Expression of genes found in the brains of autism, bipolar, and schizophrenia patients identified as overlapping. The overlap is a state in which the values of genes are similar. This paper aims to determine the best performance of support vector machines algorithm in classifying autism, bipolar, and schizophrenia based on the expression of genes using genome-wide association studies data. Using three support vector machine kernels, this study evaluates the performance of gaussian, laplacian, and sigmoid for genome-wide association studies datasets. The datasets were obtained from Psychiatric Genomics Consortium publications, where 660 data were taken with each disorder consisting of 220 data. This study proposes an optimal kernel for one-against-one and one-against-all multiclass support vector machine, and the performance is evaluated using accuracy. The study results show that the Gaussian kernel has the best accuracy performance compared to other support vector machines kernels in classifying genome-wide association studies data of autism, bipolar, and schizophrenia as early diagnosis.

This research aimed to design a smart dustbin. The smart dustbin was made by using ultrasonic sensors to detect the object and the volume of trash height. NodeMCU was used as data processing center, and LCD used as information output. The dustbin also using fuzzy logic to produce the volume status output of the trash height. It’s starting from empty to fully loaded. The janitor also can do re-check of the dustbin’s volume efficiently and effective through web application. Based on the testing result, the conclusion of the research is the sensor system has accuracy of precision rate of 93,4.

No abstract

<div style="’text-align: justify;">Telah dilakukan penelitian tentang pengaruh perubahan nilai parameter Number Scan Average (NSA) terhadap kualitas citra MRI yang direpresentasikan oleh nilai Signal to Noise Ratio (SNR). Penelitian dilakukan menggunakan citra otak potongan aksial menggunakan sekuen T2 Fast Spin Echo. Variasi nilai NSA yang digunakan adalah 2, 4 dan 6. Nilai SNR dihitung memanfaatkan algoritma median filter pada software Matlab 2013a. SNR diperoleh dengan membandingkan nilai piksel rata-rata dari citra setelah diberi median filter dengan nilai piksel rata-rata dari selisih citra sebelum dan sesudah diberi median filter. Nilai SNR pada NSA 2,4 dan 6 masing-masing sebesar 81,3411, 85,8796, dan 87,2757. Hal tersebut menunjukkan bahwa semakin besar nilai NSA, semakin besar pula nilai SNR yang diperoleh. Kenaikan NSA dari 2 ke 4, meningkatkan NSA sebesar 5,6%, dan perubahan NSA dari 4 ke 6, meningkatkan SNR sebanyak 1,6%. Namun, kenaikan nilai NSA juga menambah waktu scanning. Kenaikan NSA dari 2 ke 4, dan 4 ke 6, menambah waktu scanning rata-rata sebesar 2 menit.</div>