International Journal of Intelligent Systems最新文献

The central pattern generator (CPG) is widely applied in biped gait generation, and the particle swarm optimization (PSO) algorithm is commonly used to solve optimization problems for CPG network controllers. However, the canonical PSO algorithms fail to balance exploration and exploitation, resulting in reduced optimization accuracy and stability, decreasing the control effectiveness of CPG controllers. In order to address this issue, a balanced PSO (BPSO) algorithm is proposed, which achieves better performance by balancing the algorithm’s exploration and exploitation capabilities. The BPSO algorithm’s solving process consists of two phases: the free exploration phase (FEP), which emphasizes exploration, and the attention exploration phase (AEP), which emphasizes exploitation. The proportion of each phase during optimization is controlled by an adjustable parameter. The BPSO algorithm is subjected to qualitative, numerical, convergence, and statistical analyses based on 13 benchmark functions. The experimental results from the benchmark functions demonstrate that the BPSO algorithm outperforms other comparison algorithms. Finally, a linear walking optimization method for humanoid robots based on the BPSO algorithm is established and tested in the Webots simulator. Comparative results with two other optimization methods show that the BPSO-based optimization method enables the robot to achieve greater walking distance and smaller lateral deviation within a fixed number of iterations. Compared to the other two methods, walking distance increases by at least 60.98% and lateral deviation decreases by at least 1.96%. This research contributes to enhancing the locomotion capabilities of CPG-controlled humanoid robots, enriching biped gait optimization theory and promoting the application of CPG gait control methods in humanoid robots.

In the global fight against breast cancer, the importance of early diagnosis is unparalleled. Early identification not only improves treatment options but also significantly improves survival rates. Our research introduces an innovative ensemble method that synergistically combines the strengths of four state-of-the-art convolutional neural networks (CNNs): EfficientNet, AlexNet, ResNet, and DenseNet. These networks were chosen for their architectural advances and proven efficacy in image classification tasks, particularly in medical imaging. Each network within our ensemble is uniquely optimized: EfficientNet is fine-tuned with customized scaling to address dataset specifics; AlexNet employs a variable dropout mechanism to reduce overfitting; ResNet benefits from learnable weighted skip connections for better gradient flow; and DenseNet uses selective connectivity to balance computational efficiency and feature extraction. This ensembling strategy combines the predictive output of multiple CNNs, each trained with an individually optimized network, to enhance the ensemble’s overall diagnostic performance. This provides higher precision and stability than any model and shows outstanding performance in the early stage of breast cancer with a precision of up to 94.6%, sensitivity of 92.4%, specificity of 96.1%, and area under the curve (AUC) of 98.0%. This ensemble framework indicated a leap in the early diagnosis of breast cancer as it is a powerful tool that combines several state-of-the-art techniques, hence providing better results.

Low-light enhancement significantly aids vision tasks under poor illumination conditions. Existing methods primarily focus on enhancing severely degraded low-light areas, improving illumination accuracy, or noise suppression, yet they often overlook the loss of additional details and color distortion during calculation. In this paper, we propose an innovative entropy-weighted low-light image enhancement method via the reverse diffusion model, aiming at addressing the limitations of the traditional Retinex decomposition model in preserving local pixel details and handling excessive smoothing issues. This method integrates an entropy-weighting mechanism for improved image quality and entropy, along with a reverse diffusion model to address the detail loss in total variation regularization and refine the enhancement process. Furthermore, we utilize long short-term memory networks for the learning reverse process and the simulation of image degradation, based on a thermodynamics-based nonlinear anisotropic diffusion model. Comparative experiments reveal the superiority of our method over conventional Retinex-based approaches in terms of detail preservation and visual quality. Extensive tests across diverse datasets demonstrate the exceptional performance of our method, evidencing its potential as a robust solution for low-light image enhancement.

Speech emotion recognition plays a crucial role in analyzing psychological disorders, behavioral decision-making, and human-machine interaction applications. However, the majority of current methods for speech emotion recognition heavily rely on data-driven approaches, and the scarcity of emotion speech datasets limits the progress in research and development of emotion analysis and recognition. To address this issue, this study introduces a new English speech dataset specifically designed for emotion analysis and recognition. This dataset consists of 5503 voices from over 60 English speakers in different emotional states. Furthermore, to enhance emotion analysis and recognition, fast Fourier transform (FFT), short-time Fourier transform (STFT), mel-frequency cepstral coefficients (MFCCs), and continuous wavelet transform (CWT) are employed for feature extraction from the speech data. Utilizing these algorithms, the spectrum images of the speeches are obtained, forming four datasets consisting of different speech feature images. Furthermore, to evaluate the dataset, 16 classification models and 19 detection algorithms are selected. The experimental results demonstrate that the majority of classification and detection models achieve exceptionally high recognition accuracy on this dataset, confirming its effectiveness and utility. The dataset proves to be valuable in advancing research and development in the field of emotion recognition.

