Abstract Synthetic aperture radar tomography (TomoSAR) has shown significant potential for the 3D Reconstruction of buildings, especially in critical areas such as topographic mapping, urban planning, and disaster monitoring. In practical applications, the constraints of observation trajectories frequently lead to the acquisition of a limited dataset of sparse SAR images, presenting challenges for TomoSAR 3D Reconstruction and affecting its signal‐to‐noise ratio and elevation resolution performance. The study introduces a cascade adversarial strategy based on the Conditional Generative Adversarial Network (CGAN), optimised explicitly for sparse observation trajectories. In the preliminary phase of the CGAN, the U‐Net architecture was employed to capture more global information and enhance image detail recovery capability, which is subsequently utilised in the cascade refinement network. The ResNet34 residual network in the advanced network stage was adopted to bolster feature extraction and image generation capabilities further. Based on experimental validation performed on the curated TomoSAR 3D super‐resolution dataset tailored for buildings, the findings reveal that the methodology yields a notable enhancement in image quality and accuracy compared to other techniques.

Background: Code pre-training and large language models are heavily dependent on data quality. These models require a vast, high-quality corpus matching text descriptions with codes to establish semantic correlations between natural and programming languages. Unlike NLP tasks, code comment heavily relies on specialized programming knowledge and is often limited in quantity and variety. Thus, most widely available open-source datasets are established with compromise and noise from platforms, such as StackOverflow, where code snippets are often incomplete. This may lead to significant errors when deploying the trained models in real-world applications. Aims: Comments as a substitute for queries are used to build code search datasets from GitHub. While comments describe code functionality and details, they often contain noise and differ from queries. Thus, our research focuses on improving the syntactic and semantic quality of code comments. Method: We propose a comment-based data refinement framework CoCoRF 1 via an unsupervised and supervised co-learning technique. It applies manually defined rules for syntax filtering and constructs a bootstrap query corpus via the WTFF algorithm for training the TVAE model for further semantic filtering. Results: Our study shows that CoCoRF achieves high efficiency with less computational resource, and outperforms comparison models in DeepCS code search task. Conclusions: Our findings indicate that the CoCoRF framework significantly improves the performance of code search tasks by enhancing the quality of code datasets.

Nowadays, with the application of 5G, graph-based recommendation algorithms have become a research hotspot. Graph neural networks encode the graph structure information in the node representation through an iterative neighbor aggregation method, which can effectively alleviate the problem of data sparsity. In addition, more and more information graph can be used in collaborative filtering recommendation, such as user social information graph, user or item attributed information graph, etc. In this paper, we propose a novel heterogeneous information fusion based graph collaborative filtering method, which models graph data from different heterogeneous graph, and combines them together to enhance presentation learning. Through information propagation and aggregation, our model can learn the latent embeddings effectively and enhance the performance of recommendation. Experimental results on different datasets validate the outperformance of the proposed framework.

Generative Adversarial Nets (GAN) has been a popular research topic in processing of images, speech, texts, and videos, and many other fields.However, GAN still has some drawbacks such as unstable training and mode collapse.To address these challenges, this paper proposes an auto-encoding GAN, which is composed of a set of generators, a discriminator, an encoder and a decoder.A set of generators is responsible for learning different modes, accelerating the convergence of the model and preventing model collapse.The discriminator is used to distinguish between real samples and generated ones.In order to improve feature representation of the encoder and prevent multiple generators from covering a certain mode, an approach consisting of three phases is proposed accordingly.First, a clustering algorithm is presented to perceive the distribution of real and generated samples.Then, cluster center matching is utilized to keep consistency of the distribution of real and generated samples.Finally, the encoder and decoder are jointly optimized by the generated and real samples.Therefore, the encoder can map the generated and real samples to the embedding space so as to encode distinguishable features, and the decoder can distinguish from which generator the generated samples come and from which mode the real samples come.Experiments are conducted on image datasets to verify effectiveness of the auto-encoding GAN for reducing mode collapse and enhancing feature representation.

