Selected Data Sets Research Articles

Prediction of Resilient Modulus Value of Cohesive and Non-Cohesive Soils Using Artificial Neural Network

This paper investigates the application of Artificial Neural Networks (ANNs) for predicting the resilient modulus (Mr) of subgrade and subbase soils, which is a critical parameter in pavement design. Utilizing a dataset of 1683 Mr observations, the ANN model incorporates eight input variables, including soil gradation, plasticity, and stress conditions. The model was optimized using a quasi-Newton method, achieving high predictive accuracy, with a coefficient of determination (R2) of 0.9613 and low error rates for both selection and testing datasets. To further enhance model interpretability, SHAP (SHapley Additive exPlanations) analysis was conducted, revealing the significant influence of specific input parameters, such as saturation ratio, plasticity index and soil gradation, on Mr predictions. This study underscores the potential of ANNs as a practical tool for estimating resilient modulus, offering a reliable alternative to conventional laboratory testing methods. The findings suggest that integrating ANNs into pavement design processes can lead to more accurate predictions of pavement performance, ultimately supporting the development of more efficient and durable road structures.

An assessment of whether educated non-researcher audiences understand how to reuse research data

PurposeThe purpose of this study is to assess whether educated non-researcher audiences understand how to reuse research data stored in a data repository.Design/methodology/approachA total of 44 participants in two user studies were asked to study a data set accessed from re3data.org. The participants were non-researcher audiences of the disciplines of the selected data sets. They were asked to figure out whether they understood how to reuse a data set after reading all the metadata or contextual information about the data set.FindingsMost participants reported that they figured out how to reuse the data, although their self-reports can be an overestimated assessment. However, the participants understand how to reuse a data set either numerically or statistically significantly worse than what the data set is, how it was collected or created and its purpose. Data set type tends to play a role in understanding how to reuse data sets and the purpose of data sets. Participants reported that unless a data set is self-explanatory, instructions on data set reuse and the purpose of data set were necessary for understanding how to reuse data set. However, because data reuse requires domain knowledge and data processing skills, some non-researcher audiences who lack domain knowledge and data processing skills may not understand how to reuse the data set in any way.Research limitations/implicationsThis study’s findings enrich the theoretical framework of data sharing and reuse by expanding the necessary information to be included in data documentation to support non-researchers’ data reuse. The findings of the study complement previous literature.Practical implicationsThis study extended previous literature by suggesting detailed data reuse instructions be included in data documentation if data producers and data curators wish to support educated non-researchers’ data reuse. This study’s findings enable policymakers of research data management (RDM) to formulate guidelines for supporting non-researchers’ data reuse. If data curators need to work with data producers to prepare the instructions on data reuse for non-researcher audiences, they probably need computing and data processing skills. This has implications for Library and Information Science schools to educate data librarians.Originality/valueThe research question is original because non-researcher audiences in the context of RDM have not been studied before. This study extended previous literature by suggesting detailed data reuse instructions be included in data documentation if data curators and data producers and data curators wish to support educated non-researchers’ data reuse. This study’s findings enable policymakers of RDM to formulate guidelines for supporting non-researchers’ data reuse.

Improving Responsiveness: Our Journey from Manual Yearly Updates to Automated Linkage for Near Real-Time Understanding of Outcomes and Modelling Future Service Demand

