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
คณะเทคโนโลยีการเกษตร
This study examines the effects of chemical mutagens, ethyl methane sulfonate (EMS) and colchicine in inducing mutations in Chrysanthemum spp. through tissue culture techniques. In vitro cultures of Chrysanthemum were treated with various concentrations of EMS and colchicine to assess their impact on shoot regeneration and mutation frequency. Results indicated that EMS significantly increased phenotypic variability, leading to enhanced flower color and size, while colchicine treatment effectively induced polyploidy, resulting in plants with greater flower size and overall vigor. Morphological assessments, along with genetic analyses using molecular markers, confirmed the mutations associated with these treatments. The integration of chemical mutagenesis with tissue culture presents a promising approach for developing novel Chrysanthemum varieties with improved ornamental traits.
คณะอุตสาหกรรมอาหาร
Bio-calcium powders were extracted from Asian sea bass bone by heat-treated alkaline with fat removal and bleaching supplementary method. Cereal bars (CBs) were fortified with produced bio-calcium at 3 levels: (1) increased calcium (IS-Ca; calcium ≥10% Thai RDI), (2) good source of calcium (GS-Ca; calcium ≥15% Thai RDI), and (3) high calcium (H-Ca; calcium ≥30% Thai RDI) which were consistent with the notification of the Ministry of Public Health, Thailand: No. 445; Nutrition claim issued in B.E. 2023. Moisture content, water activity, color, calcium content and FTIR analysis of bio-calcium powders were measured. Dimension, color, water activity, pH and texture of fortified CBs were determined. Produced bio-calcium could be classified as a dried food with light yellow-white color. Calcium contents in bio-calcium powder was 23.4% (w/w). Dimension, weight and color except b* and ΔE* values of fortified CBs were not different (P > 0.05) from those of the control. Fortifying of bio-calcium resulted in harder texture CBs. An increase of fortified bio-calcium amounts decreased carbohydrate and fat but increased of protein, ash and calcium in the fortified CBs. Shelf life of CBs was to be shorten by fortification of bio-calcium powder because of the increment of moisture, water activity and pH. Yield of bio-calcium production was 40.30%. Production cost of bio-calcium was approximately 7,416 Bth/kg while cost of fortified CBs increased almost 2-3 times compared to the control. Calcium contents in IS-Ca (921.12 mg/100g), GS-Ca (1,287.10 mg/100g) and H-Ca (2,639.70 mg/100g) cereal bars could be claimed as increased calcium, good source of calcium and high calcium, respectively. In conclusion, production of cereal bar fortified with Asian sea bass bone bio-calcium powder as a fortified food was possible. However, checking the remained hazardous reagents in bio-calcium powder must be carried out before using in food products and analysis of calcium bioavailability, sensory acceptance and shelf life of the developed products should be determined in further studies.
คณะวิทยาศาสตร์
Sugar production from sugarcane is a complex process that requires precise control. One of the major issues is sugar loss, which can result from various factors, particularly "burnt cane," before being sent to the mill. This affects the quality of the sugarcane and the efficiency of sugar extraction, along with the performance of the machinery and the properties of the cane, which impact the amount of sugar extracted. This study aims to analyze the factors that influence sugar loss in the sugar production process, using quantitative data from a sugar factory. Nine variables were examined, including mechanical efficiency, machine downtime per day, cane waiting time per day, sand content in cane juice, pol extraction efficiency, overall working time efficiency, cane juice purity, cane sugar content (C.C.S.), and burnt cane. The data were analyzed using correlation analysis to examine relationships between variables and regression modeling to predict sugar loss. The results showed that mechanical efficiency, cane sugar content, and the amount of sand or impurities in the cane juice were significantly correlated with sugar loss. Mechanical efficiency had a direct relationship with the amount of cane milled, which improved sugar production. On the other hand, burnt cane, or cane that was burnt before harvesting, resulted in reduced sugar extraction and impacted the quality of the sugar. Therefore, reducing sugar loss in the production process can be achieved by improving machine efficiency, reducing impurities in cane juice, and managing burnt cane, which will improve sugar production efficiency in the future.