scholarly journals Disease Detection using CNN and Transfer Learning

2021 ◽  
pp. 617-621
Author(s):  
Sachin Kumar Jha ◽  
Aditya Raj ◽  
Rahul Kumar ◽  
Vikash Vishal
Keyword(s):  
Machine Learning ◽  
Urban Area ◽  
Rural Area ◽  
Transfer Learning ◽  
Rural Areas ◽  
Plant Disease ◽  
Fruits And Vegetables ◽  
Disease Detection ◽  
Proposed Model ◽  
Learning Technique

Plant disease have great affect over the productivity of fruits and vegetables in rural area. It is estimated that pest and diseases cause loss of 20% crops in rural area vs 10% in urban area. One of the main reasons of this loss is lack of knowledge to identity the disease, its cause and its treatment. To overcome this problem in most economical way, we have used machine learning to identify the disease and suggest remedies to the farmers in rural areas. The proposed model simply accepts an image of leaf with unknown disease, identify the disease and suggest remedies. In this model we are using transfer learning technique to train our model in least amount of time over relatively smaller data. We have achieved up to 98.8% accuracy in identifying 38 different diseases among 14 different fruits and vegetables.

scholarly journals The seasonal variability of the amount of global solar radiation reaching the ground in urban and rural areas on the example of Warsaw and Belsk

2016 ◽  
Vol 20 (4) ◽  
pp. 29-37
Author(s):  
Kinga Nelken ◽  
Kamil Leziak
Keyword(s):  
Solar Radiation ◽  
Urban Area ◽  
Rural Area ◽  
Rural Areas ◽  
Meteorological Data ◽  
Global Solar Radiation ◽  
Urban Station ◽  
Reverse Relationship ◽  
Urban And Rural Areas ◽  
The Relationship

AbstractThe aim of this paper is to determine the contemporary differences in the inflow of global solar radiation in Warsaw (urban station) and Belsk (rural station). The meteorological data used comprised daily sums of global solar radiation (in MJ•m−2) and the duration of sunshine (in hours) for the period 2008 2014. On clear days in spring and summer, the rural area receives more solar radiation in comparison to the urban area, whereas in autumn a reverse relationship occurs. On cloudy days in all seasons, the rural area receives more solar radiation than the urban area, and the relationship is the strongest in winter. Differences between urban and rural areas on cloudy days are smaller than those observed on clear days.

scholarly journals Assessment of Women participation in Agriculture in Vavuniya district, Sri Lanka

2016 ◽  
Vol 3 (3) ◽  
pp. 159-162
Author(s):  
Gopalakrishnan Tharani ◽  
Mohamed Sameem Roshan Akther ◽  
Nanthakumaran Ananthini
Keyword(s):  
Decision Making ◽  
Sri Lanka ◽  
Multiple Regression ◽  
Urban Area ◽  
Rural Area ◽  
Rural Women ◽  
Rural Areas ◽  
Agricultural Activities ◽  
Urban And Rural Areas ◽  
Women Participation

An attempt was made to assess the women contribution towards agriculture in Vavuniya district, Sri Lanka. 60 farm family households' women were randomly selected from rural and urban area of Kovilkulam AI region of Vavuniya district in Sri Lanka and the data were collected by constructed questionnaire. The objectives of this study are to identify the factors contributing women participation in agriculture, to identify the constraints faced by the women in participating agriculture and to evaluate the women participation in decision making activity in agriculture. Minitab 15 and MS excel were used for data analysis. The level of women participation in agricultural activities was found out using chi-square test and the factors contributing for women participation in agricultural activities were identified using multiple regression analysis in urban and rural areas separately (α=0.05). The results revealed that 90% of the rural women respondents and 50% of the urban respondents participated in the agricultural activities which is a significant difference. The mean values of women participation in agricultural activities in urban and rural areas were 77 hours and 836 hours per annum respectively. The multiple regression model for women participation in urban area found that the participation of women negatively correlated with status of employment, age and education level (p=0.000). In rural area, age and educational level were negatively influencing on women participation in agricultural activities (p=0.000). R-square values of fitted regression models were 72 % and 91% in urban and rural area respectively 72% and 91% variation in respective women participation were explained by these models. The obstacles for the women in participation in agricultural activities were reported as lack of knowledge and training in agriculture field, family burden, cultural and social barriers and physical constraints. 60% of women from rural areas and 90% of women from urban areas were involved in decision making especially in the selection of crops and varieties for planting and livestock rearing. Enhancing the awareness and the technical knowledge to the women in the field of agriculture would contribute to increase income from agriculture at household level, district level and finally at national level. Int. J. Soc. Sc. Manage. Vol. 3, Issue-3: 159-162

