David Gil

Review: Application of artificial neural networks in the diagnosis of urological dysfunctions

In this article, we evaluate the work out of some artificial neural network models as tools for support in the medical diagnosis of urological dysfunctions. We develop two types of unsupervised and one supervised neural network. This scheme is meant to help the urologists in obtaining a diagnosis for complex multi-variable diseases and to reduce painful and costly medical treatments since neurological dysfunctions are difficult to diagnose. The clinical study has been carried out using medical registers of patients with urological dysfunctions. The proposal is able to distinguish and classify between ill and healthy patients.

Internet of Things: A Review of Surveys Based on Context Aware Intelligent Services.

The Internet of Things (IoT) has made it possible for devices around the world to acquire information and store it, in order to be able to use it at a later stage. However, this potential opportunity is often not exploited because of the excessively big interval between the data collection and the capability to process and analyse it. In this paper, we review the current IoT technologies, approaches and models in order to discover what challenges need to be met to make more sense of data. The main goal of this paper is to review the surveys related to IoT in order to provide well integrated and context aware intelligent services for IoT. Moreover, we present a state-of-the-art of IoT from the context aware perspective that allows the integration of IoT and social networks in the emerging Social Internet of Things (SIoT) term.

Predicting seminal quality with artificial intelligence methods

Fertility rates have dramatically decreased in the last two decades, especially in men. It has been described that environmental factors, as well as life habits, may affect semen quality. Artificial intelligence techniques are now an emerging methodology as decision support systems in medicine. In this paper we compare three artificial intelligence techniques, decision trees, Multilayer Perceptron and Support Vector Machines, in order to evaluate their performance in the prediction of the seminal quality from the data of the environmental factors and lifestyle. To do that we collect data by a normalized questionnaire from young healthy volunteers and then, we use the results of a semen analysis to asses the accuracy in the prediction of the three classification methods mentioned above. The results show that Multilayer Perceptron and Support Vector Machines show the highest accuracy, with prediction accuracy values of 86% for some of the seminal parameters. In contrast decision trees provide a visual and illustrative approach that can compensate the slightly lower accuracy obtained. In conclusion artificial intelligence methods are a useful tool in order to predict the seminal profile of an individual from the environmental factors and life habits. From the studied methods, Multilayer Perceptron and Support Vector Machines are the most accurate in the prediction. Therefore these tools, together with the visual help that decision trees offer, are the suggested methods to be included in the evaluation of the infertile patient.

Associative Self-Organizing Map

Simulation hypothesis, Cognitive modelling. Abstract: We present a study of a novel variant of the Self-Organizing Map (SOM) called the Associative Self- Organizing Map (A-SOM). The A-SOM is similar to the SOM and thus develops a representation of its input space, but in addition it also learns to associate its activi ty with the activity of one or several external SOMs. The A-SOM has relevance in e.g. the modelling of expectations in one modality due to the activity invoked in another modality, and in the modelling of the neuroscientific simulation hypothesis. The paper presents the algorithm generalized to an arbitrary number of associated activities together with simulation results to find out about its performance and its ability to generalize t o new inputs that it has not been trained on. The simulation results were very encouraging and confirmed the a bility of the A-SOM to learn to associate the rep- resentations of its input space with the representations of the input spaces developed in two connected SOMs. Good generalization ability was also demonstrated.

A Computational Architecture Based on RFID Sensors for Traceability in Smart Cities

Information Technology and Communications (ICT) is presented as the main element in order to achieve more efficient and sustainable city resource management, while making sure that the needs of the citizens to improve their quality of life are satisfied. A key element will be the creation of new systems that allow the acquisition of context information, automatically and transparently, in order to provide it to decision support systems. In this paper, we present a novel distributed system for obtaining, representing and providing the flow and movement of people in densely populated geographical areas. In order to accomplish these tasks, we propose the design of a smart sensor network based on RFID communication technologies, reliability patterns and integration techniques. Contrary to other proposals, this system represents a comprehensive solution that permits the acquisition of user information in a transparent and reliable way in a non-controlled and heterogeneous environment. This knowledge will be useful in moving towards the design of smart cities in which decision support on transport strategies, business evaluation or initiatives in the tourism sector will be supported by real relevant information. As a final result, a case study will be presented which will allow the validation of the proposal.

