Aayush Mishra

The growing trends in fluoride pollution of drinking water pose significant health risks to the general population these include dental and skeletal fluorosis, alongside cardiovascular and nervous system disorders. Past methods for fluoride detection have largely been labor-intensive, time-consuming, and incapable of being monitored in real time. Current development in this area has now led to the evolution of IoT-integrated smart sensors that aid real-time, accurate, and efficient monitoring of fluoride levels in water. This review covers their features in extensive detail, regarding integration in optical sensing mechanisms of nanomaterials and applying sensor fusion techniques for improving detection accuracy and sensitivity. This paper presents an analysis of some aspects, such as sensor calibration methods, wireless data transmission techniques, and power efficiency. Standards like water quality index, wireless sensor networks, and water quality monitoring systems have also been discussed in-depth, security protocols and encryption methods also discussed to safeguard data integrity and reliability. In addressing existing technical challenges, this review aims to provide in water quality monitoring with motives to produce more advanced and useful smart sensing solutions. Their integration into Internet of Things(IoT) platforms renders these sensors as highly promising for real-time monitoring and data analytics, thereby piloting in a vast change in the water quality management scenario. This study conveys concepts and ideas about the way forward for smart sensing in water quality monitoring.

To effectively manage the wastage of perishable fruits, it is crucial to accurately predict their freshness or shelf life using non-invasive methods that rely on visual data. In this regard, deep learning techniques can offer a viable solution. However, obtaining fine-grained fruit freshness labels from experts is costly, leading to a scarcity of data. Closed proprietary Vision Language Models (VLMs), such as Gemini, have demonstrated strong performance in fruit freshness detection task in both zero-shot and few-shot settings. Nonetheless, food retail organizations are unable to utilize these proprietary models due to concerns related to data privacy, while existing open-source VLMs yield sub-optimal performance for the task. Fine-tuning these open-source models with limited data fails to achieve the performance levels of proprietary models. In this work, we introduce a Model-Agnostic Ordinal Meta-Learning (MAOML) algorithm, designed to train smaller VLMs. This approach utilizes meta-learning to address data sparsity and leverages label ordinality, thereby achieving state-of-the-art performance in the fruit freshness classification task under both zero-shot and few-shot settings. Our method achieves an industry-standard accuracy of 92.71%, averaged across all fruits. Keywords: Fruit Quality Prediction, Vision Language Models, Meta Learning, Ordinal Regression

We present a composite machine learning framework to estimate posterior probability distributions of bulge-to-total light ratio, half-light radius, and flux for active galactic nucleus (AGN) host galaxies within z < 1.4 and m < 23 in the Hyper Supreme-Cam (HSC) Wide survey. We divide the data into five redshift bins: low (0 < z < 0.25), mid (0.25 < z < 0.5), high (0.5 < z < 0.9), extra (0.9 < z < 1.1), and extreme (1.1 < z < 1.4), and train our models independently in each bin. We use PSFGAN to decompose the AGN point-source light from its host galaxy, and invoke the Galaxy Morphology Posterior Estimation Network (GaMPEN) to estimate morphological parameters of the recovered host galaxy. We first trained our models on simulated data, and then fine-tuned our algorithm via transfer learning using labeled real data. To create training labels for transfer learning, we used GALFIT to fit ∼20,000 real HSC galaxies in each redshift bin. We comprehensively examined that the predicted values from our final models agree well with the GALFIT values for the vast majority of cases. Our PSFGAN + GaMPEN framework runs at least three orders of magnitude faster than traditional light-profile fitting methods, and can be easily retrained for other morphological parameters or on other data sets with diverse ranges of resolutions, seeing conditions, and signal-to-noise ratios, making it an ideal tool for analyzing AGN host galaxies from large surveys coming soon from the Rubin-LSST, Euclid, and Roman telescopes.

Structural health monitoring (SHM) is a modern and innovative method used to assess the integrity, safety, and performance of structures without causing any damage. The need for SHM is particularly critical for infrastructure, such as dams, where timely detection of damage allows for the implementation of remedial safety measures. Structural integrity can be compromised by events, such as earthquakes, floods, and other disasters, which create significant disturbances in man-made constructions. The longevity of a structure is influenced by construction methods and the quality of materials used. Researchers have developed various techniques to evaluate the lifespan of constructed structures and propose safety measures. Recent advancements in technology, including the Internet of Things (IoT), artificial intelligence (AI), and wireless integrated sensor devices, have revolutionized the field of SHM. IoT-based wireless sensors monitor different structural parameters and transmit data to cloud-based storage systems in real-time. AI techniques, particularly machine learning, analyze this data to predict potential issues and provide actionable insights to user agencies, researchers, and administrative bodies, such as Dam Monitoring Centers (DMCs). The ability of these technologies to monitor dam behavior in real-time has garnered significant attention. This study reviews current research on real-time SHM of dams using AI and IoT cloud-based sensor techniques, aiming to support researchers and practitioners in advancing SHM methodologies.

We use the Galaxy Morphology Posterior Estimation Network (GaMPEN) to estimate morphological parameters and associated uncertainties for ∼8 million galaxies in the Hyper Suprime-Cam Wide survey with z ≤ 0.75 and m ≤ 23. GaMPEN is a machine-learning framework that estimates Bayesian posteriors for a galaxy’s bulge-to-total light ratio (L _B /L _T ), effective radius (R _e ), and flux (F). By first training on simulations of galaxies and then applying transfer learning using real data, we trained GaMPEN with L _B /L _T that can be used to convert between these two parameters. The catalog presented here represents a significant improvement in size (∼10×), depth (∼4 mag), and uncertainty quantification over previous state-of-the-art bulge+disk decomposition catalogs. With this work, we also release GaMPEN’s source code and trained models, which can be adapted to other data sets.