1
|
Wu T, Neri F, Pan L. On the tuning of the computation capability of spiking neural membrane systems with communication on request. Int J Neural Syst 2022; 32:2250037. [DOI: 10.1142/s012906572250037x] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
2
|
An Extended Tissue-like P System Based on Membrane Systems and Quantum-Behaved Particle Swarm Optimization for Image Segmentation. Processes (Basel) 2022. [DOI: 10.3390/pr10020287] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
An extended membrane system using a tissue-like P system with evolutional symport/antiport rules and a promoter/inhibitor, which is based on the evolutionary mechanism of quantum-behaved particle swarm optimization (QPSO) and improved QPSO, named CQPSO-ETP, is designed and developed in this paper. The purpose of CQPSO-ETP is to enhance the optimization performance of statistical network structure-based membrane-inspired evolutionary algorithms (SNS-based MIEAs) and the QPSO technique. In CQPSO-ETP, evolution rules with a promoter based on a standard QPSO mechanism are introduced to evolve objects, and evolution rules with an inhibitor based on an improved QPSO mechanism using self-adaptive selection, and cooperative evolutionary and logistic chaotic mapping methods, are adopted to avoid prematurity. The communication rules with a promoter/inhibitor for objects are introduced to achieve the exchange and sharing of information between different membranes. Under the control of the evolution and communication mechanism, the CQPSO-ETP can effectively improve the performance with the help of a distributed parallel computing model. The proposed CQPSO-ETP is compared with PSO, QPSO and two existing improved QPSO approaches which are conducted on eight classic numerical benchmark functions to verify the effectiveness. Furthermore, computational experiments which are made on eight tested images with three comparative clustering approaches are adopted, and the experimental results demonstrate the clustering validity of the proposed CQPSO-ETP.
Collapse
|
3
|
A Complex Chained P System Based on Evolutionary Mechanism for Image Segmentation. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2021; 2020:6524919. [PMID: 32831818 PMCID: PMC7428845 DOI: 10.1155/2020/6524919] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/01/2019] [Revised: 02/06/2020] [Accepted: 02/25/2020] [Indexed: 12/04/2022]
Abstract
A new clustering membrane system using a complex chained P system (CCP) based on evolutionary mechanism is designed, developed, implemented, and tested. The purpose of CCP is to solve clustering problems. In CCP, two kinds of evolution rules in different chained membranes are used to enhance the global search ability. The first kind of evolution rules using traditional and modified particle swarm optimization (PSO) clustering techniques are used to evolve the objects. Another based on differential evolution (DE) is introduced to further improve the global search ability. The communication rules are adopted to accelerate the convergence and avoid prematurity. Under the control of evolution-communication mechanism, the CCP can effectively search for the optimal partitioning and improve the clustering performance with the help of the distributed parallel computing model. This proposed CCP is compared with four existing PSO clustering approaches on eight real-life datasets to verify the validity. The computational results on tested images also clearly show the effectiveness of CCP in solving image segmentation problems.
Collapse
|
4
|
Optimization of Correlation Filters Using Extended Particle Swarm Optimization Technique. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2021; 2021:6321860. [PMID: 34306177 PMCID: PMC8279855 DOI: 10.1155/2021/6321860] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/05/2021] [Revised: 05/16/2021] [Accepted: 06/23/2021] [Indexed: 11/17/2022]
Abstract
In the past few decades, the field of image processing has seen a rapid advancement in the correlation filters, which serves as a very promising tool for object detection and recognition. Mostly, complex filter equations are used for deriving the correlation filters, leading to a filter solution in a closed loop. Selection of optimal tradeoff (OT) parameters is crucial for the effectiveness of correlation filters. This paper proposes extended particle swarm optimization (EPSO) technique for the optimal selection of OT parameters. The optimal solution is proposed based on two cost functions. The best result for each target is obtained by applying the optimization technique separately. The obtained results are compared with the conventional particle swarm optimization method for various test images belonging from different state-of-the-art datasets. The obtained results depict the performance of filters improved significantly using the proposed optimization method.
