VLSI Bio-Inspired Microsystem for Robust Microarrray Image Analysis and Recognition

A microsystem architecture for real-time, on-site, robust bioinformatic patterns recognition and analysis has been proposed. This system is compatible with on-chip DNA analysis means such as polymerase chain reaction (PCR) amplification. A corresponding novel artificial neural network (ANN) learning algorithm using new sigmoid-logarithmic transfer function based on error backpropagation (EBP) algorithm is invented. Our results show the trained new ANN can recognize low fluorescence patterns better than the conventional sigmoidal ANN does. A differential logarithmic imaging chip is designed for calculating logarithm of relative intensities of fluorescence signals. The single-rail logarithmic circuit and a prototype ANN chip are designed, fabricated and characterized

The use of renewable energy sources in the production of electricity has become inevitable in order to reduce the greenhouse gases left in the atmosphere that cause the Earth to warm up. Although countries on a national basis have implemented a number of policies to support electricity generated from renewable energy sources, investments to produce electricity without a license on a local basis are not desirable. According to the climatic conditions of the power plant of 1 MW installed founded in Konya and power plant production data are monitored. Machine learning is a sub-branch of artificial intelligence that deals with the design and development of algorithms that allow computers to develop their behavior based on experimental data. In this study, Naive Bayes, Decision Tree, CN2 Rule Induction, Random Forest, Support Vector Machine, k-Nearest Neighbor, Artificial Neural Network, Logistic Regression and AdaBoost machine learning algorithms are used for prediction and classification. Generally, energy investors are curious about the return on their investment. It is very important for energy providers to predict how much electricity will be generated from existing solar power plants and accordingly determine the measures they will take to meet the electricity demand in the future. ROC analyzes were performed for machine learning models and performance evaluation was performed. In this study, the best performance estimation value obtained from the solar power plant depending on the weather conditions was obtained with 92.24% accuracy.

A hybrid machine learning and embedded IoT-based water quality monitoring system

The electricity demand is increasing day by day due to industrial growth and the rise in the living standards of human beings in Kadoma, Zimbabwe. Electricity generation cannot only be dependent on fossil fuels because of carbon dioxide emissions to the atmosphere, which causes global warming and its devastating effects. In the context of distributed generation, renewable energies (RE)-based Microgrids (MGs) could be sourced to meet the electricity demand. However, the unpredictable nature of RE resources may pose a significant risk of unavailable and/or unreliable electricity supply. This paper proposes optimal scheduling by making use of Internet of Things (IoT) devices in the MG. The MG system comprised a solar farm, wind farm, battery storage system (BSS), diesel generator, and a residential load. The proposed decision-making algorithm was developed using python and was implemented to improve scheduling in the MG system. Additionally, a comparison between three machine learning algorithms (Artificial Neural Network, Random Forest and Extreme Gradient Boosting) was implemented to determine the superior algorithm when it comes to accurately predict the sources to give power at a certain time to satisfy the load. The results indicated that the availability of electricity was enhanced by the use of IoTs in the microgrid. For accuracy prediction, the Extreme Gradient Boosting machine learning algorithm outperformed the Artificial Neural Network and Random Forest machine learning algorithms.

The Levenberg-Marquardt and Newton are two algorithms that use the Hessian for the artificial neural network learning. In this article, we propose a modified Levenberg-Marquardt algorithm for the artificial neural network learning containing the training and testing stages. The modified Levenberg-Marquardt algorithm is based on the Levenberg-Marquardt and Newton algorithms but with the following two differences to assure the error stability and weights boundedness: 1) there is a singularity point in the learning rates of the Levenberg-Marquardt and Newton algorithms, while there is not a singularity point in the learning rate of the modified Levenberg-Marquardt algorithm and 2) the Levenberg-Marquardt and Newton algorithms have three different learning rates, while the modified Levenberg-Marquardt algorithm only has one learning rate. The error stability and weights boundedness of the modified Levenberg-Marquardt algorithm are assured based on the Lyapunov technique. We compare the artificial neural network learning with the modified Levenberg-Marquardt, Levenberg-Marquardt, Newton, and stable gradient algorithms for the learning of the electric and brain signals data set.

