Data augmentation is crucial for addressing insufficient training data, especially for augmenting positive samples. However, existing methods mostly rely on neural network-based feedback for data augmentation and often overlook the optimization of feature distribution. In this study, we present a practical, distribution-preserving data augmentation pipeline that augments positive samples by optimizing a feature indicator (e.g., two-dimensional entropy), aiming to maintain alignment with the original data distribution. Inspired by the manifold hypothesis, we propose a Manifold Heuristic Optimization Algorithm (MHOA), which augments positive samples by exploring the low-dimensional Euclidean space around object contour pixels instead of the entire decision space. Guided by a "distribution-preservation-first" perspective, our approach explicitly optimizes fidelity to the original data manifold and only retains augmented samples whose feature statistics (e.g., mean, variance) align with the source class. It significantly improves image classification accuracy across neural networks, outperforming state-of-the-art data augmentation methods-especially when the dataset's feature indicator follows a Gaussian distribution. The algorithm's search space, focused on neighborhoods of key feature pixels, is the core driver of its superior performance.

ABSTRACT Objective The task of code generation aims to transform natural language descriptions into corresponding target code. Among the various approaches, syntax‐aware code generation has emerged as a significant approach that strives to generate code by directly modeling the underlying syntactic rules. However, existing works typically adopt an autoregressive approach to sequentially generate each abstract syntax rule, which inevitably neglects the rich structural semantic information inherent within the syntax rules. To address this issue, we propose an enhanced architecture of structure semantics based on Graph Neural Network for code generation. Methods Our approach explicitly models the internal structure of syntactic rules by treating them as graph data, thereby enabling the extraction of deeper structural semantics. Furthermore, we jointly model both the sequential semantics and structural semantics of syntactic rules, effectively addressing the limitations of solely sequence‐based approaches in capturing the inherent structural semantics of code. Results Experimental results on two widely used code generation datasets demonstrate that the proposed model consistently outperforms strong baselines, with gains of up to 2.14 BLEU points and 2.02 CodeBLEU points, highlighting the effectiveness of our structural‐semantic modeling approach for code generation.

Automated test case generation based on path coverage is not only a large-scale black-box optimization problem , but also a key scientific problem in software automatic testing technology. Evolutionary algorithms and other search-based algorithms are representative methods for this problem. However, existing research mainly focuses on the multi-function case, where generating test cases for multiple functions is difficult due to the combinatorial explosion of the path number. In this paper, we propose a multi-task collaborative method based on manifold optimization by considering the topological manifold relationship between the test case space (decision space) and the program path space (target space). This method achieves the goal of collaborative optimization for different function coverage tasks by coordinating the allocation of computing resources and knowledge transfer mechanisms among them. To verify the effectiveness of the proposed method, we compare it with general solution methods for single-function automated test case generation based on path coverage, such as the manifold-inspired search-based algorithm. The experimental results show that the proposed method outperforms the compared single-function optimization algorithms especially on programs with strong coding similarities. This study verifies the feasibility of collaborative optimization methods for solving large-scale black-box optimization problems, such as the automated test case generation based on path coverage, and expands their application scenarios.

Handling energy resource management (ERM) in today’s energy systems is complex and challenging due to uncertainties arising from the high penetration of distributed energy resources. Such penetration introduces various uncertain factors, such as renewable energy, energy storage, and electric vehicles, making it difficult for traditional mathematical methods to find effective solutions. However, Evolutionary Algorithms (EAs) have shown good performance in solving this problem. Therefore, in this paper, a self-adaptive collaborative differential evolution algorithm (SADEA) is proposed to solve the ERM problem under uncertainty. In SADEA, a three-stage adaptive collaboration strategy, includes boundary randomization stage, knowledge-assisted collaboration stage, and range restructuration stage, is used to generate collaborative solutions. The collaborative solutions generated in the above stages will jointly participate in the perturbation of DE strategies to explore promising solutions. In addition, different DE strategies are selected according to count values and random factors. At the end of the algorithm, boundary control, elite selection and retention are used to ensure the legitimacy and robustness of solutions. The proposed SADEA is compared to several state-of-the-art algorithms on a real-world distribution network located in Salamanca, Spain. The results show that SADEA is superior to its competitors in terms of the objective function, ranking index, and convergence. In summary, the proposed algorithm is effective to handle the ERM problem under uncertainty.

