Search

Search Results

• A Review Regarding Deep Learning Technology in Mobile Robots

  1-5.

  Vlad Ovidiu Mihalca

  Flaviu Birouaș

  Florin Avram

  Arnold Nilgesz

  Views:

  113

  Deep Learning usage is spread across many fields of application. This paper presents details from a selected variety of works published in recent years to illustrate the versatility of the Deep Learning techniques, their potential in current and future research and industry applications as well as their state-of-the-art status in vision tasks, where their efficiency is experimentally proven to near 100% accuracy. The presented applications range from navigation to localization, object recognition and more advanced interactions such as grasping.

• Overview of Modern Teaching Equipment that Supports Distant Learning

  1-22.

  Csongor Márk Horváth

  Trygve Thomessen

  Gábor Sziebig

  Views:

  260

  Laboratory is a key element of engineering and applied sciences educational systems. With the development of Internet and connecting IT technologies, the appearance of remote laboratories was inevitable. Virtual laboratories are also available; they place the experiment in a simulated environment. However, this writing focuses on remote experiments not virtual ones. From the students’ point of view, it is a great help not only for those enrolling in distant or online courses but also for those studying in a more traditional way. With the spread of smart, portable devices capable of connection to the internet, students can expand or restructure time spent on studying. This is a huge help to them and also allows them to individually divide their time up, to learn how to self-study. This independent approach can prepare them for working environments. It offers flexibility and convenience to the students. From the universities’ point of view, it helps reduce maintenance costs and universities can share experiments which also helps the not so well-resourced educational facilities.

• MARG Sensor Based Position Estimation for Periodic Movements

  Balázs Nagy

  Views:

  152

  The research examined the fusion of signals from magnetometer, gyroscope and acceleration sensors (MARG sensor). The focus of the article is the sensor fusion by supervised learning, which is an estimate of the situation based on the parallel processing of different types of measured data in the case of periodic movements. The applicability of the learning algorithms was examined through a practical example of a pendulum.

• Classification of Mushroom Data Set by Ensemble Methods

  1-4.

  Şahin Yildirim

  Mehmet Safa Bingöl

  Views:

  670

  Due to disease of mushrooms, it is very important to classify mushrooms for predicting the best quality mushrooms. There are many methods to analyse the main parts of mushrooms. For above mentioned descriptions; in this simulation study five types of classification algorithm are employed to predict the structure of mushrooms. Mushroom dataset is used to predict the classes of mushrooms. The results are improved that these methods will be used to predict exact mushrooms features and classifications in real time approaches.

• Rule-base Reduction in Fuzzy Rule Interpolation-based Q-learning

  1-6.

  Dávid Vincze

  Szilveszter Kovács

  Views:

  107

  The method called Fuzzy Rule Interpolation-based Q-learning (FRIQ-learning for short) uses a fuzzy rule interpolation method to be the reasoning engine applied within Q-learning. This method was introduced previously by the authors along with a rule-base construction extension for FRIQlearning, which can construct the requested FRI fuzzy model from scratch in a reduced size, implementing an incremental creation strategy. The rule-base created this way will most probably contain only those rules which were significant during the construction process, but have no important role in the final rule-base. Also there can be rules which became redundant (can be calculated by using fuzzy rule interpolation) thanks to another rule in the finished rule base. The goal of the paper is to introduce possible methods, which aim to find and remove the redundant and unnecessary rules from the rule-base automatically by using variations of newly developed decremental rule base reduction strategies. The paper also includes an application example presenting the applicability of the methods via a well known reinforcement learning example: the cart-pole simulation.