Research on artificial neural networks (ANNs) has been carried out for more than five decades. A renewed interest appeared in the 80's with the finding of powerful models like J. Hopfield's recurrent networks, T. Kohonen's self-organizing feature maps, and the back-propagation rule. At that time, there was no platform that was at the same time versatile enough for any ANN model to be implemented and fast enough to solve large problems. Super-computers were the sole exception to this rule, but were prohibitively expensive for most applications. However, both research scientists and application engineers clearly identified the need for such a computing power. This triggered many projects in the field. In parallel, research on multi-processor systems started during the 60's. Systolic arrays have been proposed in 1979 as a means to fully exploit the possibilities of VLSI. Two previous theses, by F. Blayo and C. Lehmann, have studied the use of bi-dimensional systolic arrays for neural computation. At first, the presented system, called GENES, has been designed for the Hopfield model. Extensions to other ANNs have also been proposed. The goal of the present thesis is to study, design, build, and analyze an efficient accelerator for neural computation. In a first step, the GENES architecture has been extended towards generality and efficiency. This includes a thorough analysis of ANN models, of other neural computers, and of previous GENES implementations. The result of this work is the GENES IV integrated circuit, whose architecture has been co-designed by P. Ienne and the author. The main part of this thesis discusses the architecture, the design and the analysis of the MANTRA I machine, a neural computer based on a GENES IV array with up to 40 × 40 processing elements (PEs). The delta rule (and hence the Perceptron and Adaline rules), the back-propagation rule, the Hopfield model, and the Kohonen model can be implemented on this system. Although not a generic system, such a machine may be regarded as a multi-model neural computer. A prototype has been running for a year and is used daily by software designers. Several novel features distinguish the MANTRA I machine from other neural systems. First, it belongs to the few existing neural computers, contrary to the majority of implementations, which are specific to an application or to an algorithm. The machine does not hard-wire any algorithm, but provides the necessary primitives to implement the target models. This is a key feature for research, since several algorithms or versions of an algorithm can be tested on a problem. It is an important aspect for applications as well, because different ANN models are often cascaded to solve a problem. The GENES IV array — that is, the computing core of the MANTRA I machine — features synapse-level parallelism (i.e., one real or virtual PE is allocated per synapse or neural connection), while most other systems exploit only neuron-level parallelism (i.e., one PE per neuron). Hence, this system aims at a much finer parallelism grain and is well suited for massively parallel architectures. The problem size that can be computed by a neural accelerator should not be limited by the hardware (except for memory size). Therefore, it is essential to support time-sharing of PEs. On the MANTRA I machine, this is achieved by the concept of virtual arrays. Matrices are divided into sub-matrices that can be mapped onto the physical array, which is then time-shared among them. An efficient mechanism has been implemented to swap sub-matrices in background, while some other computation is performed. Since systolic arrays are pipelined systems, it is important to avoid emptying and re-filling them too often, in order to keep the hardware utilization rate high. Therefore, a systolic instruction flow has been implemented, so that each instruction follows the data for which it has been issued. Like any SIMD system, the MANTRA I machine is composed of a parallel or SIMD module and a control module. The SIMD module consists of the GENES IV array and a set of dedicated units designed for the computation that scales with the number of neurons and would poorly fit on a bi-dimensional array. A complex system of FIFOs and memories sustains the required input/output streams for the systolic array. The control module is a complete SISD system. Its tasks are (1) to control the SIMD module by dispatching instructions, (2) to manage data input and output, (3) to communicate with the external world, and (4) to perform data pre- and post-processing. The SIMD instructions are of the very long instruction word (VLIW) type. Synchronization between the two modules is achieved by an instruction FIFO. The performance of the MANTRA I machine has been analyzed using the delta rule. Measurements show that the sustained performance is very close to its peak value, as long as the problem fits in the memory banks connected to the GENES IV array. Experiments have also been run to investigate the impact of the constraints imposed by the hardware on the convergence of algorithms. Finally, the use of systolic arrays as neural accelerators is discussed in the light of the experience acquired with the GENES IV array and the MANTRA I machine. The weaknesses of the machine are analyzed, and several solutions are proposed to avoid them in a future design. A general discussion of the future of neural computers concludes this thesis.