Collapse
|
5
|
Abstract
Spiking neural P systems (SNP systems) are a class of distributed and parallel computation models, which are inspired by the way in which neurons process information through spikes, where the integrate-and-fire behavior of neurons and the distribution of produced spikes are achieved by spiking rules. In this work, a novel mechanism for separately describing the integrate-and-fire behavior of neurons and the distribution of produced spikes, and a novel variant of the SNP systems, named evolution-communication SNP (ECSNP) systems, is proposed. More precisely, the integrate-and-fire behavior of neurons is achieved by spike-evolution rules, and the distribution of produced spikes is achieved by spike-communication rules. Then, the computational power of ECSNP systems is examined. It is demonstrated that ECSNP systems are Turing universal as number-generating devices. Furthermore, the computational power of ECSNP systems with a restricted form, i.e. the quantity of spikes in each neuron throughout a computation does not exceed some constant, is also investigated, and it is shown that such restricted ECSNP systems can only characterize the family of semilinear number sets. These results manifest that the capacity of neurons for information storage (i.e. the quantity of spikes) has a critical impact on the ECSNP systems to achieve a desired computational power.
Collapse
Affiliation(s)
- Tingfang Wu
- School of Computer Science and Technology, Soochow University, Suzhou 215006, P. R. China.,Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Suzhou 215006, P. R. China
| | - Qiang Lyu
- School of Computer Science and Technology, Soochow University, Suzhou 215006, P. R. China.,Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Suzhou 215006, P. R. China
| | - Linqiang Pan
- Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China, China.,Institute of Artificial Intelligence, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, Hubei, P. R. China
| |
Collapse
|
6
|
Dynamic Threshold Neural P Systems with Multiple Channels and Inhibitory Rules. Processes (Basel) 2020. [DOI: 10.3390/pr8101281] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022] Open
Abstract
In biological neural networks, neurons transmit chemical signals through synapses, and there are multiple ion channels during transmission. Moreover, synapses are divided into inhibitory synapses and excitatory synapses. The firing mechanism of previous spiking neural P (SNP) systems and their variants is basically the same as excitatory synapses, but the function of inhibitory synapses is rarely reflected in these systems. In order to more fully simulate the characteristics of neurons communicating through synapses, this paper proposes a dynamic threshold neural P system with inhibitory rules and multiple channels (DTNP-MCIR systems). DTNP-MCIR systems represent a distributed parallel computing model. We prove that DTNP-MCIR systems are Turing universal as number generating/accepting devices. In addition, we design a small universal DTNP-MCIR system with 73 neurons as function computing devices.
Collapse
|
7
|
Peng H, Bao T, Luo X, Wang J, Song X, Riscos-Núñez A, Pérez-Jiménez MJ. Dendrite P systems. Neural Netw 2020; 127:110-120. [DOI: 10.1016/j.neunet.2020.04.014] [Citation(s) in RCA: 26] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2019] [Revised: 03/27/2020] [Accepted: 04/14/2020] [Indexed: 10/24/2022]
|
8
|
Kheradpisheh SR, Masquelier T. Temporal Backpropagation for Spiking Neural Networks with One Spike per Neuron. Int J Neural Syst 2020; 30:2050027. [DOI: 10.1142/s0129065720500276] [Citation(s) in RCA: 57] [Impact Index Per Article: 14.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
We propose a new supervised learning rule for multilayer spiking neural networks (SNNs) that use a form of temporal coding known as rank-order-coding. With this coding scheme, all neurons fire exactly one spike per stimulus, but the firing order carries information. In particular, in the readout layer, the first neuron to fire determines the class of the stimulus. We derive a new learning rule for this sort of network, named S4NN, akin to traditional error backpropagation, yet based on latencies. We show how approximated error gradients can be computed backward in a feedforward network with any number of layers. This approach reaches state-of-the-art performance with supervised multi-fully connected layer SNNs: test accuracy of 97.4% for the MNIST dataset, and 99.2% for the Caltech Face/Motorbike dataset. Yet, the neuron model that we use, nonleaky integrate-and-fire, is much simpler than the one used in all previous works. The source codes of the proposed S4NN are publicly available at https://github.com/SRKH/S4NN .
