Small Subset Of Data Research Articles

Empowering Research With the American Heart Association Get With The Guidelines Registries Through Integration of a Database and Research Tools.

The American Heart Association's Get With The Guidelines (GWTG) has emerged as a vital resource in advancing the standards and practices of inpatient care across stroke, heart failure, coronary artery disease, atrial fibrillation, and resuscitation focus areas. The GWTG registry data have also created new opportunities for secondary use of real-world clinical data in biomedical research. Our goal was to implement a scalable database with an integrated user interface (UI) to improve GWTG data management and accessibility. The curation of registry data begins by going through a data processing and quality control pipeline programmed in Python. This pipeline includes data cleaning and record exclusion, variable derivation and unit harmonization, limited data set preparation, and documentation generation of the registry data. The database was built using PostgreSQL, and integrations between the database and the UI were built using the Django Web Framework in Python. Smaller subsets of data were created using SQLite database files for distribution purposes. Use cases of these tools are provided in the article. We implemented an automated data curation pipeline, centralized database, and UI application for the American Heart Association GWTG registry data. The database and the UI are accessible through a Precision Medicine Platform workspace. As of March 2024, the database contains over 13.2 million cleaned GWTG patient records. The SQLite subsets benefit researchers by optimizing data extraction and manipulation using Structured Query Language. The UI improves accessibility for nontechnical researchers by presenting data in a user-friendly tabular format with intuitive filtering options. With the implementation of the GWTG database and UI application, we addressed data management and accessibility concerns despite its growing scale. We have launched tools to provide streamlined access and accessibility of GWTG registry data to all researchers, regardless of familiarity or experience in coding.

NaTech triggered by lightning: Novel insights from past events in the process industry

Lightning strikes, a prominent meteorological event, pose a significant risk of triggering technological disruptions within the process industry. To better understand this phenomenon, an analysis focused on past lightning-triggered events was carried out, examining open-source industrial-accident databases to compile a new NaTech-driven dataset of 689 records. First, an overall quantitative analysis revealed that over 80 % of these events involved incidents or loss of containment. Notably, 83.3 % of them occurred during the spring and summer, indicating a seasonal pattern. Based on the frequency of functional attributes, the chemical and petrochemical macro-sector was the most vulnerable, followed by storage and warehousing. About 40 % of all classifiable events happened on storage equipment, while 21 % happened on electric and electronic devices. Given the lack of valuable information for the principal source of data (NRC), the technological scenarios triggered were characterized using a refined subset of 127 observations, obtained considering the “other sources” of data. Fire scenarios predominated at 56 %; coincidentally, roughly 70 % of all scenarios involved hazardous substances classified as physical hazards. Estimated losses for the available information underscored the adverse consequences of lightning-triggered NaTech events, highlighting their major impact on both safety and the environment. An analysis of the event tree showed the logical path from the lightning strike to the final ignition scenarios (considering a subset of 107 records). This path accounted for 36 % of the classifiable records that directly affected the structure, while more than 50 % of them did not. Bayesian network structures made it possible to get conditional probabilities from the event tree and improved the model by adding attributes for vulnerable equipment and macro-sectors. In order to deal with the uncertain data, algorithms were used to generalize the models that were obtained from smaller subsets of data with more accurate information to the whole dataset. It provides an important additional view of unclassifiable data that otherwise remained in the dark. This novel insight contributes to increase the vulnerability awareness of industrial assets against lightning strikes.

Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling

Human evaluation is viewed as a reliable evaluation method for NLG which is expensive and time-consuming. To save labor and costs, researchers usually perform human evaluation on a small subset of data sampled from the whole dataset in practice. However, different selection subsets will lead to different rankings of the systems. To give a more correct inter-system ranking and make the gold standard human evaluation more reliable, we propose a Constrained Active Sampling Framework (CASF) for reliable human judgment. CASF operates through a Learner, a Systematic Sampler and a Constrained Controller to select representative samples for getting a more correct inter-system ranking. Experiment results on 137 real NLG evaluation setups with 44 human evaluation metrics across 16 datasets and 5 NLG tasks demonstrate CASF receives 93.18\% top-ranked system recognition accuracy and ranks first or ranks second on 90.91\% of the human metrics with 0.83 overall inter-system ranking Kendall correlation. Code and data are publicly available online.

