Search

Publisher Summary This chapter provides an overview of the dynamic ring architecture. It presents the architecture for the emulation of multi-layered perceptrons with backpropagation learning. Each processor contains three communication ports and is also connected to a common bus. At each particular time slice, a layer is emulated and only two ports are activated simultaneously—one for the input and the other for the output. The bus serves both for fetching instructions and exchanging data with the array controller and host. This structure has several advantages, such as: (1) it is modular, (2) easily expandable, and (3) efficient in the use of computing resources. Two concepts embodied in the architecture are worth mentioning: (1) virtual neurons—wherein each processor may actually emulate several physical neurons. (2) Virtual layers—wherein each processor and the whole architecture emulate a particular neural network layer depending on the time-slice considered. Because of the virtual layer capability of the architecture, it is clear that a two-dimensional structure is mapped to a one-dimensional architecture.

Associative memories can be modeled theoretically from neural networks using the feature extractor and a MAXNET. However, from the practical standpoint, the feature extractor has the inconvenience of needing complex operations and/or analog weight values, while the MAXNET is difficult to implement due to the high interconnectivity and analog weight values. The proposed solution is to use an encoding scheme which performs the Hamming distance calculation on encoded vectors, equivalent to a real-valued distance calculation. A memory compression technique is then applied to reduce the number of bits. For the MAXNET, synchronous digital circuit techniques are used. The resulting associative memory processors are simple, modular, and not too costly in terms of logic. The proposed content addressable memory matches data according to that which produces a minimum distance between the searched key and each of the stored record's fields. Each field's relevance in the search operation is controlled using a mask. >

10 pages, 9 figures, 3 tables, Fish otolith morphology has been closely related to landmark selection in order to establish the most discriminating points that can help to differentiate or find common characteristics in sets of otolith images. Fourier analysis has traditionally been used to represent otolith images, since it can reconstruct a version of the contour that is close to the original by choosing a reduced set of harmonic terms. However, it is difficult to locate the contour’s singularities from this spectrum. As an alternative, wavelet transform and curvature scale space representation allow us to quantify the irregularities of the contour and determine its precise position. These properties make these techniques suitable for pattern recognition purposes, ageing, stock determination and species identification studies. In the present study both techniques are applied and used in an otolith classification system that shows robustness against affine image transformations, shears and the presence of noise. The results are interpreted and discussed in relation to traditional morphology studies., The current work was supported by the Spanish project MYCYT TIC2000-0376-P4-04.

The age decay of two indicators of the stellar magnetic activity (λ 2800 Mgii emission flux and λ 10830 Hei equivalent width) have been studied for field solar-type stars. The Li abundance has been used, in most of the cases, as a stellar age indicator. A calibrated decay law for Mgii has been determined and compared with a similar one, recently published, for the Caii K emission. The greater scatter in the Hei results is atributed to the different rotation rates.

A numerical procedure is described to calculate the parameters of the equivalent circuit of a solar cell, based on the application of algorithms to optimise nonlinear functions defining the difference between experimental characteristics and the theoretical model. The authors have obtained empirical data from dark I(V) characteristics. A study of the method to obtain the initial solution is also included. Results obtained for space solar cells and commercial cells (terrestrial use) are given. Modifications of the commonly used equivalent circuit model of solar cells are suggested.

A microprocessor-based solar cell standard characteristics measurement system is described. Data aquisition and digital conversion of the current-to-voltage characteristics and the spectral response allows the performance of several operations as averaging, storage, minicomputer connection, and parameter determination of the theoretical models introduced. Several results are shown concerning the accuracy of the method on the determination of series resistance, reverse saturation current, and the minority carriers lifetime on the base region of solar cells.