ObjectiveDemand for real-time data during the COVID-19 pandemic revealed a need to increase efficiencies in manual linkage processes to respond to events in near real-time. In response, our jurisdictional linkage agency transitioned from yearly to daily, weekly and monthly linkage practices through increasing automation and improving process flows. ApproachOur linkage agency transitioned to a fully automated process utilising scalable cloud infrastructure. Source data is now provided directly to a common data platform. This data is split into linkage and content, cleansed and quality assured in Python and set to automatically run via Azure data pipelines. The data is then linked via a combination of deterministic and probabilistic criteria, with data quality checks automatically performed along the way. Researchers can analyse this data in a secure virtual machine that only they can access and retrieve data from. Results This infrastructure expedites the data linkage process allowing daily linkage results to select datasets, and enables advanced research such as a predictive micro-simulation model, which leverages the platform to predict and intervene on outcomes influenced by governmental policies. This model relies on timely administrative data to build targeted interventions for groups with poor future outcomes, tests these interventions, and monitors outcomes in near real-time. ConclusionOur linkage agency has transitioned from manual to automated linkage processes in response to increasing need for timely data. By embracing cloud infrastructure and leveraging automation, we have streamlined our operations, enabling responsive linkage depending on need and expediting the provision of de-identified, linked data to researchers.

PMSOMA: optical microscope algorithm based on piecewise linear chaotic mapping and sparse adaptive exploration

The optical microscope algorithm (OMA) is a metaheuristic algorithm that draws inspiration from the magnifying functionality of optical microscopes. This study introduces an enhanced variant of OMA, termed PMSOMA, designed to mitigate the original version's limitations, notably its slow convergence rates and vulnerability to local optima. PMSOMA integrates a piecewise linear chaotic map to refine population initialization and augment diversity, alongside a sparse adaptive exploration mechanism to bolster search efficacy. The performance of PMSOMA was rigorously tested using a suite of 50 benchmark functions, the CEC2017 test suite, feature selection datasets, and three classical engineering challenges. The empirical findings confirm that PMSOMA surpasses both the original OMA and competing algorithms by delivering superior solutions, accelerating convergence, and demonstrating enhanced robustness in convergence.

Multi-algorithm based evolutionary strategy with Adaptive Mutation Mechanism for Constraint Engineering Design Problems

This paper proposes a new multi-algorithm based evolution strategy with the addition of adaptive mutation operators for global optimization. The new algorithm namely Kepler meerkat naked (KMN) algorithm is based on Kepler’s optimization algorithm (KOA), meerkat optimization algorithm (MOA), and naked mole-rat algorithm (NMRA), as the core algorithms and, grey wolf optimizer (GWO) and cuckoo search (CS) inspired equations for enhanced exploration and exploitation. The proposed algorithm uses six new mutation operators for parametric enhancements, and follows an iterative division mechanism for a balanced operation. A comparative analysis is done with respect to classical benchmarks, CEC 2014, CEC 2017, CEC 2019 and CEC 2022 benchmark datasets for performance evaluation. Six engineering design problems are also used to test the performance of the proposed KMN algorithm for constraint optimization. Apart from that, a binary version of KMN namely bKMN is also proposed, and ten feature selection datasets are used for performance evaluation. Performance testing of the KMN and bKMN algorithm is done with success history-based DE (SHADE), LSHADE-SPACMA, self-adaptive DE (SaDE), fast opposition-based learning golden jackal optimization (FROBL-GJO), LSHADE-EpSin, jSO, EBOwithCMAR, among others. Experimental and statistical results are performed using Wilcoxon’s and Friedman’s tests, and it has been found that the proposed algorithms are highly competitive in contrast to other algorithms under study.

Research on the Development Height Prediction Model of Water-Conduction Fracture Zones under Conditions of Extremely Thin Coal Seam Mining