Detecting ringed seal vocalizations in multiple environments using deep learning

Deep learning methods have recently been successfully applied to create a variety of automated acoustic detectors in the field of marine bioacoustics. Automated detectors are essential for analyzing large volumes of passive acoustic monitoring (PAM) data since manual analysis is prohibitively time-consuming and costly. PAM is the primary method for obtaining data on species which are endemic to remote regions, such as the Canadian Arctic. Arctic ringed seals are listed as a Species of Special Concern in Canada due to a loss of critical habitat caused by the effects of climate change. Here, ResNet, a convolutional neural network architecture, is trained on thousands of examples of ringed seal vocalizations recorded at various locations within the Canadian Arctic to create the first practical automated ringed seal detector. The network achieves a precision of 0.89, recall of 0.80, and F1 score of 0.85 when tested on 215 five-minute recordings from sites included in the training process. To improve the generalizability of the detector for new locations, fine-tuning is performed using a small subset of annotated data from new sites. The detector will be available as an open-source tool for researchers to use as the basis for further development of new automated detectors.

Live Iterative Ptychography.

We demonstrate live-updating ptychographic reconstruction with the extended ptychographical iterative engine, an iterative ptychography method, during ongoing data acquisition. The reconstruction starts with a small subset of the total data, and as the acquisition proceeds the data used for reconstruction are extended. This creates a live-updating view of object and illumination that allows monitoring the ongoing experiment and adjusting parameters with quick turn around. This is particularly advantageous for long-running acquisitions. We show that such a gradual reconstruction yields interpretable results already with a small subset of the data. We show simulated live processing with various scan patterns, parallelized reconstruction, and real-world live processing at the hard X-ray ptychographic nanoanalytical microscope PtyNAMi at the PETRA III beamline.

A distributed photonic crystal fiber reverse design framework based on multi-source knowledge fusion

Recent advances in artificial intelligence (AI) have inspired researchers to explore machine learning (ML)-based optimization and reverse design techniques for photonic crystal fibers (PCFs). These studies often seek to improve model generalization, particularly for data that the model has not previously encountered. Traditional centralized training methods are challenging for devices with limited resources, as they rely on aggregating expansive datasets, which is hindered by constraints in storage capacity and communication efficiency. This paper introduces an innovative distributed framework for optimizing PCF parameters, utilizing decentralized training to amalgamate knowledge across various institutions while maintaining data privacy. Each institution develops a lightweight neural network using a small subset of local data, contributing to the construction of a collective and robust global model. This approach is advantageous for both internal and external applications in PCF engineering. Rigorous empirical experiments conducted with real-world PCF optimization data substantiate the efficacy and benefits of the proposed framework. This framework shows promise in achieving an equilibrium between data protection and resource efficiency, offering a novel platform for the reverse design of microstructured optical fibers.

Collaborative analysis for drug discovery by federated learning on non-IID data.

With the increasing availability of large-scale QSAR (Quantitative Structure-Activity Relationship) datasets, collaborative analysis has become a promising approach for drug discovery. Traditional centralized analysis which typically concentrates data on a central server for training faces challenges such as data privacy and security. Distributed analysis such as federated learning offers a solution by enabling collaborative model training without sharing raw data. However, it may fail when the training data in the local devices are non-independent and identically distributed (non-IID). In this paper, we propose a novel framework for collaborative drug discovery using federated learning on non-IID datasets. We address the difficulty of training on non-IID data by globally sharing a small subset of data among all institutions. Our framework allows multiple institutions to jointly train a robust predictive model while preserving the privacy of their individual data. We leverage the federated learning paradigm to distribute the model training process across local devices, eliminating the need for data exchange. The experimental results on 15 benchmark datasets demonstrate that the proposed method achieves competitive predictive accuracy to centralized analysis while respecting data privacy. Moreover, our framework offers benefits such as reduced data transmission and enhanced scalability, making it suitable for large-scale collaborative drug discovery efforts.

