Challenge For Various Applications Research Articles

Optimized multi-layer self-attention network for feature-level data fusion in emotion recognition

<p>Understanding human emotions across diverse data sources presents challenges in various applications including healthcare, human-machine interaction, security, marketing, and gaming. Prior research has explored fusion techniques to address multimodal data heterogeneity, yet often overlooks the importance of discriminative unimodal information and potential complementarity among fusion strategies. Recognizing emotions from video and audio data poses challenges such as non-verbal cues interpretation, varying expression, ambiguity in context, and the need for nuanced feature extraction to capture subtle emotional nuances accurately. To tackle these issues, it is imperative to employ efficient emotion representation and multimodal fusion techniques, as these tasks have significant importance within the realm of multifaceted recognizing study. This study introduced a novel approach, optimized multi-layer self-attention network for emotion recognition (OMSN-ER), focusing on feature-level data fusion. OMSN-ER precisely assesses emotional states by merging facial and voice data, utilizing a multi-layer progressive dense residual fusion network and a self-attention mountain gazelle convolution neural network. Implemented in Python with the RAVDESS dataset, the methodology achieves exceptional accuracy (0.9908), surpassing benchmarks and demonstrating efficacy in multimodal emotion recognition. This research represents promising advancements in the intricate field of emotion recognition.</p>

Harnessing perovskite materials for water decontamination: a comprehensive review.

Perovskites have recently emerged as a promising class of materials with a wide range of applications, including solar cells, light-emitting diodes, and catalysts. In addition, perovskites have demonstrated significant potential for water decontamination due to their tunable properties and facile synthesis. This review article provides a comprehensive overview of perovskites, including their preparation techniques, crystal structure, and electronic properties. The article also highlights the various applications of perovskites, with a particular focus on their use in water decontamination. The different types of perovskites for water decontamination, including simple, substituted, and doped perovskites, as well as nanoscopic and supported perovskites, are discussed in detail. Furthermore, the article addresses the beneficial costs of perovskites and the environmental impacts associated with their use, including toxicity and end-of-life management. The aim of this review article is to provide a broad perspective on perovskites and their potential for water decontamination, as well as future prospects and challenges in various applications.

Fuzzy anomaly scores for Isolation Forest

The detection of anomalies in data presents a significant challenge in various applications. The Isolation Forest (IF) has gained attention due to its notable performance features, including high accuracy, efficiency, simplicity, and rapid computation. However, prior research has primarily concentrated on the constructing isolation trees (iTrees), overlooking the considerable influence of anomaly scoring methods on anomaly detection performance. This study introduces an innovative anomaly scoring method that integrates fuzzy concepts to enhance detection performance. Fuzzy concepts adeptly manage ambiguity and uncertainty, making them more readily applicable in anomaly scoring than in iTree training. Unlike conventional methods that assign a sample to a single child node in the decision path, the proposed fuzzy anomaly scoring method allows samples to be assigned to all child nodes with varying membership degrees based on the target sample. Consequently, this method aggregates the path lengths of all external nodes in a weighted manner, minimizing the impact of irrelevant splits on anomaly scores. Considering that even IF algorithms using informative splits select splits based on data distribution rather than label information, introducing fuzziness to the splits themselves can effectively mitigate performance degradation caused by irrelevant splits. Extensive experiments on 25 benchmark datasets demonstrated that the proposed anomaly scoring method significantly improved both the performance and stability of anomaly detection with the base IF algorithm, outperforming other IF algorithms and fuzzy rough set-based anomaly detection methods.

Deep Learning Conceptual Design of Sit-to-Stand Parallel Motion Six-Bar Mechanisms

Abstract The sit-to-stand (STS) motion is a crucial activity in the daily lives of individuals, and its impairment can significantly impact independence and mobility, particularly among disabled individuals. Addressing this challenge necessitates the design of mobility assist devices that can simultaneously satisfy multiple conflicting constraints. The effective design of such devices often involves the generation of numerous conceptual mechanism designs. This paper introduces an innovative single-degree-of-freedom (DOF) mechanism synthesis process for developing a highly customizable sit-to-stand (STS) mechanical device by integrating rigid body kinematics with machine learning. Unlike traditional mechanism synthesis approaches that primarily focus on limited functional requirements, such as path or motion generation, our proposed design pipeline efficiently generates a large number of 1DOF mechanism geometries and their corresponding motion paths, known as coupler curves. Leveraging a generative deep neural network, we establish a probabilistic distribution of coupler curves and their mapping to mechanism parameters. Additionally, we introduce novel metrics for quantitatively evaluating and prioritizing design concepts. The methodology yields a diverse set of viable conceptual design solutions that adhere to the specified constraints. We showcase various single-degree-of-freedom six-bar linkage mechanisms designed for STS motion, presenting them in a ranked order based on established criteria. While the primary focus is on the integration of STS motion into a versatile mobility assist device, the proposed approach holds broad applicability for addressing design challenges in various applications.

