Search Results (1,337)

This study addresses the problem of correcting systematic errors in classical cascade object detectors under severe data scarcity and distribution shift. We focus on the widely used Viola–Jones framework enhanced with a modified Census transform and propose a modular “corrector” architecture that can be attached to an existing detector without retraining it. The key idea is to exploit the blessing of dimensionality: high-dimensional feature vectors constructed from multiple cascade stages are transformed by PCA and whitening into a space where simple linear Fisher discriminants can reliably separate rare error patterns from normal operation using only a few labeled examples. This study presents a novel algorithm designed to correct the outputs of object detectors constructed using the Viola–Jones framework enhanced with a modified census transform. The proposed method introduces several improvements addressing error correction and robustness in data-limited conditions. The approach involves image partitioning through a sliding window of fixed aspect ratio and a modified census transform in which pixel intensity is compared to the mean value within a rectangular neighborhood. Training samples for false negative and false positive correctors are selected using dual Intersection-over-Union (IoU) thresholds and probabilistic sampling of true positive and true negative fragments. Corrector models are trained based on the principles of high-dimensional separability within the paradigm of one- and few-shot learning, utilizing features derived from cascade stages of the detector. Decision boundaries are optimized using Fisher’s rule, with adaptive thresholding to guarantee zero false acceptance. Experimental results indicate that the proposed correction scheme enhances object detection accuracy by effectively compensating for classifier errors, particularly under conditions of scarce training data. On two railway image datasets with only about one thousand images each, the proposed correctors increase Precision from 0.36 to 0.65 on identifier detection while maintaining high Recall (0.98 → 0.94), and improve digit detection Recall from 0.94 to 0.98 with negligible loss in Precision (0.92 → 0.91). These results demonstrate that even under scarce training data, high-dimensional feature separation enables effective one-/few-shot error correction for cascade detectors with minimal computational overhead. Full article

This study proposes an artificial intelligence (AI)-powered multimodal system designed to enhance the appreciation of traditional poetry, using Japanese haiku as the primary application domain. At the core of the system is an intelligent data analysis pipeline that extracts key emotional features from poetic texts. A fine-tuned Japanese BERT model is employed to compute three affective indices—valence, energy, and dynamism—which form a quantitative emotional representation of each haiku. These features guide a generative AI workflow: ChatGPT constructs structured image prompts based on the extracted affective cues and contextual information, and these prompts are used by DALL·E to synthesize stylistically consistent watercolor illustrations. Simultaneously, background music is automatically selected from an open-source collection by matching each poem’s affective vector with that of instrumental tracks, producing a coherent multimodal (text, image, sound) experience. A series of validation experiments demonstrated the reliability and stability of the extracted emotional features, as well as their effectiveness in supporting consistent cross-modal alignment. These results indicate that poetic emotion can be represented within a low-dimensional affective space and used as a bridge across linguistic and artistic modalities. The proposed framework illustrates a novel integration of affective computing and natural language processing (NLP) within cultural computing. Because the underlying emotional representation is linguistically agnostic, the system holds strong potential for cross-cultural extensions, including applications to Chinese classical poetry and other forms of traditional literature. Full article

Polyphenol oxidase (PPO) is the primary biochemical driver of browning and the subsequent decline of market quality in harvested fruit. In this work, a fully non-invasive analytical framework was built using Visible/Near-Infrared (VIS/NIR) spectroscopy coupled with chemometric modeling in order to estimate PPO activity in two commercially relevant plum cultivars (Khormaei and Khoni). A comprehensive comparative study was conducted utilizing multiple machine learning and linear regression techniques, including Support Vector Regression (SVR), Decision Tree (DT), and Partial Least Squares Regression (PLSR). After acquiring the full VIS/NIR spectra, a suite of metaheuristic feature selection strategies was applied to compress the spectral space to roughly 10–15 highly informative wavelengths. SVR, DT, and PLSR models were then trained and benchmarked using (a) the complete spectral domain and (b) the reduced wavelength subsets. The results consistently demonstrated that non-linear models (DT and SVR) significantly outperformed the linear PLSR method, confirming the inherent complexity and non-linearity of the relationship between the spectra and PPO activity. Across all tests, DT consistently produced the strongest generalization. Under full spectra inputs, DT reached RPD values of 4.93 for Khormaei and 5.41 for Khoni. Even more importantly, the wavelength-reduced configuration further enhanced performance while substantially lowering computational cost, yielding RPDs of 3.32 (Khormaei) and 5.69 (Khoni). The results show that VIS/NIR combined with optimized key-wavelength DT modeling provides a robust, fast, and field-realistic route for quantifying PPO activity in plums without physical destruction of the product. Full article

