Search

Software defect prediction is one of the most active research areas in software engineering and plays an important role in software quality assurance. In recent years, many new defect prediction studies have been proposed. There are four main aspects of research: machine learning-based prediction algorithms, manipulating the data, effor-softaware prediction and empirical studies. The research community is still facing many challenges in constructing methods, and there are also many research opportunities in the meantime. This paper proposes a method of applying spiking neural network to software defect prediction. The software defect prediction model is constructed by feed-forward spiking neural networks and trained by spike train learning algorithm. This model uses the existing project data sets to predict software defects projects. Extensive experiments on 28 public projects from five data sources indicate that the effectiveness of the proposed approach with respect to the considered metrics.

In biological nervous systems, the synaptic transmission of information is a complex process through the release of neurotransmitters. The input of multiple signals shows nonlinear interaction characteristics in synapses, so nonlinear synaptic interaction is considered as an important part of biological neural networks. At present, most artificial neural networks simplify synapses into a linear structure. Considering the nonlinear interaction of the input multiple signals of synapse, this paper proposes an online supervised learning algorithm for spiking neural networks based on nonlinear synaptic kernels, which can implement the complex spatio-temporal pattern learning of spike trains. The algorithm is successfully applied to learn sequences of spikes. In addition, different learning parameters are analyzed, such as synaptic kernel. The experimental results show that the proposed algorithm has high learning accuracy.

Deep spiking belief network (DSBN) uses unsupervised layer-wise pre-training method to train the network weights, it is stacked with the spike neural machine (SNM) modules. However, the synaptic weights of SNMs are difficult to pre-training through simple and effective approach for spike-train driven networks. This paper proposes a new algorithm that uses unsupervised multi-spike learning rule to train SNMs, which can implement the complex spatio-temporal pattern learning of spike trains. The spike signals first propagate in the forward direction, and then are reconstructed in the reverse direction, and the synaptic weights are adjusted according to the reconstruction error. The algorithm is successfully applied to spike train patterns, the module parameters are analyzed, such as the neuron number and learning rate in the SNMs. In addition, the low reconstruction errors of DSBNs are shown by the experimental results.

Through reviewing the current international market for traditional Chinese medicine (TCM), this paper identified the internationalization challenges for TCM, including unclear therapeutic material basis and mechanism, difficulty of quality control, low preparation level, registration/policy barriers, and shortage of intellectual property. To deal with these challenges, suggestions were given including: (1) product innovation of TCM (study the TCM by using the methods and means of western medicine; innovate the basic theory of TCM; develop TCM health product); (2) standard innovation of TCM; (3) building big data platform of Chinese medicine (big data platform of TCM preparation; big data platform on the quality of TCM).

Computational modeling of neuronal morphologies is significant for understanding structure-function relationships and brain information processing in computational neuroscience. Using a gene regulatory network model, an evolutionary developmental approach is presented for efficient generation of 3D virtual neurons. This approach describes the developmental process of dendritic morphologies by locally inter-correlating morphological variables which can be represented by the dynamics of gene expression. Then, the multi-objective evolutionary algorithm with gene segmental duplication and divergence operators is applied to evolve the virtual neurons, which aims at generating virtual neurons that are as good as the experimentally traced real neurons in terms of statistical morphological measurements. We experimentally generated motoneurons and statistically compared between the real neurons and the generated virtual neurons by measuring a series of emergent morphological features. The results show that the generated virtual neurons are seemingly realistic, accurate, and further suggest that this approach is an efficient tool for understanding neural development and investigating the relation of neuronal structure to function in particular.

Recent advances in neurosciences have revealed that neural information in the brain is encoded through precisely timed spike trains, not only through the neural firing rate. This paper presents a new supervised, multi-spike learning algorithm for multilayer spiking neural networks, which can implement the complex spatio-temporal pattern learning of spike trains. The proposed algorithm firstly defines inner product operators to mathematically describe and manipulate spike trains, and then solves the problems of error function construction and backpropagation among multiple output spikes during learning. The algorithm is successfully applied to different temporal tasks, such as learning sequences of spikes and nonlinear pattern classification problems. The experimental results show that the proposed algorithm has higher learning accuracy and efficiency than the Multi-ReSuMe learning algorithm. It is effective for solving complex spatio-temporal pattern learning problems.

