Render lighting dataset: A collection of rendered images with varied lighting conditions using blender render engines.

The quality of datasets is crucial in computer graphics and machine learning research and development. This paper presents the Render Lighting Dataset, featuring 63,648 rendered images of Blender's primitive shapes with various lighting conditions and engines. The images were created using Blender 4.0's Cycles and Eevee Render Engines, with careful attention to detail in texture mapping and UV unwrapping. The dataset covers six different lighting conditions, including Area Light, Spotlight, Point Light, Tri-Light, HDRI (Sunlight), and HDRI (Overcast), each adjusted using Blender's different options in the Color Management panel. With thirteen unique materials, ranging from Coastal Sand to Glossy Plastic, the dataset provides visual diversity for researchers to explore material properties under different lighting conditions using different render engines. This dataset serves as a valuable resource for researchers looking to enhance 3D rendering engines. Its diverse set of rendered images under varied lighting conditions and material properties allows researchers to benchmark and evaluate the performance of different rendering engines, develop new rendering algorithms and techniques, optimize rendering parameters, and understand rendering challenges. By enabling more realistic and efficient rendering, advancing research in lighting simulation, and facilitating the development of AI-driven rendering techniques, this dataset has the potential to shape the future of computer graphics and rendering technology.

Dataset of computer science course queries from students: Categorized and scored according to Bloom's taxonomy.

"Why don't students learn?" is a common question that educators try to address. To encourage students to become more engaged in the learning process, we believe in fostering their natural curiosity by encouraging them to ask high-level questions. To support this approach, we have compiled a dataset of questions that we hope will aid in the training of artificial intelligence (AI) models and ultimately improve the learning experience for students. To develop our dataset, we collected anonymous student questioning data in the Summer 2023 semester, utilizing our online application named "Palta Question", resulting in a dataset of 8,811 unique questions. The dataset consists of students' inquiries which underwent basic question validation using a sophisticated keyword-based approach, manual categorization by topic and course content, as well as complexity assessment using Bloom's taxonomy keywords which have also been included in the dataset. To ensure question uniqueness, we implemented the Levenshtein distance algorithm to exclude questions with a high similarity rate. This dataset provides targeted insights into student inquiry patterns and knowledge gaps within the domain of 'Introduction to Computers and Research' and 'Data Structure' courses, originating from the students at Independent University, Bangladesh (IUB). While its scope is confined to a specific student group and academic context, limiting broader applicability, it remains valuable for detailed studies in these subjects and serves as a useful foundation for AI-based educational research tools. To demonstrate the effectiveness of the dataset, we also tested it to train the AI to perform basic tasks like sorting questions according to their courses and topics. However, we envision researchers utilizing it to enhance education and aid in students' learning.