KMITL Innovation Expo 2025 Logo

The Development of Hand Gesture Recognition for Controlling Electronic Devices

Abstract

This research will begin with a review of literature and related studies to examine existing technologies and methods for hand gesture recognition and their applications in controlling electronic devices such as drones, robots, and gaming systems. Subsequently, a hand gesture recognition system will be designed and developed using machine learning and computer vision techniques, with a focus on creating an algorithm that operates quickly and accurately, making it suitable for real-time control. The developed system will be tested and refined using various simulated scenarios to evaluate its efficiency and accuracy in diverse environments. Additionally, a user-friendly interface will be developed to ensure accessibility for all user groups. The research will also incorporate qualitative studies to gather feedback from both novice users and experts, which will contribute to further system improvements, ensuring it effectively meets user needs. Ultimately, the findings of this research will lead to the development of a functional prototype for gesture-based control, which can be applied in industries and entertainment. This will contribute to advancements in innovation and new technologies in the future.

Objective

ในยุคปัจจุบัน เทคโนโลยีโดรน หุ่นยนต์ และเกมดิจิทัลได้เข้ามามีบทบาทสำคัญในชีวิตประจำวันและอุตสาหกรรมต่าง ๆ มากขึ้นอย่างต่อเนื่อง การควบคุมอุปกรณ์เหล่านี้ส่วนใหญ่ยังคงพึ่งพารีโมทคอนโทรล จอยสติก หรืออุปกรณ์ควบคุมเฉพาะทาง ซึ่งอาจมีข้อจำกัดในด้านความยืดหยุ่น ความเป็นธรรมชาติในการใช้งาน และการเข้าถึงสำหรับผู้ใช้บางกลุ่ม เช่น ผู้พิการ หรือผู้สูงอายุ นอกจากนี้ ในสถานการณ์ที่ต้องการความคล่องตัวสูง เช่น การควบคุมโดรนในพื้นที่จำกัด หรือการเล่นเกมที่ต้องการการตอบสนองที่รวดเร็ว การใช้อุปกรณ์ควบคุมแบบดั้งเดิมอาจเป็นข้อจำกัดในการเพิ่มประสิทธิภาพการทำงานหรือประสบการณ์การเล่นเกม การพัฒนาเทคโนโลยีการรู้จำท่าทางมือ (Hand Gesture Recognition) จึงเป็นแนวทางที่มีศักยภาพอย่างสูงในการแก้ไขปัญหาดังกล่าว โดยเทคโนโลยีนี้สามารถช่วยให้ผู้ใช้ควบคุมโดรน หุ่นยนต์ หรือเล่นเกม ฯลฯ เป็นต้น ได้อย่างเป็นธรรมชาติมากขึ้น เพียงแค่ใช้ท่าทางมือที่กำหนดไว้ ซึ่งนอกจากจะเพิ่มความสะดวกสบายและความคล่องตัวในการควบคุมแล้ว ยังช่วยเพิ่มความสามารถในการเข้าถึงเทคโนโลยีสำหรับผู้ใช้ที่มีข้อจำกัดทางร่างกาย อีกทั้งยังเปิดโอกาสให้มีการพัฒนารูปแบบการควบคุมและการเล่นเกมแบบใหม่ ๆ ที่ไม่เคยมีมาก่อน

Other Innovations

Intelligent Web System for Employee Recruitment with AI

คณะวิทยาศาสตร์

Intelligent Web System for Employee Recruitment with AI

Recruitment is a crucial process that enables organizations to select candidates whose qualifications match the requirements of a given position. However, this process often faces challenges related to data management, delays, and human bias. This research aims to design and develop an intelligent web application for employee recruitment using artificial intelligence (AI) technology to evaluate and score candidates' suitability for job positions. The system leverages data analysis techniques on resumes and a qualification-matching process based on predefined criteria. Developed using Agile principles, the system employs Natural Language Processing (NLP) to analyze resumes, assess candidates’ qualifications, skills, and experience, and utilizes Machine Learning to predict and rank suitability. The system consolidates data from multiple sources into a unified database to reduce redundancy and input errors. Additionally, it presents insights through a dashboard, enabling HR teams to make more effective hiring decisions.

Read more
Bacteriocinogenomic analysis and anti-pathogenic activity of potential Lactococcus lactis TKP1-5 isolated from the feces of Anas platyrhynchos

คณะวิทยาศาสตร์

Bacteriocinogenomic analysis and anti-pathogenic activity of potential Lactococcus lactis TKP1-5 isolated from the feces of Anas platyrhynchos

Bacteriocins are microbial peptides that demonstrate potency against pathogens. This study evaluated the inhibitory effects on pathogens and characterized the bacteriogenomic profile of strain TKP1-5, isolated from the feces of Anas platyrhynchos domesticus. Strain TKP1-5 was characterized using phenotypic traits, 16S rRNA sequencing, and Whole-Genome Sequencing (WGS). It exhibited growth in the presence of 2-6% NaCl, temperatures of 25-45°C, and pH levels ranging from 3 to 9. Based on ANIb, ANIm, and dDDH values, strain TKP1-5 was identified as Lactococcus lactis. Whole genome analysis revealed that strain TKP1-5 harbors the Nisin Z peptide gene cluster with a bit-score of 114.775. The antimicrobial spectrum of bacteriocin TKP1-5 showed inhibitory effects against pathogenic bacteria including Pediococcus pentosaceus JCM5885, Listeria monocytogenes ATCC 19115, Enterococcus faecalis JCM 5803T, Salmonella Typhimurium ATCC 13311ᵀ, Aeromonas hydrophila B1 AhB1, Streptococcus agalactiae 1611 and Streptococcus cowan I. Genomic analysis confirmed L. lactis TKP1-5 as a non-human pathogen without antibiotic resistance genes or plasmids. Furthermore, L. lactis TKP1-5 contains potential genes associated with various probiotic properties and health benefits. This suggests that L. lactis TKP1-5, with its antibacterial activity and probiotic potential, could be a promising candidate for further research and application in the food industry.

Read more
Web Application for Shrimp Feed Transportation Route Optimization: A Case Study of an Animal Feed Store

คณะวิทยาศาสตร์

Web Application for Shrimp Feed Transportation Route Optimization: A Case Study of an Animal Feed Store

Efficient logistics management requires the development of advanced tools to streamline delivery operations. This study aims to optimize vehicle routes for an animal feed store and develop a web-based application for route planning. The research compares two optimization methods: the Branch and Bound Method and Clustering with the Branch and Bound Method. These methods are evaluated against the store’s existing delivery route by analyzing differences in average travel distance across three dependent groups using Repeated Measures ANOVA. The findings reveal a statistically significant difference in average daily travel distances among the three methods at a 0.05 significance level. The Branch and Bound Method yields the shortest average daily travel distance. Additionally, pairwise comparisons of total daily travel distances using the Paired t-test confirm that the Branch and Bound Method produces the most efficient route with statistical significance at 0.05 level. Implementing this method can reduce total travel distance by 957.51, representing a 30.88% reduction, which translates into fuel cost savings of 2,579.45 THB per month. Based on these results, the Branch and Bound Method was selected for implementation in a web-based application. The application features an intuitive user interface, product inventory management, and optimized daily delivery route recommendations for the case study store. Following development, the web application was deployed and tested in real-world operations. The results demonstrate that it effectively provides map-based route recommendations, ensuring ease of use and accessibility on standard mobile devices.

Read more