A good and feasible centrifuge is needed in the world of health, therefore a digital tachometer is needed to calibrate a centrifuge. Digital tachometer is a measuring instrument used to measure the rotation speed of a motor. This tachometer will be tested to function by being compared to using Digital Laser Photo Tachometer. This tachometer will display the number of rotations per minute of a motor according to the speed setting on the centrifuge using the output of this E18-D80NK sensor which will later be processed by the Arduino Nano. As for this feature charger and data storage mode, so that user can save the data of measurement results on SD Card, and beside that user can also be a way of charging when after usage or before usage. At testing the tool used point settings 1000, 2000, 3000, 4000, 5000, and 12000 RPM. Based on the measurement results of centrifuge using tachometer module and comparison tachometer have average percentage of error varying at each setting point. The smallest error 0.8% at the setting Point 3000 RPM, while the largest error 4.9% at the setting point 1000 RPM. The Tacometer error value on this Centrifuge measurement is still within the tolerance limit of ± 10%. ABSTRAKCentrifuge yang baik dan laik pakai sangat dibutuhkan dalam dunia kesehatan, oleh karena itu dibutuhkan tachometer digital untuk mengkalibrasi centrifuge. Tachometer digital merupakan alat ukur yang digunakan untuk mengukur kecepatan perputaran suatu motor. Tachometer ini akan diuji fungsi dengan dibandingankan menggunakan Digital Laser Photo Tachometer. Tachometer ini akan menampilkan jumlah rotasi per menit suatu motor sesuai dengan setting kecepatan pada centrifuge menggunakan output dari sensor E18-D80NK ini yang nantinya akan diproses oleh arduino nano. Adapun ini memiliki fitur charger dan mode penyimpanan data, sehingga user dapat menyimpan data hasil pengukuran pada SD Card, dan disamping itu user juga dapat melaukan pengisian daya apabila setelah pemakaian maupun sebelum pemakaian. Pada pengujian alat digunakan titik setting 1000 , 2000 Berdasarkan hasil pengukuran dari centrifuge yang menggunakan tachometer modul dan tachometer pembanding memiliki rata -rata presentase error yang berbedabeda pada setiap titik setting. Error terkecil 0,8% pada titik setting 3000 RPM, sedangkan error terbesar 4,9% pada titik setting 1000 RPM. Nilai error Tacometer pada pengukuran Centrifuge ini masih di dalam batas toleransi yaitu ±10%.Kata Kunci: Arduino Nano, Sensor E18-D80NK, LCD, RPM, Tachometer.

No abstract

It is critical to develop a method for detecting cracks in historic building concrete structures. This is due to the fact that it is a method of preserving historic building and protecting visitors from the collapse of a historic structure. The purpose of this research is to determine the best method for identifying cracks in the concrete surface of old buildings by using cracked images of old buildings. The various surface textures, crack irregularities, and background complexity that distinguish crack detection from other forms of image detection research present challenges in crack detection of old buildings. This study presents a framework for detecting concrete cracks in old buildings in Semarang's old town using a modified Convolutional Neural Network with a combination of several convolutional layers. This study employs ten convolutional layers (Deca Convolutional Layer Neural Network (DCL-NN)) to provide mapping features for images of concrete cracks in ancient buildings at preservation area. This study also compares commonly used machine learning models such as KNeighbors (n neighbors=3), Random Forest, Support Vector Machine (SVM), ExtraTrees (n estimators=10), and other CNN-pretained models such as VGG19, Xception, and MobileNet. Four performance indicators are used to validate each model's performance: accuracy, recall, precision, F1-score, Matthews Correlation Coefficient (MCC), and Cohen Kappa (CK). This study's data set is comprised of primary data obtained from cracked and normal images of several buildings in Semarang's old town. The accuracy of this study using DCL-NN is 98.87%, recall is 99.40%, precision is 98.33%, F1 is 98.86%, MCC is 97.74%, and CK is 98.86% for crack class. From this study, it was found that the ten convolution layers have higher classification performance compared to other comparison models such as machine learning and other CNN models and are more effective in detecting cracks in concrete structures.

Glioblastoma is listed as a malignant brain tumor. Due to its heterogeneous composition in one area of the tumor, the area of tumor is difficult to segment from healthy tissue. On the other side,  the segmentation of brain tumor MRI imaging is also erroneous and takes time because of the large MRI image data. An automated segmentation approach based on fully convolutional architecture was developed to overcome the problem. One of fully convolutional network that used is U-Net framework. U-Net architecture is evaluated base on the number of epochs and drop-out values to achieve the most suitable architecture for the automatic segmentation of glioblastoma brain tumors. Through experimental findings, the most fitting architectural model is mU-Net architecture with an epoch number of 90 and a drop out layer value of 0.5. The results of the segmentation performance are shown by a dice value of 0.909 which is greater than that of the previous research.

No abstract