Neuro-Fuzzy and Soft Computing - A Computational Approach to Learning and Artificial Intelligence

Zhang, Shiyi; Sakulyeva, Tatyana; Pitukhin, Eugene; Догучаева, Светлана Магомедовна

doi:10.15866/ireaco.v13i4.19179

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of crisis events in the economy, global economic problems caused by quarantine measures and the decline in international economic cooperation, special attention should be paid to the issue of ensuring the effectiveness of management accounting as part of the functions of planning, organizing and monitoring the operational and strategic activities of economic entities [12][13][14]. Prior to the quarantine period in Ukraine, more than 1900 thousand economic entities belonging to small and medium-sized businesses were registered (Fig.…”

Section: Methodsmentioning

confidence: 99%

Certain Aspects of the Management Accounting System for Small and Medium-Sized Enterprises

Diegtiar¹,

Bezuhlyi²,

Tararuyev³

et al. 2021

ujaf

View full text Add to dashboard Cite

The importance of sustaining small and medium-sized enterprises (SMEs) around the world is increasing rapidly each year. In modern days many countries try to develop methods to preserve this type of companies given recent global crisis. SMEs in the Ukrainian economy account for 99.98% of the total business population. Relevance of this study consists in the significant role of the SMEs in the structure of national economy and their importance in development of the modern domestic economic systems. Objectives of the study are to determine prospects, shortcomings and features of establishing management accounting practices (MAPs) in SMEs. The problem of the study consists in fragmentation of the knowledge in the literature relating to management accounting practices in small and medium sized enterprises and problems of establishing them, due to restriction of resources and particularly wide gap between management accounting theory and practice compared to larger companies. Trends in the small and medium-sized enterprises in the structure of the national economy and their role in the development of the domestic economic system can be predicted on the basis of several reviewed cases. This confirms the relevance of the analysis of the management accounting system of economic entities in order to determine financial reserves to ensure economic activity in a crisis. Automated parametric control systems have been developed and proposed for implementation as elements of management accounting in order to provide processes for planning, monitoring and controlling of operational processes, as well as provide information and analytical support for management decision-making as a result of this study.

show abstract

Section: Methodsmentioning

confidence: 99%

Certain Aspects of the Management Accounting System for Small and Medium-Sized Enterprises

Diegtiar¹,

Bezuhlyi²,

Tararuyev³

et al. 2021

ujaf

View full text Add to dashboard Cite

show abstract

“…The Learning Rate (LR) hyper-parameter controls the step size in weight updates during neural network training [12], [22]. Using a small LR during VNN model training can help prevent missing local minima and improve network accuracy by slowing down the downward slope movement.…”

Section: Ii1 the Neural Network Learning Paradigmmentioning

confidence: 99%

Influence of Learning Rate Hyper-Parameter and Early Stopping Training Technique in Training Vanilla Neural Network Model for Effective Signal Power Loss Prediction

Ebhota,

Shongwe

2023

IRECAP

View full text Add to dashboard Cite

In this research work, the authors employed a Vanilla Neural Network (VNN) model to examine the influence of the Learning Rate (LR) hyper-parameter, early stopping training technique, Levenberg-Marquardt (LM) and Bayesian Regularization (BR) training algorithms in the training and prediction of signal power loss using a measured dataset from a Long Term Evolution (LTE) micro-cell environment. First order statistical performance indices, including the Mean Squared Error (MSE), Root Mean Square Error (RMSE), and Regression (R), were adopted for interpreting and analyzing the results. The LR hyper-parameters were sequentially selected cyclically from 0.002 to 1.00, while the early stopping training technique was chosen at a ratio of 70%:15%:15% for training, testing, and validation of the neural network model during network training. The authors examined the neural network training and its predictive abilities of the measured signal power by training the model with LM and BR training algorithms and applying varied LR values and the early stopping training technique. Comparative analysis was also conducted by training the VNN model without the application of LR hyper-parameter and the early stopping training technique. The LR hyper-parameter is a distinct training parameter that, when efficiently applied, improves network convergence, while the application of training techniques such as early stopping minimizes over-fitting during network training. The training result outputs demonstrate the effectiveness of the VNN model when applying a very small LR of 0.002. The best prediction results of the VNN model were observed when using an LR of 0.002, with an R value of 0.9922, performance MSE of 1.48, and RMSE of 1.6790 while training the VNN model with the BR algorithm and applying the early stopping training technique. When training the VNN model with an LR of 0.002 using the LM algorithm, an R value of 0.9816, performance MSE of 5.060, and RMSE of 2.5619 were obtained. The worst prediction results were computed when training the VNN model without the application of LR and the early stopping training technique, resulting in an R value of 0.97480, performance MSE of 6.3, and RMSE of 3.0167. However, when training the same VNN model without the application of LR and the early stopping training technique using the BR training algorithm, an R value of 0.9910, performance MSE of 3.3, and RMSE of 1.8045 were obtained. This strongly demonstrates that the BR training algorithm is not only a good training algorithm but also an excellent training technique.

show abstract

Project management in the context of digital transformation of the economy for the sustainable development of Kazakhstan

Sembin¹,

Tussupova²,

Селезнева³

et al. 2022

Rivista Di Studi Sulla Sostenibilita'

View full text Add to dashboard Cite

The Fourth Industrial Revolution and the introduction of the Industry 4.0 innova-tions create a unique opportunity for enterprises to increase productivity, opera-tional efficiency and rational use of resources, scale up successful pilot projects and acquire qualitatively new expertise for employees. The current stage of mod-ernisation of production can provide a significant impetus for economic growth and is a priority for governments and business leaders. Therefore, it is important to study project management strategies in the context of digital transformation in order to implement them in the enterprises of Kazakhstan. The purpose of the pa-per is to investigate the features and specifics of project management in modern conditions and search for methods of sustainable development of the state. The leading research method was the analysis, which made it possible to identify global trends in the field of project management for the implementation of innovations, as well as to assess the current state of enterprises in Kazakhstan after the Gov-ernment of the Republic of Kazakhstan approved the State Program "Digital Ka-zakhstan". As a result of the study, the features of project management for creat-ing a platform for the implementation of the Industry 4.0 for sustainable devel-opment of the state were identified. The authors concluded that the knowledge in-tensive business services need a deep understanding of user preferences and needs. Data-driven business models are the entry point for the digital transformation of enterprises.

show abstract

Neuro-Fuzzy and Soft Computing - A Computational Approach to Learning and Artificial Intelligence

Cited by 3 publications

References 0 publications

Certain Aspects of the Management Accounting System for Small and Medium-Sized Enterprises

Certain Aspects of the Management Accounting System for Small and Medium-Sized Enterprises

Influence of Learning Rate Hyper-Parameter and Early Stopping Training Technique in Training Vanilla Neural Network Model for Effective Signal Power Loss Prediction

Project management in the context of digital transformation of the economy for the sustainable development of Kazakhstan

Contact Info

Product

Resources

About