A Novel Normalization Algorithm to Facilitate Pre-Assessment of Covid-19 Disease from Chest X-ray Image and its FPGA implementation

COVID-19 is still a fatal disease, which has threatened all people by affecting the human lungs. Chest X-Ray or computed tomography (CT) imaging is commonly used to make a fast and reliable medical investigation to detect the COVID-19 virus from these medical images is remarkably challenging because it is a full-time job and prone to human errors. In this paper, a new normalization algorithm that consists of Mean-Variance-Softmax-Rescale (MVSR) processes respectively is proposed to provide facilitation pre-assessment and diagnosis Covid-19 disease. In order to show the effect of MVSR normalization technique on image processing, the algorithm is applied to chest X-ray images. Therefore, the normalized X-ray images with MVSR are used to recognize via one of the neural network models as known Convolutional Neural Networks (CNNs). At the implementation stage, the MVSR algorithm is executed on MATLAB environment, then it is implemented on FPGA platform. All the arithmetic operations of the MVSR normalization are coded in VHDL with the help of fixed-point fractional number representation format. The experimental platform consists of Zynq-7000 Development Board and VGA monitor to display the both original X-ray and MVSR normalized image. The CNN model is constructed and executed using Anaconda Navigator interface with python language. Based on the results of this study, infections of Covid-19 disease can be easily diagnosed for MVSR normalized image. The proposed MVSR normalization makes the accuracy of CNN model increase from 83.01%, to 96.16% for binary class of chest X-ray images.

Intelligent stability margin improvement using series and shunt controllers

Electric market always prefers to use full capacity of existing power system to control the costs. Flexible alternate current transmission system (FACTS) devices introduced by Electric Power Research Institute (EPRI) to increase the usable capacity of power system. Placement of FACTS controllers in power system is a critical issue to reach their maximum advantages. This article focused on the application of FACTS devices to increase the stability of power system using artificial intelligence. Five types of series and shunt FACTS controllers are considered in this study. Continuation power flow (CPF) analysis used to calculate the collapse point of power systems. Controlling parameters of FACTS devices including their locations are determined using real number representation based genetic algorithm (RNRGA) in order to improve the secure margin of operating condition of power system. The 14 and 118 buses IEEE standard test systems are utilized to verify the recommended method. The achieved results manifestly proved the effectiveness of proposed intelligent method to increase the stability of power system by determining the optimum location and size of each type of FACTS devices.

Neuromuscular Diseases Affect Number Representation and Processing: An Exploratory Study

Spinal muscular atrophy (SMA) and Duchenne muscular dystrophy (DMD) both are rare genetic neuromuscular diseases with progressive loss of motor ability. The neuromotor developmental course of those diseases is well documented. In contrast, there is only little evidence about characteristics of general and specific cognitive development. In both conditions the final motor outcome is characterized by an inability to move autonomously: children with SMA never accomplish independent motoric exploration of their environment, while children with DMD do but later lose this ability again. These profound differences in developmental pathways might affect cognitive development of SMA vs. DMD children, as cognition is shaped by individual motor experiences. DMD patients show impaired executive functions, working memory, and verbal IQ, whereas only motor ability seems to be impaired in SMA. Advanced cognitive capacity in SMA may serve as a compensatory mechanism for achieving in education, career progression, and social satisfaction. This study aimed to relate differences in basic numerical concepts and arithmetic achievement in SMA and DMD patients to differences in their motor development and resulting sensorimotor and environmental experiences. Horizontal and vertical spatial-numerical associations were explored in SMA/DMD children ranging between 6 and 12 years through the random number generation task. Furthermore, arithmetic skills as well as general cognitive ability were assessed. Groups differed in spatial number processing as well as in arithmetic and domain-general cognitive functions. Children with SMA showed no horizontal and even reversed vertical spatial-numerical associations. Children with DMD on the other hand revealed patterns in spatial numerical associations comparable to healthy developing children. From the embodied Cognition perspective, early sensorimotor experience does play a role in development of mental number representations. However, it remains open whether and how this becomes relevant for the acquisition of higher order cognitive and arithmetic skills.

Visualization of RNA secondary structure with pseudoknots

The function of pseudoknots cannot be ignored in the RNA secondary structure. Existing methods for analyzing RNA secondary structures with pseudoknots exhibit many shortcomings. This paper presents a novel RNA secondary structure visualization method in the case of a joint analysis of RNA primary structures and secondary structures. The way is based on the page number representation of the RNA secondary structure. It innovatively uses five vectors to represent bases, which are sequentially connected to outline the characteristics of the RNA secondary structure. The method covers almost all the constituent elements of the RNA secondary structure and extracts features completely. Experiments are based on the available techniques for large-scale annotation of RNA secondary structures, using a combination method of discrete wavelet transform and fractal dimension. The classification effect is compared with the previous RNA secondary structure representation methods. Experimental results show that the RNA secondary structure visualization method proposed in this paper has good application prospects in RNA secondary structure classification.

