scholarly journals MYLPHerb-1: A Dataset of Malaysian Local Perennial Herbs for the Study of Plant Images Classification under Uncontrolled Environment

2022 ◽  
Vol 30 (1) ◽  
pp. 413-431
Author(s):  
Kalananthni Pushpanathan ◽  
Marsyita Hanafi ◽  
Syamsiah Masohor ◽  
Wan Fazilah Fazlil Ilahi
Keyword(s):  
Deep Learning ◽  
Medicinal Plants ◽  
Medicinal Plant ◽  
High Performance ◽  
Learning Algorithms ◽  
Automatic Classification ◽  
Medicinal Value ◽  
New Findings ◽  
Perennial Herbs ◽  
Imaging Conditions

Research in the medicinal plants’ recognition field has received great attention due to the need of producing a reliable and accurate system that can recognise medicinal plants under various imaging conditions. Nevertheless, the standard medicinal plant datasets publicly available for research are very limited. This paper proposes a dataset consisting of 34200 images of twelve different high medicinal value local perennial herbs in Malaysia. The images were captured under various imaging conditions, such as different scales, illuminations, and angles. It will enable larger interclass and intraclass variability, creating abundant opportunities for new findings in leaf classification. The complexity of the dataset is investigated through automatic classification using several high-performance deep learning algorithms. The experiment results showed that the dataset creates more opportunities for advanced classification research due to the complexity of the images. The dataset can be accessed through https://www.mylpherbs.com/.

scholarly journals Assessment of Traditional Medicinal Plants Used for Treatment of Human Diseases in Oromia Region, West Shewa Zone: Jeldu Woreda, Ethiopia

2018 ◽  
pp. 1-12
Author(s):  
Chala Dandessa ◽  
Tokuma Negisho ◽  
Gadisa Bekele
Keyword(s):  
Medicinal Plants ◽  
Medicinal Plant ◽  
Plant Species ◽  
Digestive System ◽  
Circulatory System ◽  
System Disease ◽  
Traditional Medicinal Plants ◽  
Medicinal Value ◽  
Mode Of Application ◽  
Infected Skin

Most of the information regarding traditional medicinal plants are still in the hands of traditional vendors, and knowledge of vendors is either lost or passed orally from generation to next generation. This study aimed to survey and document the currently used plants by herbalists in Jeldu Woreda and record their medicinal usage and mode of preparation. Due to most of the vendors of traditional medicinal plants in Jeldu Woreda are alliterated, the data was gathered by supported questionnaire from both vendors and the users of this traditional medicinal plants. The study was limited to traditional medicinal plants which used to treat diseases related to skin, digestive system and circulatory system. The technique used to select the sample from the traditional medicinal plant venders was available sampling since the number of venders in the selected site is not large in number. Thus all the traditional medicinal plant venders in Jeldu Woreda were the respondents of the study. From selected research site about 21 medicinal plants vendorsand 47 users were participated in the study. The finding of the study concluded that there were some plants used to treat some human disease in Jeldu Woreda. Therefore, this research tried to document some medicinal plants used to treat human gastrointestinal, skin and other diseases by including the mode of preparation and how to apply. In this research about 68 respondents have participated. Out of those respondents, 21 were vendors of medicinal plants while 47 were users of medicinal plants. According to data from the medicinal plant vendors and users total of 26 plant species were identified with an identification of the plants’ part with medicinal value. Also, the modes of preparation and mode of application were described in this research. Among this plants species, more than half of them used to treat digestive system disease. From the 26 plant species about half of those plants were recorded for their ability to treat skin disease. The application of the prepared medicine on the skin is mostly by painting the liquidified medicine from plant on infected skin.

Automatic classification and detection of oral cancer in photographic images using deep learning algorithms

2021 ◽  
Author(s):  
Kritsasith Warin ◽  
Wasit Limprasert ◽  
Siriwan Suebnukarn ◽  
Suthin Jinaporntham ◽  
Patcharapon Jantana
Keyword(s):  
Deep Learning ◽  
Oral Cancer ◽  
Learning Algorithms ◽  
Automatic Classification ◽  
Photographic Images

Automatic Classification of Vulnerabilities using Deep Learning and Machine Learning Algorithms

2021 ◽  
Author(s):  
Vishnu Ramesh ◽  
Sara Abraham ◽  
P Vinod ◽  
Isham Mohamed ◽  
Corrado A. Visaggio ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Automatic Classification ◽  
Machine Learning Algorithms

scholarly journals Mapillary based plant distributions of ethnobotanical afforestation.

