Browse Items (11810 total)
Sort by:
-
Comparing keyframe extraction for video summarization in CPU and GPU
Most of the information is captured through multimedia techniques. Videos contain many frames which might be redundant. Since processing of many frames is involved, these redundant frames must be removed for better and efficient results. Summarizing these frames by removing similar frames can speed up processing. In this paper video summarization is achieved by generating key frames. Key frames are generated using discrete wavelet transforms (DWT) technique and we subtract background from the keyframes to get region of interest. A video of 920&Times;720 resolution and length 120 second was used as test video and the run-time was 111 second in CPU and 60 second in GPU. The speed up is nearly 100%. A HD video which took 23 minutes in serial implementation to extract foreground object from key frames generated was reduced to 7 minutes using GPU acceleration. 2015 IEEE. -
Comparing machine learning and ensemble learning in the field of football
Football has been one of the most popular and loved sports since its birth on November 6th, 1869. The main reason for this is because it is highly unpredictable in nature. Predicting football matches results seems like the perfect problem for machine learning models. But there are various caveats such as picking the right features from an enormous number of available features. There have been many models which have been applied to various football-related datasets. This paper aims to compare Support Vector Machines a machine learning model and XGBoost an Ensemble learning model and how Ensemble Learning can greatly improve the accuracy of the predictions. Copyright 2019 Institute of Advanced Engineering and Science. All rights reserved. -
Comparing maritime piracy along the coasts of Africa: In search of a solution for the Gulf of Guinea
Merchant ships at sea have been under threat for centuries from criminal activities such as maritime piracy and armed robbery. Such acts have seen a rise in recent years, with new breeding grounds mushrooming across the globe. In Africa, such criminal activities are as old as maritime trade, with three severely affected regions, each with its own dynamics. While piracy on the eastern coast (Gulf of Aden) has been brought under control by international maritime forces and that on the south-eastern coast (Mozambique Channel) by local maritime forces, piracy on the western side (Gulf of Guinea) continues unabated and has become a matter of concern for the world's maritime fraternity. In an effort to find a solution for piracy in the Gulf of Guinea, this article aims to compare and analyse incidents of piracy along the coasts of Africa and understand whether the countermeasures adopted on the eastern coasts can be replicated on the western one. 2020 National Maritime Foundation. -
Comparing Strategies for Post-Hoc Explanations in Machine Learning Models
Most of the machine learning models act as black boxes, and hence, the need for interpreting them is rising. There are multiple approaches to understand the outcomes of a model. But in order to be able to trust the interpretations, there is a need to have a closer look at these approaches. This project compared three such frameworksELI5, LIME and SHAP. ELI5 and LIME follow the same approach toward interpreting the outcomes of machine learning algorithms by building an explainable model in the vicinity of the datapoint that needs to be explained, whereas SHAP works with Shapley values, a game theory approach toward assigning feature attribution. LIME outputs an R-squared value along with its feature attribution reports which help in quantifying the trust one must have in those interpretations. The R-squared value for surrogate models within different machine learning models varies. SHAP trades-off accuracy with time (theoretically). Assigning SHAP values to features is a time and computationally consuming task, and hence, it might require sampling beforehand. SHAP triumphs over LIME with respect to optimization of different kinds of machine learning models as it has explainers for different types of machine learning models, and LIME has one generic explainer for all model types. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Comparing the Accuracy of CNN Model with Inception V3 for Music Instrument Recognition
Identification of music instruments from an audio signal is a complex but useful task in music information retrieval. Deep Learning and traditional machine learning models are extremely very useful in many music related tasks such as music genre classification, recognizing music similarity, identifying the singer etc. Music Instrument recognition and classification would be helpful in categorizing different categories of music. Many researchers have proposed models for classifying western music instruments. But very little research has been done in identifying instruments accompanied with South Indian music. This research aims at identifying string instrument such as violin and woodwind instrument such as flute accompanied in a Carnatic music concert and also in other categories of music. In order to identify the instruments accompanied, Convolutional Neural Network model and Inception V3 models were used. The Mel Frequency Cepstral Coefficients images were extracted from the audio input and fed in to the neural network model. The model has been trained for the above mentioned instruments, tested and validated on different types of audio input. This research also evaluates the performance of Inception V3 transfer learning model with CNN model in recognizing the instruments used in different categories of music. 2024, Ismail Saritas. All rights reserved. -
