Browse Items (2150 total)
Sort by:
-
5G-UFMC System For PAPR Reduction Using SRC-Precoding With Different Numerologies
Universal Filtered Multicarrier (UFMC) has been incorporated in 5G and is likely to be considered in future generations (B5G). The prominent limitation of UFMC manifests as a high Peak-to-Average Power Ratio (PAPR). Our suggested approach to address the Peak-to-Average Power Ratio (PAPR) issue in UFMC signals involves the application of diverse precoding matrices, including Square Root Raised Cosine Function (SRC), Discrete Cosine Transform (DCT), and Discrete Hartley Transform (DHT).This technique reduces the PAPR performance of UFMC signals over current state of the art methods. In square root raised cosine (SRC) precoding techniques, a novel precoding matrix is adapted for minimizing PAPR and improvement of BER respectively. Results show that the different subcarrier was applied and surpasses all existing techniques in reduction of PAPR and BER improvement. A novel SRC-Precoding technique reduces PAPR by 5dB for considering 512 sample points with QAM modulation as compared to 10dB for the conventional technique. Additionally, the Bit Error Rate Performance is maintaining 14dB when compared to conventional technique. Furthermore, the evaluation of Bit Error Rate (BER) performance and Peak-to-Average Power Ratio (PAPR) in the UFMC system reveals superior results compared to conventional technique. 2024 IEEE. -
An Intelligent Model forPost Covid Hearing Loss
Several viral infections tend to cause Sudden Sensorineural Hearing Loss (SSNHL) in humans. Covid-19 being a viral disease could also cause hearing deficiencies in people as a side effect. There have been pieces of evidence from various case studies wherein covid infected patients have reported to be suffering from sudden sensorineural hearing loss. The main objective of this study is to inspect the phenomenon and treatment of SSNHL in post-COVID-19 patients. This study proposes a mathematical model of hearing loss as a consequence of covid-19 infection using ordinary differential equations. The solutions obtained for the model are established to be non-negative and bounded. The disease-free equilibrium, endemic equilibrium and basic reproductive number have been obtained for the model which helps analyse the models trend through stability analysis. Moreover, numerical simulations have been performedfor validating the obtained theoretical results. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Design and Implementation of Machine Learning-Based Hybrid Model for Face Recognition System
Face recognition technologies must be able to recognize users faces in a chaotic environment. Facial detection is a different issue from facial recognition in that it requires reporting the position and size of every face in an image, whereas facial recognition does not allow for this. Due to their general similarity in look, the photographs of the same face have several alterations, which makes it a challenging challenge to solve. Face recognition is an extremely challenging process to do in an uncontrolled environment because the lighting, perspective, and quality of the image to be identified all have a significant impact on the process's output. The paper proposed a hybrid model for the face recognition using machine learning. Their performance is calculated on the basis of value derived for the FAR, FRR, TSR, ERR. At the same time their performance is compared with some existing machine learning model. It was found that the proposed hybrid model achieved the accuracy of almost 98%. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Real-Time Cyber-Physical Risk Management Leveraging Advanced Security Technologies
Conducting an in-depth study on algorithms addressing the interaction problem in the fields of machine learning and IoT security involves a meticulous evaluation of performance measures to ensure global reliability. The study examines key metrics such as accuracy, precision, recall, and F1 scores across ten scenarios. The highly competitive algorithms showcase accuracy rates ranging from 95.5 to 98.2%, demonstrating their ability to perform accurately in various situations. Precision and recall measurements yield similar information about the model's capabilities. The achieved balance between accuracy and recovery, as determined by the F1 tests ranging from 95.2 to 98.0%, emphasizes the practical importance of data transfer in the proposed method. Numerical evaluation, in addition to an analysis of overall performance metrics, provides a comprehensive understanding of the algorithm's performance and identifies potential areas for improvement. This research leads to advancements in the theoretical vision of machine learning for IoT protection. It offers real-world insights into the practical use of robust models in dynamically changing situations. As the Internet of Things environment continues to evolve, the study's results serve as crucial guides, laying the foundation for developing strong and effective security systems in the realm of interaction between virtual and material reality. The Author(s) 2024. -
An Improved Image Up-Scaling Technique using Optimize Filter and Iterative Gradient Method
