Browse Items (14421 total)
Sort by:
-
A Lightweight Hybrid Deep Learning model for Real-Time Intrusion Detection in IoT Networks.
In IoT networks, cyber threats are hard to identify because of dynamic and heterogenic nature of IoT traffic as it cannot be identified with more traditional intrusion detection systems. This paper discusses the deep learning methods of intrusion detection in terms of CNN+LSTM, CNN+BiLSTM, CNN+GRU, and BiGRU+RF and propose a novel Dense+SimpleRNN architecture. Preprocessing includes label encoding, feature selection, normalization, SMOTE balancing, and reshaping sequences, using the RT-IoT 2022 dataset. The paper demonstrates, CNN + BiLSTM and CNN + GRU achieving similar accuracy but with higher computational cost. On the other hand, the proposed Dense+SimpleRNN has 98.59% accuracy, precision and recall and Fl-score, which are higher than the baselines models. The results point that Dense+SimpleRNN is an efficient and lightweight IDS that is very appropriate in real-time IoT network security. 2025 IEEE. -
The Role of Artificial Intelligence in Electric and Autonomous Vehicles
The?? use of Artificial Intelligence (AI) is changing the whole car landscape. Indeed, AI is the main driving force behind the most innovative electric and autonomous vehicles. The technology is making transportation environmentally friendly, intelligent, and cost-effective. The chapter demonstrates the role of AI in self-driving cars and electric vehicles through various examples, such as autonomous driving, battery performance, charging systems, predictive maintenance, safety, efficiency, and fleet management. AI is the reason that cars can now drive themselves, whereby it is the technology that enables navigation, object detection, and systems like Tesla Autopilot. Besides, it is heavily involved in battery management as it lowers the battery life through usage, overheating, and prolongs the battery life. The chapter also talks about AI technology that supports smart EV charging, allowing integration of renewable sources and even making charging more comfortable and hassle-free. Predictive maintenance is yet another significant area where the AI system is monitoring the health of the car, the earliest detection of the faults, and extending the lifespan of EV components. Implementation of AI in safety vehicles is a great advancement in this industry. In conjunction with this technology, AI-based safety systems, like driver assistance, hazard detection, and emergency response, provide safety to the cars. Moreover, the technology enhances energy efficiency, range prediction, and real-time vehicle performance. The chapter concludes with a discussion about the coming of reflection in the AI realm of environmental sustainability, intelligent fleet management, and challenges of the future. In summary, this article accentuates how AI is rewiring the future of electric and self-driving vehicles and why its role is key for researchers, industry professionals, and ??policymakers. 2026 -
An improved atom search optimization algorithm based on ranking strategy and sine cosine algorithm for epileptic seizure detection
Epilepsy is a serious neurological disorder that remains difficult to detect with high accuracy. Automated seizure detection using EEG signals has gained increasing attention, and optimization algorithms are often applied to improve system performance. Atom Search Optimization (ASO) has strong global search ability but frequently suffers from premature convergence and limited local search efficiency. To address these issues, this study proposes a hybrid algorithm that combines ASO with the SineCosine Algorithm (SCA) and a ranking strategy (RSHASOSCA). ASO provides effective global exploration, SCA enhances local exploitation, and the ranking strategy stabilizes convergence, together creating a more balanced and reliable search process. The method was evaluated on the CHB-MIT scalp EEG dataset. Features were extracted using Wavelet Packet Transform (WPT) and refined with the KruskalWallis test (p ? 0.001). Comparative experiments against twelve established optimization algorithms showed that the RSHASOSCA framework achieved superior performance. When applied with an SVM classifier, it reached 99.13% accuracy and an AUC of 1. These findings highlight the value of integrating ASO, SCA, and ranking strategy, and demonstrate the potential of the proposed framework for reliable and efficient seizure detection in clinical practice. The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025. -
PERFORMANCE EVALUATION OF IPE AND IE-AFFECTED PATIENTS USING A MODIFIED PSO AND ANFIS