Comparing the roles of cryptography and blockchain technology in relation to Internet of Things
Cryptography and blockchain technology are super important for keeping all our smart devices safe in the Internet of Things (IoT) which can be considered as social security. As more and more of our gadgets connect to the internet, we really need to make sure theyre secure. This article talks about how we can use blockchain technology with IoT devices. Introduction and literature survey provides the challenges of having cryptography and blockchain technology in relation to Internet of Things, the proposed methodology provides the limited internet speed, and how blockchain affects how fast our devices can work and compare the cryptography attributes and blockchain technologies with the IoT world. To maintain the data safe and securely and provide the integrity and provide the high throughput, the Weight Allocation Authority (WAA) gives priority to users based on their characteristics. The Secure Hash Algorithm-512 helps make bigger data smaller. This work deals with the Hybrid Weighted Algorithm (HWA) and how IoT devices can improve the faster data transmission securely. WAA and HWA algorithms canalso create a safe and decentralized system that can quickly stop any bad transactions. 2024, Taru Publications. All rights reserved. -
Comparison between Symmetrical and Asymmetrical 13 Level MLI with Minimal Switches
Voltage source converters that are dependable and of the highest quality are offered by Multilevel Inverter to convert DC power systems to the AC power grid. One of the intriguing technologies in the field of power electronics are multilevel inverters (MLIs) in various configurations. It is also possible to integrate a few DC sources in MLIs to create a singular output, reducing the number of isolated inverters, the overall component count, and losses. MLIs are the top converters in many applications because to their capacity for medium and high-power applications. In order to produce the levels for the stair case wave shape, this research work introduces a new configuration module for asymmetrical multilevel in which capacitors are employed as DC linkages. With two unequal DC sources, the suggested Box -type modular structure will produce more voltage levels. It is useful for a variety of renewable applications since it has two back-to-back T-type inverters and minimal parts. This module contains this structured method to lessen the Total Harmonic Distortion (THD) rating and raise the quality of the sinusoidal output voltage. 2022 IEEE -
Comparison of Affine and DCGAN-based Data Augmentation Techniques for Chest X-Ray Classification
Data augmentation, also called implicit regularization, is one of the popular strategies to improve the generalization capability of deep neural networks. It is crucial in situations where there is a scarcity of high-quality ground-truth data. Also getting new samples is expensive and time consuming. This is a typical issue in the medical domain. Therefore, this study compares the performance of Affine and Generative Adversarial Networks (GAN)- based data augmentation techniques on the chest image X-Ray dataset. The Pneumonia dataset contains 5863 chest X-Ray images. The traditional Affine data augmentation technique is applied as a pre-processing technique to various deep learning-based CNN models like VGG16, Inception V3, InceptionResNetV2, DenseNet-169 and DenseNet-202 to compare their performance. On the other hand, DCGAN architecture is applied to the dataset for augmentation. Evaluation measures like accuracy, recall and AUC depict that DCGAN outperforms other traditional models. The most important advantage of DCGAN is that it is able to identify fake images with 100% accuracy. This is especially relevant for the medical domain as it deals with the life of individuals. Thus, it can be concluded that DCGAN has better performance as compared to affine transformations applied to traditional CNN models. 2023 The Authors. Published by Elsevier B.V. -
Comparison of Augmentation and Preprocessing Techniques for Improved Generalization Performance in Deep Learning based Chest X-Ray Classification
Convolutional Neural Network (CNN) models are well known for image classification; however, the downside of CNN is the ineffectiveness to generalize and inclination towards over-fitting in case of a small train dataset. A balanced and sufficient data is thus essential to effectively train a CNN model, but this is not always possible, especially in the case of medical imaging data, as often patients with the same disease are not always available. Image augmentation addresses the given issue by creating new data points artificially with slight modifications. This study, investigates ten different methods with various parameters and probability and their combined effect on the test dataset's generalization performance and F1 Score. For the study, three pre-Trained CNN models, namely ResNetl8, ResNet34, and ResNet50, are fine tuned on a small training dataset of 500 Pneumonia and 160 Non-Pneumonia(Normal) Images for each augmentation setting. The test accuracy, F1 Score, and generalization performance were calculated for a test dataset consisting of 50 Pneumonia and 16 Non-Pneumonia(Normal) Images. 2022 IEEE. -
Comparison of cultivated Cordyceps militaris and wild Ophiocordyceps sinensis using high-performance thin-layer chromatography
