Search Results (400)

Generative AI has been gaining attention across various creative domains. In particular, MusicGen stands out as a representative approach capable of generating music based on text or audio inputs. However, it has limitations in producing high-quality outputs for specific genres and fully reflecting user intentions. This paper proposes a prompt tuning technique that effectively adjusts the output quality of MusicGen without modifying its original parameters and optimizes its ability to generate music tailored to specific genres and styles. Experiments were conducted to compare the performance of the traditional MusicGen with the proposed method and evaluate the quality of generated music using the Contrastive Language-Audio Pretraining (CLAP) and Kullback–Leibler Divergence (KLD) scoring approaches. The results demonstrated that the proposed method significantly improved the output quality and musical coherence, particularly for specific genres and styles. Compared with the traditional model, the CLAP score was increased by 0.1270, and the KLD score was increased by 0.00403 on average. The effectiveness of prompt tuning in optimizing the performance of MusicGen validated the proposed method and highlighted its potential for advancing generative AI-based music generation tools. Full article

This study suggests a hybrid approach that combines improved feature selection and intelligent diagnosis to increase the operational safety and intelligent diagnosis capabilities of hydropower units. In order to handle the vibration data, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used initially. A novel comprehensive index is constructed by combining the Pearson correlation coefficient, mutual information (MI), and Kullback–Leibler divergence (KLD) to select intrinsic mode functions (IMFs). Next, feature extraction is performed on the selected IMFs using Refined Composite Multiscale Fluctuation Dispersion Entropy (RCMFDE). Then, time and frequency domain features are screened by calculating dispersion and combined with IMF features to build a hybrid feature vector. The vector is then fed into a CNN-GRU-Attention model for intelligent diagnosis. The improved slime mold algorithm (ISMA) is employed for the first time to optimize the hyperparameters of the CNN-GRU-Attention model. The experimental results show that the classification accuracy reaches 96.79% for raw signals and 93.33% for noisy signals, significantly outperforming traditional methods. This study incorporates entropy-based feature extraction, combines hyperparameter optimization with the classification model, and addresses the limitations of single feature selection methods for non-stationary and nonlinear signals. The proposed approach provides an excellent solution for intelligent optimized diagnosis of hydropower units. Full article

Most image forgery localization methods rely on supervised learning, requiring large labeled datasets for training. Recently, several unsupervised approaches based on the variational autoencoder (VAE) framework have been proposed for forged pixel detection. In these approaches, the latent space is built by a simple Gaussian distribution or a Gaussian Mixture Model. Despite their success, there are still some limitations: (1) A simple Gaussian distribution assumption in the latent space constrains performance due to the diverse distribution of forged images. (2) Gaussian Mixture Models (GMMs) introduce non-convex log-sum-exp functions in the Kullback–Leibler (KL) divergence term, leading to gradient instability and convergence issues during training. (3) Estimating GMM mixing coefficients typically involves either the expectation-maximization (EM) algorithm before VAE training or a multilayer perceptron (MLP), both of which increase computational complexity. To address these limitations, we propose the Deep ViT-VAE-GMM (DVVG) framework. First, we employ Jensen’s inequality to simplify the KL divergence computation, reducing gradient instability and improving training stability. Second, we introduce convolutional neural networks (CNNs) to adaptively estimate the mixing coefficients, enabling an end-to-end architecture while significantly lowering computational costs. Experimental results on benchmark datasets demonstrate that DVVG not only enhances VAE performance but also improves efficiency in modeling complex latent distributions. Our method effectively balances performance and computational feasibility, making it a practical solution for real-world image forgery localization. Full article

The absence of skin color information in skin cancer datasets poses a significant challenge for accurate diagnosis using artificial intelligence models, particularly for non-white populations. In this paper, based on the Monk Skin Tone (MST) scale, which is less biased than the Fitzpatrick scale, we propose MST-AI, a novel method for detecting skin color in images of large datasets, such as the International Skin Imaging Collaboration (ISIC) archive. The approach includes automatic frame, lesion removal, and lesion segmentation using convolutional neural networks, and modeling normal skin tones with a Variational Bayesian Gaussian Mixture Model (VB-GMM). The distribution of skin color predictions was compared with MST scale probability distribution functions (PDFs) using the Kullback-Leibler Divergence (KLD) metric. Validation against manual annotations and comparison with K-means clustering of image and skin mean RGBs demonstrated the superior performance of the MST-AI, with Kendall’s Tau, Spearman’s Rho, and Normalized Discounted Cumulative Gain (NDGC) of 0.68, 0.69, and 1.00, respectively. This research lays the groundwork for developing unbiased AI models for early skin cancer diagnosis by addressing skin color imbalances in large datasets. Full article

