scholarly journals Predicting Business Distress Using Neural Network in SME-Arab Region

2018 ◽  
Vol 1 (1) ◽  
pp. 68-84 ◽  
Author(s):  
Ananth Rao ◽  
Malik AL KHATIB ◽  
Worku B GENANEW
Keyword(s):  
Neural Network ◽  
Logistic Model ◽  
Key Factors ◽  
Jel Codes ◽  
Arab Region ◽  
Leverage Ratio ◽  
Fixed Assets ◽  
Alternative Techniques ◽  
Credit Worthiness ◽  
Analytical Frameworks

The paper analyzes the financial and operational measures for Small and medium-sized enterprises (SME) business distress for predicting credit worthiness by using panel data of 110 observations from 22 SME companies for a period of 5 years (2009 – 2013). Panel logistic and Neural Network (NN) models are developed as alternative techniques for predicting the business distress.  The result suggests that cash cycle, net fixed assets, and leverage ratio are key factors in making credit decisions by lenders. The logistic model overall correctly classified 70 percent while NN framework outperformed the logistic model with 93 percent overall correct classification in training phase, and 83 percent in testing phase. The study opens up potential opportunities for the lending firms to adopt advanced analytical frameworks for predicting distress behavior of business firms. Keywords: SME, Business distress, Arab region, Petrochemical sub-sectors, Logit Model, Neural Network.   JEL codes: G29, G32

scholarly journals Graphene-based 3D XNOR-VRRAM with ternary precision for neuromorphic computing

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Batyrbek Alimkhanuly ◽  
Joon Sohn ◽  
Ik-Joon Chang ◽  
Seunghyun Lee
Keyword(s):  
Neural Network ◽  
Energy Consumption ◽  
Recognition Accuracy ◽  
Material Selection ◽  
Weighted Sum ◽  
Device Design ◽  
Key Factors ◽  
Neuromorphic Computing ◽  
Device Scaling ◽  
The Impact

AbstractRecent studies on neural network quantization have demonstrated a beneficial compromise between accuracy, computation rate, and architecture size. Implementing a 3D Vertical RRAM (VRRAM) array accompanied by device scaling may further improve such networks’ density and energy consumption. Individual device design, optimized interconnects, and careful material selection are key factors determining the overall computation performance. In this work, the impact of replacing conventional devices with microfabricated, graphene-based VRRAM is investigated for circuit and algorithmic levels. By exploiting a sub-nm thin 2D material, the VRRAM array demonstrates an improved read/write margins and read inaccuracy level for the weighted-sum procedure. Moreover, energy consumption is significantly reduced in array programming operations. Finally, an XNOR logic-inspired architecture designed to integrate 1-bit ternary precision synaptic weights into graphene-based VRRAM is introduced. Simulations on VRRAM with metal and graphene word-planes demonstrate 83.5 and 94.1% recognition accuracy, respectively, denoting the importance of material innovation in neuromorphic computing.

Long-Term Wind Power Prediction Based on Rough Set

2013 ◽  
Vol 329 ◽  
pp. 411-415 ◽  
Author(s):  
Shuang Gao ◽  
Lei Dong ◽  
Xiao Zhong Liao ◽  
Yang Gao
Keyword(s):  
Neural Network ◽  
Wind Power ◽  
Rough Set ◽  
Wind Farm ◽  
Rough Set Theory ◽  
Prediction Method ◽  
Key Factors ◽  
Power Prediction ◽  
Wind Power Prediction

In long-term wind power prediction, dealing with the relevant factors correctly is the key point to improve the prediction accuracy. This paper presents a prediction method with rough set analysis. The key factors that affect the wind power prediction are identified by rough set theory. The chaotic characteristics of wind speed time series are analyzed. The rough set neural network prediction model is built by adding the key factors as the additional inputs to the chaotic neural network model. Data of Fujin wind farm are used for this paper to verify the new method of long-term wind power prediction. The results show that rough set method is a useful tool in long-term prediction of wind power.

