Browse Items (16488 total)
Sort by:
-
An Novel Cutting Edge ANN Machine Learning Algorithm for Sepsis Early Prediction and Diagnosis
Early detection and diagnosis of sepsis can significantly improve patient outcomes, but current diagnostic methods are limited. The problem addressed in this paper is the early detection and diagnosis of sepsis using machine learning algorithms. Sepsis is a life-threatening condition that can rapidly progress and cause organ failure, leading to increased mortality rates. Early detection and treatment of sepsis are critical for improving patient outcomes and reducing healthcare costs. However, sepsis can be challenging to diagnose, and existing methods have limitations in terms of accuracy and timeliness This research proposes a new cutting-edge Optimized Artificial Neural Network machine learning algorithm for sepsis early prediction and diagnosis. The proposed algorithm combines different data sources, including patient vital signs, laboratory results, and clinical notes, to predict the likelihood of sepsis development. The algorithm was evaluated on a large dataset of patient records and achieved promising results in terms of accuracy, Precision and Recall. The proposed algorithm can potentially serve as a valuable tool for clinicians in the early detection and diagnosis of sepsis, leading to better patient outcomes. 2023 American Institute of Physics Inc.. All rights reserved. -
AI-enabled risk identification and traffic prediction in vehicular Ad hoc Networks
The proposed research presents a two-fold approach for advancing Vehicular Ad-Hoc Networks (VANETs). Firstly, it introduces a Residual Convolutional Neural Network (RCNN) architecture to extract real-time traffic data features, enabling accurate traffic flow prediction and hazard identification. The RCNN model, trained and tested on real- world data, outperforms existing models in both accuracy and efficiency, promising improved road safety and traffic management within VANETs. Secondly, the study introduces a Genetic Algorithm-enhanced Convolutional Neural Network (GACNN) routing algorithm, challenging traditional VANET routing methods with metaheuristic techniques. Experiments in various VANET network scenarios confirm GACNN's superior performance over existing routing protocols, marking a significant step toward more efficient and adaptive VANET traffic management. 2024 Author(s). -
Mitigating post-harvest losses through IoT-based machine learning algorithms in smart farming
This research paper explores the transformative potential of Internet of Things (IoT) technology in mitigating the longstanding issue of post-harvest losses within the agriculture sector. These losses, which encompass both quantitative and qualitative deterioration of food commodities from harvest to consumption, have posed persistent challenges, resulting in economic losses and food wastage. By delving into the current landscape of post-harvest losses and the application of IoT technology, the paper offers valuable insights into how IoT can be harnessed to reduce these losses effectively. It not only highlights the benefits and existing IoT solutions but also addresses the inherent challenges, providing recommendations for their resolution. Moreover, the research introduces a machine learning-based model, specifically Random Forest ML, to identify and prevent losses in tandem with IoT devices, empowering farmers with timely alert messages for informed decision-making, thus fostering a more sustainable and efficient agricultural ecosystem. 2024 Author(s). -
Improving EEG based brain computer interface emotion detection with EKO ALSTM model
Decoding signals from the CNS brain activity is done by a computer-based communication device called a BCI. In contrast, the system is considered compelling communication equipment enabling command, communication, and action without using neuromuscular or muscle channels. Various techniques for automatic emotion identification based on body language, speech, or facial expressions are nowadays in use. However, the monitoring of exterior emotions, which are easily manipulated, limits the applicability of these procedures. EEG-based emotion detection research might yield significant benefits for enhancing BCI application performance and user experience. To overcome these issues, this study proposed a novel EKO-ALSTM for emotion detection in EEG-based braincomputer interfaces. The proposed study comprises EEG-based signals that record the electrical activity of the brain connected to various emotional states, which are gathered as real-time acquired EEG signals for emotion detection. The data was pre-processed using a bandpass