Population model of Temnothorax albipennis as a distributed dynamical system II: secret of "chemical reaction" in collective house-hunting in ant colonies is unveiled by operator methods

The collective intelligence of animal groups is a complex algorithm for computer scientist and a many-body problem for physics of living system. We show how the time evolution of features in such a system, like number of ants in particular state for colonies, can be mapped to many-body problems in non-equilibrium statistical mechanics. There exist role transitions of active and passive ant between distributed functions, including exploration, assessing, recruiting and transportation in the house-hunting process. Theoretically, such a process can be approximately described as birth-death process where large number of particles living in the Fock space and particles of one sub-type transfer to a different sub-type with some probability. Started from the master equation with constrain of the quorum criterion, we express the evolution operator as a functional integral mapping from operators acting on Fock space in number representation to functional space in coherent state representation. We then read out the action from the evolution operator, and we use least action principal equations of motion, which are the number field equations. The equations we get are couple ordinary differential equations, which can faithfully describe the original master equation, and hence fully describe the system. This method provides us differential equation-based algorithm, which allow us explore parameter space with respect to more complicated agent-based algorithm. The algorithm also allows exploring stochastic process with memory in a Markovian way, which provide testable prediction on collective decision making.

Processing of Digital Signals in (+1, -1) Binary System

Digital Signal Processing in (+1, -1) system has been studied in detail. Effects of number representation on quantization and truncation of rounding have been discussed. First order and second order filters have been investigated. Differential pulse code modulation method of coding is being studied. It is found that this system is well suited for VLSI design. The hardware realization of different components of DPCM is easy and straight. The position and negative signals can be processed in a unified way. It gives better performance in comparison of two’s complement representation of conventional binary system. The effect of limit cycles, stability and round off noise in first and second order filter have been discussed too.

A multi-objective scheduling method for operational coordination time using improved triangular fuzzy number representation

In modern warfare, the comprehensiveness of combat domain and the complexity of tasks pose great challenges to operational coordination.To address this challenge, we use the improved triangular fuzzy number to express the combat mission time, first present a new multi-objective operational cooperative time scheduling model that takes the fluctuation of combat coordinative time and the time flexibility between each task into account. The resulting model is essentially a large-scale multi-objective combinatorial optimization problem, intractably complicated to solve optimally. We next propose multi-objective improved Bat algorithm based on angle decomposition (MOIBA/AD) to quickly identify high-quality solutions to the model. Our proposed algorithm improves the decomposition strategy by replacing the planar space with the angle space, which helps greatly reduce the difficulty of processing evolutionary individuals and hence the time complexity of the multi-objective evolutionary algorithm based on decomposition (MOEA/D). Moreover, the population replacement strategy is enhanced utilizing the improved bat algorithm, which helps evolutionary individuals avoid getting trapped in local optima. Computational experiments on multi-objective operational cooperative time scheduling (MOOCTS) problems of different scales demonstrate the superiority of our proposed method over four state-of-the-art multi-objective evolutionary algorithms (MOEAs), including multi-objective bat Algorithm (MOBA), MOEA/D, non-dominated sorting genetic algorithm version II (NSGA-II) and multi-objective particle swarm optimization algorithm (MOPSO). Our proposed method performs better in terms of four performance criteria, producing solutions of higher quality while keeping a better distribution of the Pareto solution set.

Filtration network: A frame sampling strategy via deep reinforcement learning for video captioning

Recently many methods use encoder-decoder framework for video captioning, aiming to translate short videos into natural language. These methods usually use equal interval frame sampling. However, lacking a good efficiency in sampling, it has a high temporal and spatial redundancy, resulting in unnecessary computation cost. In addition, the existing approaches simply splice different visual features on the fully connection layer. Therefore, features cannot be effectively utilized. In order to solve the defects, we proposed filtration network (FN) to select key frames, which is trained by deep reinforcement learning algorithm actor-double-critic. According to behavior psychology, the core idea of actor-double-critic is that the behavior of agent is determined by both the external environment and the internal personality. It avoids the phenomenon of unclear reward and sparse feedback in training because it gives steady feedback after each action. The key frames are sent to combine codec network (CCN) to generate sentences. The operation of feature combination in CCN make fusion of visual features by complex number representation to make good semantic modeling. Experiments and comparisons with other methods on two datasets (MSVD/MSR-VTT) show that our approach achieves better performance in terms of four metrics, BLEU-4, METEOR, ROUGE-L and CIDEr.

A Database for Learning Numbers by Visual Finger Recognition in Developmental Neuro-Robotics

Numerical cognition is a fundamental component of human intelligence that has not been fully understood yet. Indeed, it is a subject of research in many disciplines, e.g., neuroscience, education, cognitive and developmental psychology, philosophy of mathematics, linguistics. In Artificial Intelligence, aspects of numerical cognition have been modelled through neural networks to replicate and analytically study children behaviours. However, artificial models need to incorporate realistic sensory-motor information from the body to fully mimic the children's learning behaviours, e.g., the use of fingers to learn and manipulate numbers. To this end, this article presents a database of images, focused on number representation with fingers using both human and robot hands, which can constitute the base for building new realistic models of numerical cognition in humanoid robots, enabling a grounded learning approach in developmental autonomous agents. The article provides a benchmark analysis of the datasets in the database that are used to train, validate, and test five state-of-the art deep neural networks, which are compared for classification accuracy together with an analysis of the computational requirements of each network. The discussion highlights the trade-off between speed and precision in the detection, which is required for realistic applications in robotics.