2019 ◽  
Author(s):  
Anil Kumar Bheemaiah
Keyword(s):  
Deep Learning ◽  
Medicinal Plants ◽  
Open Source ◽  
Source Code ◽  
Semantic Segmentation ◽  
Edible Plants ◽  
Open Source Code ◽  
Scientific Images ◽  
Medicinal Value ◽  
Code Base

Abstract:Mapillary is an open-source code base for the use of GPU based Deep Learning for Semantic Segmentation of wild images. We propose the creation of an autonomous drone for the automated capture of scientific images of medicinal and edible plants to create geotagged maps of plants on Mapillary.com with additional tags on plant sizes, species, and edible and medicinal value. This information is used in the planning of sponsored five or more level afforestation as social and academic forestry for edible and medicinal value. The same research is also useful in planning afforestation on Mars. Keywords: Miyawakis, Mapillary, Seamless Segmentation, FPN, ResNet50, Redtail, Edible and Medicinal Plants, Geotag

scholarly journals Factors influencing the use of Deep Learning for Medicinal Plants Recognition

2021 ◽  
Vol 2089 (1) ◽  
pp. 012055
Author(s):  
J V Anchitaalagammai ◽  
J S Shantha Lakshmi Revathy ◽  
S Kavitha ◽  
S Murali
Keyword(s):  
Deep Learning ◽  
Medicinal Plants ◽  
Medicinal Plant ◽  
Success Rate ◽  
Plant Species ◽  
High Accuracy ◽  
Medicinal Plant Species ◽  
Identification System ◽  
Human Beings ◽  
Physical And Mental Health

Abstract Medicinal plants are very essential in maintaining the physical and mental health of human beings. For providing better treatment, Identification and classification of medicinal plants is essential. In this research paper, main objective is to create a medicinal plant identification system using Deep Learning concept. This system identifies and classifies the medicinal plant species with high accuracy. In this system, five different Indian medicinal plant species namely Pungai, Jamun (Naval), Jatropha curcas, kuppaimeni and Basil are used for identification and classification. The dataset contains 58,280 images, includes approximately 10,000 images for each species. The leaf texture, shape, color, physiological or morphological as the features set for leaf identification. The CNN architecture is used to train the collected dataset and develop the system with high accuracy. As result of this model, 96.67% success rate in finding the corresponding medicinal plant. This model is advisable to use as early detection tool for finding the medicinal plant because of its best success rate

scholarly journals End-to-End Speech Recognition Using Recurrent Neural Network (RNN)

2021 ◽  
Author(s):  
Rene Avalloni de Morais ◽  
Baidya Nath Saha
Keyword(s):  
Deep Learning ◽  
Speech Recognition ◽  
Language Processing ◽  
High Performance ◽  
Short Term Memory ◽  
Learning Algorithms ◽  
Recognition System ◽  
End To End ◽  
Performance Computing

Deep learning algorithms have received dramatic progress in the area of natural language processing and automatic human speech recognition. However, the accuracy of the deep learning algorithms depends on the amount and quality of the data and training deep models requires high-performance computing resources. In this backdrop, this paper adresses an end-to-end speech recognition system where we finetune Mozilla DeepSpeech architecture using two different datasets: LibriSpeech clean dataset and Harvard speech dataset. We train Long Short Term Memory (LSTM) based deep Recurrent Neural Netowrk (RNN) models in Google Colab platform and use their GPU resources. Extensive experimental results demonstrate that Mozilla DeepSpeech model could be fine-tuned for different audio datasets to recognize speeches successfully.