filter to remove unwanted frequency noise for the obtained data. Then, feature extraction is performed using DWT from pre-processed data. Specifically, the proposed approach is implemented using Python software. The proposed system and existing algorithms are compared using a variety of evaluation criteria, including specificity, F1 score, accuracy, recall or sensitivity, and positive predictive values or precision. The results demonstrated that the proposed method achieved better performance in EEG-based BCI emotion detection with an accuracy of 97.93%, a positive predictive value of 96.24%, a sensitivity of 97.81%, and a specificity of 97.75%. This study emphasizes that innovative approaches have significantly increased the accuracy of emotion identification when applied to EEG-based emotion recognition systems. Additionally, the findings suggest that integrating advanced machine learning techniques can further enhance the effectiveness and reliability of these systems in real-world applications, paving the way for more responsive and intuitive BCI technologies. The Author(s) 2025. -
Enhancing Cybethreat Intelligence Feeds Using Generative Adversarial Networks
Cyberthreat Intelligence (CTI) feeds serve as crucial resources for organizations seeking to fortify their defenses against emerging cyberthreats. However, these feeds often suffer from deficiencies such as incomplete data, false positives, and a lack of contextual information. This chapter proposes an innovative approach to address these challenges by leveraging Generative Adversarial Networks (GANs) to enhance CTI feeds. We introduce ThreatGAN, a novel GAN architecture specifically designed for cyberthreat modeling. Trained on accurate CTI data, ThreatGAN learns to generate synthetic yet realistic threat indicators, including malicious uniform resource locators (URLs), Internet Protocol (IP) addresses, and attack patterns. We demonstrate the efficacy of ThreatGAN in filling gaps in existing feeds, reducing false positives, and providing essential contextual information. The quantitative and qualitative evaluation shows that ThreatGAN significantly improves CTI quality. This technique can strengthen organizations cyber defenses by enabling them to work with higher quality, more complete Threat Intelligence. 2026 selection and editorial matter, E. Chandra Blessie, Pethuru Raj, and B. Sundaravadivazhagan; individual chapters, the contributors. -
-
Experimental Investigation of Salt Hydrate Phase-Change Material (Shape-Stabilized) Applied to a Solar Collector
A complex element of water heater by solar power involves the requirements of storage tank, which not only occupies considerable space but also adds com-plexity to the plumbing and installation procedures; this research marks the initial endeavor to practically utilize shape-stabilized (SS) phase-change material (PCM) within a tank-less, evacuated tube with direct absorption (ET-Direct Absorption) solar collector. The primary objective was to tackle challenge of storage of the solar power. A PCM (salt hydrate) was proposed, with different component concentrations explored to determine the most effective mixture. Once the optimal compound was identified, it underwent rigorous testing over numerous cycles to ensure its sustainable its storing capabilities. Additionally, the planetary system was charged in dormancy mode (without flow of water) and subsequently discharged at the rate of flows of 15, 25, and 35 liters per hour (LPH). Results indicated a note-worthy improvement in efficiency of the heat system in the stasis mode, which increases from 62 to 80% with the utilization of this heat storing cum collecting unit. Moreover, it was observed that transitioning from a rate of flow of 1525 LPH had minimal impact on the collec-tors heat gain, but using a rate of flow of 35 LPH sig-nificantly reduced efficiency of discharge. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Future perspectives on new innovative technologies comparison against hybrid renewable energy systems
The increase in the dispatchable amount of renewable energy and rural access to the point is proposed. The fuel is used to generate power and electrical energy for the machine. This causes the electricity to manage the single connection point to analyze the hybrid generations. Improving this hybrid generator of renewable power resources can be enabled for the analysis. Photovoltaic power sources have been introduced for converting the power loads and the dumps. The vehicle energy power management technique and the renewable energy system have been used for the analysis. This study shows how vehicle and renewable energy management can help develop geothermal against hydrothermal vents. Hydropower and vehicles can enable bioethanol for vehicle biodiesel. This study allows for the analysis of hydrothermal and biodiesel. In this study, the power of the energy enables the hybrid system, and the combination of the power generator to access the vehicle is proposed. 2023 -
