Search

In our continuous attempts to model natural intelligence and emotions in machine learning, many research works emerge with different methods that are often driven by engineering concerns and have the common goal of modeling human perception in machines. This paper aims to go further in that direction by investigating the integration of emotion at the structural level of cognitive systems using the novel emotional DuoNeural Network (DuoNN). This network has hidden layer DuoNeurons, where each has two embedded neurons: a dorsal neuron and a ventral neuron for cognitive and emotional data processing, respectively. When input visual stimuli are presented to the DuoNN, the dorsal cognitive neurons process local features while the ventral emotional neurons process the entire pattern. We present the computational model and the learning algorithm of the DuoNN, the input information-cognitive and emotional-parallel streaming method, and a comparison between the DuoNN and a recently developed emotional neural network. Experimental results show that the DuoNN architecture, configuration, and the additional emotional information processing, yield higher recognition rates and faster learning and decision making., (Copyright © 2010 Elsevier Ltd. All rights reserved.)

Much of the research work into artificial intelligence (AI) has been focusing on exploring various potential applications of intelligent systems with successful results in most cases. In our attempts to model human intelligence by mimicking the brain structure and function, we overlook an important aspect in human learning and decision making: the emotional factor. While it currently sounds impossible to have "machines with emotions," it is quite conceivable to artificially simulate some emotions in machine learning. This paper presents a modified backpropagation (BP) learning algorithm, namely, the emotional backpropagation (EmBP) learning algorithm. The new algorithm has additional emotional weights that are updated using two additional emotional parameters: anxiety and confidence. The proposed "emotional" neural network will be implemented to a facial recognition problem, and the results will be compared to a similar application using a conventional neural network. Experimental results show that the addition of the two novel emotional parameters improves the performance of the neural network yielding higher recognition rates and faster recognition time.

Advances in digital technologies have allowed us to generate more images than ever. Images of scanned documents are examples of these images that form a vital part in digital libraries and archives. Scanned degraded documents contain background noise and varying contrast and illumination, therefore, document image binarisation must be performed in order to separate foreground from background layers. Image binarisation is performed using either local adaptive thresholding or global thresholding; with local thresholding being generally considered as more successful. This paper presents a novel method to global thresholding, where a neural network is trained using local threshold values of an image in order to determine an optimum global threshold value which is used to binarise the whole image. The proposed method is compared with five local thresholding methods, and the experimental results indicate that our method is computationally cost-effective and capable of binarising scanned degraded documents with superior results.

This paper demonstrates how different scientific disciplines can be successfully merged for efficient real life applications. We propose a novel approach to a social science application using artificial intelligence, by suggesting a neural network designto anticipate or predict people’s perceptions regarding the Cyprus conflict and the peace mediation process.Our novel model is based on associating people’s views and thoughts on critical issues related to the conflict together with their anticipation for securing a peace treaty by year 2020. Our database is our own and has been collected through completed surveys by the international relations department students at the Near East University. The obtained digitally-coded values of the entire database as well as the proposed associative neural predicting model can be further used in training and testing the neural model, which certainly waives the way for further research in this rare application area for artificial intelligence. [ABSTRACT FROM AUTHOR]

Artificial intelligence and its diverse applications are examples of emerging new technologies that have so far been shown to be successful in merging scientific applications. Generally, intelligent systems outperform their traditional counterparts in solving non-linear tasks. Artificial neural network (ANN) models are usually designed and used to arbitrate these non-linear problems; as they mimic the structure and function of a biological brain. In this paper, an intelligent classification system is proposed to decide the result of a routine and laborious civil engineering quality control process. The ANN model is specifically designed, implemented and tested in order to classify the compressive strength grade of different concrete mixes as low, normal or high strength. Concrete elements of varying compressive strength classes and qualities, are required to be used for different purposes and under different environmental conditions. The grade of the concrete’s strength is highly dependent on many non-linear factors and it is often conventionally determined by using civil engineering methods involving the destruction of concrete samples. Our aim is to classify the concrete strength without destructing any samples. Experimental results in this work show high efficiency in correctly classifying the compressive strength. [ABSTRACT FROM AUTHOR]

This paper presents a novel application in the emerging field of computational politics. Here, we anticipate American congressional voting outcome using support vector machines (SVM) and back propagation learning algorithm neural network models. Our proposed method successfully associates opinions of American congress members on defined national issues with their political party affiliation as republican or democrat, thus providing a artificially intelligent anticipation system of the congressional voting outcome based on previous knowledge of how the congress members perceive national issues. Knowledge is obtained from existing congressional records which are unclassified and available online for research purposes. The obtained experimental results suggest that our novel method and application can be further applied to similar voting polls in order to anticipate the party members voting inclination. [ABSTRACT FROM AUTHOR]

The thought that machines could have emotions has so far been unacceptable by humans. However, few decades ago the idea of machines with intelligence was also ridiculed, but today not only we have developed intelligent machines, but we are also exploring many areas for their application with great success. We have always overlooked the emotional factors during machine learning and decision making; however, it is quite conceivable to artificially model some emotions in machine learning. This paper presents four emotional neural network models (EmNNs) that are based on the emotional back propagation (EmBP) learning algorithm. The EmNNs have emotional weights and two emotional parameters; anxiety and confidence, which are updated during learning. The four EmNN models differ in their topologies as a result of different input data coding methods. The performance of the EmNN models when applied to a blood cell type identification problem will be evaluated. Experimental results show that the additional emotional parameters and weights in all four models improve the identification rate as well as the classification time. [ABSTRACT FROM AUTHOR]

The idea of machines having emotions sounds like science fiction, however, few decades ago the idea of machines with intelligence seemed also like fiction, but today we are developing intelligent machines with successful applications. We have always overlooked the emotional factors during machine learning and decision making; however, it is quite conceivable to artificially model certain emotions in machine learning. This paper presents an emotional neural network (EmNN) that is based on the emotional back propagation (EmBP) learning algorithm. The EmNN has emotional weights and two emotional parameters; anxiety and confidence, which are updated during learning. The performances of the EmNN and a conventional BP-based neural network, using two topologies for each network, will be compared when applied to a blood cell type identification problem. Experimental results show that the additional emotional parameters and weights improved the identification rate as well as the classification time. [ABSTRACT FROM AUTHOR]

Credit scoring is one of the key analytical techniques in credit risk evaluation which has been an active research area in financial risk management. This paper presents a credit risk evaluation system that uses a neural network model based on the back propagation learning algorithm. We train and implement the neural network to decide whether to approve or reject a credit application, using seven learning schemes and real world credit applications from the Australian credit approval datasets. A comparison of the system performance under the different learning schemes is provided, furthermore, we compare the performance of two neural networks; with one and two hidden layers following the ideal learning scheme. Experimental results suggest that neural networks can be effectively used in automatic processing of credit applications. [ABSTRACT FROM AUTHOR]