This paper introduces a tool for classifying software issue reports using machine learning techniques. The tool implements traditional machine learning techniques, AutoML, and more advanced large-language models to support automated categorization of issue reports. The tool has been evaluated on datasets from multiple open-source and closed-source software projects. The tool has also been evaluated in real industrial settings. The evaluation results and the feedback from practitioners indicate that the tool has the potential to assist practitioners in the early classification of issue reports. • A tool that implements leading ML techniques for issue report classification. • Provides evaluation results from several open-source and closed-source projects. • Provides results and insights from real-industrial validations. • A reusable package.

In this paper, we present FastKpp , a C++ implementation of an exact accelerated k -means + + algorithm using two geometry-aware filters: one based on the Triangle Inequality (TIE) and another based on point norms. Both provably preserve the original D 2 sampling distribution while avoiding redundant distance computations. The library provides a header-only API, a command-line tool, and a fully reproducible capsule. Experiments show substantial reductions in distance computations and speedups that increase with k (with typical median between 2 and 8). Furthermore, FastKpp outperforms other state-of-the-art exact acceleration techniques. Results are reproducible via the public GitHub repository and Code Ocean capsule. • Exact k-means++ acceleration with TIE and norm filters preserving D 2 sampling. • Large speedups that increase with k by reducing the number of distance evaluations. • The TIE version excels in low dimensions, while the TIE+Norm version leads in high-dimensional data with high norm variance. • Header-only C++ library with drop-in API and CLI. • Tight per-point lower bounds computed during seeding for later k-means accelerations.

STFATool is a professional signal-processing application implemented in Python. It integrates several state-of-the-art sparse time–frequency analysis algorithms, including Synchroextracting Transform, Transient-Extracting Transform, Multisynchrosqueezing Transform, and Time-Reassigned Multisynchrosqueezing Transform. It provides a user-friendly interface, users can import signals for detailed time–frequency feature visualization and processing, enabling efficient extraction of critical signal characteristics. • STFATool is a Python-based, professional-grade signal-processing suite that brings together cutting-edge sparse time–frequency methods, including Synchroextracting Transform, Transient-Extracting Transform, Multisynchrosqueezing Transform, and Time-Reassigned Multisynchrosqueezing Transform. With its intuitive GUI, users can simply load their data to perform in-depth time–frequency visualization and analysis, streamlining the extraction of vital signal features.

This article presents FLECO Studio 2.0, which enhances cybersecurity situational awareness training through realistic scenarios. Organizations face increasing cyber threats but struggle with a global shortage of cybersecurity professionals. To address this, they must upskill existing personnel across all functional areas. Situational awareness is crucial for identifying, understanding, and responding to threats dynamically. FLECO Studio 2.0 includes new features designed to improve this skill, enabling multidisciplinary teams to assess risks, anticipate attacks, and coordinate effective responses. These enhancements strengthen an organization’s cybersecurity posture, fostering a unified and proactive defense against evolving threats. • FLECO Studio 2.0 enhances cyber situational awareness through realistic, scenario-based training. • The tool improves cross-functional collaboration and holistic cybersecurity understanding. • Experimental results show up to 54% improvement in trainees’ situational awareness compared to traditional methods.

This paper presents Eiffel-Store , an open-source tool for real-time traceability in Continuous Integration (CI) pipelines. Unlike traditional batch visualization tools, Eiffel-Store dynamically visualizes live Eiffel events from CI tools (e.g., Jenkins) using MongoDB and Meteor.js. It supports incremental updates, enabling users to trace faults back to specific commits across the pipeline. Events can be streamed from RabbitMQ or added manually, offering flexibility for diverse workflows. By connecting code changes to final product faults, Eiffel-Store improves transparency, debugging, and quality assurance. The tool has been tested with industry partners and is available publicly to promote adoption and further development.

Bibliometric analyses often depend on extracting metadata from large scientific databases, a process that is still largely manual, repetitive, and error prone. This paper presents PubMedMetaTool, an open-source Python-based solution that automates the retrieval and transformation of bibliographic metadata from PubMed, using either article titles or Digital Object Identifiers as input. The tool implements a modular pipeline that extracts metadata using NCBI’s Entrez programming utilities and transforms it into formats compatible with tools such as Bibliometrix, VOSviewer, and pyBibX. Designed to be transparent and configurable, the tool improves bibliometric workflow efficiency, accuracy, and interoperability workflows. • Developed a Python-based tool for automated metadata extraction from PubMed, minimizing manual effort. • Ensures metadata compatibility with popular bibliometric tools, including Bibliometrix, VOSviewer, and pyBibX. • Demonstrated significant time reduction in bibliometric data collection and processing. • Automation of bibliometric search using database PubMed. • Guarantees seamless integration with Bibliometrix, VOSviewer, and pyBibX for advanced bibliometric analysis. • Open-Source Solution: Provides an open-source, configurable platform to democratize access to bibliometric analysis tools.