Graph Convolutional Network (GCN) is a new method for extracting, learning, and inferencing graph data that builds an embedded representation of the target node by aggregating information from neighbouring nodes. GCN is decisive for node classification and link prediction tasks in recent research. Although the existing GCN performs well, we argue that the current design ignores the potential features of the node. In addition, the presence of features with low correlation to nodes can likewise limit the learning ability of the model. Due to the above two problems, we propose Feature Recommendation Strategy (FRS) for Graph Convolutional Network in this paper. The core of FRS is to employ a principled approach to capture both node-to-node and node-to-feature relationships for encoding, then recommending the maximum possible features of nodes and replacing low-correlation features, and finally using GCN for learning of features. We perform a node clustering task on three citation network datasets and experimentally demonstrate that FRS can improve learning on challenging tasks relative to state-of-the-art (SOTA) baselines.

Graph Convolutional Network (GCN) is a powerful emerging deep learning technique for learning graph data. However, there are still some challenges for GCN. For example, the model is shallow; the performance is poor when labelled nodes are severely scarce. In this paper, we propose a Multi-Semantic Aligned Graph Convolutional Network (MSAGCN), which contains two fundamental operations: multi-angle aggregation and semantic alignment, to resolve two challenges simultaneously. The core of MSAGCN is the aggregation of nodes that belong to the same class from three perspectives: nodes, features, and graph structure, and expects the obtained node features to be mapped nearby. Specifically, multi-angle aggregation is applied to extract features from three angles of the labelled nodes, and semantic alignment is utilised to align the semantics in the extracted features to enhance the similar content from different angles. In this way, the problem of over-smoothing and over-fitting for GCN can be alleviated. We perform the node clustering task on three citation datasets, and the experimental results demonstrate that our method outperforms the state-of-the-art (SOTA) baselines.

Abstract As a two-dimensional formal method, graph grammar is widely used in defining various visual programming languages. This paper presents a new graph grammar formalism called coordinate graph grammar (CGG). CGG is extended from the edge-based graph grammar (EGG) by introducing the spatial mechanism into the theoretical framework, which consists of continuous coordinate graph grammar (cCGG) and discrete coordinate graph grammar (dCGG). By combining quantitative and qualitative spatial semantics in one framework, CGG provides strong expressiveness and flexibility for specifying various spatial graphs. This paper focuses on several important issues on the new formalism. First, the theoretical framework of CGG is given. Second, two matching algorithms for cCGG and dCGG are proposed, which use the spatial relationships between nodes to narrow down the search space during parsing. Finally, an application of CGG is demonstrated, which generates parsable flowcharts in a uniform layout.

Context-sensitive graph grammars have been suitable formalisms for specifying visual programming languages, as they are intuitive, sufficient expressive and equipped with parsing mechanisms. Parsing has been a fundamental issue in the research of context-sensitive graph grammars. However, the existent parsing algorithms are either inefficient or confined to a minority of graph grammars. This paper presents two strategies for general parsing algorithms, one is context matching, and the other is partitioning of productions. Through narrowing down the searching space of potential redexex, the two strategies can considerably improve the parsing performance.

Summary As a two‐dimensional formal tool, graph grammars are capable of handling the layout problems of visual programming languages. Based on an edge‐based graph grammar (EGG), this paper proposes a novel layout approach that uses the unique features of EGG and overcomes the weakness of existing layout approaches. In order to make the approach rigorous yet concise, the graph grammar mechanisms with layout constraints and quantitative analysis techniques are combined together as an integrity. First, the basic notions of EGG are briefly introduced; second, the layout approach is presented that consists of two phases, ie, bottom‐up parsing and top‐down derivation. Finally, a case study is given by taking the standard flowchart as an example to demonstrate the working process of the proposed approach.

Context-sensitive graph grammars have been rigorous formalisms for specifying visual programming languages, as they possess sufficient expressive powers and intuitive forms. Efficient parsing mechanisms are essential to these formalisms. However, the existent parsing algorithms are either inefficient or confined to a minority of graph grammars. This paper introduces the notion of partial precedence, defines the partial precedence graph of a graph grammar and theoretically unveils the existence of a valid parsing path conforming to the topological orderings of the partial precedence graph. Then, it provides algorithms for computing the partial precedence graph and presents an approach to improving general parsing algorithms with the graph based on the drawn conclusion. It is shown that the approach can considerably improve the efficiency of general parsing algorithms.

In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.

Analyzing the underlying social network is very important for the development of online applications. Owing to the increasingly growing size of these networks, parallel techniques play important roles in many network analysis tasks. In this paper, we explore the link sign prediction problem in large-scale online social networks, and propose a parallel approach, called PLSP, to solve the problem. Specifically, we first extract a set of features that serve as a base for prediction. Experiments on several real datasets show that these features outperform those proposed by existing methods in predictive accuracy. Next, we present two speedup strategies, i.e. dataset division and feature selection, to shorten the training time. Experimental evaluations show that our parallel approach is much faster than the traditional non-parallel method and achieves higher predictive accuracy than other methods at the same time.

