Computational Intelligence

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.

We use the Ucidata1 dataset for this Huber problem.，the matrix A := (a1,a2,...,aS) ∈ Rn×S and the vector b :=(b1,b2,...,bS)T∈RS.

This dataset collection is curated to support research in feature selection. It contains several widely-used benchmark datasets, including COIL-20, DrivFace, GISETTE, ISOLET, ORL, TCGA, USPS, and WarpPIE10P. All datasets have been preprocessed and are provided in .mat format for convenient use in MATLAB or Python environments. This collection aims to facilitate the reproducibility of experimental results for feature selection algorithms.

Accurate plant species identification from leaf images is a fundamental task in botanical research, biodiversity conservation, agriculture, and computer vision–based decision support systems. However, variations in illumination, scale, and color consistency often degrade the performance and generalizability of image-based plant recognition models. To address these challenges, we present LeafCalibNet, a curated and annotated leaf image dataset captured using a standard color and scale calibration card to ensure visual consistency and reproducibility.

Ex-ToxiCN-MM. This dataset offers opposing interpretations, categorized as "harmful" and "non-harmful", for each meme, aiming to rigorously evaluate a model's ability to discern and comprehend ambiguous, culturally grounded content. We built a specialized knowledge base of Chinese cultural concepts and offensive vocabulary to supply models with essential prior knowledge (C-HarmKB).

Causal Structure Graph-Guided Symbolic Regression and Derivative-Based Robust Operation Optimization for Spinning Process

Sentiment Analysis (SA), also known as opinion mining is used to ascertain the sentiment or emotional undertone of a text. According to how strongly an opinion is held in favor of or against the subject matter being discussed, it can be categorized as either positive, negative, or objective. In the realm of SA, most research is mainly focused on the English language. According to the literature, the Sinhala Language gets minimal attention in the field of SA. The reason for that is that the Sinhala language is considered a morphologically rich but under-resourced language.

This repository includes the Python code for the manuscript "Design and Optimization of a Two-Tier Supply Chain Network Under Demand Uncertainty Using Genetic Algorithm and Particle Swarm Optimization". The data used in the study is embedded in the given codes as follows: Scenario1: Code&DataSet1, Scenario2: Code&DataSet2, Scenario3: Code&DataSet3

This dataset provides reference batik images intended for evaluating user-generated outline drawings in an augmented reality (AR) learning environment. The dataset consists of original batik motif images that serve as ground truth for similarity assessment between predefined outlines and outlines drawn by users. In the actual system implementation, edge representations are extracted from user drawings using image processing techniques, and their similarity to the reference images is measured using structural and edge-based comparison methods.

Mainframe platforms continue to support missioncritical
enterprise workloads; however, growing requirements
for scalability, agility, and cost efficiency are accelerating the
adoption of cloud-native architectures. Modernization of legacy
COBOL-based systems remains challenging due to monolithic
program structures, complex interdependencies, and limited
documentation. This paper proposes a Generative Artificial Intelligence
(GenAI)-driven modernization framework that systematically
transforms simple and complex COBOL, COBOL/DB2,