Search

Hand gesture for communication has proven effective for humans, and active research is ongoing in replicating the same success in computer vision systems. Human-computer interaction can be significantly improved from advances in systems that are capable of recognizing different hand gestures. In contrast to many earlier works, which consider the recognition of significantly differentiable hand gestures, and therefore often selecting a few gestures from the American Sign Language (ASL) for recognition, we propose applying deep learning to the problem of hand gesture recognition for the whole 24 hand gestures obtained from the Thomas Moeslund's gesture recognition database. We show that more biologically inspired and deep neural networks such as convolutional neural network and stacked denoising autoencoder are capable of learning the complex hand gesture classification task with lower error rates. The considered networks are trained and tested on data obtained from the above-mentioned public database; results comparison is then made against earlier works in which only small subsets of the ASL hand gestures are considered for recognition. [ABSTRACT FROM AUTHOR]

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]

Our thirst for progress as humans is reflected by our continuous research activities in different areas leading to many useful emerging applications and technologies. Artificial intelligence and its applications are good examples of such explored fields with varying expectations and realistic results. Generally, artificially intelligent systems have shown their capability in solving real-life problems; particularly in non-linear tasks. Such tasks are often assigned to an artificial neural network (ANN) model to arbitrate as they mimic the structure and function of a biological brain; albeit at a basic level. In this paper, we investigate a newly emerging application area for ANNs; namely civil engineering. We design, implement and test an ANN model to predict and classify the compressive strength of different concrete mixes into low, moderate or high strength. Traditionally, the performance of concrete is affected by many non-linear factors and testing its strength comprises a destructive procedure of concrete samples. Numerical results in this work show high efficiency in correctly classifying the compressive strength, thus making it possible to use in real-life applications. [ABSTRACT FROM AUTHOR]

This work presents the diagnosis of iris nevus using a convolutional neural network (CNN) and deep belief network (DBN). Iris nevus is a pigmented growth (tumor) found in the front of the eye or around the pupil. It is seen that racial and environmental factors affect the iris color (e.g., blue, hazel, brown) of patients; hence, pigmented growths may be masked in the eye background or iris. In this work, some image processing techniques are applied to images to reinforce areas of interests in them, after which the considered classifiers are trained. We describe the automated diagnosis of iris nevus using neural network-based systems for the classification of eye images as "nevus affected" and "unaffected". Recognition rates of 93.35% and 93.67% were achieved for the CNN and DBN, respectively. Hence, the systems described in this work can be used satisfactorily for diagnosis or to reinforce the confidence in manual-visual diagnosis by medical experts. [ABSTRACT FROM AUTHOR]

In this research work, we have implemented an intelligent system for diagnosis of diabetic retinopathy. Diabetic retinopathy is a damage caused by diabetes to the retinal blood vessels. This causes the leak of blood and other fluid that resulted into swelling of retina tissue and cloudy vision. This can be classified into two; non-proliferative diabetic retinopathy and proliferative diabetic retinopathy. The dataset used for the implementation of this intelligent system is obtained from the freely available UCI machine learning repository. This system will aid physicians to accurately diagnose the disease. Such a system will make the diagnosis faster, accurate and easier as compared to manual diagnosis. Our novel system uses a feedforward neural network trained with backpropagation neural network. The results obtained in this work are compared with previously proposed systems using the same dataset. Experimental results indicate that our novel system outperforms the other systems in diagnosing diabetic retinopathy. [ABSTRACT FROM AUTHOR]

The relationship between environmental pollution and economic growth has lately been the focus of discussion among policy makers and scientists worldwide. In Turkey, the agriculture sector is a major contributor to the national economy and consequently growth in agriculture leads to economic growth; which in turn affects pollution levels. In this paper, we present a novel application of neural networks based on using the simple and yet efficient back propagation learning algorithm. We estimate the carbon dioxide (CO 2 ) emission levels by approximating the non-linear relationship between agricultural factors and alterations in CO 2 emission levels. We use a public Turkish dataset spanning 1968-2010 and showing recorded major agricultural and economical indictors and the level of CO 2 . The experimental results indicate that such approximation is successfully possible and encouraging to be used in more similar non-linear applications. [ABSTRACT FROM AUTHOR]

Document Segmentation is a process that aims to filter documents while identifying certain regions of interest. Generally, the regions of interest include texts, graphics (image occupied regions) and the background. This paper presents a novel top-bottom approach to perform document segmentation using texture features that are extracted from the specified/selected documents. A mask of suitable size is used to summarize textural features, and statistical parameters are captured as blocks in document images. Four textural features that are extracted from masks using the gray level co-occurrence matrix (glcm) include entropy, contrast, energy and homogeneity. Furthermore, two statistical parameters extracted from corresponding masks are the modal and median pixel values. The extracted attributes allow the classification of each mask or block as text, graphics, and background. A feedforward network is trained on the 6 extracted attributes, using documents obtained from a public database ; an error rate of 15.77 % is achieved. Furthermore, it is shown that this novel approach produces promising performance in segmenting documents and is expected to be significantly efficient for content-based information retrieval systems. Detection of duplicate documents within large databases is another potential area of application. [ABSTRACT FROM AUTHOR]

