10 results on '"Khilar, Rashmita"'
Search Results
2. Prediction of disease from symptoms due to climate change using random forest classifier over gradient boosting classifier.
- Author
-
Reddy, Bujunuri Harish and Khilar, Rashmita
- Subjects
- *
RANDOM forest algorithms , *SYMPTOMS , *CLIMATE change , *STATISTICAL significance , *FORECASTING , *MEDICAL climatology - Abstract
The study's overarching goal is to enhance the accuracy with which the healthcare dataset's Random forest classifier can predict disease from symptoms in the face of climate change. There are two groups in this research. A random forest classifier is first created, then compared to the Gradient boosting classifier. With a sample size of 25, we may achieve a significance level of 0.001 when comparing the models' accuracies to those of these algorithms. The purpose of this research was to determine whether or not the more accurate Random forest classifier (97.16 percent) or the less accurate Gradient boosting classifier (97.1 percent) could be used to predict diseases based on symptoms (75 percent). When using an independent sample test, the Random forest classifier consistently achieves a high level of statistical significance (p0.05). In a head-to-head comparison with a Gradient boosting classifier, the suggested model's results were shown to be more accurate. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. A novel method for enhancing the accuracy in plant leaf disease detection using convolution neural network over fuzzy classifier.
- Author
-
Kalyan, Nunna Venkata and Khilar, Rashmita
- Subjects
- *
CONVOLUTIONAL neural networks , *MACHINE learning , *PLANT classification , *FOLIAGE plants , *NOSOLOGY , *FUZZY neural networks - Abstract
The main objective of this research is to enhance the accuracy of plant disease classification by processing leaf images. This article consists of 2 groupsi.e Convolutional Neural Network (CNN) and Fuzzy Classifier with a sample size of 10 for each group. G Power software is used to determine sample size with a pretest power value is 0.8 and alpha 0.05. The Novel Convolution Neural Network and the Fuzzy algorithms were implemented and compared accuracy results. Convolution Neural Network appears to be more significant with 92.48% accuracy than Fuzzy Classifier with 82%. The CNN map appears to perform significantly better than the Fuzzy with the value of p=0.19. The result shows that the Convolution Neural Network algorithm's accuracy was better than other machine learning algorithms in Plant disease classification. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. Segmentation of lung on CXR images based on CXR-auto encoder segmentation with MRF.
- Author
-
Kiruthika, K. and Khilar, Rashmita
- Subjects
- *
LUNGS , *MARKOV random fields , *CHEST X rays , *MACHINE learning , *DEEP learning , *FEATURE extraction , *PIXELS - Abstract
Chest X-ray (CXR) images serve as a fundamental diagnostic tool in the field of medical imaging. Accurate and robust lung segmentation in CXR images is a crucial step toward prediction of age, automating disease diagnosis and monitoring. Deep learning algorithms have been fig used in the segmentation process. The low-resolution output closely resembles the original high-resolution image. However, after being resampled, the image borders become blurred and, in some cases, CXR images may have low contrast between lung tissue and surrounding structures, making it challenging for algorithms to distinguish between them accurately. To overcome the difficulties noted above, a novel approach is introduced for lung segmentation in CXR images, which combines the power of CXR-Autoencoder Segmentation (CXR-AES) with Markov Random Fields (MRF) to achieve enhanced precision and performance. The CXR-AES component is responsible for feature extraction and initial segmentation, while the MRF serves as a contextual model that refines the segmentation results by considering spatial dependencies among pixels. This synergistic fusion of techniques enables the model to capture intricate lung boundaries and handle challenging cases, including pathologies and image artifacts. Finally, the above method gives a good result with dice, sensitivity, specificity, and precision performance metrics of 95.6, 89.9, 99.5, and 91.0% on segmented masks and lung, respectively. CXR-AES with MRF in lung segmentation has broad implications for clinical practice, research, and healthcare innovation. It enhances the efficiency of lung region extraction in CXR images, ultimately improving the diagnosis, treatment, and management of lung-related conditions. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
5. Enhancing accuracy to track and count multiple vehicles from surveillance video using back propagation neural network over oriented and rotated brief algorithm.