2014 A new and simple technique to evaluate the series resistance of a solar cell is described. This procedure only needs dark I(V) measurements and a simple experimental-arrangement including a calibrated standard resistor. Comparison with other commonly used methods is also discussed. Revue Phys. Appl. 18 (1983) 565-567 SEPTEMBRE 1983, : Classification Physics Abstracts 73.40L The series resistance of a solar cell is a parameter of special interest because of its influence in the maximum available power and fill factor. It is also a parameter that indicates in some way the quality of the device and can be used as production test There exists a number of methods to evaluate the series resistance of the cells based on I(V) characteristics, most of them using more than one I(V) curve (Refs. 1, 2). The new method is based on the dark I(V) characteristics model that can be written with the help of figure 1, where R. is the series resistance, Rsh is the shunt resistance and Dl and D2 are the two diodes accounting for Shockley diffusion term (Dl), and Space Charge Region recombination term (D2). through Dl and the second, i = 2, is the current that flows through D2. The last term takes into account the shunt current which can be an important effect for low bias levels. Our method is based in the experimental arrangement shown in figure 2 where only the addition of an external calibrated resistor Rext is needed Obviously, the model given in equation 1 is still valid and only RS must-be replaced by (Rs + Rext). Series resistance effects appears for the higher voltage values where the term given by i = 2 and the last one can be neglected in front of the diffusion term modified by the series resistance effect.

The work here reported is the result of an analytic and experimental investigation on the use of the optimum topology dc-to-dc switching converter (Cuk converter) in the development of panel-to- -accumulator interfaces. As a result a CMOS digital design of a maximum power point tracker acting on a Cuk-type PWM shunt regulator is presented. The results reported in the paper can contribute to better design this Kind of interfaces in medium-low power solar plants.

The circuit models commonly used for the I(v) characteristics in order to determine the equivalent circuit pa. rameters of a solar cell fail when terrestrial textured surface solar cells are concerned with high percentage of metal covered area. Two alternatives are proposed, first is an empirical approach in which a parameter will be considered non constant and the second alternative is to include a new exponential term in the I(v) characteristic.

A methodology for evaluation of band gap narrowing (BGN) in the heavily doped emitter region of solar cells, using independent measurements of the emitter and base lifetimes and relaxation time is presented. The method is based on the theory developed by F.A. Lind-holm, using the charge control model. The measurements of τB and τE has been made using a transient laser induced photocurrent technique. Also is presented a discussion on the Open Circuit Voltage Decay (O.C.V.D.) method in order to measure the relaxation time τm.

FIPSOC (field programmable system on chip) is a novel device shown to be suitable for rapid prototyping of electronic systems. After a description of its architecture and associated development tools, its distinguishing features are highlighted. In particular, integration of a microprocessor, programmable logic and configurable analog channels in the same chip provides a monolithic platform with capability to prototype complete systems. The integrated development software and chip capabilities offer low-cost emulation on the target device, hardware and software emulation, and integrated real-time probing. An application example of a DC motor controller illustrates the benefits in cost and development time that FIPSOC can provide.

In order to prevent and reduce water pollution, promote a sustainable use, protect the environment and enhance the status of aquatic ecosystems, this article deals with the application of advanced mathematical techniques designed to aid in the management of records of different water quality monitoring networks. These studies include the development of a software tool for decision support, based on the application of fuzzy logic techniques, which can indicate water quality episodes from the behaviour of variables measured at continuous automatic water control networks. Using a few physicalchemical variables recorded continuously, the expert system is able to obtain water quality phenomena indicators, which can be associated, with a high probability of cause-effect relationship, with human pressure on the water environment, such as urban discharges or diffuse agricultural pollution. In this sense, at the proposed expert system, automatic water quality control networks complement manual sampling of official administrative networks and laboratory analysis, providing information related to specific events (discharges) or continuous processes (eutrophication, fish risk) which can hardly be detected by discrete sampling.

This paper describes a new self-adaptive hardware architecture with fault tolerance capabilities and a development system that allows the creation of applications. This bioinspired architecture is based on an array of cells with capacity for parallel processing, which implements in a distributed way self-adaptive capabilities, like self-routing, self-placement and runtime self-configuration. This cell array together with a component-level routing constitutes a SANE (Self-Adaptive Networked Entity). An integrated development environment and a physical prototype based on two FPGA boards has been built in order to assess the features of the proposed architecture.

