Modeling Techniques Research Articles

Detection and classification of breast cancer in mammographic images with fine-tuned convolutional neural networks

ABSTRACT Breast cancer is cancer that forms in the cells of the breasts and is a severe health issue that affects many people around the world, especially since it is the most deadly cancer in women. By finding it early and using new treatments, patients can overcome this challenge and get back to a healthier life. This study proposed a procedure to fine-tune the Convolutional Neural Networks (CNN) model with data preprocessing and augmentation in classifying mammogram images called the Hybrid Mammogram Classification and Detection Pipeline (HMCaD). After using CNN for classification because it brings higher confidence in classifying tasks, the YOLOv8 has been applied for localization subtask to detect abnormal positions with predicted bounding boxes. The database is provided by the Mammographic Image Analysis Society (MIAS) and is protected by the United Kingdom. It comprises 330 samples, including 79 benign, 54 malignant, and 207 normal images. As a result, the classification in our model based on the custom EfficientNetB3 model and seam carving technique received a great validation accuracy, test accuracy, and F1 score throughout three scenarios at 96.73%, 97.59%, and 97.58%, respectively. Furthermore, the area under the Receiver Operating Characteristic (ROC) curve also has a surprise result of 0.96 (i.e. AUC = 0.96 ). Moreover, YOLOv8 for detecting abnormal positions in our study achieved 83.22% in Intersection over Union (IoU). This led to the research reaching good results in classifying and detecting breast cancer by considering several performance metrics.

Examining the AISAS Model and Tourist Citizenship Behaviour in context of Mining Heritage Tourism

Therefore, the objective of the research is to test the effectiveness of the Attention-Interest-Search-Action-Share model in mining heritage tourism but replacing the Action component with tourist citizenship behaviour. This will therefore yield new and key insights because there are few studies conducted in this area. The current study selected 220 tourists through a convenience sampling technique. The gathered data was treated with exploratory factor analysis and structural equation modelling techniques. Confirmatory results found on the acceptance of the first hypothesis, which is Attention Influences Interest, attention becomes very important in ensuring riveting tactics are put in place when promoting mining heritage tourism. The second hypothesis, Curiosity influences Search, is also supported and confirms that only in the condition of a deep level of curiosity, tourists search for information. The third hypothesis is stating that interest influences TCB. The fourth hypothesis postulates that interest influences Share. It supported the sixth hypothesis stating that Search influences TCB. The rejection was of the sixth hypothesis that stated Search influences Share. The seventh theory stated that TCB influences Share, thereby is accepted. These findings bear some significant implications for attaining the sustainable development goals. Precisely, it means that the promotion of mining heritage tourism advances SDG 11—Sustainable Cities and Communities—since this ensures cultural heritage is preserved and contributes to inclusive and sustainable urban development. Likewise, with increased engagement of tourists during citizenship behaviours, this particular act contributes to SDG 12 through the aspect of sustainable tourism and raising awareness. Similarly, the positive experiences that are increasingly wide follow up essentially give rise to SDG 8 through the promotion of tourism as one of the prime movers for improving the economy.

Hydromechanical behaviour of a slope reinforced by grass roots under rainfall conditions

Soil bioengineering using vegetation has been considered an environmentally friendly solution to improve slope stability. Although several studies have demonstrated the contribution of vegetation to slope stability, a gap in understanding the mechanisms of grass root–soil interactions under rainfall conditions remains. This study investigates the effects of the roots of vetiver grass (Chrysopogon zizanioides) on the hydromechanical behaviour of an unsaturated soil slope using the centrifuge modelling technique. The changes in pore water pressure and slope deformation were monitored during the test. The monitored data were subsequently back-analysed and interpreted using seepage–stability analyses. In addition, this study focused on evaluating the effect of roots on slope stability, considering safety and pore water pressure during rainfall. Results revealed that the vetiver roots remarkably affected the initial suction of the slope by increasing the soil's air-entry value. The increased suction and the additional cohesion provided by the roots enhanced slope stability under rainfall conditions.