A Comprehensive Survey of Continual Learning: Theory, Method and Application.

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to develop themselves adaptively. In a general sense, continual learning is explicitly limited by catastrophic forgetting, where learning a new task usually results in a dramatic performance drop of the old tasks. Beyond this, increasingly numerous advances have emerged in recent years that largely extend the understanding and application of continual learning. The growing and widespread interest in this direction demonstrates its realistic significance as well as complexity. In this work, we present a comprehensive survey of continual learning, seeking to bridge the basic settings, theoretical foundations, representative methods, and practical applications. Based on existing theoretical and empirical results, we summarize the general objectives of continual learning as ensuring a proper stability-plasticity trade-off and an adequate intra/inter-task generalizability in the context of resource efficiency. Then we provide a state-of-the-art and elaborated taxonomy, extensively analyzing how representative strategies address continual learning, and how they are adapted to particular challenges in various applications. Through an in-depth discussion of promising directions, we believe that such a holistic perspective can greatly facilitate subsequent exploration in this field and beyond.

FUSION3D: Multimodal data fusion for 3D shape reconstruction: A soft-sensing approach

Traditional high-fidelity imaging techniques, such as X-ray computer tomography (CT), excel in capturing intricate shape details through high-resolution two-dimensional (2D) images. However, the extensive cost or impracticality of obtaining X-ray images poses a significant challenge in various applications (e.g., dense metal components in manufacturing). To overcome this limitation, we propose a soft sensing approach, named FUSION3D, aimed at reconstructing three-dimensional (3D) shapes from 2D sliced images and heterogenous process inputs using a novel model based on multi-modal process knowledge. The developed FUSION3D method is built upon a deep learning framework that utilizes continuous normalizing flow to model the complex shape distribution of 3D objects. We propose a principled probabilistic framework to regularize 3D point clouds by modeling them as a distribution of distributions. Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes, and the second level is the distribution of points given a shape. Our generative regularization model learns each level of the distribution with a continuous normalizing flow. The invertibility of normalizing flows enables the computation of the likelihood during training and allows us to train our model in the variational inference framework. Our methodology is validated through a case study in additive manufacturing, demonstrating its effectiveness as a soft sensing approach for accurate 3D shape reconstruction without relying on high-fidelity imaging techniques like CT during model deployment.

Robust two-stage instance-level cost-sensitive learning method for class imbalance problem

The class imbalance problem is a pervasive challenge in various applications, prompting researchers to design specialized loss functions for instance-level cost-sensitive learning models. However, the performance deteriorates when datasets are contaminated by label noise, especially in scenarios with uneven noise distribution. Additionally, specific hard-to-classify samples can further impede performance. Addressing these issues and establishing a robust instance-level cost-sensitive learning framework remains a formidable challenge. In this paper, we propose a robust Two-Stage instance-level cost-sensitive learning method with the Bounded Quadratic Type Squared Error (BQTSE) loss function, termed TSBQT. The asymmetric and bounded nature of the BQTSE loss function not only allows for distinct cost assignments to majority and minority instances, but also enhances the robustness to uneven noise. Moreover, our two-stage learning strategy prioritizes hard-to-classify instances by considering their classification difficulty. We solve TSBQT using the alternating direction method of multipliers and gradient descent algorithm. The generalization capability of TSBQT is analyzed with the Rademacher complexity theory. Extensive experiments validate the effectiveness of TSBQT.

