SCHOOL submission: 28th of january, 2018 Running Head: artificial






We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now




Submitted by: 
Namitha sudhakaran

Roll: 178920

Subject: business research methodology

Submitted to: Dr. Ritanjali Majhi

Date of submission: 28th of january, 2018

Running Head: artificial neural networks in business









National  Institute 
of  Technology,  Warangal

















Artificial neural networks are commonly used in
business but the studies and finding regarding that is very few in number. They
are connected nodes or units and each unit passes a  signal through it. Here i am trying to go
through the main functional areas and uses of artificial neural networks by
reviewing the literature papers on the topic. In the past decade it grow up and
performing many activities in wide variety of areas. reviewed more than 6
papers to find out different functional areas and usages of artificial neural























Utilization of neural networks are largely increased
in the two decades. Artificial neural networks are computational structures
that are used to emulate the knowledge in the central nervous system. Here I am
trying to analyze the recent papers in artificial neural network to prepare a
literature review on the papers that are already presented. i had gone through
some papers and trying to convey the main ideas of the particular one. They
have high efficiency and easily adaptable to use in different kind of analysis.
Most applications of this can be published in bankruptcy prediction  and stock forecasting. Most common research
area of artificial neural network should be come under finance in future. All the studies revealing the  importance of this artificial intelligence
method and illustrate about  recent
research for both academics and practitioners. This review paper not only
emphasizes the historical progressions in the field of neural networks, it
discusses the prospective development in the neural network research areas.



















Paper1: Artificial
Neural Networks: State of the Art in Business Intelligence

Author :Sunil Sapra.Department
of Economics and Statistics, California State University, Los Angeles, CA
90032, USA

The paper demonstrating about how ANN is used for
business and the important of ANN in business forecasting.ANNs are an excellent
tool for forecasting, but their results are difficult to interpret since ANNs
introduce complex interactions. In the absence of appropriate controls, the
ANNs can over-fit the data producing overoptimistic predictions. ANNs work very
well for large complex data sets in comparison with statistical methods. A key
weakness of the ANNs  is that they do not
possess sound statistical theory for inference, diagnostics, and model
selection. ANNs used carefully, can outperform statistical methods for certain
problems. in some areas ANN failed . things have changed over the past few
years due to the feasibility of deep networks made  by new training techniques, availability of
billions of documents, images and videos available for training purposes with
the rise of internet, and the realization that graphical processing units
(GPUs), the specialized chips used in PCs and videogame help to generate
graphics, that are suited to modeling neural networks. Along With deeper
networks, more training data and powerful and new hardware, also deep neural
networks that have made rapid progress in the areas of speech recognition and
image classification and language translation. now it cover  all areas and performing up to the expectation
compared to previous.

PAPER 2: Deep
learning in neural networks: An overview

AUTHOR: jurgen schmidhuber

This paper dealing with historical survey of usage
and popularity of artificial neural network In recent years, deep artificial
neural networks have won numerous contests in pattern recognition and machine
learning. This historical survey  summarizes
relevant work, this is also comment on Deep Learners are distinguished by the
depth of credit assignment paths which are chains of possibly learnable, normal
links between actions and effects. deep supervised learning , unsupervised learning,
reinforcement learning,evolutionary computation, and indirect search for short
programs and also encoding deep and large networks. and their usage on
different historical survey areas.

Paper 2: Improved system identification using
artificial neural networks and analysis of individual differences in responses
of an identified neuron

Author: AliciaCo stalago Meruelo
 David M.Simpson Sandor M.Veres  Philip L Newlan

This paper deals with the modeling and process of
artificial neural networks mathematical modeling is used to understand the
coding properties and dynamics of responses of neurons and neural
networks.  analyze and evaluate the
effectiveness of Artificial Neural Networks (ANNs) as a modeling tool for motor
neuron responses.  ANNs used  to model the synaptic responses of an
identified motor neuron and also, the fast extensor motor neuron, one of the
desert locust in response to displacement of a sensory organ, the femoral chord
tonal organ, this  monitors movements of
the tibia relative to the femur of the leg which is under consideration. The
aim of the study are, to determine the potential value of ANNs as tools to
model and investigate neural networks, and  second to understand the main general properties
of ANNs across individuals and to different input signals and last, to
understand individual differences in responses of the identified neuron. The
performance of the models are generated by the ANNs was compared with those
generated through the previous mathematical models of the same neuron. then The
results suggest that ANNs are significantly good compared to LNL and Wiener
models in predicting specific neural responses to Gaussian White Noise, but not
significantly different when tested with sinusoidal inputs. They are also able
to predict responses of the same neuron in different individuals irrespective
of which animal was used to develop the model, although notable differences
between some individuals were evident. this paper is all about the application
of ANN in the medical industry.


Paper3: Failure load prediction of single lap
adhesive joints using artificial neural networks

The objective of this paper was to predict the
failure load in single lap adhesive joints subjected to tensile loading by
using artificial neural networks. Experimental data obtained single lap
adhesive joints with various geometric models under the tensile loading. The
data are arranged in a format such that 2 input parameters cover the length and
width of bond area in single lap adhesive joints and also the corresponding
output is the ultimate failure load. An artificial neural network model was
developed to estimate relationship between failure loads by using geometric
dimensions of bond area which as input data. A 3-layer feed forward artificial
neural network that utilized a particular kind of algorithm model its used in
order to train the network. It is observed that artificial neural network model
which can also estimate failure load of single lap adhesive joints with
acceptable error. and the results showed that the artificial neural network is
an efficient alternative method to predict the failure load of single lap
adhesive joints.


