International Journal of Human Computations and Intelligence

Artificial Intelligence for Mitigating the Spread of Communicable Diseases: Elephant Health and Population in the Dooars Region of North Bengal

Rabin Kumar Mullick — 2026-03-28

The Dooars area of North Bengal is a highly sensitive border of built-up population and migratory elephant routes. This closeness forms a special avenue through which communicable diseases are passed. In this paper, the authors discuss the potentials of Artificial Intelligence (AI) to track the health of elephants, anticipate their behavior, and prevent the probability of a zoonotic spillover. After incorporating a single concept of health data with remote sensing, bioacoustics, and predictive modeling, AI provides a proactive design to the protection of the elephant conservation and health. In this paper, the author suggests a research agenda, outlines a conceptual model, explains methods of experiment and evaluation, ethical and implementation issues, and policy suggestions. It is aimed at practical, fair AI that will lower the risk of zoonotic and communicable diseases without undermining the health and maintenance of the elephants.

ANTISPOOFAI: A Deep Learning Framework for Face Spoof Detection

A Jyothi — 2026-05-03

Facial recognition technology has been applied to smartphones, mobile payment systems, intelligent access systems, and surveillance systems. But with its wide application comes the susceptibility to spoofing attacks based on printed pictures, replayed videos, or face masks. The common anti-spoofing measures based on previous studies rely on the addition of more hardware components such as infrared cameras and depth cameras. This makes the systems more expensive to implement.To overcome these issues, the proposed work introduces a software-oriented facial anti-spoofing technique using the Streamlit platform that can function properly usingnormal cameras. The proposed approach utilizes Convolutional Neural Networks to extract facial characteristics and a Siamese Network to discriminate between actual and spoofed facial images. The proposed technique is efficient, hardware agnostic, scalable, and can be used successfully as a real-time or uploaded video analysis tool.