ROBOT OBSTACLE AVOIDANCE DENGAN ALGORITMA Q-LEARNING

Perancangan prototipe robot obsctale avoidance tipe beroda dengan menerapkan algoritma Q-Learning telah diimplementasikan pada penelitian ini. Robot dirancang menggunakan mikrokontroler ATMega2560 pada platform Arduino Mega2560 sebagai pusat kontrol. Robot dilengkapi dengan lima sensor ultrasonik HC-SR04 dan lima sensor IR sharp GP2Y0A21YK0F. Posisi rintangan dibagi menjadi zona dan sektor. Zona menunjukkan posisi kanan atau kiri dan sektor adalah posisi sudut. Berdasarkan kombinasi nilai zona dan sektor, state terdiri atas 144 kondisi, sedangkan action dibagi menjadi lurus, kanan dan kiri. Dari 300 kali percobaan, nilai optimal learning rate konvergen di angka 0,5 dan discount factor di angka 0,9 setelah mencapai 250 percobaan. Robot mampu beradaptasi dengan cepat pada rintangan statis, dan lebih lama pada rintangan dinamis. Robot akan terus memperbarui nilai reward untuk beradaptasi pada setiap eksplorasi baru. Kata Kunci: reinforcement learning, q-learning, robot beroda, obsctale avoidance, navigasi robot.

Learning rate optimisation of an image processing deep convolutional neural network

The major contribution of this dissertation is the proposal of the use of mathematical models to identify an optimal learning rate for an image processing deep convolutional neural network (DCNN). This model is derived from a nonlinear regression relationship between the learning rate and the accuracy of a test DCNN model. This relationship is meant to (A) resolve the problem of arbitrarily selecting the initial learning rate (B) reduce computational resource requirement and (C) reduce training instabilities. An algorithm is developed to analyse an inputted DCNN model and subsequently render output parameters that may be used to aid in the selection of an OLR. The benefit of an OLR includes improved training stability and reduced computational resources. The results rendered by the OLR algorithm proposes that an optimal learning rate improves model performance; this is described by the test model average accuracy of 91%. Furthermore, a model validation graph is also extrapolated. which will illustrate the mathematical model accuracy and the region of interest (ROI). The ROI defines the region in the learning rate spectrum with a positive effect on model performance.

Convergence analysis of distributed multi-penalty regularized pairwise learning

In this paper, we establish the error analysis for distributed pairwise learning with multi-penalty regularization, based on a divide-and-conquer strategy. We demonstrate with [Formula: see text]-error bound that the learning performance of this distributed learning scheme is as good as that of a single machine which could process the whole data. With semi-supervised data, we can relax the restriction of the number of local machines and enlarge the range of the target function to guarantee the optimal learning rate. As a concrete example, we show that the work in this paper can apply to the distributed pairwise learning algorithm with manifold regularization.

Modeling and Simulation of Gas Emission Based on Recursive Modified Elman Neural Network

For the purpose of achieving more effective prediction of the absolute gas emission quantity, this paper puts forward a new model based on the hidden recurrent feedback Elman. The recursive part of classic Elman cannot be adjusted because it is fixed. To a certain extent, this drawback affects the approximation ability of the Elman, so this paper adds the correction factors in recursive part and uses the error feedback to determine the parameters. The stability of the recursive modified Elman neural network is proved in the sense of Lyapunov stability theory, and the optimal learning rate is given. With the historical data of mine actual monitoring to experiment and analysis, the results show that the recursive modified Elman neural network model can effectively predict the gas emission and improve the accuracy and efficiency of prediction compared with the classic Elman prediction model.

SIMULASI NEURAL NETWORK UNTUK PREDIKSI LOKASI USER PADA MOBILE NETWORK

Prediksi lokasi user pada mobile network merupakan hal sangat penting, karena routing panggilan pada mobile station (MS) bergantung pada posisi MS saat itu. Mobilitas MS yang cukup tinggi, terutama di daerah perkotaan, menyebabkan pencarian (tracking) MS akan berpengaruh pada kinerja sistem mobile network, khususnya dalam hal efisiensi kanal kontrol pada air interface. Salah satu bentuk pencarian adalah dengan mengetahui perilaku gerakan yang menentukan posisi MS. Dari MSC/VLR dapat diketahui posisi MS pada waktu tertentu. Karena location area suatu MS selalu unik dari waktu ke waktu, dan hal itu merupakan perilaku (behaviour) MS, maka dapat dibuat profil pergerakannya. Dengan menggunakan Neural Network (NN) akan diperoleh location area MS pada masa yang akan datang. Model NN yang digunakan pada penelitian ini adalah Propagasi Balik. Beberapa parameter NN yang diteliti dalam mempengaruhi kinerja prediksi lokasi user meliputi noise factor, momentum dan learning rate. Pada penelitian ini diperoleh nilai optimal learning rate = 0,5 dan noise factor = 1.