Applied Intelligence最新文献

Differential cryptanalysis involves searching for high-probability differential trails. Traditionally, this search requires the use of constraint solvers or dedicated algorithms. Data-driven methods that rely on machine learning are typically limited to constructing statistical distinguishers for specific ciphers. In this paper, we develop a data-driven approach to the differential search problem by introducing DiffGen, a fully data-driven truncated differential search framework. DiffGen employs a metaheuristic algorithm with an active S-box prediction machine learning model as its fitness function to identify potentially valid truncated differentials within a given range of active S-boxes. A second machine learning model then validates the identified truncated differentials. We demonstrate the effectiveness of the DiffGen framework on generalized Feistel ciphers as a case study. Our results show that DiffGen can effectively generate valid truncated differentials, particularly when using particle swarm optimization as a metaheuristic and a differential validation model based on a fully connected artificial neural network. We verified that 84% of the truncated differentials generated by DiffGen in this setting correspond to actual differential trails. Our findings highlight, for the first time, the feasibility of applying a data-driven approach to the differential search problem.

Scoliosis is one of the most common diseases in adolescents. Traditional screening methods for the scoliosis usually use radiographic examination, which requires certified experts with medical instruments and brings the radiation risk. Considering such requirement and inconvenience, we propose to use natural images of the human back for wide-range scoliosis screening, which is a challenging problem. In this paper, we notice that the human back has a certain degree of symmetry, and asymmetrical human backs are usually caused by spinal lesions. Besides, scoliosis severity levels have ordinal relationships. Taking inspiration from this, we propose a dual-path scoliosis detection network with two main modules: symmetric feature matching module (SFMM) and ordinal regression head (ORH). Specifically, we first adopt a backbone to extract features from both the input image and its horizontally flipped image. Then, we feed the two extracted features into the SFMM to capture symmetric relationships. Finally, we use the ORH to transform the ordinal regression problem into a series of binary classification sub-problems. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods as well as human performance, which provides a promising and economic solution to wide-range scoliosis screening. In particular, our method achieves accuracies of 95.11% and 81.46% in estimation of general severity level and fine-grained severity level of the scoliosis, respectively.

Cross-project defect prediction enables a target software project with limited defect data to build a defect prediction model by leveraging abundant data in the source project. However, existing methods of cross-project defect prediction ignore the relative importance of global and local distributions in learning project-invariant feature spaces. This paper proposes a novel approach for cross-project defect prediction called Adan (autoencoder with dynamic adversarial adaptation) to dynamically adjust a project-invariant feature space by aligning global and local distributions simultaneously with adversarial learning. Specifically, the au-encoder was adopted to produce a latent space used as a project-invariant feature space for source and target artifacts. Global and local discriminators were used to adjust the latent space to ensure that representations of source and target artifacts in the project-invariant feature space have approximate global distribution and local distribution, respectively. The prediction model for the target artifacts was then trained using representations of the source artifacts in the project-invariant feature space. Experiments on four open-source projects with 12 pairs of tasks on cross-project defect prediction demonstrated that the proposed Adan approach outperformed state-of-the-art techniques, with an average improvement of 8.42% in terms of AUC.

In order to address the issue of automatic charging for electric vehicles, a hanging automatic charging system was proposed, with a particular focus on the time-optimal trajectory planning of the robotic arm within the system. Additionally, a multi-strategy improved Sand Cat Swarm Optimization Algorithm (YSCSO) was put forth as a potential solution. The 0805A six-axis manipulator was selected as the research object, and a kinematic model was constructed using the D-H parameter method. The 5-7-5 polynomial interpolation function was proposed and solved to construct the motion trajectory of the robotic arm joint. The cubic chaos-refraction inverse learning, introduced to initialize the population based on the sand cat swarm algorithm SCSO, balances the relationship between the elite pool weighted guided search behavior and the spiral Lévy flight predation behavior through the use of a dynamic nonlinear sensitivity range. Furthermore, the vigilance behavior mechanism of the sand cat was increased to improve the overall optimization performance of the algorithm. The proposed method was applied to 36 benchmark functions of global optimization, and the improvement strategy, convergence behavior, population diversity, exploration, and development of the algorithm were experimentally analyzed. The results demonstrated that the proposed method exhibited superior performance, with 80.86% of the test results significantly different from those of the comparison algorithm. Three constrained mechanical design optimization problems were employed to assess the algorithm’s practicality in engineering applications. Subsequently, the algorithm was applied to the optimal trajectory planning of a robotic arm, resulting in a significant reduction in the optimized joint motion time, a smooth and continuous kinematic curve devoid of abrupt changes, and a 42.72% reduction in motion time. These findings further substantiate the theoretical feasibility and superiority of the algorithm in addressing engineering challenges.

Rare safety-critical events remain a major challenge in autonomous vehicle testing. This paper proposes to use game theory to build a novel testing environment for autonomous vehicles. In this environment, a virtual agent based on counterfactual minimization (CFR) is used to accelerate testing and validate the safety performance of autonomous vehicles. The virtual agent updates the adversarial policies to be enforced by continuously accumulating regret values, thus increasing the probability of security-critical events occurring during the testing process. Finally, recognized metrics such as Time-to-Collision (TTC) and Minimum Safe Distance Factor (MSDF) are introduced to assess the quality of the scenario. Experimental results show that the virtual agent based on counterfactual minimization explicitly generates more safety-critical scenarios and accelerates the evaluation process by multiple orders of magnitude ((10^{3}) times faster).

