Some musicians are hearing impaired, some have finished their careers, but some continue to work, and it is much harder for them to be deaf than for musicians who are not. Some use hearing aids in their daily lives and use in-ear monitors in their live performances, which seem normal, but in their in-ears they only hear the metronome and drums. How can we improve the performance of in-ear monitors to near normal?
นักดนตรีบางคนที่พิการทางการได้ยิน บางคนจบอาชีพการงาน แต่บางคนยังคงทำงานต่อไปโดยที่หูหนวกนั้นยากกว่านักดนตรีปกติมาก บางคนใช้เครื่องช่วยฟังในชีวิตประจำวันและใช้เครื่องช่วยฟังแบบอินเอียร์ในการแสดง สดซึ่งดูเหมือนปกติ แต่ในอินเอียร์ของพวกเขา ได้ยินเพียงเครื่องเมตรอนอมและกลองเท่านั้น ถ้าพวกเขาสามารถใช้อินเอียร์มอนิเตอร์ในการทำงานได้แต่ยังไม่สามารถทำได้อย่างเต็มประสิทธิภำพเกิดจากอะไรและแก้ไขอย่างไร
คณะวิศวกรรมศาสตร์
This research aims to reduce the time required to resolve customer issues by focusing on improvements based on lean principles and the application of technology. The researcher conducts the case study at Nexter Digital and Solution Co., Ltd. to enhance workflows, establish new work standards, and integrate Bot technology into the processes to reduce resolution time and set new performance benchmarks for the company. The research proposes key ideas, such as identifying the root cause of problems, reducing redundant processes, implementing Lean methodologies, and applying technology to streamline operations. The research identifies two main issues to be resolved. The first involves addressing customer complaints, where the results show that the average resolution time reduces from 5 days to 3 days, representing a 38% decrease. The second issue involves solving problems for vendors, where the results show that the average response time reduces from 20 minutes to within 1 minute, a 98.5% decrease. The findings from both cases not only improve customer service but also establish a new standard for responding to and resolving internal issues more efficiently.
คณะอุตสาหกรรมอาหาร
This study aims to investigate the co-encapsulation technique of vitamin C and coenzyme Q10 within liposomes to enhance their stability and encapsulation efficiency and evaluate their antioxidant activity and release behavior under simulated gastrointestinal conditions. Liposomes were prepared using the High-Speed Homogenization Method, and their characteristics, including particle size, zeta potential, encapsulation efficiency, and antioxidant activity, were analyzed using DPPH, ABTS, and FRAP assays. The results demonstrated that co-encapsulation significantly improved the stability of vitamin C and coenzyme Q10 compared to single encapsulation. The liposomes exhibited high encapsulation efficiency and maintained strong antioxidant activity. The release profile under simulated gastrointestinal conditions also indicated a sustained and controlled release. These findings highlight the potential of the co-encapsulation technique in enhancing the efficacy of functional bioactive compounds, making it applicable to the food and nutraceutical industries.
คณะเทคโนโลยีสารสนเทศ
Facial Expression Recognition (FER) has attracted considerable attention in fields such as healthcare, customer service, and behavior analysis. However, challenges remain in developing a robust system capable of adapting to various environments and dynamic situations. In this study, the researchers introduced an Ensemble Learning approach to merge outputs from multiple models trained in specific conditions, allowing the system to retain old information while efficiently learning new data. This technique is advantageous in terms of training time and resource usage, as it reduces the need to retrain a new model entirely when faced with new conditions. Instead, new specialized models can be added to the Ensemble system with minimal resource requirements. The study explores two main approaches to Ensemble Learning: averaging outputs from dedicated models trained under specific scenarios and using Mixture of Experts (MoE), a technique that combines multiple models each specialized in different situations. Experimental results showed that Mixture of Experts (MoE) performs more effectively than the Averaging Ensemble method for emotion classification in all scenarios. The MoE system achieved an average accuracy of 84.41% on the CK+ dataset, 54.20% on Oulu-CASIA, and 61.66% on RAVDESS, surpassing the 71.64%, 44.99%, and 57.60% achieved by Averaging Ensemble in these datasets, respectively. These results demonstrate MoE’s ability to accurately select the model specialized for each specific scenario, enhancing the system’s capacity to handle more complex environments.