Microscopic Detection and Quantification of Microplastic Particles in Environmental Water Samples by Derek Lam (11944213)

“…Image processing algorithms, implemented in Python using adaptive thresholding techniques, were applied to segment particles from the background. …”

End-to-end example-based sim-to-real RL policy transfer based on neural stylisation with application to robotic cutting by Jamie Hathaway (10285367)

“…</p><h3>policy/</h3><p dir="ltr">This folder contains pickled trajectories, in the form of a Python list.</p><p dir="ltr">The list's elements are TrajWithRew dataclass objects from the Imitation Python library (https://imitation.readthedocs.io/en/latest/)</p><p dir="ltr">TrajWithRew contains 4 main fields</p><ul><li> obs - the (unnormalised) observations, in the form of a [WINDOW_LENGTH * NUM_CHANNELS] array</li><li> acts - the actions in the form of a [WINDOW_LENGTH - 1 * NUM_ACTS] array</li><li> infos - the info values at each timestep, as a [WINDOW_LENGTH - 1] array of dicts</li><li> terminals - boolean indicating if that trajectory segment is a terminal segment</li><li> rews - the rewards as a [WINDOW_LENGTH - 1] array</li></ul><p dir="ltr">Each TrajWithRew represents not a full episodic trajectory, as is usually the case with Imitiation - rather they represent segments of a full episodic trajectory, of length WINDOW_LENGTH. …”

Metaverse Gait Authentication Dataset (MGAD) by sandeep ravikanti (20704127)

“…How to Use the Dataset</b></h2><ul><li>Load the dataset in Python using Pandas:</li></ul><p><br></p><ul><li>Use the features for machine learning models in biometric authentication.…”

<b>Challenges and Strategies for the Management of Quality-Oriented Education Bases in Universities under Informatization Background</b> by Yang Yanxi (21571568)

“…Final codes, together with basic demographic attributes supplied by the institutions’ HR offices, were exported to Excel and cleaned in Python 3.10 using pandas 2.2.1 and numpy 1.26. …”

Modules organization over different course editions. by Gabriele Pozzati (21094166)

“…<p>Course editions starting from 2019 are represented side-by-side, while different working days and weeks of the same course edition are displayed vertically. …”

Image 1_An explainable analysis of depression status and influencing factors among nursing students.png by Yingying Li (50341)

“…Data cleaning was performed in Excel, and statistical analyses were conducted using SPSS Statistics version 27.0 and Python 3.9.</p>Results<p>The incidence of depression among nursing students is 28.60%. …”

Chromosomal rearrangements among clade A pathogenic <i>Cryptococcus</i> species. by Marco A. Coelho (7353659)

“…<p>(A) Synteny comparisons between <i>C. neoformans</i> strain 125.91 (reference) and representative strains from 7 other clade A species (8 species total). …”

Machine Learning-Driven Discovery and Database of Cyanobacteria Bioactive Compounds: A Resource for Therapeutics and Bioremediation by Renato Soares (20348202)

“…The biochemical descriptors were then used to determine the most promising protein targets for human therapeutic approaches and environmental bioremediation using the best machine learning (ML) model. The creation of our database, coupled with the integration of computational docking protocols, represents an innovative approach to understanding the potential of cyanobacteria bioactive compounds. …”

Datasets from the Programmatic Analysis of Fuel Treatments: from the landscape to the national level Joint Fire Science Project (14-5-01-1) by Douglas B. Rideout (19657906)

“…Included for each study site are individual rasters representing the fire affected resources for that study site. …”

Summary of Tourism Dataset. by Jing Zhang (23775)

“…The proposed TourVaRNN integrates variational autoencoders to capture latent variables representing visitor preferences and spending habits, while recurrent neural networks model complex temporal dependencies in tourism data. …”

Segment-wise Spending Analysis. by Jing Zhang (23775)

“…The proposed TourVaRNN integrates variational autoencoders to capture latent variables representing visitor preferences and spending habits, while recurrent neural networks model complex temporal dependencies in tourism data. …”

Hyperparameter Parameter Setting. by Jing Zhang (23775)

“…The proposed TourVaRNN integrates variational autoencoders to capture latent variables representing visitor preferences and spending habits, while recurrent neural networks model complex temporal dependencies in tourism data. …”

Marketing Campaign Analysis. by Jing Zhang (23775)

“…The proposed TourVaRNN integrates variational autoencoders to capture latent variables representing visitor preferences and spending habits, while recurrent neural networks model complex temporal dependencies in tourism data. …”

Visitor Segmentation Validation Accuracy. by Jing Zhang (23775)

“…The proposed TourVaRNN integrates variational autoencoders to capture latent variables representing visitor preferences and spending habits, while recurrent neural networks model complex temporal dependencies in tourism data. …”

Integration of VAE and RNN Architecture. by Jing Zhang (23775)

“…The proposed TourVaRNN integrates variational autoencoders to capture latent variables representing visitor preferences and spending habits, while recurrent neural networks model complex temporal dependencies in tourism data. …”

Core data by Baoqiang Chen (21099509)

“…</p><p><br></p><p dir="ltr">For the 5′ UTR library, we developed a Python script to extract sequences and Unique Molecular Identifiers (UMIs) from the FASTQ files. …”

Indirect Reciprocity and the Evolution of Prejudicial Groups by Gualtiero Colombo (19078925)

“…This is conducted through an agent based model over a population of agents that interact through a `donation game' in which resources are donated to third parties at a cost without receiving a direct benefit. …”

Automatically Generated Chemical KG by Connor Oryan (19851477)

“…The files are in JSON format and are intended to be loaded within Python as dictionaries. The <i>Full_SSKG.json </i>file is approximately 11GB in size when extracted. …”

Nucleotide analogue tolerant synthetic RdRp mutant construct for Surveillance and Therapeutic Resistance Monitoring in SARS-CoV-2 by Tahir Bhatti (20961974)

“…From that massive dataset all publicly available sequences were extracted then a representative consensus genome was built.</p><p dir="ltr">A local custom AI model was trained on 10 Million historical genomes and data for Q1 of 2025 simulating remdesivir pressure to predict which mutations are likely to emerge under therapeutic selection.…”