Semen Parameters Can Be Predicted from Environmental Factors and Lifestyle Using Artificial Intelligence Methods

ABSTRACT Fertility rates have dramatically decreased in the last two decades, especially in men. It has been described that environmental factors as well as life habits may affect semen quality. In this paper we use artificial intelligence techniques in order to predict semen characteristics resulting from environmental factors, life habits, and health status, with these techniques constituting a possible decision support system that can help in the study of male fertility potential. A total of 123 young, healthy volunteers provided a semen sample that was analyzed according to the World Health Organization 2010 criteria. They also were asked to complete a validated questionnaire about life habits and health status. Sperm concentration and percentage of motile sperm were related to sociodemographic data, environmental factors, health status, and life habits in order to determine the predictive accuracy of a multilayer perceptron network, a type of artificial neural network. In conclusion, we have developed an artificial neural network that can predict the results of the semen analysis based on the data collected by the questionnaire. The semen parameter that is best predicted using this methodology is the sperm concentration. Although the accuracy for motility is slightly lower than that for concentration, it is possible to predict it with a significant degree of accuracy. This methodology can be a useful tool in early diagnosis of patients with seminal disorders or in the selection of candidates to become semen donors.

2012 Special Issue: Using GNG to improve 3D feature extraction-Application to 6DoF egomotion

Several recent works deal with 3D data in mobile robotic problems, e.g. mapping or egomotion. Data comes from any kind of sensor such as stereo vision systems, time of flight cameras or 3D lasers, providing a huge amount of unorganized 3D data. In this paper, we describe an efficient method to build complete 3D models from a Growing Neural Gas (GNG). The GNG is applied to the 3D raw data and it reduces both the subjacent error and the number of points, keeping the topology of the 3D data. The GNG output is then used in a 3D feature extraction method. We have performed a deep study in which we quantitatively show that the use of GNG improves the 3D feature extraction method. We also show that our method can be applied to any kind of 3D data. The 3D features obtained are used as input in an Iterative Closest Point (ICP)-like method to compute the 6DoF movement performed by a mobile robot. A comparison with standard ICP is performed, showing that the use of GNG improves the results. Final results of 3D mapping from the egomotion calculated are also shown.

Review: Using support vector machines in diagnoses of urological dysfunctions

Urinary incontinence is one of the largest diseases affecting between 10% and 30% of the adult population and an increase is expected in the next decade with rising treatment costs as a consequence. There are many types of urological dysfunctions causing urinary incontinence, which makes cheap and accurate diagnosing an important issue. This paper proposes a support vector machine (SVM) based method for diagnosing urological dysfunctions. 381 registers collected from patients suffering from a variety of urological dysfunctions have been used to ensure the (generalization) performance of the decision support system. Moreover, the robustness of the proposed system is examined by fivefold cross-validation and the results show that the SVM-based method can achieve an average classification accuracy at 84.25%.

Collaborative building of behavioural models based on internet of things

A framework for distributing the computation among the objects of IoT is proposed.The proposal enables building collaborative models for achieving a common goal.This approach allows extending the computation capabilities to a closed and controlled environment.Healthcare applications can benefit from this to preserve user privacy. Display Omitted This paper proposes a new framework that takes advantage of the computing capabilities provided by the Internet of Thing (IoT) paradigm in order to support collaborative applications. It looks at the requirements needed to run a wide range of computing tasks on a set of devices in the user environment with limited computing resources. This approach contributes to building the social dimension of the IoT by enabling the addition of computing resources accessible to the user without harming the other activities for which the IoT devices are intended. The framework mainly includes a model of the computing load, a scheduling mechanism and a handover procedure for transferring tasks between available devices. The experiments show the feasibility of the approach and compare different implementation alternatives.

Flexible Framework for Real-Time Embedded Systems Based on Mobile Cloud Computing Paradigm

The development of applications as well as the services for mobile systems faces a varied range of devices with very heterogeneous capabilities whose response times are difficult to predict. The research described in this work aims to respond to this issue by developing a computational model that formalizes the problem and that defines adjusting computing methods. The described proposal combines imprecise computing strategies with cloud computing paradigms in order to provide flexible implementation frameworks for embedded or mobile devices. As a result, the imprecise computation scheduling method on the workload of the embedded system is the solution to move computing to the cloud according to the priority and response time of the tasks to be executed and hereby be able to meet productivity and quality of desired services. A technique to estimate network delays and to schedule more accurately tasks is illustrated in this paper. An application example in which this technique is experimented in running contexts with heterogeneous work loading for checking the validity of the proposed model is described.