In numerous realtime applications, image upscaling often relies on several polynomial techniques to reduce computational complexity. However, in high-resolution (HR) images, such polynomial interpolation can lead to blurring artifacts due to edge degradation. Similarly, various edge-directed and learning-based systems can cause similar blurring effects in high-frequency images. To mitigate these issues, directional filtering is employed post corner averaging interpolation, involving two passes to complete the corner average process. The initial step in low-resolution (LR) picture interpolation involves corner pixel refinement after averaging interpolation. A directional filter is then applied to preserve the edges of the interpolated image. This process yields two distinct outputs: the base image and the detail image. Furthermore, an additional cuckoo-optimized filter is implemented on the base image, focusing on texture features and boundary edges to recover neighboring boundary edges. Additionally, a Laplacian filter is utilized to enhance intra-region information within the detailed image. To minimize reconstruction errors, an iterative gradient approach combines the optimally filtered image with the sharpened detail image, generating an enhanced HR image. Empirical data supports the effectiveness of the proposed algorithm, indicating superior performance compared to state-of-the-art methods in terms of both visual appeal and measured parameters. The proposed method's superiority is demonstrated experimentally across multiple image datasets, with higher PSNR, SSIM, and FSIM values indicating better image degradation reduction, improved edge preservation, and superior restoration capabilities, particularly when upscaling High-Frequency regions of images. 2023 IEEE. -
Biomedical Mammography Image Classification Using Patches-Based Feature Engineering with Deep Learning and Ensemble Classifier
In order to reduce the expense of radiologists, deep learning algorithms have recently been used in the mammograms screening field. Deep learning-based methods, like a Convolutional Neural Network (CNN), are now being used to categorize breast lumps. When it involves classifying mammogram imagery, CNN-based systems clearly outperform machine learning-based systems, but they do have certain disadvantages as well. Additional challenges include a dearth of knowledge on feature engineering and the impossibility of feature analysis for the existing patches of pictures, which are challenging to distinguish in low-contrast mammograms. Inaccurate patch assessments, higher calculation costs, inaccurate patch examinations, and non-recovered patched intensity variation are all results of mammogram image patches. This led to evidence that a CNN-based technique for identifying breast masses had poor classification accuracy. Deep Learning-Based Featured Reconstruction is a novel breast mass classification technique that boosts precision on low-contrast pictures (DFN). This system uses random forest boosting techniques together with CNN architectures like VGG 16 and Resnet 50 to characterize breast masses. Using two publicly accessible datasets of mammographic images, the suggested DFN approach is also contrasted with modern classification methods. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Finding Real-Time Crime Detections during Video Surveillance by Live CCTV Streaming Using the Deep Learning Models
Nowadays, securing people in public places is an emerging social issue in the research of real-Time crime detection (RCD) by video surveillance, in which initial automatic recognition of suspicious objects is considered a prime problem in RCD. Dynamic live CCTV monitoring and finding real-Time crime activities by detecting suspicious objects is required to prevent unusual activities in public places. Continuous live CCTV video surveillance of objects and classification of suspicious activities are essential for real-Time crime detection. Deep training models have greatly succeeded in image and video classifications. Thus, this paper focuses on the use of trustworthy deep learning models to intelligently classify suspicious objects to detect real-Time crimes during live video surveillance by CCTV. In the experimental study, various convolutional neural network (CNN) models are trained using real-Time crime and non-crime videos. Three performance parameters, accuracy, loss, and computational time, are estimated for three variants of CNN models for the real-Time crime classifications. Three categories of videos, i.e., crime video (CV), non-crime video (NCV), and weapon-crime video (WCV), are used in the training of three deep models, CNN, 3D CNN, and Convolutional Long short-Term memory (ConvLSTM). The ConvLSTM scored higher accuracy, lower loss values, and runtime efficiency than CNN and 3D CNN when detecting real-Time crimes. 2024 ACM. -
A comprehensive investigation of the effect of mineral additives to bituminous concrete