To address the challenges brought by the high penetration of renewable energy in power systems, such as multi-scale dynamic interactions, high feature dimensionality, and limited model generalization, this paper proposes a transient stability assessment (TSA) method that combines temporal feature selection with deep learning-based modeling. First, a two-stage feature selection strategy is designed using the inter-class Mahalanobis distance and Spearman rank correlation. This helps extract highly discriminative and low-redundancy features from wide-area measurement system (WAMS) time-series data. Then, a parallel LSTM-Transformer architecture is constructed to capture both short-term local fluctuations and long-term global dependencies. A variational inference mechanism based on a Gaussian mixture model (GMM) is introduced to enable dynamic representations fusion and uncertainty modeling. A composite loss function combining improved focal loss and Kullback–Leibler (KL) divergence regularization is designed to enhance model robustness and training stability under complex disturbances. The proposed method is validated on a modified IEEE 39-bus system. Results show that it outperforms existing models in accuracy, robustness, interpretability, and other aspects. This provides an effective solution for TSA in power systems with high renewable energy integration. Full article

The Bayesian network is a directed, acyclic graphical model that can offer a structured description for probabilistic dependencies among random variables. As powerful tools for classification tasks, Bayesian classifiers often require computing joint probability distributions, which can be computationally intractable due to potential full dependencies among feature variables. On the other hand, Naïve Bayes, which presumes zero dependencies among features, trades accuracy for efficiency and often comes with underperformance. As a result, non-zero dependency structures, such as trees, are often used as more feasible probabilistic graph approximations; in particular, Tree Augmented Naïve Bayes (TAN) has been demonstrated to outperform Naïve Bayes and has become a popular choice. For applications where a variable is strongly influenced by multiple other features, TAN has been further extended to the k-dependency Bayesian classifier (KDB), where one feature can depend on up to k other features (for a given $k\ge 2$). In such cases, however, the selection of the k parent features for each variable is often made through heuristic search methods (such as sorting), which do not guarantee an optimal approximation of network topology. In this paper, the novel notion of k-tree Augmented Naïve Bayes (k-TAN) is introduced to augment Naïve Bayesian classifiers with k-tree topology as an approximation of Bayesian networks. It is proved that, under the Kullback–Leibler divergence measurement, k-tree topology approximation of Bayesian classifiers loses the minimum information with the topology of a maximum spanning k-tree, where the edge weights of the graph are mutual information between random variables conditional upon the class label. In addition, while in general finding a maximum spanning k-tree is NP-hard for fixed $k\ge 2$, this work shows that the approximation problem can be solved in time $O\left(n^{k+1}\right)$ if the spanning k-tree also desires to retain a given Hamiltonian path in the graph. Therefore, this algorithm can be employed to ensure efficient approximation of Bayesian networks with k-tree augmented Naïve Bayesian classifiers of the guaranteed minimum loss of information. Full article

Accurate prediction of lithium-ion battery capacity degradation under dynamic loads is crucial yet challenging due to limited data availability and high cell-to-cell variability. This study proposes a Latent Gaussian Process (GP) model to forecast the full distribution of capacity fade in the form of high-dimensional histograms, rather than relying on point estimates. The model integrates Principal Component Analysis with GP regression to learn temporal degradation patterns from partial early-cycle data of a target cell, using a fully degraded reference cell. Experiments on the NASA dataset with randomized dynamic load profiles demonstrate that Latent GP enables full-lifecycle capacity distribution prediction using only early-cycle observations. Compared with standard GP, long short-term memory (LSTM), and Monte Carlo Dropout LSTM baselines, it achieves superior accuracy in terms of Kullback–Leibler divergence and mean squared error. Sensitivity analyses further confirm the model’s robustness to input noise and hyperparameter settings, highlighting its potential for practical deployment in real-world battery health prognostics. Full article

