Plant diseases affect the availability and safety of plants for human and animal consumption and threaten food safety, thus reducing food availability and access, as well as reducing crop yield and quality. There is a need for novel disease detection methods that can be used to reduce plant losses due to disease. Thus, this study aims to diagnose tomato leaf diseases by classifying healthy and unhealthy tomato leaf images using two pre-trained convolutional neural networks (CNNs): Inception V3 and Inception ResNet V2. The two models were trained using an open-source database (PlantVillage) and field-recorded images with a total of 5225 images. The models were investigated with dropout rates of 5%, 10%, 15%, 20%, 25%, 30%, 40%, and 50%. The most important results showed that the Inception V3 model with a 50% dropout rate and the Inception ResNet V2 model with a 15% dropout rate, as they gave the best performance with an accuracy of 99.22% and a loss of 0.03. The high-performance rate shows the possibility of utilizing CNNs models for diagnosing tomato diseases under field and laboratory conditions. It is also an approach that can be expanded to support an integrated system for diagnosing various plant diseases.

No abstract

The objectives of this study were to design and evaluation performance of mechanism for green onion crop handling, as well as, improving the crop quality based on the suggested handling system. However, the suggested handling system consists of feeding unit, trimming unit which based on rotary cutting mechanism, antioxidant unit and tying unit. The following technical parameters had been considered to evaluate the suggesting mechanism: feeding belt speed, feeding rate, cutting disc speed, tying position of onion bundle relative to the cutting disc, angle of cutting disc and discharge rate of ascorbic acid. However, the following technical indicators had been estimated such as machine productivity, trimming efficiency, cutting offset angle of plants, the quality of the final product and the costs of green onion produced by mechanism system. Results indicated that the machine productivity was found to be 316.2 kg/h, handling system efficiency was 75.89 %, the trimming efficiency was 89.15 %, cutting offset angle of plants was 22º, at 12.5 cm/s feeding-belt speed and when 5.6 kg/min feeding rate. With operated at 5.11 m/s cutting disc speed, the optimum tying position during trimming process is 7.5 cm, the wilting coefficient was (0.09 mm/day) at discharge rate of 5 l/h and handling machine reduced the cost of green onion trimming to 1: 2.67 as compared with manual method.

This research develops an automatic algorithm for orange fruits sorting image processing technique in MATLAB (7.8) program. The orange fruits were acquired using a digital camera in illumination chamber. A picture handling system was produced to quantify the volume and size of orange fruits. Surface images of every orange, caught with an advanced camera, were used in the picture preparing method. An effective calculation was structured and actualized in MATLAB (7.8) programming. The volumes figured demonstrated great concurrence with the real volumes dictated by water displacement technique. The coefficient of determination "R2" of orange was more than 98%, and the size code by the MATLAB Graphical User Interface (GUI) for orange fruits was concurrence and fast compared to the manual method for sizing. Image processing strategy palatably evaluated orange volume and size. In like manner, image processing gives a precise, straightforward, fast, and noninvasive technique to evaluate orange fruits volume and size and can be effortlessly executed in arranging of orange fruits amid postharvest processing.

Recent trends in digital comnrunications are opening h;ommercial applications to Code Diviqion Multiple Access (CDMA). The paper presents an analytical model for the effects of tiodinearities and mobile channel on the performance of synchronous QPsK ivi5;icsn ~u~t~p l e -~c c~s s (CDh4.A) systems. The combined eEect of both, the travelling wave tube (TWT) power amplifier exhibits PiM-to-AM an M-to-PM conversion, down-link thermal noise and the multipath fading mobile channel are taken into consid eration in the analysis. System performance in terms of the error probability is explored A key element determining the satellite network complexity and eXiciency is the multiple access scheme selected Considering the environmental conditions, the optimal access scheme s~~u~~ provide the following [l] cknt use o f the available transponder power and bandwidth for single or multiple beam satellites * Resistance to hostile propagation conditions like multipath fading and shadowing * Adaptability to highly variable trafic patterns. * Flexibility to different applications * Adaptability to different network configurations * Compliance with power flux density requirements for user terminals providing minimum R.F interference to other services.'Then: has been increasing interest recently in using direct sequence spread spectrum (DS-SS) e division m~~~i p~e access (CDMA) for corrmercial applications IDS-CDiteA. is propo Key Teatures of C D M are the ~~e i l -k~o w n robustness to narrow-band interference and to frequency selective multipath fading, secure communisation, the low power flux density emission and the possibili to exploit diversity reception [2]. The propagation channei can be classified either uns owed or shadowed channel The aim of this work is to study and test the link perfomlance under the joint effect of both, the transponder (TWTA) nonlinearity, the multipath fading mobile channel and the down-link AWGN. For this purpose, an analytical and simulation were performed for DS-CDMNQPSK for satellite [ 11 and for indoor/terrestrial [ 21, [3] M e r this introduction, section 2 describes DS-CDMA system model. The performance analysis is presented in section 3, Section 4 is concerned with mobile fading channel. A summary and concluding remarks are finally reported in section 5. DS-CDMA SYSTEM MODELThe system model is depicted in Fig. 1. The current approach to dealing with the near-far problem in direct-sequence code-division multiple-access (DS-CDMA) communication systems is to use transmitter power control. The input signal S(t) consists o f a sum of synchronous CDMA.The nonlinear amplifier can be seen as nonlinear pipe, which is especially well known in the satellite comunications. We hrther assume the down-link is an Additive White Gaussian Noise (AWGN) channel. This system model can be viewed as a satellite system with high uplink power which leads to omission of uplink noise.