Addressing the difficult problem of predicting the height of water-conducting fracture zones in shallow and thin coal seams, a prediction model of water-conduction fracture zones based on a backpropagation (BP) neural network was developed by integrating theoretical analysis, field measurements, and algorithmic advancements. Firstly, through overburden migration analysis and correlation tests, the height index system of the water-conducting fracture zone was determined. This system includes mining height, buried depth, dip angle, working face width, and overburden rock lithology, with five groups of characteristic parameters. Then, 35 pairs of minefield-measured data were collected to establish the measured height data set of the water-conducting fracture zone. Secondly, a BP neural network prediction model and a traditional support vector regression (SVR) prediction model were constructed based on a Pytorch framework, and the models were trained and tested by selecting data sets. Thirdly, the optimal prediction model was determined by comparing the model with the empirical model and multiple regression model of mining regulations for coal pillar maintenance and pressure in buildings, water bodies, railways, and main shafts. Finally, a typical mine was selected for application to verify the suitability of the optimal model. The results show that: (1) the predicted value of the neural network model is consistent with the change trend of the measured value, which accords with the theoretical law; (2) compared with traditional forecasting methods, the error of the BP neural network prediction model is stable and the prediction effect is the best; (3) dropout can effectively mitigate mitigation training overfitting, achieve regularization, and improve prediction accuracy; (4) the field application further verified that the BP neural network model is the best for predicting the height of water-conducting fracture zones of extremely thin coal seams, and the research results can provide technical guidance for similar fragile coal seams.

Hybrid deep learning models for the screening of Diabetic Macular Edema in optical coherence tomography volumes

Several studies published so far used highly selective image datasets from unclear sources to train computer vision models and that may lead to overestimated results, while those studies conducted in real-life remain scarce. To avoid image selection bias, we stacked convolutional and recurrent neural networks (CNN-RNN) to analyze complete optical coherence tomography (OCT) cubes in a row and predict diabetic macular edema (DME), in a real-world diabetic retinopathy screening program. A retrospective cohort study was carried out. Throughout 4-years, 5314 OCT cubes from 4408 subjects who attended to the diabetic retinopathy (DR) screening program were included. We arranged twenty-two (22) pre-trained CNNs in parallel with a bidirectional RNN layer stacked at the bottom, allowing the model to make a prediction for the whole OCT cube. The staff of retina experts built a ground truth of DME later used to train a set of these CNN-RNN models with different configurations. For each trained CNN-RNN model, we performed threshold tuning to find the optimal cut-off point for binary classification of DME. Finally, the best models were selected according to sensitivity, specificity, and area under the receiver operating characteristics curve (AUROC) with their 95% confidence intervals (95%CI). An ensemble of the best models was also explored. 5188 cubes were non-DME and 126 were DME. Three models achieved an AUROC of 0.94. Among these, sensitivity, and specificity (95%CI) ranged from 84.1–90.5 and 89.7–93.3, respectively, at threshold 1, from 89.7–92.1 and 80–83.1 at threshold 2, and from 80.2–81 and 93.8–97, at threshold 3. The ensemble model improved these results, and lower specificity was observed among subjects with sight-threatening DR. Analysis by age, gender, or grade of DME did not vary the performance of the models. CNN-RNN models showed high diagnostic accuracy for detecting DME in a real-world setting. This engine allowed us to detect extra-foveal DMEs commonly overlooked in other studies, and showed potential for application as the first filter of non-referable patients in an outpatient center within a population-based DR screening program, otherwise ended up in specialized care.

Mitigating implicit and explicit bias in structured data without sacrificing accuracy in pattern classification

AbstractUsing biased data to train Artificial Intelligence (AI) algorithms will lead to biased decisions, discriminating against certain groups or individuals. Bias can be explicit (one or several protected features directly influence the decisions) or implicit (one or several protected features indirectly influence the decisions). Unsurprisingly, biased patterns are difficult to detect and mitigate. This paper investigates the extent to which explicit and implicit against one or more protected features in structured classification data sets can be mitigated simultaneously while retaining the data’s discriminatory power. The main contribution of this paper concerns an optimization-based bias mitigation method that reweights the training instances. The algorithm operates with numerical and nominal data and can mitigate implicit and explicit bias against several protected features simultaneously. The trade-off between bias mitigation and accuracy loss can be controlled using parameters in the objective function. The numerical simulations using real-world data sets show a reduction of up to 77% of implicit bias and a complete removal of explicit bias against protected features at no cost of accuracy of a wrapper classifier trained on the data. Overall, the proposed method outperforms the state-of-the-art bias mitigation methods for the selected data sets.