Amorphous Ru-Pi nanoclusters decorated on PEDOT modified carbon fibre paper as a highly efficient electrocatalyst for oxygen evolution reaction
Amorphous Ru-Pi nanoclusters deposited on PEDOT modified carbon fibre paper electrode have been investigated as a potential oxygen evolution electrocatalyst. CFP/PEDOT/Ru-Pi electrode was prepared by electrodeposition of Ru-Pi nanoclusters on PEDOT decorated CFP using cyclic voltammetry (CV). Field emission scanning electron microscopy with energy-dispersive X-ray spectroscopy (FESEM-EDS), attenuated total reflection with Fourier-transform infrared spectroscopy (ATR-FTIR) and X-ray diffraction (XRD) were used for physicochemical characterization. Linear sweep voltammetric (LSV) studies corroborated that CFP/PEDOT/Ru-Pi has exhibited higher oxidation peak current when compared to other modified electrodes. CFP/PEDOT/Ru-Pi electrode has displayed better catalytic activity towards oxygen evolution reaction at low onset and over potential. The modified electrode has also offered better stability towards the oxidation reaction in phosphate buffer solution (PBS) and the working stability of these electrodes were determined using LSV and CV. 2021 Elsevier B.V. -
Surface adsorption and anticorrosive behavior of benzimidazolium inhibitor in acid medium for carbon steel corrosion
Corrosion inhibition property of a newly synthesized 3-(4-chlorobenzoylmethyl) benzimidazolium bromide inhibitor against carbon steel corrosion in 1N hydrochloric acid solution was studied and analyzed utilizing various electrochemical methods. Electrochemical impedance study inferred that the inhibition efficiency increased with increasing inhibitor concentration and give 93.5% at 250ppm. Potentiodynamic polarization study emphasized that inhibitor acted as a mixed type inhibitor and the adsorption of inhibitor on the metal surface followed Langmuir adsorption isotherm. The noise results were in good correlation with other electrochemical results obtained. The increase of inhibition efficiency with concentrations of inhibitor is attributed to the blocking of the active area by the inhibitor adsorption on the metal surface. The thermodynamic parameter values were calculated and discussed to explain the adsorption mechanism of inhibitor in an acidic medium. The protective surface morphology governed by the inhibited medium was investigated using the scanning electron microscopic technique. The surface roughness of the sample in the absence and presence of inhibitor was obtained using atomic force microscopic study. The effect and reactivity of the inhibitor are further clarified with quantum chemical analysis. Finally, the corrosion protection mechanism is proposed on the ground of experimental and theoretical studies. Graphical abstract: [Figure not available: see fulltext.] 2022, The Author(s), under exclusive licence to Springer Nature B.V. -
Exploring the inhibition performance of tetrachloroferrate ionic liquid in acid environment using scanning electrochemical microscope and theoretical approaches
The corrosion inhibition performance of carbon steel by Benzyltributylammonium tetrachloroferrate ([BTBA]+[FeCl4]?)was investigated in 1 N HCl solution and compared with theoretical results. The electrochemical impedance results showed that [BTBA]+[FeCl4]?ionic liquid act as an effective inhibitor for carbon steel corrosion in acidic medium and maximum inhibition efficiency was found to be 99.5% at 400 ppm. The SECM results also confirmed the adsorption of [BTBA]+[FeCl4]?on carbon steel and thereby forming a relatively insulated surface at the interface. The adsorption of ferrate ionic liquid on carbon steel was found to obey Langmuir adsorption isotherm. Ionic liquid effectively inhibits anodic and cathodic reaction site thereby showed its mixed type inhibition behaviour. In presence of the inhibitor higher resistance values were obtained for impedance and polarization studies. The presence of ionic liquid and its surface protection tendency at the metal/solution interface was confirmed by SEM surface studies. UVVis and ATR-FTIR characterization also contributed in corroborating the complex formation between Fe2+ and ionic liquid. Monte Carlo simulation and quantum chemical parameters substantiated the experimental findings and gave further insights about the inhibition mechanism. 2020 Elsevier B.V. -