FATE is a project funded by the European Union under the program CIP/ICT-PSP with the main objective of organizing a big pilot on the automatic falls detection in aging people living at home. Automatic detection of falls is done in indoors and outdoors conditions, and in both cases the detection generates an alarm sent to a call center. The detection system is designed around a sensor sub-system based on accelerometers and gyroscopes able to detect falls with a high reliability. The complete system is based on a communications layer based in ZigBee and Bluetooth protocols. The gateway for sending the alarm to the call center is a mobile phone. Pilots are organized in three different countries (Spain, Italy and Ireland) where different models of health service and implemented call centers are available. Pilots duration will be one year, involving 175 users and one of the main final objectives is to gain experience with the integration of an automatic fall detection service in an already care/health existing service.

Electron-beam detecting devices for IC controllability purposes are presented in this paper. For an electron-beam IC controlling cell to be practical, it should detect the beam at normal observation beam energies (less than 2 kV), be small in size, and have a short response time. Logic state generation has been experimentally achieved by charging a MOS transistor floating gate or injecting current to a parasitic bipolar transistor floating base. To improve speed, electron beam sensitive CMOS devices (floating-gate MOST, floating-base parasitic BJT) and amplifiers have been designed and manufactured. Simulations show speed ranges of microseconds.

Human movement analysis is a field of wide interest since it enables the assessment of a large variety of variables related to quality of life. Human movement can be accurately evaluated through Inertial Measurement Units (IMU), which are wearable and comfortable devices with long battery life. The IMU’s movement signals might be, on the one hand, stored in a digital support, in which an analysis is performed a posteriori. On the other hand, the signal analysis might take place in the same IMU at the same time as the signal acquisition through online classifiers. The new sensor system presented in this paper is designed for both collecting movement signals and analyzing them in real-time. This system is a flexible platform useful for collecting data via a triaxial accelerometer, a gyroscope and a magnetometer, with the possibility to incorporate other information sources in real-time. A μSD card can store all inertial data and a Bluetooth module is able to send information to other external devices and receive data from other sources. The system presented is being used in the real-time detection and analysis of Parkinson’s disease symptoms, in gait analysis, and in a fall detection system

Otoliths are calcified structures in the inner ear of fish. The otolith shape changes during a fish's lifetime are particular to individual species. Then, otolith shape can be used to differentiate between species and between fish of the same species. Fishery research has used the growth patterns (i.e. rings) found in these calcified structures to estimate the age of individual fish. However, many factors, such as seasonal variations, temperature, habitat and food, may influence otolith growth. Then, the manual classification of otoliths remains a difficult task, and even experienced examiners can give inaccurate age estimation. We propose to use statistical learning techniques (artificial neural networks) to improve and automate the process. ANN classification methods are evaluated and used with some real otolith databases, giving significant results

The final publication is available at Springer via https://doi.org/10.1007/978-3-319-59147-6_30 Freezing of gait (FOG) is one of the most incapacitating symptoms among the motor alterations of Parkinson’s disease (PD). Manifesting FOG episodes reduce patients’ quality of life and their autonomy to perform daily living activities, while it may provoke falls. Accurate ambulatory FOG assessment would enable non-pharmacologic support based on cues and would provide relevant information to neurologists on the disease evolution. This paper presents a method for FOG detection based on deep learning and signal processing techniques. This is, to the best of our knowledge, the first time that FOG detection is addressed with deep learning. The evaluation of the model has been done based on the data from 15 PD patients who manifested FOG. An inertial measurement unit placed at the left side of the waist recorded tri-axial accelerometer, gyroscope and magnetometer signals. Our approach achieved comparable results to the state-of-the-art, reaching validation performances of 88.6% and 78% for sensitivity and specificity respectively.

A sequentiality study for mixed-signal VLSI implementations of neuro/fuzzy feedforward algorithms is presented. Implications of sequential processing and mixed-signal operation are derived. Basic building blocks for sequential mixed-signal neural and fuzzy computing are proposed, and two example sequential processors are described. Feedback from designed processors and subcircuits allows consideration of the technology constraints for analysis and extension to different sequentiality degrees.

