KMITL Innovation Expo 2025 Logo

HORAI: Immersive Tarot-based Divination Platform Powered by LLMs

HORAI: Immersive Tarot-based Divination Platform Powered by LLMs

Abstract

Our project seek to create an Al-powered tarot card reader that bridges the gap between traditional fortune-telling and modern technology. By leveraging a combination of 3D modeling, natural language processing, text-to-speech (TTS), and speech-to-text (STT) systems, the service will deliver an interactive and culturally sensitive experience in Thai and English. Users will input their queries through voice, which will be processed via STT, and receive engaging Al-generated tarot readings through TTS. Additionally, a 3D animated avatar will mimic a real-life fortune teller, adding a visual dimension to the experience. Hosted on a user-friendly website, this platform will redefine fortune-telling by blending tradition with innovation, making it both accessible and engaging for modern users.

Objective

ในปัจจุบัน AI Chatbots และ LLM ถูกนำมาใช้ในหลายธุรกิจ รวมถึงการให้คำแนะนำและการพยากรณ์ อย่างไรก็ตาม ในตลาดการพยากรณ์ออนไลน์ยังไม่มีระบบ AI ที่สามารถให้บริการพยากรณ์ไพ่ทาโรต์ได้อย่างมีประสิทธิภาพและให้ประสบการณ์ที่ใกล้เคียงกับนักพยากรณ์จริง จากการสังเกตพฤติกรรมของผู้ใช้สื่อโซเชียลในไทย พบว่ามีผู้ใช้จำนวนมากที่นิยมใช้ ChatGPT และ AI อื่น ๆ เพื่อขอคำพยากรณ์เกี่ยวกับอนาคตของตนเอง ซึ่งบ่งบอกถึงความสนใจในบริการลักษณะนี้ อย่างไรก็ตาม ยังไม่มีแพลตฟอร์มที่พัฒนาเพื่อจุดประสงค์ในการดูดวงโดยเฉพาะ ดังนั้น โครงการนี้จึงมีเป้าหมายในการพัฒนา AI ที่สามารถโต้ตอบกับผู้ใช้ได้อย่างสมจริง โดยใช้โมเดลภาษาและเทคโนโลยีที่ทันสมัย

Other Innovations

Development of Carbon Nanofiber Composite Materials for Supercapacitors in Energy Storage

วิทยาลัยการจัดการนวัตกรรมและอุตสาหกรรม

Development of Carbon Nanofiber Composite Materials for Supercapacitors in Energy Storage

This study presents the development of carbon-based multiphase metal oxide nanocomposites (CNF@MOx; M = Ag, Mn, Bi, Fe) incorporating silver, manganese, bismuth, and iron nanoparticles within polyacrylonitrile (PAN)-derived carbon nanofibers. These nanocomposites were fabricated via the electrospinning technique followed by annealing in an argon atmosphere. The resulting nanofibers exhibited a uniform structure, with diameters ranging from 559 to 830 nm and embedded nanoparticles of 9-21 nm. Structural characterization confirmed the presence of various oxidation states of metal oxides, which play a crucial role in charge storage mechanisms. Electrochemical performance testing demonstrated that CNF@Ag/Mn/Bi/Fe-20 achieved the highest specific capacitance of 156 F g⁻¹ at a scan rate of 2 mV s⁻¹ and exhibited excellent cycling stability, retaining over 96% of its capacitance after 1400 charge-discharge cycles. The synergistic combination of electric double-layer capacitance and redox-based charge storage enhances the performance of these nanofibers as promising electrode materials for supercapacitor applications.

Read more
Flow of Humane

คณะสถาปัตยกรรม ศิลปะและการออกแบบ

Flow of Humane

This piece represents the collection of all human elements, applied to design for maximum efficiency, following the principles of Modern designers who embraced the famous phrase "Form follows Function." Every line and structure of the design is carefully considered for user comfort and practical use, while reflecting the idea that the user's experience is central to the design process. The beauty emerges from the harmony between function and form, not only meeting functional needs but also enhancing the aesthetic of Modernist design in a complete and meaningful way.

Read more
Detection of Durian Leaf Diseases Using Image Analysis and Artificial Intelligence

คณะเทคโนโลยีการเกษตร

Detection of Durian Leaf Diseases Using Image Analysis and Artificial Intelligence

Durian is a crucial economic crop of Thailand and one of the most exported agricultural products in the world. However, producing high-quality durian requires maintaining the health of durian trees, ensuring they remain strong and disease-free to optimize productivity and minimize potential damage to both the tree and its fruit. Among the various diseases affecting durian, foliar diseases are among the most common and rapidly spreading, directly impacting tree growth and fruit quality. Therefore, monitoring and controlling leaf diseases is essential for preserving durian quality. This study aims to apply image analysis technology combined with artificial intelligence (AI) to classify diseases in durian leaves, enabling farmers to diagnose diseases independently without relying on experts. The classification includes three categories: healthy leaves (H), leaves infected with anthracnose (A), and leaves affected by algal spot (S). To develop the classification model, convolutional neural network (CNN) algorithms—ResNet-50, GoogleNet, and AlexNet—were employed. Experimental results indicate that the classification accuracy of ResNet-50, GoogleNet, and AlexNet is 93.57%, 93.95%, and 68.69%, respectively.

Read more