scholarly journals An Evaluation on Investment of Research Funds with a Neural Network Algorithm in “Double First-Class” Universities

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Jihong Sun ◽  
Yahui Li ◽  
Xiaoyun Zhao ◽  
Nanxing Zhang
Keyword(s):  
Neural Network ◽  
Evaluation System ◽  
University Research ◽  
Backpropagation Neural Network ◽  
Fixed Assets ◽  
Network Method ◽  
Neural Network Algorithm ◽  
Current Context ◽  
World Class ◽  
World Class Universities

In the current context of the establishment of world-class universities and disciplines in China, this study examined the investment of research funds at universities. First, six variables were selected as evaluation indicators from the perspective of fixed assets, teaching configuration, research instruments, and the number of books in libraries. Seventy-two universities were investigated from 2013 to 2017. Second, an evaluation system was constructed using the BP (backpropagation) neural network method and its applicability was verified. Finally, by adjusting the six indicators, the investment of university research funds could be adjusted and predicted to provide a reference for the construction of “first-class” universities and disciplines.

Predictive Models for Pre-Operative Diagnosis of Rotator Cuff Tear: A Comparison Study of Two Methods between Logistic Regression and Artificial Neural Network

2014 ◽  
Vol 595 ◽  
pp. 263-268
Author(s):  
Chen Chiang Lin ◽  
Hsin Hui Chan ◽  
Chen Yuan Huang ◽  
Nang Shu Yang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Logistic Regression ◽  
Rotator Cuff ◽  
Logistic Model ◽  
Predictive Accuracy ◽  
Rotator Cuff Tears ◽  
Comparison Study ◽  
Accuracy Rate ◽  
Artificial Neural

Rotator cuff tears are the most common disorder of the shoulders.agnetic resonance Image (MRI) is the diagnostic gold standard of rotator cuff tears. However, there are some dilemmas in the rotator cuff tears treatment. Clinically, surgical results of rotator cuff tears are sometimes different from MRI results of rotator cuff tears. The main purpose of this study is to build up predicative models for pre-operative diagnosis of rotator cuff tears There are two models of this study are proposed: logistic regression model and artificial neural network model. Patients are divided into two sets: Set1 is patients with full thickness rotators cuff tears. Set 2 is patients with partial thickness rotators cuff tears. The charts of 158 patients are completely reviewed and the collected data were analyzed. The results showed that the predictive accuracy of artificial neural networks model is higher than the predictive accuracy of logistic model. The application of this study can assist doctors to increase the accuracy rate of pre-operative diagnosis and to decrease the legal problems.

scholarly journals Early Warning Signals to Predict Islamic Bank Failure

2018 ◽  
Vol 2 (2) ◽  
pp. 147-151
Author(s):  
Zahid ur Rehman Khokher
Keyword(s):  
North Africa ◽  
Early Warning ◽  
Logistic Model ◽  
Islamic Banking ◽  
Islamic Banks ◽  
Warning Signals ◽  
Early Warning Signals ◽  
Leverage Ratio ◽  
Macroeconomic Variables ◽  
Banking Institutions

  The paper empiricialy tests the use of various stability factors as early warning signals that can effectively predict the failure in Islamic banking institutions. These early warning signals enable the regulatory and supervisory authorities to take timely corrective action to safeguard the interest of fund providers such as depositors, investment account holders, creditors as well as other stakeholders. Using a 10-year panel data of 65 Islamic banks from 13 banking systems in the Middle East, North Africa, Asia and Europe, this study uses six stability indicators of CAMELS supervisory framework in a logistic model to see their effecitveness in predicting distress in Islamic banks. The model is then extended with the alternative capital are leverage ratios as well as macroeconomic variables in order to see whether simple leverage ratio offers better estimation results than the complex, risk weighted measures as debated by (Haldane, 2012).  

scholarly journals COVID-LIBERTY, A Machine Learning Computational Framework for the Study of the Covid-19 Pandemic in Europe. Part 1: Building of an Artificial Neural Network and Analysis and Parametrization of Key Factors which Influence the Spread of the Virus.

