The agricultural industry has undergone several significant changes over the past few centuries, influenced by the industrial revolutions that have occurred. These changes have progressed from Indigenous agriculture to mechanized farming and the current precision agriculture. While the industrial farming model has increased output, it has also faced various challenges in recent years. Industry 5.0 is expected to have a significant impact on the agriculture sector and potentially lead to a fifth agricultural revolution. In this paper, we examine the motivation behind the industrial and agricultural revolutions 4.0 and 5.0, review the phases of these revolutions that have occurred so far, and offer suggestions for the future. We also provide an overview of the concepts of Industry 4.0 and 5.0, as well as Agriculture 4.0 and 5.0, and discuss the smart strategies that are being implemented in different countries to advance these sectors. Additionally, we focus on the potential applications of Industry 5.0 technologies in the agriculture industry and the research challenges associated with them. Our goal is to provide industrial and agricultural professionals with new research opportunities.

Radio Frequency Identification (RFID) is a technology that not only serves to identify objects but also communicates other information, allowing the real-time monitoring of objects at each step in a mobile object network and the reporting of information on their current status. RFID has become one of the most promising research areas and has attracted increasing attention. This interest sparks a huge amount of literature in the field of RFID. However, the research has been conducted from different perspectives and, as a result, has led to a growing body of knowledge dispersed in different fields. To fill this gap, we carried out a systematic mapping study (SMS) based on a well-established research methodology from the medical and software engineering scientific communities, which aims to study and identify the approaches used, quantity and quality of publications, types of research, and publication trends that shaped the field of RFID research over the past two decades. Its results were based on 219 studies, rigorously selected from among 4294 studies identified in the IEEE Xplore, Scopus, and Web of Science digital libraries and classified according to the research type facet, research area facet, citation facet, and application domain facet. We synthesized and interpreted the results of this SMS to devise future research directions in the RFID domain. This breadth-first SMS provides a solid, comprehensive, and reproducible picture of state-of-the-art RFID technology; the obtained results may have implications for practitioners willing to understand and adopt RFID, including researchers, journal editors, reviewers, and universities. The results obtained revealed that (1) there is a considerable and continuous rise of RFID research activities around different parts of the globe, including in the USA and China, and other English-speaking developed countries, such as Australia, Canada, and the U.K., have a significant influence on this growth; (2) with the technological progress of RFID hardware components and increasingly demanding application domains, RFID technology brings opportunities in some new areas, such as “IoT applications”, “Complex Environments”, and “Industry 4.0”; (3) despite the high number of studies carried out in the field of RFID, especially in the hardware design and performances subfield, a limited number of works have detailed or focused on the “middleware” component of RFID systems, indicating that RFID data processing and management remain an open research issue; and (4) RFID domain challenges, gaps, and feasible future recommendations were highlighted in this study.

Machine learning techniques are being widely used to develop an intrusion detection system (IDS) for detecting and classifying cyber attacks at the network-level and the host-level in a timely and automatic manner. However, Traditional Intrusion Detection Systems (IDS), based on traditional machine learning methods, lacks reliability and accuracy. Instead of the traditional machine learning used in previous researches, we think deep learning has the potential to perform better in extracting features of massive data considering the massive cyber traffic in real life. Generally Mobile Ad Hoc Networks have given the low physical security for mobile devices, because of the properties such as node mobility, lack of centralized management and limited bandwidth. To tackle these security issues, traditional cryptography schemes can-not completely safeguard MANETs in terms of novel threats and vulnerabilities, thus by applying Deep learning methods techniques in IDS are capable of adapting the dynamic environments of MANETs and enables the system to make decisions on intrusion while continuing to learn about their mobile environment. An IDS in MANET is a sensoring mechanism that monitors nodes and network activities in order to detect malicious actions and malicious attempt performed by Intruders. Recently, multiple deep learning approaches have been proposed to enhance the performance of intrusion detection system. In this paper, we made a systematic comparison of three models, Inceprtion architecture convolutional neural network Inception-CNN, Bidirectional long short-term memory (BLSTM) and deep belief network (DBN) on the deep learning-based intrusion detection systems, using the NSL-KDD dataset containing information about intrusion and regular network connections, the goal is to provide basic guidance on the choice of deep learning methods in MANET.

The purpose of this study is to enhance RFID application benefits as a green Airport luggage tracking system. Firstly, by defining RFID architecture, components, functioning and middleware roles. Secondly, by discussing the implementation of Role-Based Access Control as a tool regulating access to RFID data, therefore making authentication methods more robust and flexible. To eventually presenting our UIR middleware solution and BAGTRAC application, allowing easier manipulation and real-time visualization of the luggage transportation process.

Multi criteria decision making methods achieve an unprecedented success in various domains. However, they are not infallible. TOPSIS, one of the most used, does not check the decision makers' assessments consistency nor their level of confidence. To take account of the preeminent uncertainty, we propose a TOPSIS-based method with interval type 2 fuzzy numbers. An improved algorithm is presented to take into account both coherence and confidence level. An illustrative example treating an agriculture supply chain demonstrates a better sorting capacity of the proposed methodology. In addition, the suggested aims prevent rank reversal.