Research efforts to employ sustainable materials for road construction have been on the rise in recent years. In particular, the use of polymers as additives in asphalt mix has been actively explored by several researchers. Bituminous pavementsnormally constructed in India, have increasing number of premature failures, due to increase in traffic density and noteworthy variations in road temperatures. The modified binders have proven to improve numerous properties of bituminous surfaces such as temperature susceptibility, fatigue life, creep, resistance to permanent deformation and rutting. The present study has focussed on the experimental investigations conducted to evaluate the influence of mineral additives, such as wollostonite and Rice Husk Ash (RHA) on Indirect Tensile Strength (ITS) and Tensile Strength Ratio (TSR) of bituminous concrete (BC)maintaining uniformity of aggregate properties.The results establish that the bituminous concrete blends modified using rice husk ash at 20% and wollostonite at 8%, with hydrated lime are most suitable for practical applications. 2021 Elsevier Ltd. All rights reserved. -
Template based speech enhancement of disordered speech
In this paper, we have taken Electro-Larynx (EL) speech and have improved the speech quality, electro-larynx speech was improved in terms of naturalness and intelligibility by introducing variations in the F0-contour and template matching with correlation coefficient. Initially, we introduced two different speech signals, the first speech signal introduced was healthy speech signal and the second speech signal introduced was disordered speech signal. Here, the second speech signal, the disordered speech is taken as the EL speech. The fundamental frequency or pitch was extracted first from the two inputed speech signals, then the contour of each fundamental frequency was extracted from the two input speech signals. Using these extracted features of fundamental frequency the gender classification by K-means algorithm was instigated. The same process was implemented with F0 contour features which was extracted using K-NN algorithm. EL speech contains directly radiated electrolarynx noise (DREL). The noise was filtered out using spectral subtraction algorithm. Once DREL noise is removed from EL speech, the quality of the speech was greatly improved. Then EL enhanced speech signal is compared and mapped with healthy speech signal using template matching algorithm with the help of correlation coefficient, this improves the overall quality, that is the naturalness and intelligibity of the introduced disordered speech signal. This technique helps solve the major problem of speech faced by differently abled persons with larynx disorder. 2016 IEEE. -
Modelling Networks withAttached Storage Using Perfect Italian Domination
Network-attached storage (NAS) is how data is stored and shared among hosts through a configured network. This is cheaper yet the best solution for sharing and using any huge unstructured data in an organization. Optimal distribution of NAS in a network of servers can be done using the concept of Perfect Italian Domination (PID). PID is a vertex labelling where the vertices of a graph G are labelled by 0, 1, 2 such that a vertex with label 0 should have a neighbourhood where the summation of the labels is exactly 2. The minimum possible sum of the labels obtained for graph G is its PID number. A network in an organization can have any structure. It can be highly interconnected, like a graph obtained from the Join of two graphs or the Corona product of two graphs. Hence, this paper discusses the PID of different graphs generated by the Join and the Corona products. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
On Some Graphs Whose Domination Number Is thePerfect Italian Domination Number
Perfect Italian Domination (PID) is a vertex labelling of a graph G by numbers from the set such that a vertex in G labelled 0 has a neighbourhood where the summation of the labels of the vertices in it is precisely 2. The summation of labels on the vertices of the graph which satisfy the PID labelling is known as its PID number, and is the minimum possible PID number of a graph G. We find some characterization of graphs for which . We also find a lower bound for |V(G)|, which satisfies the same. Further, we discuss the graphs that satisfies or . A realisation problem is used to prove that PID cannot be bounded by a scalar multiple of the Domination number. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Some characterizations of Gallai graphs
Gallai graph of a graph G is a graph whose vertices are the edges of G and the adjacency of the vertices depends on whether they are part of a triangle or not in G. We find some forbidden subgraph characterization of graphs for which Gallai graph is either a trivially perfect graph or a 3-sun-free graph or an interval graph. 2020 Author(s). -
ELCCFD: An Efficient and Enhanced Credit Card Fraud Detection using Enhanced Deep Learning Principle