The Era of Advanced Machine Learning and Deep Learning Algorithms for Malware Detection

2022 ◽  
pp. 59-73
Author(s):  
Kwok Tai Chui ◽  
Patricia Ordóñez de Pablos ◽  
Miltiadis D. Lytras ◽  
Ryan Wen Liu ◽  
Chien-wen Shen
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Learning Algorithms ◽  
Malware Detection ◽  
Essential Element ◽  
Future Research ◽  
Detection Algorithms ◽  
Computing Services ◽  
Digital Era ◽  
Future Research Directions

Software has been the essential element to computers in today's digital era. Unfortunately, it has experienced challenges from various types of malware, which are designed for sabotage, criminal money-making, and information theft. To protect the gadgets from malware, numerous malware detection algorithms have been proposed. In the olden days there were shallow learning algorithms, and in recent years there are deep learning algorithms. With the availability of big data for training of model and affordable and high-performance computing services, deep learning has demonstrated its superiority in many smart city applications, in terms of accuracy, error rate, etc. This chapter intends to conduct a systematic review on the latest development of deep learning algorithms for malware detection. Some future research directions are suggested for further exploration.

IMPLEMENTATION POSSIBILITY OF A LIKE DEEP LEARNING ALGORITHMS ON NON-DEEP NETWORKS WITH HIDDEN LAYERS

2020 ◽  
pp. 14-19
Author(s):  
G. V. Shilovskii ◽  
V. M. Yulkova
Keyword(s):  
Deep Learning ◽  
Sparse Coding ◽  
High Performance ◽  
Learning Algorithms ◽  
Gabor Filters ◽  
Classification Performance ◽  
Point Of View ◽  
Test Accuracy ◽  
Backpropagation Algorithm ◽  
Hidden Layer

Learning deep neural networks using the backpropagation algorithm is considered implausible from a biological point of view. Numerous recent publications offer sophisticated models for biologically plausible deep learning options that typically define success as achieving a test accuracy of around 98 % in the MNIST dataset. Here we examine how far we can go in the classification of numbers (MNIST) with biologically plausible rules for learning in a network with one hidden layer and one reading layer. The weights of the hidden layer are either fixed (random or random Gabor filters), or are trained by uncontrolled methods (analysis of main/independent components or sparse coding), which can be implemented in accordance with local training rules. The paper shows that high dimensionality of hidden layers is more important for high performance than global functions retrieved by PCA, ICA, or SC. Tests on the CIFAR10 object recognition problem lead to the same conclusion, indicating that this observation is not entirely problem specific. Unlike biologically plausible deep learning algorithms that are derived from the backpropagation algorithm approximations, we have focused here on shallow networks with only one hidden layer. Globally applied, randomly initialized filters with fixed weights/Gabor coefficients (RP/RGs) of large hidden layers result in better classification performance than training them with unsupervised methods such as principal/independent analysis (PCA/ICA) or sparse coding (SC). Therefore, the conclusion is that uncontrolled training does not lead to better performance than fixed random projections or Gabor filters for large hidden layers.

scholarly journals ESTIMATION OF CURRENT STATUS OF FLORAL BIODIVERSITY AT M.J.B COLLEGE CAMPUS INDORE WITH SPECIAL REFERENCE TO MEDICINAL AND ORNAMENTAL PLANTS

2019 ◽  
Vol 7 (11) ◽  
pp. 75-79
Author(s):  
Saroj Mahajan ◽  
Anita Gangrade
Keyword(s):  
Pain Management ◽  
Medicinal Plants ◽  
Medicinal Plant ◽  
Traditional Knowledge ◽  
Ornamental Plants ◽  
College Campus ◽  
Current Status ◽  
Ancient Science ◽  
Medicinal Value ◽  
Large Numbers

The traditional knowledge started from Vedic Time (1000-5000B.C.) Our epics Ayurveda, Rigvade, Yagurveda were reported Plants used as a medicinal plant.  These medicinal plants were used by Tribal people, villagers, Urban of India. The traditional knowledge of medicinal plants of Tribals are transferred from one gene ration to other generation. Plants have medicinal value too along with ornamental purpose. Indians have been using plants as medicines to treat many diseases like wounds healing, inflammation. The ancient science of Ayurveda and Yoga relied heavily on these plants to treat major conditions, from pain management to weight management and everything in between. The list of medicinal plants too long but some important which are present in our college campus are Aloevera, Awala, Hadjod, Tulsi, Giloy, Neem Arjun, Bel, Ashwagandha. The large numbers of plant i.e. plant vegetations enormous in the college campus which shows the biodiversity of college campus.

Sign in / Sign up

Export Citation Format

Share Document