طبقه بندی کننده گروهی الهام گرفته از یادگیری عاطفی مغز ) ELiEC )
Abstract— In this paper, we suggest an inspired architecture
by brain emotional processing for classification applications.
The architecture is a type of ensemble classifier and is referred
to as ‘emotional learning-inspired ensemble classifier’ (ELiEC).
In this paper, we suggest the weighted k-nearest neighbor
classifier as the basic classifier of ELiEC. We evaluate the
ELiEC’s performance by classifying some benchmark datasets.
lassification methods have been widely used in the area
of science, engineering, industry, business and
medicine; they can be used for classification problems e.g.,
anomaly detection, handwriting recognition, speech
recognition and medical diagnosis. Among them, the data
driven classification approaches e.g., neural network-based
models and neuro-fuzzy-based methods are the most popular
methods due to the self-adaptive and high generalization
capability. However, they have some significant issues: over
fitting, model complexity and the curse of dimensionality,
etc. -. Thus, developing new classification models to
increase the classification’s accuracy while resolving the
mentioned issues are an open research topic in data mining.
In this paper, a new classification model is suggested that
can be considered as an ensemble classification with a
different integration mechanism and combination algorithm.
The model is an emotionally inspired model and is named
‘brain emotional learning-inspired ensemble classifier’
The rest of this paper is organized as follows: Section II
reviews some works in classification and emotional
learning–based models. Section III explains the ELiEC’s
structure. In Section IV, the benchmarks classification data
sets are examined by ELiEC and the obtained results
compared with other methods. Finally in Section V, we
conclude and recommendsome possible future improvements
فایل ارسالی توسط کاربر سایت جناب آقای داوود شاطرزاده