Reduction Algorithm Research Articles

Sequential Convex Programming for Reentry Trajectory Optimization Utilizing Modified hp-Adaptive Mesh Refinement and Variable Quadratic Penalty

Due to the strong nonlinearity in the reentry trajectory planning problem for reusable launch vehicles (RLVs), the scale of the problem after high-precision discretization can become significantly large, and the non-convex path constraints are prone to exceed limits. Meanwhile, the objective function oscillation phenomenon may occur due to successive convexification, which results in poor convergence. To address these issues, a novel sequential convex programming (SCP) method utilizing modified hp-adaptive mesh refinement and variable quadratic penalty is proposed in this paper. Firstly, a local mesh refinement algorithm based on constraint violation is proposed. Additional mesh intervals and mesh points are added in the vicinity of the constraint violation points, which improves the satisfaction of non-convex path constraints. Secondly, a sliding window-based mesh reduction algorithm is designed and introduced into the hp-adaptive pseudospectral (PS) method. Unnecessary mesh intervals are merged to reduce the scale of the problem. Thirdly, a variable quadratic penalty-based SCP method is proposed. The quadratic penalty term related to the iteration direction and the weight coefficient updating strategy is designed to eliminate the oscillation. Numerical simulation results show that the proposed method can strictly satisfy path constraints while the computational efficiency and convergence of SCP are improved.

Sustainable energy: Advancing wind power forecasting with grey wolf optimization and GRU models

Wind power forecasting is critical for optimizing energy use and ensuring the reliability of wind power systems in renewable energy. This paper introduces a novel method that combines the Grey Wolf Optimization (GWO) algorithm with data compression techniques to enhance feature selection and reduce redundancy in wind speed prediction. By employing GWO, essential features were identified by grouping the dataset into intervals and analyzing their frequencies. Performance evaluation was conducted using various compression measures, including Rate DC-Miss, Rate DC-MEF, and Rate DC-BDG, compared with other models such as extreme gradient boosting, space-time graph neural networks, and deep learning models. The study's results show significant improvements in accuracy and efficiency for predicting wind speed compared to existing techniques. The proposed approach addresses both larger datasets and the impact of noise samples on prediction errors. Additionally, an MLDDR model was introduced to predict DC power generated from wind datasets, encompassing five stages: Data Preparation, Feature Selection, Data Compression, GRU-Based Predictions, and Rate of Reduction. Data reduction results are notable. The original wind dataset (104857613) was reduced to 1093913 after processing missing values, achieving a reduction rate of 0.136. Applying the MEF-GWO algorithm further reduced the dataset to 109395, with a reduction rate of 0.385. The BDG dataset was compressed to 1805, with a reduction rate of 0.607. In terms of prediction performance, the GRU model was evaluated on three datasets: the original, MEF, and BDG-GWO datasets. The GRU model demonstrated the highest accuracy (99.20 %) with the BDG-GWO dataset, with precision (0.9965), recall (0.9978), and F1 scores (0.9897) indicating superior performance. Training and testing times varied significantly, highlighting the computational challenges associated with deep learning techniques. This research addresses both programming and application challenges. Programming challenges include high computational demands and the trial-and-error nature of parameter determination in deep learning, mitigated by using GWO. Application challenges involve reducing large datasets, grouping them into intervals, and evaluating performance using different compression measures. The main research questions addressed include the suitability of the GWO algorithm for dataset reduction in terms of dimensions (features and records) and the effectiveness of combining GWO with deep learning, specifically GRU, for enhanced prediction results. The study concludes that the GWO-PCA and GRU combination significantly improves prediction accuracy and reduces implementation time.

Mitigating signal interferences in quantum computing applications

The use of a crest factor reduction algorithm suppresses voltage peaks caused by multi-tone microwave signals, potentially allowing for advanced quantum computing applications

Evaluation of a Metal Artifact Reduction Algorithm for Image Reconstruction on a Novel CBCT Platform.