Credit card fraud poses a serious threat to financial institutions and their customers; hence, stringent detection protocols are necessary. This study introduces an approach known as Enhanced Learning for Credit Card Fraud Detection (ELCCFD) to enhance the accuracy of credit card fraud detection. To improve the fraud detection process, the proposed method combines the strengths of Convolutional Neural Networks (CNNs), AlexNet architecture, and Gradient Boosting Machines (GBM). The proposed approach begins with cleaning up the credit card data to get useful features, then trains a Convolutional Neural Network (CNN) using AlexNet to figure out complex patterns and representations on its own. This study generates a complete set of features by merging the CNN's output with features generated using GBM. The final model is trained by using a combination of deep learning and other conventional machine learning techniques to achieve the best results. Experimental findings on benchmark datasets demonstrate the effectiveness of the ELCCFD methodology, achieving an accuracy rate of 98%. This study combines AlexNet with GBM to get a model to capture the complex patterns and is easier to understand with the feature importance analysis. With its strong accuracy and reliability, the proposed methodology offers a strong option to fight credit card fraud, and it shows the potential for actual use in financial systems. 2024 IEEE. -
A Systematic Review of AI Privileges to Combat Widen Threat of Flavivirus
In order to prevent the extraordinary spread of sickness caused by Flavivirus, the healthcare business as well as public health are working tirelessly. Individual lives have been affected, but mosquito-infested public locations have made a considerable influence on the general publics health. Site adaptability, climate change, and inadequate healthcare services and surveillance all contribute to the spread of the virus. The potential dangers of this virus, on the other hand, have been uncovered through extensive and ongoing research in the healthcare business. Modern healthcare facilities may benefit from the reasoning capabilities and ever-evolving analysis techniques provided by artificial intelligence. More conclusive findings have been demonstrated in the realm of AI applications in healthcare domains such as cancer, neurology, and cardiology. A number of research works have justified the use of AI-oriented algorithms for intelligently handling unstructured and huge healthcare data. When it comes to using artificial intelligence (AI) to identify, forecast, diagnose, and treat disease using data from public health and biological databases, the current effort aims to undertake an extensive examination. There may be issues in integrating assistive technology into the current healthcare system, as well. Because of this review, we hope that by merging AI research with clinical and public health specialists, critical knowledge may be extracted from data in order to unchain the relevant information of Flavivirus disease from its chains. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
An Analytical Study on the influence of using Trimmed Gait Energy Images for Human Gait Biometrics using Deep Learning
Gait based human recognition is founded on the principle that every human being has a distinctive style of walking. With the rise in the use of video surveillance devices, gait is one of the most convenient biometrics to use, in forensics. This paper is an analytical study of the effect of using trimmed Gait Energy Images (GEI) for Human Recognition using different deep learning techniques. Gait energy images are a spatiotemporal, silhouette-based representation of the human gait. GEIs from the CASIA B Multiview dataset was used to build two other sets of data by subtracting the upper body Deep learning and transfer learning techniques including Convolution Neural Networks (CNN) and VGG16 algorithms had been implemented to carry out the recognition. Results showed that the performance of the model using upper body images gives a greater accuracy than the lower body images. It has also been observed that the accuracy of recognition provided by the upper part of the body is almost the same as that achieved by the whole body, which brings forth the idea that the upper part of the body is the most pertinent in Human Identification using Gait as a biometric. 2022 IEEE. -
Structured text programming to visualize the distribution of packages on a conveyor
Automation is a process of increasing production and reducing the downtime of any industry. With the integration of sensor data to the cloud using an OPC-VA communication protocol, the automation becomes more prominent and interesting. However, many existing industrial controllers do not support open platform communication unified architecture (OPC-VA) and it needs an IIoT device to connect the cloud. The existing programmable logic controller in any industry have to be connected to an IIoT device through Ethernet. Sensors connected to the controller will transmit the data to the IIoT device. The transmission can also be bidirectional. In this paper, a conveyor which distributes packages is simulated in Codesys and it is visualized in a human-machine interface (HMI) screen which is in-built in the software. The hardware set-up is made with the industrial controller to execute the same. A methodology to send the data from the controller to the cloud using open platform communication unified architecture (OPC-UA) is proposed 2023 IEEE. -