Challenges in applying water budget framework for estimating groundwater storage changes from GRACE observations

The application of a water budget framework to isolate Gravity Recovery and Climate Experiment (GRACE) groundwater storage anomalies (GRACE-GWA) from GRACE terrestrial water storage anomalies (GRACE-TWSA) is hindered by the lack of direct observations of water budget components. In GRACE groundwater studies, water budget components are frequently applied to isolate changes in a storage component from various auxiliary methods (e.g., land surface or hydrology models, reanalysis, or remote sensing) and are used as a supplement to, or a substitute for, in-situ measurements when direct observations are sparse or unavailable. The contribution of select auxiliary datasets to isolate GRACE-GWA from GRACE-TWSA is an enduring quandary, attributed to the various assumptions applied to resemble hydrologic processes in model formulations. This study systematically allocates water budget components from assorted auxiliary sources to demonstrate bias and distortion of GRACE-GWA resulting simply from water storage component data selection. Whereas previous GRACE-GWA studies used combinations of water budget component datasets with uncertainty derived from the variance of the combined water budget components, this study applies single estimates for each component to measure bias and variability. An initial comparative analysis focused on three basins with suitable in-situ groundwater observations and complex hydrology stores (e.g., large lakes and seasonal snow cover), with correlation coefficients ranging from 0.32 to 0.89. Our systematic analysis was extended to 12 additional basins that capture a range of hydrologic characteristics to highlight the inconsistency in GRACE-GWA estimates. The variability evident in GRACE-GWA estimates highlights that the selection of water budget components carries the risk of misleading outcomes when disaggregating GRACE-TWSA into GRACE-GWA. Our water budget intercomparison provides an important assessment of the limitation in extraction of GRACE-GWA, highlighting the usefulness of comprehensive appraisal of water budget components for GRACE groundwater studies.

A survey on planet leaf disease identification and classification by various machine-learning technique

An overview of methods for identifying plants diseases is given in this article. Each sample is categorized by being divided into various groups. The approach of classification involves identifying healthy and diseased leaves based on morphological traits including texture, color, shape, and pattern, among others. Sorting and categorizing plants can be challenging, especially when doing so across a large area, due to the closeness of their visual qualities. There are several methods based on computer vision and image processing. Selecting the right categorization method can be difficult because the outcomes rely on the data you supply. There are several applications for the categorization of plant leaf diseases in fields like agriculture and biological research. This article gives a summary of several approaches currently in use for identifying and categorizing leaf diseases, as well as their benefits and drawbacks. These approaches include preprocessing methods, feature extraction and selection methods, datasets employed, classifiers, and performance metrics

Q-learning guided mutational Harris hawk optimizer for high-dimensional gene data feature selection

With the widespread application of high-throughput sequencing technology in recent years, the scale of high-dimensional gene sequence datasets has rapidly expanded. However, due to the high-dimensional nature of gene sequence data, researchers face the challenge of processing such complex data. One common preprocessing technique that can improve performance is feature selection, which selects the most relevant features from the original dataset, reducing its dimensionality. However, feature selection is often an NP-hard problem, and medical feature selection is mainly affected by the multiple attributes of features, which affect classification accuracy. In order to improve the generality of the algorithm, we propose RLHHO, which solves the feature selection problem of various medical gene datasets by combining Q-learning-guided mutation strategies. We also created binary RLHHO (bRLHHO) through conversion functions and evaluated its performance on 12 high-dimensional datasets. The experimental results show that bRLHHO is superior to the original HHO in improving classification accuracy and reducing the number of selected features. When processing high-dimensional medical gene datasets with over 1000 dimensions, bRLHHO can achieve good accuracy with fewer features. In summary, compared with other algorithms, including the original Harris Hawks Optimization (HHO), our proposed improved version of HHO, RLHHO, can handle various feature selection datasets and exhibits superior performance.

