Context-aware content generation for virtual environments

A hand gestural interaction system for handling a desktop haptic strip for shape rendering

In the era of artificial intelligence, personality analysis is no longer limited to traditional psychometric assessments. This project, titled "AI-Powered Personality Analysis Using Gemini 2.5 Pro", explores the application of Google’s state-of-the-art generative AI model, Gemini 2.5 Pro, for interpreting human personality traits. By integrating the Big Five Personality Traits (Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism), the system accepts numerical trait inputs and generates descriptive personality summaries with natural language fluency. The core of the project leverages the Gemini API to ensure accurate and context-aware content generation. A fallback mechanism ensures reliability by switching to alternate models when necessary, making the solution robust and fault-tolerant. Additionally, user-friendly functions like take Command and say simulate a conversational interface for testing and interaction. This project demonstrates the potential of large language models in behavioural analysis, offering new avenues for applications in HR, mental health, education, and personalized digital experiences. The system can serve as a foundation for further development in AI-driven personality diagnostics and recommendation systems.

Abstract: Interactive entertainments using AI have become possible due to merging AI with games. The paper explores in-depth multi-dimensional relations among AI in gaming, including Game AI, Adaptive Gameplay, and ML in VE. The study intends to investigate how the current AI in games landscape impacts gameplay dynamics and customer experience. The paper discusses the latest approaches such as AI-driven NPCs and procedural generation of content that transforms gameplay experience. Secondly, it analyzes how machine-learning can help in designing adaptable gaming situations to satisfy different tastes and skills players. Further, this study identifies trends and envisages future breakthroughs in AI in gaming. This work aims at addressing challenges and ethical issues associated with artificial intelligence and virtual environment domain in order to understand where is future heading for gaming experience.

Terrain generation in open-world video games plays a crucial role in creating immersive and visually appealing virtual environments. This paper presents a comparative analysis of generative models for terrain generation in open-world video games, encompassing Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), Convolutional Neural Networks (CNNs), and Procedural Content Generation (PCG). The objective is to assess the effectiveness and suitability of these approaches in generating diverse and realistic terrains that enhance the user’s experience. The study begins by explaining techniques of terrain generation that are commonly used in video games. It shows the disadvantages of these methods by explaining how these techniques of terrain generation in open-world video games can result in repetitive patterns, excessive time dedication, and dull landscapes. In contrast, generative models can create diverse and realistic terrain while consuming significantly fewer resources. To compare the different methods of terrain generation, the generated terrains are evaluated using quantitative and qualitative metrics through a meta-analysis of various research papers. The results of the evaluation reveal the strengths and limitations of each approach, providing valuable information for developers and researchers in selecting the most suitable method for various terrain generation scenarios in open-world video games.