Computer Science and Mathematics

Abstract: This paper proposes a switching mode beamforming (SMVB) technique for a two-microphone array setup in a multi-source acoustic environment with one dominant target and two interferers. The proposed method adaptively switches between a robust minimum variance beamformer (RMVB) and a linearly constrained minimum variance (LCMV) beamformer based on the eigenvalue characteristics of the spatial covariance matrix. The eigenvalue distribution is used to infer the signal environment and select the appropriate beamforming strategy. Simulation results show that the proposed SMVB method outperforms conventional MVDR, RMVB, and LCMV beamformers in terms of interference suppression and target signal preservation, achieving improved output signal-to-interference-plus-noise ratio (SINR) and overall signal quality.

Abstract: Always-on keyword spotting (KWS) on microcontrollers must reconcile high recognition accuracy with severe constraints on memory, computation, and energy. Most small-footprint KWS research targets English, and its conclusions remain largely unverified for typologically different, consonant-rich languages such as Polish. In this work, we present a complete, hardware-validated KWS solution for Polish on the RP2350 microcontroller (Raspberry Pi Pico 2). We design three compact architectures from the convolutional (CNN), convolutional-recurrent (CRNN), and depthwise-separable (DS-CNN) families and benchmark them against BC-ResNet, a state-of-the-art reference, on a 25-keyword Polish vocabulary using MFCC features. All models are evaluated in full precision (Float32) and after 8-bit integer (INT8) post-training quantization, with inference latency measured directly on the target hardware. BC-ResNet attains the highest full-precision accuracy (97.81%) but is the most fragile under quantization, whereas the proposed CRNN becomes the most accurate quantized model (94.28%), the DS-CNN the smallest (46.15 KB), and the CNN the fastest (107.5 ms); all quantized models meet a one-second real-time budget. We further show that the accuracy ranking inverts after quantization, that memory savings are highly architecture-dependent, and that phonetically similar Polish words are the dominant source of error. These results offer practical guidance for deploying small-footprint KWS in Polish and other under-represented languages.

Abstract: Fine-grained and open-set fault diagnosis of analog circuits poses two challenges that generic deep classifiers fail to address. First, under a closed-set assumption, models assign unseen fault types to known classes with unwarranted confidence, lacking any mechanism to reject out-of-distribution inputs. Second, component manufacturing tolerances induce structured intra-class variation that causes the frequency responses of distinct fault modes to overlap, severely degrading fine-grained discrimination. This paper proposes a Tolerance-Aware Contrastive Siamese Network (TCSN), a metric-learning framework that constructs a discriminative embedding space jointly addressing both issues. The core contribution is the Tolerance-Aware Contrastive Loss (TACL), comprising a tolerance term \( (\mathcal{L}_{\mathrm{tol}}) \) that suppresses tolerance-induced intra-class scatter across Monte Carlo realizations, and a fine-grained term \( (\mathcal{L}_{\mathrm{fg}}) \) that enforces separation of near-identical overlapping classes. For open-set rejection, an energy-based scoring mechanism maps prototype distances into in-/out-of-distribution scores, identifying unknown faults without retraining. The framework is validated on a Sallen-Key second-order Butterworth low-pass filter benchmark (10 known and 2 unknown fault classes). It attains an open-set AUROC of 0.9309 and an FPR@95%TPR of 0.2500; for closed-set classification it reaches 90% accuracy (macro-F1: 0.88), and it retains 83.0% accuracy under one-shot conditions (n = 1). Under corrupted inputs it degrades gracefully, outperforming all baselines at 10 dB SNR. Ablations confirm the necessity of each component: removing \( \mathcal{L}_{\mathrm{tol}} \) drops the open-set AUROC by 0.3793, removing \( \mathcal{L}_{\mathrm{fg}} \) reduces fine-grained accuracy by 11 percentage points, and replacing energy scoring with distance thresholding lowers the AUROC by 0.2683.

