Browse Items (9795 total)
Sort by:
-
Performance analysis of Clustering algorithms for dyslexia detection
Clustering algorithms plays vital role in analysing and evaluating vast number of high dimensional health care data ranging from medical data repositories, clinical data, electronic health records, body sensor networks, IoT devices, and so on. Dyslexia, a learning disorder is a common problem that is found in children during the initial stages of formal education, which is detected as mild to severe. It can also be one of the reasons of failure in the school. According to the literature this difficulty is commonly seen among Special Education Need children. There are few studies focussed on the application of classification algorithms for detecting the presence of dyslexia. This paper focusses one of SDG, goal 4:Quality Education, as dyslexic students can be given equal and quality education. Analyses of an online gamified test-based dataset is done by applying various clustering techniques such as K-means, Fuzzy c-means, and Bat K-means to assess their effectiveness in detecting the problem dyslexia. As the dataset is large, it is observed that usage of clustering methods gives us gain insight into the distribution of data to observe characteristics of each cluster. The clustering results are evaluated using root mean squared error (RMSE), mean absolute error (MAE), Xie-Beni index and it is found K Means outperforms FCM, Bat K Means algorithm for analysing different levels of the learning disorder. The Electrochemical Society -
Performance Analysis of Deep Learning Algorithms for Intrusion Detection in IoT
Due to the wide availability of IoT devices at affordable cost and the ease of use has increased IoT devices increased usage. Due to the enormous usage of the Internet of Things (IoT) devices, the security aspects related to the data are also a significant concern in this data-driven world. Negligence of security measures from users can result in severe data falsification or data thefts. In this scenario, the Intrusion Detection System has a pivotal role in IoT security. Incorporating the deep learning techniques is an effective way to predict various attacks, either known or unknown. This paper highlights the various security threats associated with IoT, the importance of deep learning in IoT intrusion detection, and various IoT intrusion detection systems using deep learning. Comparative analysis of the different deep learning techniques was performed. The results have shown Convolution Neural Networks gave high accuracy in prediction based on various evaluation metrics. 2021 IEEE. -
Performance Analysis of Deep Learning Pretrained Image Classifiation Models
Convolutional Neural Networks (CNNs) is revolutionized in the field of computer vision, with the high accuracy and capability to learn features from raw data. In this research work focused on a comparative analysis of two popular CNN architectures, VGG16 and VGG19. The CIFAR dataset consists of 60,000 images, each with a resolution of 32x32 and it's belong to one of the 10 classes. Experimental results are compared with VGG16 and VGG19 in terms of their accuracy and training time, and to identify any differences in their ability to learn features from the CIFAR-10 dataset. The results of this research can aid in directing the choice of appropriate architectures for image classification tasks as well as the advantages of optimisation strategies for enhancing the efficiency of deep learning models. In order to enhance the performance of these structures, more optimisation methods and datasets may be investigated in subsequent research. 2023 IEEE. -
Performance Analysis of Deterministic Finite Automata and Turing Machine Using JFLAP Tool
In real life, the increased data accessing speed and data storage ability is required by most of the machinery fields. However, the real-world problems can be studied effectively with the combination of scientific computational techniques with the mathematical models. Automata theory is known to be the popular mathematical model. Towards most of the software and hardware related applications, the computational methods are analyzed and designed using significant automata theory concepts (likely, pushdown automata (PDA), Turing machines (TMs) and finite automata (FA)). Hence, the conventional lecture-driven style has attracted the reflective preferences of learners using these abstract natured concepts. But the lecture-driven teaching style has less motivated the computer engineering learners. In order to learn automata theory and computational models, we introduce the PDA and TM in a virtual platform. However, this work has motivated the improvement of longitudinal experimental validation and learning using the modern technology. Java Formal Languages and Automata Package (JFLAP) tool is used to write our simulators in JAVA language and the results are obtained from each machine through simulating the input strings. 2021 World Scientific Publishing Company. -
Performance analysis of different classifier for remote sensing application
The classification of remotely sensed data on thematic map is a challenging task from very long time and it is also a goal of todays remote sensing because of complexity level of earth surface and selection of suitable classification technique. Hence selection of best classification technique in remote sensing will give better result. Classification of remotely sensed data is an important task within the domain of remote sensing and it is outlined as processing technique that uses a systematic approach to group the pixels into different classes. In this study, we have classified the multispectral data of Udupi district, Karnataka, India using different classifier including Support Vector Machine (SVM), Maximum Likelihood, Minimum Distance and Mahalanobis Distance classifier. The data of dimension 3980x3201 pixels are collected from a Landsat-3 satellite. Performance of the each classifier is compared by conducting accuracy assessment test and Kappa analysis. The obtained results shows that SVM will give accuracy of 95.35% and kappa value of 0.9408 respectively when compared other classifier, hence effectiveness of SVM is a good choice for classifying remotely sensed data. BEIESP. -