Data fusion is currently used extensively in information retrieval for various tasks. It has proved to be a useful technology because it is able to improve retrieval performance frequently. However, in almost all prior research in data fusion, static search environments have been used, and dynamic search environments have generally not been considered. In this article, we investigate adaptive data fusion methods that can change their behavior when the search environment changes. Three adaptive data fusion methods are proposed and investigated. To test these proposed methods properly, we generate a benchmark from a historic T ext RE trieval Conference data set. Experiments with the benchmark show that 2 of the proposed methods are good and may potentially be used in practice.

The purpose of supervised learning with temporal encoding for spiking neurons is to make the neurons emit a specific spike train encoded by the precise firing times of spikes. If only running time is considered, the supervised learning for a spiking neuron is equivalent to distinguishing the times of desired output spikes and the other time during the running process of the neuron through adjusting synaptic weights, which can be regarded as a classification problem. Based on this idea, this letter proposes a new supervised learning method for spiking neurons with temporal encoding; it first transforms the supervised learning into a classification problem and then solves the problem by using the perceptron learning rule. The experiment results show that the proposed method has higher learning accuracy and efficiency over the existing learning methods, so it is more powerful for solving complex and real-time problems.

This paper, with an aim at improving neural networks' generalization performance, proposes an effective neural network ensemble approach with two novel ideas. One is to apply neural networks' output sensitivity as a measure to evaluate neural networks' output diversity at the inputs near training samples so as to be able to select diverse individuals from a pool of well-trained neural networks; the other is to employ a learning mechanism to assign complementary weights for the combination of the selected individuals. Experimental results show that the proposed approach could construct a neural network ensemble with better generalization performance than that of each individual in the ensemble combining with all the other individuals, and than that of the ensembles with simply averaged weights.

This paper proposes a set of adaptive learning rules for binary feedforward neural networks (BFNNs) by means of the sensitivity measure that is established to investigate the effect of a BFNN's weight variation on its output. The rules are based on three basic adaptive learning principles: the benefit principle, the minimal disturbance principle, and the burden-sharing principle. In order to follow the benefit principle and the minimal disturbance principle, a neuron selection rule and a weight adaptation rule are developed. Besides, a learning control rule is developed to follow the burden-sharing principle. The advantage of the rules is that they can effectively guide the BFNN's learning to conduct constructive adaptations and avoid destructive ones. With these rules, a sensitivity-based adaptive learning (SBALR) algorithm for BFNNs is presented. Experimental results on a number of benchmark data demonstrate that the SBALR algorithm has better learning performance than the Madaline rule II and backpropagation algorithms.

The sensitivity of a neural network's output to its parameter variation is an important issue in both theoretical researches and practical applications of neural networks. This paper proposes a quantified sensitivity measure of the Radial Basis Function Neural Networks (RBFNNs) to input variation. The sensitivity is defined as the mathematical expectation of squared output deviations caused by input variations. In order to quantify the sensitivity, the input is treated as a statistical variable and a numerical integral technique is employed to approximately compute the expectation. Experimental verifications are run and the results show a very good agreement between the proposed sensitivity computation and computer simulation. The quantified sensitivity measure could be helpful as a general tool for evaluating RBFNNs' performance.

We investigate the problem of adaptive traffic light control using real-time traffic information collected by a wireless sensor network (WSN). Existing studies mainly focused on determining the green light length in a fixed sequence of traffic lights. In this paper, we propose an adaptive traffic light control algorithm that adjusts both the sequence and length of traffic lights in accordance with the real time traffic detected. Our algorithm considers a number of traffic factors such as traffic volume, waiting time, vehicle density, etc., to determine green light sequence and the optimal green light length. Simulation results demonstrate that our algorithm produces much higher throughput and lower vehicle's average waiting time, compared with a fixed-time control algorithm and an actuated control algorithm. We also implement proposed algorithm on our transportation testbed, iSensNet, and the result shows that our algorithm is effective and practical.