Non-animal models for blood–brain barrier permeability evaluation of drug-like compounds

Diseases related to the central nervous system (CNS) are major health concerns and have serious social and economic impacts. Developing new drugs for CNS-related disorders presents a major challenge as it actively involves delivering drugs into the CNS. Therefore, it is imperative to develop in silico methodologies to reliably identify potential lead compounds that can penetrate the blood–brain barrier (BBB) and help to thoroughly understand the role of different physicochemical properties fundamental to the BBB permeation of molecules. In this study, we have analysed the chemical space of the CNS drugs and compared it to the non-CNS-approved drugs. Additionally, we have collected a feature selection dataset from Muehlbacher et al. (J Comput Aided Mol Des 25(12):1095–1106, 2011. 10.1007/s10822-011-9478-1) and an in-house dataset. This information was utilised to design a molecular fingerprint that was used to train machine learning (ML) models. The best-performing models reported in this study achieved accuracies of 0.997 and 0.98, sensitivities of 1.0 and 0.992, specificities of 0.971 and 0.962, MCCs of 0.984 and 0.958, and ROC-AUCs of 0.997 and 0.999 on an imbalanced and a balanced dataset, respectively. They demonstrated overall good accuracies and sensitivities in the blind validation dataset. The reported models can be applied for fast and early screening drug-like molecules with BBB potential. Furthermore, the bbbPythoN package can be used by the research community to both produce the BBB-specific molecular fingerprints and employ the models mentioned earlier for BBB-permeability prediction.

BGOA-TVG: Binary Grasshopper Optimization Algorithm with Time-Varying Gaussian Transfer Functions for Feature Selection.

Feature selection aims to select crucial features to improve classification accuracy in machine learning and data mining. In this paper, a new binary grasshopper optimization algorithm using time-varying Gaussian transfer functions (BGOA-TVG) is proposed for feature selection. Compared with the traditional S-shaped and V-shaped transfer functions, the proposed Gaussian time-varying transfer functions have the characteristics of a fast convergence speed and a strong global search capability to convert a continuous search space to a binary one. The BGOA-TVG is tested and compared to S-shaped and V-shaped binary grasshopper optimization algorithms and five state-of-the-art swarm intelligence algorithms for feature selection. The experimental results show that the BGOA-TVG has better performance in UCI, DEAP, and EPILEPSY datasets for feature selection.

Improving Sleep Using Mentored Behavioral and Environmental Restructuring (SLUMBER)

ObjectivesTo evaluate the impact of a mentoring program to encourage staff-delivered sleep-promoting strategies on sleep, function, depression, and anxiety among skilled nursing facility (SNF) residents. DesignModified stepped-wedge unit-level intervention. Setting and ParticipantsSeventy-two residents (mean age 75 ± 15 years; 61.5% female, 41% non-Hispanic white, 35% Black, 20% Hispanic, 3% Asian) of 2 New York City urban SNFs. MethodsExpert mentors provided SNF staff webinars, in-person workshops, and weekly sleep pearls via text messaging. Resident data were collected at baseline, post-intervention (V1), and 3-month follow-up (V2), including wrist actigraphy, resident behavioral observations, Pittsburgh Sleep Quality Index (PSQI), Patient Health Questionnaire-9 (PHQ-9) depression scale, Brief Anxiety and Depression Scale (BADS), Brief Cognitive Assessment Tool (BCAT), and select Minimum Data Set 3.0 (MDS 3.0) measures. Linear mixed models were fit for continuous outcomes and mixed-effects logistic models for binary outcomes. Outcomes were modeled as a function of time. Planned contrasts compared baseline to V1 and V2. ResultsThere was significant improvement in PSQI scores from baseline to V1 (P = .009), and from baseline to V2 (P = .008). Other significant changes between baseline and V1 included decreased depression (PHQ-9) (P = .028), increased daytime observed out of bed (P ≤ .001), and increased daytime observed being awake (P < .001). At V2 (vs baseline) being observed out of bed decreased (P < .001). Daytime sleeping by actigraphy increased from baseline to V1 (P = .004), but not V2. MDS 3.0 activities of daily living and pain showed improvements by the second quarter following implementation of SLUMBER (P's ≤ .034). There were no significant changes in BADS or BCAT between baseline and V1 or V2. Conclusions and ImplicationsSNF residents had improvements in sleep quality and depression with intervention, but improvements were not sustained at 3-month follow-up. The COVID-19 pandemic led to premature study termination, so full impacts remain unknown.