Cordyceps, a fungus from the Clavicipitaceae family, has long been utilised in traditional Chinese medicine as a rare and prized mushroom. Among 750 known species, two noteworthy species within the genus are Ophiocordyceps sinensis and Cordyceps militaris. Among the active components generated by this genus, cordycepin and adenosine are particularly significant and exhibit various pharmacological properties. To evaluate and compare the concentrations of cordycepin and adenosine, high-performance thin-layer chromatography profiling was employed on lab-grown C. militaris and wild O. sinensis. Water and ethanol were utilised to extract the nucleosides. The concentrations of these nucleosides from different samples were calculated by using Rf (Retention factor) values of both cordycepin and adenosine standards. Interestingly, the fruiting bodies of C. militaris obtained through solid-state fermentation exhibited a higher cordycepin content (12.3 mg/g) compared to biomass obtained via liquid static culture. In the case of O. sinensis, cordycepin was found to be absent, with only adenosine (approximately 0.81 mg/g) being quantified. 2024 World Researchers Associations. All rights reserved. -
Comparison of DQ Method with I cos? Controller in Solar Power System Connected to Grid with EV Load
Electric Vehicles and Photovoltaic power generation integrated to grid introduces power quality issues. Power quality issues during power integration needs improvement. Control of grid interfaced converters improves grid side power quality in integrated solutions. Power injection to the grid is controlled to get rid of power quality issues. Control techniques that can improve the power injection to the grid needs to be analyzed. This paper compares DQ and I cos ? controller while PV and EVs with non-linear loads are also connected in the power grid. Performance evaluation of both controllers are analyzed by comparing power injection to the grid. 2022 IEEE. -
Comparison of Full Training and Transfer Learning in Deep Learning for Image Classification
The deep learning algorithms on a small dataset are often not efficient for image classification problems. Make use of the features learned by a model trained on large similar dataset and saved for future reference is a method to solve this problem. In this work, we present a comparison of full training and transfer learning for image classification using Deep Learning. Three different deep learning architectures namely MobileNetV2, InceptionV3 and VGG16 were used for this experiment. Transfer learning showed higher accuracy and less loss than full-training. According to transfer learning results, MobileNetV2 model achieved 98.96%, InceptionV3 model achieved 98.44% and VGG16 model achieved 97.405 as highest test accuracies. The full-trained models did not achieve as much accuracy as that of transfer learning models on the same dataset. The accuracies achieved by full-training for MobileNetV2, InceptionV3 and VGG16 are 79.08%, 73.44% and 75.62% respectively. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Comparison of genetic algorithm with Particle Swarm Optimisation, ant colony optimisation and Tabu search based on university course scheduling system
Objectives: Planning and allocation of the various resources according to the constraints is a hilarious task. The paper aims to find a suitable method to solve the university course scheduling problem. Methods and Statistical Analysis: This paper compares the usage of Particle Swarm Optimisation (PSO), Ant Colony Optimisation (ACO), Tabu Search and Genetic Algorithm (GA) in the preparation of University Course Scheduling System. Certain hard constraints, which has to be satisfied and some soft constraints that can be satisfied are considered. Findings: The algorithm should check for the satisfaction of the hard constraints and the possibility of satisfying the soft constraints. Application/Improvements: The performance of the suitable method is found by comparing with the other methods based on various parameters. -
Comparison of Gradient Boosting and Extreme Boosting Ensemble Methods for Webpage Classification
Web page classification is an important task in various areas like web content filtering, contextual advertising and maintaining or expanding web directories etc. Machine Learning methods have been found to perform well to classify web pages, and ensemble models have been used to improve the results obtained from single classifiers. The Gradient Boosting and Extreme Boosting ensemble models are used in this work for binary classification. The dataset containing URLs of web pages have been collected manually. The comparison between the two boosting algorithms validated the improvement in accuracy and speed obtained through Extreme boosting. Extreme boosting has been found to be around ten times faster than Gradient boosting and also shows improvement in accuracy. The effect of three preprocessing techniques; lemmatization, stop words removal and regular expressions shows that these preprocessing techniques improves the accuracy of the results but not significantly. 2020 IEEE. -
Comparison of HOG and fisherfaces based face recognition system using MATLAB
Face recognition and validation is not an easy task due to barriers in between like variation in pose, facial expressions and illumination. There are many algorithms available to build a face recognition system. One such popular method of approach is the Histogram of Oriented Gradients (HOG). It is a simple but effective algorithm. Even though it gives satisfactory results, it sometimes mismatches query image with irrelevant images, especially in poor lighting conditions. This paper presents a more accurate technique called Fisherfaces. It is a more reliable method for face recognition and validation. Fisherface algorithm is utilized primarily for reducing the dimensionality of the feature space. Fisherface method for image recognition involves a series of steps. Firstly, the face space dimension is reduced using Principal Component Analysis (PCA) method, then the Linear Discriminant Analysis (LDA) method is used for feature extraction. Fisherface method produced good results even under complex situations like varying illumination conditions and images with different poses and expressions which is a major drawback of HOG. Fisherface algorithm can reach a maximum accuracy of 96.87%. Error Correcting Output Code (ECOC) is the classifier used for both HOG and Fisherfaces. 2021 IEEE. -
