Medicinal Plant Recognition based on CNN and Machine Learning

Dudi, Bhanuprakash

doi:10.30534/ijatcse/2019/03842019

Cited by 31 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Their algorithm worked on smali files. They employed LSTM-a deep learning technique [16], [17] to make the system learn from opcode sequences to classify an app as malicious or benign. As entire raw opcode sequence may not possess malicious behavior, they also build the filter to separate the opcode subsequence which does not contain malicious behavior.…”

Section: Related Workmentioning

confidence: 99%

Classification of Android Malware using its Image Sections

Thakur¹

2020

IJATCSE

View full text Add to dashboard Cite

Privacy is a big concern as hackers are stealing data and misusing it by engineering malicious applications. There is a rapid increase in malware attacks like spyware, premium-rate SMS Trojans, botnets, aggressive adware, privilege escalation, and banking trojans which were distributed through the applications present on Google play store as well as unofficial application stores. Malware uses dominant techniques such as packing, encryption, a transformation of code, environment-aware approaches to evade detection. The traditional methods such as static and dynamic analysis of Android malware consume high computation resources and time. Moreover, cybercriminals use automation tools to generate numerous malware variants of the same family. This paper proposes a method to advance the classification of Android malware using visualization techniques. The visualization technique tends to transform Android malware into different image sections. The GIST algorithm is used to extract the features from the image sections. The extracted features are classified using machine learning algorithms such as K-Nearest Neighbors, Support Vector Machines, Random Forests, and Naive Bayes. This study evaluates the classification performance metrics of each classifier against every image file section. Experiment results show that the Android manifest image files have achieved a high accuracy of 92.7% with the SVM classifier.

show abstract

Section: Related Workmentioning

confidence: 99%

Classification of Android Malware using its Image Sections

Thakur¹

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…Figure 4 shows general methodology of circuit sketch acknowledgment. We acquired some of circuit parts utilizing end point investigation [22,25,28]. In any case, we have to order remaining segment districts.…”

Section: Recognition Processmentioning

confidence: 99%

Synthesizing of Hand-drawn Electrical Circuits Using Machine Learning Techniques

2020

IJETER

View full text Add to dashboard Cite

A circuit outline in electrical science is a graphical representation of an electrical circuit with a fundamental picture to address the electrical fragments and their accessibility between parts. For example, an electrical diagram resistor has a value and is connected to two separate sections. These electrical components can be seen by the people from their new understanding. From here on, you can insert the portions into your console to play the relevant game, although the diagram is confused by vast quantities of fragments. If an occurrence with uncommon graphics may occur, this is not a feasible method. In this paper we have suggested another technique for circuit validation by which the computer can arrange a vertical circuit contour. There is an electrical circuit by integrating different symbols of components and their connections. This is a technique for fragmenting images that perceives the diagrams of the hand drawing circuit. The handdrawn image will be inspected, and the filtered image of the hand-drawn circuit board prepared so that the unwanted pieces in the graph can be removed and converted into bilayers. An electrical circuit typically consists of portion images and their memberships. This project proposes a changed validation system for the hand drawing of electric circuits that are subject to the division of images and game schemes. --part of the picture is removed from the associated wires, so each part of the image is verified by a distinctive process. The machine output is a netlist that senses the types of pictures and their interconnections. You may use the netlist to render Printed Circuit Board (PCB) circuit schemes

show abstract

“…The recommended method is image-processing based totally and additionally will be very based totally on K-Means clustering technique in addition to ANN. This approach includes four primary stages: after pre-processing phase, the photos available are segmented using K suggests strategies after that a few shape functions are removed in which they may be lengthy beyond via a pre licensed neural community [13,20,21] In this studies look at, a plant situation based totally definitely leaf popularity method changed into brought on this paper. The suggested formula ends up universities on five sort of maize infection.…”

Section: Literature Surveymentioning

confidence: 99%

Disease Identification and Intimation of Cauli Flower Crop through Tensor Flow and Open CV

2020

IJETER

View full text Add to dashboard Cite

In India 70% of the agriculture field is based on crops only. It might be directly or by indirectly incorporated. So the management of the crops is most important activity. For survival of the crops from many more attacks of diseases, it will take more time to observe by manually. From many more years most of the people tried to do the same thing in different ways that is manual intervention. Each method is having its advantages and disadvantages too. We tried it at most thing has to be done to eliminate the manual intervention by introducing the advanced technologies in to the agriculture field. By using raspberry pi micro-controller and with python we can monitor the crop fields and we get the accurate results with minimal hardware. In this project we are using pi controller and with python software for image processing. In this project we are introducing the cloud storage for storing the data from live feed for the futuristic purpose. All the time we cannot get the past data from the live fields. For understanding the diseases data base and for the analysis we need data has to be mined in the cloud storage. So that we can retrieve the data whenever we need. And for the other future researches also. One more way to collect the data from the files first is we should know the data set types. After knowing what types of dataset, we need, then we should search for the same type of crop but we don't know which place we can get the same crop data set. Even though if we found it owner of the crop fields has to agree to collect the data sets from fields. Because he don't have the knowledge of these all collection he may have fear what if crop may get damaged. So first of all we should clear his fearful thoughts, then only we can get the permission to collect the live feeding of the crop. After that we should keep our hardware setup first in the crop field. After setting up us should start collect the data. Before starting the work we should know clearly about the data sets, how we are going to analysis the data sets, and the storage type of the data. How we are collecting the data and how we are storing the data is important. It may be either local storage, global storage or live feed etc...

show abstract

Medicinal Plant Recognition based on CNN and Machine Learning

Cited by 31 publications

References 9 publications

Classification of Android Malware using its Image Sections

Classification of Android Malware using its Image Sections

Synthesizing of Hand-drawn Electrical Circuits Using Machine Learning Techniques

Disease Identification and Intimation of Cauli Flower Crop through Tensor Flow and Open CV

Contact Info

Product

Resources

About