With the development of social networking applications, microblog has turned to be an indispensable online communication network in our daily life. For microblog users, recommending high quality information is a demanding service. Some microblog services encourage users to annotate themselves with tags, which are used to describe their interests or attributes. However, few users are willing to create tags and available tags are not fully exploited for microblog recommendation. Besides, following/follower relationship in microblog is asymmetric, which can be used not only for communicating with friends or acquaintances but also for getting information on particular subjects. So far, there is no microblog recommendation algorithm which employs all the above mentioned information. This paper aims to investigate a joint framework to combine tag correlation and user social relation for microblog recommendation. Our approach identifies users interests via their personal tags and social relations. More specifically, a user tag retrieval strategy is established to add tags for users without or with few tags, and the user-tag matrix is then built and user-tag weights are then obtained. In order to solve the problem of sparsity of the matrix, both inner and outer correlation between tags are investigated to update the user-tag matrix. Considering the significance of user social relation for microblog recommendation, a useruser social relation similarity matrix is constructed. Moreover, an iterative updating scheme is developed to get the final tag-user matrix for computing the similarities between microblogs and users. We illustrate the capability of our algorithm by making experiments on real microblog datasets. Experimental results show that the algorithm is effective for microblog recommendation.

Sleep stage classification can provide important reference factors in enhancing diagnosis and treatment of sleep disorders and sleep-related diseases. However, such classification tasks based on polysomnography are more complicated. This article tried a novel approach to deal with the polysomnography data by using spiking neural networks, including a coding scheme for complex spatio-temporal data and a multi-spike supervised algorithm for training our neural network to implement the learning goal of spike trains. This automatic sleep stage recognition approach can be applied to solve polysomnography data multi-classification problem and avoid manual handling whenever possible. In the experiments, the effects of the different network parameters on the sleep stage classification accuracy are analyzed, and the final results indicate that the proposed approach can be used to assist sleep diagnosis.

Epilepsy is a chronic disease, and seizures are a limited episode of brain dysfunction caused by abnormal discharges of cerebral neurons. Seizures are characterized by periodic episodes and unpredictability. The automatic detection and analysis of seizures based on Electroencephalogram (EEG) data is of grate important for accurately identifying patients and reducing the work intensity of medical staff. This paper presents an epilepsy and seizure classification approach based on multi-spike liquid state machines. Firstly, this paper describes the network structure and neuron model, and introduces the EEG data encoding method. In addition, the proposed approach is used to solve the multi-classification problems of epilepsy data and conduct related experiments. At last, the experimental results show that the proposed approach has a great ability to solve the classification problems of epilepsy EEG data, and has a high classification accuracy rate. The average recognition accuracy rate reaches 71.23%, which has certain value in real life.

Neurons are the basic building and computational units of the nervous system, and have complex and diverse spatial geometric structures. By solving the neuronal classification problem, we can further understand the characteristics of neurons and the process of information transmission. This paper presents a neuronal morphology classification approach based on locally cumulative connected deep neural networks, where 43 geometric features were extracted from two different neuron datasets and applied to classify types of neurons. Then, the effects of different parameters of deep learning networks on the performance of neuron classification were analyzed including mini-batch size, number of intermediate layers, and number of building blocks. The accuracy of the approach was also compared with that of the other mainstream machine learning approaches. The experimental results showed that the proposed approach is effective for solving complex neuronal morphology classification problems.

The neuron classification problem is significant for understanding structure-function relationships in computational neuroscience. By solving neuronal classification problem, we can further understand the characteristic of neurons and the process of information transmission. In the training process of the neuron geometry classifier, selecting the appropriate neuron feature data is the premise of obtaining good classification results. First, a data set of 200 three-dimensional neurons was constructed, and there were 10 different types of neurons. Secondly, according to the difference of the extracted neuron characteristic parameters, it is divided into two categories: global features and distribution features. Finally, the machine learning methods such as Logistic Regression, K-Nearest Neighbor, Naive Bayes, Decision Tree, Random Forest, Extremely Randomized Trees and Extreme Gradient Boosting are used to classify neurons, and the effects of different features on neuron classification results are analyzed. The experimental results show: (1) For the K-Nearest Neighbor and Naive Bayes, the distribution feature of the neuron is more critical than the global feature, and even if the effect of the combination of the two will not be improved; (2) The ensemble classifier based on decision trees, such as Random Forests, Extremely Randomized Trees and Extreme Gradient Boosting have better accuracy and stability for neuron classification.

