Suchergebnisse

ABSTRACTArtificial neural networks are new methods for classification. We investigate two important issues in building neural network models; network architecture and size of training samples. Experiments were designed and carried out on two‐group classification problems to find answers to these model building questions. The first experiment deals with selection of architecture and sample size for different classification problems. Results show that choice of architecture and choice of sample size depend on the objective: to maximize the classification rate of training samples, or to maximize the generalizability of neural networks. The second experiment compares neural network models with classical models such as linear discriminant analysis and quadratic discriminant analysis, and nonparametric methods such as k‐nearest‐neighbor and linear programming. Results show that neural networks are comparable to, if not better than, these other methods in terms of classification rates in the training samples but not in the test samples.

The article examines risks faced by banks during their lending processes and the mechanisms for managing these risks, utilizing modern statistical methods. Specifically, the study focused on the artificial neural network model as a technique of artificial intelligence that has successfully applied various classifications and discrimination tasks among institutions. A random sample of 46 institutions obtained loans from the branches of the National Bank of Algeria (BNA), Local Development Bank (BDL), Popular Credit of Algeria (CPA), and Agricultural and Rural Development Bank (BADR) in El Bayadh province, Algeria. Each of these institutions was characterized by 14 measurable variables with numerical values derived from the financial statements (balance sheets and income statements), as well as 3 qualitative non-accounting variables extracted from the loan applicants' files (age of the institution, sector of activity (services/productive), institution status (viable/struggling). The sample of these 46 institutions was initially divided into two groups: 64% comprised financially stable institutions, and the other 36% were struggling institutions. The research checks whether the risk assessment of each of these 46 institutions using artificial neural networks will identify their institution status (viable/struggling) in the same way as it was in the base sample. The training phase recorded a prediction error rate of 0%, and the network testing phase misclassification rate was 5.6%. The overall correct classification rate for the multilayer artificial neural network was 92.9%, with a total error rate of 7.1%. The contribution rate of the non-accounting variable "sector of activity" was 100%, and the variable "age of the institution" was 94.4%. Other variables had minor percentages, underscoring the importance of qualitative variables in the classification process. Thus, the study proved that artificial neural network model is an effective model for distinguishing between viable and struggling institutions, significantly contributing to banking risk management.

In artificial neural networks, the knowledge stored as the strength of the interconnection weights is modified through a processcalled learning, using a learning algorithm. This algorithmic function, in conjunction with a learning rule, (i.e., back-propagation) is used tomodify the weights in the network in an orderly fashion. In this proposed system a technique is used for extracting business knowledge fromtrained ANNs. It is organized into four sections that include acquisition of business data, knowledge extraction, representation by rules, andController for maintain the consistency of knowledge. The technique will use Back-propagation NN to predict stock prices and stockperformance based on input of external variants such as government policies, quarterly export volumes etc. The application will also providerecommendations (or decisions) based on expected outcome, overall customer portfolio, and current market situation. Key Words: neural network, knowledge acquisition, knowledge extraction, rules, back propagation algorithm.

This book presents as its main subject new models in mathematical neuroscience. A wide range of neural networks models with discontinuities are discussed, including impulsive differential equations, differential equations with piecewise constant arguments, and models of mixed type. These models involve discontinuities, which are natural because huge velocities and short distances are usually observed in devices modeling the networks. A discussion of the models, appropriate for the proposed applications, is also provided.

This paper devises an optimization-based technique for sentiment analysis using the set of reviews. The major processes involved for the developed sentiment analysis approach are tokenization and sentiment classification. Initially, the input reviews are considered from the database and are subjected to the tokenization process. The tokenization process is performed using Bidirectional Encoder Representations from Transformer (BERT) where the input review data is partitioned into individual words, named as tokens. Finally, sentiment classification is carried out using Attention-based Bidirectional CNN-RNN Deep Model (ABCDM), which is trained by proposed Chimp Deer Hunting Optimization (CDHO) approach. Accordingly, the proposed CDHO algorithm is newly designed by incorporating Chimp Optimization Algorithm (ChOA) and Deer Hunting Optimization Algorithm (DHOA). The proposed CDHO-based ABCDM provided enhanced performance with highest precision of 93.5%, recall of 94.5% and F-measure of 94%.

This paper applies neural network technology, a standard approach in computer science that has been unaccountably ignored by sociologists, to the problem of developing rigorous sociological theories. A simulation program employing a "varimax" model of human learning and decision-making models central elements of the Stark-Bainbridge theory of religion. Individuals in a micro-society of 24 simulated people learn which categories of potential exchange partners to seek for each of four material rewards which in fact can be provided by other actors in the society. However, when they seek eternal life, they are unable to find suitable human exchange partners who can provide it to them, so they postulate the existence of supernatural exchange partners as substitutes. The explanation of how the particular neural net works, including reference to modulo arithmetic, introduces some aspects of this new technology to sociology, and this paper invites readers to explore the wide range of other neural net techniques that may be of value for social scientists

The main goal of the study is to analyze all relevant properties of the electro hydraulic systems and based on that to make a proper choice of the neural network control strategy that may be used for the control of the mechatronic system. A combination of electronic and hydraulic systems is widely used since it combines the advantages of both. Hydraulic systems are widely spread because of their properties as accuracy, flexibility, high horsepower-to-weight ratio, fast starting, stopping and reversal with smoothness and precision, and simplicity of operations. On the other hand, the modern control of hydraulic systems is based on control of the circuit fed to the inductive solenoid that controls the position of the hydraulic valve. Since this circuit may be easily handled by PWM (Pulse Width Modulation) signal with a proper frequency, the combination of electrical and hydraulic systems became very fruitful and usable in specific areas as airplane and military industry. The study shows and discusses the experimental results obtained by the control strategy of neural network control using MATLAB and SIMULINK [1]. Finally, the special attention was paid to the possibility of neuro-controller design and its application to control of electro-hydraulic systems and to make comparative with other kinds of control.