Zone-based many-objective building decarbonization considering outdoor temperature and occupation uncertainty

Operational building decarbonization is challenging due to complex weather conditions and occupation uncertainty. This paper introduces a precise optimization framework integrating the building information modelling technique and intelligent algorithms to dynamically predict multi-scenario building carbon emissions and optimize the building emissions performance considering building zones and weather conditions. Firstly, the on-site data and building information modeling-supported building emissions simulation data are collected for model training. Secondly, using intelligent algorithms, zone-based hourly carbon emissions and multi-scenario carbon emissions prediction are conducted simultaneously. Thirdly, the optimal decarbonization strategies are conducted using intelligent algorithms under various weather conditions. This framework has been verified for decarbonization in a high-rise operational building. The results reveal that: (1) The carbon emissions prediction is highly consistent with the ground truth after considering the sub-zone correlations; the R2 for the west, south, and east zones are 0.900, 0.900, and 0.942, respectively; (2) The surrogate models can accurately predict carbon emissions and thermal comforts with all R2 are higher than 0.912. The optimization rate of the building reaches 59.2 % while the outdoor temperature is above 35 °C. (3) In the many-objective optimization model, considering occupation uncertainty makes the strategy close to the actual situation, reaching the decarbonization by 6815.23 kg compared to the empirical operation for the cooling period. This work provides a new path for operational building precise management and control-oriented optimization decarbonization.

UPAYA MENINGKATKAN HALAL ADOPTION PADA TENUN SONGKET ETNIK LOKAL PANDAI SIKEK

The rapid transition of the global halal fashion industry may require a series of innovations and adaptations in the MSMEs sector. Therefore, technology adoption and organizational openness to change are the main challenges for stakeholders. This study was conducted to examine and analyze the effects of technology, organization, and an increasingly competitive environment on halal adoption in the MSME weaving sector. By using a purposive sampling technique with certain criteria, as many as 30 MSMEs owners or members were obtained to contribute and respond to the research questionnaire, and then those responses were analyzed through the Structural equation model technique with Smart-PLS software's latest version. Results stated that halal adoption in the MSMEs weaving sector is not affected by technological and organizational aspects, it is due to a lack of openness to accept the changes, then most of the actors also thought that halal adoption didn’t provide value-added. Therefore, the motivation for human resource development and technology utilization was also low. Halal adoption is significantly affected by environmental aspects. External pressures such as market demand and government regulations will force weaving MSME actors to adapt to the changes for business sustainability and maintaining national fashion cultural heritage.

Estimation Stand Volume, Basal Area and Quadratic Mean Diameter Using Landsat 8 OLI and Sentinel‐2 Satellite Image With Different Machine Learning Techniques

ABSTRACTThe data required for sustainable forest planning is provided by traditional forest inventories, which are labor, time, and cost‐intensive. Providing this data quickly, reliably, and accurately is crucial for planners and researchers. The objective of this study was to predict stand basal area (BA), stand volume (V), and quadratic mean diameter (dq) by leveraging vegetation indices (VIs) and reflectance (R) derived from Landsat 8 OLI and Sentinel 2 satellite images, along with topographic (T) data obtained from ALOS‐PALSAR satellite imagery. Forest inventory data for a total of 250 sample plots were used for modeling in the study. Stand parameters were estimated using support vector machines (SVM), multiple linear regression (MLR), decision tree (DT), and random forest (RF) algorithms. In modeling V, BA, and dq, both individual and combinations of R, VIs, and T values obtained from satellite imagery were used as independent variables. Using the generated datasets, each of the stand parameters was modeled separately with MLR, SVM, RF, and DT algorithms, and the success of the models was compared to determine the modeling technique and dataset with the highest success for the relevant parameter. The results showed that for each stand parameter, the highest model success was achieved in the combined dataset, which was created by combining all datasets. However, in terms of modeling techniques, the highest success for each stand parameter was achieved with different modeling techniques. The highest success for V is obtained in the model using the SVM method (R2 = 0.78; RMSE = 0.28 m3/ha), the RF method yielded the highest model performance for BA (R2 = 0.70; RMSE = 2.53 m2/ha), and finally, the highest success for dq was obtained in the DT method (R2 = 0.74; RMSE = 0.02 cm). In general, the datasets obtained from Sentinel 2 images showed higher model success than the datasets obtained from Landsat 8 OLI images.