We consider efficient channel estimation for massive multiple-input multiple-output (MIMO) systems using one-bit analog-to-digital converters (ADCs) with antenna-varying thresholds at the receivers. We introduce a computationally efficient majorization-minimization (MM) based maximum likelihood (ML) channel matrix estimator (referred to as 1bMM-ML), which maximizes the one-bit likelihood function iteratively by solving simple linear least squares problems. Moreover, to take into account the low-rank property of the millimeter-wave (mmWave) massive MIMO channels, we add a nuclear-norm based penalty term to the negative log-likelihood function and solve the resulting problem efficiently using the MM approach (referred to as 1bMM-LR). To further enhance the channel estimation performance, we consider an angular-domain channel model and introduce a hybrid approach (referred to as 1bLR-RELAX), which combines 1bMM-LR with an existing parametric algorithm called 1bRELAX, to recover the angular-domain channel parameters. Numerical examples are provided to demonstrate the effectiveness and efficiency of the proposed channel estimation algorithms.

Learning binary classifiers only from positive and unlabeled (PU) data is an important and challenging task in many real-world applications, including web text classification, disease gene identification and fraud detection, where negative samples are difficult to verify experimentally. Most recent PU learning methods are developed based on the misclassification risk of the supervised learning type, and they may suffer from inaccurate estimates of class prior probabilities. In this paper, we introduce a variational principle for PU learning that allows us to quantitatively evaluate the modeling error of the Bayesian classifier directly from given data. This leads to a loss function which can be efficiently calculated without involving class prior estimation or any other intermediate estimation problems, and the variational learning method can then be employed to optimize the classifier under general conditions. We illustrate the effectiveness of the proposed variational method on a number of benchmark examples.

We consider the problem of direction-of-arrival (DOA) and waveform estimation from coarsely quantized measurement samples obtained with an array of sensors. We introduce a majorization minimization based algorithm to cyclically maximize the likelihood function of the quantized array data. We also use the Bayesian information criterion (BIC) to determine the number of incident signals. Numerical examples are provided to demonstrate the effectiveness of our approaches.

We consider the problem of sinusoidal parameter estimation from signed measurement samples. We formulate the sinusoidal parameter estimation problem as a sparse signal recovery problem and apply the alternating direction method of multipliers (ADMM) to efficiently solve it. The ℓ1-norm and log-norm approximations are used to replace the ℓ0-norm. We then judiciously design the detailed update steps of ADMM for the two approximations, so that most or all update steps involve computationally efficient closed-form solutions. Numerical examples are provided to demonstrate the effectiveness of our approaches.

Fog computing plays an important role in industrial and information process. The programs in fog computing, such as iFogSim toolkit, usually contain some infeasible paths (paths that cannot be covered), which makes it impossible to compare algorithm in models that require covering all paths. In this paper, we proposed a mathematical model to build automated test case generation based on path coverage (ATCG-PC) in fog computing programs as a single-objective problem. Single objective helps to reduce the cost of evaluation functions, which is proportional to the number of test cases. When infeasible paths are contained in tested programs, algorithms can also be compared in this model. In this paper, classical differential evolution (DE) is used to solve the ATCG-PC. However, it is difficult for DE to use generated test cases covering remaining paths in the ATCG-PC of fog computing. Therefore, we proposed a test-case-path relationship matrix to empower DE (RP-DE). Experiment results show that RP-DE uses significantly less test cases and achieves higher path coverage rate than compared state-of-the-art algorithms.

Software testing is an important process of software development. One of the challenges in testing software is to generate test cases which help to reveal errors. Automated software test data generation problem is hard because it needs to search the whole feasible area to find test cases covering all possible paths under acceptable time consumption. In this paper, evolutionary algorithm with convergence speed controller (EA-CSC) is presented for using the least test case overhead in solving automated test case generation problem. EA-CSC is designed as a framework which have fast convergence speed and capability to jump out of the local optimal solution over a range of problems. There are two critical steps in EA-CSC. The adaptive step size searching method accelerates the convergence speed of EA. The mutation operator can disrupt the population distribution and slows down the convergence process of EA. Moreover, the EA-CSC results are compared to the algorithms tested on the same benchmark problems, showing strong competitive.