Collapse
Affiliation(s)
- Saeed Reza Kheradpisheh
- Department of Computer and Data Sciences, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran, Iran
| | | |
Collapse
|
9
|
Peng H, Lv Z, Li B, Luo X, Wang J, Song X, Wang T, Pérez-Jiménez MJ, Riscos-Núñez A. Nonlinear Spiking Neural P Systems. Int J Neural Syst 2020; 30:2050008. [DOI: 10.1142/s0129065720500082] [Citation(s) in RCA: 33] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
This paper proposes a new variant of spiking neural P systems (in short, SNP systems), nonlinear spiking neural P systems (in short, NSNP systems). In NSNP systems, the state of each neuron is denoted by a real number, and a real configuration vector is used to characterize the state of the whole system. A new type of spiking rules, nonlinear spiking rules, is introduced to handle the neuron’s firing, where the consumed and generated amounts of spikes are often expressed by the nonlinear functions of the state of the neuron. NSNP systems are a class of distributed parallel and nondeterministic computing systems. The computational power of NSNP systems is discussed. Specifically, it is proved that NSNP systems as number-generating/accepting devices are Turing-universal. Moreover, we establish two small universal NSNP systems for function computing and number generator, containing 117 neurons and 164 neurons, respectively.
Collapse
Affiliation(s)
- Hong Peng
- School of Computer and Software Engineering, Xihua University, Chengdu, Sichuan 610039, P. R. China
| | - Zeqiong Lv
- School of Computer and Software Engineering, Xihua University, Chengdu, Sichuan 610039, P. R. China
| | - Bo Li
- School of Computer and Software Engineering, Xihua University, Chengdu, Sichuan 610039, P. R. China
| | - Xiaohui Luo
- School of Computer and Software Engineering, Xihua University, Chengdu, Sichuan 610039, P. R. China
| | - Jun Wang
- School of Electrical Engineering and Electronic Information, Xihua University, Chengdu, Sichuan 610039, P. R. China
| | - Xiaoxiao Song
- School of Electrical Engineering and Electronic Information, Xihua University, Chengdu, Sichuan 610039, P. R. China
| | - Tao Wang
- School of Electrical Engineering and Electronic Information, Xihua University, Chengdu, Sichuan 610039, P. R. China
| | - Mario J. Pérez-Jiménez
- Research Group of Natural Computing, Department of Computer Sciences and Artificial Intelligence, School of Computer Engineering, University of Seville, 41012, C. P. Sevilla, Spain
| | - Agustín Riscos-Núñez
- Research Group of Natural Computing, Department of Computer Sciences and Artificial Intelligence, School of Computer Engineering, University of Seville, 41012, C. P. Sevilla, Spain
| |
Collapse
|
10
|
|
11
|
Mirzaei G, Adeli H. Segmentation and clustering in brain MRI imaging. Rev Neurosci 2019; 30:31-44. [PMID: 30265656 DOI: 10.1515/revneuro-2018-0050] [Citation(s) in RCA: 29] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2018] [Accepted: 07/19/2018] [Indexed: 12/17/2022]
Abstract
Clustering is a vital task in magnetic resonance imaging (MRI) brain imaging and plays an important role in the reliability of brain disease detection, diagnosis, and effectiveness of the treatment. Clustering is used in processing and analysis of brain images for different tasks, including segmentation of brain regions and tissues (grey matter, white matter, and cerebrospinal fluid) and clustering of the atrophy in different parts of the brain. This paper presents a state-of-the-art review of brain MRI studies that use clustering techniques for different tasks.
