Early detection and identification of plant diseases from leaf images using machine learning is an important and challenging research area in the field of agriculture. There is a need for such kinds of research studies in India because agriculture is one of the main sources of income which contributes seventeen percent of the total gross domestic product (GDP). Effective and improved crop products can increase the farmer’s profit as well as the economy of the country. In this paper, a comprehensive review of the different research works carried out in the field of plant disease detection using both state-of-art, handcrafted-features- and deep-learning-based techniques are presented. We address the challenges faced in the identification of plant diseases using handcrafted-features-based approaches. The application of deep-learning-based approaches overcomes the challenges faced in handcrafted-features-based approaches. This survey provides the research improvement in the identification of plant diseases from handcrafted-features-based to deep-learning-based models. We report that deep-learning-based approaches achieve significant accuracy rates on a particular dataset, but the performance of the model may be decreased significantly when the system is tested on field image condition or on different datasets. Among the deep learning models, deep learning with an inception layer such as GoogleNet and InceptionV3 have better ability to extract the features and produce higher performance results. We also address some of the challenges that are needed to be solved to identify the plant diseases effectively.

Article targets to show potential of software goniophotometer from point of view calculation of the luminous flux leads to the upper hemisphere from road lighting system. Basis for this article was real model of blocks of flats in Frydek-Mistek. Software goniophotometer was originally checked in terms of accuracy for calculation direct and reflected part of the luminous flux [1]. In next step was creating of basic model formed from several objects including buildings and road lighting system realized by five luminaires [2]. Software upgrade allows possibility of inserting calculation grid in sphere shape. These points represented normal illuminance in direction to the middle of sphere and behave like an imagine luxmeter sensors. Aim of implementation this net is update simulation program for calculation of the luminous flux radiated to the upper hemisphere from artificial lighting systems as basis for next astronomic calculation which are deeply focused on night sky luminance description [3]. Using this model will possible to do models of the artificial light radiation of whole towns contains not only road light systems, but other artificial light sources too. Principle is to include radiation characteristics of these big units to LDT file as a one luminaire with information about luminous flux and shape of luminous intensity distribution. This LDT file could be used for next calculations which will evaluate influence of big light sources to night sky luminance.

The article deals with the testing of the beta version extension of the BUILDING DESIGN computational programme. The superstructure was conceived as the possibility of inserting a network of calculating points in the shape of a sphere. Points showing normal illuminance towards the centre of the sphere. The goal of implementing such a network of calculation points is to extend the possibilities of a computational program for modelling the luminous intensity curves of existing luminaires as well as newly composed of many discrete optical systems installed in different directions of radiation and having different luminous fluxes in order to achieve the desired resultant characteristic already in a model form. There will be considerable cost savings in the development of such types of luminaires. In the future, the use of this network of computing points and the modelling of the light output emitted into the upper half-space from outdoor lighting systems is the goal. It will be the basis for further astronomical calculations that focus on distracting light and increased sky luminance.

The paper presents the development of a low-cost luxmeter designed for usage in automatic applications for continual (long-term) measurement of illuminance. The measured information is used to adjust the level of lighting systems of artificial lighting on railways (platforms, marshalling yard, tracks etc.). The reason of this measuring device is a requirement for massive deployment of dimmable lighting systems for railways, in order to limit the maximum energy consumption. Due to the requirements for its deployment it is necessary to put particular emphasis on its low cost, reliability and universality, not accuracy. The concept of the device is designed so that it can transmit measured data especially in the FARCOM-ECO system, which is used to control of technological processes on the railways in the Czech Republic.