Search

Copyright of Iraqi Journal of Agricultural Sciences is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Misr Journal of Agricultural Engineering is the property of Egyptian National Agricultural Library (ENAL) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Convolutional Neural Networks (CNN), as artificial intelligence (AI) technology, is vital in identifying and recognizing features that affect cropping from images. Therefore, the current research uses CNN to diagnose tomato stress through thermal images. The paper presents four models of deep learning for image training: VGG16, Inception ResNet V2, Inception V3, and SVGGNet. The normal and Stress tomato leaf images taken from the field (thermal images) were trained on the four models. Transfer learning was used to train the VGG16, Inception ResNet V2, and Inception V3 models, while the SVGGNet model was trained from scratch. The dropout ratios of the models were studied at the ratios of 20, 40, 60, and 80% at an image size of 299 x 299 pixels. The most important results when training limited-size thermal images to diagnose thermal stress were the superiority of the SVGGNet model that was trained from the beginning over other models at all the dropout ratios that were studied. The best result was at a dropout of 40%, and its results came with an accuracy of 96.88% and a loss of 0.19. It has been shown that it is not preferable to train small-scale thermal data using transfer learning, but it is preferable to train the model from scratch. [ABSTRACT FROM AUTHOR]

Copyright of Misr Journal of Agricultural Engineering is the property of Egyptian National Agricultural Library (ENAL) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Innovative daylighting systems (IDS) are used to deliver daylight into windowless spaces and building cores. Cleaning the exposed surfaces is essential for maintaining their efficiency because the accumulation of dirt inhibits their effectiveness. However, a review of the literature has indicated that this issue has not received the attention it deserves. This study reviews the cleaning methods currently used for solar devices and conventional daylighting systems. It also presents the technologies that can currently be employed to produce an IDS cleaning system, and suggests six cleaning mechanisms and 12 cleaning systems that suit different types of IDS in various operating circumstances. These include air-blowing, water-jetting, dragging-contact, rotary-contact and certain aid treatments. Air-cleaning and washing with water can both be used to restore functionality. Wiping and scrubbing are effective for increasing efficiency. Further productivity can be obtained by drying solar collectors after they have been washed. The systems suggested herein can be developed using already available technologies in order to achieve the ultimate in IDS efficiency restoration. However, before this can be done, the economic, environmental and operational aspects, in addition to potential levels of efficacy and applicability, must be assessed. [ABSTRACT FROM AUTHOR]

Daylight guidance systems deliver daylight into remote parts of buildings. However, they still lack market penetration. The primary difficulty lies within the installation process. Daylight guidance systems use light ducts to distribute daylight, which occupy significant amounts of space. The integration of light ducts and heating, ventilation and air conditioning ducts is a promising solution. This study compares the differences and similarities of the two ducting systems, suggests an integrated system and evaluates the potential of and challenges faced by the proposed dual ducting system. A schematic application is completed and demonstrates that the dual ducting system has the economic potential to reduce costs, avoid conflicts between building systems and simplify the installation of daylight guidance systems. [ABSTRACT FROM AUTHOR]

This paper reviews developments in hybrid light guidance systems. In these daylight and electric light are simultaneously delivered into a building where they are combined and distributed via luminaires. The technology used in hybrid systems, both conceptual and realised, is discussed. The review speculates as to their likely performance in terms of daylight delivery; capital and running costs; user reaction to the systems; potential impact of the systems on the building which they light; and suitable design methods. It is noted that a substantial amount of work remains before the potential of hybrid systems may be realised, notably on their long-term economics and feasibility in different geographic locations. [ABSTRACT FROM AUTHOR]