Optimizing a machine learning design of dielectric properties in lead-free piezoelectric ceramics

Designing lead-free piezoelectric ceramics with tailored electrical properties remains a critical challenge for various applications. In this paper we present a novel methodology integrating Machine Learning (ML) and optimization procedures to fine-tune electrical properties in lead-free (1-x) Na0.5 Bi0.5 TiO3 - x CaTiO3 piezoelectric ceramics. A comprehensive dataset of dielectric measurements serves as the foundation for training ML models that accurately predict the permittivity (ε′) and dielectric loss (tan δ) as functions of Ca2+ concentration (x % Ca), temperature and frequency. Two ML techniques are evaluated: random forest regression, and Multi-Layer Perceptron neural network Regression (MLPR). The MLPR model exhibited a superior regression performance, achieving a correlation coefficient of 0.931 and a root mean squared error of 0.029. The MLPR was then optimized by the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to maximizes ε′ while minimizes tan δ. Within the NSGA-II framework, the optimal values were found at the Pareto curve knee, corresponding to a frequency, temperature, and x % Ca of 609.739 kHz, 398.15 K, and 6.10, respectively, resulting in ε′ equal to 857.87 and tan δ equal to 0.0120. This approach demonstrates the effectiveness of combining ML and optimization for designing the electrical properties of piezoelectric ceramics, paving the way for more efficient and targeted material development.

Shaping an evanescent focus of light for high spatial resolution optogenetic activations in live cells

Confining light illumination in the three dimensions of space is a challenge for various applications. Among these, optogenetic methods developed for live experiments in cell biology would benefit from such a localized illumination as it would improve the spatial resolution of diffusive photosensitive proteins leading to spatially constrained biological responses in specific subcellular organelles. Here, we describe a method to create and move a focused evanescent spot, at the interface between a glass substrate and an aqueous sample, across the field of view of a high numerical aperture microscope objective, using a digital micro-mirror device (DMD). We show that, after correcting the optical aberrations, light is confined within a spot of sub-micron lateral size and ∼100 nm axial depth above the coverslip, resulting in a volume of illumination drastically smaller than the one generated by a standard propagative focus. This evanescent focus is sufficient to induce a more intense and localized recruitment compared to a propagative focus on the optogenetic system CRY2-CIBN, improving the resolution of its pattern of activation.

Optimal surface clothing with elastic nets

The clothing problem aims at identifying the shape of a planar fabric for covering a target surface in the three-dimensional space. It poses significant challenges in various applications, ranging from fashion industry to digital manufacturing. Here, we propose a novel inverse design approach to the elastic clothing problem that is formulated as a constrained optimization problem. We assume that the textile behaves as an orthotropic, nonlinear elastic surface with fibers distributed along its warp and weft threads, and we enforce mechanical equilibrium as a variational problem. The target surface is frictionless, except at its boundary where the textile is pinned, imposing a unilateral obstacle condition for the reactive forces at the target surface. The constrained optimization problem also accounts for an elongation condition of the warp and weft fibers, possibly with bounded shearing angle. We numerically solve the resulting constrained optimization problem by means of a gradient descent algorithm. The numerical results are first validated against known clothing solutions for Chebyshev nets, taking the limit of inextensible fibers. We later unravel the interplay between thread and shear stiffness for driving the optimal cloth shape covering the hemisphere and the hemicatenoid. We show how the metric of these target surfaces strongly affects the resulting distribution of the reaction forces. When considering the limit of covering the full sphere, we show how clothing with elastic nets allows to avoid the onset of singularities in the corresponding Chebyshev net, by developing corners at the cloth boundary.

Identification of acetaldehyde based on plasmonic patterns of a gold nanostructure conjugated with chromophore and H2O2: a new platform for the rapid and low-cost analysis of carcinogenic agents by colorimetric affordable test strip (CATS).

Acetaldehyde, a prevalent carbonyl compound in fermented foods, poses challenges in various applications due to its reactivity. This study addresses the need for efficient acetaldehyde detection methods across biotechnological, environmental, pharmaceutical, and food sectors. Herein, we present a novel colorimetric/UV spectrophotometric approach utilizing gold nanoparticles (AuNPs), particularly gold nano-flowers (AuNFs), for sensitive acetaldehyde identification. The method exhibits a notable sensitivity, detecting acetaldehyde at concentrations as low as 0.1 μM. The mechanism involves the interaction of acetaldehyde molecules with AuNFs, leading to a significant change in the absorbance spectrum, which serves as the basis for detection. Moreover, its applicability extends to human biofluids, notably urine samples. Integration with a cost-effective one-drop microfluidic colorimetric device (OD-μPCD) enables the development of an affordable test strip (CATS). This semi-analytical device, employing a multichannel OD-μPCD, facilitates real-time analysis of acetaldehyde in human samples. Our findings demonstrate the pioneering utilization of AuNPs for selective and sensitive acetaldehyde detection, promising advancements in environmental and occupational safety standards, and laying a foundation for enhanced detection and monitoring of related volatile organic compounds (VOCs).