Integration of Geological Model and Numerical Simulation Technique to Characterize the Remaining Oil of Fractured Biogenic Limestone Reservoirs

AbstractFine geological modeling leads to accurate reservoirs numerical simulations. Fractured biogenic limestone has abundant storage spaces and flow paths to accumulate oil and gas. The complexity and diversity of fractured biogenic limestone also lead to challenges in accurately characterizing its pore volume and remaining oil. This investigation aimed to enhance the understanding of fractured biotite reservoir properties via geological modeling. Numerical simulations were used to characterize the remaining oil during the late stage of field development. Considering the differences in porosity and permeability between fractures and matrix, a facies-controlled stochastic modeling technique was used to establish a dual-porosity and dual-permeability (DPDP) model for numerical simulation. Core information, logging data, and multiple seismic attributes were combined to guide low-level sequence fault interpretation for tectonic refinement. Based on classified seismic inversion, sedimentary phases were reconstructed. A discrete fracture network (DFN) model was obtained based on fracture occurrences and density models. The optimized discrete adjoint (ODA) algorithm was utilized to calibrate model parameters. The findings revealed that dense tectonic fractures develop in thick biogenic limestone areas. Combined with advanced reservoir simulation technology, these findings suggest that areas of thicker biogenic limestone were consistent with areas of higher fracture matrix conductivity multipliers. The remaining oil distribution patterns were investigated, and to deploy new wells was guided. Therefore, it is essential to better understand the tectonic characteristics of fractured biogenic limestone reservoirs and their remaining oil distribution patterns by integrating multiple sources of information and mastering advanced reservoir simulation technology for oilfield development.

Evaluating Enablers and Outcomes of Clients' Behavioral Intention to Use Electronic Mobile Payment Services during Covid-19 Pandemic: An Empirical Study on Jordanian Insurance Companies

By applying the Unified Theory of Acceptance Use of Technology 2 (UTAUT2), this study aimed to evaluate the enablers and outcomes of National Wallet (NW) company clients' behavioral intention to use electronic mobile payment services in the Jordanian insurance industry during the pandemic of Covid-19. The current study employed quantitative and qualitative research approaches. The proposed hypotheses were tested quantitatively by developing and examining the UTAUT2 model along with the Perceived Risk (PR) variable which was added to the original model and tested based on the moderators of income, education, age, gender and experience that would influence clients' behavioral intention to use mobile payment services and in turn influence clients' use behavior. Based on a sample comprised of 426 NW clients who used mobile payment services in the Jordanian insurance companies during Covid-19 pandemic, the Hayes Process Macro by Andrew F. Hayes plugin was used as a statistical analysis in Statistical Package for Social Sciences (SPSS) software to evaluate path coefficients. Data was collected via an online survey questionnaire and then analyzed and hypotheses were examined by employing both Structural-equation Modeling (SEM) and Machine-learning (ML) techniques. Results showed that performance expectancy, hedonic motivation, price value, perceived risk and habit impacted behavioral intention, whereas effort expectancy, social influence and facilitating conditions did not. Moreover, behavioral intention had statistically significant path coefficients on use behavior and habit on use behavior. In addition, several qualitative interviews were conducted with NW clients to verify the research results. Quirkos 2.3.1 application was used for qualitative analysis of three interviews.

Rice Protein Peptides Alleviate Alcoholic Liver Disease via the PPARγ Signaling Pathway: Through Liver Metabolomics and Gut Microbiota Analysis.