Epilepsy, a complex neurological disorder, is particularly challenging to diagnose and manage when driven by genetic factors. This study focuses on the analysis of Idiopathic Partial Epilepsy (IPE) and Idiopathic Epilepsy (IE) in both children and women, using a novel approach combining Modified Particle Swarm Optimization (MPSO) with a 9-rule Adaptive Neuro-Fuzzy Inference System (ANFIS). Four feature extraction techniquesDiscrete Wavelet Transform (DWT), Shearlet Transform (SLT), Contourlet Transform (CLT), and Stockwell Transform (SWT)are employed to process electroencephalogram (EEG) signals. The performance of the proposed MPSO-ANFIS model is evaluated and compared with existing methods. Results indicate that the SWT-ANFIS-MPSO method achieves superior classification accuracy for both IE and IPE patients, highlighting its potential to improve epilepsy diagnosis and treatment strategies. 2025, Institute of Mechanics of Continua and Mathematical Sciences. All rights reserved. -
Full Reference Image Quality Assessment (FR-IQA) of Pre-processed Structural Magnetic Resonance Images
Deep learning-based Artificial Intelligence algorithms have surpassed human-level performance in many fields including medicine. Specifically in diagnosis using radiology images, deep neural networks empowered AI to excel by educating intricate nonlinear relationships which is a core part of the complicated radiology problems. However, these models require a massive amount of quality data for training. The accuracy of the deep learning model is based on the amount of training data and the quality of the trained data being fed. So, preprocessing the data from different capturing devices is inevitable. This study aimed to highlight some of the image quality metrics that can be used to quantify the efficiency of the chosen preprocessing pipeline. By quantifying the result of each preprocess step, the user can choose an optimal set of preprocesses that can greatly improve the image quality, leading to a high and accurate diagnosis through a deep learning model. Thus, this study detailed how the full reference image quality metrics can be used to validate the performance of sMRI preprocess tasks. 2024 IEEE. -
Arts education, academic achievement and cognitive ability
Although art is often considered to be a means for maximizing human potential, the causes and consequences of artistic experiences are poorly understood. The present chapter reviews the relevant literature concerning the consequences of participating in the arts. It is clear that training in the arts improves performance on arts-specific tasks. For example, children who take music lessons perform better than their untrained peers on musical tasks such as perceiving musical key and harmony (Corrigall and Trainor, 2009). But training in the arts may also be associated with performance in non-arts domains. This chapter examines the possibility of four such associations, namely whether arts education is associated with academic achievement, general cognitive ability, language processing and visuospatial skills. In each case, the literature is evaluated in terms of the consistency of the findings and the evidence for claims of causation. Training in the arts and academic achievement Training in the arts is associated positively with academic achievement. For example, in a sample of Canadian high-school students, participation in musical activities in the eleventh grade predicted academic achievement in the twelfth grade (Gouzouasis, Guhn and Kishor, 2007). Other results point to similar associations between academic achievement and involvement in any type of arts-related activity. In one study that included more than 25,000 American high-school students, arts participation and school grades were recorded during the eighth, tenth and twelfth grades (Catterall, Chapleau and Iwanaga, 1999). At each point in time, students who were involved in the arts had better grades than other students. A similar positive association emerged in a meta-analysis of five correlational studies (Winner and Cooper, 2000). In a larger meta-analysis of 10 years of data from the American College Board (198898), Vaughn and Winner (2000) concluded that compared to students without arts training, students reporting any form of arts involvement (dance, drama, music and visual arts) obtained higher scores on the Scholastic Aptitude Test (SAT). This advantage for the arts group was evident for the verbal score, the mathematics score and the composite score. Students with drama lessons showed the strongest association, followed (in descending order) by students studying music, painting and dance. Even enrollment in theoretical classes (e.g., music or art history courses) was predictive of better SAT scores. Cambridge University Press 2014. -
Label-Based Feature Classification Model for Extracting Information with Dynamic Load Balancing
