Roads are land transportation infrastructure that covers all parts of the road. Roads with bad conditions will interfere with the achievement of activities to a destination. The situation also includes damage to the road surface in the form of holes. To overcome this, in this Final Project a hole detector was detected in the road using the Gray Level Co-occurrence Matrix (GLCM) and Neural Network (NN). The tool detects holes in the surface of the road using a camera by walking along the road being examined. The camera is used instead of the eye to detect road surface damage. The method used to detect holes is the GLCM. The GLCM method produces several features, namely entropy, contrast, energy, homogeneity, and correlation which will then be processed using a NN to produce a decision whether there is a hole or not. In addition to knowing where the location of the damage is equipped with GPS (Global Positioning System). The results of image feature extraction using the GLCM and road classification using NN can be used in the hole detection process. Testing is done using a car prototype that is monitored through the computer. The percentage of successful hole detection is 86.6% using 10 hidden. When a hole is detected the device manages to take a picture, then sends the hole coordinates to the server.
An improved Elman neural network (IENN) controller with particle swarm optimization (PSO) is presented for nonlinear systems. The proposed controller is composed of a quasi-ARX neural network (QARXNN) prediction model and a switching mechanism. The switching mechanism is used to guarantee that the prediction model works well. The primary controller is designed based on IENN using the backpropagation (BP) learning algorithm with PSO. PSO is used to adjust the learning rates in the BP process for improving the learning capability. The adaptive learning rates of the controller are investigated via the Lyapunov stability theorem. The proposed controller performance is verified through numerical simulation. The method is compared with the fuzzy switching and 0/1 switching methods to show its effectiveness in terms of stability, accuracy, and robustness.
<p>Potensi pertanian lahan kering di Nusa Tenggara Timur cukup luas sekitar 1.528.308 ha dan di daerah ini cocok untuk dikembangkan kacang tanah. Tanaman kacang tanah masih dibudidayakan secara subsisten sehingga perlu diidentifikasi faktor-faktor penghambat dan pendukung dalam upaya pengembangannya. Penelitian dilakukan di Kabupaten Sumba Timur pada musim tanam 2015 dengan cara ‘Rapid Rural Appraisal (RRA)’. Metode analisis data yaitu analisis SWOT, tabulasi dan tingkat daya saing. Hasil penelitian menunjukkan bahwa faktor kesesuaian lahan untuk kacang tanah total nilai bobot (TNB=2,0) dan biomassa kacang tanah termanfaatkan untuk pakan (TNB=1,1) menjadi faktor penguat internal pengembangan kacang tanah di NTT. Sedang penguat eksternalnya adalah pasar kacang tanah sudah terbentuk (TNB=2,3) dan permintaan kacang tanah tinggi (1,6). Meskipun ada penghambat seperti faktor benih kacang tanah bermutu rendah (TNB=1,2) dan ada ancaman seperti faktor kekeringan (TNB=1,2), tetapi pengaruhnya lebih kecil dibanding penguat dan potensi sumberdaya yang dimiliki. Strategi pengembangan yang digunakan adalah (1) pengelolaan usahatani yang saat ini harus dilakukan lebih intensif dengan penggunaan VUB kacang tanah dan teknologi tanam, (2) peningkatan skala usaha dengan memanfaatkan lahan-lahan kosong dan peningkatan indeks pertanaman (IP). Komoditas kacang tanah dapat berkompetisi dengan jagung dan sorgum dan peningkatan daya saingnya mudah dilakukan dengan penggunaan VUB kacang tanah yang telah tersedia sesuai dengan agroekologi dan preferensi petani di NTT. Nilai ekonomi dalam pendapatan komoditas kacang tanah saat ini berkontribusi sebesar 30% terhadap pengeluaran keluarga dan berpeluang dapat ditingkatkan.</p>
A quasi-ARX (quasi-linear ARX) neural network (QARXNN) model is able to demonstrate its ability for identification and prediction highly nonlinear system. The model is simplified by a linear correlation between the input vector and its nonlinear coefficients. The coefficients are used to parameterize the input vector performed by an embedded system called as state dependent parameter estimation (SDPE), which is executed by multi layer parceptron neural network (MLPNN). SDPE consists of the linear and nonlinear parts. The controller law is derived via SDPE of the linear and nonlinear parts through switching mechanism. The dynamic tracking controller error is derived then the stability analysis of the closed-loop controller is performed based Lyapunov theorem. Linear based adaptive robust control and nonlinear based adaptive robust control is performed with the switching of the linear and nonlinear parts parameters based Lyapunov theorem to guarantee bounded and convergence error.
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.