Papers by SRIVALLI DEVI S
MNIST Image: Color to Sound Conversion and Classification Using SVM
Springer eBooks, Nov 9, 2021
Sound is a longitude wave. Light , transverse one. Frequency is the common term in between these ... more Sound is a longitude wave. Light , transverse one. Frequency is the common term in between these two. Using the visible light spectrum and audible sound ranges, the color (light) in an image is converted into the sound for that specific frequency. MNIST dataset containing the handwritten images of digits from zero to nine is used for the research and those images are converted from image (light) to sound (audio). The image is mapped to piano musical audio notes.Then the audio is classified as belonging to disease category image or not, using SVM.The accuracy we got is nearly 83.35% using audio classification.
International Journal of Innovative Technology and Exploring Engineering, 2020
Clustering is defined as grouping similar items . The three types of machine learning techniques ... more Clustering is defined as grouping similar items . The three types of machine learning techniques are supervised, unsupervised and semi-supervised. In unsupervised technique, there are no class labels given to the input data. Clustering is a type of unsupervised learning technique. Recently clustering is applied in many fields such as medicine, agriculture, biology, computers, finance and robotics. Black sigatoka is a bacterial disease occurring commonly in banana plants .The research currently focuses on segmenting the disease area from non-diseased area.The segmentation class training is done via Trainable Weka Segmentation and we also do segmentation using k-means algorithm. In this paper we propose a novel approach for extraction of the black sigatoka diseased area on banana leaves from images using pixel color values and grouping them into their respective clusters accordingly. This is a segmentation cum clustering algorithm. The novel approach has been proposed to overcome the ...
Deep learning is a sub field of machine learning. Learning can be of supervised, semi-supervised ... more Deep learning is a sub field of machine learning. Learning can be of supervised, semi-supervised and unsupervised. There are different types of architectures for deep learning . In this paper we are giving an overview of different architectures that are widely used and their application area. Deep learning is applied in many areas such as image processing, speech recognition, data mining, natural language processing, social network filtering, machine translation, bioinformatics and drug design. IndexTerms Deep learning ;deep learning architecture; machine learning _________________________________________________________________________________________________________________
Features of Image To Audio Converted Tomato Leaf (Bacterial Spot and Healthy Leaf ) Dataset
This csv format dataset consists of audio features of the image dataset converted from from tomat... more This csv format dataset consists of audio features of the image dataset converted from from tomato leaf disease(bacterial spot) and healthy leaf images to audio dataset . This process of converting raw image data into sound data(audio format) is done with Audacity. Then the features from the audio dataset are extracted from pyAudioAnalysis and stored in csv format. This dataset consists of only the features which are already selected using feature selection algorithms.
Tomato_ImagetoAudio
Tomato leaf diseases image dataset converted into audio dataset
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2019
This paper reviews the systems and methods that have been employed in the recognition of the frui... more This paper reviews the systems and methods that have been employed in the recognition of the fruits, vegetables and other plant parts or the entire plant itself .Deep learning algorithms are the current trend in computer vision applications and are broadly employed in agricultural domains for identification of plants and its parts, soil type classification, water resources, harvesting prediction and in fertilizer and pest management. The deep learning algorithm CNN and its types are used widely in current research fields. Higher accuracies are obtained for the detection of plants parts such as leaves and fruits. This can be applied in the field of robotics, agriculture and in some medicinal industries where identification of plants, its parts and where weed detection is necessary. Plant identification is of great value to the agriculturists and medical industries which wants to automate.
International Journal of Innovative Technology and Exploring Engineering, 2020
Agriculture has been evolving since humans started cultivating plants for food consumption. As th... more Agriculture has been evolving since humans started cultivating plants for food consumption. As the agriculture field evolves, the disease control measures too have evolved. Now in this modern era, disease in plants can be easily identified using computers. Data mining is the process of obtaining the useful information from the data. Before the electronic era, diseases in plants are identified just by seeing the symptoms of the plants. Similarly, we can identify the diseases in plants using data mining by supplying the disease symptoms data and classify them accordingly. The purpose of this paper is focusing on the prediction of the diseases from images of black sigatoka disease and uses the following methods: MultilayerPerceptrons, SVM,KNeighborsClassifier,K-NeighborsRegressor, Gaussian Process Regressor, Gaussian Process Classifier, GaussianNB, Decision Tree Classifier, Decision Tree Regressor, linear models such as Linear Regression, RidgeCV, Lasso, ElasticNet, Logistic Regression...