Accurate wind power forecasting is crucial for the secure and efficient integration of renewable energy into the power grid. However, the inherent intermittency and non-stationary nature of wind power pose significant challenges to prediction models. To address these issues, this paper proposes a novel hybrid forecasting framework named VMD-IPCA-IHSO-FSRVFL. This model synergistically combines variational mode decomposition (VMD), incremental principal component analysis (IPCA) for feature selection, an improved holistic swarm optimization (IHSO) algorithm, and a feature space-regularized random vector functional link (FSRVFL) network. The VMD first decomposes the complex original wind power signal into several stable sub-sequences to simplify the prediction task. The IPCA then identifies and selects the most relevant features, reducing data redundancy and noise. Subsequently, the IHSO algorithm is employed to automatically optimize the hyperparameters of the FSRVFL model, enhancing its performance and convergence speed. Finally, the optimized FSRVFL, a computationally efficient semi-supervised learning model, performs the final prediction. The proposed model was validated using four seasonal datasets from a Chinese offshore wind farm. Experimental results demonstrate that our VMD-IPCA-IHSO-FSRVFL model significantly outperforms other benchmark models, including BP, ELM, RVFL, and their variants, across all evaluation metrics (MSE, RMSE, MAE, and R²). The findings confirm that the integration of signal decomposition, effective feature selection, and intelligent parameter optimization substantially improves forecasting accuracy and stability under different seasonal conditions. This study provides a robust and effective solution for wind power prediction, offering valuable insights for wind farm operation and grid management. Full article

Accurate fault diagnosis of power transformers is critical for maintaining grid reliability, yet conventional dissolved gas analysis (DGA) methods face challenges in feature representation and high-dimensional data processing. This paper presents an intelligent diagnostic framework that synergistically integrates systematic feature engineering, tensor decomposition-based feature selection, and a sparrow search algorithm (SSA)-optimized multi-kernel support vector machine (MKSVM) for transformer fault classification. The proposed approach first expands the original five-dimensional gas concentration measurements to a twelve-dimensional feature space by incorporating domain-driven IEC 60599 ratio indicators and statistical aggregation descriptors, effectively capturing nonlinear interactions among gas components. Subsequently, a novel Tucker decomposition framework is developed to construct a three-way tensor encoding sample–feature–class relationships, where feature importance is quantified through both discriminative power and structural significance in low-rank representations, successfully reducing dimensionality from twelve to seven critical features while retaining 95% of discriminative information. The multi-kernel SVM architecture combines radial basis function, polynomial, and sigmoid kernels with optimized weights and hyperparameters configured through SSA’s hierarchical producer–scrounger search mechanism. Experimental validation on DGA samples across seven fault categories demonstrates that the proposed method achieves 98.33% classification accuracy, significantly outperforming existing methods, including kernel PCA-based approaches, deep learning models, and ensemble techniques. The framework establishes a reliable and accurate solution for transformer condition monitoring in power systems. Full article

This paper introduces a similarity index aimed at modeling psychological well-being through a set-theoretic formalization of self–ideal alignment. Inspired by Tversky’s feature-based model of similarity, the proposed index quantifies the degree of overlap and divergence between the current self-perception and the ideal self, each represented as a vector of signed attributes. The formulation extends traditional approaches in Personal Construct Psychology by incorporating directional and magnitude-based comparisons across constructs, and its mathematical properties can be expressed within a fuzzy similarity space that ensures boundedness and internal coherence. Unlike standard correlational methods commonly used in psychological assessment, this model provides an alternative framework that allows for asymmetric weighting of discrepancies and non-linear representations of similarity. Developed within the WimpGrid formalism—a graph-theoretical extension of constructivist assessment—the index offers potential applications in clinical modeling, idiographic measurement, and the mathematical analysis of dynamic self-concept systems. We discuss its relevance as a generalizable tool for quantitative psychology, and its potential for integration into computational models of personality and self-organization. Full article