- Author
-
Kumar, S. Prabhu and Khilar, Rashmita
- Subjects
- *
BACK propagation , *VIDEO surveillance , *ALGORITHMS , *TRACKING radar - Abstract
The project's goal is to identify vehicles, measure count and provide results as the vehicle count. Materials and methods: The performance measure for highest accuracy rate in novel vehicle detection using back propagation neural network (N=10)over Oriented fast and rotated brief which identifies and counts distance. identification can be done using an image set to distinguish vehicles. The Gpower test used in about 85% (g power setting parameters: α=0.05 and power=0.85) Result: Back propagation neural network (94.32%) identifies vehicle and measures the count accurately over Oriented fast and rotated brief (91.16%) with a level of significance as 0.506 (Two tailed,p>0.05). Conclusion: The accuracy rate of Back propagation neural network is higher compared with that of oriented fast and rotated brief. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
6. Improving the Efficiency of Photovoltaic Panels Using Machine Learning Approach.
- Author
-
Khilar, Rashmita, Suba, G. Merlin, Kumar, T. Sathesh, Samson Isaac, J., Shinde, Santaji Krishna, Ramya, S., Prabhu, V., and Erko, Kuma Gowwomsa
- Subjects
- *
SOLAR panels , *MACHINE learning , *DUST , *WIND speed , *SOLAR energy , *SMART power grids - Abstract
Photovoltaic (PV) solar panels account for a major portion of the smart grid capacity. On the other hand, the accumulation of solar panels dust is a significant challenge for PV-based systems. The accumulation of solar panels dust results in a significant reduction in the amount of energy produced. Because of the country's low wind velocity and rainfall, frequent cleaning of solar panels is necessary either by manual or automated means. Cleaning activities should only be initiated when absolutely essential to reduce maintenance costs and increase the power output of solar panels that have been projected to be affected by dust accumulation. In this paper, we develop a deep belief network model to detect the dust particles in the solar panels installed as a large unit. The study takes into account various input metrics that includes solar irradiance, temperature level, and dust level on the panels. These metrics are used for the estimation of the level of dust present in the atmosphere and how often the panels can be cleaned at regular intervals. The simulation is conducted to test the efficacy of the model in cleaning the panels. The results are estimated in terms of accuracy, precision, recall, and F-measure. The results of the simulation show that the proposed model achieves higher accuracy rate of more than 99% than other methods. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
7. Deep hybrid classification model for leaf disease classification of underground crops.
- Author
-
Salini, R., Charlyn Pushpa Latha, G., and Khilar, Rashmita
- Abstract
Underground crop leave disease classification is the most significant area in the agriculture sector as they are the significant source of carbohydrates for human food. However, a disease-ridden plant could threaten the availability of food for millions of people. Researchers tried to use computer vision (CV) to develop an image classification algorithm that might warn farmers by clicking the images of plant’s leaves to find if the crop is diseased or not. This work develops anew DHCLDC model for underground crop leave disease classification that considers the plants like cassava, potato and groundnut. Here, preprocessing is done by employing median filter, followed by segmentation using Improved U-net (U-Net with nested convolutional block). Further, the features extracted comprise of color features, shape features and improved multi text on (MT) features. Finally, Hybrid classifier (HC) model is developed for DHCLDC, which comprised CNN and LSTM models. The outputs from HC(CNN + LSTM) are then given for improved score level fusion (SLF) from which final detected e are attained. Finally, simulations are done with 3 datasets to show the betterment of HC (CNN + LSTM) based DHCLDC model. The specificity of HC (CNN + LSTM) is high, at 95.41, compared to DBN, NN, RF, KNN, CNN, LSTM, DCNN, and SVM. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
8. Optical handwritten character recognition for Tamil language using CNN-VGG-16 model with RF classifier.
- Author
-
Pughazendi, N., HariKrishnan, M., Khilar, Rashmita, and Sharmila, L.