The presence of metal implants can produce artifacts and distort Hounsfield units (HU) in patient computed tomography (CT) images. The purpose of this work was to characterize a novel metal artifact reduction (MAR) algorithm for reconstruction of CBCT images obtained by the HyperSight imaging system. Three tissue-equivalent phantoms were fitted with materials commonly used in medical applications. The first consisted of a variety of metal samples centered within a solid water block, the second was an Advanced Electron Density phantom with metal rods, and the third consisted of hip prostheses positioned within a water tank. CBCT images of all phantoms were acquired and reconstructed using the MAR and iCBCT Acuros algorithms on the HyperSight system. The signal-to-noise ratio (SNR), artifact index (AI), structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and mean-square error (MSE) were computed to assess the image quality in comparison to artifact-free reference images. The mean HU at various VOI positions around the cavity was calculated to evaluate the artifact dependence on distance and angle from the center of the cavity. The artifact volume of the phantom (excluding the cavity) was estimated by summing the volume of all voxels with HU values outside the 5th and 95th percentiles of the phantom CBCT with no artifact. The SNR, AI, SSIM, PSNR, and MSE metrics demonstrated significantly higher similarity to baseline when using MAR compared to iCBCT Acuros for all high-density materials, except for aluminum. Mean HU returned to expected solid water background at a shorter distance from metal sample in the MAR images, and the standard deviation remained lower for the MAR images at all distances from the insert. The artifact volume decreased using the novel MAR algorithm for all metal samples excluding aluminum (p<0.001) and all hip prostheses (p<0.05). Varian's HyperSight MAR reconstruction algorithm shows a reduction in metal artifact metrics, motivating the use of MAR reconstruction for patients with metal implants.

A TMSBL underwater acoustic channel estimation method based on dictionary learning denoising

The shallow sea underwater acoustic channel exhibits a significant sparse multipath structure. The temporally multiple sparse Bayesian learning (TMSBL) algorithm can effectively estimate this sparse multipath channel. However, the complexity of the algorithm is high, the signal-to-noise ratio (SNR) of shallow-sea underwater acoustic communication is low, and the estimation performance of the TMSBL algorithm is greatly affected by noise. To address this problem, an improved TMSBL underwater acoustic channel estimation method based on a dictionary learning noise reduction algorithm is proposed. Firstly, the K-Singular Value Decomposition (K-SVD) dictionary learning method is used to reduce the noise of the received pilot matrix, reducing the influence of noise on the signal. Then, the Generalized Orthogonal Matching Pursuit (GOMP) channel estimation method is combined to obtain a priori information such as the perceptual matrix and hyperparameter matrix for TMSBL channel estimation; and the noise variance is obtained by using the null subcarrier calculation instead of iteratively updating the noise variance in the TMSBL, to improve the estimation accuracy and reduce the algorithmic complexity. Finally, the TMSBL channel estimation method is used to estimate the underwater acoustic channels of different symbols jointly. The simulation results show that the normalized mean square error of the channel estimation of the improved TMSBL method is reduced by about 92.2% compared with the TMSBL algorithm, obtaining higher estimation accuracy; running time is reduced by about 45.6%, and there is also better performance in terms of the running speed, which provides a reference for underwater acoustic channel estimation.

Wiener Filter with Convolutional Neural Network for Noise Removal in API-Based AI Models

This research aims to develop a robust Application Program Interface (API)-Based Artificial Intelligence (AI) system for effective noise removal from audio signals, enhancing speech quality and intelligibility in noisy environments to be fed into different AI models to assess the applicant interview. The proposed methodology combines sophisticated signal processing techniques and noise reduction algorithms with AI models trained on clean voice data and noise patterns. To achieve this goal, we leverage two key components: the Wiener filter and a Convolutional Neural Network (CNN). The Wiener filter serves as the foundational noise reduction technique, exploiting statistical properties of the signal and the noise to suppress unwanted noise components effectively. Concurrently, CNN is integrated to classify the clean and noisy audio. In this research, the best optimizers selected, including Adam, SGD, RMSprop, Adagrad, and Adadelta are evaluated to identify the most suitable classification. The optimizers evaluated through cross-validation and hold-out validation in the same batch size (25) and epoch (25) were used. The study demonstrates that the Adam optimizer yields the best results. The epoch was optimized to 35, 75, 105, and 125 and epoch of 105 was selected with accuracy of 99.52%, Recall of 100%, F1-Score of 99.50%, and ROC_AUC of 99.99% for cross-validation while Accuracy of 98.79%, Recall of 99.21%, F1-Score of 98.81%, and ROC_AUC of 99.54% for hold-out validation, significantly improving AI model performance. Lastly, we ensured the batch size parameter was suitable for our model by tuning it with different settings (25, 50, 75, and 125) using the optimized optimizer and epoch. The batch size of 25 yielded the best accuracy. The modeled CNN also included kernel regularization L2 to avoid overfitting.

