2 results
Search Results
Now showing 1 - 2 of 2
Article Citation - WoS: 103Citation - Scopus: 160Cassava Disease Recognition From Low-Quality Images Using Enhanced Data Augmentation Model and Deep Learning(Wiley, 2021) Abayomi-Alli, Olusola Oluwakemi; Damasevicius, Robertas; Misra, Sanjay; Maskeliunas, RytisImprovement of deep learning algorithms in smart agriculture is important to support the early detection of plant diseases, thereby improving crop yields. Data acquisition for machine learning applications is an expensive task due to the requirements of expert knowledge and professional equipment. The usability of any application in a real-world setting is often limited by unskilled users and the limitations of devices used for acquiring images for classification. We aim to improve the accuracy of deep learning models on low-quality test images using data augmentation techniques for neural network training. We generate synthetic images with a modified colour value distribution to expand the trainable image colour space and to train the neural network to recognize important colour-based features, which are less sensitive to the deficiencies of low-quality images such as those affected by blurring or motion. This paper introduces a novel image colour histogram transformation technique for generating synthetic images for data augmentation in image classification tasks. The approach is based on the convolution of the Chebyshev orthogonal functions with the probability distribution functions of image colour histograms. To validate our proposed model, we used four methods (resolution down-sampling, Gaussian blurring, motion blur, and overexposure) for reducing image quality from the Cassava leaf disease dataset. The results based on the modified MobileNetV2 neural network showed a statistically significant improvement of cassava leaf disease recognition accuracy on lower-quality testing images when compared with the baseline network. The model can be easily deployed for recognizing and detecting cassava leaf diseases in lower quality images, which is a major factor in practical data acquisition.Article Citation - WoS: 33Citation - Scopus: 56Smart irrigation system for environmental sustainability in Africa: An Internet of Everything (IoE) approach(Amer inst Mathematical Sciences-aims, 2019) Adenugba, Favour; Misra, Sanjay; Maskeliunas, Rytis; Damasevicius, Robertas; Kazanavicius, EgidijusWater and food are two of the most important commodities in the world, which makes agriculture crucial to mankind as it utilizes water (irrigation) to provide us with food. Climate change and a rapid increase in population have put a lot of pressure on agriculture which has a snowball effect on the earth's water resource, which has been proven to be crucial for sustainable development. The need to do away with fossil fuel in powering irrigation systems cannot be over emphasized due to climate change. Smart Irrigation systems powered by renewable energy sources (RES) have been proven to substantially improve crop yield and the profitability of agriculture. Here we show how the control and monitoring of a solar powered smart irrigation system can be achieved using sensors and environmental data from an Internet of Everything (IoE). The collected data is used to predict environment conditions using the Radial Basis Function Network (RBFN). The predicted values of water level, weather forecast, humidity, temperature and irrigation data are used to control the irrigation system. A web platform was developed for monitoring and controlling the system remotely.