Alcoholic liver disease (ALD) is the predominant type of liver disease worldwide, resulting in significant mortality and a high disease burden. ALD damages multiple organs, including the liver, gut, and brain, causing inflammation, oxidative stress, and fat deposition. In this study, we investigated the effects of rice protein peptides (RPP) on ALD in mice with a primary focus on the gut microbiota and liver metabolites. The results showed that administration of RPP significantly alleviated the symptoms of ALD in mice including adiposity, oxidative stress, and inflammation. The KEGG pathway shows that RPP downregulates the liver metabolite of capric acid and the metabolism of fatty acid biosynthesis compared with the MOD group. Mechanistically, RPP downregulated the PPARγ signaling pathway and suppressed the expression of fatty acid biosynthesis genes (FASN, ACC1, ACSL1, and ACSL3). Furthermore, two active peptides (YLPTKQ and PKLPR) with potential therapeutic functions for ALD were screened by Caco-2 cell modeling and molecular docking techniques. In addition, RPP treatment alleviates gut microbiota dysbiosis by reversing the F/B ratio, increasing the relative abundance of Alloprevotella and Alistipes, and upregulating the level of short-chain fatty acids. In conclusion, RPP alleviates ALD steatosis through the PPARγ signaling pathway by YLPTKQ and PKLPR and regulates gut microbiota.

뉴스 기사 빅데이터 분석을 통한 북한이탈주민의 사회적 이슈와 언어 문제 탐색: 2019-2024

Objectives The purpose of this study is to explore social issues and language problems that appear in news articles related to North Korean defectors and to suggest their implications. Methods 561 news articles related to North Korean defectors covered by major domestic newspapers and media companies from 2019 to June 2024 were collected. For analysis tools, language network analysis and topic modeling techniques were used to analyze major keywords and topics and visualize them. In addition, based on the analysis results, social issues and language problems of North Korean defectors were explored, and Korean language education implications were presented. Results he research results are as follows. First, the amount of news coverage has been increasing significantly over the past three years, and political articles have shown an overwhelmingly high proportion. Second, the main keywords are ‘government, support, human rights, protection, and settlement’. The main topics were protection of human rights of North Korean defectors, increasing number of North Korean defectors among elites and the 2030 generation, and complaints of difficulties due to mental and economic discrimination and prejudice in the process of settling in Korea. The content of the government's integrated support policy accounted for a high proportion. Third, it was found that North Korean defectors were struggling with the language difference between North and South Korea, and Korean language education focusing on pronunciation, accent, and vocabulary in each area was necessary for them. Conclusions The main topic of the news article was the integrated support for the protection of human rights and stable settlement of North Korean defectors. However, although North Korean defectors complain of ‘difficulty’ due to economic, psychological, emotional, and linguistic differences, these related topics are hardly covered in the media. Therefore, this paper suggested implications for Korean language education research for North Korean defectors' language adaptation.

Petroleum system analysis of Fujairah basin, eastern offshore of the United Arab Emirates

The Fujairah basin, located on the eastern margin of the United Arab Emirates, forms part of the hinterland basin of the Oman-UAE mountains. Despite its geological significance, the hydrocarbon potential of this basin remains unexplored. This study aims to address this knowledge gap by using 2D seismic reflection data, three exploration wells, geochemical data from one well, a 2D velocity section, and two pseudo-wells. The study began with the interpretation of the seismic profiles and then proceeded to create depth maps for the most significant units. We used Rock-Eval pyrolysis plots to identify the primary source rocks and to classify their kerogen types. The seismic interpretation formed a basis for the 1D and 2D basin modeling techniques that are used to determine the petroleum system of the basin. Our results identify the Pliocene, Miocene, and Eocene sequences as potential source rocks in the basin with TOC values less than 1 wt% and low expulsion efficiencies. The Pliocene and Miocene source rocks are mainly type-II kerogen, whereas most Eocene samples are characterized as type-III kerogen. The Pliocene and Miocene source rocks are immature in the basin. The Eocene is mature depending on the burial within the sub-basins. The Eocene started expelling hydrocarbons during the Burdigalian, which was linked to the collision of the Arabian and Central Iran plates along the Zagros suture zone. Structural and stratigraphic traps may have entrapped the generated hydrocarbons. The three drilled wells in the basin lack good reservoir rocks. However, low-velocity anomalies and bright spots indicate possible hydrocarbon accumulations in the basin.