As the third-generation artificial neural network, the spiking neural network is characterized by using an accurate neural model to simulate and transmit spikes in biological neurons. In this paper, we present a new image segmentation method based on spiking neural network with adaptive synaptic weights. Using the time-to-first-spike encoding strategy and the excitability of neurons in a receptive field, we sort the first spike time of neurons. If the neurons in the receptive field are more excitatory than the center neuron, the connection weights are positive numbers. Otherwise, the center neuron of the field inhibits the pixel information input, the connection weights are inhibitory. According to the weight rules of the neurons in the receptive field, we implement synaptic weight adaptation based on spike firing times. In the experiment, maximum Shannon entropy is used to evaluate image segmentation results. The segmentation results of different noise images are shown to verify the effectiveness of the proposed algorithm. Experimental results show that the algorithm has a good performance in noisy image processing.

Short texts have become a kind of prevalent source of information, and the classification of these short texts in various forms is valuable to many applications. However, most existing short text classification approaches circumvent the sparsity problem by extending short texts (or their feature representations) or exploiting additional information to adapt short texts to traditional text classification approaches. In this paper, we try to solve the sparsity problem of short text classification in a different direction: adapting the classifier to short texts. We propose a sparse representation short text classification method based on entropy weighted constraint. The main idea behind this study is to consider that the short texts are similar in potentially specific subspace. Specifically, we first introduce word embedding to represent the initial sparse representation dictionary, and then a fast feature subset selection algorithm is used to filter the dictionary. Again, we design an objective function based on sparse representation of entropy weight constraint. The optimal value of the objective function is obtained by Lagrange multiplier method. Finally, the distance between the short text to be classified and the short text in each class is calculated under the subspace, and the short text is classified according to three classification rules. Experiments over five datasets show that the proposed approach can effectively alleviate the problem of sparse feature of short text and is more efficient and effective than the existing short text classification method.

Measuring the similarity between short texts is made difficult by the fact that two texts that are semantically related may not contain any words in common. In this paper, we propose a novel short text similarity measure which aggregates coupled semantic relation (CSR) and strong classification features (SCF) to provide a richer semantic context. On the one hand, CSR considers both intra-relation (i.e. co-occurrence of terms based on the modified weighting strategy) and inter-relation (i.e. dependency of terms via paths that connect linking terms) between a pair of terms. On the other hand, Based on SCF for similarity measure is established based on the idea that the more similar two texts are, the more features of strong classification they share. Finally, we combine the above two techniques to address the semantic sparseness of short text. We carry out extensive experiments on real world short texts. The results demonstrate that our method significantly outperforms baseline methods on several evaluation metrics.

China promotes the development of the offshore wind industry to reduce CO2 emissions, tackle air pollution, commit to the Paris Climate Agreement and develop a strategic emerging industry. The installed capacity of offshore wind power in China reached 4445 MW in 2018 which was ranked third in the world. Big developers dominated the offshore wind energy market with domestic turbines. Many projects are under construction. The offshore wind industry in China has experienced four stages of price policy: demonstration, concession, feed-in tariff and market-oriented competition policy. Nevertheless, it is impossible to expand the installed capacity, lower the on-grid price (cost) and reduce the subsidy for the offshore wind power industry at the same time. This is the trilemma (impossible trinity) that needs to be addressed by the price policy. In the past decade, China has implemented an evolving price policy, i.e., a system and mechanism that encourage firms to invest in the offshore wind industry to expand the capacity of the industry by setting price and providing subsidy and other benefits. An overall evaluation based on the indicators of installed capacity, price, subsidy, spatial distribution, technology and industrial linkage shows that the price policy has been effective in balancing capacity, price and subsidy up to now. However, lowering the price and reducing the subsidy will be the major challenges that China has to overcome in the coming years in order to sustain its current growth trend. To boost the development of its offshore wind industry further, China needs to implement a market-oriented competition price policy and mechanism, learn from the experience of price policy evolution in European countries and open the market to foreign investors.