Discovery of structure–property relations for molecules via hypothesis-driven active learning over the chemical space

The discovery of the molecular candidates for application in drug targets, biomolecular systems, catalysts, photovoltaics, organic electronics, and batteries necessitates the development of machine learning algorithms capable of rapid exploration of chemical spaces targeting the desired functionalities. Here, we introduce a novel approach for active learning over the chemical spaces based on hypothesis learning. We construct the hypotheses on the possible relationships between structures and functionalities of interest based on a small subset of data followed by introducing them as (probabilistic) mean functions for the Gaussian process. This approach combines the elements from the symbolic regression methods, such as SISSO and active learning, into a single framework. The primary focus of constructing this framework is to approximate physical laws in an active learning regime toward a more robust predictive performance, as traditional evaluation on hold-out sets in machine learning does not account for out-of-distribution effects which may lead to a complete failure on unseen chemical space. Here, we demonstrate it for the QM9 dataset, but it can be applied more broadly to datasets from both domains of molecular and solid-state materials sciences.

TAVI-PREP: A Deep Learning-Based Tool for Automated Measurements Extraction in TAVI Planning.

Transcatheter aortic valve implantation (TAVI) is a less invasive alternative to open-heart surgery for treating severe aortic stenosis. Despite its benefits, the risk of procedural complications necessitates careful preoperative planning. This study proposes a fully automated deep learning-based method, TAVI-PREP, for pre-TAVI planning, focusing on measurements extracted from computed tomography (CT) scans. The algorithm was trained on the public MM-WHS dataset and a small subset of private data. It uses MeshDeformNet for 3D surface mesh generation and a 3D Residual U-Net for landmark detection. TAVI-PREP is designed to extract 22 different measurements from the aortic valvular complex. A total of 200 CT-scans were analyzed, and automatic measurements were compared to the ones made manually by an expert cardiologist. A second cardiologist analyzed 115 scans to evaluate inter-operator variability. High Pearson correlation coefficients between the expert and the algorithm were obtained for most parameters (0.90-0.97), except for left and right coronary height (0.8 and 0.72, respectively). Similarly, the mean absolute relative error was within 5% for most measurements, except for left and right coronary height (11.6% and 16.5%, respectively). A greater consensus was observed among experts than when compared to the automatic approach, with TAVI-PREP showing no discernable bias towards either the lower or higher ends of the measurement spectrum. TAVI-PREP provides reliable and time-efficient measurements of the aortic valvular complex that could aid clinicians in the preprocedural planning of TAVI procedures.

Leveraging global binary masks for structure segmentation in medical images

Deep learning (DL) models for medical image segmentation are highly influenced by intensity variations of input images and lack generalization due to primarily utilizing pixels’ intensity information for inference. Acquiring sufficient training data is another challenge limiting models’ applications. Here, we proposed to leverage the consistency of organs’ anatomical position and shape information in medical images. We introduced a framework leveraging recurring anatomical patterns through global binary masks for organ segmentation. Two scenarios were studied: (1) global binary masks were the only input for the U-Net based model, forcing exclusively encoding organs’ position and shape information for rough segmentation or localization. (2) Global binary masks were incorporated as an additional channel providing position/shape clues to mitigate training data scarcity. Two datasets of the brain and heart computed tomography (CT) images with their ground-truth were split into (26:10:10) and (12:3:5) for training, validation, and test respectively. The two scenarios were evaluated using full training split as well as reduced subsets of training data. In scenario (1), training exclusively on global binary masks led to Dice scores of 0.77 ± 0.06 and 0.85 ± 0.04 for the brain and heart structures respectively. Average Euclidian distance of 3.12 ± 1.43 mm and 2.5 ± 0.93 mm were obtained relative to the center of mass of the ground truth for the brain and heart structures respectively. The outcomes indicated encoding a surprising degree of position and shape information through global binary masks. In scenario (2), incorporating global binary masks led to significantly higher accuracy relative to the model trained on only CT images in small subsets of training data; the performance improved by 4.3%–125.3% and 1.3%–48.1% for 1–8 training cases of the brain and heart datasets respectively. The findings imply the advantages of utilizing global binary masks for building models that are robust to image intensity variations as well as an effective approach to boost performance when access to labeled training data is highly limited.

Semi-supervised machine learning for motor eccentricity fault diagnosis

Eccentricity is one major indicator of mechanical faults in electric machines and needs to be detected early to avoid machine failures. Data-driven techniques based on machine learning and deep learning algorithms have been proposed in recent years for motor fault detection. However, majority of these methods use supervised learning algorithms and require large, labelled datasets, which can be challenging to obtain. In this paper, we propose a semi-supervised learning method based on a deep generative model using variational auto-encoder for eccentricity fault quantification. Good prediction accuracy can be achieved when only a small subset of training data has labels.

