Classifier Selection in Resource Limited Hardware: Decision Analysis and Resolution Approach

نویسندگان

چکیده

Digitalization, Industry 4.0 and Internet of things (IoT) have become more popular in the recent years. Most these systems depend on micro-controllers sensors. These sensors are mostly cheap, low RAM CPU systems; thus, they resource constrained environments. In this study, a supervised learning classifier comparison technique suitable for environments is proposed. This technique, Decision Analysis Resolution (DAR), originated domain Software Engineering. First, DAR explained using an example car buying scenario. Then 11 off-the-shelf classifiers compared less powerful intrusion detection scenario simulated well-known KDD99 dataset. All experiments realized python scikit-learn package. According to experiments, Tree most implement with small lead. Results other three (Bagging, Multi Layer Perceptron, Random Forest) also very similar. To aid reproducibility whole source code study provided open repository https://github.com/ati-ozgur/classifier-comparison-using-DAR.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Fuzzy Decision Making Approach to Enterprise Resource Planning System Selection

Here, we propose a fuzzy analytic hierarchy process (FAHP) method to evaluate the alternatives of enterprise resource planning (ERP) system. The fuzzy AHP approach allows the users get values more accurately to model the vagueness which changes according subjective ideas in the decision-making environment for ERP system selection problem. Therefore, fuzzy AHP method is used to obtain firm decis...

متن کامل

Portfolio Decision Analysis for Robust Project Selection and Resource Allocation

Organizations must take decisions on how to allocate resources to `go/nogo' projects to maximize the value of their project portfolio. Often these decisions are complicated by several value criteria, multiple resource types and exogenous uncertainties that in uence the projects' values. Especially when the number of projects is large, the e ciency of the resource allocation and the quality of t...

متن کامل

A New Classifier Based on Resource Limited Artificial Immune Systems

This paper presents a new tool for supervised learning, modeled on resource limited Artificial Immune Systems. A supervised learning system, it is self-regulatory, efficient, and stable under a wide range of user-set parameters. Its performance is comparable to well-established classifiers on a variety of testbeds, including the iris data, the diabetes classification problem, the ionosphere pro...

متن کامل

Decision based Resource Selection in Grid Environment

Grid computing allows users to locate computing resources and data dynamically during the computation. One of the main challenges in Grid computing is efficient selection of resources for the tasks submitted by users. Resource Selection is the most crucial phase in grid scheduling and resource management. The goal of selection is to identify list of authenticated resources that are available in...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Zeki sistemler teori ve uygulamalar? dergisi

سال: 2021

ISSN: ['2651-3927']

DOI: https://doi.org/10.38016/jista.755419