Bradykinesia is a cardinal symptom of Parkinson's disease (PD) and describes the slowness of movement revealed in patients. Current PD therapies are based on dopamine replacement, and given that bradykinesia is the symptom that best correlates with the dopaminergic deficiency, the knowledge of its fluctuations may be useful in the diagnosis, treatment and better understanding of the disease progression. This paper evaluates a machine learning method that analyses the signals provided by a triaxial accelerometer placed on the waist of PD patients in order to automatically assess bradykinetic gait unobtrusively. This method employs Support Vector Machines to determine those parts of the signals corresponding to gait. The frequency content of strides is then used to determine bradykinetic walking bouts and to estimate bradykinesia severity based on an epsilon-Support Vector Regression model. The method is validated in 12 PD patients, which leads to two main conclusions. Firstly, the frequency content of the strides allows for the dichotomic detection of bradykinesia with an accuracy higher than 90%. This process requires the use of a patient-dependant threshold that is estimated based on a leave-one-patient-out regression model. Secondly, bradykinesia severity measured through UPDRS scores is approximated by means of a regression model with errors below 10%. Although the method has to be further validated in more patients, results obtained suggest that the presented approach can be successfully used to rate bradykinesia in the daily life of PD patients unobtrusively. A method is proposed to detect and rate bradykinetic gait in an unobtrusive way.A waist-worn triaxial accelerometer, SVM and strides' frequency content are employed.Detection accuracy based on a leave-one-patient-out (LOPO) evaluation is 92%.Severity estimation error through LOPO is ~10%.Results suggest the method can unobtrusively rate bradykinesia in patients' daily life.

Altered movement control is typically the first noticeable symptom manifested by Parkinson’s disease (PD) patients. Once under treatment, the effect of the medication is very patent and patients often recover correct movement control over several hours. Nonetheless, as the disease advances, patients present motor complications. Obtaining precise information on the long-term evolution of these motor complications and their short-term fluctuations is crucial to provide optimal therapy to PD patients and to properly measure the outcome of clinical trials. This paper presents an algorithm based on the accelerometer signals provided by a waist sensor that has been validated in the automatic assessment of patient’s motor fluctuations (ON and OFF motor states) during their activities of daily living. A total of 15 patients have participated in the experiments in ambulatory conditions during 1 to 3 days. The state recognised by the algorithm and the motor state annotated by patients in standard diaries are contrasted. Results show that the average specificity and sensitivity are higher than 90%, while their values are higher than 80% of all patients, thereby showing that PD motor status is able to be monitored through a single sensor during daily life of patients in a precise and objective way.

In order to extract learning algorithms from living neural aggregates it would be advantageous to achieve one-to-one neuron-electrode interfacing with in vitro networks. Towards this goal, we have developed a hybrid glass-elastomer technology, which allows topology specification in small networks (of the order of 10 neurons) and recording of extracellular potentials from individual neurites grown through microfluidic channels. Here we report on progress towards adhesion-free placement of cells within microwells, promotion of neurite growth and recording of intra-channel extracellular spikes.

The design of a digital neural processor based on a VLSI architecture is discussed. Each processor is an element of a systolic array capable of performing the backpropagation algorithm. The processor's internal structure and its characteristics are discussed. >

Background: Our group earlier developed a small monitoring device, which uses accelerometer measurements to accurately detect motor fluctuations in patients with Parkinson’s (On and Off state) based on an algorithm that characterizes gait through the frequency content of strides. To further validate the algorithm, we studied the correlation of its outputs with the motor section of the Unified Parkinson’s Disease Rating Scale part-III (UPDRS-III). Method: Seventy-five patients suffering from Parkinson’s disease were asked to walk both in the Off and the On state while wearing the inertial sensor on the waist. Additionally, all patients were administered the motor section of the UPDRS in both motor phases. Tests were conducted at the patient’s home. Convergence between the algorithm and the scale was evaluated by using the Spearman’s correlation coefficient. results: Correlation with the UPDRS-III was moderate (rho -0.56; p < 0.001). Correlation between the algorithm outputs and the gait item in the UPDRS-III was good (rho -0.73; p < 0.001). The factorial analysis of the UPDRS-III has repeatedly shown that several of its items can be clustered under the so-called Factor 1: “axial function, balance, and gait.” The correlation between the algorithm outputs and this factor of the UPDRS-III was -0.67 (p < 0.01). conclusion: The correlation achieved by the algorithm with the UPDRS-III scale suggests that this algorithm might be a useful tool for monitoring patients with Parkinson’s disease and motor fluctuations.