Adversarial Coreset Selection for Efficient Robust Training

It has been shown that neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches to training robust models against such attacks. Unfortunately, this method is much slower than vanilla training of neural networks since it needs to construct adversarial examples for the entire training data at every iteration. By leveraging the theory of coreset selection, we show how selecting a small subset of training data provides a principled approach to reducing the time complexity of robust training. To this end, we first provide convergence guarantees for adversarial coreset selection. In particular, we show that the convergence bound is directly related to how well our coresets can approximate the gradient computed over the entire training data. Motivated by our theoretical analysis, we propose using this gradient approximation error as our adversarial coreset selection objective to reduce the training set size effectively. Once built, we run adversarial training over this subset of the training data. Unlike existing methods, our approach can be adapted to a wide variety of training objectives, including TRADES, ell _p-PGD, and Perceptual Adversarial Training. We conduct extensive experiments to demonstrate that our approach speeds up adversarial training by 2–3 times while experiencing a slight degradation in the clean and robust accuracy.

Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasets

BackgroundState-space models, such as Hidden Markov Models (HMMs), are increasingly used to classify animal tracks into behavioural states. Typically, step length and turning angles of successive locations are used to infer where and when an animal is resting, foraging, or travelling. However, the accuracy of behavioural classifications is seldom validated, which may badly contaminate posterior analyses. In general, models appear to efficiently infer behaviour in species with discrete foraging and travelling areas, but classification is challenging for species foraging opportunistically across homogenous environments, such as tropical seas. Here, we use a subset of GPS loggers deployed simultaneously with wet-dry data from geolocators, activity measurements from accelerometers, and dive events from Time Depth Recorders (TDR), to improve the classification of HMMs of a large GPS tracking dataset (478 deployments) of red-billed tropicbirds (Phaethon aethereus), a poorly studied pantropical seabird.MethodsWe classified a subset of fixes as either resting, foraging or travelling based on the three auxiliary sensors and evaluated the increase in overall accuracy, sensitivity (true positive rate), specificity (true negative rate) and precision (positive predictive value) of the models in relation to the increasing inclusion of fixes with known behaviours.ResultsWe demonstrate that even with a small informed sub-dataset (representing only 9% of the full dataset), we can significantly improve the overall behavioural classification of these models, increasing model accuracy from 0.77 ± 0.01 to 0.85 ± 0.01 (mean ± sd). Despite overall improvements, the sensitivity and precision of foraging behaviour remained low (reaching 0.37 ± 0.06, and 0.06 ± 0.01, respectively).ConclusionsThis study demonstrates that the use of a small subset of auxiliary data with known behaviours can both validate and notably improve behavioural classifications of state space models of opportunistic foragers. However, the improvement is state-dependant and caution should be taken when interpreting inferences of foraging behaviour from GPS data in species foraging on the go across homogenous environments.

Learning from Forest Trees: Improving Urban Tree Biomass Functions

Trees are one of the few carbon sinks in urban areas. Different methods are available to assess the biomass of urban trees, one of these being allometric biomass functions. Biomass functions are well investigated, reliable and easy to apply if the required information is available. Our goal is to use biomass functions to enhance urban forest management tools with information on stored biomass and carbon. In this study, we test several approaches to estimate new species-specific biomass functions. We include data from urban and traditional forest trees since both origins can be modeled by the allometric relationship solely giving different parameter estimates. The tested models include mixed allometric models for urban trees only, the adjustments of available forest tree biomass models and a cross-classified mixed model (CCMM) using both data from urban and forest trees. We then show by cross validation that the CCMM, statistically separating the data into different species and origins, shows greater improvement over the simpler models. Hence, we state that the inclusion of forest tree data improves the performance on biomass predictions for urban trees: the urban tree biomass functions “learned from forest trees”. The CCMM is also compared against the predictions of the above-ground biomass functions applied in the German National Forest Inventory. Comparable RMSE and slightly lower BIAS values are found, both for deciduous and coniferous tree species. With the approach of a cross-classified model, we also enable predictions for non-observed conifers in urban space, assuming comparable growth differences between deciduous and conifer species in forest stands and urban areas. A sample application using the CCMM model shows results for a small subset of data of an urban tree inventory, collected in a residential area in the city of Munich, Germany. It is applied to estimate carbon storage at two points in time and, hence, carbon fluxes in the period under consideration. Such information can help in the decision making and management of urban trees.