Probing the effect of newly synthesized phenyltrimethylammonium tetrachloroaluminate ionic liquid as an inhibitor for carbon steel corrosion
The corrosion protection effect of phenyltrimethylammoniumtetrachloroaluminate[PTMA]+[AlCl4]?as an inhibitor was explored in the present work. In this paper, the authors have explored a non-heterocyclicbased ionic liquid as a corrosion inhibitor for metal protection in the acid cleaning process of metal. In particular, a negative ion is designed based onthe lewis acid concept by which it could cover the maximum surface by the bigger molecule size. The inhibition efficiency was found to be steadily increasing as the concentration of the [PTMA]+[AlCl4]? ionic liquids increased.These studies revealed thatthe inhibitor exhibited a remarkable potential for corrosion protection on carbon steel in 1 N HCl solution. Stable corrosion protection efficiency (96%) was achieved for 1.3 mMof inhibitor. The adsorption of the inhibitive molecule was studied by Langmuir adsorption isotherm. The anti-corrosion effect of ionic liquid on the surface protection was revealed by scanning electron microscope (SEM)and lower surface roughness attained at an optimum concentration of inhibitor in atomic force microscope (AFM) analysis. In this study, with the view of the experimental and theoretical investigation (gaseous and aqueous forms of [PTMA]+[AlCl4]? ionic liquid in presence of HCl)was investigated, and finding deduced that the ionic liquid offered maximum dispenses with the heterocyclic group. In addition, to validate the experimental result, dynamic simulation studies were performed in both gaseous and liquid stimulation conditions. 2021 The Author(s) -
Evaluating prolonged corrosion inhibition performance of benzyltributylammonium tetrachloroaluminate ionic liquid using electrochemical analysis and Monte Carlo simulation
Corrosion inhibition performance of a newly synthesized ionic liquid Benzyltributylammonium tetrachloroaluminate [BTBA]+[AlCl4]?on carbon steel has been studied using electrochemical impedance and noise analysis in 2 N HCl medium. The synthesized product was characterized by ATR-FTIR and1H NMR spectroscopic studies. The investigation revealed that the synthesized ionic liquid, [BTBA]+[AlCl4]?showed a remarkable noise and charge transfer resistance against corrosion. The adsorption behaviour of [BTBA]+[AlCl4]- on metal surface was found to follow Langmuir adsorption isotherm. The inhibition efficiency is measured as a function of immersion time and exhibited prolonged protection against acidic corrosion. Results derived from UVVis spectra explained the complex formation between the metal surface and ionic liquid in acid medium. SEM/EDAX has been used to examine the surface protection offered by the ionic liquid. [BTBA]+[AlCl4]?ionic liquid exhibited good corrosion inhibitor property with an efficiency of 97% at the optimum concentration. Quantum chemical analysis and molecular simulation studies were performed to support the experimental data. 2019 Elsevier B.V. -
Evaluation of Corrosion Mitigation Performance of 1-(3,4,5-Trimethoxyphenylmethylidene)-2-Naphthylamine (TMPNA) Schiffs Base on Carbon Steel Using Electrochemical, Thermodynamic and Theoretical Approaches
A novel Schiff base,1-(3,4,5-trimethoxyphenylmethylidene)-2-naphthylamine(TMPNA) has been synthesized using naphthylamine and 3,4,5-trimethoxybenzaldehyde.The effective corrosion resistance and inhibition effect of TMPNA was studied at different concentrations in water medium on carbon steel by electrochemical techniques. The protective behavior of the passive film formed by the inhibitor was characterized through electrochemical impedance spectroscopy with an increased charge transfer resistance of 954 ?.cm2. The inhibition efficiency exhibited a gradual increase up to 92% with increase in schiff base concentration. Potentiodynamic polarization studies revealed that corrosion current decreased to 0.35 10?5A/cm2 with the addition of the inhibitor, TMPNA. Through various electrochemical studies such as impedance, polarization and electrochemical noise analysis (ENA), the concentration of TMPNA was optimized to 300ppm at which the maximum corrosion resistance was observed. Inhibition efficiency was found to decrease with increase in temperature. Also, the increased activation energy (Ea) value of 27kJ/mol confirmed that the inhibitor hindered the metal dissolution reaction. Adsorption of TMPNA on carbon steel/electrolyte interface was found to obey Langmuir adsorption isotherm. Scanning electron microscope (SEM) was used to evaluate the surface morphology. The Quantum chemical analysis (QCA) revealed that there was an electron transfer between TMPNA and the metal surface at ? 6.340eV. Molecular dynamic simulation study was carried out to investigate the adsorption of TMPNA on Fe (1 1 0) surface and adsorption energy value for the gaseous form was found to be ? 4197cal/mol. 2020, Springer Nature Switzerland AG. -