Poor design has been a major source of software security problems. Rigorous and designer-friendly methodologies for modeling and analyzing secure software are highly desirable. A formal method for software development, however, often suffers from a gap between the rigidity of the method and the informal nature of system requirements. To narrow this gap, this paper presents a UML-based framework for modeling and analyzing security threats (i.e. potential security attacks) rigorously and visually. We model the intended functions of a software application with UML statechart diagrams and the security threats with sequence diagrams, respectively. Statechart diagrams are automatically converted into a graph transformation system, which has a well-established theoretical foundation. Method invocations in a sequence diagram of a security threat are interpreted as a sequence of paired graph transformations. Therefore, the analysis of a security threat is conducted through simulating the state transitions from an initial state to a final state triggered by method invocations. In our approach, designers directly work with UML diagrams to visually model system behaviors and security threats while threats can still be rigorously analyzed based on graph transformation.

How to design proper architectures of neural networks for solving given problems is an important issue in neural network research. Nowadays, the existing training algorithms of neural networks only focus on adjusting neural networks' weights to improve training accuracy, and few of them adaptively adjust the networks' architecture. However, the architecture is indeed very critical for training neural networks to have high performance and needs to be coped with in the training process. In this paper, we present a new training algorithm of Madalines, which takes not only weight but also architecture adjusting into consideration. The algorithm can thus train Madalines with smaller architecture and higher generalization ability. Experimental results have demonstrated that our algorithm is effective.

Ensemble learning to construct learners in regression and classification has practically and theoretically been proved to be able to improve the generalization capability of the learners. Nowadays, most neural network ensembles are obtained by manipulating training data and networks' architecture etc, such as Bagging, Boosting, and other methods like evolutionary techniques. In this paper, a new method to construct neural network ensembles is presented, which aims at selecting, by means of output sensitivity of an individual network, the most diverse members from a pool of trained networks. Conceptually, the sensitivity reflects a network's output behavior at a given data point, for example, the trend of the network's output nearby. So the sensitivity can be helpful to explicitly measure the output diversity among individuals in the pool. In our research, Multilayer Perceptrons (MLPs) are focused on, and the sensitivity is adopted as the partial derivative of an MLP's output to its input at data point. Based on the sensitivity, we developed four different measures for the selection of the most diverse individuals from a given pool of trained MLPs. Some experiments on the UCI benchmark data have been conducted, and the comparisons of our results with those from Bagging and Boosting show that our method has some advantages over the existing ensemble methods in ensemble size and generalization performance.

Multiple Classifier Systems (MCSs) have been shown theoretically and empirically to outperform a single classifier in many applications. However, many ensemble training algorithms sometimes create a very large MCS which is combined by many individual classifiers. A large MCS not only consumes computational resources but also decreases the effectiveness. One of the solutions is the pruning method. It reduces the number of individual classifiers inside an MCS that maintains the performance well or is just slightly worse than the original one. In this paper, a new pruning method, called NNEPSM, for Neural Network ensemble based on a sensitivity measure is proposed. The classifiers which have less impact to the final output of MCS will be removed. The advantages of this method include efficient performance, low-complexity and independence on training method. NNEPSM has been applied in Web applications and other benchmark dataset. The experimental results showed that our approach performs well using different datasets.

Madalines with discrete input, output and activation function are suitable for solving many inherently discrete problems and meanwhile are more facile for implementing and less complex for computing than their continuous counterparts. However, there has not yet been efficient training algorithm for Madalines. By now the most popular one must be the MRII proposed by Winter and Widrow [1] [2]. In this paper, based on the MRII, we present a new algorithm to improve the training accuracy and convergence for Madalines. In our algorithm, a sensitivity measure is used to replace the confidence measure used in MRII so as to better satisfy the minimal disturbance principle. Computer simulations are run to verify the effects of our training algorithm. The experimental verification shows that our algorithm has higher success rate and faster convergence speed than the MRII.

The sensitivity of a neural network's output to its input and weight perturbations is an important measure for evaluating the network's performance. In this letter, we propose an approach to quantify the sensitivity of Madalines. The sensitivity is defined as the probability of output deviation due to input and weight perturbations with respect to overall input patterns. Based on the structural characteristics of Madalines, a bottom-up strategy is followed, along which the sensitivity of single neurons, that is, Adalines, is considered first and then the sensitivity of the entire Madaline network. By means of probability theory, an analytical formula is derived for the calculation of Adalines' sensitivity, and an algorithm is designed for the computation of Madalines' sensitivity. Computer simulations are run to verify the effectiveness of the formula and algorithm. The simulation results are in good agreement with the theoretical results.