Key aspects of the categorical perception of initial stop consonants by human and animal listeners are replicated by a ‘‘synthetic listener’’ in the form of a computational auditory model. This model is a composite of a physiologically faithful ‘‘front end’’ [M. J. Pont and R. I. Damper, J. Acoust. Soc. Am. 89, 1213–1228 (1991)] and an artificial neural network (ANN) ‘‘back end.’’ ANNs are trained on neurograms (i.e., the front end’s auditory-nerve representation) for the 0- and 80-ms end points of three voice-onset time continua (bilabial, alveolar, and velar), and tested on the intermediate (10, 20, ..., 70 ms) patterns. Replication of the behavioral data—in terms of warping of similarity space and shift of phoneme boundary with place of articulation—is robust in that it is maintained across a variety of ANN architectures and learning algorithms. Unlike real listeners, the synthetic listener can be analyzed easily and manipulated purposefully to reveal the acoustic and auditory features underlying the voicing contrast. A contribution analysis of the weights and activations of the ANNs highlights the auditory features. Replacement of the Pont–Damper front end by a simple Fourier-based spectral analysis abolishes the boundary-shift effect, although similarity warping is maintained. This suggests that restructuring of the acoustic features by the peripheral auditory system is crucial to phonetic classification.

This paper presents the development of several efficient learning algorithms for neural networks (ELEANNE). The ELEANNE 1 and ELEANNE 2 are two recursive least-squares learning algorithms, proposed for training single-layered neural networks with analog output. This paper also proposes a new optimization strategy for training single-layered neural networks, which provides the basis for the development of a variety of efficient learning algorithms. This optimization strategy is the source of the ELEANNE 3, a second-order learning algorithm for training single-layered neural networks with binary output. A simplified version of this algorithm, called ELEANNE 4, is also derived on the basis of some simplifying but reasonable assumptions. The two algorithms developed for single-layered neural networks provide the basis for the derivation of ELEANNE 5 and ELEANNE 6, which are proposed for training multilayered neural networks with binary output. The ELEANNE 7 is an efficient algorithm developed for training multilayered neural networks with either binary or analog output. >

A compact integrated system-on-chip (SoC) architecture solution for robust, real-time, and on-site genetic analysis and biomarker recognition has been developed. This microsystem solution is noise tolerable and suitable for analyzing the weak fluorescence patterns from a PCR prepared dual-labeled DNA microchip assay. In the architecture, a preceding VLSI differential logarithm microchip is designed for effectively computing the logarithm of the normalized input fluorescence signals. A posterior VLSI artificial neural network (ANN) processor chip is used for analyzing the processed signals from the differential logarithm stage. A single-channel logarithmic circuit was fabricated and characterized. A prototype ANN chip with unsupervised winner-take-all (WTA) function was designed, fabricated, and tested. An ANN learning algorithm using a novel sigmoid-logarithmic transfer function based on the supervised backpropagation (BP) algorithm is proposed for robustly recognizing low intensity patterns. Our results show the trained new ANN can recognize low fluorescence patterns better than an ANN using the conventional sigmoid function.

