At Readime, every question we ask begins and ends with people. We believe rigorous inquiry, when grounded in empathy and curiosity, can illuminate paths toward a more equitable and thoughtful world.
Our research agenda is set by questions, not funding pressures. We operate without institutional bias so findings remain honest and actionable.
We publish our work openly and welcome scrutiny. Knowledge only grows through sharing, critique, and collaboration across disciplines.
The hardest problems resist single-discipline thinking. Our researchers bring together sociology, cognitive science, technology, and ethics.
Human experience is not uniform. Our research is rooted in diverse geographic, cultural, and socioeconomic contexts, not just dominant narratives.
Agritech
About 65 percent of Nepal's population depends on agriculture, with pigeon pea ('Rahar') being a key legume crop for traditional food products. Frequent disease outbreaks, coupled with limited access to agronomists and challenging terrain, force small-scale farmers to rely on manual visual inspection, often resulting in delayed or inaccurate disease identification and excessive pesticide use.
Read paper →Technology & Society
Driver fatigue is a prominent source of traffic accidents and requires the need for accurate real-time detection algorithms. In this paper, the authors propose the design of "DrowsyDriveNet," a hybrid deep learning architecture that is capable of classifying the driver alertness level into four stages: "Alert," "Slight," "Moderate," and "Severe."
Read paper →Health & Behavior
Women's empowerment is a well-known and intriguing subject. Every business and institution should place a priority on the health and privacy of women because they are the foundation of society. The women must be given access to facilities that will improve sanitation and menstrual hygiene for this reason. In order to make women's pads conveniently accessible at their workplaces or other public locations,
Read paper →AI & ML
The growing complexity of modern power networks requires intelligent fault classification techniques capable of handling multiple fault conditions with high accuracy. Classifying faults in transmission lines with higher accuracy is very important to provide reliability to the power system along with a shorter fault clearance time.
Read paper →We welcome questions from readers, researchers, journalists, and institutions. Whether you want to discuss our findings, propose a joint research topic, or simply get in touch — drop us a line.
Let's Collaborate →