Development of a water-soluble ouroboros-like calix[6]arene-trisimidazole-based ligand for enhanced binding of zinc.

Increasing the thermodynamic stability of metal complexes in water is a key challenge for various applications of coordination chemistry. In this study, a calix[6]arene macrocycle functionalized with three imidazole units on the narrow rim and three primary amino legs on the wide rim was synthesized and studied. This ligand coordinates a Zn2+ cation in water, within a pH window centered around 7, through the three imidazole units and one self-included amino leg occupying the coordination site within the macrocycle cavity. The coordination process benefits from a favourable entropic effect, conferring greater thermodynamic stability to the resulting ouroboros-like complex compared to the one stabilized by an exogenous amine. Additionally, the intramolecular coordination ensures a supramolecular protection, which can be exploited for the site-selective functionalization of two out of the three amino groups. These findings demonstrate that the use of macrocyclic ligands capable of forming ouroboros-like molecular complexes represents a valuable strategy for stabilizing metal ions in water.

Quinoxaline derivatives as attractive electron-transporting materials.

This review article provides a comprehensive overview of recent advancements in electron transport materials derived from quinoxaline, along with their applications in various electronic devices. We focus on their utilization in organic solar cells (OSCs), dye-sensitized solar cells (DSSCs), organic field-effect transistors (OFETs), organic-light emitting diodes (OLEDs) and other organic electronic technologies. Notably, the potential of quinoxaline derivatives as non-fullerene acceptors in OSCs, auxiliary acceptors and bridging materials in DSSCs, and n-type semiconductors in transistor devices is discussed in detail. Additionally, their significance as thermally activated delayed fluorescence emitters and chromophores for OLEDs, sensors and electrochromic devices is explored. The review emphasizes the remarkable characteristics and versatility of quinoxaline derivatives in electron transport applications. Furthermore, ongoing research efforts aimed at enhancing their performance and addressing key challenges in various applications are presented.

Multifunctional photoactive cotton fabric coated with Ag-AgI/TiO2 nanocomposite for environmental and biological applications under sunlight

Developing multifunctional cellulose-based materials with photoactive properties, suitable for a wide range of environmental and biological applications under sunlight, is of paramount importance. In this study, we describe the synthesis of an Ag-AgI/TiO2 nanocomposite on cotton fabric (CF) using a moderate hydrothermal method to create a TiO2 layer that effectively coats the CF. The subsequent photoreduction via the impregnation method yields evenly distributed Ag-AgI nanoparticles (NPs) on the TiO2 layer. Raman spectroscopy, X-ray diffraction (XRD), and X-ray photoelectron spectroscopy (XPS) characterizations unequivocally confirm the presence of anatase TiO2 and Ag-AgI nanoparticles as the principal constituents of the photoactive textile. Our prepared photoactive textile exhibits exceptional performance in the photocatalytic degradation of aniline pollutants, achieving an impressive 97% removal rate under simulated sunlight irradiation for 6 h. Moreover, the textile can be easily reused following a simple washing process. When exposed to volatile organic compounds (VOCs), it demonstrates complete ethanol decomposition with a mineralization rate of 79% after 4 h of illumination. Additionally, our composite showcases potent antibacterial properties by effectively inactivating pathogenic bacteria such as Escherichia coli, highlighting its versatility as a photocatalyst for a wide range of environmental and biological applications. The significant improvement in photocatalytic properties can be primarily attributed to the synergistic effect between TiO2 and Ag-AgI a pronounced surface plasmon resonance (SPR) effect of Ag-AgI NPs, increased visible light absorption, and suppressed charge carriers recombination. Moreover, our photoactive textile demonstrates exceptional durability and augmented mechanical strength, ensuring long-term functionality.The elaborated multifunctional Ag-AgI/TiO2/CF photoactive textile offers substantial potential for sustainable solutions to contemporary challenges in various applications.

