: if the floating gat...

Community views of factors influencing participation in dengue research: Fuzzy cognitive mapping in Dhaka, Bangladesh

Background Bangladesh is among the countries most affected by dengue, the fastest spreading vector-borne disease worldwide. Engaging communities in designing and implementing solutions is a promising strategy for dengue control. However, collaborating with communities in urban se...

Developing attributes and attribute-levels for a discrete choice experiment on preference for primary healthcare providers among urban slum dwellers in Bangladesh

Abstract Background Due to rapid urbanization, in many low- and middle-income countries (LMICs), urban primary healthcare (PHC) systems are not compatible with meeting the growing need for healthcare services. However, limited research exists on what patients consider important w...

From hope to health: improving sexual and reproductive health knowledge among adolescent orphan girls through the ‘HopeBox’ intervention in Bangladesh

Background: Orphaned adolescent girls face critical barriers to accessing accurate sexual and reproductive health (SRH) knowledge, which predisposes them to risky sexual behaviours and their consequences. We aimed to evaluate the effectiveness of the 'HopeBox' intervention in imp...

Optimal placement and sizing of microgrid with electric vehicle considering demand response: Optimization strategies, future prospects and recommendations

MG design is becoming a vital aspect of power system planning because to the integration of DERs, EVs, and DR into power systems. However, it becomes challenging to optimize MG size and placement. Since there is strong interdependence between placement and size of the MG, an indi...

Barrier-Function-Constrained Residual RL-Based Current Control for LCL-Filtered NPC Inverters under Weak-Grid Operation

As renewable energy penetration continues to grow, grid-connected inverters are increasingly required to operate reliably under weak-grid conditions, where low short-circuit ratios, changing grid impedances, and rapid disturbances reveal the limitations of conventional fixed-gain...

Applications and challenges of artificial intelligence in cancer management

Artificial intelligence (AI) is increasingly transforming cancer management by enabling the analysis of complex multimodal data generated across the cancer care continuum. This structured narrative review synthesizes current applications of AI, machine learning, and deep learning...

Hybrid deep learning for smart grid SCADA intrusion detection with mutual information feature selection for smart meter data analysis

The rapid evolution of smart grid infrastructure has intensified the dependence on SCADA-based supervisory systems for real-time energy management, grid reliability monitoring, and seamless integration of renewable energy sources. However, the growing digitalization of these cybe...

The Recursive Structural Architecture: A Cross-Disciplinary Synthesis of Self-Referential Dynamics and an Emergent Analysis on Time

Work in progress.

Prevalence and factors associated with depression, anxiety, and stress symptoms among the students in Bangladesh

Abstract Background: The prevalence of mental illness is increasing among all age groups worldwide. Students are more likely to develop mental disorders due to exam pressure and other education-related affairs. This study aims to evaluate prevalence and associated factors of depr...

Wearable neural biosensors for early detection of neurodegenerative diseases

Neurodegenerative diseases, which include Alzheimer’s disease, Parkinson’s disease, and amyotrophic lateral sclerosis, represent a growing worldwide health burden that can be attributed to the ageing of the population and the lack of effective modalities of early diagnosis. Conve...

Digital device usage and psychological well-being in the post-COVID-19 era: insights from a cross-sectional survey

Abstract The COVID-19 pandemic accelerated digital technology adoption worldwide, yet limited evidence links post-pandemic multi-purpose online behavior with health outcomes and psychological well-being (PWB) in a single, integrated analysis. This study examines how digital devic...