Papre4: Artificial neural networks in
business: Two decades of research

Author : MichalTká?
  Robert vernor

This paper dealings with the research studies and
progress that had already happened in the area of artificial neural network and
what are the areas and upcoming trends that the artificial intelligence are
covered when the business trends are developed more and more, this paper
include the literature review of the papers which are already  done in the field of ANN artificial neural
networks have been extensively used in many business applications. Despite the
growing number of research papers, only few studies have been presented
focusing on the overview of published findings in this important and popular
area. Moreover, the majority of these reviews were introduced more than 15
years ago. The aim of this work is to expand the range of earlier surveys and
provide a systematic overview of neural network applications. The author
covered a total of 412 articles and classified them according to the year of
publication, application area, type of neural network, learning algorithm,
benchmark method, citations and journal. Our investigation revealed that most
of the research has aimed at financial distress and bankruptcy problems, stock
price forecasting & decision support, special attention to classification
tasks. Besides conventional multilayer feed forward network with gradient
descent back propagation, also various hybrid networks has been developed in
order to improve the performance of standard models. Even if neural networks
has been established as well-known method in business, there is enormous space
for additional research in order to improve their functioning and increase our
understanding of this influential area of the subject.


Paper5: Studying the Effect of Activation
Function on Classification Accuracy Using Deep Artificial Neural Networks

Author: Serwa A ,Faculty of
Engineering in El- Mataria

Artificial Neural Networks (ANN) is widely used
in remote sensing applications. Optimizing ANN still an enigmatic field of
research especially in remote sensing. This reaserch work is a trial to
discover the ANN activation function to be used perfectly in classification the
first step is preparing the reference map then assume a selected activation
function and receive the ANN  output. The
last step is comparing the output with the reference to reach the accuracy
assessment. The research result is fixing the activation function that is
perfect to be used in remote sensing classification. A real multi-spectral
Landsat 7 satellite images were used and was classified and the accuracy of the
classification was assessed with different activation functions. The sigmoid
function was found to be the best activation function. and the entire paper is
dealing with the different kind and area of application of ANN in remote





Paper6 : Artificial
Neural Networks Controller for Crude Oil Distillation Column of Baiji Refinery

Authors :Duraid Fadhil
Ahmed and Ali Hussein Khalaf

This paper is dealing with a specific application of
ANN in the area of crude oil distillation column of a particular refinery and
how the process are going on there with the help of ANN.A neural networks
controller is developed and used to regulate the temperatures in a crude oil
distillation unit. Two types of neural networks are used; neural networks
predictive and nonlinear autoregressive moving average (NARMA-L2) controllers. The
neural networks controller that is implemented in the neural network toolbox
software uses a neural network model of a nonlinear plant to predict future
plant performance. Artificial neural network in MATLAB simulator is used to
model Baiji crude oil distillation unit based on data generated from
aspen-HYSYS simulator. A comparison has been made between two methods to test
the effectiveness and performance of the responses. The results show that a
good improvement is achieved when the NARMA-L2 controller is used. Also shown
priority of neural networks NARMA-L2 controller which gives less offset value
and the temperature response reach the steady state value in less time with
lower over-shoot compared with neural networks predictive controller.


Paper 7: applications of artificial neural
networks for medical diagnostics and prognostics

Jaouher Ben Ali  
University of Sousse, Tunisia

Application of ANN in the medical field is already
discussed previously since it is one or other way related with business aspects
again we have to go to in detail on the another application In the medical
field, diagnostic and prognostic remain the most important step to identify
disease type and thereby define the adequate treatment before reaching
catastrophic and fatal states. However, clinical symptoms and syndromes are not
sufficient to detect some diseases. Consequently, the definition of new
advanced techniques for medical diagnostics and prognostics are becoming of
great interest to assist specialists in clinical researches and hence to ensure
safety for millions of people. Artificial neural networks (ANNs) are inspired
by the way that the brain performs computations: they are classified as one of
the best and most used soft computing techniques. In this context, two innovative
methods for early-stage Alzheimer’s disease diagnosis and blood glucose level
prediction of Type 1 diabetes prediction and other cancer image analysis will
be presented, as well as the result interpretation and some case studies. The
aim of this work is to show the great assistance provided by these advanced
techniques to the medical staff where the big data are processed through a
trained ANNs leading accurate statistics leading suitable diagnostic decision



Artificial neural networks have been taken an
enormous attention in last two decades. Much of the research has focused on
various business disciplines, however, only a small number of surveys have been
published in this area. Presented paper has examined 412 neural network
applications in different areas of business published between 1994 and 2015 in
well-known influential journals.

Proper integration of met heuristic methods into the
neural network methodology might be a key for achieving the optimal
performance. In general, neural networks have been successfully applied in wide
range of business tasks and were able to detect complex and nonlinear
relationships without requiring any specific assumptions about the distribution
or characteristics of the data.




















·       Artificial
Neural Networks: State of the Art in Business Intelligence Sunil Sapra.Department of Economics
and Statistics, California State University, Los Angeles, CA 90032, USA

·       of
artificial neural networks for medical diagnostics and prognostics

·       Artificial
neural networks in business: Two decades of research  Author : MichalTká?   Robert vernor

·       Deep
learning in neural networks: An overview 
AUTHOR: jurgen schmidhuber

·       Improved
system identification using artificial neural networks and analysis of
individual differences in responses of an identified neuron   Author: Alicia Co stalago Meruelo  David M.Simpson Sandor M.Veres  Philip L Newlan


·       Artificial
neural networks in business: Two decades of research Michal Tká?c1, Robert
Verner? University of Economics in Bratislava, Department of Quantitative
Methods, Tajovského 13, 04013 Ko?sice, Slovakia