Explainable AI and computational intelligence in healthcare: Application to clinical decision support and personalized medicine
Human intelligence system simulation has made significant strides in several areas, including clinical decision-making using medical imaging and electronic health records, health referral systems, discovering recommended medications and vaccines, recognizing prescribed errors, and real-time data analysis. Therefore it is essential to discover patterns and transfer knowledge in the medical domain. The obstacles at the level of data collection, data analysis, model development, decision-making, and ethical concerns need to be addressed. It is vital that clinical interpretation tools associated with both hardware and software employed by medical professionals be precisely examined when rendering decisions regarding diagnoses and therapies related to the diagnosis. Computer scientists generally lack training in medical concepts specific to their field. Another crucial aspect is that black box algorithms based on artificial and computational intelligence are opaque and devoid of logical justification. Owing to these limitations, the technique of eXplainable Artificial Intelligence (XAI) models is explored in this chapter, primarily focusing on improving the interpretability of computational models. Specific objectives of this chapter are to: a) discuss the role that CI techniques and methods in the construction of an intelligent health prediction system; b) demonstrate the multiple CI paradigms utilized in medical prediction; and c) present recent case studies to showcase the performance of the computational intelligent models. 2026 Elsevier Inc. All rights reserved. -
An enhancement of machine learning model performance in disease prediction with synthetic data generation
The challenges of handling imbalanced datasets in machine learning significantly affect the model performance and predictive accuracy. Classifiers tend to favor the majority class, leading to biased training and poor generalization of minority classes. Initially, the model incorrectly treats the target variable as an independent feature during data generation, resulting in suboptimal outcomes. To address this limitation, the model was adjusted to more effectively manage target variable generation and mitigate the issue. This study employed advanced techniques for synthetic data generation, such as synthetic minority oversampling (SMOTE) and Adaptive Synthetic Sampling (ADASYN), to enhance the representation of minority classes by generating synthetic samples. In addition, data augmentation strategies using Deep Conditional Tabular Generative Adversarial Networks (Deep-CTGANs) integrated with ResNet have been utilized to improve model robustness and overall generalizability. For classification, TabNet, a model tailored specifically for tabular data, proved highly effective with its sequential attention mechanism that dynamically processes features, making it well suited for handling complex and imbalanced datasets. Model performance was evaluated using a novel approach of training synthetic data and testing on real data (TSTR). The framework was validated on the COVID-19, Kidney, and Dengue datasets, achieving impressive testing accuracies of 99.2%, 99.4%, and 99.5%, respectively. Furthermore, similarity scores of 84.25%, 87.35%, and 86.73% between the real and synthetic data for the COVID-19, Kidney, and Dengue datasets, respectively, confirmed the reliability of the synthetic data. TabNet consistently showed substantial improvements in F1-scores compared to other models, such as Random Forest, XGBoost, and KNN, emphasizing the importance of selecting the right synthetic data augmentation techniques and classifiers. Additionally, SHapley Additive exPlanations (SHAP)-based explainable AI tools were used to interpret model performance, providing insights into feature importance and its impact on predictions. These findings confirm that the proposed approach enhances the accuracy, robustness, and interpretability, offering a valuable solution for addressing data imbalance in classification tasks. The Author(s) 2025. -
Surface adsorption and anticorrosive behavior of benzimidazolium inhibitor in acid medium for carbon steel corrosion /
Journal of Applied Electrochemistry, Vol.52, Issue 11, pp.1659–1674, ISSN No: 0021-891X (Print) 1572-8838 (Online).