The analysis of Hermite factor of BKZ algorithm on small lattices

Lattice cryptography is one of the promising directions in modern cryptography research. Digital signatures and key encapsulation mechanisms on lattices have already been used in practice. In the future, such quantum-resistant transformations on lattices replace all standards that are not resistant to attacks on quantum computers. This makes the analysis of their security extremely relevant. Analysis of the security of cryptographic transformations on lattices is often reduced to the estimation of the minimum block size in the lattice reduction algorithm. For the expansion of small vectors, a reduction algorithm can be obtained for a given block size, the GSA model is often used, which uses the so-called Hermitian factor to predict the size of the vectors that the lattice reduction algorithm can obtain given the parameters. Asymptotic formulas have been developed to evaluate it in practice, but the question of their accuracy on cryptographic lattices has not been fully investigated. The work obtained estimates of the accuracy of the existing asymptotic estimates of the Hermite factor for lattices of sizes 120, 145, 170 for the classical BKZ algorithm. Research was conducted using the fpylll library. It was shown that the existing estimators are equivalent from a practical point of view and have a sufficiently small root mean square deviation from the true values. A formula was obtained that binds the root-mean-square error of approximation of the Hermit factor to the cryptographic parameters of lattices. The obtained results are useful for refining the security assessments of existing cryptographic transformations.

Incremental attribute reduction for dynamic fuzzy decision information systems based on fuzzy knowledge granularity

Rough set-based attribute reduction is a powerful technique for data preprocessing in data mining. Knowledge granularity, as a reliable measure for assessing uncertainty in decision information systems (DIS), finds applicability in attribute reduction within such systems. Nevertheless, the limitation arises from the fact that static attribute reduction methods fail to effectively utilize the information contained in acquired data and promptly update knowledge due to the continuous evolution of data. In addition, existing incremental methods based on knowledge granularity are designed exclusively for symbolic data and lack the capability to handle real-valued data. Inspired by this, our study focuses on the attribute reduction approach for fuzzy decision information systems (FDIS) that encompass object variations by utilizing fuzzy knowledge granularity. Firstly, fuzzy knowledge granulation is defined to quantify uncertainty within FDIS, and utilized to determine the importance of attributes for attribute reduction. Additionally, the incremental mechanisms and attribute reduction algorithms are investigated for adding an object and an object set to FDIS, respectively. Moreover, an explication of how the incremental mechanism for increasing an object set can be viewed as a generalization of the mechanism used for a single object is provided. Finally, comparative experiments on various datasets are conducted to validate the effectiveness and efficiency of the proposed incremental algorithms. The results demonstrate that our algorithms achieve superior classification accuracy and while requiring minimal computing time when compared to the comparative algorithms.

DendroTweaks: An interactive approach for unraveling dendritic dynamics.

Neurons rely on the interplay between dendritic morphology and ion channels to transform synaptic inputs into a sequence of somatic spikes. Detailed biophysical models with active dendrites have been instrumental in exploring this interaction. However, such models can be challenging to understand and validate due to the large number of parameters involved. In this work, we introduce DendroTweaks - a toolbox designed to illuminate how morpho-electric properties map to dendritic events and how these dendritic events shape neuronal output. DendroTweaks features a web-based graphical interface, where users can explore single-cell neuronal models and adjust their morphological and biophysical parameters with real-time visual feedback. In particular, DendroTweaks is tailored to interactive fine-tuning of subcellular properties, such as kinetics and distributions of ion channels, as well as the dynamics and allocation of synaptic inputs. It offers an automated approach for standardization and refinement of voltage-gated ion channel models to make them more comprehensible and reusable. The toolbox allows users to run various experimental protocols and record data from multiple dendritic and somatic locations, thereby enhancing model validation. Finally, it aims to deepen our understanding of which dendritic properties are essential for neuronal input-output transformation. Using this knowledge, one can simplify models through a built-in morphology reduction algorithm and export them for further use in faster, more interpretable networks. With DendroTweaks, users can gain better control and understanding of their models, advancing research on dendritic input-output transformations and their role in network computations.