scholarly journals Kelainan refraksi pada siswa SMP daerah pedesaan

e-CliniC ◽  
2016 ◽  
Vol 4 (2) ◽  
Author(s):  
Indo Mamesah ◽  
Josefien S. M. Saerang ◽  
Laya M. Rares
Keyword(s):  
High School Students ◽  
Visual Impairment ◽  
Urban Area ◽  
Rural Area ◽  
Junior High School ◽  
Rural Areas ◽  
Functional Limitation ◽  
Visual Field Loss ◽  
School Students ◽  
Cross Sectional

Abstract: Visual impairment is defined as a functional limitation of the eye/eyes or visual system and can manifest in decreased visual acuity or contrast sensitivity, visual field loss, photophobia, visual distortion, visual perceptual difficulties, or a combination of them. Examination of the eye and vision assessment are very important to detect conditions that can cause blindness and serious systemic conditions, which cause problems in school performance, or at a more severe level, life threatening. This study aimed to obtain the occurence of refractive anomalies among junior high school students in rural areas. This was an analytical observational study with a cross-sectional design. The study was conducted in SMP I Wori (rural area) and SMP I Airmadidi (urban area). There were 60 respondents; 30 respondents of each school. Distributions of respondent genders were nearly the same for both schools; the number of females was higher than males. The majority of SMP I Airmadidi students were 11 years old (36.7%), meanwhile the majority of SMP Wori students were 13 years (50%). Most student complaints in SMP I Airmadidi were itchy eyes and drowsiness (16.7%), meanwhile in SMP I Wori was headache (18.4%). Visual impairment was found in 16.6% of students of SMP I Airmadidi, meanwhile in SMP I there was no student with refractive anomaly. Conclusion: There was no refractive anomaly found among students of rural area, however, among students of urban area myopia was the refractive anomaly found.Keywords: refractive anomalyAbstrak: Gangguan penglihatan didefinisikan sebagai suatu keterbatasan fungsional pada mata atau kedua mata atau sistem visual yang dapat bermanifestasi terhadap penurunan ketajaman penglihatan atau sensitifitas kontras, hilangnya lapangan penglihatan, photofobia, distorsi visual, kesulitan perseptual visual atau kombinasi dari semua diatas. Pemeriksaan mata dan penilaian penglihatan sangat penting untuk mendeteksi kondisi yang dapat menyebabkan kebutaan dan kondisi sistemik serius, yang memicu masalah performa di sekolah, atau pada tingkat yang lebih berat, mengancam kehidupan anak. Penelitian ini bertujuan untuk mengetahui gambaran kelainan refraksi pada anak SMP di daerah pedesaan. Jenis penelitian ini analitik observasional dengan desain potong lintang. Penelitian dilakukan di SMPN I Wori (daerah luar Minahasa Utara/pedesaan) dan SMPN I Airmadidi (kota Kabupaten Minahasa Utara), dan diperoleh 60 responden penelitian. Distribusi jenis kelamin responden kedua sekolah hampir sama dimana jumlah perempuan lebih banyak dari laki-laki. Usia terbanyak di SMPN I Airmadidi ialah 11 tahun (36,7%) sedangkan di SMPN Wori 13 tahun (50%). Keluhan terbanyak siswa di SMPN I Airmadidi ialah mata gatal dan rasa kantuk (16,7%), sedangkan di SMPN I Wori ialah sakit kepala (18, 4%). Gangguan penglihatan ditemukan pada responden di SMPN I Airmadidi sebanyak 16,6 % sedangkan di SMPN I tidak ditemukan kelainan visus. Simpulan: Tidak ditemukan adanya gangguan refraksi pada siswa SMP di daerah pedesaan. Kelainan refraksi miopia ditemukan pada siswa SMP di perkotaan.Kata kunci: gangguan refraksi