Loss-aware automatic selection of structured pruning criteria for deep neural network acceleration

Structured pruning is a well-established technique for compressing neural networks, making them suitable for deployment in resource-limited edge devices. This study presents an efficient loss-aware automatic selection of structured pruning (LAASP) criteria for slimming and accelerating deep neural networks. The majority of pruning methods employ a sequential process consisting of three stages, 1) training, 2) pruning, and 3) fine-tuning, whereas the proposed pruning technique adopts a pruning-while-training approach that eliminates the first stage and integrates the second and third stages into a single cycle. The automatic selection of magnitude or similarity-based filter pruning criteria from a specified pool of criteria and the specific pruning layer at each pruning iteration is guided by the network's overall loss on a small subset of training data. To mitigate the abrupt accuracy drop due to pruning, the network is retrained briefly after each reduction of a predefined number of floating-point operations (FLOPs). The optimal pruning rates for each layer in the network are automatically determined, eliminating the need for manual allocation of fixed or variable pruning rates for each layer. Experiments on the VGGNet, ResNet, and MobileNet models on the CIFAR-10 and ImageNet benchmark datasets demonstrate the effectiveness of the proposed method. In particular, the ResNet56 and ResNet110 models on the CIFAR-10 dataset significantly improve the top-1 accuracy compared to state-of-the-art methods while reducing the network FLOPs by 52%. Furthermore, pruning the ResNet50 model on the ImageNet dataset reduces FLOPs by more than 42% with a negligible 0.33% drop in the top-5 accuracy. The source code of this study is publicly available on GitHub: https://github.com/ghimiredhikura/laasp.

Grizzly bear movement models predict habitat use for nearby populations

Conservation planning and decision-making can be enhanced by ecological models that reliably transfer to times and places beyond those where models were developed. Transferrable models can be especially helpful for species of conservation concern, such as grizzly bears (Ursus arctos). Currently, only four grizzly bear populations remain in the contiguous United States. We evaluated transferability of previously derived individual-based, integrated step selection functions (iSSFs) developed from GPS-collared grizzly bears in the Northern Continental Divide Ecosystem by applying them within the nearby Selkirk (SE), Cabinet-Yaak (CYE), and Greater Yellowstone Ecosystems (GYE). We simulated 100 replicates of 5000 steps for each iSSF in each ecosystem, summarized relative use into 10 equal-area classes for each sex, and overlaid GPS locations from bears in the SE, CYE, and GYE on resulting maps. Spearman rank correlations between numbers of locations and class rank were ≥ 0.96 within each study area, indicating models were highly predictive of grizzly bear space use in these nearby populations. Assessment of models using smaller subsets of data in space and time demonstrated generally high predictive accuracy for females. Although generally high across space and time, predictive accuracy for males was low within some watersheds and in summer within the SE and CYE, potentially due to seasonal effects, vegetation, and food assemblage differences. Altogether, these results demonstrated high transferability of our models to landscapes in the Northern Rocky Mountains, suggesting they may be used to evaluate habitat suitability and connectivity throughout the region to benefit conservation planning.

Adaptive SVM-based pixel accumulation technique for a SPAD-based lidar system.

This paper proposes an adaptive support vector machine (SVM)-based pixel accumulation technique for the single-photon avalanche diode (SPAD)-based flash lidar system to greatly improve the accuracy of depth images. In this method, an adaptive incremental SVM classifier is proposed to distinguish the target and background to avoid the boundary blur caused by accumulation. With the SVM classifier, only the pixels belonging to the same target are accumulated. Then by accumulating the multiple measurements of the results of neighboring pixels, the influence of noisy photons can be reduced, and an accurate peak position of the laser signal in the histogram generated by the SPAD detector can be derived. Different from most existing classification algorithms in which the SVM model is used to recognize the target in depth, the image is trained with huge amounts of offline data, which neglect the ability to handle the changes of target's features by building a small subset of input data that contains all needed information of the trained SVM model. The new method could quickly update itself with the motion of target or light intensity changes online and definitely enhance the practicability of the proposed depth image-processing method. Experimental results show that using the proposed adaptive pixel accumulation technique, the mean squared error of depth images can be reduced by 61% compared with raw images and 44% compared with the static SVM-based method when the target moves.