2021 ◽  
Vol 8 ◽  
pp. 12-26
Author(s):  
Nicholas Christakis ◽  
Michael Politis ◽  
Panagiotis Tirchas ◽  
Minas Achladianakis ◽  
Eleftherios Avgenikou ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Seasonal Variability ◽  
Back Propagation ◽  
Key Factors ◽  
Computational Framework ◽  
Virus Family ◽  
Feed Forward Back Propagation ◽  
Rapid Spread ◽  
Artificial Neural

Covid-19 is the most recent strain from the corona virus family that its rapid spread across the globe has caused a pandemic, resulting in over 200,000,000 infections and over 4,000,000 deaths so far. Many countries had to impose full lockdowns, with serious effects in all aspects of everyday life (economic, social etc.). In this paper, a computational framework is introduced, aptly named COVID-LIBERTY, in order to assist the study of the pandemic in Europe. Initially, the mathematics and details of the computational engine of the framework, a feed-forward, back-propagation Artificial Neural Network are presented. 5 European countries with similar population numbers were chosen and we examined the main factors that influence the spread of the virus, in order to be taken into consideration in the simulations. In this way lockdown, seasonal variability and virus effective reproduction were considered. The effectiveness of lockdown in the spread of the virus was examined and the Lockdown Index was introduced. Moreover, the relation of Covid- 19 to seasonal variability was demonstrated and the parametrization of seasonality presented.

A Study on the Contribution of 12 Key-Factors to the Growth Rates of the Region of the East Macedonia-Thrace (EMTH) by Using a Neural Network Model

2012 ◽  
Vol 1 (1) ◽  
pp. 18-28
Author(s):  
E. Stathakis ◽  
M. Hanias ◽  
P. Antoniades ◽  
L. Magafas ◽  
D. Bandekas
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Regional Growth ◽  
Network Models ◽  
Domestic Product ◽  
Key Factors ◽  
Neural Network Models ◽  
First Time

This study gives a new methodological framework regarding the measuring of the contribution of some key-factors on the regional growth rate and forecasting the future development rates, based on Neural Network Models (NN Models). It’s a serious attempt to study the contribution of twelve key-factors to the change of the Regional Gross Domestic Product of the Region of East Macedonia -Thrace during a long-term of growth process, by creating and using a suitable Neural Network Model. Specifically, twelve key-factors, time functioned in the period 1991-2008, are studied for the first time, in order to be investigated, scientifically, firstly their % contribution to growth of the regional economy and secondly, to be predicted how much the (Regional Growth Domestic Product) RGDP-under certain conditions-will be changed. It’s a NN Model with inputs the twelve key-factors in order to be evaluated and measured, at the best precise, their percentage contribution to the RGDP. The model and results can be found further into the article.

High-Pressure Water Spray Research Based on Neural Network

2010 ◽  
Vol 29-32 ◽  
pp. 138-142
Author(s):  
Rui Li ◽  
Zi Ming Kou
Keyword(s):  
Neural Network ◽  
High Pressure ◽  
Influencing Factors ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Industrial Processes ◽  
Water Spray ◽  
Key Factors ◽  
Pressure Water ◽  
The Relationship

The spray cleaning method is important and universal in many industrial processes and other occasion. Because the size of the waterdrop is one of key factors for cleaning, this paper not only studied the relationship between the size of waterdrop and other influencing factors, but also researched the forecasted method for the size of waterdrop. In lab, by measuring the size of the waterdrop, jetted by one kind of nozzle, data were acquired and were used to train the Back Propagation Neural Network ( BPNN ). Through comparing those diameters, between measured in lab and calculated by BPNN after trained. It was acquired that the maximum errors was smaller than 1.62%, between the computed results and the factual measured ones. The experimental results showed that BPNN is an effective tool to predict the variation of the non-linear waterdrop diameter.

Sign in / Sign up

Export Citation Format

Share Document