Since biological neurons have complex and diverse spatial geometric structures, classifying neurons according to their geometries has been an important issue. At present, the main approaches of neuron classification generally extract the structural features of neurons by the specified methods, and then use such features for classification. However, there are mainly two problems for these approaches. One is that there is no feature extraction standard of neuronal morphology, and the other is that a lot of useful information for neuron classification may be lost. Therefore, using the convolutional neural network model, this paper proposes a new three-dimensional (3D) neuronal morphology classification approach without geometric feature extraction. This approach first converts SWC format data of neuron into the scaled 3D neuronal graphics, and obtains the voxel data of neuronal morphology, and then uses convolutional neural network for training and classification. The experimental results show that this approach can classify the brain region cholinergic neurons of drosophila melanogaster, and obtains better classification accuracy.

The liquid state machines have been well applied for solving large-scale spatio-temporal pattern recognition problems. The current supervised learning algorithms for the liquid state machines of spiking neurons generally only adjust the synaptic weights in the output layer, the synaptic weights of input and hidden layers are generated in the process of network structure initialization and no longer change. That is to say, the hidden layer is a static network, which usually neglects the dynamic characteristics of the liquid state machines. Therefore, a new supervised learning algorithm for the liquid state machines of spiking neurons based on bidirectional modification is proposed, which not only adjusts the synaptic weights in the output layer, but also changes the synaptic weights in the input and hidden layers. The algorithm is successfully applied to the spike trains learning. The experimental results show that the proposed learning algorithm can effectively learn the spike trains pattern with different learning parameter.

Clustering is one of the most basic unsupervised learning problems in the field of machine learning and its main goal is to separate data into clusters with similar data points. Because of various redundant and complex structures for the raw data, the general algorithm usually is difficult to separate different clusters from the data and the effect is not obvious. Deep learning is a technology that automatically learns nonlinear and more conducive clustering features from complex data structures. This paper presents a deep clustering algorithm based on self-organizing map neural network. This method combines the feature learning ability of stacked auto-encoder from the raw data and feature clustering with unsupervised learning of self-organizing map neural network. It is aim to achieve the greatest separability for the data space. Through the experimental analysis and comparison, the proposed algorithm has better recognition rate, and improves the clustering performance on low and high dimension data.

The neuron classification problem is significant for understanding structure-function relationships in computational neuroscience. Advances in recent years have accelerated the speed of data collection, resulting in a large amount of data on the geometric, morphological, physiological, and molecular characteristics of neurons. These data encourage researchers to strive for automated neuron classification through powerful machine learning techniques. This paper extracts a statistical dataset of 43 geometrical features obtained from 116 human neurons, and proposes a neuronal morphology classification approach based on deep residual neural networks with feature scaling. The approach is applied to classify 18 types of human neurons and compares the accuracy of different number of residual block. Then, we also compare the accuracy between the proposed approach and other mainstream machine learning approaches, the classification accuracy of our approach is 100% in the training set and the testing set accuracy is 76.96%. The experimental results show that the deep residual neural network model has better classification accuracy for human neurons.

A reliable assessment model can help financial institutions to increase profits and reduce losses. In credit data, classes of the data are extremely imbalanced owing to the small sample size of bad customers. In this paper, we propose a credit risk assessment algorithm using deep neural networks with clustering and merging, to achieve a balanced dataset and judge whether customer can be granted loans. In the algorithm, the majority class samples are divided into several subgroups by k-means clustering algorithm, each subgroup is merged with the minority class samples to produce several balanced subgroups, and these balanced subgroups are classified using deep neural networks respectively. In the experiments, we analyze influences of the model parameters and data sampling methods on the model performance, and compare classification ability of different models. The experimental results show that the proposed algorithm has a higher prediction accuracy in credit risk assessment.

Inspired by the evolution of biological brains, the study of neurally-driven evolved autonomous agents has received more and more attention. In this paper, we propose an evolutionary algorithm for neurally-driven autonomous agents, each agent is controlled by a spiking neural network, and the network receives the sensory inputs and processes the motor outputs through the encoded spike information. The controlling spiking neural networks of autonomous agents are developed by the evolutionary algorithms that apply some of genetic operators and selection to a population of agents that undergo evolution. The corresponding food gathering experiment results show that the autonomous agents appear intelligent behaviours for the simulation environment. Additionally, the parameters of networks and agents play an important role in the evolutionary process.