Collapse
Affiliation(s)
- Golrokh Mirzaei
- Department of Computer Science and Engineering, The Ohio State University, Marion, OH 43302, USA
| | - Hojjat Adeli
- Departments of Biomedical Informatics, Neurology, Neuroscience, The Ohio State University, Columbus, OH 43210, USA
| |
Collapse
|
12
|
Yang Q, Lv Z, Liu L, Peng H, Song X, Wang J. Spiking neural P systems with multiple channels and polarizations. Biosystems 2019; 185:104020. [PMID: 31437527 DOI: 10.1016/j.biosystems.2019.104020] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2019] [Revised: 07/15/2019] [Accepted: 08/15/2019] [Indexed: 11/29/2022]
Abstract
In this paper, we investigate a new variant of spiking neural P systems (SNP systems, in short), called spiking neural P systems with multiple channels and polarizations (SNP-MCP systems, in short). The variant integrates two interesting features: multiple channel and polarization. Each neuron can use its multiple channels to connect one or more subsequent sets of neurons. Moreover, both polarizations and regular expressions are used in rules to control the spiking of neurons. The computational power of the variant is discussed. The Turing universality of the variant as number generating/accepting devices is proven, and then a small universal system with 150 neurons is constructed to compute any Turing computable function.
Collapse
Affiliation(s)
- Qian Yang
- School of Computer and Software Engineering, Xihua University, Chengdu 610039, China
| | - Zeqiong Lv
- School of Computer and Software Engineering, Xihua University, Chengdu 610039, China
| | - Liucheng Liu
- School of Computer and Software Engineering, Xihua University, Chengdu 610039, China
| | - Hong Peng
- School of Computer and Software Engineering, Xihua University, Chengdu 610039, China.
| | - Xiaoxiao Song
- School of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, China
| | - Jun Wang
- School of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, China
| |
Collapse
|
13
|
Peng H, Wang J. Coupled Neural P Systems. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2019; 30:1672-1682. [PMID: 30369454 DOI: 10.1109/tnnls.2018.2872999] [Citation(s) in RCA: 28] [Impact Index Per Article: 5.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
Inspired by Eckhorn's neuron model that emulates a mammal's visual cortex, this paper proposes a new kind of neural-like P system, called a coupled neural P (CNP) system. The CNP system consists of some coupled neurons, each with three components: receptive field, modulation, and output module. CNP systems are a kind of distributed parallel-computing model with a directed graph structure like spiking neural P systems. Moreover, CNP systems have a nonlinear coupled-modulation characteristic and a dynamic threshold mechanism. The computational power of CNP systems is discussed. Specifically, it is proved that CNP systems as number-generating devices are Turing universal. Moreover, we provide a small universal CNP system for function-computing devices.
Collapse
|
14
|
|
15
|
Song X, Wang J, Peng H, Ning G, Sun Z, Wang T, Yang F. Spiking neural P systems with multiple channels and anti-spikes. Biosystems 2018; 169-170:13-19. [DOI: 10.1016/j.biosystems.2018.05.004] [Citation(s) in RCA: 32] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2017] [Revised: 04/08/2018] [Accepted: 05/21/2018] [Indexed: 11/28/2022]
|
16
|
Peng H, Chen R, Wang J, Song X, Wang T, Yang F, Sun Z. Competitive Spiking Neural P Systems With Rules on Synapses. IEEE Trans Nanobioscience 2017; 16:888-895. [DOI: 10.1109/tnb.2017.2783890] [Citation(s) in RCA: 25] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
|
17
|
Pan L, Păun G, Zhang G, Neri F. Spiking Neural P Systems with Communication on Request. Int J Neural Syst 2017; 27:1750042. [DOI: 10.1142/s0129065717500423] [Citation(s) in RCA: 133] [Impact Index Per Article: 19.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Spiking Neural [Formula: see text] Systems are Neural System models characterized by the fact that each neuron mimics a biological cell and the communication between neurons is based on spikes. In the Spiking Neural [Formula: see text] systems investigated so far, the application of evolution rules depends on the contents of a neuron (checked by means of a regular expression). In these [Formula: see text] systems, a specified number of spikes are consumed and a specified number of spikes are produced, and then sent to each of the neurons linked by a synapse to the evolving neuron. [Formula: see text]In the present work, a novel communication strategy among neurons of Spiking Neural [Formula: see text] Systems is proposed. In the resulting models, called Spiking Neural [Formula: see text] Systems with Communication on Request, the spikes are requested from neighboring neurons, depending on the contents of the neuron (still checked by means of a regular expression). Unlike the traditional Spiking Neural [Formula: see text] systems, no spikes are consumed or created: the spikes are only moved along synapses and replicated (when two or more neurons request the contents of the same neuron). [Formula: see text]The Spiking Neural [Formula: see text] Systems with Communication on Request are proved to be computationally universal, that is, equivalent with Turing machines as long as two types of spikes are used. Following this work, further research questions are listed to be open problems.