Efficient extraction of information from various sources is very tedious. Achieving this requires very sophisticated feature classification model and ability of the system to adapt to changing environments of data and its random distributions with an efficient use of computational resources. Label-based feature classification model (LFCM) with dynamic load balancing is proposed to address an efficient model to extract information in data set. This technique is effective in data analysis to discover the new feature set. Label approach incorporates unique label concept and it avoids any data duplication using labels. Each data sample is assigned to only one label to improve the accuracy and effectiveness of the retrieval process. Based on the data relevancy and specific features that can be extracted using proposed algorithm, classification model and semantic representation of data in vector form minimizes the data loss, and dimensionality reduction plays a vital role in building an efficient model. Various graphs and results obtained from the experiments show an improvement of information extraction using this proposed labeled LFCM approach. This approach brings lots of real time challenges that are handled to bring accuracy factor as the main focus in this proposed system. Both classification and extraction uses different model to obtain the intended results. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Secure Bitcoin Transaction and IoT Device usage in Decentralized Application
In the recent years, there has been a boom in the number of connected devices due to developments in the field of Internet of things. This has also increased the requirements of security specification. The proposed method is introducing a secure information transmission system by using Blockchain technology. Blockchain is a relatively new technology which was introduced by stoshi nakamoto, which was also the basis for developing crypto currency [bitcoin]. Crypto currencies are made transparent and secure using their network architecture, which is a combo of a decentralized and distributed network. In this paper is try to exploit the same methodology used in crypto currencies to develope an IOT network, where the devices can talk to their peers in a secure manner. They explored all the different networks and features of developing a Decentralized application that is named as Dapp. 2018 IEEE. -
Automated Diabetic Retinopathy Diagnosis Using Ensemble Approach
Diabetic Retinopathy is a major reason of vision impairment among diabetic patients, early and accurate diagnosis is crucial. This research focuses on developing a machine learning-based classification system to detect different stages of DR using Support Vector Machine (SVM), Random Forest (RF) and ensemble model. The dataset is divided into five categories: Healthy, Mild, Moderate, Proliferative and Severe DR. Performance evaluation using various metrics, including Accuracy, F1-score, RMSE and AUC-ROC, indicates that the ensemble model achieves the best results, with an accuracy of 77.66% and an AUC-ROC of 0.9015. The confusion matrices show that existing models struggle with certain misclassifications, the ensemble approach enhances overall predictive capability. Future improvements can include integrating deep learning models such as convolutional Neural Networks leveraging larger and more diverse datasets and incorporating image preprocessing techniques to enhance feature extraction. This system can help ophthalmologists to detect early and treatment planning, ultimately decrease the risk of blindness in diabetic patients. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Facile mechanochemical assembly of PANI-modified tetra-amino zinc phthalocyanine@Bi2O3 hybrid for enhanced visible-light-driven dye degradation
This work describes a fast, green, and solvent-free mechanochemical route to produce an advanced photocatalyst tetra-amino zinc phthalocyanine embedded in a polyanilineBi2O3 matrix (PANI-TAZnPc@Bi2O3). Comprehensive FTIR, Raman, FESEM, XRD, HRTEM, and DRS analyses confirm the successful synthesis of the materials, revealing irregular nanoscale particles with crystallite sizes of 8.36 nm (TAZnPc), 29.26 nm (Bi2O3), and 29.86 nm (PANITAZnPc@Bi2O3). TGA reveals that Bi2O3 exhibits excellent thermal stability up to 930 C, while the PANITAZnPc@Bi2O3 composite up to about 150 C. The photocatalytic performance was evaluated by degrading methylene blue (MB) in the presence of H2O2 under visible light, with systematic variations in catalyst dosage, irradiation time, solution pH, and reusability. Compared to bare Bi2O3 and TAZnPc@Bi2O3, the PANI-TAZnPc@Bi2O3 composite showed superior activity- its narrower band gap, enhanced MB adsorption, and reduced electronhole recombination, achieving 99.75 % dye removal in 100 min under optimal conditions. The PANITAZnPc@Bi2O3 photocatalyst demonstrated excellent stability, retaining its photocatalytic activity over five consecutive cycles with no significant changes in its XRD and FTIR profiles. Reactive species such as OH and O?? drive methylene blue degradation, leading to its mineralization into inorganic ions as confirmed by ionic chromatography. Finally, a detailed photocatalytic mechanism is proposed to explain the enhanced performance of this nanocomposite. 2025 Elsevier B.V. -
The Quantum Leap: Integrating Quantum Computing With AI for Next-Gen Automotive Safety
Integrating quantum computing and artificial intelligence (AI) in automotive safety presents a paradigm shift, addressing complex challenges such as real-time traffic management, accident prevention, and system optimization. Quantum computing's principles of superposition, entanglement, and parallelism enhance AI's ability to process and analyze vast datasets, enabling precise and efficient decision-making in dynamic environments. Industry leaders like BMW, Volkswagen, and Waymo demonstrate the transformative potential of quantum-enhanced systems with applications in traffic optimization, autonomous navigation, and predictive maintenance. However, hardware scalability, ethical concerns, and regulatory gaps persist. 2025 by IGI Global Scientific Publishing. All rights reserved. -