Toward effective SVM sample reduction based on fuzzy membership functions

Support vector machine (SVM) is known for its good generalization performance and wide application in various fields. Despite its success, the learning efficiency of SVM decreases significantly originating from the assumption that the number of training samples increases rapidly. Consequently, the traditional SVM with standard optimization methods faces challenges such as excessive memory requirements and slow training speed, especially for large-scale training sets. To address this issue, this paper draws inspiration from the fuzzy support vector machine (FSVM). Considering that each sample has varying contributions to the decision plane, we propose an effective SVM sample reduction method based on the fuzzy membership function (FMF). This method uses FMF to calculate the fuzzy membership of each training sample. Training samples with low fuzzy memberships are then deleted. Specifically, we propose SVM sample reduction algorithms based on class center distance, kernel target alignment, centered kernel alignment, slack factor, entropy, and bilateral weighted FMF, respectively. Comprehensive experiments on UCI and KEEL datasets demonstrate that our proposed algorithms outperform other comparative methods in terms of accuracy, F-measure, and hinge-loss measures.

Intelligent Fuzzy Traffic Signal Control System for Complex Intersections Using Fuzzy Rule Base Reduction

In this study, the concept of symmetry is employed to implement an intelligent fuzzy traffic signal control system for complex intersections. This approach suggests that the implementation of reduced fuzzy rules through the reduction method, without compromising the performance of the original fuzzy rule base, constitutes a symmetrical approach. In recent decades, urban and city traffic congestion has become a significant issue because of the time lost as a result of heavy traffic, which negatively affects economic productivity and efficiency and leads to energy loss, and also because of the heavy environmental pollution effect. In addition, traffic congestion prevents an immediate response by the ambulance, police, and fire brigades to urgent events. To mitigate these problems, a three-stage intelligent and flexible fuzzy traffic control system for complex intersections, using a novel hybrid reduction approach was proposed. The three-stage fuzzy traffic control system performs four primary functions. The first stage prioritizes emergency car(s) and identifies the degree of urgency of the traffic conditions in the red-light phase. The second stage guarantees a fair distribution of green-light durations even for periods of extremely unbalanced traffic with long vehicle queues in certain directions and, especially, when heavy traffic is loaded for an extended period in one direction and the short vehicle queues in the conflicting directions require passing in a reasonable time. The third stage adjusts the green-light time to the traffic conditions, to the appearance of one or more emergency car(s), and to the overall waiting times of the other vehicles by using a fuzzy inference engine. The original complete fuzzy rule base set up by listing all possible input combinations was reduced using a novel hybrid reduction algorithm for fuzzy rule bases, which resulted in a significant reduction of the original base, namely, by 72.1%. The proposed novel approach, including the model and the hybrid reduction algorithm, were implemented and simulated using Python 3.9 and SUMO (version 1.14.1). Subsequently, the obtained fuzzy rule system was compared in terms of running time and efficiency with a traffic control system using the original fuzzy rules. The results showed that the reduced fuzzy rule base had better results in terms of the average waiting time, calculated fuel consumption, and CO2 emission. Furthermore, the fuzzy traffic control system with reduced fuzzy rules performed better as it required less execution time and thus lower computational costs. Summarizing the above results, it may be stated that this new approach to intersection traffic light control is a practical solution for managing complex traffic conditions at lower computational costs.