Ensuring secure data transmission has become crucial in modern digital communication, especially with rising risks of interception and manipulation. Steganography is vital in protecting sensitive information by embedding it within digital images without compromising their visual quality. This paper introduces IrsyadStego, an open-source using a Difference Expansion method with customized pixel difference to improve payload capacity and image fidelity. Experimental results show high PSNR and SSIM values, with a 100 dB PSNR between the cover image and the image recovered from extraction—demonstrating full reversibility. IrsyadStego supports further research, contributing to robust, secure, and efficient steganographic techniques in digital security. • A steganographic software that leverages a DE-based approach to have high payload capacity while preserving image quality. • A method optimizes embedding efficiency without significant distortion utilizing customized pixel difference thresholds. • It achieves high PSNR and SSIM values, ensuring the reversibility of the steganographic process for recovered cover images. • It is a flexible and accessible platform for further exploration and enhancement of image steganography techniques. • It is more robust against evolving threats while maintaining high imperceptibility and data integrity.

This paper investigates and introduce an AI-driven CNN-KNN Fusion Software (ACKFS) for symptom-based early detection and classification of plant diseases. The approach integrates Convolutional Neural Networks and K-Nearest Neighbor’s to enhance classification accuracy. This research follows a structured four-phase process: pre-processing, segmentation, feature extraction, and classification. Using two datasets, ACKFS significantly improved accuracy to 94.56% and 87.52%, respectively. These results surpass the performance reported by previous researcher’s, demonstrating the effectiveness of CNN-KNN fusion for real-time plant disease detection on smart devices, contributing to precision agriculture and enhanced plant health monitoring. • Early Disease Detection to Mitigate Crop Loss: Reduces delays in mango disease detection, preventing 30% crop losses from Anthracnose. • Reduce Economic Impact: Enables rapid, automated detection for timely intervention, protecting yields and farmer livelihoods. • State-of-the-Art Accuracy: Achieves 94.56% accuracy on Mango Leaf-BD and 87.52% on Leaf Repository, surpassing MobileNet R-CNN (70.53%). • Cross-Dataset Generalizability: Performs robustly across diverse datasets, adapting to different disease complexities in mango and multi-species leaves. • Low Prediction Error: Minimizes training (0.1112), validation (0.1023), and testing (0.1059) losses, ensuring reliable real-world application. • Reduces economic impact: Enables rapid, automated detection for timely interventions, protecting yields and farmer livelihoods. • State-of-the-Art Accuracy: • Achieves 94.56% testing accuracy on Mango Leaf-BD and 87.52% on Leaf Repository datasets, outperforming prior benchmarks (e.g., MobileNet R-CNN: 70.53%). • Cross-Dataset Generalizability: • Maintains robust performance across diverse datasets (mango-specific vs. multi-species leaves), demonstrating adaptability to varying disease complexities. • Low Prediction Error: • Minimized divergence between training (0.1112), validation (0.1023), and testing (0.1059) losses, ensuring reliable deployment in real-world farming.

The ArSLR-ML is a real-time interactive application that uses multi-class Support Vector Machines (SVM) machine learning applied in the classification procedure and MediaPipe in the feature extraction procedure to recognize static Arabic sign language gestures, focusing on numbers and letters and translating them into text and Arabic audio output. The ArSLR-ML was built within the PyCharm IDE using Python with a graphical user interface (GUI), thereby allowing for effective recognition of gestures. The application utilizes the laptop camera and GUI to capture hand gestures to create dataset for machine learning models and implement them in real time. • Develops an interactive laptop application for real-time Arabic Sign Language recognition using ML and a GUI. • Utilizes Support Vector Machines for classification and MediaPipe for feature extraction, enhancing efficiency and accuracy. • Provides Arabic voice output alongside text-based recognition, improving accessibility for deaf individuals. • Facilitates fast and accurate hand gesture data capture using a standard camera, ensuring user-friendly operation. • Designed as a scalable platform for advancements in sign language technology.