This paper presents STNeRF, a method for synthesizing novel views of vehicles from single-view 2D images without the need for 3D ground truth data, such as point clouds, depth maps, CAD models, etc., as prior knowledge. A significant challenge in this task arises from the characteristics of CNNs and the utilization of local features can lead to a flattened representation of the synthesized image when training and validation with images from a single viewpoint. Many current methodologies tend to overlook local features and rely on global features throughout the entire reconstruction process, potentially resulting in the loss of fine-grained details in the synthesized image. To tackle this issue, we introduce Symmetric Triplane Neural Radiance Fields (STNeRF). STNeRF employs a triplane feature extractor with spatially aware convolution to extend 2D image features into 3D. This decouples the appearance component, which includes local features, and the shape component, which consists of global features, and utilizes them to construct a neural radiance field. These neural priors are then employed for rendering novel views. Furthermore, STNeRF leverages the symmetric properties of vehicles to liberate the appearance component from reliance on the original viewpoint and to align it with the symmetry of the target space, thereby enhancing the neural radiance field network’s ability to represent the invisible regions. The qualitative and quantitative evaluations demonstrate that STNeRF outperforms existing solutions in terms of both geometry and appearance reconstruction. More supplementary materials and the implementation code are available for access at the following link: https://github.com/ll594282475/STNeRF.

Sentiment analysis is the process of determining the expressive direction of the user reviews. Recently, sentiment analysis gets more attention. However, low data sentiment analysis receives less attention. The existing works try to augment the samples to consider this issue. In this study, we have utilized a semi-supervised approach to propose a new approach for low-data sentiment analysis. To do so, we have utilized pre-trained XLNet as a feature extractor network to initialize the feature vector for each tweet. Next, these initial representations are fed into the embedding update module to map features into the new space by optimizing the contrastive loss. Then, we utilized a semi-supervised boosting method to assign pseudo labels to unlabeled data. The iteration between the semi-supervised module and the embedding update module is done until convergence is happened. During these iterations, the embedding update module propagates the error-correcting signals to a semi-supervised module. To evaluate the proposed approach, we have applied it to the SemEval2017dataset (task 4), Sentiment 140, and IMDB Movie Reviews. We have designed many different experiment settings to validate the proposed approach’s different modules. On SemEval2017dataset (task 4), we have got 75.9% and 77.1% in AvgRec and ({F}_{1}^{PN}) respectively. Also, when only 10% of the training samples as labeled samples are used, we get the 71.8% and 73.6% in AvgRec and ({F}_{1}^{PN}) respectively. The results show that our approach significantly improves with respect to the comparable methods. Also, on IMDB Movie Reviews and Sentiment 140, the proposed approach demonstrates improved performance compared to comparable methods.

Given the intricate spatial dependencies and dynamic trends among diverse road segments, the prediction of spatio-temporal traffic flow data presents a formidable challenge. To address this challenge within the complexity of urban multi-mode transportation systems, this paper introduces an innovative solution. Anchored by the TSHDNet framework, the proposed methodology presents a novel spatio-temporal heterogeneous decoupling network that adeptly captures the inherent relationships between traffic patterns and temporal-spatial fluctuations. By seamlessly integrating temporal and nodal embeddings, dynamic graph learning, and multi-scale representation modules, TSHDNet demonstrates remarkable efficacy in unraveling the subtle dynamics of traffic flow. Empirical evaluations and ablation experiments conducted on four real-world datasets affirm the framework’s capability and the effectiveness of the decoupling approach.The source codes are available at: https://github.com/MeiWu2/TSHDNet.git

This paper proposes a learning artificial visual system, the Learning Dendritic Model Artificial Visual System (DModel-AVS), for orientation detection inspired by biological visual mechanisms. The DModel-AVS consists of two layers: local orientation detection neurons layer and global orientation detection neurons layer. The local neurons detect local features of an image, utilizing dendrite model neurons. The global neurons are designed to implement global features of the image by summing the outputs of the local dendritic neurons. The backpropagation-based learning is performed only to the dendritic neurons. The effectiveness of the DModel-AVS is evaluated through several experiments comparing it with various convolutional neural network (CNN)-based orientation detection systems. Results show that the DModel-AVS is a more biologically plausible and effective solution to orientation detection, with higher accuracy, and lower learning costs. The proposed system has practical applications in various fields such as computer vision and robotics.

With the increasing demand for Unmanned Aerial Vehicles (UAVs) in both military and civil applications, the ability for UAVs to automatically avoid obstacles and navigate to specific destinations has been receiving growing attention. However, most current methods focus on environments where global information is available or both destination and obstacles are static, which are not suitable for dense, dynamic, complex real-time tasks. Therefore, we propose a novel autonomous navigation method based on Deep Reinforcement Learning (DRL), which is suitable for more complex environments. Based on the Soft Actor-Critic (SAC) algorithm, this method incorporates changes of the state space into network input with a temporal attention mechanism, which allows UAVs to adaptively extract key information from historical environments while maintaining sensitivity to the current environment. We establish a visualized two-dimensional navigation task environment and design different simulation tests to evaluate its the performance and generalization. Results show that compared to baselines, our algorithm can achieve higher average rewards and more stable convergence after training in a static multi-obstacle environment, and can demonstrate better performance in environments featuring multiple obstacles of varying numbers, sizes, and speeds, thereby achieving a balance between task completion efficiency and security.