- Subjects
- *
OPTICAL character recognition , *TEXT recognition , *PATTERN recognition systems , *NATURAL language processing , *TAMIL (Indic people) , *RECOMMENDER systems , *PROGRAMMING languages - Abstract
In this world of modern data, it is so difficult to recognize handwritten characters for Tamil as many people have different styles of writing, so some of the letters are very difficult to understand and only a few can understand them. So, to overcome this issue, we built an algorithm in which the system could recognize the character and return the output. As it is difficult to understand letters manually for all their text, there is a need for some automatic method. The only intention of character recognition is that it wants to create a high-quality, accurate result that has the important points while considering the outlined input source image. Mostly, natural language processing and machine learning face the same problem with text recognition. The main goal of automatic character recognition is to create a high degree of accuracy as best as a human can do. Character recognition is the process of filtering the required information from the input-trained source to output the most useful content. This paper proposes a CNN-VGG16-RF model (convolution neural network-VGGNet-random forest) which employs an effective method to pick out the correct output. Experimental tests for our model were carried out to evaluate text quality, and the Tamil language dataset from the HP Tamil Lab website was used to compare our model to some other models; our model was found to be more effective in solving the handwritten recognition problem. In this model, we are going to propose Tamil vowels such as 12 letters only for the training and testing process. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
9. Driver Drowsiness Alert System Using Deep Learning.
- Author
-
Pughazendi, N., C., Thyagarajan, Sathish, N., Harish, Yeluri, Y., Venkata Sai Prakash, Ashish, Gattu, and Khilar, Rashmita
- Subjects
- *
DROWSINESS , *DEEP learning , *FEATURE extraction , *TRANSPORTATION safety measures , *TRAFFIC accidents - Abstract
Laziness, outlined as a condition of languor once one needs to rest, may result in symptoms that considerably impact action execution, like reduced time interval, occasional want for attentiveness, or microsleeps, to name a couple of examples. In reality, continuous weariness can impair performance at levels that admire those produced by alcohol. once driving, these aspect effects square measure particularly dangerous as a result of they increase the chances of drivers missing road signs or exits, floating into different lanes, or fucking their vehicle into another object, inflicting Associate in Nursing accident. His paper presents a brand new experimental model for detective work driver weariness to reduce accidents caused by this condition and improve transportation safety. To do this, 2 strategies for detective work a human weariness are used. The driver's face is first taken followed by eye detection and facial feature extraction, further because of the calculation of blinking values and threshold values. Second, the deep learning model can classify the frames as closed or open eyes by employing a straightforward binary classification technique, and therefore the system can behave appropriately. [ABSTRACT FROM AUTHOR]
- Published
- 2022
10. A comparative analysis of transformer based models for figurative language classification.
- Author
-
Junaid, Taha, Sumathi, D., Sasikumar, A.N., Suthir, S., Manikandan, J., Khilar, Rashmita, Kuppusamy, P.G., and Janardhana Raju, M.
- Subjects
- *
FIGURES of speech , *NATURAL language processing , *SHORT-term memory , *LONG-term memory , *COMPARATIVE studies - Abstract
• This research aims to identify whether or not transformers work significantly well for figurative language classification and not just literal language classification as well as how well do they generalize over other subclasses of a figurative language class. • The models fine tuned on the dataset used are LSTM, Bi-LSTM models, transformer architecture based models which are BERT (Base & talking Heads), roberta and XLNet. • An accuracy of 81% was obtained by roberta and is able to generalize better in most cases. Efficient and effective methods are required to construct a model to rapidly extractdifferent sentiments from large volumes of text. To augment the performance of the models, contemporary developments in Natural Language Processing (NLP) have been utilized by researchers to work on several model architecture and pretraining tasks. This work explores several models based on transformer architecture and analyses its performance. In this work, the researchersusea dataset to answer the question of whether or not transformers work significantly well for figurative language and not just literal language classification. The results of various models are compared and have come up as a result of research over time. The studyexplains why it is necessary for computers to understand the occurrence of figurative language, why it is yet a challenge and is being intensively worked on to date, and how it is different from literal language classification. This research also covers how well these models train on a specific type of figurative language and generalize on a few other similar types. [Display omitted] [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.