Collapse
Affiliation(s)
- Linqiang Pan
- Key Laboratory of Image Information Processing, and Intelligent Control of Education Ministry of China, School of Automation, Huazhong University of Science and Technology, Wuhan 430074, Hubei, P. R. China
- and Zhengzhou University of Light Industry, Zhengzhou 450002, Henan, P. R. China
| | - Gheorghe Păun
- Institute of Mathematics of the Romanian Academy, P. O. Box 1-764, RO-014700 Bucharest, Romania
| | - Gexiang Zhang
- Robotics Research Center, Xihua University, Chengdu 610039, P. R. China
- Key Laboratory of Fluid and Power Machinery (Xihua University), Ministry of Education, Chengdu 610039, P. R. China
- School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, P. R. China
| | - Ferrante Neri
- Centre for Computational Intelligence, School of Computer Science and Informatics, De Montfort University, The Gateway, Leicester LE1 9BH, England, UK
| |
Collapse
|
18
|
Ortiz-Rosario A, Adeli H, Buford JA. MUSIC-Expected maximization gaussian mixture methodology for clustering and detection of task-related neuronal firing rates. Behav Brain Res 2016; 317:226-236. [PMID: 27650101 DOI: 10.1016/j.bbr.2016.09.022] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2016] [Revised: 09/07/2016] [Accepted: 09/11/2016] [Indexed: 01/07/2023]
Abstract
Researchers often rely on simple methods to identify involvement of neurons in a particular motor task. The historical approach has been to inspect large groups of neurons and subjectively separate neurons into groups based on the expertise of the investigator. In cases where neuron populations are small it is reasonable to inspect these neuronal recordings and their firing rates carefully to avoid data omissions. In this paper, a new methodology is presented for automatic objective classification of neurons recorded in association with behavioral tasks into groups. By identifying characteristics of neurons in a particular group, the investigator can then identify functional classes of neurons based on their relationship to the task. The methodology is based on integration of a multiple signal classification (MUSIC) algorithm to extract relevant features from the firing rate and an expectation-maximization Gaussian mixture algorithm (EM-GMM) to cluster the extracted features. The methodology is capable of identifying and clustering similar firing rate profiles automatically based on specific signal features. An empirical wavelet transform (EWT) was used to validate the features found in the MUSIC pseudospectrum and the resulting signal features captured by the methodology. Additionally, this methodology was used to inspect behavioral elements of neurons to physiologically validate the model. This methodology was tested using a set of data collected from awake behaving non-human primates.
Collapse
Affiliation(s)
| | - Hojjat Adeli
- Departments of Biomedical Engineering, Biomedical Informatics, Civil and Environmental Engineering and Geodetic Science, Electrical and Computer Engineering, Neurology, and Neuroscience, The Ohio State University, 470 Hitchcock Hall, 2070 Neil Avenue, Columbus, OH 43210, United States.
| | - John A Buford
- Physical Therapy Division, School of Health and Rehabilitation Sciences, The Ohio State University, 453 W 10th Ave, Rm. 516E, Columbus, OH 43210, United States
| |
Collapse
|