In this paper, the sensitivity of Adalines to weight perturbation is discussed. According to the discrete feature of Adalines' input and output, the sensitivity is defined as the probability of an Adaline's erroneous outputs due to weight perturbation with respect to all possible inputs. By means of hypercube model and analytical geometry method, a heuristic algorithm is given to accurately compute the sensitivity. The accuracy of the algorithm is verified by computer simulations.

In a graphical user interface, physical layout and abstract structure are two important aspects of a graph. This article proposes a new graph grammar formalism which integrates both the spatial and structural specification mechanisms in a single framework. This formalism is equipped with a parser that performs in polynomial time with an improved parsing complexity over its nonspatial predecessor, that is, the Reserved Graph Grammar. With the extended expressive power, the formalism is suitable for many user interface applications. The article presents its application in adaptive Web design and presentation.

Enhancing the reserved graph grammar (RGG) formalism, this paper introduces a size-increasing condition on the structure of graph grammars' productions to simplify the definition of graph grammars, and a general parsing algorithm to extend the power of the RGG parsing algorithm.

This paper presents an approach to determine the relevance of individual input attributes for trained Multilayer Perceptrons (MLPs). To reflect the impact of an input attribute on the output of an MLP, the relevance is aimed at representing the output sensitivity of the MLP to the attribute variation. The sensitivity is defined as the mathematical expectation of output deviations of an MLP due to its input deviation with respect to overall input patterns. The basic idea for the introduction of such a relevance measure is that a well-trained MLP can capture salient features of the problem it deals with and thus become more sensitive to those input attributes that make more contributions to the MLP's behavior. The relevance can be employed as a relative criterion for assessing individual input attributes. The results from the experiments on two typical problems demonstrate the effectiveness of the relevance in identifying irrelevant input attribute.

The sensitivity of a neural network's output to its input perturbation is an important issue with both theoretical and practical values. In this article, we propose an approach to quantify the sensitivity of the most popular and general feedforward network: multilayer perceptron (MLP). The sensitivity measure is defined as the mathematical expectation of output deviation due to expected input deviation with respect to overall input patterns in a continuous interval. Based on the structural characteristics of the MLP, a bottom-up approach is adopted. A single neuron is considered first, and algorithms with approximately derived analytical expressions that are functions of expected input deviation are given for the computation of its sensitivity. Then another algorithm is given to compute the sensitivity of the entire MLP network. Computer simulations are used to verify the derived theoretical formulas. The agreement between theoretical and experimental results is quite good. The sensitivity measure can be used to evaluate the MLP's performance.

An important issue in the design and implementation of a neural network is the sensitivity of its output to input and weight perturbations. In this paper, we discuss the sensitivity of the most popular and general feedforward neural networks--multilayer perceptron (MLP). The sensitivity is defined as the mathematical expectation of the output errors of the MLP due to input and weight perturbations with respect to all input and weight values in a given continuous interval. The sensitivity for a single neuron is discussed first and an analytical expression that is a function of the absolute values of input and weight perturbations is approximately derived. Then an algorithm is given to compute the sensitivity for the entire MLP. As intuitively expected, the sensitivity increases with input and weight perturbations, but the increase has an upper bound that is determined by the structural configuration of the MLP, namely the number of neurons per layer and the number of layers. There exists an optimal value for the number of neurons in a layer, which yields the highest sensitivity value. The effect caused by the number of layers is quite unexpected. The sensitivity of a neural network may decrease at first and then almost keeps constant while the number increases.

An important issue in the design and implementation of neural networks is the sensitivity of neural network output to parameter perturbations. Past research in this area has focused on network sensitivity analysis after training. Very few research projects have considered sensitivity analysis as a design issue prior to network implementation. The authors discuss the sensitivity of the most popular and general feedforward networks (multilayer perceptron (MLP)) to its input perturbation. The sensitivity is defined as the mathematical expectation of output errors of the MLP arising from input error with respect to all input and weight values in a given continuous interval. The sensitivity for a single neuron is discussed first, and an analytical expression that is a function of the input error is approximately derived. Then an algorithm is given to compute the sensitivity for an entire MLP network. The theoretical results of the derived formula were shown to agree with experimental results. By analyzing the derived analytical expression and implementing the given algorithm on a number of representative MLP networks, some significant observations on the behavior of sensitivity are discovered, which could be useful for network design consideration.