Marketing information system based on unsupervised visual data to manage transportation industry using signal processing

AbstractAdvance signal processing techniques are becoming one of the essential requirements for secure and efficient communication in the future innovative world. These requirements are due to the tremendous advancement of various latest cutting‐edge technologies that are very useful for the present generation. Marketing information system visualization is essential for the services of every advanced technology established in this way to reach people. Citing this, signal processing is a significant issue in most new technological innovations and challenges in various applications. A marketing information system, or MIS, based on these processes provides a valuable marketing method that helps marketers make better decisions. In this mode of operation, the existing methods are discarded, and the new methods, such as visual images, sound waves, and seismic waves, are implemented as digital signal processes, and their benefits are used as inputs for the processing of humankind. Based on this perspective, collaborative Management Information Systems (MIS) is proposed. This process‐based bridge enables MIS professionals to benefit from their investments in personnel, equipment, and business processes. In particular, transportation challenges such as total order intensity ratio, rising fuel prices, unexpected delays in transportation, shortage of skilled workers, deplorable warehouse conditions, insufficient and over‐stressed delivery staff, etc., and how road transport is giving its full attention to these fluctuations. Research paper explains very clearly and adequately explains the impact of such explained traffic problems, such as the volume of traffic and passengers, road network, lack of rehabilitation of half of the roads, and lack of national highways. Performance analysis for MIS measures with various factors is taken, and how the process varies in them and the answers to them are clarified through this research. This research citation shows how the marketing performance of an MIS measures the best practices in this research. Through this, online marketing performance based on MIS measures can be increased through MIS analysis reports for MIS measures. Finally, the Performance of the proposed MIS‐Transport with the MIS‐hospital Industry is taken as an example and explained.

A Generalized Scalar Potential Integral Equation Formulation for the DC Analysis of Conductors

The electrostatic modeling of conductors is a fundamental challenge in various applications, including the prediction of parasitic effects in electrical interconnects, the design of biasing networks, and the modeling of biological, microelectromechanical, and sensing systems. The boundary element method (BEM) can be an effective simulation tool for these problems because it allows modeling three-dimensional objects with only a surface mesh. However, existing BEM formulations can be restrictive because they make assumptions specific to particular applications. For example, capacitance extraction formulations usually assume a constant electric scalar potential on the surface of each conductor and cannot be used to model a flowing current, nor to extract the resistance. When modeling steady currents, many existing techniques do not address mathematical challenges such as the null space associated with the operators representing the internal region of a conductor. We propose a more general BEM framework based on the electric scalar potential for modeling conductive objects in various scenarios in a unified manner. Restrictive application-specific assumptions are not made, and the aforementioned operator null space is handled in an intuitive and rigorous manner. Numerical examples drawn from diverse applications confirm the accuracy and generality of the proposed method.

Copy-Move Forgery Detection Using an Equilibrium Optimization Algorithm (CMFDEOA)

Image forgery detection is a new challenge. One type of image forgery is a copy-move forgery. In this method, part of the image is copied and placed at the most similar point. Given the existing algorithms and processing software, identifying forgery areas is difficult and has created challenges in various applications. The proposed method based on the Equilibrium Optimization Algorithm (EOA) helps image forgery detection by finding forgery areas. The proposed method includes feature detection, image segmentation, and detection of forgery areas using the EOA algorithm. In the first step, the image converts to a grayscale. Then, with the help of a discrete cosine transform (DCT) algorithm, it is taken to the signal domain. With the help of discrete wavelet transform (DWT), its appropriate properties are introduced. In the next step, the image is divided into blocks of equal size. Then the similarity search is performed with the help of an equilibrium optimization algorithm and a suitable proportion function. Copy-move forgery detection using the Equilibrium Optimization Algorithm (CMFDEOA) can find areas of forgery with an accuracy of about 86.21% for the IMD data set and about 83.98% for the MICC-F600 data set.

