Fig 6 - uploaded by Praveen M Dhulavvagol
Content may be subject to copyright.
Source publication
In today’s multimedia age, Content Based Video Retrieval (CBVR) is a trending area and lot of research is being carried out in Video Surveillance, Big Data analysis and multimedia applications. Usage of multimedia data is becoming very common in day today life, content based video retrieval provides an effective mechanism for maintaining, managing...
Similar publications
Intelligent agriculture can renovate agricultural production and management, making agricultural production truly scientific and efficient. The existing data mining technology for agricultural information is powerful and professional. But the technology is not well adapted for intelligent agriculture. Therefore, this paper introduces data visualiza...
Citations
... And both Logistic Regression and Naïve Bayes consume less memory, whereas decision tree and random forest consume large memory space [5]. Decision tree has the highest, Logistic regression, Naïve Bayes and KNN have medium, while random forest has the lowest transparency of all.Hence, on comparing the performance of all algorithms, we analysed that Logistic regression and Naïve Bayes have an upper hand compared to others [6]. ...
... The dataset was classified comments/messages made by people in the online social web blogs as legal or illegal. Here the supervised machine learning algorithms i.e, Naive Bayes and Support Vector Machine are integrated to produce a hybrid algorithm [6]. Hybrid algorithm increases the efficiency and accuracy of the results and reduces the complexity, computational cost and individual model variance. ...
... Classification techniques were used for prediction [6,7] the staking methodology is used to integrate different classification algorithms and performance was analyzed with each of the staking techniques. it is useful to stack individual algorithms to obtain much powerful learning model. As we know that predictions can be highly co-related, this stacking algorithm overcomes the issue and still being at faster rate and easy to interpret. ...
Classification is very important in day-to-day life as well as in cooperate world. Classification is mainly used to classify relevant data into different set of classes. Classification of data mainly involves different steps like sorting, storing of the data which can be used for prediction and decision-making. The existing classification algorithms like logistic regression, Naïve Bayes, decision tree, support vector machine, and K-nearest neighbours have limitations like sensitivity towards the dataset, high time requirement to train the data, performance, etc. In order to overcome these limitations, in this paper, we propose the hybridization of algorithms using ensemble technique. Hybridization enhances the accuracy and precision value and also over comes the limitations of existing classification algorithms. In this study, we have analysed different classification algorithms on medical dataset and performed the comparative study analysis of different existing algorithms with the proposed hybridization method. The results interpret that the proposed method shows high accuracy, precision and F1-score in classifying the text data as compared to the existing methods.KeywordsLogistic regressionNaïve BayesDecision treeSupport vector machine
... i.e. an output, a path between source to destination, can be generated in short duration using 2D rather than 3D map in RL. This is an example dimensionality reduction which is used in other areas such as [21]. Computationally intensive tasks are performed using GPUs, but in certain RL algorithms , using multicore CPUs for computations have been proven to be more efficient in terms of time taken and also resources used. ...
Indoor navigation solutions are essential for navigating within the building where GPS based solutions cannot be used. The applications of indoor navigations are robotics, drones, and few gaming apps. Deep reinforcement learning algorithms are used for building indoor navigation solutions, but such algorithms are computationally intensive and practically infeasible. But it is feasible to use reinforcement learning by reducing the scope and indoor scene representation information to propose an indoor navigation solution, which is the focus of the proposed work. The proposed work uses deep learning to detect objects in the given indoor scene and find a path using deep reinforcement learning. The proposed solution gives the navigation path in 2 minutes 10 seconds approximately, which is comparable with previous works. The authors also indicate the research work to be carried out in the future.
Xplorer link:
https://ieeexplore.ieee.org/document/9112385
With the exponential growth of data, it is difficult to efficiently store and retrieve data using traditional methods. There is a need to optimize the storage and to efficiently retrieve relevant data matching the user query. Traditional methods lack optimized storage and to effectively retrieve data. To overcome these limitations, in this project, we propose a distributed architecture framework to optimize memory usage and to effectively retrieve relevant data using Content-Based Image Retrieval (CBIR). The experimental results show that the proposed model enhances storage performance and retrieval time by 20%.