Human Selective Matting

Existing human matting methods are incapable of accurately estimating the alpha mattes of arbitrarily selected humans from a group photo. An alternative solution is to apply them to the corresponding cropped image patches. However, this option obtains an inaccurate alpha estimation due to the interference of the body parts of the neighboring humans. In addition, these methods are only trained on finely annotated synthetic data, which causes poor performance in real-world scenarios due to the domain shift. To address these problems, we propose human selective matting (HSMatt), which performs matting for arbitrarily selected humans from a group photo given only a simple bounding box as guidance. Specifically, we design a global–local context network to extract both local and global semantic context features. A human-aware trimap network is then proposed to generate human-aware trimaps for the selected humans, which adopts stacked bidirectional inference modules with intermediate supervision to progressively refine the estimated trimap. Finally, a partially supervised matting network is introduced to estimate the alpha matte, which uses a sample-varying loss to train the network on both the finely annotated synthetic data and coarsely annotated real-world data, resulting in high accuracy and good generalization. To evaluate the proposed HSMatt, we construct the first human selective matting dataset, named HSM-200K, which contains over 200,000 human images with instance-level alpha matte annotations. Experimental results demonstrate that the proposed HSMatt outperforms state-of-the-art methods.

System for Analysis of Wind Collocations (SAWC): A Novel Archive and Collocation Software Application for the Intercomparison of Winds from Multiple Observing Platforms

Accurate atmospheric 3D wind observations are one of the top priorities for the global scientific community. To address this requirement, and to support researchers’ needs to acquire and analyze wind data from multiple sources, the System for Analysis of Wind Collocations (SAWC) was jointly developed by NOAA/NESDIS/STAR, UMD/ESSIC/CISESS, and UW-Madison/CIMSS. SAWC encompasses the following: a multi-year archive of global 3D winds observed by Aeolus, sondes, aircraft, stratospheric superpressure balloons, and satellite-derived atmospheric motion vectors, archived and uniformly formatted in netCDF for public consumption; identified pairings between select datasets collocated in space and time; and a downloadable software application developed for users to interactively collocate and statistically compare wind observations based on their research needs. The utility of SAWC is demonstrated by conducting a one-year (September 2019–August 2020) evaluation of Aeolus level-2B (L2B) winds (Baseline 11 L2B processor version). Observations from four archived conventional wind datasets are collocated with Aeolus. The recommended quality controls are applied. Wind comparisons are assessed using the SAWC collocation application. Comparison statistics are stratified by season, geographic region, and Aeolus observing mode. The results highlight the value of SAWC’s capabilities, from product validation through intercomparison studies to the evaluation of data usage in applications and advances in the global Earth observing architecture.

Music genre selection based on computer data analysis for user preference using fuzzy classification by deep learning model

The rapid advancement of communication and information technology has led to the expansion and blossoming of digital music. Recently, music feature extraction and classification have emerged as a research hotspot due to the difficulty of quickly and accurately retrieving the music that consumers are looking for from a large volume of music repositories. Traditional approaches to music classification rely heavily on a wide variety of synthetically produced aural features. In this research, we propose a novel approach to selecting the musical genre from user playlists by using a classification and feature selection machine learning model. To filter, normalise, and eliminate missing variables, we collect information on the playlist’s music genre and user history. The characteristics of this data are then selected using a convolutional belief transfer Gaussian model (CBTG) and a fuzzy recurrent adversarial encoder neural network (FRAENN). The experimental examination of a number of music genre selection datasets includes measures of training accuracy, mean average precision, F-1 score, root mean squared error (RMSE), and area under the curve (AUC). Results show that this model can both create a respectable classification result and extract valuable feature representation of songs using a wide variety of criteria.

