AbstrakTujuan utama dari penelitian yang dilakukan adalah melakukan pengenalan pola isyarat tangan statis dalam bahasa Indonesia. Pengenalan pola isyarat tangan statis dalam bentuk citra secara garis besar dilakukan dalam 3 tahapan yang meliputi: 1) Segmentasi bagian citra yang akan dikenali berupa tangan dan wajah, 2) ekstraksi ciri, dan 3) klasifikasi pola. Data citra yang diterapkan ada 15 kelas kata isyarat statis. Segmentasi dilakukan dengan menggunakan filter HSV dengan ambang berdasarkan warna kulit. Ekstraksi ciri dilakukan dengan dekomposisi wavelet Haar filter sampai level 2. Klasifikasi dilakukan dengan menerapkan sistem jaringan syaraf tiruan perambatan balik dengan arsitektur 4096 neuron pada lapisan input, 75 neuron pada lapisan tersembunyi dan 15 neuron pada lapisan output. Sistem diuji dengan menggunakan 225 data validasi dan akurasi yang dicapai adalah 69%. AbstractStatic Hand Gesture Recognition of Indonesian Sign Language System Based on Backpropagation Neural Networks. The main objective of this research is to perform pattern recognition of static hand gesture in Indonesian sign language. Basically, pattern recognition of static hand gesture in the form of image had three phases include: 1) segmentation of the image that will be recognizable form of the hands and face, 2) feature extraction and 3) pattern classification. In this research, we used images data of 15 classes of words static. Segmentation is performed using HSV with a threshold filter based on skin color. Feature extraction performed with the Haar wavelet decomposition filter to level 2. Classification is done by applying the back propagation system of neural network architecture with 4096 neurons in input layer, 75 neurons in hidden layer and 15 neurons in output layer. The system was tested by using 225 data validation and accuracy achieved was 69%.

The capacity of concrete beams will decrease by many external factors. To find simple and reliable method to monitor the quality of concrete beams is a challenging task. An optical-based fiber sensors is very interesting to develop for such task because of its many advantages. In this study, the optical fiber sensors were embedded in reinforced concrete beams to detect and to monitor deflection of the beam where a straight-line configuration of optical fiber was used. We perform experimental work to test performance of the use of optical fiber sensor by collecting data from flexural testing the concrete beam with the Universal Testing Machine (UTM). While the concrete deflection was measured by (linear variable differtial transducer (LVDT) as elongation unit, the fiber optic sensor output was observed in volts unit. We test the sensitivity of the optical fiber sensor by analyzing the relationship graph between the changes in the deflection of the concrete beam and output voltage of optical fiber sensors. The results show that optical fiber sensors have good sensitivity to detect and monitor concrete beam deflection.

Abstract-The developments in the construction of buildings, roads, and bridges commonly use concrete as the main material due to its strength and hardiness. However, the quality of the concrete may decrease due to some factors namely the age of the concrete, temperature, pressure, tension, etc. Thus, it is important to monitor its condition to find out any small damage such as cracks. Utilizing optical fiber power loss, a sensor capable of detecting cracks on a concrete can be made. This research uses multimode fiber optic planted inside the concrete. Sensor variation model being planted is in the form of wave. The lightweight concrete is designed using plastic aggregate. A specific tool capable of responding the change of the laser power coming through the fiber optic using phototransistor is also made in this research. The concrete is tested using two testing equipment at a time namely pressure testing that uses UTM (Universal Test Machine) to assess mechanical loading. Testing out the concrete using designed result tool is done by shooting laser on one side of the optical fiber and read the output power. During the test, the concrete is loaded continually and gradually increases using the UTM. The source of the light is laser, 850 nm of length. The result of the experiment and tool testing show that when the quality of the concrete decreases, laser power output through optical fiber increases.

No abstract

Komoditas unggas mempunyai prospek pasar yang sangat baik karena didukung oleh karakteristik produk unggas yang dapat diterima oleh masyarakat Indonesia yang sebagian besar muslim, karena harga yang relatif murah dengan akses yang mudah diperoleh dan sudah merupakan barang publik. Karena unggas merupakan komoditas penting maka dibutuhkan mesin penetas telur yang dapat memudahkan peternak dalam penetasan telur menjadi unggas. Akan tetapi masih ada kelemahan dalam penggunaan mesin penetas telur. Karena peternak diharuskan untuk selalu monitoring pada mesin penetas telur, hal ini akan membuang sia sia waktu peternak, untuk itu diciptakan sebuah pembaruan dalam sistem monitoring mesin penetas telur. Pembaruan yang ditawarkan berupa sistem monitoring melalui web dan telegram. Dimana pembaruan ini menggunakan metode komunikasi tx/rx pada Arduino dan Nodemcu untuk mengirimkan data ke web dan telegram. Komunikasi ini digunakan untuk menambah banyaknya inputan data pada mesin penetas telur untuk ditampilkan pada web dan telegram. Karena fokus pada penelitian ini adalah pengiriman data dari arduino ke nodemcu menggunakan komunikasi tx/rx. Maka untuk pengujian yang dilakukan adalah menguji berapa lama pengiriman data yang dilakukan oleh komunikasi tx/rx sampai ditampilkan ke web dan telegram.