Smart farming relies heavily on IoT automation and data-driven decision making, but this growing connectivity also increases exposure to cyberattacks. Flow-based unsupervised intrusion detection is a privacy-preserving alternative to signature and payload inspection, yet it still faces three challenges: loss of subtle anomaly cues during Autoencoder (AE) compression, instability of fixed reconstruction-error thresholds, and performance degradation of clustering in noisy high-dimensional spaces. To address these issues, we propose a fog-aware two-stage hierarchical AE with latent-space gating, followed by Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for attack categorization. A shallow AE compresses the input into a compact 21-dimensional latent space, reducing computational demand for fog-node deployment. A deep AE then computes reconstruction-error scores to isolate malicious behavior while denoising latent features. Only high-error latent vectors are forwarded to DBSCAN, which improves cluster separability, reduces noise sensitivity, and avoids predefined cluster counts or labels. The framework is evaluated on two benchmark datasets. On CIC IoT-DIAD 2024, it achieves 98.99% accuracy, 0.9897 F1-score, 0.895 Adjusted Rand Index (ARI), and 0.019 Davies–Bouldin Index (DBI). To examine generalizability beyond smart farming traffic, we also evaluate the framework on the CSE-CIC-IDS2018 benchmark, where it achieves 99.33% accuracy, 0.9928 F1-score, 0.9013 ARI, and 0.0174 DBI. These results confirm that the proposed model can reliably detect and categorize major cyberattack families across distinct IoT threat landscapes while remaining compatible with resource-constrained fog computing environments. Full article

Indoor landmarks play a crucial role in the process of indoor positioning and route planning for pedestrians or unmanned devices. Indoor structural landmarks, a type of indoor landmarks, can provide rich steering and semantic descriptions for indoor navigation services. However, most traditional indoor landmark extraction methods rely on indoor points of interest and indoor vector map data. These methods face the problem of difficult acquisition of indoor data and overlook the exploration of indoor structural landmarks. Therefore, this paper innovatively proposes a method for extracting indoor structural landmarks based on the commonly available indoor fire protection plan images. First, the HSV model is employed to eliminate noise from the original image, and vector data of indoor components is obtained using the constructed Canny operator. Subsequently, the visibility is calculated based on the grids of indoor space segmentation. Finally, the identification and extraction of indoor structural landmarks are achieved through grid visibility classification, directional clustering analysis, and spatial proximity verification. This approach opens up new ideas for indoor landmark extraction methods. The experimental results show that the method proposed in this paper can effectively extract indoor structural landmarks, the extraction accuracy of indoor structural landmarks reaches over 90%, verifying the feasibility of using indoor fire protection plan data for landmark extraction and expanding the data sources for indoor landmark extraction. Full article

Permanent Magnet Synchronous Generators (PMSGs) have become increasingly important in industrial applications such as wind turbine systems due to their high efficiency and power density. However, their operational reliability can be affected by asymmetries such as static eccentricity (SE) and load current unbalance (UnB), which exhibit similar spectral features and are therefore difficult to differentiate using conventional techniques such as Motor Current Signature Analysis (MCSA). Stray flux analysis provides an alternative diagnostic approach, yet single-point measurements often lack the sensitivity required for accurate fault discrimination. This study introduces a diagnostic methodology based on the Space Vector Stray Flux (SVSF) for identifying static eccentricity (SE) and load current unbalance (UnB) faults in PMSG-based systems. The SVSF is derived from three external stray flux sensors placed 120° electrical degrees apart and analyzed through symmetrical component decomposition, focusing on the +5f_s positive-sequence harmonic. Two-dimensional Finite Element Analysis (FEA) conducted on a 36-slot/12-pole PMSG model shows that the amplitude of the +5f_s harmonic increases markedly under static eccentricity, while it remains nearly unchanged under load current unbalance. To validate the simulation findings, comprehensive experiments have been conducted on a dedicated test rig equipped with high-sensitivity fluxgate sensors. The experimental results confirm the robustness of the proposed SVSF method against practical constraints such as sensor placement asymmetry, 3D axial flux effects, and electromagnetic interference (EMI). The identified harmonic thus serves as a distinct and reliable indicator for differentiating static eccentricity from load current unbalance faults. The proposed SVSF-based approach significantly enhances the accuracy and robustness of fault detection and provides a practical tool for condition monitoring in PMSG. Full article