Some new invariant sum tests and MAD tests for the assessment of Benford’s law

AbstractThe Benford law is used world-wide for detecting non-conformance or data fraud of numerical data. It says that the significand of a data set from the universe is not uniformly, but logarithmically distributed. Especially, the first non-zero digit is One with an approximate probability of 0.3. There are several tests available for testing Benford, the best known are Pearson’s $$\chi ^2$$ χ 2 -test, the Kolmogorov–Smirnov test and a modified version of the MAD-test. In the present paper we propose some tests, three of the four invariant sum tests are new and they are motivated by the sum invariance property of the Benford law. Two distance measures are investigated, Euclidean and Mahalanobis distance of the standardized sums to the orign. We use the significands corresponding to the first significant digit as well as the second significant digit, respectively. Moreover, we suggest inproved versions of the MAD-test and obtain critical values that are independent of the sample sizes. For illustration the tests are applied to specifically selected data sets where prior knowledge is available about being or not being Benford. Furthermore we discuss the role of truncation of distributions.

Prediction of linear B-cell epitopes based on protein sequence features and BERT embeddings

Linear B-cell epitopes (BCEs) play a key role in the development of peptide vaccines and immunodiagnostic reagents. Therefore, the accurate identification of linear BCEs is of great importance in the prevention of infectious diseases and the diagnosis of related diseases. The experimental methods used to identify BCEs are both expensive and time-consuming and they do not meet the demand for identification of large-scale protein sequence data. As a result, there is a need to develop an efficient and accurate computational method to rapidly identify linear BCE sequences. In this work, we developed the new linear BCE prediction method LBCE-BERT. This method is based on peptide chain sequence information and natural language model BERT embedding information, using an XGBoost classifier. The models were trained on three benchmark datasets. The model was training on three benchmark datasets for hyperparameter selection and was subsequently evaluated on several test datasets. The result indicate that our proposed method outperforms others in terms of AUROC and accuracy. The LBCE-BERT model is publicly available at: https://github.com/Lfang111/LBCE-BERT.

Development of IIOT-Based Pd-Maas Using RNN-LSTM Model with Jelly Fish Optimization in the Indian Ship Building Industry

Building and repair of ships are considered the Evergreen industry nationally as well as globally. The ships are generally gone in by the periodic scheduled repairs by the Indian shipbuilding industries. Sometimes industries lack productivity and lack of modernization some modern methods should be followed. The study focuses on the optimization of predictive maintenance as a service on the industrial Internet of Things by machine learning algorithms. The main contribution of the study is the use of optimization techniques for feature selection and RNN-LSTM for improved accuracy. The selected data set is pre-processed and feature selection for the optimization for the improvement in accuracy, and automation decision making the framework of the convolution neural network along with the ensemble boosted tree classifier developed is optimized using the jellyfish optimization and Recurrent Neural Network and Long Short-Term Memory (RNN-LSTM) model for the recognition of patterns and numerical vectors in the real-world data after processing of output then it is sent back as the input for the recurrent network to make the decision in the shipbuilding process. By evaluating the performance results and confusion matrix through the training and testing output all the metrics for training and testing are classified in the confusion matrix. Our proposed predictive maintenance model with high accuracy for the detection of failures in earlier stages and maintenance of Indian ships can help in the avoidance of accidents in voyages and the loss of goods and money during transportation. The validation of the proposed predictive maintenance model optimization with different types of deep learning algorithms shows that our proposed methodology gives an improved accuracy of 98.9336% which is higher than any other models. The proposed Pd-MaaS helps in early detection of failures in the ships which is the greatest advantage in the Indian shipbuilding industry.