Rapid and optimized parallel attribute reduction based on neighborhood rough sets and MapReduce

Attribute reduction is a crucial step in data pre-processing and feature engineering. It is the selection of a subset of relevant data attributes to reduce the computational complexity of machine learning models and improve their performance. Neighborhood rough set (NRS) theory provides a valuable framework for attribute reduction. It leverages neighborhood information to identify non-redundant and informative attributes for data analysis and machine learning tasks. Attribute subsets based on NRS theory are highly qualitative, producing effective prediction accuracies in Euclidean space. However, existing NRS-based solutions are resource-intensive because of the large search space required for finding neighborhoods and redundant computations. To overcome these limitations, we propose the rapid and optimized attribute reduction (ROAR) algorithm that optimizes the current state-of-the-art attribute-reduction method in NRS theory. The strength of ROAR lies in its ability to accelerate computations by rapidly determining the neighborhood consistency of data samples and consequently expediting the identification of both positive and boundary regions. This efficiency significantly enhances the overall processing time for the data analysis tasks. Experimental results on 12 standard datasets demonstrate that the ROAR algorithm exhibits high efficiency by obtaining accurate reduction results with rapid response times. To ensure that the ROAR algorithm is suitable for high-dimensional datasets, we provide a parallel implementation, namely, the P-ROAR algorithm. The P-ROAR algorithm is the first parallel attribute-reduction algorithm in the classical NRS theory. Computational speeds and scalability metrics establish that P-ROAR is much faster and more scalable for datasets with an enormous attribute space. These algorithms provide a tool for handling feature reduction in data engineering without compromising accuracy and performance.

The Noise Reduction Algorithm May Not Compensate for the Degradation in Output Signal-to-Noise Ratio Caused by Wide Dynamic Range Compression.

Most modern hearing aids (HAs) employ wide dynamic range compression (WDRC) and noise reduction (NR) algorithms. It is known that the nonlinear effects of WDRC and NR cause changes to the output signal-to-noise ratio (SNR) of an HA. However, the relative contributions of WDRC and NR to the nonlinear effects are not fully understood. The current study investigated (a) whether WDRC or NR dominates the nonlinear effects measured at the output of a digital HA and (b) whether the electroacoustic effectiveness of NR depends on WDRC parameters while input SNR and background noise are systematically varied. Test stimuli were Connected Speech Test sentences in multitalker babble noise (2- or 20-talker), presented at input SNRs ranging from -10 to +10 dB. The HA was programmed using multiband WDRC set according to the National Acoustic Laboratories for Nonlinear HA fitting formula 2 prescriptive fits for four standard audiograms and two compression speeds. The NR algorithm of the HA was switched on or off in separate conditions. Nonlinear electroacoustic effects from the WDRC and NR algorithms were assessed by measuring the output SNR of the HA using a phase-inversion technique. To investigate whether there are other factors that may be important besides the output SNR, the Hearing Aid Speech Intelligibility Index and the Hearing Aid Speech Quality Index were applied to the recordings to generate inferences on aided speech intelligibility and perceived speech quality. Results showed that WDRC dominated the net nonlinear effect at low-input SNRs, and the net nonlinear effect of WDRC and NR was reduced at high-input SNRs. Results also showed that the effectiveness of NR depended on compression parameters. The effectiveness of NR was partially explained by the trend of Hearing Aid Speech Intelligibility Index and Hearing Aid Speech Quality Index scores, potentially indicating that the Hearing Aid Speech Intelligibility Index and Hearing Aid Speech Quality Index scores may capture factors that cannot be captured by the output SNR metric. Results suggest that the individual signal-processing stages in an HA should not be considered as independent. Electroacoustic evaluation of WDRC and NR algorithms in isolation is not sufficient to capture the combined nonlinear effect of the two algorithms. https://doi.org/10.23641/asha.25962541.

An improved denoising method for [formula omitted]-OTDR signal based on the combination of temporal local GMCC and ICEEMDAN-WT

A noise reduction method based on the combination of improved complete ensemble empirical mode decomposition with adaptive noise and temporal local generalized maximum cross-correlation entropy and wavelet threshold (ICEEMDAN-TLGMCC-WT) is proposed to improve the noise rejection ratio (NRR) of phase-sensitive optical time-domain reflectometer (φ-OTDR) system signals. Firstly, the principle of the proposed ICEEMDAN-TLGMCC-WT denoising method is introduced. On this basis, experiments are carried out to verify the feasibility of the noise reduction algorithm for non-stationary signals. and the results demonstrate that the vibration event can be detected with an improved average NRR of 72.18 dB and a root mean square error (RMSE) 0.017 within 5 km sensing distance by employing the ICEEMDAN-TLGMCC-WT denoising method, which confirm the effectiveness of proposed scheme for the performance improvement of φ-OTDR system.