Modeling and LES of high-pressure liquid injection under evaporating and non-evaporating conditions by a real fluid model and surface density approach

Numerical modeling of high-pressure liquid fuel injection remains a challenge in various applications. Indeed, experimental observations have shown that injected liquid fuel jet undergoes a continuous change of state from classical two-phase atomization and spray droplets evaporation to a dense-fluid mixing phenomenon depending on the ambient pressure, temperature, and fuel properties. Accordingly, a predictive and efficient computational fluid dynamics (CFD) model that can represent the possible coexistence of subcritical and supercritical regimes during the fuel injection event is required. The widely used Lagrangian Discrete Droplet Method (DDM) requires parameter tuning of model constants and cannot model the dense near-nozzle region. Meanwhile, the high computational cost of Interface Capturing Methods (ICM) has prohibited their application to industrial cases. Thus, another alternative is an Eulerian Diffuse Interface Model (DIM), where the unresolved interface features are modeled instead of being tracked. Accordingly, the current work proposes a fully compressible multi-component two-phase real-fluid model (RFM) with a diffused interface and closed by a thermodynamic equilibrium tabulation method based on a real-fluid equation of state. The RFM model is complemented with a postulated surface density equation for fuel atomization modeling within the Large Eddy Simulation (LES) framework. The Engine Combustion Network (ECN) Spray A injector non-evaporating and nominal evaporating conditions are used as a reference for the proposed model validation. Simulations are performed using the proposed RFM model that has been implemented in the CONVERGE CFD solver. Under the non-evaporating condition, the RFM model can capture well the fuel mass distribution in the near-nozzle field, but also the interfacial surface area. Besides, the predicted drop size from simulations falls within the experimental data range. On the other hand, under the evaporating condition, spray liquid and vapor penetrations and fuel mixture fraction distribution are also accurately predicted. The vaporization effect on the surface area density is revealed to enhance surface generation in the dense spray region while reducing the surface density in the dilute spray region. The mean droplet size is also relatively reduced under the evaporating condition in the diluted spray region. Overall, the accuracy and computationally efficiency of the proposed RFM model coupled with the surface density equation for high-pressure fuel injection modeling are confirmed, allowing its use for high pressure industrial configurations in future studies.

De-erosion of X chromosome dosage compensation by the editing of XIST regulatory regions restores the differentiation potential in hPSCs

Human pluripotent stem cells (hPSCs) regularly and irreversibly show the erosion of X chromosome inactivation (XCI) by long non-coding RNA (lncRNA) XIST silencing, causing challenges in various applications of female hPSCs. Here, we report reliable methods to reactivate XIST with monoallelic expression in female hPSCs. Surprisingly, we find that the editing of XIST regulatory regions by Cas9-mediated non-homologous end joining is sufficient for the reactivation of XIST by endogenous systems. Proliferated hPSCs with XIST reactivation show XCI from an eroded X chromosome, suggesting that hPSCs with normal dosage compensation might lead to a growth advantage. Furthermore, the use of targeting vectors, including the XIST regulatory region sequences and selection cassette, enables XIST reactivation in hPSCs with high efficiency. XIST-reactivated hPSCs can show the restoration of differentiation potential. Thus, our findings demonstrate that XIST re-expression is a beneficial method to maximize the use of female hPSCs in various applications, such as proper disease modeling.

Quantum Water Strider Algorithm with Hybrid-Deep-Learning-Based Activity Recognition for Human–Computer Interaction

Human action and activity recognition are clues that alleviate human behavior analysis. Human action recognition (HAR) becomes a significant challenge in various applications involving human computer interaction (HCI) and intellectual video surveillance for enhancing security in distinct fields. Precise action recognition is highly challenging because of the variations in clutter, backgrounds, and viewpoint. The evaluation method depends on the proper extraction and learning of data. The achievement of deep learning (DL) models results in effectual performance in several image-related tasks. In this view, this paper presents a new quantum water strider algorithm with hybrid-deep-learning-based activity recognition (QWSA-HDLAR) model for HCI. The proposed QWSA-HDLAR technique mainly aims to recognize the different types of activities. To recognize activities, the QWSA-HDLAR model employs a deep-transfer-learning-based, neural-architectural-search-network (NASNet)-based feature extractor to generate feature vectors. In addition, the presented QWSA-HDLAR model exploits a QWSA-based hyperparameter tuning process to choose the hyperparameter values of the NASNet model optimally. Finally, the classification of human activities is carried out by the use of a hybrid convolutional neural network with a bidirectional recurrent neural network (HCNN-BiRNN) model. The experimental validation of the QWSA-HDLAR model is tested using two datasets, namely KTH and UCF Sports datasets. The experimental values reported the supremacy of the QWSA-HDLAR model over recent DL approaches.