Corrosion inhibition property of a newly synthesized 3-(4-chlorobenzoylmethyl) benzimidazolium bromide inhibitor against carbon steel corrosion in 1 N hydrochloric acid solution was studied and analyzed utilizing various electrochemical methods. Electrochemical impedance study inferred that the inhibition efficiency increased with increasing inhibitor concentration and give 93.5% at 250 ppm. Potentiodynamic polarization study emphasized that inhibitor acted as a mixed type inhibitor and the adsorption of inhibitor on the metal surface followed Langmuir adsorption isotherm. The noise results were in good correlation with other electrochemical results obtained. -
A modern approach of swarm intelligence analysis in big data: Methods, tools, and applications
Swarm intelligence is one of the most modern and less discovered artificial intelligence types. Until now it has been proven that the most comprehensive method to solve complex problems is using behaviours of swarms. Big data analysis plays a beneficial role in decision making, education domain, innovations, and healthcare in this digitally growing world. To synchronize and make decisions by analysing such a big amount of data may not be possible by the traditional methods. Traditional model-based methods may fail because of problem varieties such as volume, dynamic changes, noise, and so forth. Because of the above varieties, the traditional data processing approach will become inefficient. On the basis of the combination of swarm intelligence and data mining techniques, we can have better understanding of big data analytics, so utilizing swarm intelligence to analyse big data will give massive results. By utilizing existing information about this domain, more efficient algorithm can be designed to solve real-life problems. 2023, IGI Global. All rights reserved. -
Impact of Leverage on Valuation of Non-Financial Firms in India under Profitabilitys Moderating Effect: Evidence in Scenarios Applying Quantile Regression
The firms valuation (FV) is the key element for all stakeholders, particularly the investors, for their investment decisions. The main impetus of this research is to estimate the effects of the debt ratio (DR, i.e., leverage) on the FV (i.e., assets and market capitalisation) of the non-financial firms listed in India. The quantile panel data regression (QPDR) on the secondary data of 76 non-financial BSE-100 listed firms in India is employed. This study also checks the effect of the net profit margin (NPM) as profitability on the association between DR and FV. The QPDR estimates result in multiple quantiles and provide evidence in scenarios. The findings reveal a positive relationship of DR to assets only in higher quantiles, i.e., 90%ile), and a negative association of DR is found with a market capitalisation in all quantiles. Under the interaction effect, profitability (NPM) does not affect the association of DR with assets but negatively affects the association of debt ratio with market capitalisation in the middle (50%) quantile. The findings indicate that leverage (DR) affects a firms value. The studys outcomes are helpful to all stakeholders, particularly investors, to realise the leverage (DR) as a critical indicator of FV before making any investment decisions. Managers should also consider lower debt ratios for better firm value. The present analysis is original and holds novelty in the form of the moderating role of the net profit margin, i.e., the profitability of the firm between DR and FV in the non-financial firm in India. To the best of our knowledge, no such studies have been performed to look for the association of the debt ratio with a firms value under the effect of profitability in different quantiles using quantile regression. 2023 by the authors. -
A Diabetes Detection Framework Based on Datadriven Predictive Technologies
Diabetes is a chronic disease spreading worldwide with major health challenges. It is not only caused by medical factors but other factors too such as genetic, demographics and lifestyle factors. With traditional or manual diagnosis methods, timely diagnosis becomes challenging due to complex and fragmented datasets. Recent advancements in machine learning (ML) models have greatly enhanced the efficiency and accuracy in disease diagnosis and risk evaluation. This review synthesizes the findings from the recent studies in the field of diabetes, major contributions and limitations, identifies the directions for the future work. This review has included the articles from three databases: Scopus, IEEE Xplore and PubMed; published between 2017 and 2025. The study has employed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) model for the review process. The scope of this work includes datadriven predictive technologies for diabetes detection, risk of complications and disease progression. It also sheds light on ongoing challenges such as data imbalance, limited interpretability, and population generalizability, while pointing to future opportunities in explainable AI and more personalized approaches to diabetes care. The review highlights that hybrid or ensemble models performing better than classical single models for risk prediction. 2025 IEEE.