Machine Learning

This dataset provides a synthetic collection of breath-based volatile organic compound (VOC) measurements for the non-invasive detection of cancer using machine learning techniques. The data were generated based on reported concentration ranges of clinically relevant VOC biomarkers, including acetone, isoprene, ethanol, formaldehyde, benzene, toluene, and methane, which are known to be associated with metabolic alterations in cancer patients. In addition to VOC features, demographic variables such as age, sex, and smoking status are included to enhance classification performance.

This dataset contains experimental and model-assisted time-series data describing the solar drying kinetics of whole charal (Chirostoma spp.) under low-temperature conditions. Drying experiments were conducted using different configurations, including forced convection, natural convection, and open-air drying, representative of artisanal and small-scale fish processing practices. The dataset includes gravimetrically measured moisture data recorded at 30-minute intervals from initial conditions to equilibrium moisture content.

The dataset provided is synthetically generated to provide a binary classification for a set of IoT nodes to act as storage devices for individual blocks, with respect to edge blockchain applications, where an edge miner originally responsible for storing the blockchain may occasionally exhaust its internal space to hold additional blocks, at which point it may delegate new blocks to be stored over individual IoT nodes, also scattered at the edge, provided that the said nodes internal configurations support block storage without hampering the nodes' normal functioning.

This dataset contains 60 CSV files, comprising 30 charging test files and 30 discharging test files. In all experimental tests, four lithium-ion cells of the INR18650-30Q model were connected in series, with a nominal voltage of 4.2 V and a nominal capacity of 3000 mAh. It is important to note that all cells used in the experiments were new, presenting a state of health (SOH) of 100%.

The charging tests were performed using the constant current–constant voltage (CC–CV) method, as described below:

This dataset presents a large-scale collection of VVC (H.266)–compressed multiview dynamic volumetric video content designed for objective and subjective quality assessment in immersive media applications. The dataset is derived from the 8i Voxelized Full Bodies v2 dataset and focuses exclusively on dynamic human performance sequences captured from four viewpoints, enabling realistic evaluation of motion, view dependency, and compression artefacts in volumetric video.

Precise astronomical dates and fixed meteorological calendars do not capture the near-surface temporal variability of seasons. This study presents a purely data-driven framework to objectively quantify trends in seasons locally, validated using 45 years (1980–2024) of hourly ERA5 data for a subtropical location in India. By integrating spectral analysis for primary interval detection with unsupervised k-means clustering, the framework reveals dynamic seasonal soft boundaries.

In the upset forging process, real-time monitoring of forging stock dimensions is crucial for ensuring deformation quality. However, continuous shape deformation and harsh environmental conditions make dimensional inspection difficult. Traditional manual inspections and conventional vision systems often fail to provide reliable and continuous feedback, leading to inconsistent product quality and material waste. To address these issues, this study proposes a deformation-adaptive and lightweight YOLOv5s-based framework tailored to forging environments.

we propose an adaptive regularized inversion framework that integrates a deep-learning-based regularization network with an imaging enhancement network to mitigate resolution loss caused by electromagnetic diffusion

This dataset contains 32-channel electroencephalography (EEG) recordings acquired for multi-class imagined speech decoding using a structured and controlled experimental protocol. Data were collected from ten male participants at the Biomedical Instrumentation Laboratory, Indian Institute of Technology (IIT) Roorkee. Following standard preparation procedures including informed consent, EEG cap placement, and system calibration participants performed tasks across three linguistic categories: vowels, words, and sentences.