In raising crickets for meat consumption, the growth rate and growth period of crickets are important data used to identify the number of crickets per breeding area at each age. Therefore, the researcher has an idea to create a system for monitoring the growth rate of crickets in a closed system using an infrared camera combined with computer image processing to study the growth and identify the growth period of crickets at each age in order to obtain knowledge that can be disseminated to farmers to improve the breeding process for maximum efficiency.
ปัจจุบันจิ้งหรีดถือได้ว่าเป็นสัตว์เศรษฐกิจชนิดใหม่ของประเทศไทยซึ่งทางภาครัฐโดยเฉพาะกรมปศุสัตว์ได้เริ่มมีการส่งเสริมให้ภาคการเกษตรได้เพาะเลี้ยงจิ้งหรีดเพื่อการบริโภคสำหรับการส่งออก และเป็นการตอบรับกับเทรนด์อุตสาหกรรมอาหารใหม่ (Novel food) ตามแนวทางขององค์การอาหาร และเกษตรแห่งสหประชาชาติ (FAO : Food and Agriculture Organization) ซึ่งคาดการณ์เอาไว้ว่าจำนวนประชากรโลกจะเพิ่มขึ้นอย่างต่อเนื่องทำให้ความต้องการแหล่งโปรตีนมีมากขึ้นตามไปด้วย คณะผู้วิจัยจึงมีแนวความคิดที่จะหาสร้างระบบเลี้ยงจิ้งหรีดที่มีประสิทธิภาพ
คณะวิศวกรรมศาสตร์
The Thai Sign Language Generation System aims to create a comprehensive 3D modeling and animation platform that translates Thai sentences into dynamic and accurate representations of Thai Sign Language (TSL) gestures. This project enhances communication for the Thai deaf community by leveraging a landmark-based approach using a Vector Quantized Variational Autoencoder (VQVAE) and a Large Language Model (LLM) for sign language generation. The system first trains a VQVAE encoder using landmark data extracted from sign videos, allowing it to learn compact latent representations of TSL gestures. These encoded representations are then used to generate additional landmark-based sign sequences, effectively expanding the training dataset using the BigSign ThaiPBS dataset. Once the dataset is augmented, an LLM is trained to output accurate landmark sequences from Thai text inputs, which are then used to animate a 3D model in Blender, ensuring fluid and natural TSL gestures. The project is implemented using Python, incorporating MediaPipe for landmark extraction, OpenCV for real-time image processing, and Blender’s Python API for 3D animation. By integrating AI, VQVAE-based encoding, and LLM-driven landmark generation, this system aspires to bridge the communication gap between written Thai text and expressive TSL gestures, providing the Thai deaf community with an interactive, real-time sign language animation platform.
คณะเทคโนโลยีสารสนเทศ
This report is part of applying the knowledge gained from studying machine learning models and methods for developing a predictive model to identify customers likely to cancel their credit card services with a bank. The project was carried out during an internship at a financial institution, where the creator developed a model to predict customers likely to churn from their credit card services using real customer data through the organization's system. The focus was on building a model that can accurately predict customer churn by selecting features that are appropriate for the prediction model and the unique characteristics of the credit card industry data to ensure the highest possible accuracy and efficiency. This report also covers the integration of the model into the development of a website, which allows related departments to conveniently use the prediction model. Users can upload data for prediction and receive model results instantly. In addition, a dashboard has been created to present insights from the model's predictions, such as identifying high-risk customers likely to cancel services, as well as other important analytical information for strategic decision-making. This will help support more efficient marketing planning and customer retention efforts within the organization.
คณะวิศวกรรมศาสตร์
This project aims to develop a conceptual prototype of a weapon aiming system that simulates an anti-aircraft gun. Utilizing an optical camera, the system detects moving objects and calculates their trajectories in real time. The results are then used to control a motorized laser pointer with two degrees of freedom (DoF) of rotation, enabling it to aim at the predicted position of the target. Our system is built on the Raspberry Pi platform, employing machine vision software. The object motion tracking functionality was developed using the OpenCV library, based on color detection algorithms. Experimental results indicate that the system successfully detects the movement of a tennis ball at a rate of 30 frames per second (fps). The current phase involves designing and integratively testing the mechanical system for precise laser pointer position control. This project exemplifies the integration of knowledge in electronics (computer programming) and mechanical engineering (motor control).