Performance Analysis of Different Classifiers to Build a Classification Model and to Improve the Vigilance Skills in Crime Detection Using Data Mining Techniques
International Journal of Advanced Research in Computer Science, Vol-3 (7), pp. 314-317. ISSN-0976-5697 -
Performance analysis of Flyash with Bentonite in grounding pit
In modern era of power systems, generation, transmission and distribution is well operated and maintained to satisfy the demand and supply management. Various problems are faced every day in all the power system areas. One among the problems faced in all the high voltage electrical equipment's is grounding. Natural grounding is done using charcoal and salt to maintain the less resistance in the grounding pit but the less resistance grounding pit becomes high resistive area due to various reasons like improper maintenance, charcoal and salt getting dissolved in soil after some period of time. In this paper a new method of grounding which uses Flyash and Bentonite is proposed and the performance is been analyzed by various standard methods. 2016 IEEE. -
Performance Analysis of Logical Structures Using Ternary Quantum Dot Cellular Automata (TQCA)-Based Nanotechnology
Ternary Quantum-Dot Cellular Automata (TQCA) is a developing nanotechnology that guarantees lower power utilization and littler size, with quicker speed contrasted with innovative transistor. In this article, we are going to propose a novel architecture of level-sensitive scan design (LSSD) in TQCA. These circuits are helpful for the structure of numerous legitimate and useful circuits. Recreation consequences of proposed TQCA circuits are developed by utilizing such QCA designer tool. In realization to particular specification, we need to find the parameter values by using Schrodinger equation. Here, we have optimized the different parameter in the equation of Schrodinger. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Performance Analysis of Logistic Regression, KNN, SVM, Nae Bayes Classifier for Healthcare Application During COVID-19
Heart disease is one of the main causes of mortality in India and the USA. According to statistics, a person dies out of a heart-related disease every 36s. COVID-19 has introduced several problems that have intensified the issue, resulting in increased deaths associated to heart disease and diabetes. The entire world is searching for new technology to address thesechallenges. Artificial intelligence [AI] and machine learning [ML] are considered as the technologies, which are capable of implementing a remarkable change in the lives of common people. Health care is the domain, which is expected to get the desirable benefit to implement a positive change in the lives of common people and the society at large. Previous pandemics have given enough evidence for the utilization of AI-ML algorithm as an effective tool to fight against and control the pandemic. The present epidemic, which is caused by Sars-Cov-2, has created several challenges that necessitate the rapid use of cutting-edge technology and healthcare domain expertise in order to save lives. AI-ML is used for various tasks during pandemic like tracing contacts, managing healthcare-related emergencies, automatic bed allocation, recommending nearby hospitals, recommending vaccine centers nearby, drug-related information sharing, recommending locations by utilizing their mobile location. Prediction techniques are used to save lives as early detections help to save lives. One of the problems that might make a person suffering from COVID-19 extremely sick is heart disease. In this research, four distinct machine learning algorithms are used to try to detect heart disease earlier. Many lives can be saved if heart disease can be predicted earlier. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Performance Analysis of Machine Learning Algorithms for Classifying Hand Motion-Based EEG Brain Signals
Brain-computer interfaces (BCIs) records brain activity using electroencephalogram (EEG) headsets in the form of EEG signals; these signals can be recorded, processed and classified into different hand movements, which can be used to control other IoT devices. Classification of hand movements will be one step closer to applying these algorithms in real-life situations using EEG headsets. This paper uses different feature extraction techniques and sophisticated machine learning algorithms to classify hand movements from EEG brain signals to control prosthetic hands for amputated persons. To achieve good classification accuracy, denoising and feature extraction of EEG signals is a significant step. We saw a considerable increase in all the machine learning models when the moving average filter was applied to the raw EEG data. Feature extraction techniques like a fast fourier transform (FFT) and continuous wave transform (CWT) were used in this study; three types of features were extracted, i.e., FFT Features, CWT Coefficients and CWT scalogram images. We trained and compared different machine learning (ML) models like logistic regression, random forest, k-nearest neighbors (KNN), light gradient boosting machine (GBM) and XG boost on FFT and CWT features and deep learning (DL) models like VGG-16, Dense-Net201 and ResNet50 trained on CWT scalogram images. XG Boost with FFT features gave the maximum accuracy of 88%. 2022 CRL Publishing. All rights reserved. -
