Search

A medical database of 589 women thought to have osteoporosis has been analyzed. A hybrid algorithm consisting of Artificial Neural Networks and Genetic Algorithms was used for the assessment of osteoporosis. Osteoporosis is a common disease, especially in women, and a timely and accurate diagnosis is important for avoiding fractures. In this paper, the 33 initial osteoporosis risk factors are reduced to only 2 risk factors by the proposed hybrid algorithm. That leads to faster data analysis procedures and more accurate diagnostic results. The proposed method may be used as a screening tool that assists surgeons in making an osteoporosis diagnosis.

We generalize the clustering theorem by Lanchier (2012) on the infinite one-dimensional integer lattice ℤ for the constrained voter model and the two-feature two-trait Axelrod model to multitype biased models with confidence threshold. Types are represented by a connected graph Γ, and dynamics is described as follows. At independent exponential times for each site of type i, one of the neighboring sites is chosen randomly, and its type j is adopted if i, j are adjacent on Γ. Starting from a product measure with positive type densities, the clustering theorem dictates that fluctuation and clustering occurs, i.e., each site changes type at arbitrary large times and looking at a finite interval consensus is reached asymptotically with probability 1, if there is one or two vertices of Γ adjacent to all other vertices but each other. Additionally, we propose a simple definition of clustering on a finite set, in which case one can apply the clustering theorem that justifies known previous claims.

We present mathematical models that describe individual neural networks of the Central Nervous System. Three cases are examined, varying in each case the values of the refractory period and the synaptic delay of a neuron. In the case where both the refractory period and the synaptic delay are bigger than one, we split the population of neurons into sub-groups with their own distinct synaptic delay. It is shown that the proposed approach describes the neural activity of the network efficiently, especially in the case mentioned above. Various examples with different network parameters are presented to investigate the network’s behavior.

This study examines Probabilistic Neural Network (PNNs) models in terms of their classification efficiency in the Vesicoureteral Reflux (VUR) disease. PNNs were developed for the estimation of VUR risk factor. The obtained results lead to the conclusion that in this case the PNNs can be potentially used towards VUR risk prediction. There is a redundancy in the diagnostic factors, so pruned PNN was used in order to evaluate the contribution of each one. Moreover, the Receiver Operating Characteristic (ROC) analysis was used in order to select the most significant factors for the estimation of VUR risk. The results of the pruned PNN model were found in accordance with the ROC analysis. The obtained results may support that a number of the diagnostic factors that are recorded in patient's history may be omitted with no compromise to the fidelity of clinical evaluation.

Abdominal pain in childhood is a common cause of emergency admission in hospital. Its assessment and diagnosis, especially the decision about performing a surgical operation of the abdomen, continues to be a clinical challenge. This study investigates the possibilities of applying state of the art computational intelligence methods for the analysis of abdominal pain data. Specifically, the application of a Genetic Clustering Algorithm and of the Random Forests algorithm (RF) is explored. Clinical appendicitis prediction involves the estimation of at least 15 clinical and laboratory factors (features). The contribution of each factor to the prediction is not known. Thus, the goal of abdominal pain data analysis is not restricted to the classification of the data, but includes the exploration of the underlying data structure. In this study a genetic clustering algorithm is employed for the later task and its performance is compared to a classical K-means clustering approach. For classification purposes, tree methods are frequently used in medical applications since they often reveal simple relationships between variables that can be used to interpret the data. They are however very prone to overfitting problems. Random Forests, applied in this study, is a novel ensemble classifier which builds a number of decision trees to improve the single tree classifier generalization ability. The application of the above mentioned algorithms to real data resulted in very low error rates, (less than 5%), indicating the usefulness of the respective approach. The most informative diagnostic features as proposed by the algorithms are in accordance with known medical expert knowledge. The experimental results furthermore confirmed both, the greater ability of the genetic clustering algorithm to reveal the underlying data patterns as compared to the K-means approach and the effectiveness of RF-based diagnosis as compared to a single decision tree algorithm.

In the current paper we present an integrated genetic programming environment with a graphical user interface (GUI), called jGPModeling. The jGPModeling environment was developed using the JAVA programming language, and is an implementation of the steady-state genetic programming algorithm. That algorithm evolves tree based structures that represent models of input --- output relation of a system. During the design and implementation of the application, we focused on the execution time optimization and tried to limit the bloat effect. In order to evaluate the performance of the jGPModeling environment, two different real world system modeling tasks were used.

In this contribution we present a novel software tool that can be used to implement intelligent signal processing techniques. BSPS which stands for (Bio magnetic Signal Processing Software) is either a standalone application, or it can be embedded in the kernel of an Artificial Intelligence tool, since it performs signal classification. It can be used to analyze both linear and non linear time series, deterministic and stochastic processes. We used our application in order to analyze and predict the behavior of fetal heart during several phases of women pregnancy. By using evolutionary techniques like genetic algorithms, the theory of Kalman filtering, the Multi-model Partitioning Theory, the Approximate Entropy and other approaches we managed the accomplishment of our objectives.