This thesis presents the application of deep learning for object classification. The selected deep learning architectures studied include Convolutional Neural Networks (CNN) and ResNet18. It covers data preparation, feature extraction, parameter tuning for accuracy comparison, and performance evaluation of the selected models. The aim is to propose an efficient model for use in devices that assist visually impaired individuals in classifying indoor objects and providing sound alerts.
ในปัจจุบันปัญหาในการเคลื่อนที่และการรับรู้สภาพแวดล้อมรอบตัวสำหรับผู้บกพร่องทางสายตายังคงเป็นอุปสรรคสำคัญในสังคมส่งผลให้เกิดความเสี่ยงต่อการเดินชนสิ่งกีดขวางและได้รับอันตราย ด้วยการนำเทคโนโลยีปัญญาประดิษฐ์เข้ามาใช้ในการเรียนรู้ การวิเคราะห์ และประมวลผลข้อมูลได้อย่างรวดเร็วเพื่อจำแนกวัตถุ ปริญญานิพนธ์นี้จึงมีจุดประสงค์เพื่อสร้างอุปกรณ์สำหรับช่วยเหลือผู้บกพร่องทางสายตาที่ใช้อัลกอริทึมการเรียนรู้เชิงลึกแบบต่างๆ เพื่อนำไปจำแนกวัตถุที่เป็นอุปสรรคสำหรับผู้บกพร่องทางสายตาในการทำกิจวัตรประจำวันภายในอาคารและส่งสัญญาณเตือนให้ผู้ใช้งานทราบให้เคลื่อนที่อย่างปลอดภัย
คณะอุตสาหกรรมอาหาร
Fish gelatin is increasingly recognized as an alternative source of gelatin, but its use has been limited due to weak gelling properties. To address these issues, the effect of furcellaran, a gelling agent, was examined at various levels (25-100% FG substitution) on the structural and physicochemical properties of FG gels. As the amount of FUR increased to 25%, the FG/FUR gel showed improved hardness and gel strength (P<0.05). Additionally, increasing FUR levels led to higher gelling and melting points, showing a dose-dependent relationship. Microstructural analysis revealed that adding FUR created a denser gel network with smaller gaps. SAXS scattering intensities also increased as FUR concentration rose. Overall, adding FUR improved the gelling properties of FG without negatively affecting springiness and syneresis, enhancing gel strength and gelling temperature.
คณะอุตสาหกรรมอาหาร
This study aims to investigate the encapsulation of anthocyanins in water-in-oil-in-water (W/O/W) emulsions and their spray-drying process to enhance anthocyanin stability against external factors such as light, temperature, and pH changes. The W/O/W emulsion was prepared using suitable surfactants and dried using a spray dryer at an inlet temperature of 120–140°C and an outlet temperature not lower than 80°C. The results showed that the composition ratios of water, oil, and surfactants significantly influenced the physical and chemical properties of the emulsion, as well as the encapsulation efficiency of anthocyanins. The spray-dried W/O/W emulsion demonstrated effective anthocyanin retention and improved long-term stability, making it applicable for food and health-related products.
คณะเทคโนโลยีสารสนเทศ
The AfterDay Horizon project is a two-player survival game developed to raise awareness of the impact of climate change. It leverages Virtual Reality (VR) technology and a website as gaming platforms. In the game, players experience a world where civilization has collapsed due to global warming, forcing the remaining population to live in bunkers to avoid environmental dangers. AfterDay Horizon focuses on collaboration between the two players to complete various missions that help the bunker’s inhabitants survive as long as possible. These missions are designed to encourage teamwork and decision-making in challenging scenarios, while also raising awareness of the potential consequences of climate change if left unresolved. Preliminary testing of the game showed that players successfully completed the missions and worked well together. However, some missions were complex and time-consuming, indicating areas for improvement to enhance the overall enjoyment and gameplay experience.