The identification of Chinese medicinal plants was conducted to rely on ampelographic manual assessment by experts. More recently, machine learning algorithms for pattern recognition have been successfully applied to leaf recognition in other plant species. These new tools make the classification of Chinese medicinal plants easier, more efficient and cost effective. This study showed comparative results between machine learning models obtained from two methods: i) a morpho-colorimetric method and ii) a visible (VIS)/Near Infrared (NIR) spectral analysis from sampled leaves of 20 different Chinese medicinal plants. Specifically, the automated image analysis and VIS/NIR spectral based parameters obtained from leaves were used separately as inputs to construct customized artificial neural network (ANN) models. Results showed that the ANN model developed using the morpho-colorimetric parameters as inputs (Model A) had an accuracy of 98.3% in the classification of leaves for the 20 medicinal plants studied. In the case of the model based on spectral data from leaves (Model B), the ANN model obtained using the averaged VIS/NIR spectra per leaf as inputs showed 92.5% accuracy for the classification of all medicinal plants used. Model A has the advantage of being cost effective, requiring only a normal document scanner as measuring instrument. This method can be adapted for non-destructive assessment of leaves in-situ by using portable wireless scanners. Model B combines the fast, non-destructive advantages of VIS/NIR spectroscopy, which can be used for rapid and non-invasive identification of Chinese medicinal plants and other applications by analyzing specific light spectra overtones from leaves to assess concentration of pigments such as chlorophyll, anthocyanins and others that are related active compounds from the medicinal plants. Keywords: ampelography, computer vision, artificial neural networks, pattern recognition, Chinese medicinal plants DOI: 10.25165/j.ijabe.20191202.4637 Citation: Xue J R, Fuentes S, Poblete-Echeverria C, Viejo C G, Tongson E, Du H J, et al. Automated Chinese medicinal plants classification based on machine learning using leaf morpho-colorimetry, fractal dimension and visible/near infrared spectroscopy. Int J Agric & Biol Eng, 2019; 12(2): 123–131.

The considerable improvement of technology produced for various applications has resulted in a growth in data sizes, such as healthcare data, which is renowned for having a large number of variables and data samples. Artificial neural networks (ANN) have demonstrated adaptability and effectiveness in classification, regression, and function approximation tasks. ANN is used extensively in function approximation, prediction, and classification. Irrespective of the task, ANN learns from the data by adjusting the edge weights to minimize the error between the actual and predicted values. Back Propagation is the most frequent learning technique that is used to learn the weights of ANN. However, this approach is prone to the problem of sluggish convergence, which is especially problematic in the case of Big Data. In this paper, we propose a Distributed Genetic Algorithm based ANN Learning Algorithm for addressing challenges associated with ANN learning for Big data. Genetic Algorithm is one of the well-utilized bio-inspired combinatorial optimization methods. Also, it is possible to parallelize it at multiple stages, and this may be done in an extremely effective manner for the distributed learning process. The proposed model is tested with various datasets to evaluate its realizability and efficiency. The results obtained from the experiments show that after a specific volume of data, the proposed learning method outperformed the traditional methods in terms of convergence time and accuracy. The proposed model outperformed the traditional model by almost 80% improvement in computational time.

Volumetric efficiency modelling of internal combustion engines based on a novel adaptive learning algorithm of artificial neural networks

A neuro-emulator with embedded capabilities for generalized learning

Road traffic forecasting — A hybrid approach combining Artificial Neural Network with Singular Spectrum Analysis

This paper describes the design, implementation and testing of the software tool designated as UV-SRNA-PDA (Universidad del Valle’s artificial neural network simulator for a personal digital assistant), which is oriented to artificial neural networks simulation and complex industrial processes identification. This application works on a PDA (personal digital assistant) Palm T5 using a customized data acquisition system. Two kinds of artificial neural networks were implemented: perceptron and multi-layer perceptron (MLP) using as learning algorithms the following: backpropagation, descendent gradient, variable learning rate and momentum. To test the proposed system, first and second order systems were selected (only the latter is reported here), finding their neural models and validating their results with MATLAB and UV-SRNA 2.0 (PC version of UV-SRNA-PDA). These tests achieved an average training error of 5.62 × 10-3 ± 3.55 × 10-4 and an average validating error of 4.56 × 10-3 ± 5.95 × 10-4. In both cases, the results were better or comparable with those from other software simulation tools. However, the typical training time on the UV-SRNA-PDA was 900 s compared to 3 s in MATLAB and 8 s in UV-SRNA 2.0.