Enhancing Disease Prediction in Healthcare: A Comparative Analysis of PSO and Extreme Learning Approach
The healthcare business generates a tremendous quantity of data, and the goal is to collect it and use it effectively for analysis, prediction, and treatment. The best approach to disease management is disease prevention through early intervention. There are a number of methods that can advise you on how to treat a specific sickness, but much fewer that can tell you with any degree of certainty if you will actually get sick in the first place. Preprocessing, feature selection, feature extraction, and model training are all parts of the proposed method. The suggested layout includes a preprocessing stage that takes care of things like moving average, missing values, and normalization. Feature selection describes the process of selecting the most relevant features from a dataset. After gathering features, the models are trained using PSO-ELM. The proposed strategy is superior to the widely used PSO and ELM. 2023 IEEE. -
The Optimization of Output of Wind Turbine with the Ongoing Grid System through BP Method Using ANN
Wind turbines are intricate devices that need careful planning, evaluation, and installation to guarantee peak performance under a range of environmental circumstances. Comprehensive load calculations, performance evaluations, and iterative optimisation processes are all part of the design process. However, complex simulation techniques are required to adequately depict the non-linear behaviour of wind turbine systems because of their complicated structure. Automation of optimisation processes and simulation executions is crucial to optimise the design process and manage the large number of simulations that are needed. This work provides a thorough framework using back propagation (BP) and artificial neural networks (ANN) for simulation and optimization that will make it easier to manage and automate the execution of iterative simulations during the design and development of wind turbines. The framework's main goals are to make design load case simulations easier and optimise activities more automatically. The framework makes it possible to optimise wind turbine systems and explore design options more effectively by automating these procedures. Three example optimisation jobs illustrate the framework's versatility and functionality. 2024 IEEE. -
Preparation and Characterization of Tungsten Carbide/Epoxy Composites for J-Ray Shielding
Polymer composites have attracted considerable attention as potential light weight and cost-effective shielding materials which could be used for applications in nuclear reactors, nuclear waste transportation, as protective cloth/apron for personnel in hospitals, and shielding instruments on-board satellites from space radiations. In this context, we have developed diglycidyl ether of bisphenol A (DGEBA)-based epoxy resin composites loaded with tungsten carbide (WC) for J-ray shielding. Epoxy composites containing different loadings (0, 10, 30 and 50 wt%) of WC were synthesized by room temperature solution casting technique. Structural and morphological studies of the composites were performed using X-ray diffraction (XRD) and scanning electron microscopy (SEM). Thermal and tensile properties of epoxy were enhanced in the presence of WC fillers. Thermogravimetric analysis revealed the major degradation temperature occurring between 430C and 580C for all epoxy/WC composites. The tensile strength and Youngs modulus of the composites enhanced with loading, owing to greater intermolecular reinforcing effect, uniform stress distribution and enhanced energy-absorbing capacity. J-Ray attenuation studies performed in the energy region of 0.356 1.332 MeV using NaI(Tl) detector spectrometer showed the 50 wt% tungsten carbide/epoxy composites to have highest radiation attenuation at all the energies. The overall enhancement in thermal, mechanical, and radiation shielding characteristics of the composites may be attributed to the uniformity in distribution of the fillers in epoxy matrix. These nontoxic tungsten carbide/epoxy composites may be suitable as materials for shielding in radiation environments. 2022 American Institute of Physics Inc.. All rights reserved. -
Effect of salt spray parameters on TiC reinforced aluminium based in-situ metal matrix composites
This paper aims attention at characteristics of corrosion of reinforced primary and secondary processed Al6061 based composites along TiC particles. Using potassium hexaflourotitanate (K2TiF6) and potassium tetrafluoroborate (KB4) halide salts, the synthesis of composites was done utilizing in-situ technique using stir casting route at temperature 850 Celsius. Open die forging was subjected upon in-situ composites of cast aluminium alloy at a temperature 500C. Both microstructure studies and salt spray test were subjected upon to forged and cast alloy 6061 and its in-situ composites. In accordance to ASTM B117 standard test procedure, salt spray test was conducted utilizing 5% NaCl test solution. The results impart that, the alloy forged, and respective in-situ composites exhibited enhanced corrosion resistance comparatively. 2019 Elsevier Ltd. All rights reserved.