Navigating Technological Risks: An Uncertainty Analysis of Powertrain Technology in Hybrid-Electric Commuter Aircraft

Abstract This study addresses the uncertainties in hybrid-electric powertrain technology for a 19-passenger commuter aircraft, focusing on two future Entry-Into-Service timeframes: 2030 and 2040. The methodology is split into a preliminary optimization of aircraft design based on nominal technology scenarios followed by Monte Carlo simulations to investigate the impact of diverse technology projections and distribution types. Advanced surrogate modeling techniques, leveraging deep neural networks (DNN) trained on a dataset from an aircraft design framework, are employed. Key outcomes from this work reveal a marked increase in computational efficiency, with a speed-up factor of approximately 500 times when utilizing surrogate models. The results indicate that the 2040 entry-into-service (EIS) scenario could achieve larger reductions in fuel and total energy consumption—20.4% and 15.8% respectively—relative to the 2030 scenario, but with higher uncertainty. Across all scenarios examined, the hybrid-electric model showcased superior performance compared to its conventional counterpart. The battery-specific energy density is proved to be a critical parameter of the aircraft’s performance across both timeframes. The findings emphasize the importance of continuous innovation in battery and motor technologies to target toward greater system-level efficiency and reduced environmental impact.

Augmenting a Concentrated Solar Power (CSP) Plant With a Solar PV Plant

The search for enhanced dispatchability at decreased prices has led to a surge in research on hybrid renewable energy systems. This paper explores the integration of Photovoltaic (PV) technology with Concentrating Solar Power (CSP) plants to enhance energy generation and economic feasibility, focusing on optimising the size of PV augmentation for existing CSP facilities. The study considers CSP plants with both Time-of-Day (ToD) and single tariffs, employing modelling techniques to assess the synergies between these two technologies. The cost of PV technology has significantly reduced, making it a cost-effective choice for electricity generation compared to CSP. CSP-PV augmentation promises to reduce online and offline auxiliary consumption, resulting in enhanced energy generation and a subsequent reduction in energy production costs. This study aims to explore the advantages of combining solar PV with a CSP system and determine the ideal PV size to maximise return, building upon previous studies to assess the technological and economic potential of integrating solar PV with CSP, focusing on South Africa. It utilises a rigorous analysis, combining the System Advisory Model and PVSyst modelling tool within an MS Excel framework. This economic assessment and sizing exercise aims to maximise profits while adhering to the limitations imposed by the power purchase agreement of a 100 MW CSP facility. The optimal size is 15 MWp for the ToD tariff and 16 MWp for the flat tariff. This highlights the potential for CSP-PV augmentation to improve energy dispatchability and financial viability, making it a compelling solution for existing CSP plants.

Tectonostratigraphic models of an extensional back-arc basin: inferences for the evolution of the Pannonian Basin system

The subsidence history and sedimentary architecture of extensional basins are controlled by the interplay between tectonics, mantle dynamics, and climatic variations. Observations from outcrop to regional seismic scales coupled with numerical modelling techniques, including basin-scale stratigraphic, crustal-scale tectonic and mantle-scale subduction models contribute to quantify basin evolution. Here, we review and discuss both tectonic and stratigraphic applications of such models and compare them with observations from the Pannonian Basin system of Central Europe. We show that diachronous localization of back-arc extension, crustal thinning, asthenospheric upwelling and subsequent thermal relaxation are superimposed on an overall slow plate convergence. These processes result in contrasting subsidence and uplift patterns and a variable heat flow evolution in different parts of the basin system. The crustal stress-field of the subbasins does not always reflect their contrasting vertical motions. Extensional deformation generally migrates from the basin margins towards the basin centre. Structural inversion is localized along hot and weak inherited zones from the Middle Miocene to Present. Tectonic subsidence focuses sedimentation along deep depocenters, sourced by exhumed footwalls and from the neighbouring orogens. The overall post-rift sediment progradation are influenced by inherited bathymetries from the preceding syn-rift stage and by enhanced differential vertical motions.

