A Two-step Supervised Learning Artificial Neural Network for Imbalanced Dataset Problems

نویسندگان

  • Asrul Adam
  • Zuwairie Ibrahim
  • Mohd Ibrahim Shapiai
  • Lim Chun Chew
  • Lee Wen Jau
  • Marzuki Khalid
  • Junzo Watada
چکیده

In this paper, a two-step supervised learning algorithm of a single layer feedforward Artificial Neural Network (ANN) is proposed for solving imbalanced dataset problems. Levenberg Marquart backpropagation learning algorithm is utilized in the first step learning, while the second step learning mechanism is introduced by optimizing the decision threshold of the step function at the output layer of ANN using particle swarm optimization (PSO). After all the steps learning are accomplished, the best weights and decision threshold value are obtained to be used for testing process. Several imbalanced datasets, which are available in UCI Machine Learning Repository, are chosen as case study. The prediction performance is assessed by Geometric Mean (G-mean), which is a standard measure to indicate the efficiency of classifier for imbalanced datasets. Based on the experimental results, the proposed method is able to provide good G-mean value compared with the conventional ANN approaches.

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A METAHEURISTIC-BASED ARTIFICIAL NEURAL NETWORK FOR PLASTIC LIMIT ANALYSIS OF FRAMES

Despite the advantages of the plastic limit analysis of structures, this robust method suffers from some drawbacks such as intense computational cost. Through two recent decades, metaheuristic algorithms have improved the performance of plastic limit analysis, especially in structural problems. Additionally, graph theoretical algorithms have decreased the computational time of the process impre...

متن کامل

Classification of Iranian traditional musical modes (DASTGÄH) with artificial neural network

The concept of Iranian traditional musical modes, namely DASTGÄH, is the basis for the traditional music system. The concept introduces seven DASTGÄHs. It is not an easy process to distinguish these modes and such practice is commonly performed by an experienced person in this field. Apparently, applying artificial intelligence to do such classification requires a combination of the basic infor...

متن کامل

Learning Document Image Features With SqueezeNet Convolutional Neural Network

The classification of various document images is considered an important step towards building a modern digital library or office automation system. Convolutional Neural Network (CNN) classifiers trained with backpropagation are considered to be the current state of the art model for this task. However, there are two major drawbacks for these classifiers: the huge computational power demand for...

متن کامل

Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification

Some deep convolutional neural networks were proposed for time-series classification and class imbalanced problems. However, those models performed degraded and even failed to recognize the minority class of an imbalanced temporal sequences dataset. Minority samples would bring troubles for temporal deep learning classifiers due to the equal treatments of majority and minority class. Until rece...

متن کامل

Generalization of Deep Neural Networks for Chest Pathology Classification in X-Rays Using Generative Adversarial Networks

Medical datasets are often highly imbalanced with overrepresentation of common medical problems and a paucity of data from rare conditions. We propose simulation of pathology in images to overcome the above limitations. Using chest X-rays as a model medical image, we implement a generative adversarial network (GAN) to create artificial images based upon a modest sized labeled dataset. We employ...

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

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012