AI-Driven Enhancements in Indian Payment Systems: A Futuristic Perspective on Financial Applications and Modifications
This study explores the application of machine learning (ML) to improve Indian payment systems, with a focus on AI-driven developments for tasks including fraud detection, transaction validation, and consumer behaviour research. We evaluate the effectiveness of several machine learning (ML) systems, including K-Nearest Neighbours (KNN), Random Forest (RF), Decision Trees (DT), Support Vector Machine (SVM), and Logistic Regression (LR), using a variety of criteria. The results, which include precision, F1 score, accuracy, recall, and AUC, show how well Random Forest and Logistic Regression work to detect fraudulent transactions. Important elements including transaction amount, payment method, and user behaviour patterns are also revealed by the feature importance evaluation. Significant differences exist between models in terms of training times and hyperparameter optimisation outcomes. All things considered, this study highlights how ML models can spur innovation in Indian payment systems, enhancing security, effectiveness, and consumer satisfaction while offering a thorough assessment structure for potential future implementation in the fintech industry. 2025 IEEE. -
Beyond brick and mortar: determinants of retail investors investment intention in indirect real estate through REITs in India
Purpose: This research aims to identify the factors that influence the investment intention of retail investors in Indian REITs. The study incorporates the theory of planned behavior and innovation diffusion theory as the research framework, with perceived risk and mass media influence as additional constructs. Design/methodology/approach: Primary data were collected using self-administered questionnaires from 534 potential investors in India. The data were analyzed using partial least square structural equation modeling. Findings: The study showed that factors such as relative advantage, compatibility, attitude, subjective norms, perceived behavioral control and mass media significantly and positively influence investment intention in Indian REITs. However, perceived risk was found to have a negative and significant influence, while complexity did not affect investment intention. Originality/value: This is the first quantitative investigation into determining the factors influencing the investment intention of Indian retail investors on Indian REITs. 2024, Emerald Publishing Limited. -
Unveiling the Indian REIT narrative-qualitative insights intoretail investors perspectives
Purpose: The present study delves into the causes of relatively lower retail participation in the Indian REIT market. Specifically, it investigates investors' attitudes and perceptions towards REITs as a unique asset class. This paper provides a comprehensive understanding of the perception and factors influencing Indian retail investors' reluctance to participate in the REIT market. Design/methodology/approach: Qualitative research was conducted through semi-structured interviews to gather insights from non-investors in REITs. The data were transcribed and analyzed using content analysis techniques. Finally, coding techniques were used to identify broad study themes. Findings: According to the study results, many retail investors are unfamiliar with REITs. Even among those knowledgeable about REITs and with a favorable view, it is not commonly seen as a feasible investment option due to its early stage, unattractive returns and limited number of REITs. Practical implications: Developed countries have established REIT markets, while it is still in its infancy in developing countries such as India. Financial advisors, fund houses and the media should focus on educating investors to increase awareness. Originality/value: The study is the first qualitative investigation into the perception of retail investors to understand the reasons for lower retail engagement in the Indian REIT market. 2024, Emerald Publishing Limited. -
Beyond brick and mortar: determinants of retail investors investment intention in indirect real estate through REITs in India
Purpose: This research aims to identify the factors that influence the investment intention of retail investors in Indian REITs. The study incorporates the theory of planned behavior and innovation diffusion theory as the research framework, with perceived risk and mass media influence as additional constructs. Design/methodology/approach: Primary data were collected using self-administered questionnaires from 534 potential investors in India. The data were analyzed using partial least square structural equation modeling. Findings: The study showed that factors such as relative advantage, compatibility, attitude, subjective norms, perceived behavioral control and mass media significantly and positively influence investment intention in Indian REITs. However, perceived risk was found to have a negative and significant influence, while complexity did not affect investment intention. Originality/value: This is the first quantitative investigation into determining the factors influencing the investment intention of Indian retail investors on Indian REITs. 2024, Emerald Publishing Limited. -