Creating Sustainable Flood Maps Using Machine Learning and Free Remote Sensing Data in Unmapped Areas

This study leverages a Random Forest model to predict flood hazard in Arizona, New Mexico, Colorado, and Utah, focusing on enhancing sustainability in flood management. Utilizing the National Flood Hazard Layer (NFHL), an intricate flood map of Arizona was generated, with the Random Forest Classification algorithm assessing flood hazard for each grid cell. Weather variable predictions from TerraClimate were integrated with NFHL classifications and Digital Elevation Model (DEM) analyses, providing a comprehensive understanding of flood dynamics. The research highlights the model’s capability to predict flood hazard in areas lacking NFHL classifications, thereby supporting sustainable flood management by elucidating weather’s influence on flood hazard. This approach aligns with sustainable development goals by aiding in resilient infrastructure design and informed urban planning, reducing the impact of floods on communities. Despite recognizing constraints such as input data precision and the model’s potential limitations in capturing complex variable interactions, the methodology offers a robust framework for flood hazard evaluation in other regions. Integrating diverse data sources, this study presents a valuable tool for decision-makers, supporting sustainable practices, and enhancing the resilience of vulnerable regions against flood hazards. This integrated approach underscores the potential of advanced modeling techniques in promoting sustainability in environmental hazard management.

Particularities on the Low-Velocity Impact Behavior of 3D-Printed Sandwich Panels with Re-Entrant and Honeycomb Core Topologies

This work describes, through experimental and numerical investigations, the mechanical behavior and energy absorption characteristics of 3D-printed sandwich panels with cellular cores subjected to low-velocity impact. Using fused deposition modeling techniques (FDM), three different sandwich panels, one with a regular hexagonal core and two with re-entrant cores at 0 and 90 degrees, were fabricated. The sandwich panels were subjected to low-velocity impact, at impact energies of 10 J and 15 J. A comprehensive investigation of the panels’ behavior through experimental testing and numerical simulation was conducted. The results indicate that the sandwich panel with a 90 degrees re-entrant core is stiffer and absorbs the largest amount of impact energy but, at the same time, suffers significant damage to the upper facesheet. The 0 degrees re-entrant core is compliant and provides both impact resistance and good energy absorption characteristics. Such a sandwich panel finds its application in the construction of personal protective equipment, where the aim is to minimize the forces transmitted during low-velocity impacts and maximize the total absorbed energy. Re-entrant core sandwich panels prove to be very good candidates for replacing the honeycomb core sandwich, depending on the desired engineering application.

Enhancing predictive accuracy of electoral outcomes: A comparative study of dimension reduction techniques in linear regression models

The effectiveness of Principal Component Analysis (PCA) and Factor Analysis (FA) in enhancing the predictive accuracy and interpretability of linear regression models for electoral outcomes is examined in this study, with a focus on the Croatian presidential election. Challenges such as multicollinearity and model complexity were addressed through the application of PCA and FA to socio-demographic and political variables, resulting in their transformation into a simpler, more manageable form. Multicollinearity was significantly reduced by PCA, and model stability was improved. Deeper insights into voter behavior were provided by FA through the identification of latent variables. Improvements were noted; however, issues with homoscedasticity were identified, which affected the predictive reliability of the models. The optimized linear regression model, specifically designed to address homoscedasticity (LR2), was found to demonstrate superior performance in terms of predictive accuracy and stability when compared to models that utilized PCA and FA alone. The importance of maintaining homoscedasticity in regression models is underscored by the findings, and the potential of dimension reduction techniques to improve electoral predictions is highlighted. The integration of these techniques in forecasting models is advocated for, with the aim of assisting political analysts and policymakers. It is suggested that future research could explore the combination of these methods with other advanced modeling approaches to further enhance predictive capabilities.