Recent advances in large language models (LLMs) have enabled the effective representation of customer behaviors, including purchases, repairs, and consultations. These LLM-based customer representation models apply to predicting future behavior of the customer or clustering customers with similar representations by latent vectors. Since these representation technologies depend on data, this paper examines whether training a recommendation model (BERT4Rec) from scratch or fine-tuning a pre-trained LLM (ELECTRA) is more effective for our customer data. To address this, a three-step approach is conducted: (1) defining a sequence of customer behaviors into textual inputs for LLM-based representation learning, (2) extracting customer representation as latent vectors by training or fine-tuning representation models on a dataset of 14 million customers, and (3) training classifiers to predict purchase outcomes for eight products. Our focus is on comparing two primary approaches in step (2): training BERT4Rec from scratch versus fine-tuning pre-trained ELECTRA. The average AUC and F1-score of classifiers across eight products reveal that both methods achieve gaps of only 0.012 in AUC and 0.007 in F1-score. On the other hand, the fine-tuned ELECTRA achieves a 0.27 improvement in the top 10% lift for targeted marketing strategies. This result is particularly meaningful given that buyers of products constitute only about 0.5% of the entire dataset. Beyond the three-step approach, we make an effort to interpret latent space in two-dimensional and attention shifts in fine-tuned ELECTRA. Furthermore, we compare its efficiency advantages against fine-tuned LLaMA2. These findings provide practical insights for optimizing LLM-based representation models in industrial applications. Full article

The Bloom filter remains one of the most influential constructs in probabilistic computation, a structure that achieves a mathematically elegant balance between accuracy, space efficiency, and computational speed. Since the original formulation of Dr. Burton H. Bloom in 1970, its design principles have expanded into a family of approximate membership query (AMQ) structures that now underpin a wide spectrum of modern computational systems. This review synthesizes the theoretical, algorithmic, and applied dimensions of Bloom filters, tracing their evolution from classical bit-vector models to contemporary learned and cryptographically reinforced variants. It further underscores their relevance in artificial intelligence and blockchain environments, where they act as relevance filters. Core developments, which include counting, scalable, stable, and spectral filters, are outlined alongside information-theoretic bounds that formalize their optimality. The analysis extends to adversarial environments, where cryptographic hashing and privacy-oriented adaptations enhance resilience under active attack, and to data-intensive domains such as network systems, databases, cybersecurity, and bioinformatics. Through the integration of historical insight and contemporary advances in learning, security, and system design, the Bloom filter emerges not merely as a data structure but as a unified paradigm for computation under uncertainty. The results presented in this review support practical advances in network traffic control, cybersecurity analysis, distributed storage systems, and large-scale data platforms that depend on compact and fast probabilistic structures. Full article

Frequent fluctuations in virtual item transactions make data access in virtual games highly dynamic. These heat changes denote temporal variations in data popularity driven by trading activity, which in turn cause traditional storage systems to struggle with timely heat adaptation, increased latency, and energy waste. This study proposes an AI-driven modeling framework for virtual game data centers. The heat feature vector composed of transaction frequency, price fluctuation, and scarcity forms the state space of a Markov decision process, while data migration between multi-layer storage structures constitutes the action space. The model captures temporal locality and spatial clustering in transaction behaviors, applies a sliding-window prediction mechanism to estimate access intensity, and enhances load perception. A scheduling mechanism combining an R2D3 (Recurrent Replay Distributed DQN from Demonstrations) policy network with temporal attention and mixed integer programming jointly optimizes latency, energy consumption, and resource constraints to achieve global data allocation tuning. Experiments on a simulated high-frequency trading dataset show that the system reduces access delay to 420 ms at a transaction intensity of 1000 per second and controls the total migration energy consumption to 85.7 Wh. The Edge layer achieves a peak hit rate of 63%, demonstrating that the proposed method enables accurate heat identification and energy-efficient multi-layer scheduling under highly dynamic environments. Full article

