International Journal of Advanced Studies in Computer Science and Engineering (IJASCSE)

                                                                                                                                                                                                   ISSN : 2278 7917 

Call For Papers

May 2019

  Submission         May 10

  Acceptance         May 20

  Publication          May 31

Bookmark and Share

International Journal of advanced studies in Computer Science and Engineering (IJASCSE) is here to provide a timely and broad coverage of research in ever-challenging field of Computer Science and Computer Science Engineering. IJASCSE is an interdisciplinary, peer reviewed, fully refereed, monthly, Open Access journal for research scholars with a mix of regular and theme based issues to share their new and advanced research in Computer Science and Engineering. 

The papers published at IJASCSE are currently Abstracted & Indexed by some world famous databases.

 Call For Papers

April  2019

     Submission                     April 10

      Notification                     April 20

      Publication                     April 30

Bookmark and Share

Open Access Database

IJASCSE is an online peer reviewed quality publication, which publishes research papers from diverse fields in computers, sciences, engineering and technologies that emphasizes new research, development and their applications. It provides an open access database for all who are interested to exchange their research work, technical notes & surveying results among professionals through out the world.


 IJASCSE volume 5 issue 10                           


A balanced approach for combining rule based reasoning with case based reasoning for lung disease diagnosis

Adane N. Tarekegn, Alemu K. Tegegne, Tamir anteneh

AbstractThe diagnosis of lung disease is often complicated and time consuming due to the significant number of vague variables involved. The symptoms of patients are usually unclear and the similarities in symptoms of some lung diseases are difficult to distinguish. This creates many difficulties for physicians to reach at a right decision or diagnosis. This paper presents hybrid intelligent system that uses a combination of rule based reasoning and case based reasoning techniques to achieve the diagnose of lung diseases. Rule based reasoning uses existing domain knowledge for making decision support while case-based reasoning system captures previous experiences to solve new problems. To develop the hybrid intelligent system, data and knowledge is acquired from documented and non- documented sources. The acquired data and knowledge are modeled using decision tree structure that represents concepts and procedures involved in the diagnosis of lung disease. The hybrid intelligent system is developed using SWI Prolog. The system is tested and evaluated to ensure that whether the performance of the system is accurate and the system is usable by physicians and patients. The hybrid system has registered an average accuracy of 86.4%


Ripple formation on Polypropylene surfaces by low energy oblique ion beam irradiation

Meetika Goyal, Sanjeev Aggarwal and Annu Sharma 


The formation of self-organized ripple patterns on the solid surfaces by ion beam sputtering is an emerging field of research in materials science. In the present work, nano patterning of amorphous Polypropylene substrates as a result of 40 keV N2+ ions sputtering has been investigated. The specimens were irradiated with varying off normal incidences of 300,400 and500 at ion beam fluence of 2.5 x 1016 ions cm-2. The topographical evolution of ripple like patterns has been clearly observed on the irradiated surfaces through Atomic Force Microscope (AFM). The morphological parameters like surface roughness, ripple amplitude and ripple wavelength were measured as a function of oblique ion incidence. Degree of ordering and dimensions of these nano-ripples have been found to be greatly dependent on the angle of incidence at which surfaces are irradiated.


Question Classification in Amharic Question Answering System: Machine Learning Approach

Adane Nega, Workneh Chekol, Alemu Kumlachew

Abstract The Question Answering Systems (QAS) uses method of information retrieval and Information extraction to retrieve documents that contain special answers to the question. One of the existence problem is finding the desired information from this very high variety. For this reason, it is necessary to find ways for organizing, classification and retrieving of information. Question Classification is growing in popularity as it has an important role in question answering systems, information retrieval and it can be used in a wide range of other domains. The main aim of question classification is to accurately assign labels to questions based on expected answer type. Most approaches in the past have relied on matching questions against hand- crafted rules. However, rules require enormous effort to create and often suffer from being too specific. A great deal of current research works on question classification is based on statistical approach to overcome these issues by employing machine learning techniques such as Support Vector Machine (SVM). This paper presents Amharic question classification using machine learning approaches. The dataset set used in this research consist of 180 questions collected from the agriculture domain. The average accuracy of SVM classifier was 80.6% in classifying both positive and negative test examples for each class of question.

Impact of Digital Communication for Academic Institutions

Laveena Chhajed, Nimisha Kothari, Dr. SK Pandey

AbstractDigital communication has taken over the dominant form of classroom study. Using digital communication each day will help to gain knowledge, understand concepts and learn new ways of seeing the things around them. 

Keywords- AI, Intelligent system, Hybrid reasoning systems, Knowledge representation, RBR, CBR.

Keywords- ion beam irradition, low energy oblique;

Keywords—Question Answering System (QAS), Support Vector Machine (SVM)

Keywords—Digital Communication, Digital Learning, Digital Marketing, Learning models

To download Click on PDF logo
To download Click on PDF logo