Parsimonious Tensor Dimension Reduction

Tensor data is emerging in many scientific applications, such as multi-tissue transcriptomics. In such cases, the covariates for each individual are no longer a vector. To apply traditional vector-based methods to this type of data, we need to either do the vectorization or analyze data marginally, which suffers a significant information loss. We propose a novel parsimonious tensor dimension reduction (pTDR) approach to directly link the response and tensor covariate through an unknown function g. In pTDR, the response variable, continuous or discrete, depends on K rank-one projections of the covariates, with the projections estimated via a sequential iterative dimension reduction algorithm. We further propose an asymptotic sequential statistical test to select the correct number of rank-one tensors. In contrast to the classic low-rank tensor regression, pTDR model is not restricted to the linear relationship between response and covariates. We apply pTDR to two modern genomic studies. We find that the gene expression of multiple tissues has a stronger association with aging and obesity than was apparent using previous approaches. Numerical results demonstrate the advantages of pTDR over competitors in terms of prediction accuracy and computing efficiency. Our software is publicly available on GitHub (https://github.com/BioAlgs/pTDR).

Non-invasive follow-up for intracranial aneurysms treated with contour neurovascular system-comparison of digital subtraction angiography (DSA) to magnetic resonance imaging (MRI) and spectral computed tomography angiography (CTA) in vitro.

The contour neurovascular system (CNS) is an intrasaccular flow-disrupting device designed for the treatment of intracranial wide-necked bifurcation aneurysms. Metal artifacts limit magnetic resonance imaging (MRI) accessibility after implantation. The purpose of this in vitro study was to evaluate non-invasive imaging alternatives to digital subtraction angiography (DSA). Three aneurysms of patients originally treated with CNS were three-dimensional (3D)-printed (one at the basilar tip and two at the middle cerebral artery bifurcation). CNS devices were implanted under fluoroscopic control into the 3D models. Post-implantation two-dimensional-DSA, flat panel computed tomography angiography (CTA), MRI, and spectral CTA were performed. Time of flight angiography and T1 weighted sequences showed large susceptibility artifacts at the detachment zone of the devices. A thin-sliced T2 weighted sequence in cross-sectional orientation to the aneurysm allowed visualization of the aneurysm dome, but the aneurysm neck and parent vessel could not be assessed. Focused spectral CTA, especially a 40 keV reconstruction with a metal artifact reduction algorithm (orthopedic metal artifact reduction (OMAR)), showed only minor artifacts at the detachment zone. This approach achieved a very similar result to DSA and flat panel computed tomography, enabling the assessment of the device structure, aneurysm perfusion, and parent vessel perfusion. For non-invasive follow-up of CNS, focused 40 keV CTA with OMAR seems to be a valuable option. MRI can be valuable for larger aneurysms to assess the aneurysm dome, but was not suitable for evaluating the parent vessels and aneurysm neck after CNS implantation in this study.

Rapid identification of moxa wool storage period based on hyperspectral imaging technology and machine learning

Moxa wool (MW), derived from the dried leaves of Artemisiaargyi, plays a significant role in traditional Chinese medicine. However, the quality of MW varies with its storage period, impacting its therapeutic efficacy. Traditional methods for quality detection are limited and destructive. To address this, we propose a non-destructive detection method using hyperspectral imaging technology and machine learning algorithms to accurately identify the storage period of MW. Nevertheless, hyperspectral data poses challenges due to its high dimensionality and redundancy, leading to increased computational complexity. To overcome this, we employed principal component analysis (PCA), competitive adaptive reweighted sampling (CARS), and successive projection algorithm (SPA) for data dimensionality reduction and wavelength selection. The results demonstrate that these techniques significantly enhance the accuracy of MW storage year identification. For Nanyang MW, the CARS+SVM model achieved the highest accuracy rates of 99.8% in the visible-near-infrared (VNIR) range and 99.55% in the shortwave infrared (SWIR) range. Similarly, for Qichun MW, the SPA+SVM model achieved identification accuracies of 99.78% and 99.47% in the VNIR and SWIR ranges, respectively. This research provides valuable insights into the rapid detection of MW quality by indication of storage years and presents a novel approach for quality control of MW in the field of traditional Chinese medicine. The combination of hyperspectral imaging and machine learning offers a promising solution for efficient and accurate MW identification, contributing to the advancement of traditional medicine practices.

