ترجمه مقاله نقش ضروری ارتباطات 6G با چشم انداز صنعت 4.0
- مبلغ: ۸۶,۰۰۰ تومان
ترجمه مقاله پایداری توسعه شهری، تعدیل ساختار صنعتی و کارایی کاربری زمین
- مبلغ: ۹۱,۰۰۰ تومان
The problem of automatically extracting novel and interesting knowledge from large amount of data is often performed heuristically when pattern extraction through classical statistical methods is found hard. In this paper an evolutionary approach, based on Differential Evolution, is proposed, which is able to perform the automatic discovery of comprehensible classification rules as a set of IF...THEN rules over a database of Multiple Sclerosis potential lesions. Moreover, this tool also determines which the most discriminant database attributes are in categorizing instances. Therefore, this evolutionary tool provides an efficient decision support system for clinical decisions, that could be a useful tool for medical experts to help them gain insight into the reasons for assessing the abnormality of a lesion.
I. INTRODUCTION
Multiple sclerosis (MS) is a long-lasting and disabling disease of the central nervous system which disrupts the information flow within the brain, and between the brain and body [1]. This results in several signs and symptoms, which include physical, mental, and in some cases psychiatric problems. Some such symptoms may be double vision, blindness in one eye, muscle weakness, sensorial or coordination troubles. MS is the most common autoimmune disorder affecting the central nervous system. In 2013, about 2.3 million people were affected worldwide, and about 20,000 people died from it. MS is complex and there is no single test that is proof-positive for its diagnosis. Although its not the sole test used to diagnose MS, magnetic resonance imaging (MRI) that makes detailed pictures of the body structures is very commonly used to visualize lesions [2] and represents a giant step in confirming a diagnosis and in evaluating its evolution. The use of MR images as a marker for MS needs the exploitation of all the knowledge of experts to correctly identify MS lesions.
V. CONCLUSIONS AND FUTURE WORK
In this paper, an approach relying on Differential Evolution for the automatic classification of potential lesions in a realworld Multiple Sclerosis database has been proposed to implement a valuable decision support system that could be useful to doctors. Namely, the DEC tool has been utilized to extract in an automatic way explicit knowledge from the database as a set of IF-THEN rules, each composed by AND–connected literals on the database attributes, and to show them to the users.