Abstract: The digitized models of Chinese traditional musical instruments have fallen behind those of Western musical instruments, therefore they have restricted the preservation work and the research acquiring. This article deals with score-to-audio generation for the Chinese bamboo flute (dizi), it produces expressive audio from MIDI scores which has human performance detail. The current existing methods have two obstacles that they face. First, the large-scale paired training data (MIDI-audio) for traditional Chinese musical instruments is not much. Second, the already existing systems are not able to control the techniques that are specific to instruments—vibrato, pitch bends, ornaments—which the standard MIDI has no ability to encode. We put forward a expandable working flow that produces infinite artificial MIDI-audio matching groups through rule-based music score random arrangement, automatic DAW drawing output by using business sample storage banks, and systemized character pick-up. The information of technique is directly coded in the MIDI stream through the use of note numbers that lie outside the normal range, which thus proves to be more effective than the method of external conditioning. This system is constructed on the basis of MIDI-DDSP. Pre-training makes use of large-scale man-made data to obtain timbre consistency; The fine adjustment carries out the use of actual recording materials (URMP flute corpus) to realize expressive dynamic changes. Only the synthetic data can generate output that is stable but has no life. The real data which exist alone can bring about the problem of overfitting. This combined result can give realistic tone, which has controllable dynamic changes and playing skills.

Abstract: The accuracy of spectro-temporal features for Makhaarij al-Huroof and Sifaat distinguishes between the ten canonical Qiraát recitation styles of the Holy Quran. However, real-world room reverberations blur formant contours and corrupt inter-word energies, thus making Qiraat discrimination difficult. The current dereverberation methods were designed to work under ordinary speech conditions and are not capable of preserving phonetic qualities for domain-specific purposes. This paper introduces a four-step, phase-consistent signal processing approach prioritizing phonetic preservation over direct reverberation suppression. The four steps are: (1) adaptive noise floor attenuation; (2) soft voice activity detection using power-law boundary decay; (3) application-specific spectral contour adjustment from clean Quranic reference audio; and (4) Griffin-Lim algorithm-based phase correction. A total of 48 real-world room recordings were utilized for the evaluation of this approach based on Energy Ratio (ER), Spectral Contrast (SC), and Formant Clarity (FC) – measures specific to the Quran audio domain – alongside conventional speech quality metrics. The proposed approach yielded the highest scores in four out of seven metrics, namely ER (+19.58 dB), SC (+40.11), FC (+822.94), and PESQ (+1.251), while being superior to Spectral Subtraction, Wiener Filtering and WPE Dereverberation approaches. Moreover, the perceptual enhancement was verified in a synthetic controlled experiment where the proposed approach scored an improved PESQ metric (+2.495; SNR −1.874dB). The results illustrate the fact that an optimization for general purpose metrics does not necessarily ensure phonetic preservation required for specific classification.

Abstract: Interpersonal synchrony is a time-dependent coordination pattern in which interacting partners' body movements become temporally aligned. This study frames interpersonal synchrony as a human motion analysis problem and presents Synchrony Vision, an RGB-D sensor-based system for real-time monitoring and event-level analysis of interpersonal motion synchrony in free dialog. The system transforms Kinect-derived skeletal positions into joint acceleration signals, applies sensor-specific conditioning, detects movement peaks, and estimates event-level phase differences between two participants within a ±1.0 s window. The operator-facing interface supports live RGB-D monitoring, acceleration visualization, joint selection, millisecond-scale phase-difference histograms, four synchrony metrics (Frequency, Direction, Width, and Strength), and exportable acceleration, timestamp, peak-pairing, and summary artifacts. We evaluated the deployed pipeline on 25 Kinect-tracked dyads engaged in unconstrained conversation. Across 200.6 min comprising 245,835 frames, the system detected 2,681 synchrony events, exceeded circular-surrogate baselines, and preserved between-dyad ordering across reasonable parameter settings. Motion Energy Analysis-style cross-correlation on the same acceleration signals also confirmed above-chance synchrony but produced different dyad rankings. These findings show that RGB-D skeletal sensing can extend human motion analysis from individual movement capture to transparent, event-level quantification of interpersonal coordination.