Intelligent traffic signal systems, crucial for intelligent transportation systems, have been widely studied and deployed to enhance vehicle traffic efficiency and reduce air pollution. Unfortunately, intelligent traffic signal systems are at risk of data spoofing attack, causing traffic delays, congestion, and even paralysis. In this paper, we reveal a multivehicle collaborative data spoofing attack to intelligent traffic signal systems and propose a collaborative attack sequence generation model based on multiagent reinforcement learning (RL), aiming to explore efficient and stealthy attacks. Specifically, we first model the spoofing attack based on Partially Observable Markov Decision Process (POMDP) at single and multiple intersections. This involves constructing the state space, action space, and defining a reward function for the attack. Then, based on the attack modeling, we propose an automated approach for generating collaborative attack sequences using the Multi-Actor-Attention-Critic (MAAC) algorithm, a mainstream multiagent RL algorithm. Experiments conducted on the multimodal traffic simulation (VISSIM) platform demonstrate a 15% increase in delay time (DT) and a 40% reduction in attack ratio (AR) compared to the single-vehicle attack, confirming the effectiveness and stealthiness of our collaborative attack.

More than 80% of video coding times are consumed by motion estimation calculations, which are the most complex aspect of the process. This method eliminates temporal redundancies in a video sequence to achieve maximum compression. Numerous efforts have been made to bring calculations closer to real time, yielding fruitful results. This study proposes a fast subpixel motion estimation algorithm for video encoding with fewer search points. This method employs the capabilities of human visual systems (HVSs), physical motion characteristics of real-world objects, and special image information from successive frames. The number of search points (NSP) using the statistical data of the movement of the blocks in the frames of video sequences is reduced to apply fewer calculations to the system while maintaining the quality of images. Therefore, it is possible to approach fast and real-time calculations instead of time-consuming algorithms by accurately modeling this algorithm.

Reversible adversarial example (RAE) is an effective cutting-edge technology for protecting the intellectual property (IP) of datasets. However, existing RAE schemes primarily focus on the adversarial and restoration capabilities of adversarial examples (AE), with little attention paid to traceability, which is crucial for IP protection. This oversight leads to the inability to prevent authorized users from redistributing data, thereby posing significant IP security risks. To address this issue, we propose a novel approach named TAE-RWP, wherein adversarial perturbations in AEs are treated as tools for IP verification. To enable the traceability of AEs, we introduce varying degrees of warping to the adversarial perturbations within the AEs of authorized users, utilizing the warping degree as a traceable feature. To further strengthen traceability, we adopt a technique named “random warping” to maintain the resilience of adversarial perturbations against distortions, and employ a strategy named “noise mode” to improve the verification model’s capacity to recognize distortion features. Experimental results indicate that AEs generated by TAE-RWP exhibit remarkable adversarial strength and restoration abilities, while the verification model demonstrates excellence in recognizing distortion features.

With the rapid development of entity recognition technology, animal recognition has gradually become essential in modern society, supporting labour-intensive agriculture and animal husbandry tasks. Severe problems such as maintaining biodiversity can also benefit from animal identification technology. However, certain invasive recognition systems have resulted in permanent harm to animals, while noninvasive identification methods also exhibit certain drawbacks. This paper conducts a systematic literature review (SLR), presenting a comprehensive overview of various animal recognition technologies and their applications. Specifically, it examines methodologies such as deep learning, image processing and acoustic analysis used for different animal characteristics and identification purposes. The contribution of machine learning to animal feature extraction is highlighted, emphasising its significance for animal taxonomy and wild species monitoring. Additionally, this review addresses the challenges and limitations of current technologies, including data scarcity, model accuracy and computational requirements, and suggests opportunities for future research to overcome these obstacles.

The field of generative artificial intelligence (AI) is experiencing rapid advancements, impacting a multitude of sectors, from computer vision to healthcare. This paper provides a comprehensive review of generative AI’s evolution, significance, and applications, including the foundational architectures such as generative adversarial networks (GANs), variational autoencoders (VAEs), autoregressive models, flow-based models, and diffusion models. We delve into the impact of generative algorithms on computer vision, natural language processing, artistic creation, and healthcare, demonstrating their revolutionary potential in data augmentation, text and speech synthesis, and medical image interpretation. While the transformative capabilities of generative AI are acknowledged, the paper also examines ethical concerns, most notably the advent of deepfakes, calling for the development of robust detection frameworks and responsible use guidelines. As generative AI continues to evolve, driven by advances in neural network architectures and deep learning methodologies, this paper provides a holistic overview of the current landscape and a roadmap for future research and ethical considerations in generative AI.

The one-class classification (OCC) problem has always been a popular topic because it is difficult or expensive to obtain abnormal data in many practical applications. Most of OCC methods focused on monomodal data, such as support vector data description (SVDD) and its variants, while we often face multimodal data in reality. The data come from the same task in multimodal learning, and thus, the inherent structures among all modalities should be hold, which is called the consistency principle. However, each modality contains unique information that can be used to repair the incompleteness of other modalities. It is called the complementarity principle. To follow the above two principles, we designed a multimodal graph–regularized term and a sparse projection matrix–regularized term. The former aims to preserve the within-modal structural and between-modal relationships, while the latter aims to richly use the complementarity information hidden in multimodal data. Further, we follow the multimodal subspace (MS) SVDD architecture and use two regularized terms to regularize SVDD. Consequently, a novel OCC method for multimodal data is proposed, called the consistency and complementarity jointly regularized subspace SVDD (CCS-SVDD). Extensive experimental results demonstrate that our approach is more effective and competitive than other algorithms. The source codes are available at https://github.com/wongchuang/CCS_SVDD.