Exhaustive Exploitation of Nature-Inspired Computation for Cancer Screening in an Ensemble Manner.

Accurate screening of cancer types is crucial for effective cancer detection and precise treatment selection. However, the association between gene expression profiles and tumors is often limited to a small number of biomarker genes. While computational methods using nature-inspired algorithms have shown promise in selecting predictive genes, existing techniques are limited by inefficient search and poor generalization across diverse datasets. This study presents a framework termed Evolutionary Optimized Diverse Ensemble Learning (EODE) to improve ensemble learning for cancer classification from gene expression data. The EODE methodology combines an intelligent grey wolf optimization algorithm for selective feature space reduction, guided random injection modeling for ensemble diversity enhancement, and subset model optimization for synergistic classifier combinations. Extensive experiments were conducted across 35 gene expression benchmark datasets encompassing varied cancer types. Results demonstrated that EODE obtained significantly improved screening accuracy over individual and conventionally aggregated models. The integrated optimization of advanced feature selection, directed specialized modeling, and cooperative classifier ensembles helps address key challenges in current nature-inspired approaches. This provides an effective framework for robust and generalized ensemble learning with gene expression biomarkers.

Ambulatory ECG noise reduction algorithm for conditional diffusion model based on multi-kernel convolutional transformer.

Ambulatory electrocardiogram (ECG) testing plays a crucial role in the early detection, diagnosis, treatment evaluation, and prevention of cardiovascular diseases. Clear ECG signals are essential for the subsequent analysis of these conditions. However, ECG signals obtained during exercise are susceptible to various noise interferences, including electrode motion artifact, baseline wander, and muscle artifact. These interferences can blur the characteristic ECG waveforms, potentially leading to misjudgment by physicians. To suppress noise in ECG signals more effectively, this paper proposes a novel deep learning-based noise reduction method. This method enhances the diffusion model network by introducing conditional noise, designing a multi-kernel convolutional transformer network structure based on noise prediction, and integrating the diffusion model inverse process to achieve noise reduction. Experiments were conducted on the QT database and MIT-BIH Noise Stress Test Database and compared with the algorithms in other papers to verify the effectiveness of the present method. The results indicate that the proposed method achieves optimal noise reduction performance across both statistical and distance-based evaluation metrics as well as waveform visualization, surpassing eight other state-of-the-art methods. The network proposed in this paper demonstrates stable performance in addressing electrode motion artifact, baseline wander, muscle artifact, and the mixed complex noise of these three types, and it is anticipated to be applied in future noise reduction analysis of clinical dynamic ECG signals.

Asymmetry index for data and its verification in dimensionality reduction and data visualization

We propose an asymmetry index as a measure of degree of asymmetry of a given dataset. It provides an additional information on a dataset allowing to guide and improve any further analysis. The index reflects the intensity of the asymmetric relationships among data resulting from hierarchical data structure. Using the information retrieved by our asymmetry index, one obtains a justification and explanation of the effectiveness of the subsequent asymmetric data analysis methods, as well as helpful preparation to asymmetrizing the tools for the further analysis. The asymmetry index is based on the k-nearest neighbors graph representing the considered data. Therefore, it uses the intrinsic geometry-based information on the data, in this way, providing an insight into the data structure. Our experiments on real data are designed to verify the usefulness of the asymmetry index and the correctness of its theoretical fundamentals. In our empirical validation, we employ the symmetric and asymmetric dimensionality reduction algorithms and evaluate their results on the basis of clustering in the 2-dimensional visualization space. We test, whether our index indeed predicts the level of superiority of the asymmetric methods over their symmetric counterparts.