Abstract: Accurate R-peak detection in electrocardiogram (ECG) signals is fundamental for cardiovascular analysis. However, most existing methods address differences in sampling frequency (fs) through signal resampling or transfer learning, which may alter the temporal definition of annotated events. In this study, we propose a fs consistent framework for ECG R-peak detection that avoids both resampling and retraining. The proposed method is based on low-sampling morphological learning combined with physiological temporal constraints (PTC). A lightweight classifier (Extreme Gradient Boosting) is trained on 128 Hz ECG data (MIT-BIH Normal Sinus Rhythm Database, XGB) to learn local morphological structures, and feature extraction is defined in milliseconds with time-normalized derivatives to ensure consistency across fs. The trained model is directly applied to higher- fs datasets (360 Hz, 500 Hz, and 1000 Hz) without modification. Final peak locations are determined through deterministic processing, including PTC and local snap processing. Experimental results demonstrated that the proposed method achieved stable detection performance across multiple sampling frequencies. When evaluated in a sample-wise manner, the proposed method achieved mean F1-scores of 0.885 on MIT-BIH Arrhythmia Database (360 Hz), 0.848 on Lobachevsky University Electrocardiography Database (LUDB, 500 Hz, sinus rhythm), 0.837 on LUDB (500 Hz, arrhythmia), and 0.953 on PTB Diagnostic ECG Database (1000 Hz), without any resampling or retraining. The integration of probabilistic candidate detection and deterministic temporal alignment enables consistent peak localization under cross-frequency conditions. These findings demonstrate that augmenting machine learning with deterministic decision mechanisms provides a principled framework for fs -consistent ECG peak detection.

Abstract: Optical imaging is among the safest and most highly impactful biomedical imaging modalities. Aberration in the optical imaging systems leads to distorted images. This distortion is almost nonlinear and hence affects the relative size, intensity and appearance of image details. Image aberration has many types with some or all of them can be imposed on the image based on the quality of the imaging system and/or surrounding conditions. Many approaches have been introduced to remove or minimize aberration from optical images. If the transfer function of an imaging system and the function of the noise added during the imaging process are known, then an ideal image can be obtained from the image produced by this system. The point spread function (PSF) of the optical imaging system is the image it produces for a point object. PSF is the observable form of the transfer function. The transfer function itself is the exit pupil function or typically the system aberration. The nonlinearity and multiplicity of the aberration imposed on the image together with the added noise makes it difficult to obtain the transfer function from the degraded images. In this work, optimization and global search techniques are utilized in an iterative image restoration algorithm. The proposed technique updates an initially suggested solution of transfer function by optimizing the aberration coefficients. The final solution of the transfer function and hence the PSF is reached when the optimum restored image is obtained. The proposed algorithm is validated by a testing image and then its performance is assessed by a set of aberrated images with different degradation. The results obtained in this work showed 100% success rate to obtain the PSF.

Abstract: This paper proposes a novel Topological Data Analysis (TDA) pipeline to extract robust structural features from functional near-infrared spectroscopy (fNIRS) signals for the classification of Alzheimer's Disease (AD) stages. Alzheimer's disease is increasingly understood as a disconnection syndrome, where the disruption of functional brain net-works precedes gross anatomical atrophy. However, traditional graph-theoretic ap-proaches rely on arbitrary connectivity thresholds, which can obscure critical multi-scale topological information and are sensitive to noise. To address this, our framework lev-erages Persistent Homology (PH) to analyse the topological evolution of brain networks across a continuous range of scales. By modeling 48-channel hemoglobin concentration time-series as high-dimensional point clouds via Granger causality metrics, we construct filtration sequences of Vietoris-Rips complexes. The resulting topological invari-ants—specifically 0-dimensional connected components, 1-dimensional loops, and 2-dimensional voids—are captured in Persistence Diagrams and subsequently vectorized into Persistence Images (PIs) using Gaussian kernel smoothing. This transformation enables the integration of complex topological features into standard machine learning workflows. Our experimental results on 284 recordings demonstrate that this topolo-gy-driven feature extraction method yields high discriminative power, achieving 77% accuracy in multi-class diagnosis (NC vs. MCI vs. AD). This study validates the efficacy of TDA as a sophisticated signal processing tool for revealing intrinsic neurodegenerative patterns in hemodynamic data, offering a potential non-invasive biomarker for early detection.

