Aboul Ella Hassanien (Abo)

Powdery mildew caused by Erysiphe graminis f. sp. tritici is one of the most harmful disease causing great losses in wheat yield. Currently, thermal spectral sensing of plant disease under different environmental conditions in field is a cutting-edge research. Objectives of this study were to assess thermal imaging of normal and infected leaves for early detection of powdery mildew in wheat after the artificial infection with Erysiphe graminis fungus in a pot experiment under greenhouse conditions. Pot experiment lasting for 30 days was conducted. Additionally, wheat seedlings were artificially infected with pathogen at 10 days from sowing. This is the first study in Egypt to use thermal imaging technique for early detection of powdery mildew disease on leaf using thermal signatures of artificial infected leaves as a reference images. Particularly, the variations in temperature between infected and healthy leaves of wheat and the variation between air and leaf-surface temperatures under greenhouse conditions were sensed for early detection of disease. Results revealed that infection with powdery mildew pathogen induced changes in leaf temperature (from 0.37 °C after one hour from the infection to 0.78 °C at 21 days after infection with the pathogen) and metabolism, contributing to a distinct thermal signature characterizing the early and late phases of the infection.

Complex social networks analysis is an important research trend, which basically based on community detection. Community detection is the process of dividing the complex social network into a dynamic number of clusters based on their edges connectivity. This paper presents an efficient Elephant Swarm Optimization Algorithm for community detection problem (EESO) as an optimization approach. EESO can define dynamically the number of communities within complex social network. Experimental results are proved that EESO can handle the community detection problem and define the structure of complex networks with high accuracy and quality measures of NMI and modularity over four popular benchmarks such as Zachary Karate Club, Bottlenose Dolphin, American college football and Facebook. EESO presents high promised results against eight community detection algorithms such as discrete krill herd algorithm, discrete Bat algorithm, artificial fish swarm algorithm, fast greedy, label propagation, walktrap, Multilevel and InfoMap.

World Wide Web (WWW) provides interlinked hypertext documents (Web pages) that may contain text, images, videos, and other multimedia. WWW is growing at a remarkable rate and finding appropriate information can therefore be challenging. Web information retrieval deals with the search for documents, for information within documents and for metadata about documents, as well as that of searching databases in the WWW. Web information retrieval is an interdisciplinary science and deals with this challenge by exploiting various information technologies and computational intelligence approaches to design the next generation of web-information retrieval technologies. This Volume provides reviews of cutting-edge technologies and insights into various topics related to XML-based and multimedia information access and retrieval under the umbrella of Web Intelligence, it also illustrates how organizations can gain competitive advantages by applying new techniques in real-world scenarios. The 18 chapters are arranged in three parts and have identified several important problem formulations in the area of Web and multimedia information querying, modelling user interactions and advanced information security and access control models. Chapters are authored by reputed scientists in the field and all articles are self-contained to provide the greatest reading flexibility.

This book presents cutting-edge research in the field of semantic technologies. Its seventeen chapters are arranged into four parts and identify interdisciplinary challenges in the areas of the Semantic Web, artificial intelligence, and knowledge-based services. The chapters provide analysis and insight into semantic Web techniques and are authored by reputable scientists in the field. All articles are self-contained to provide the greatest reading flexibility and aim to serve as a reference for researchers in the Semantic Web community.