MNIST Image: Color to Sound Conversion and Classification Using SVM
Lecture Notes in Electrical Engineering
Sound is a longitude wave. Light , transverse one. Frequency is the common term in between these ... more Sound is a longitude wave. Light , transverse one. Frequency is the common term in between these two. Using the visible light spectrum and audible sound ranges, the color (light) in an image is converted into the sound for that specific frequency. MNIST dataset containing the handwritten images of digits from zero to nine is used for the research and those images are converted from image (light) to sound (audio). The image is mapped to piano musical audio notes.Then the audio is classified as belonging to disease category image or not, using SVM.The accuracy we got is nearly 83.35% using audio classification.
Springer, Singapore, 2021
Sound is a longitude wave. Light , transverse one. Frequency is the common term in between these ... more Sound is a longitude wave. Light , transverse one. Frequency is the common term in between these two. Using the visible light spectrum and audible sound ranges, the color (light) in an image is converted into the sound for that specific frequency. MNIST dataset containing the handwritten images of digits from zero to nine is used for the research and those images are converted from image (light) to sound (audio). The image is mapped to piano musical audio notes.Then the audio is classified as belonging to disease category image or not, using SVM.The accuracy we got is nearly 83.35% using audio classification.
Agriculture has been evolving since humans started cultivating plants for food consumption. As th... more Agriculture has been evolving since humans started cultivating plants for food consumption. As the agriculture field evolves, the disease control measures too have evolved. Now in this modern era, disease in plants can be easily identified using computers. Data mining is the process of obtaining the useful information from the data. Before the electronic era, diseases in plants are identified just by seeing the symptoms of the plants. Similarly, we can identify the diseases in plants using data mining by supplying the disease symptoms data and classify them accordingly. The purpose of this paper is focusing on the prediction of the diseases from images of black sigatoka disease and uses the following methods:
Clustering is defined as grouping similar items. The three types of machine learning techniques a... more Clustering is defined as grouping similar items. The three types of machine learning techniques are supervised, unsupervised and semi-supervised. In unsupervised technique, there are no class labels given to the input data. Clustering is a type of unsupervised learning technique. Recently clustering is applied in many fields such as medicine, agriculture, biology, computers, finance and robotics. Black sigatoka is a bacterial disease occurring commonly in banana plants .The research currently focuses on segmenting the disease area from non-diseased area.The segmentation class training is done via Trainable Weka Segmentation and we also do segmentation using k-means algorithm. In this paper we propose a novel approach for extraction of the black sigatoka diseased area on banana leaves from images using pixel color values and grouping them into their respective clusters accordingly. This is a segmentation cum clustering algorithm. The novel approach has been proposed to overcome the shortfall of k-means clustering when segmenting using automatic value selection for k-means by using silhouette values.Using this novel approach its easy to cluster and segment at the same time. The segmented image from this algorithm can be used in disease classification tasks.
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2019
This paper reviews the systems and methods that have been employed in the recognition of the frui... more This paper reviews the systems and methods that have been employed in the recognition of the fruits, vegetables and other plant parts or the entire plant itself .Deep learning algorithms are the current trend in computer vision applications and are broadly employed in agricultural domains for identification of plants and its parts, soil type classification, water resources, harvesting prediction and in fertilizer and pest management. The deep learning algorithm CNN and its types are used widely in current research fields. Higher accuracies are obtained for the detection of plants parts such as leaves and fruits. This can be applied in the field of robotics, agriculture and in some medicinal industries where identification of plants, its parts and where weed detection is necessary. Plant identification is of great value to the agriculturists and medical industries which wants to automate.
Uploads
Papers by SRIVALLI DEVI S