کنفرانس مهندسی برق ایران

صفحه اصلی / سی و دومین کنفرانس بین المللی مهندسی برق

A novel clustering-based over-sampling technique for imbalanced data sets

نویسندگان :

Behzad Mirzaei¹ Hossein Nezamabadi-pour² Javad Mahmoodi³

1- دانشگاه شهید باهنر کرمان 2- دانشگاه شهید باهنر کرمان 3- دانشگاه شهید باهنر کرمان

کلمات کلیدی :

Imbalanced data،Clustering،K-means algorithm،Over-sampling،Preprocessing methods

چکیده :

One of the most challenging problems in machine learning is the classification of imbalanced data. This problem arises when the samples of data are distributed unevenly among the classes, such that compared to one class (the majority or negative class), the other class (the minority or positive class) has far fewer samples. The classical classifiers are inappropriate to classify data sets of this nature. To address these classifiers' shortcoming in class imbalance situations, we present a novel clustering-based over-sampling technique in this paper. First, the k-means clustering algorithm is used to cluster the minority class samples. Then, sparse clusters including fewer samples are chosen. Finally, we use the nearest neighbor of each cluster center to create synthetic samples for the minority class. Also, to select clusters based on probabilities, we apply the roulette wheel selection operator during over-sampling. The C4.5 decision tree classifier is utilized in our experiments, and the F-measure criterion is considered to evaluate methods. According to the results, our method outperforms six other methods over fifteen imbalanced data sets.

لیست مقالات

لیست مقالات بایگانی شده

Integral Sliding-mode H∞ Control for Isothermal CSTR Based on Singular Systems Model with Sector Input Nonlinearity

Hamid Reza Ahmadzadeh - Masoud Shafiee

بهبود پردازش وفقی فضا-زمان (STAP) در سیستم‌های رادار هوابرد با استفاده از الگوریتم‌های آگاه به تنک بودن (Sparsity) سیستم

علی شیخیان - سارا میهن دوست - نعمت الله عزتی - احسان مصطفی پور

Implementation of a 14-Channel Real-time Compact Data Logger for Structure and Mechanical Engineering Laboratories

Keivan Sadeghinezhad - Esmaeil Najafiaghdam - Sara Dezhakam - Ali Sadeghinezhad

A New Method Based on Emprical Wavelet Transform in Order to Detect Current Transformer Saturation in Distance Relay

Amir Ali Ahmadi Pishkohi - Seyed Amir Hosseini - Behrooz Taheri

A Subsurface Microwave Imaging System Based on the Combination of Sub-Band-Subspace Images

Mohammad Ramezaninia - Mohammad Zoofaghari - Abolfazl Gheibollahi - Abbas Ali Heidari

Second-Order Sliding Mode Design Based on the Integration of Proportional-Integral and Nonlinear $\mathcal{H}_\infty$ Controllers for Load Frequency Control

Behrad Samari - Mohammad Javad Yazdanpanah

Modeling the Cable Bridge Based on Two Dimensional System and Analysing the Stability of Desired Model Based on Wave Advanced Model

Mehdi Mirshahi - Masoud Shafiee - Mehdi Mohammadi

Kickback noise reduction and offset cancellation technique for dynamic latch comparator

Mansoure Yousefirad - Mohammad Yavari

A Bidirectional Transformerless Direct AC-AC Dynamic Voltage Restorer with Extended Compensation Range and Up/Down Capability

ُSeyed Mohsen Mortazavi - MohammadHadi Mokhtari - Mohammad Reza Zolghadri

A Method Based on Attention Mechanism using Bidirectional Long-Short Term Memory(BLSTM) for Question Answering

Seyed Vahid Moravvej - Mohammad Javad Maleki Kahaki - Moein Salimi Sartakhti - Abdolreza Mirzaei

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.3.2