Process optimization of SLA-fabricated BN-reinforced photopolymer composites using ANOVA for improved tensile strength
This study examined how the mechanical characteristics of 3D-printed photopolymer composites are affected by the inclusion of boron nitride (BN). Stereolithography technology was used to print BN-reinforced photosensitive resin composites with different BN weight percentages (0, 0.5, 1.0, and 1.5 wt%). The effect of process parameters - Material composition, build angle, post-curing time, and lift speed) on the tensile strength of the printed specimens were evaluated using a Taguchi L16 orthogonal array. The microstructure and elemental composition of the composites were characterized using energy-dispersive X-ray spectroscopy (EDAX) and scanning electron microscopy (SEM). Tensile tests were performed in accordance with ASTM D638 Type IV, and the findings were assessed using an analysis of variance (ANOVA) and signal-to-noise (S/N) ratio. SEM and EDAX investigations revealed that BN was evenly distributed throughout the photosensitive resin matrix. The ANOVA results showed that post-curing time had the biggest effect on tensile strength (38.283 % contribution), followed by material composition (27.669 %), lift speed (16.265 %), and build angle (17.782 %). For the maximum tensile strength, the ideal set of process parameters was determined to be 1.5 wt percent BN, 90 build angle, 60 min post-curing time, and 60 mm per minute lift speed. Significant interactions between the parameters under study were displayed by interaction plots. This study offers important insights into optimizing SLA process settings for increased tensile strength and shows how BN-reinforced photopolymer composites can improve the mechanical properties of SLA-printed objects. Copyright 2025. Published by Elsevier B.V. -
Emoji Sentiment Analysis of User Reviews on Online Applications Using Supervised Machine Learning
Analyzing the sentiment behind emojis can provide valuable insights into the emotional context and user sentiment associated with textual content. To conduct a comparative analysis of diverse supervised machine learning models that can achieve the highest level of accuracy in Emoji Sentiment Analysis is the purpose of this research. Five machine learning models used in this research are K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), Logistic Regression, Naive Bayes, and Random Forest. The experimental process resulted in ANN and KNN models giving an accuracy of 92%. The ANN model shows its proficiency in effectively managing large datasets. ANN also supports fault tolerance. The KNN model refrains from conducting calculations during the training phase and only constructs a model when a query is executed on the dataset. This characteristic makes KNN particularly well-suited for data mining. Both ANN and K-NN excelled in the experimental study due to these distinctive attributes. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Enhanced Artificial Neural Network for Emoji Sentiment Analysis
Emojis enhance textual communication by conveying emotions and providing contextual richness. This study compares the performance of supervised machine learning models such as Naive Bayes, Logistic Regression, Random Forest, K-Nearest Neighbors (KNN), and Artificial Neural Networks (ANNs) for emoji sentiment classification. A major addition in this study is the enhancement of the ANN model using an informed weight initialization technique, which speeds up convergence and reduces training time while maintaining improved performance. The experimental results showed that the Enhanced ANN (EANN) model obtained 94% accuracy, a 2% improvement over the baseline ANN model, while lowering training time from 45 to 18 units (60% decrease), highlighting the importance of initialization strategies in deep learning. The initialization method helped the EANN network avoid overfitting, resulting in increased generalization and accuracy. Proper initialization balanced the gradients during backpropagation, avoiding gradient issues that limit deep networks. Also, the informed weight initialization guaranteed that the EANN began training closer to an optimal solution, lowering the possibility of becoming confined in suboptimal local minima. The findings from this study contribute to advances in sentiment analysis and text mining, particularly in terms of improving the efficiency and accuracy of deep learning approaches. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Isolation and characterization of plant growth promoting bacteria (PGPB) from the rhizosphere of Spinacea oleracea L.