International audience; This paper is a major step towards a pioneering software framework for the reusable design and implementation of parallel metaheuristics on Graphics Processing Units (GPU). The objective is to revisit the ParadisEO framework to allow its utilization on GPU accelerators. The focus is on local search metaheuristics and the parallel exploration of their neighborhood. The challenge is to make the GPU as transparent as possible for the user. The first release of the new GPU-based ParadisEO framework has been experimented on the Quadratic Assignment Problem (QAP). The preliminary results are convincing, both in terms of flexibility and easiness of reuse at implementation, and in terms of efficiency at execution on GPU.

A nonlinear compartmental model is developed for the HIV detection system in Cuba with different types of detections, some random and others non-random. We analyze the dynamics of this system, compute the reproduction numbers, and use the data from the Cuban HIV/AIDS epidemic between 1986-2008 to fit the model. We obtain estimates for the detection-related parameters during two separate time periods to reflect the timeline of the implementation of various types of searches. The reproduction numbers for each time period are also computed from the sets of values of the parameters. We found that random screening is most important as a mean of surveillance. Moreover, local asymptotic stability for the Disease Free Equilibrium can be achieved if (i) random screening is sufficiently effective and (ii) infection by detected HIV-positive individuals is minimal. Our results highlight the importance of education for the known infectious for the purpose of preventing further infection. Fitting the 1986-2008 HIV data to obtain the model parameter estimates indicates that the HIV epidemic in Cuba is currently approaching an endemic equilibrium. A Genetic Algorithm is used.

This work presents the Autorregresive switching-Markov Model (AR-HMM) as a technique that allows modelling time series which are controlled by some unobserved process and finite time lags. Our objetive is to bring to light the potential of this method to give valuable information about how an efficient control strategy can be performed. As a case of study, we apply the method to the dengue fever epidemics (DF) in 2001 in Havana. For this time series, a first experiment with real data is performed in order to obtain the characterization of differents stages of the epidemics.

The present paper aims at locating the breakings of the integration process of an international system observed during about 50 years in the 19th century. A historical study could link them to special events, which operated as exogenous shocks on this process. The indicator of integration used is the spread between the highest and the lowest among the London, Hamburg and Paris gold-silver prices. Three algorithms are combined to study this integration: a periodization obtained with the SOM algorithm is confronted to the estimation of a two-regime Markov switching model, in order to give an interpretation of the changes of regime; in the same time change-points are identified over the whole period providing a more precise interpretation of the various types of regulation.

Proceedings of the 9th International Work-Conference on Artificial Neural Networks, IWANN 2007, San Sebastián, Spain, June 20-22, 2007.; This paper contribution is about guaranteed numerical methods based on interval analysis for approximating sets, and about the application of these methods to vast classes of statistical problems. 'Guaranteed' means here the inner and outer approximations of the sets of interest are obtained, which can be made as precise as desired, at the cost of increasing the computational effort. It thus becomes possible to archieve tasks still thought by many to be out of the reach of numerical methods, such as finding all solutions of sets of non-linear equations and inequalities or a global optimizer of possible multi-modal criteria.

Proceedings of the 9th International Work-Conference on Artificial Neural Networks, IWANN 2007, San Sebastián, Spain, June 20-22, 2007.; We propose an easy-to-use methodology to allocate one of the groups which have been previously built from a complete learning data base, to new individuals. The learning data base contains continuous and categorical variables for each individual. The groups (clusters) are built by using only the continuous variables and described with the help of the categorical ones. For the new individuals, only the categorical variables are available, and it is necessary to define a model which computes the probabilities to belong to each of the clusters, by using only the categorical variables. Then this model provides a decision rule to assign the new individuals and gives an efficient tool to decision-makers. This tool is shown to be very efficient for customers allocation in consumer clusters for marketing purposes, for example.