Artificial neural networks have found applications in various areas of medical diagnosis. The capability of neural networks to learn medical data, mining useful and complex relationships that exist between attributes has earned it a major domain in decision support systems. This paper proposes a fast automatic system for the diagnosis of disk hernia and spondylolisthesis using biomechanical features and neural network. Such systems as described within this work allow the diagnosis of new cases using trained neural networks; patients are classified as either having disk hernia, spondylolisthesis, or normal. Generally, both disk hernia and spondylolisthesis present similar symptoms; hence, diagnosis is prone to inter-misclassification error. This work is significant in that the proposed systems are capable of making fast decisions on such somewhat difficult diagnoses with reasonable accuracies. Feedforward neural network and radial basis function networks are trained on data obtained from a public database. The results obtained within this research are promising and show that neural networks can find applications as efficient and effective expert systems for the diagnosis of disk hernia and spondylolisthesis. [ABSTRACT FROM AUTHOR]

The analysis of blood cells in microscope images can provide useful information concerning the health of patients; however, manual classification of blood cells is time-consuming and susceptible to error due to the different morphological features of the cells. Therefore, a fast and automated method for identifying the different blood cells is required. In this paper, we investigate the use of different neural network models for the purpose of cell identification. The neural models are based on the back propagation learning algorithm and differ in design according to the way data features are extracted from the cell microscopic images. Three different topologies of neural networks are investigated, and a comparison between these models is drawn. Experimental results suggest that the proposed method performs well in identifying blood cell types regardless of their irregular shapes, sizes, and orientation. [ABSTRACT FROM AUTHOR]

Emotional processes and responses are biological and psychological processes in humans. The modelling of these biological processes in machines is considered a challenging and often controversial task in the field of bio-inspired computing. This is because of the complexity of emotional processes and rarity of available emotional computational models. However, research into possible mechanisms that allow emotional phenomena to influence cognitive and behavioural processes and how they can be implemented in robots has recently been gaining momentum with successful results in modelling emotions within systems. The motive for this trend is that future machines and robots will be capable of making better decisions if their cognition is enhanced by emotions. We present in this paper an emotional neural network based on an improved emotional back propagation (EmBP) learning algorithm. The modified algorithm, namely the iEmBP learning algorithm, models within its configuration three emotional responses: anxiety, confidence and impression. The proposed iEmBP-based emotional neural network will be implemented to a blood cell type identification problem, and its performance will be compared to two other neural networks. Experimental results show that the iEmBP-based emotional neural network has improved performance when compared to the EmBP-based network, and significantly outperforms the conventional back propagation (BP)-based neural networks in recognition results and time cost. [ABSTRACT FROM AUTHOR]

Abstract: Credit scoring and evaluation is one of the key analytical techniques in credit risk evaluation which has been an active research area in financial risk management. Artificial neural networks (NNs) have been considered to be accurate tools for credit analysis among others in the credit industry. Lately, emotional neural networks (EmNNs) have been suggested and applied successfully for pattern recognition. In this paper we investigate the efficiency of EmNNs and compare their performance to conventional NNs when applied to credit risk evaluation. In total 12 neural networks; based equally on emotional and conventional neural models; are arbitrated under three learning schemes to classify whether a credit application is approved or declined. The learning schemes differ in the ratio of training-to-validation data used during training and testing the neural networks. The emotional and conventional neural models are trained using real world credit application cases from the Australian credit approval datasets which has 690 cases; each case with 14 numerical attributes; based on which an application is accepted or rejected. The performance of the 12 neural networks will be evaluated using certain criteria. Experimental results suggest that both emotional and conventional neural models can be used effectively for credit risk evaluations, however the emotional models outperform their conventional counterparts in decision making speed and accuracy, thus, making them ideal for implementation in fast automatic processing of credit applications. [Copyright &y& Elsevier]

Abstract: 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. [ABSTRACT FROM AUTHOR]

Abstract: This paper describes a credit risk evaluation system that uses supervised neural network models based on the back propagation learning algorithm. We train and implement three neural networks to decide whether to approve or reject a credit application. Credit scoring and evaluation is one of the key analytical techniques in credit risk evaluation which has been an active research area in financial risk management. The neural networks are trained using real world credit application cases from the German credit approval datasets which has 1000 cases; each case with 24 numerical attributes; based on which an application is accepted or rejected. Nine learning schemes with different training-to-validation data ratios have been investigated, and a comparison between their implementation results has been provided. Experimental results will suggest which neural network model, and under which learning scheme, can the proposed credit risk evaluation system deliver optimum performance; where it may be used efficiently, and quickly in automatic processing of credit applications. [Copyright &y& Elsevier]

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]

In our attempts to model human intelligence by mimicking the brain structure and function, we overlook an important aspect in human cognition, which is the emotional factor. It may currently sound unthinkable to have emotional machines; however, it is possible to simulate certain artificial emotions with the aim of improving machine learning. This paper investigates the efficiency of an emotional neural network, which uses a modified back propagation learning algorithm. The modifed algorithm, namely the emotional BP learning algorithm, has two emotional parameters, anxiety and confidence, that are modeled during machine learning and decision making. The emotional neural network will be implemented to a facial recognition problem using images of faces with different orientations and contrast levels, and its performance will be compared to that of a conventional neural network. Experimental results suggest that artificial emotions can be successfully modeled and efficiciently implemented to improve neural networks learning and generaliztion. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]