Search

P systems are distributed, parallel biological computing models. Tissue P systems are an important variant of membrane computing model, where the environment can provide powerful energy support for cells. Hence, the environment plays a critical role. Nevertheless, in actual biological tissues, there exists a peculiar biological phenomenon called "homeostasis"; that is, the internal organisms maintain stable, thereby reducing their dependence on external conditions (i.e., the environment). In this work, considering cell separation, we construct a novel variant to simulate the mechanism of biological homeostasis, called homeostasis tissue-like P systems with cell separation. In this variant, objects in the environment are finite, and certain energy changes occur inside the cells; moreover, an exponential workspace can be obtained with cell separation in feasible time. The computational power of this model is studied by simulating register machines, and the results show that the variant is Turing universal as number computing devices. Furthermore, to explore the computational efficiency of the model, we use the variant to solve a classic NP-complete problem, the SAT problem, obtaining a uniform solution with a rule length of at most 3.

Tissue-like P systems are a type of distributed parallel computing models inspired by actual biological tissue. In this paper, we consider a new variant of tissue-like P systems, which is called tissue-like P systems with evolutional symport/antiport rules. Unlike traditional models of this type, in the new P systems, objects can change during transmission. In biology, an organism that is in “homeostasis” reduces its dependence on external conditions, thereby keeping it relatively constant and maintaining a relatively stable internal environment. In our work, we remove the assumption that the quantity of objects in the environment is infinite, reducing the influence of the environment on this system, so the environment no longer provides powerful energy for cells. Moreover, the time-free mode is introduced into this type of P systems, which makes the constructed systems more robust. We investigate the computational power and computational efficiency of the constructed system. Specifically, by simulating register machines, such a P system can generate any Turing computable set of numbers. In addition, we prove that this constructed system can efficiently solve the $\mathcal {SAT} $ problem. Although we restrict P systems and consider time-free manner, the results show that this system is not only Turing universal, but also can solve NP-complete problem.

Diabetic retinal image classification aims to conduct diabetic retinopathy automatically diagnosing, which has achieved considerable improvement by deep learning models. However, these methods all rely on sufficient network training by large scale annotated data, which is very labor-expensive in medical image labeling. Aiming to overcome these drawbacks, this paper focuses on embedding self-supervised framework into unsupervised deep learning architecture. Specifically, we propose a Self-supervised Fuzzy Clustering Network (SFCN) by a feature learning module, reconstruction module, and a fuzzy self-supervision module. The feature learning and reconstruction modules ensure the representative ability of the network, and fuzzy self-supervision module is in charge of further providing the training direction for the whole network. Furthermore, three losses of reconstruction, self-supervision, and fuzzy supervision jointly optimize the SFCN under an unsupervised manner. To evaluate the effectiveness of the proposed method, we implement the network on three widely used retinal image datasets, which results demonstrate the satisfied performance on unsupervised retinal image classification task.

The deep convolutional neural networks (DCNN) require large number of training data to avoid overfitting, which makes it unsuitable for processing small-scale image datasets. The transfer learning using DCNN (TCNN) reuses pre-trained layers to generate a mid-level image representation so that the optimization of more than millions CNN parameters can be avoided. By this way, overfitting problem in small-scale data can be alleviated. However, although now many public DCNNs have been trained and can be reused, the existing TCNNs are formed by only a single pre-trained DCNN structure and cannot make full use of multiple structures of pre-trained DCNNs. At the same time, the existing ensemble CNNs have not enough good representation ability. To address this problem, we combine the conventional ideas of ensemble CNNs and propose three ensemble TCNNs (TECNN). They are the voting method based on the combination of all TCNNs, the PickOver method by finding the optimal combination, and weighted method by finding weighted combination. Different from the existing ensemble CNNs, the proposed methods do not need to retrain the component CNNs and generate ensemble transferring representations by transferring the pre-trained mid-level parameters. The mathematical models of those three methods are also provided. Their versions of using fine-tuning are also compared in the experiments. In addition, we replace the Softmax classifier with ensemble linear classifiers in the full-connection layer. They outperform the current state of the art algorithms on Caltech ImageNet and some internet image data. All this research has released as an open source library called Transferring Image Ensemble Representations using Deep Convolutional Neural Networks (TECNN). The source codes and relevant datasets in different versions are available from: http://www.cquptshuyinxia.com/TECNN.html .

P systems with active membranes are a class of bioinspired computing models, where the rules are used in the non-deterministic maximally parallel manner. In this paper, first, a new variant of timed P systems with active membranes is proposed, where the application of rules can be regulated by promoters with only two polarizations. Next, we prove that any Turing computable set of numbers can be generated by such a P system in the time-free way. Moreover, we construct a uniform solution to the$\mathcal{SAT}$problem in the framework of such recognizer timed P systems in polynomial time, and the feasibility and effectiveness of the proposed system is demonstrated by an instance. Compared with the existing methods, the P systems constructed in our work require fewer necessary resources and RS-steps, which show that the solution is effective toNP-complete problem.

Adjusting superheat is very important in the production of aluminum electrolysis. However, due to the influence of the detection equipment and environment, there usually exist noise data which might have effects on the superheat adjustment. CNSMO(Class Noise based Sequential Minimal Optimization) [1] has a good performance in processing the data containing noise and prediction of superheat, which contains a large number of noise samples such that the generalizability of conventional SVMs deteriorates. The main reason is that the kernel mapping of the noise samples is likely to lead to overfitting in conventional SVMs [2]-[4]. However, ineffectiveness of CNSMO appears in asymmetric data. To deal with the problem, we optimize the relative density threshold and propose the IRDNF-SMO (Improved Relative Density Noise Filter based SMO algorithm). In the IRDNF-SMO, not only the relative density model is used for class noise detection, but the threshold of the relative density is optimized instead of setting to the fixed value such that the ineffectiveness is alleviated in asymmetric data. The experimental results on industry data sets and benchmark data sets demonstrated that the proposed algorithm has higher prediction accuracy in the data sets.