Comparison of Machine Learning Algorithms for Predicting Chronic Kidney Disease
Early detection and characterization of chronic renal disease are crucial to ensure that patients receive the best possible treatment. This study uses data mining techniques to uncover hidden information about patients. The outcomes of using the Random Forest, Multilayer Perceptron (MLP), Support Vector Machine (SVM), Decision Tree, XGBoost, LGBM Classifier, GaussianNB, KNeighbors Classifier, and XGBRF classifier have been compared. In our study, we demonstrate that Random Forest and XGBoost algorithms are more effective in classifying and predicting the severity level of chronic kidney disease 2022 IEEE. -
Comparison of Machine Learning-Based Intrusion Detection Systems Using UNSW-NB15 Dataset
Various machine learning classifiers have been employed recently to enhance network intrusion detection. In the literature, researchers have put forth a wide range of intrusion detection solutions. The accuracy of the machine learning classifiers intrusion detection is limited by the fact that they were trained on dated samples. Therefore, the most recent dataset must be used to train the machine learning classifiers. In this study, UNSW-NB15, machine learning classifiers are trained using the most recent dataset. A taxonomy of classifiers based on eager and lazy learners is used to train the chosen classifiers, such as K-Means (KNN), Polynomial Features, Random Forest (RF), and Naive Bayes (NB), Linear Regression. In order to decrease the redundant and unnecessary features in the UNSW-NB15 dataset, chi-Square, a filter-based feature selection technique, is used in this study. When comparing these machine learning classifiers, performance is measured in terms of accuracy, mean squared error (MSE), precision, recall, and F1-score with or without feature selection technique. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024. -
Comparison of streams delineated using various SRTM, ASTER and Cartosat DEM
Results from the study on the comparison of the stream network delineated from Shuttle Radar Topography Mission (SRTM) DEM, Advanced Space borne Thermal Emission and Reflection Radiometer (ASTER) DEM and Cartosat DEM with the stream network extracted from Toposheets concluded that SRTM DEM of 30m resolution was correlated well with the stream network extracted from SOI toposheets compared to ASTER and Cartosat DEM. It is recommended to utilise SRTM open access DEM of 30m resolution from research work carried out over the study area. 2021 Ecological Society of India. All rights reserved. -
Comparison of TDD and PAIR programming for improving software quality
These days, programming improvement groups utilizing coordinated procedures have started widely adopting Test-driven development and Pair Programming. Test-driven development (TDD) is a transformative way to deal with improvement, which joins test-first improvement where you compose a test before you compose simple enough creation code to satisfy that test and refactoring. Pair Programming is a sort of communitarian programming where two individuals are working at the same time on a similar programming task. In this paper the TDD and Pair Programming is applied for a dataset, collected from a group of users and compared. For our research, we executed structured experiments with five set of pair programmers and ten individual programmers. Both groups developed programs in Java. The outcome acquired demonstrates the strategy helps in expanding the software quality. IAEME Publication. -
Comparison of the effect of suction-injection-combination on Rayleigh-Bard convection in the case of asymmetric boundaries with those of symmetric ones
The effect of suction-injection-combination (SIC) on the linear and weakly nonlinear stability of Rayleigh-Bard convection is considered in the paper for the cases of symmetric and asymmetric boundary conditions. Using the Maclaurin series with an appropriate number of terms, expression for eigenfunctions is obtained. The linear theory corroborates the results obtained using the chosen eigenfunctions in the limiting case of the no-SIC effect by matching accurately with the exact values concerning the critical Rayleigh number (Rac) and the wave number (?c). It is found that the effect of SIC is to stabilize the system in the case of symmetric boundaries irrespective of SIC being pro-gravity or anti-gravity. However, the effect of SIC is to stabilize/destabilize the system depending on SIC being pro-gravity or anti-gravity in the case of the asymmetric boundaries. We also noted a similar effect in the case of ?c wherein a maximum error of order 10 ? 4 was observed. The main novelty of the present work is studying the influence of SIC on the nonlinear dynamics of the considered problem. It is shown that the effect of SIC is to hasten the onset of chaos. Using various indicators (the largest Lyapunov exponent, the time series solution, the amplitude spectrum, and the phase-space plots), the dynamical behavior of the system is analyzed and the influence of SIC on the dynamics is recorded. The change due to the boundary effect and the SIC on the size of convection rolls and the trapping region where the dynamical system evolves within a bound is highlighted in the paper. 2023 Author(s).