We theoretically investigate topological transitions between coplanar and noncoplanar magnetic states in centrosymmetric itinerant magnets on a square lattice. A canonical effective spin model incorporating bilinear and biquadratic exchange interactions at finite wave vectors is analyzed to elucidate the emergence of multiple-Q magnetic orders. By taking into account high-harmonic wave-vector interactions, we demonstrate that a coplanar double-Q spin texture continuously evolves into a noncoplanar triple-Q state carrying a finite scalar spin chirality. The stability of these multiple-Q states is examined using simulated annealing as a function of the relative strengths of the high-harmonic coupling, the biquadratic interaction, and the external magnetic field. The resulting phase diagrams reveal a competition between double-Q and triple-Q states, where the noncoplanar triple-Q phase is stabilized through the cooperative effect of the high-harmonic and biquadratic interactions. Real-space spin textures, spin structure factors, and scalar spin chirality distributions are analyzed to characterize the distinct magnetic phases and the topological transitions connecting them. These findings provide a microscopic framework for understanding the emergence of noncoplanar magnetic textures driven by the interplay between two- and four-spin interactions in centrosymmetric itinerant magnets. Full article

The flow dynamics and heat transfer of dual vertical water jets impinging a high-temperature steel plate were numerically investigated using a three-dimensional model. A systematic parametric investigation was conducted by varying key operating conditions: including the jet velocity at the nozzle exit (V = 5 m/s, 7.5 m/s, 10 m/s), the non-dimensional nozzle-to-plate distance (H = h/d = 3.3, 5.8, 8.3, 10.8), and the non-dimensional spacing between twin nozzles (W = w/d = 5, 7.5, 10). Upon impingement, multiple wall-jet flows formed on the steel plate surface, with their radial spread distance increasing along the plate’s surface. A wall-jet interaction zone developed between the two jets, accompanied by a linear fountain upwash flow. To depict the thermal and hydrodynamic characteristics, the distributions of the local Nusselt number and flow velocity vectors were examined. Findings suggest that fluctuations in W have little impact on the mean Nusselt number. Nevertheless, a growth in H brings about a concurrent increase in the Nusselt number of the stagnation point on the plate’s surface. Furthermore, the results indicate that W is a primary factor controlling the heat transfer rate within the interaction zone of the opposing wall jets. Full article

Background/Objectives: Vector-borne diseases like malaria remain a major global health concern, worsened by insecticide resistance in mosquito populations. Quinoline-based compounds have been extensively studied for their pharmacological effects, including antimalarial and larvicidal properties. Modifying quinoline structures with hydrazone groups may enhance their biological activity and physicochemical properties. This study reports the synthesis, structural characterization, and larvicidal testing of a new series of aryl hydrazones (6a–i) derived from 8-trifluoromethyl quinoline. Methods: Compounds 6a–i were prepared via condensation reactions and characterized using ¹H NMR, ¹⁹F-NMR, ¹³C NMR, and HRMS techniques. Their larvicidal activity was tested against Anopheles arabiensis. Single-crystal X-ray diffraction (XRD) was performed on compound 6d to determine its three-dimensional structure. Hirshfeld surface analysis, fingerprint plots, and interaction energy calculations (HF/3-21G) were used to examine intermolecular interactions. Quantum chemical parameters were computed using density functional theory (DFT). Molecular docking studies were performed for the synthesized compounds 6a–i against the target acetylcholinesterase from the malaria vector (6ARY). In silico ADMET properties were also calculated to evaluate the drug-likeness of all the tested compounds. Results: Compound 6a showed the highest larvicidal activity, causing significant mortality in Anopheles arabiensis larvae. Single-crystal XRD analysis of 6d revealed a monoclinic crystal system with space group P2₁/c, stabilized by N–H···N intermolecular hydrogen bonds. Hirshfeld analysis identified H···H (22.0%) and C···H (12.1%) interactions as key contributors to molecular packing. Density functional theory results indicated a favorable HOMO–LUMO energy gap, supporting molecular stability and good electronic distribution. The most active compounds, 6a and 6d, also showed strong binding interactions with the target protein 6ARY and satisfactory ADMET properties. The BOILED-Egg model is a powerful tool for predicting both blood–brain barrier (BBB) and gastrointestinal permeation by calculating the lipophilicity and polarity of the reported compounds 6a–i. Conclusions: The synthesized arylhydrazone derivatives demonstrated promising larvicidal activity. Combined crystallographic and computational studies support their structural stability and suitability for further development as eco-friendly bioactive agents in malaria vector control. Full article