Abstract: This article investigates sensor placement strategies for three-dimensional (3-D) time-of arrival (TOA)-based target localization in Underwater Acoustic Sensor Networks (UASNs). To mitigate underestimation of localization accuracy in complex marine environments, the actual acoustic ray propagation time is derived, and the TOA measurement variance is estimated using the ray acoustic propagation model. These formulations enable a novel 3-D TOA measurement model, and the trace of Cramér-Rao lower bound (CRLB) for this model serves as the optimization criterion for sensor placement. The MinMax k-Means algorithm is proposed to determine the optimal sensor placement by minimizing the average of the trace of CRLB. Extensive numerical simulations are conducted to demonstrate the effectiveness of the placement strategies.

Abstract: The health status of rolling bearings is critical to the normal operation of rotating machinery. To effectively extract vibration signal features and accurately identify different fault types, a novel method based on enhanced composite multi-scale slope entropy (ECMSE) and a honey badger algorithm-optimized kernel extreme learning machine (HBA-KELM) is proposed. Specifically, ECMSE integrates high-order differences into the composite multi-scale framework to capture high-frequency information while preserving low-frequency characteristics, thereby enhancing the discriminability of time-series representations. Meanwhile, an average coarse-graining strategy is incorporated to achieve a more comprehensive characterization of the signals. The extracted features are then input into the HBA-KELM classifier for fault identification. Experiments conducted on two public and private rolling bearing datasets demonstrate that our method achieves superior performance in distinguishing different fault types and damage levels compared with several existing approaches.

Abstract: This paper evaluates the practical use of the Three-Dimensional Discrete Cosine Transform (3D-DCT) for video and volumetric image compression. While one- and two-dimensional DCT transforms are widely used in modern multimedia standards, their three-dimensional extension has received limited attention in real coding systems. In this work, a complete 3D-DCT–based encoder is developed by extending a JPEG-like pipeline to operate on three-dimensional data blocks. The proposed approach processes groups of video frames as 3D cubes and applies a separable 3D-DCT followed by quantization, coefficient serialization, and entropy coding. Unlike conventional video codecs that rely on motion estimation and compensation, the proposed system exploits temporal redundancy directly through the transform domain, resulting in a simpler coding structure with reduced algorithmic complexity. Different configurations are evaluated, including alternative methods for computing the 3D quantization matrix, serialization schemes, and variable block depth along the temporal dimension.Experimental results obtained from multiple test videos and volumetric medical datasets, including CT and MRI studies, demonstrate that the proposed method achieves competitive compression ratios while maintaining good reconstruction quality measured in terms of Peak Signal-to-Noise Ratio (PSNR). The results indicate that 3D-DCT provides a flexible and computationally simple solution for both video compression and three-dimensional medical image coding, particularly in applications where implementation simplicity and frame-level accessibility are important.

Abstract: To address the high computational complexity and insufficient real-time performance of traditional multi-radar trajectory planning methods in complex electromagnetic interference environments, this paper proposes an imitation learning-based trajectory planning method for multi-radar systems. This method designs a trajectory policy neural network architecture based on multiple semantic information. It proposes a training data construction method with coverage rate as the optimization objective. Then the trajectory policy neural network is trained by using an imitation learning algorithm with an auxiliary target. Simulation results show that the proposed method achieves an average coverage rate of 93.95%, and improves the single-step decision efficiency by a factor of 6.7 compared with heuristic-based trajectory optimization methods.

