The World Health Organization identifies the overall increasing of noncommunicable diseases as a major issue, such as premature heart diseases, diabetes, and cancer. Unhealthy diets have been identified as the important causing factor of such diseases. In this context, personalized nutrition emerges as a new research field for providing tailored food intake advices to individuals according to their physical, physiological data, and further personal information. Specifically, in the last few years, several types of research have proposed computational models for personalized food recommendation using nutritional knowledge and user data. This paper presents a general framework for daily meal plan recommendations, incorporating as main feature the simultaneous management of nutritional-aware and preference-aware information, in contrast to the previous works which lack this global viewpoint. The proposal incorporates a pre-filtering stage that uses AHPSort as multi-criteria decision analysis tool for filtering out foods which are not appropriate to the current user characteristics. Furthermore, it incorporates an optimization-based stage for generating a daily meal plan whose goal is the recommendation of food highly preferred by the user, not consumed recently, and satisfying his/her daily nutritional requirements. A case study is developed for testing the performance of the recommender system.INDEX TERMS Daily meal plan recommendation, user preferences, nutritional information, multi-criteria decision making, recommender systems.

Currently, epilepsy disease (ED) is considered to be one of the gradual diseases in brain function over a period of several months or years. Seizure status is the primary common cause of ED. The main goal of this paper is to discover the seizure and epilepsy status using the prediction algorithm on the test results received from patient medical reports. This paper proposed an automatic epilepsy diagnostic method based on a self-organization map (SOM) method using a radial basis function (RBF) neural networks approach. The hybrid technique sought to enhance epilepsy diagnosis precision and to decrease the misdiagnosis of seizure disease. The SOM algorithm was employed to differentiate the unknown patterns of the seizure and epilepsy dataset. The experiments were performed on various RBF neural network algorithms with integrated SOM algorithms to predict and classify the standard epilepsy disease dataset. The hybrid method was tested on the UCI epilepsy dataset. The overall detection accuracy with 10-fold cross validation using SOM-RBF method achieved 97.47%. The results were compared with other modern classification techniques for seizure prediction and detection in terms of the evaluation factor. INDEX TERMS Epilepsy disease, SOM, classification, RBF, neural network.

Vehicular ad hoc network (VANET) is a style of high‐mobility mobile ad hoc network where the mobile nodes are vehicles traveling across a road or a street. VANET was proposed to provide safety, comfortability, reliability, and security of vehicles driving. One of the serious challenges is handover (HO) problem that occurs when a vehicle moves from one network area covered by a roadside unit (RSU) to another network area covered by a different RSU. The fast mobility of vehicles and the limited coverage area of the RSU (without overlapping signals) should be considered in providing a seamless HO. This paper presents a comprehensive survey on HO management for VANET based on the new features of fifth‐generation (5G) mobile network technologies. The 5G mobile network technology provides enhanced characteristics that will fit the requirements of real‐time video streaming and assist to design an effective solution for the HO problem. In addition, this paper presents the reasons for HO failures and the limitations of available HO failure solutions. Furthermore, it highlights the potential proposed solutions that will tackle the HO failures. This survey will open up the gate of developing an optimal solution based on 5G for HO problem on VANET that might be used in vehicles manufacturing.

No abstract

No abstract

Access to this document was granted through an Emerald subscription provided by For Authors:If you would like to write for this, or any other Emerald publication, then please use our Emerald for Authors service. Information about how to choose which publication to write for and submission guidelines are available for all. Please visit www.emeraldinsight.com/authors for more information. About Emerald www.emeraldinsight.comWith over forty years' experience, Emerald Group Publishing is a leading independent publisher of global research with impact in business, society, public policy and education. In total, Emerald publishes over 275 journals and more than 130 book series, as well as an extensive range of online products and services. Emerald is both COUNTER 3 and TRANSFER compliant. The organization is a partner of the Committee on Publication Ethics (COPE) and also works with Portico and the LOCKSS initiative for digital archive preservation. AbstractPurpose -The purpose of this paper is to investigate the related issues of physical annotation systems and also to study their historical development. Moreover, the paper provides a taxonomy of physical annotation systems, including augmented reality systems and concludes with future challenges concerning such systems. Design/methodology/approach -The authors first provide a review and a comparison of existing physical annotation systems. The authors' classification of the physical annotation systems is based on the capabilities they provide. Findings -Physical annotation systems evolve as technology progresses. However, there are issues such as cognitive overload, trust, transient associations, and integrating of social networking with physical annotations. Research limitations/implications -As technology develops, physical annotations will become increasingly important in daily life. Hence, there are important research issues to address with regards to physical annotation systems. Practical implications -New better physical annotation systems are needed, which will change the way we do things in life, including personal memory, tourism, commerce, security, games, traffic management, entertainment and health. Social implications -Physical annotation systems will affect the relationships between people, between people and places and between people and things. There is a potential shift in the way people view the physical world, not only as what we see but as what we see through the devices we carry. Originality/value -The paper is an original review of physical annotation systems; there does not seem to be many such reviews on this area. The paper presents a set of future challenges regarding such systems.

Although shill bidding is a common auction fraud, it is however very tough to detect. Due to the unavailability and lack of training data, in this study, we build a high-quality labeled shill bidding dataset based on recently collected auctions from eBay. Labeling shill biding instances with multidimensional features is a critical phase for the fraud classification task. For this purpose, we introduce a new approach to systematically label the fraud data with the help of the hierarchical clustering CURE that returns remarkable results as illustrated in the experiments.

No abstract