scholarly journals Applying a Deep Q Network for OpenAIs Car Racing Game

2020 ◽  
Author(s):  
Ali Fakhry
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Transfer Learning ◽  
State Of The Art ◽  
Learning Techniques ◽  
Car Racing ◽  
Custom Made ◽  
Learning Technique ◽  
Reward Threshold

The applications of Deep Q-Networks are seen throughout the field of reinforcement learning, a large subsect of machine learning. Using a classic environment from OpenAI, CarRacing-v0, a 2D car racing environment, alongside a custom based modification of the environment, a DQN, Deep Q-Network, was created to solve both the classic and custom environments. The environments are tested using custom made CNN architectures and applying transfer learning from Resnet18. While DQNs were state of the art years ago, using it for CarRacing-v0 appears somewhat unappealing and not as effective as other reinforcement learning techniques. Overall, while the model did train and the agent learned various parts of the environment, attempting to reach the reward threshold for the environment with this reinforcement learning technique seems problematic and difficult as other techniques would be more useful.

scholarly journals A Review on Advances in Automated Plant Disease Detection

2021 ◽  
Vol 11 (4) ◽  
pp. 251-264
Author(s):  
Radhika Bhagwat ◽  
Yogesh Dandawate
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Plant Disease ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Plant Diseases ◽  
Detection Methods ◽  
Economic Losses ◽  
Disease Detection ◽  
Range Images

Plant diseases cause major yield and economic losses. To detect plant disease at early stages, selecting appropriate techniques is imperative as it affects the cost, diagnosis time, and accuracy. This research gives a comprehensive review of various plant disease detection methods based on the images used and processing algorithms applied. It systematically analyzes various traditional machine learning and deep learning algorithms used for processing visible and spectral range images, and comparatively evaluates the work done in literature in terms of datasets used, various image processing techniques employed, models utilized, and efficiency achieved. The study discusses the benefits and restrictions of each method along with the challenges to be addressed for rapid and accurate plant disease detection. Results show that for plant disease detection, deep learning outperforms traditional machine learning algorithms while visible range images are more widely used compared to spectral images.

Classification of plant diseases using machine and deep learning

2021 ◽  
Vol 11 (1) ◽  
pp. 491-508
Author(s):  
Monika Lamba ◽  
Yogita Gigras ◽  
Anuradha Dhull
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Plant Disease ◽  
Nearest Neighbor ◽  
Early Recognition ◽  
Activation Function ◽  
Plant Diseases ◽  
Support Vector ◽  
Specificity And Sensitivity ◽  
Proposed Model

Abstract Detection of plant disease has a crucial role in better understanding the economy of India in terms of agricultural productivity. Early recognition and categorization of diseases in plants are very crucial as it can adversely affect the growth and development of species. Numerous machine learning methods like SVM (support vector machine), random forest, KNN (k-nearest neighbor), Naïve Bayes, decision tree, etc., have been exploited for recognition, discovery, and categorization of plant diseases; however, the advancement of machine learning by DL (deep learning) is supposed to possess tremendous potential in enhancing the accuracy. This paper proposed a model comprising of Auto-Color Correlogram as image filter and DL as classifiers with different activation functions for plant disease. This proposed model is implemented on four different datasets to solve binary and multiclass subcategories of plant diseases. Using the proposed model, results achieved are better, obtaining 99.4% accuracy and 99.9% sensitivity for binary class and 99.2% accuracy for multiclass. It is proven that the proposed model outperforms other approaches, namely LibSVM, SMO (sequential minimal optimization), and DL with activation function softmax and softsign in terms of F-measure, recall, MCC (Matthews correlation coefficient), specificity and sensitivity.

Sign in / Sign up

Export Citation Format

Share Document