No abstract

We discuss the use of matrix relevance learning, a popular extension to prototype learning algorithms, applied to a three-class classification task of diagnosing cassava diseases from spectral data. Previously this diagnosis has been done using plant image data taken with a smartphone. However for this method disease symptoms need to be visible. Unfortunately for some cassava diseases, once symptoms have manifested on the aerial part of the plant, the root which is the edible part of the plant has been totally destroyed. This research is premised on the hypothesis that diseased crops without visible symptoms can be detected using spectral information, allowing for early interventions. In this paper, we analyze visible and near-infrared spectra captured from leaves infected with two common cassava diseases (cassava brown streak disease and cassava mosaic virus disease) found in Sub-Saharan Africa. We also take spectra from leaves of healthy plants. The spectral data come with thousands of dimensions, therefore different wavelengths are analyzed in order to identify the most relevant spectral bands for diagnosing these disease. To cope with the nominally high number of input dimensions of data, functional decomposition of the spectra is applied. The classification task is addressed using Generalized Matrix Relevance Learning Vector Quantization and compared with the standard classification techniques performed in the space of expansion coefficients.INDEX TERMS Cassava disease diagnosis, feature selection, matrix relevance learning, spectral data.

Early detection of crop disease is an essential step in food security. Usually, the detection becomes possible in a stage where disease symptoms are already visible on the aerial part of the plant. However, once the disease has manifested in different parts of the plant, little can be done to salvage the situation.Here, we suggest that the use of visible and near infrared spectral information facilitates disease detection in cassava crops before symptoms can be seen by the human eye. To test this hypothesis, we grow cassava plants in a screen house where they are inoculated with disease viruses. We monitor the plants over time collecting both spectra and plant tissue for wet chemistry analysis. Our results demonstrate that suitably trained classifiers are indeed able to detect cassava diseases. Specifically, we consider Generalized Matrix Relevance Learning Vector Quantization (GMLVQ) applied to original spectra and, alternatively, in combination with dimension reduction by Principal Component Analysis (PCA). We show that successful detection is possible shortly after the infection can be confirmed by wet lab chemistry, several weeks before symptoms manifest on the plants.

Early disease identification in crops is critical for food security, especially in Sub-Saharan Africa. To identify cassava diseases, professionals visually score the plants by looking for disease indicators on the leaves which is notoriously subjective. Automating the detection and classification of crop diseases could help professionals diagnose diseases more accurately and allow farmers in remote locations to monitor their crops without the help of specialists. Machine learning algorithms have been used in the early detection and classification of crop diseases. However, traditional machine learning algorithms are not calibrated even though they have high accuracy. The ability to provide well-calibrated posterior distributions is one of the most appealing properties of Gaussian processes. Motivated by the current developments in the field of Gaussian Processes, this study proposed a deep Gaussian convolutional neural network model (DGCNN) for the detection and classification of cassava diseases using spectral data. The proposed model uses a hybrid kernel function that is the product of a rational quadratic kernel and a squared exponential kernel. Experimental results revealed that our proposed hybrid kernel function performed better in terms of accuracy of 90.10% when compared to both the squared exponential kernel with an accuracy of 88.01% and the rational quadratic kernel with an accuracy of 88.52%. In our future work, we propose to integrate the Optimised model proposed in this study with the transfer learning approach, a move that may help to improve the model performance.

No abstract

Convolutional neural networks (CNNs) are the gold standard in the machine learning (ML) community. As a result, most of the recent studies have relied on CNNs, which have achieved higher accuracies compared with traditional machine learning approaches. From prior research, we learned that multi-class image classification models can solve leaf disease identification problems, and multi-label image classification models can solve leaf disease quantification problems (severity analysis). Historically, maize leaf disease severity analysis or quantification has always relied on domain knowledge—that is, experts evaluate the images and train the CNN models based on their knowledge. Here, we propose a unique system that achieves the same objective while excluding input from specialists. This avoids bias and does not rely on a “human in the loop model” for disease quantification. The advantages of the proposed system are many. Notably, the conventional system of maize leaf disease quantification is labor intensive, time-consuming and prone to errors since it lacks standardized diagnosis guidelines. In this work, we present an approach to quantify maize leaf disease based on adaptive thresholding. The experimental work of our study is in three parts. First, we train a wide variety of well-known deep learning models for maize leaf disease classification, then we compare the performance of the deep learning models and finally extract the class activation heatmaps from the prediction layers of the CNN models. Second, we develop an adaptive thresholding technique that automatically extracts the regions of interest from the class activation maps without any prior knowledge. Lastly, we use these regions of interest to estimate image leaf disease severity. Experimental results show that transfer learning approaches can classify maize leaf diseases with up to 99% accuracy. With a high quantification accuracy, our proposed adaptive thresholding method for CNN class activation maps can be a valuable contribution to quantifying maize leaf diseases without relying on domain knowledge.

No abstract

Several systematic reviews on mobile device technologies have been undertaken mostly identifying mobile security threats and challenges to corporate organisations' sensitive private information. This paper surveyed the existing level of secure authentication achieved by various mobile device-related frameworks against their listed goals. The solutions and security level of the existing authentication approaches among these categories were compared and improved on the KANYI BYOND framework by introducing a Radius server with the 802.11 authentications supported feature that provides access control to wireless routers, access points, hotspots in EAP/WPA-Enterprise/WPA2-Enterprise modes as means to achieve multiple authentications to mobile device users in corporate networks. Testing and validation of the resulting framework were done with the help of a riverbed modeler and a Denial of Service attack was simulated on all mobile devices' nodes in the designed network. The results indicated that the resulting framework provides multiple authentications and is thought to overcome self-reassuring by mobile device users on the network.