The detection of weak moving targets in heterogeneous clutter backgrounds is a significant challenge in radar systems. In this paper, we propose a track-before-detect (TBD) method based on information geometry (IG) theory applied to range-azimuth measurements, which extends the IG detectors to multi-frame detection through inter-frame information integration. The approach capitalizes on the distinctive benefits of the information geometry detection framework in scenarios with strong clutter, while enhancing the integration of information across multiple frames within the TBD approach. Specifically, target and clutter trajectories in multi-frame range-azimuth measurements are modeled on the Hermitian positive definite (HPD) and power spectrum (PS) manifolds. A scoring function based on information geometry, which uses Kullback–Leibler (KL) divergence as a geometric metric, is then devised to assess these motion trajectories. Moreover, this study devises a solution framework employing dynamic programming (DP) with constraints on state transitions, culminating in an integrated merit function. This algorithm identifies target trajectories by maximizing the integrated merit function. Experimental validation using real-recorded sea clutter datasets showcases the effectiveness of the proposed algorithm, yielding a minimum 3 dB enhancement in signal-to-clutter ratio (SCR) compared to traditional approaches. Full article

This paper addresses multisensor multitarget tracking where the sensor network can potentially be compromised by false data injection (FDI) attacks. The existence of the targets is not known and time-varying. A tracking algorithm is proposed that can detect the possible FDI attacks over the networks. First, a local estimate is generated from the measurements of each sensor based on the labeled multi-Bernoulli (LMB) filter. Then, a detection method for FDI attacks is derived based on the Kullback–Leibler divergence (KLD) between LMB random finite set (RFS) densities. The statistical characteristics of the KLD are analyzed when the measurements are secure or compromised by FDI attacks, from which the value of the threshold is selected. Finally, the global estimate is obtained by minimizing the weighted sum of the information gains from all secure local estimates to itself. A set of suitable weight parameters is selected for the information fusion of LMB densities. An efficient Gaussian implementation of the proposed algorithm is also presented for the linear Gaussian state evolution and measurement model. Experimental results illustrate that the proposed algorithm can provide reliable tracking performance against the FDI attacks. Full article

The elucidation of protein dynamics, especially in the context of intrinsically disordered proteins, is challenging and requires cooperation between experimental studies and computational analysis. Molecular dynamics simulations are an essential investigation tool but often struggle to accurately quantify the conformational preferences of flexible proteins. To create a quantitatively validated conformational ensemble, such simulations may be refined with experimental data using Bayesian and maximum entropy methods. In this study, we present a method to optimize a conformational ensemble using Bayes’ theorem in connection with a methodology derived from Umbrella Sampling. The resulting method, called the Umbrella Refinement of Ensembles (URE), reduces the number of parameters to be optimized in comparison to the classical Bayesian Ensemble Refinement and remains methodologically suitable for use with the forward formulated Kullback–Leibler divergence. The method is validated using two established systems, an alanine–alanine zwitterion and the chignolin peptide, using nuclear magnetic resonance data from the literature. Full article

Patent licensing is essential for sustainable technological diffusion, fostering innovation and strengthening industrial resilience. However, the determinants influencing patent licensing decisions remain underexplored. This study investigates these factors at both the enterprise and patent levels, emphasizing their role in promoting sustainable industrial innovation and knowledge transfer. Given the low proportion of licensed patents, this research proposes a measurement framework to identify thematically similar but unlicensed patents and applies a conditional logistic regression model to analyze the factors affecting licensing decisions. Using patent abstracts from the intelligent connected vehicles (ICVs) sector, topic modeling is conducted to classify technological themes, and Kullback–Leibler divergence is applied to measure differences between licensed and unlicensed patents. The results indicate that technological prestige and depth negatively influence licensing, whereas technological breadth, advancement, and stability have a positive effect. From a sustainability perspective, enterprises should optimize technology management to support responsible knowledge transfer and green innovation. Universities should enhance patent quality and innovation impact to contribute more effectively to sustainable development. Policymakers should refine patent licensing frameworks to foster an efficient, inclusive, and sustainable intellectual property ecosystem, thereby facilitating cross-sectoral technology diffusion, advancing eco-friendly industrial transformation, and promoting sustainable economic growth. Full article

