AbstrakProses pasteurisasi berfungsi untuk membunuh bakteri patogen yang dapat mengganggu kesehatan. Selain itu proses pasteurisasi juga bermanfaat untuk memperpanjang masa susu tidak rusak sehingga kualitas susu dapat dipertahankan sampai jangka waktu tertentu. Pada penelitian pengabdian masyarakat ini proses pasteurisasi susu dengan model low temperature long time (LTLT) dibangun dengan menggunakan pengendali PID dan pengendali Fuzzy. Model LTLT dipilih karena adanya kebutuhan masyarakat untuk dapat mencampur susu dengan berbagai perasa selama proses pasteurisasi berlangsung. Tujuan akhir dari penambahan perasa pada susu adalah untuk meningkatkan daya jual dari susu pasteurisasi. Berdasarkan hasil pengujian diperoleh kesimpulan bahwa sistem pengendali PID dengan nilai = 31,8; = 117,8; = 4,3 memberikan respon lebih cepat daripada sistem pengendali Fuzzy berdasarkan pengukuran indikator waktu tunda, waktu naik, waktu puncak dan waktu penetapan. Sebaliknya sistem pengendali Fuzzy menghasilkan nilai mean squared error (MSE) lebih kecil daripada sistem pengendali PID yang menunjukkan bahwa sistem pengendali Fuzzy memiliki fluktuasi kesalahan lebih kecil daripada sistem pengendali PID dalam proses pasteurisasi susu. Akan tetapi, MSE kedua pengendali berada di bawah nilai 1%, hal ini menunjukkan bahwa kedua pengendali dapat mempertahankan suhu susu sesuai dengan rentang suhu standar untuk pasteurisasi susu. Hasil pengujian laboratorium terhadap susu hasil proses pasteurisasi menunjukkan bahwa jumlah cemaran mikroba telah turun pada jumlah sesuai dengan standar SNI pada saat yang sama kualitas susu hasil proses pasteurisasi tetap terjaga. Kata kunci: pasteurisasi, low temperature long time, proportional-integral-derivative, metode fuzzy Sugeno AbstractMilk pasteurization process has benefit for reducing pathogenic bacteria that may harm people's health. At the same time, this process can be used to maintain the milk quality for long period of time. In this research, a milk pasteurization process that based on the low temperature long time (LTLT) was built utilizing the Proportional-Integral-Derivative and the Fuzzy system methods. The LTLT method was chosen in this project due to the need to blend the pasteurized milk with several type of food flavoring to increase the selling power of the pasteurized milk. Therefore, it needs longer pasteurization time. Based on the 30 trials of examination, it showed that the PID controller with values of = 31,8; = 117,8; = 4,3 was able to provide a faster system response time compared to the Fuzzy controller. The measurement was done utilizing several indicators including delay time, rise time, peak time as well as settling time. In contrast, the Fuzzy controller produced a smaller mean squared error (MSE) compared to the PID controller showing that the Fuzzy controller produced smaller error fluctuation in the milk pasteurization process. Nevertheless, the results showed that both controllers exhibited MSE lower than 1%, it indicates that both controllers could maintain milk temper...
Background: Valvular heart disease is a serious disease leading to mortality and increasing medical care cost. The aortic valve is the most common valve affected by this disease. Doctors rely on echocardiogram for diagnosing and evaluating valvular heart disease. However, the images from echocardiogram are poor in comparison to Computerized Tomography and Magnetic Resonance Imaging scan. This study proposes the development of Convolutional Neural Networks (CNN) that can function optimally during a live echocardiographic examination for detection of the aortic valve. An automated detection system in an echocardiogram will improve the accuracy of medical diagnosis and can provide further medical analysis from the resulting detection. Methods: Two detection architectures, Single Shot Multibox Detector (SSD) and Faster Regional based Convolutional Neural Network (R-CNN) with various feature extractors were trained on echocardiography images from 33 patients. Thereafter, the models were tested on 10 echocardiography videos. Results: Faster R-CNN Inception v2 had shown the highest accuracy (98.6%) followed closely by SSD Mobilenet v2. In terms of speed, SSD Mobilenet v2 resulted in a loss of 46.81% in framesper- second (fps) during real-time detection but managed to perform better than the other neural network models. Additionally, SSD Mobilenet v2 used the least amount of Graphic Processing Unit (GPU) but the Central Processing Unit (CPU) usage was relatively similar throughout all models. Conclusion: Our findings provide a foundation for implementing a convolutional detection system to echocardiography for medical purposes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.