The purpose of supervised learning with temporal encoding for spiking neurons is to make the neurons emit arbitrary spike trains in response to given synaptic inputs. Recent years, the supervised learning algorithms based on synaptic plasticity have developed rapidly. As one of the most efficient supervised learning algorithms, the remote supervised method (ReSuMe) uses the conventional pair-based spike-timing-dependent plasticity rule, which depends on the precise timing of presynaptic and postsynaptic spikes. In this paper, using the triplet-based spike-timing-dependent plasticity, which is a powerful synaptic plasticity rule and acts beyond the classical rule, a novel supervised learning algorithm, dubbed T-ReSuMe, is presented to improve ReSuMe’s performance. The proposed algorithm is successfully applied to various spike trains learning tasks, in which the desired spike trains are encoded by Poisson process. The experimental results show that T-ReSuMe has higher learning accuracy and fewer iteration epoches than the traditional ReSuMe, so it is effective for solving complex spatio-temporal pattern learning problems.

Spiking neural networks are shown to be suitable tools for the processing of spatio-temporal information. However, due to their intricately discontinuous and implicit nonlinear mechanisms, the formulation of efficient supervised learning algorithms for spiking neural networks is difficult, which has become an important problem in the research area. This paper presents a new supervised, multi-spike learning algorithm for spiking neurons, which can implement the complex spatio-temporal pattern learning of spike trains. The proposed algorithm firstly defines nonlinear inner products operators to mathematically describe and manipulate spike trains, and then derive the learning rule from the common Widrow-Hoff rule with the nonlinear inner products of spike trains. The algorithm is successfully applied to learn sequences of spikes. The experimental results show that the proposed algorithm is effective for solving complex spatio-temporal pattern learning problems.

The online learning algorithm is shown to be more appropriate and effective for the processing of spatiotemporal information, but very little researches have been achieved in developing online learning approaches for spiking neural networks. This paper presents an online supervised learning algorithm based on nonlinear spike train kernels to process the spatiotemporal information, which is more biological interpretability. The main idea adopts online learning algorithm and selects a suitable kernel function. At first, the Laplacian kernel function is selected, however, in some ways, the spike trains expressed by the simple kernel function are linear in the postsynaptic neuron. Then this paper uses nonlinear functions to transform the spike train model and presents the detail experimental analysis. The proposed learning algorithm is evaluated by the learning of spike trains, and the experimental results show that the online nonlinear spike train kernels own a super-duper learning effect.

In this paper, we present a semi-supervised clustering method for microblog in which both word-level and microblog document-level constraints are automatically generated totally based on statistical information rather than any kind of external knowledge. The key idea is first to explore term correlation data, which investigates both inter and intra correlation of words, and the initial similarity between words can therefore be deduced. And then an iterative method is established to calculate both word similarity and microblog similarity. The mechanism of incorporating dual constraints is presented based on word similarity and microblog similarity. We then formulate short text clustering problem as a non-negative matrix factorization based on dual constraints. Empirical study of two real-world dataset shows the superior performance of our framework in handling noisy and microblogs.

Inspired by the structure and behavior of the human visual system, an automatic image segmentation algorithm based on a spiking neural network model is proposed. At first, the image pixel values are encoded into the timing of spikes of neurons using the time-to-first-spike coding strategy. Then the segmentation model of spiking neural networks is applied to generate the matrix of spike timing for the visual image. Finally, using the maximum Shannon entropy as the fitness function of genetic algorithm, the evolved segmentation threshold is obtained to segment the visual image. The experimental results show that the method can obtain the optimum segmentation threshold, and achieve satisfactory segmentation results for different images.

Neuronal morphology is significant for understanding structure-function relationships and brain information processing in computational neuroscience. So it is very important to simulate neuronal morphology completely and accurately. In this paper, we present a novel approach for efficient generation of 3D virtual neurons using genetic regulatory network model. This approach describes dendritic geometry and topology by locally inter-correlating morphological variables which can be represented by the dynamics of gene expression. The experimental results show that the generating virtual neurons that are anatomically indistinguishable and accurate from experimentally traced real neurons.