CSV

The increasing deployment of renewable-based microgrids requires reliable short-term load forecasting to support energy management under demand uncertainty. This paper proposes a hybrid forecasting framework for day-ahead load prediction in isolated solar microgrids. The approach integrates Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Gated Recurrent Units (GRU), and Particle Swarm Optimization (PSO). CEEMDAN decomposes nonlinear load signals into intrinsic mode components to reduce noise and prevent modal aliasing.

Intelligent Reflecting Surface (IRSs) are widely recognized as a promising solution for improving network capacity, spectral efficiency, and coverage in multi-user, multi-cell communication systems. This technology is particularly advantageous for users located in blockage regions and at cell edges, enabling more reliable data transmission and enhanced connectivity.

1.EUA Datasets

All the data is in Australia region.

• edge-servers folder: contains datasets of edge server locations.
• users folder: contains datasets of user location.
   

2.telecom_dataset

This dataset presents teacher perception data collected to support research on predicting secondary school students’ real-time online learning comprehension in Sri Lanka. The study focuses exclusively on educators’ observations and professional judgments regarding factors that influence student understanding during online learning sessions, including response accuracy, response time, facial expressions, engagement behaviors, and the feasibility of AI-driven predictive systems.

The HIT dataset integrates TCM-related information from multiple sources, including: (1) ingredient-target and herb-ingredient associations from the HIT2.0 database, and (2) symptom-target and herb-symptom associations from the SymMap database. The TCMIO dataset has a similar composition to HIT, except that its ingredient-target and herb-ingredient associations come from the TCMIO database.

Data from a Brazilian bank, collected over a period of 90 days. The data was de-identified and anonymized by removing information that could identify a customer. During this period, 23,247,143 deposit records were recorded, located in 3,076 bank branches and 8,780 different ATMs. Also, 1000 synthetic records were added simulating fraudster behavior.

Mobile app user reviews contain valuable feedback about software functionality, quality, and security. Existing approaches for analyzing security-related reviews often rely on traditional feature extraction methods, limiting their ability to detect nuanced security concerns. This study aims to develop an automated framework for classifying mobile app user reviews into security-related and non-security-related categories.

This repository introduces PPMC (Perturbed Principal Components Mechanism), a tunable anonymization method based on Principal Component Analysis (PCA), designed to support privacy-preserving analytics in Internet of Medical Things (IoMT) environments. The proposed approach employs controlled eigenvector perturbation to achieve a principled trade-off between data utility and privacy protection, without injecting noise directly into the raw feature space.

We release the dataset used in our study of inbound conveyor congestion in a food logistics warehouse with multiple conveyor lanes feeding storage via stacker cranes. Each record captures a timestamp, an SKU identifier, the conveyor lane, and the availability of the stacker cranes, enabling replay of the arrival stream and reconstruction of congestion proxies and simulator inputs.

This dataset is collected to support infrastructure-level phishing and malicious hosting detection from encrypted network traffic without decryption. It provides a large-scale collection of network and TLS infrastructure features derived from TLS 1.2 and TLS 1.3 traffic, enabling the detection of phishing URLs directly at the transport layer. The dataset contains 126,063 network sessions and URLs, each represented by 197 numeric attributes describing TLS handshake behavior, protocol versions, server implementation fingerprints, timing statistics, and HTTP/HTTPS error patterns.