Abstract: With the increasing demand for high-quality imaging in consumer electronics, image aesthetic assessment (IAA) has been widely applied to electronic cameras and display devices. Although the deformable attention mechanism has been introduced into IAA due to its perceptual capabilities, enabling models to refine attention regions by learning interest points and their corresponding offsets, existing methods often lack guidance from aesthetic composition features during the offset generation process, which limits their performance in aesthetic evaluation tasks. To address this issue, we propose a Graph Neural Network (GNN)-guided deformable attention module that incorporates composition information into the generation of interest points by modeling image features as graphs and applying GNN to guide interest point selection. In addition, we design an improved Transformer model that employs neighborhood attention to further enhance IAA performance. We evaluate the proposed model on two aesthetic datasets, AVA and TAD66K, and the experimental results demonstrate its effectiveness in improving overall model performance.

Abstract: This paper presents a hybrid model for the control of brain-computer interfaces (BCIs) for Metaverse environments, with the goal of advancing the capabilities of such interfaces beyond the traditional motor imagery (MI) or P300-based brain-computer interfaces. This hybrid model utilizes P300 for virtual devices' interaction and MI for navigation and movement imagination in the Metaverse, with each EEG modality being dedicated to a particular control state and state changes being made sequentially based on the context of the interaction. In the simulated experiment, the imagined movement of the left and right hands is used for rotational navigation, while discrete devices' actions use P300 responses under a five-stimulus oddball paradigm. In the performance evaluation, the paper shows that the hybrid model, with the use of MI and P300 under a single BCI, achieves accuracy comparable to single-mode BCIs, with advantages over existing BCI systems regarding their capabilities for interaction and adaptability, thus proving the effectiveness of hybrid control for achieving dynamic and flexible Metaverse interactions.

Abstract: Background: Sensor-based systems and virtual reality (VR) technologies provide new opportunities for the objective, technology-driven assessment and training of visuo-motor performance in applied contexts such as sport. Methods: This study examined the effects of an integrated visual training program combining stroboscopic stimula-tion, VR-based vergence exercises, and instrumented reaction-light tasks in adolescent handball players. Twenty-eight youth athletes completed two baseline assessments separated by six weeks, followed by a six-session training program integrated into reg-ular team practice. Sensor-derived outcome measures included dynamic accommoda-tive performance, simple and choice visual reaction times, peripheral-field response metrics, binocular alignment, stereoscopic depth perception, and basic oculomotor function. Results: Compared with both baseline measurements, the intervention pro-duced selective improvements in accommodative facility—particularly near–far fo-cusing speed—and in multiple reaction-time conditions involving manual and deci-sion-based responses. Specific peripheral-field locations showed increased response scores, whereas binocular alignment, AC/A ratio, near phoria, and stereoscopic acuity remained unchanged. Conclusions: These findings indicate that technology-supported visual training protocols incorporating sensor-based reaction systems and VR stimuli can be associated with measurable adaptations in dynamic visuomotor processing while preserving fundamental binocular vision parameters.

Abstract: Recently, when forming radar video frames for surface mapping, group-interacting compact onboard radar systems (CORS) are increasingly being utilized. In this context, for the cooperative functioning of the group, each compact radar should use its own unique marked signal as the probing signal. This signal must be distinguishable in the common channel and should not destructively affect the probing signals emitted by other radars within the group. This organization allows for associating the marked signals reflected from the underlying surface with specific CORS in the group. This requirement arises from the fact that each compact onboard radar in the group emits a single probing signal and then receives all the reflected signals from the surface that were emitted by the other CORS in the group. Such an organization of the group-based system of technical vision requires the search for and study of specialized marked code structures used for phase modulation of probing signals to identify them in the shared radar channel. The study focuses on the search for new complex M-sequences with lower sidelobe levels of the normalized autocorrelation function compared to traditional M-sequences. This is achieved by replacing the traditional alphabet of positive and negative ones with an asymmetric set consisting of complex numbers. Using numerical methods and computer simulations, optimal complex values of the sequence with a minimum level of sidelobes in the autocorrelation function are determined. In addition to correlation properties, the phase-modulated signals generated based on the new marked sequences are also investigated. The results obtained open up new possibilities for the construction of a group-based technical vision system, enabling cooperative surface probing with each CORS in the interacting group.