Performance Analysis of Nonlinear Companding Techniques for PAPR Mitigation in 5G GFDM Systems
Generalized Frequency Division Multiplexing (GFDM) is a 5G waveform contender that offers asynchronous and non-orthogonal data transmission, featuring several advantages, some of them being low latency, reduced out-of-band (OOB) radiation and low adjacent channel leakage ratio. GFDM is a non-orthogonal multicarrier waveform which enables data transmission on a time frequency grid. However, like orthogonal frequency division multiplexing and many other multicarrier systems, high peak-to-average power ratio (PAPR) is one of the main problems in GFDM, which degrades the high-power amplifier (HPA) efficiency and distorts the transmitted signal, thereby affecting the bit error rate (BER) performance of the system. Hence, PAPR reduction is essential for improved system performance and enhanced efficiency. Nonlinear companding techniques are known to be one of the effective low complexity PAPR reduction techniques for multicarrier systems. In this paper, a GFDM system is evaluated using mu law companding, root companding and exponential companding techniques for efficient PAPR reduction. The PAPR and BER graphs are used to evaluate the proposed methods in the presence of an HPA. Simulations show that, out of these three techniques, exponential companding was found to provide a trade-off between the PAPR reduction and BER performance. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Performance Analysis of Novel Compact Octagonal Shaped Fractal Antenna for Broadband Wireless Applications
Antenna plays an important role in any part of the communication system. It has to be designed very cautiously to provide improved system performance to meet the developments in wireless technologies with various design constraints such as small size, low cost, high data, low power consumption and wideband capabilities. Several efforts have been made by various investigators around the globe to amalgamate benefits of fractal structures with electromagnetic concepts and applications to reduce the size of the antenna without obstructing the performance of the antennas. This paper proposes a novel compact octagonal shaped broadband fractal antenna. The proposed antenna was designed on an inexpensive FR4-epoxy substrate and simulated using the High Frequency Structure Simulator. The antenna resonates in dual bands in 3.8 and 1GHz with lowest return loss of ?32.80dB and gain of 10.22dB while maintaining the VSWR in the 2:1 level. Attempts have been made to reduce the size and improve the bandwidth using fractal concept and truncation of ground plane. The fabricated antenna was verified experimentally and the results are agreeing with the simulations. The point of attraction of this antenna is the use of single patch for broadband coverage with easy fabrication. 2018, Springer Science+Business Media, LLC, part of Springer Nature. -
Performance analysis of OFF-GRID solar photo voltaic system
Day by day the demand for electrical energy is increasing. We can't rely on conventional energy sources for meeting this increasing demand as they are depleting. So it is necessary to find an alternative method to harness the energy that we are lacking. Solar energy generation seems to be a promising technology for this dilemma. It is environmental friendly and infinite source of energy. Photovoltaic systems can be broadly classified into two-an on-grid system or an off-grid system. The energy generated from a solar PV system is based on several factors like irradiance, types of solar PV used and temperature. Analyzing the existing system efficiency is of prime importance for the characterization of the problems and for the improvements. This study deals with the performance analysis of an on-grid and off-grid system. The analysis is carried out by modeling an existing system in MATLAB/SIMULINK which is already in operation. It can be extended to analyze the grid stability. This study aims the quantification of various performance parameters like power output, losses in the system, system efficiency and the total energy transfer. 2015 IEEE. -
Performance analysis of optimized corporate-fed microstrip array for ISM band applications
This paper presents a low cost high gain corporate feed rectangular microstrip patch antenna array of two elements having cuttings at the corners, with detailed steps of design process, operates in Industrial Scientific Medical (ISM) band (2.4 GHz). The proposed antenna structures are designed using FR4 dielectric substrate having permittivity ?r= 44 and substrate thickness of 1.6 mm. The gain of these simulated antennas are obtained as 2.4819 dB with return loss of -17.779 dB for a single element patch and 6.3128 dB with return loss of -15.8320 dB for an array of two elements. The simulations have been carried out by using Antenna simulator HFSS version 15.0.0 to obtain the VSWR, return loss and radiation pattern. 2017 IEEE. -
Performance analysis of semantic veracity enhance (SVE) classifier for fake news detection and demystifying the online user behaviour in social media using sentiment analysis