As the years pass by, there is an increase in abiotic stress conditions around the environment that directly or indirectly affect agriculture around the world. Therefore, there is a dire need to increase the sustainability of plants. Plant Growth Promoting Bacteria (PGPB) play an important role in maintaining the physiology and growth of plants under various stress conditions. This study looks into the isolation and characterization of different PGPB from Spinacia oleracea L. and their tolerance against salinity and commonly used commercial pesticides against the Spinacia family. The techniques used are isolation by serial dilution, 16sRna sequencing, characterization of different PGPB assays for confirmation such as ammonia production, catalase test, phosphate solubilisation, potassium solubilization, siderophore production, indole-3-acetic acid production, biofilm formation assay, halotolerance and tolerance study using Minimal Inhibitory Concentration (MIC). PGPB were isolated and characterized from Spinacia oleracea L., which was under an abiotic stress environment. Isolates were Bacillus clarus, Bacillus licheniformis, Paenibacillus alvei SJ6 and Paenibacillus alvei SJ8, having quantities as high as 78.10.004 mgL-1 phosphate solubilization, 43.8 mgL?1 of indole-3-acetic acid production, 14.5660.011 psu of siderophore production and 0.62 0.027 mol mL?1 of ammonia production. All isolates also had considerable amounts of halotolerance up to 10%, whereas Bacillus licheniformis had 12.5% halotolerance. The bacterial isolates had considerable tolerance against commonly used commercial pesticides against green leafy vegetables such as chlorpyriphos + cypermethrin combination and fungicides such as mancozeb. Therefore, this study looks into the isolation of potential plant growth promoting bacteria that have considerable amount of halotolerance and pesticide tolerance. 2025 World Researchers Associations. All rights reserved. -
MHD Maxwell nanofluid flow over a porous conical surface: A fractional approach
The current novel study focuses on the two-dimensional magnetohydrodynamic flow of fractional Maxwell nanofluid through porous conical geometry under convective boundary conditions. The nanofluids considered for the study are suspensions of single and multi-walled carbon nanotubes with blood as the base fluid. Fractional-ordered governing equations are transfigured into non-dimensional forms using appropriate transformations. The finite difference approximations are obtained by discretizing the momentum and energy profiles. The results of both profile are plotted against various physical flow-pertaining parameters. It is evident, that multi-walled carbon nanotubes consistently show higher velocity profiles and lower temperature phases than single-walled carbon nanotubes nanofluid across all embedded parameters. Further, the study revealed that the absence of magnetic parameter improves by 11.36% of velocity distribution and the presence of heat source parameter improves by 18.37% of temperature distribution. This framing highlights the convergence criterion of the findings with previous work, emphasizing both reliability and accuracy within the range of 10?4 to 10?6. Graphical representation concludes that the model involving the fractional technique is superior to the integer one. Thus, achievement demonstrates practical application potential in optimizing the efficiency of fluid heating and cooling processes, underscoring its importance in thermal management. 2025