Abstract:

Electroencephalography (EEG) has transitioned from a subjective observational method into a data-intensive analytical field that utilises sophisticated algorithms and mathematical modeling. This progression encompasses developments in signal preprocessing, artifact removal, and feature extraction techniques including time-domain, frequency-domain, time-frequency, and nonlinear complexity measures. To provide a holistic foundation for researchers, this review begins with the neurophysiological basis, recording technique and clinical applications of EEG, while maintaining its primary focus on the diverse methods used for signal analysis. It offers an overview of traditional mathematical techniques used in EEG analysis, alongside contemporary, state-of-the-art methodologies. Machine Learning (ML) and Deep Learning (DL) architectures, such as Support Vector Machines (SVMs), Convolutional Neural Networks (CNNs), and transformer models, have been employed to automate feature learning and classification across diverse applications. We conclude that the next generation of EEG analysis will likely converge into Neuro-Symbolic architectures, synergising the generative power of foundation models with the rigorous interpretability of signal theory.

Abstract: Drone localization is essential for various purposes such as navigation, autonomous flight, and object tracking. However, this task is challenging when satellite signals are unavailable. This paper addresses vision-only localization of flying drones through op-timal window velocity fusion. Multiple optimal windows are derived from a piecewise linear regression (segment) model of the image-to-real world conversion function. Each window serves as a template to estimate the drone's instantaneous velocity. The multiple velocities obtained from multiple optimal windows are integrated by two fusion rules: one is a weighted average for lateral velocity, and the other is a winner-take-all decision for longitudinal velocity. In the experiments, a drone performed a total of six short-range (about 800 m to 2 km) and high maneuvering flights in rural and urban areas. Four flights in rural areas consist of a forward-backward straight flight, a forward-backward zigzag flight (a snake path), a square path with three banked turns, and a free flight that includes both banked turns and zigzags. Two flights in urban areas are a straight outbound flight and a forward-backward straight flight. The performance was evaluated through the root mean squared error (RMSE) and drift error of the ground-truth trajectory and the rig-id-body rotated vision-only trajectory. The proposed image-based method has been shown to achieve flight errors of a few meters to tens of meters, which corresponds to around 3% of the flight length.

Abstract: Many machine-learning tasks involve structured data whose geometry, local feature distributions and global organization interact in ways that are not well captured by existing methods based on vectorization, graph metrics or homological signatures. We introduce Fiber Bundle Learning (FBL), a topological framework that represents each data sample as a discrete fiber bundle and extracts a classification signature combining persistent homology, local feature geometry and gluing structure. FBL builds a base space from the coarse geometry of each object, models local feature patches as fibers and estimates transition maps between neighboring fibers to construct a discrete connection. From this representation, FBL computes a set of invariants: persistent homology of the base, fibers and total space; holonomy obtained by transporting fiber states along cycles; curvature-like quantities measuring transition inconsistency; discrete analogues of characteristic classes. These components are assembled into a fixed-length feature vector that can be used with any standard classifier. We show that FBL yields a signature with three desirable theoretical properties: stability under perturbations of geometry and local features; invariance under isometries and global fiber reparameterizations; robustness to sampling noise. Our synthetic experiments show that FBL distinguishes twisted from untwisted bundles with identical homology, a distinction classical topological methods fail to capture. Additional tests quantify the system’s resistance to noise, its invariance to geometric transformations and the contribution of each signature component. Taken together, our results indicate that representing data through fiber-bundle structure may provide an effective tool for classifying complex, multi-level objects.