Malaria is a major health issue worldwide, and its diagnosis requires scalable solutions that can work effectively with low-cost microscopes (LCM). Deep learning-based methods have shown success in computer-aided diagnosis from microscopic images. However, these methods need annotated images that show cells affected by malaria parasites and their life stages. Annotating images from LCM significantly increases the burden on medical experts compared to annotating images from high-cost microscopes (HCM). For this reason, a practical solution would be trained on HCM images which should generalize well on LCM images during testing. While earlier methods adopted a multi-stage learning process, they did not offer an end-to-end approach. In this work, we present an end-to-end learning framework, named CodaMal (Contrastive Domain Adpation for Malaria). In order to bridge the gap between HCM (training) and LCM (testing), we propose a domain adaptive contrastive loss. It reduces the domain shift by promoting similarity between the representations of HCM and its corresponding LCM image, without imposing an additional annotation burden. In addition, the training objective includes object detection objectives with carefully designed augmentations, ensuring the accurate detection of malaria parasites. On the publicly available large-scale M5-dataset, our proposed method shows a significant improvement of 16% over the state-of-the-art methods in terms of the mean average precision metric (mAP), provides 21x speed up during inference, and requires only half learnable parameters than the prior methods. Our code is publicly available.

In a potential breaththrough for monitoring animal wellbeing, scientists say they have translated pig grunts into emotions for the first time. Researchers trained an artificial intelligence (AI) algorithm with 7,414 recordings of pig noises, gathered throughout the life stages of 411 pigs – including slaughter. The algorithm could potentially be used to build an app for pig farmers that detects whether the animals are happy just from the noise they're making. With enough data to train the algorithm, the method could also be used to better understand the emotions of other mammals, experts say. This image shows the classification of pig calls to'valence and context', based on the algorithm. The research was led by the University of Copenhagen, the ETH Zurich and the France's National Research Institute for Agriculture, Food and Environment (INRAE).

Somebody wise once said, "The stone age didn't end because they ran out of stones." I believe it was the hunger to grow, survive, and elevate; in the constant journey to move ahead, there was a new age! In an ever-evolving world, the only constant is to learn and keep yourself upgraded. The world was quick to realize this with the global pandemic of 2020. Industries had to gear up overnight to stay ahead of uncertainties and keep the businesses running seamlessly.

Tech news these days is dominated by stories on the relentless march of artificial intelligence (AI) and how it will impact our lives in the very near future. The dream is that smart machines will rise to handle all the daily tasks, leaving us free to focus on truly valuable work. Consequently, these stories are diverging from the standard of driverless cars, drones and personal assistant bots like Siri, Alexa and Watson into the realm of personal financial assistants. The technology to facilitate these tasks is certainly not new, but like all innovation, it has become cheaper, faster, more ubiquitous and simply better. By combining AI bots with big data analysis, financial institutions can formulate powerful, yet personalized, advice and recommendations that promise to open up banking with equitable service levels for all, not just the high net worth clientele.