The purpose of this paper is twofold. On a technical side, we propose an extension of the Hausdorff distance from metric spaces to spaces equipped with asymmetric distance measures. Specifically, we focus on extending it to the family of Bregman divergences, which includes the popular Kullback–Leibler divergence (also known as relative entropy). The resulting dissimilarity measure is called a Bregman–Hausdorff divergence and compares two collections of vectors—without assuming any pairing or alignment between their elements. We propose new algorithms for computing Bregman–Hausdorff divergences based on a recently developed Kd-tree data structure for nearest neighbor search with respect to Bregman divergences. The algorithms are surprisingly efficient even for large inputs with hundreds of dimensions. As a benchmark, we use the new divergence to compare two collections of probabilistic predictions produced by different machine learning models trained using the relative entropy loss. In addition to the introduction of this technical concept, we provide a survey. It outlines the basics of Bregman geometry, and motivated the Kullback–Leibler divergence using concepts from information theory. We also describe computational geometric algorithms that have been extended to this geometry, focusing on algorithms relevant for machine learning. Full article

Federated learning (FL) offers a privacy-preserving framework for distributed machine learning, enabling collaborative model training across diverse clients without centralizing sensitive data. However, statistical heterogeneity, characterized by non-independent and identically distributed (non-IID) client data, poses significant challenges, leading to model drift and poor generalization. This paper proposes a novel algorithm, pFedKD-WCL (Personalized Federated Knowledge Distillation with Weighted Combination Loss), which integrates knowledge distillation with bi-level optimization to address non-IID challenges. pFedKD-WCL leverages the current global model as a teacher to guide local models, optimizing both global convergence and local personalization efficiently. We evaluate pFedKD-WCL on the MNIST dataset and a synthetic dataset with non-IID partitioning, using multinomial logistic regression (MLR) and multilayer perceptron models (MLP). Experimental results demonstrate that pFedKD-WCL outperforms state-of-the-art algorithms, including FedAvg, FedProx, PerFedAvg, pFedMe, and FedGKD in terms of accuracy and convergence speed. For example, on MNIST data with an extreme non-IID setting, pFedKD-WCL achieves accuracy improvements of $3.1\%$, $3.2\%$, $3.9\%$, $3.3\%$, and $0.3\%$ for an MLP model with 50 clients compared to FedAvg, FedProx, PerFedAvg, pFedMe, and FedGKD, respectively, while gains reach $24.1\%$, $22.6\%$, $2.8\%$, $3.4\%$, and $25.3\%$ for an MLR model with 50 clients. Full article

Oftentimes in a complex system it is observed that as a control parameter is varied, there are certain intervals during which the system undergoes dramatic change. In biology especially, these signatures of criticality are thought to be connected with efficient computation and information processing. Guided by the classical theory of rate–distortion (RD) from information theory, we propose a measure for detecting and characterizing such phenomena from data. When applied to RD problems, the measure correctly identifies exact critical trade-off parameters emerging from the theory and allows for the discovery of new conjectures in the field. Other application domains include efficient sensory coding, machine learning generalization, and natural language. Our findings give support to the hypothesis that critical behavior is a signature of optimal processing. Full article

Stable Q-value estimation is critical for effective policy learning in deep reinforcement learning (DRL), especially continuous control tasks. Traditional algorithms like Soft Actor-Critic (SAC) and Twin Delayed Deep Deterministic (TD3) policy gradients rely on Mean Squared Error (MSE) loss for Q-value approximation, which may cause instability due to misestimation and overestimation biases. Although distributional reinforcement learning (RL) algorithms like C51 have improved robustness in discrete action spaces, their application to continuous control remains computationally expensive owing to distribution projection needs. To address this, we propose a classification-based Q-value learning method that reformulates Q-value estimation as a classification problem rather than a regression task. Replacing MSE loss with cross-entropy (CE) and Kullback–Leibler (KL) divergence losses, the proposed method improves learning stability and mitigates overestimation errors. Our statistical analysis across 30 independent runs shows that the approach achieves an approximately 10% lower Q-value estimation error in the pendulum environment and a 40–60% reduced training time compared to SAC and Continuous Twin Delayed Distributed Deep Deterministic (CTD4) Policy Gradient. Experimental results on OpenAI Gym benchmark environments demonstrate that our approach, with up to 77% fewer parameters, outperforms the SAC and CTD4 policy gradients regarding training stability and convergence speed, while maintaining a competitive final policy performance. Full article