The increased propagation of fake news is the significant concern in the digital era. Identification of fake news from social media platforms is critical to strengthen public trust and ensure social stability. This research presents an effective and accurate framework for identifying fake news that combines different steps of natural language processing (NLP) technique along with a neural network architecture. A novel semantic veracity enhancement (SVE) classifier is designed and implemented in this work for detecting fake news. The proposed approach leverages the effectiveness of sentiment analysis for identifying misleading or deceptive content and its subsequent implications on the sentiment and behaviour of social media users. A BERT model is used in this research for analysing the sentiments and classifying the texts from the social media platform. By examining the sentiments, the SVE classifier differentiates between real news and fabricated content. To achieve this, three different datasets comprising both actual content and fabricated (tweaked) tweets are employed for training the SVE classifier. The potentiality of the SVE classifier is evaluated and compared with different optimization techniques. The outcome of the experimental analysis shows that the proposed approach exhibits an excellent performance in terms of classifying misinformation from the original information with an outstanding accuracy of 99% compared to other state of art methods. 2024, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature. -
Performance Analysis of Several CNN Based Models for Brain MRI in Tumor Classification
Classification is one of the primary tasks in data mining and machine learning which is used for categorizing data into classes. In this paper, brain MRI images are used for classification of tumors into three categories namely, Meningioma, Glioma, and Pituitary Tumor. These methodologies used are spatial based, depth based, feature map based and depth based CNN showcasing the power of deep learning in automating the tumor detection process. To evaluate the performance of several deep learning models, data is divided into training and testing data where a generalization method is used for comparison. The experimental results demonstrate promising accuracy, showing that a few techniques are valuable tools for radiologists and physicians, along with further analysis. The best accuracy obtained is 96% using MobileNet and ResNet50 in comparison to other CNN methodologies used in this paper. 2024 IEEE. -
Performance analysis of training algorithms of multilayer perceptrons in diabetes prediction
Artificial Intelligence plays a vital role in developing machines or software that can create intelligence. Artificial Neural Networks is a field of neuroscience which contributes tremendous developments in Artificial Intelligence. This paper focuses on the study of performance of various training algorithms of Multilayer Perceptrons in Diabetes Prediction. In this study, we have used Pima Indian Diabetes data set from UCI Machine Learning Repository as input dataset. The system is implemented in MatlabR2013. The Pima Indian Diabetes dataset consists of about 768 instances. The input data is the patient history and the target output is the prediction result as tested positive or tested negative. From the performance analysis, it was observed that out of all the training algorithms, Levenberg-Marquardt Algorithm has given optimal training results. 2015 IEEE. -
Performance Analysis of User Behavior Pattern Mining Using Web Log Database for User Identification
User behavior analytics is a progressive research domain. Understanding the users behavior patterns and identifying their behavior patterns will provide solutions to many issues like identity theft and user authentication. So many research works are done in analyzing the frequent access patterns of the users by pre-processing access logs and applying various algorithms to understand the frequent access behavior of the user. From the literature, it founds that the frequent user access pattern identification needs improvement on prediction accuracy and the minimal false positives. To accomplish these, three different approaches were proposed to overcome the existing issues and intended to reduce false positives and improve the frequent pattern mining accuracy based on web access logs. Proposed methods were found to be good while compared with the existing works. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Performance Analysis of Various Machine Learning Classification Models Using Twitter Data: National Education Policy
With the exponential growth of social networking sites, people are using these platforms to express their sentiments on everyday issues. Collection and analysis of people's reactions to purchases of products, public services, etc. are important from a marketing and innovation perspective. Sentiment analysis also called opinion mining or emotion extraction is the classification of emotions in text. This technique has been widely used over the years to determine sentiment within given text data. Twitter is a social media platform primarily used by people to express their feelings about specific events. In this paper, collected tweets about National Education Policy which has been a hot topic for a while; and analyzed them using various machine learning algorithms such as Random Forest classifier, Logistic Regression, SVM, Decision Tree, XGBoost, Naive Bayes. This study shows that the Decision tree algorithm is performing best, compare to all the other algorithms. 2023 IEEE. -
Performance Analysis of YOLOv7 and YOLOv8 Models for Drone Detection
Drone detection techniques are used to detect unmanned aerial systems (UAS) also commonly known as drones. A rapid increase in these drones has limited the airspace safety and so the research for drone detection has emerged. This study compares between the two widely used deep-learning models, previously used YOLOv7 and the latest YOLOv8. The overall finding of this study suggests that the YOLOv8 deep-learning model appears to be more promising and may make valuable contributions on their own. We got the result that for 10 epochs YOLOv8 gave 50.16% accuracy while YOLOv7 gave 48.16% accuracy making YOLOv8 more promising for the task. As a practical application for future work, we intend to deploy YOLOv8 on edge devices to achieve real-time drone detection in critical security applications. 2023 IEEE.