An analysis-ready and quality controlled resource for pediatric brain white-matter research

We created a set of resources to enable research based on openly-available diffusion MRI (dMRI) data from the Healthy Brain Network (HBN) study. First, we curated the HBN dMRI data (N = 2747) into the Brain Imaging Data Structure and preprocessed it according to best-practices, including denoising and correcting for motion effects, susceptibility-related distortions, and eddy currents. Preprocessed, analysis-ready data was made openly available. Data quality plays a key role in the analysis of dMRI. To optimize QC and scale it to this large dataset, we trained a neural network through the combination of a small data subset scored by experts and a larger set scored by community scientists. The network performs QC highly concordant with that of experts on a held out set (ROC-AUC = 0.947). A further analysis of the neural network demonstrates that it relies on image features with relevance to QC. Altogether, this work both delivers resources to advance transdiagnostic research in brain connectivity and pediatric mental health, and establishes a novel paradigm for automated QC of large datasets.

Coresets over multiple tables for feature-rich and data-efficient machine learning

Successful machine learning (ML) needs to learn from good data. However, one common issue about train data for ML practitioners is the lack of good features. To mitigate this problem, feature augmentation is often employed by joining with (or enriching features from) multiple tables, so as to become feature-rich ML. A consequent problem is that the enriched train data may contain too many tuples, especially if the feature augmentation is obtained through 1 (or many)-to-many or fuzzy joins. Training an ML model with a very large train dataset is data-inefficient. Coreset is often used to achieve data-efficient ML training, which selects a small subset of train data that can theoretically and practically perform similarly as using the full dataset. However, coreset selection over a large train dataset is also known to be time-consuming. In this paper, we aim at achieving both feature-rich ML through feature augmentation and data-efficient ML through coreset selection. In order to avoid time-consuming coreset selection over a feature augmented (or fully materialized) table, we propose to efficiently select the coreset without materializing the augmented table. Note that coreset selection typically uses weighted gradients of the subset to approximate the full gradient of the entire train dataset. Our key idea is that the gradient computation for coreset selection of the augmented table can be pushed down to partial feature similarity of tuples within each individual table, without join materialization. These partial feature similarity values can be aggregated to estimate the gradient of the augmented table, which is upper bounded with provable theoretical guarantees. Extensive experiments show that our method can improve the efficiency by nearly 2 orders of magnitudes, while keeping almost the same accuracy as training with the fully augmented train data.

PMAL: A Proxy Model Active Learning Approach for Vision Based Industrial Applications

Deep Learning models’ performance strongly correlate with availability of annotated data; however, massive data labeling is laborious, expensive, and error-prone when performed by human experts. Active Learning (AL) effectively handles this challenge by selecting the uncertain samples from unlabeled data collection, but the existing AL approaches involve repetitive human feedback for labeling uncertain samples, thus rendering these techniques infeasible to be deployed in industry related real-world applications. In the proposed Proxy Model based Active Learning technique (PMAL) , this issue is addressed by replacing human oracle with a deep learning model, where human expertise is reduced to label only two small subsets of data for training proxy model and initializing the AL loop. In the PMAL technique, firstly, proxy model is trained with a small subset of labeled data, which subsequently acts as an oracle for annotating uncertain samples. Secondly, active model's training, uncertain samples extraction via uncertainty sampling, and annotation through proxy model is carried out until predefined iterations to achieve higher accuracy and labeled data. Finally, the active model is evaluated using testing data to verify the effectiveness of our technique for practical applications. The correct annotations by the proxy model are ensured by employing the potentials of explainable artificial intelligence. Similarly, emerging vision transformer is used as an active model to achieve maximum accuracy. Experimental results reveal that the proposed method outperforms the state-of-the-art in terms of minimum labeled data usage and improves the accuracy with 2.2%, 2.6%, and 1.35% on Caltech-101, Caltech-256, and CIFAR-10 datasets, respectively. Since the proposed technique offers a highly reasonable solution to exploit huge multimedia data, it can be widely used in different evolutionary industrial domains.