EEG-based emotional valence and emotion regulation classification: a data-centric and explainable approach

Emotion classification using electroencephalographic (EEG) data is a challenging task in the field of Artificial Intelligence. While many researchers have focused on finding the best model or feature extraction technique to achieve optimal results, few have attempted to select the best methodological steps for working with the dataset. In this study, we applied two different theoretical approaches based on the noise of the dataset: curriculum learning and confident learning. Curriculum learning involves presenting training examples to the model in a specific order, starting with easier examples and gradually increasing in difficulty. This approach has been shown to improve model performance. Confident learning is a method for identifying and correcting label errors in datasets. By identifying and correcting these errors, confident learning can improve the performance of machine learning models trained on noisy datasets. We then applied the Integrated Gradient technique in order to assess the explainability of each model. Our aim was to explore the impact of different models and methods on emotion classification performance using EEG data. We collected and used an EEG dataset in which participants rated the emotional valence of positive and negative pictures while performing an emotion regulation (ER) task, comparing a control condition (Look) with two ER strategies: cognitive reappraisal and expressive suppression. We performed a multilabel classification to identify emotional neutrality or polarization of emotional valence (both positive and negative) rated by participants and the emotion regulation strategy adopted during the task. We compared the performance of models trained on three datasets selected based on label noise and evaluated their suitability for this task. Our results suggest different patterns based on the architecture used for feature importance, highlighting both advantages and criticisms.

A Benchmarking Model for HRM Elements of Large Mining Industry: ISM-Based Approach

While human resource management (HRM) elements concerning the expansive mining industry have been acknowledged, they still need to be explored. This paper presents a novel and strategic endeavour to construct a benchmark model linking HRM elements specific to the large mining industry. Drawing from an extensive literature review, crucial HRM elements pertinent to the mineral industry are systematically identified and thoroughly examined. The study utilises the interpretive structural modelling (ISM) technique within the context of major Indian mining industries to unveil latent relationships among these HRM-related elements. Through six-phased interactions, a foundational model is established, illuminating these relationships. The findings are poised to positively impact the mining industry, contributing to enhanced system sustainability. Furthermore, this paper represents a pioneering effort as the first research to elucidate the relationship model of HRM elements within the mining industry. It encourages HRM researchers to delve further into the mining industry to address its challenges. This research serves as a foundational study and provides a platform for further investigations by HRM experts, researchers and field personnel, enabling a multifaceted exploration of HRM perspectives.

Artificial intelligence driven cyberattack detection system using integration of deep belief network with convolution neural network on industrial IoT

In Industry 4.0, information and communication technology (ICT) was employed in numerous significant infrastructures, like financial networks, smart factories, and power plants, to automate and certify industrial systems. In power control systems, ICT technologies such as IIoT have improved automated monitoring, but legacy methods, originally autonomous, now connect with external networks. This progress has presented safety vulnerabilities from legacy ICT systems. Hence, various cybersecurity approaches are developed and examined to deal with cyberattacks and vulnerabilities. Utilizing new cybersecurity models in power control systems poses risks due to their uncertified safety. Ensuring their stability and efficiency is significant for maintaining reliable power delivery and incorporating these technologies into power control systems. Therefore, this study designs a Next–Generation Cybersecurity Attack Detection using an ensemble deep learning model (NGCAD-EDLM) technique in the IIoT environment. The main cause of the NGCAD-EDLM technique is the automatic recognition of cyber-attacks. In the NGCAD-EDLM approach, the primary data normalization phase utilizing min-max normalization is performed. Next, the honey-badger algorithm (HBA) approach selects the feature subsets. Furthermore, an ensemble deep learning (DL) of two methods, namely convolutional neural networks (CNNs) and deep belief networks (DBNs) methods, are employed for classification. In addition, the DL techniques' hyperparameter selection is accomplished using the lotus effect optimization algorithm (LEOA) method. A complete set of simulation validation is performed to establish the experimental analysis of the NGCAD-EDLM method. The performance validation of the NGCAD-EDLM method exhibited a superior accuracy value of 99.21 % over other existing techniques.