The "location difference of multiple distances" and a method LDMDBA are proposed.LDMDBA has a time complexity of O(logdnlogn) and does not rely on tree structures.Only LDMDBA can be efficiently applied to high dimensional data.LDMDBA has a time complexity of (logdlogn) for predicting a new data point.LDMDBA has very good stability and can be applied to large databases. k-nearest neighbors (kNN) classifiers are commonly used in various applications due to their relative simplicity and the absence of necessary training. However, the time complexity of the basic algorithm is quadratic, which makes them inappropriate for large scale datasets. At the same time, the performance of most improved algorithms based on tree structures decreases rapidly with increase in dimensionality of dataset, and tree structures have different complexity in different datasets. In this paper, we introduce the concept of "location difference of multiple distances, and use it to measure the difference between different data points. In this way, location difference of multiple distances based nearest neighbors searching algorithm (LDMDBA) is proposed. LDMDBA has a time complexity of O(logdnlogn) and does not rely on a search tree. This makes LDMDBA the only kNN method that can be efficiently applied to high dimensional data and has very good stability on different datasets. In addition, most of the existing methods have a time complexity of O(n) to predict a data point outside the dataset. By contrast, LDMDBA has a time complexity of O(logdlogn) to predict a query point in datasets of different dimensions, and, therefore, can be applied in real systems and large scale databases. The effectiveness and efficiency of LDMDBA are demonstrated in experiments involving public and artificial datasets.

This paper presents analysis of applicability and performance of the Euclidean distance in relation to the dimensionality of the space. The effect of dimensionality on the behavior of Euclidean distance is explored; Furthermore, it is shown that the minimum distance approaches the maximum distance under a broader set of conditions without requiring the calculation of variance of random variables. It is demonstrated that the minimum distance approaches the maximum distance even for some low dimensional distributions, such as normal distribution. Many proposed measures not based directly on Euclidean distance cannot enlarger the difference between closest point and farthest point. The analysis has been performed on a wide range of artificial and publicly available datasets. As the variables of different distributions have different convergence rates, the results should not be interpreted to mean that the Euclidean distance is not applicable. In fact, it is shown in experiments that the Euclidean distance is very useful in the noncentral t-distribution even for the dimensionality higher than 10,000. Furthermore, it is observed that the behavior of Euclidean distance becomes more useful with increased number of samples.

As SVM (support vector machine) has good generalizability, it has been successfully implemented in a variety of applications. Yet in the process of resolving its mathematical model, SVM needs to compute the kernel matrix. The dimension of the kernel matrix is equal to the number of records in the training set, so computing it is very costly in terms of memory. Although some improved algorithms have been proposed to decrease the need for memory, most of these algorithms need iterative computations that cost too much time. Since the existing SVM models fail to perform well regarding both runtime and space needed, we propose a new method to decrease the memory consumption without the need for any iteration. In the method, an effective measure in kernel space is proposed to extract a subset of the database that includes the support vectors. In this way, the number of samples participating in the training process decreases, resulting in an accelerated training process which has a time complexity of only O(nlogn). Another advantage of this method is that it can be used in conjunction with other SVM methods. The experiments demonstrate effectiveness and efficiency of SVM algorithms that are enhanced with the proposed method.

As a support vector machine (SVM) has good generalization ability, it has been implemented in various applications. Yet in the process of resolving the mathematical model, it needs to compute the kernel matrix, the dimension of which is equal to the number of data points in the dataset, thereby costing a very high amount of memory. Some improved algorithms are proposed to extract the boundary of the dataset so that the number of data points participating in the training process decreases and the training process can be accelerated. But the prediction accuracy of most of these algorithms is so low that many support vectors are discarded. Moreover, those methods all need to perform the main computation by the kernel function in linear feature space, which increases the computational cost. In this paper, the concept “relative density” is proposed to extract the subset containing support vectors. The measure “relative density” is designed to be more meticulous so that the new method performs more precisely than existing methods. The proposed method makes use of the fact that it has good local characteristics to perform the computations in original space without having to use any kernel function. Therefore, efficiency is also improved. Furthermore, the proposed method can be used to detect noise data, by which an inseparable problem can be transformed into a separable problem so that cross validation can be avoided in various SVM algorithms. This is an advantage that none of the existing SVM methods has. Yet another advantage of this method is that it can be considered as a framework to be used in various SVM methods. This paper presents the details of the proposed accelerated algorithm, having a time complexity of O(n log n), that decreases training time significantly without decreasing prediction accuracy. The effectiveness and efficiency of the method is demonstrated through experiments on artificial and public datasets.

Tissue P systems are a class of computing models inspired by intercellular communication, where the rules are used in the nondeterministic maximally parallel manner. As we know, the execution time of each rule is the same in the system. However, the execution time of biochemical reactions is hard to control from a biochemical point of view. In this work, we construct a uniform and efficient solution to the SAT problem with tissue P systems in a time-free way for the first time. With the P systems constructed from the sizes of instances, the execution time of the rules has no influence on the computation results. As a result, we prove that such system is shown to be highly effective for NP-complete problem even in a time-free manner with communication rules of length at most 3.