Internet of Things (IoT) as refers to a network of devices that have the ability to connect, collect and exchange data with other devices over the Internet. IoT is a revolutionary technology that have tremendous applications in numerous fields of engineering and sciences such as logistics, healthcare, traffic, oil and gas industries and agriculture. In agriculture field, the farmer still used conventional agriculture methods resulting in low crop and fruit yields. The integration of IoT in conventional agriculture methods has led to significant developments in agriculture field. Different sensors and IoT devices are providing services to automate agriculture precision and to monitor crop conditions. These IoT devices are deployed in agriculture environment to increase yields production by making smart farming decisions and to collect data regarding crops temperature, humidity and irrigation systems. However, the integration of IoT and smart communication technologies in agriculture environment introduces cyber security attacks and vulnerabilities. Such cyber attacks have the capability to adversely affect the countries’ economies that are heavily reliant on agriculture. On the other hand, these IoT devices are resource constrained having limited memory and power capabilities and cannot be secured using conventional cyber security protocols. Therefore, designing robust and efficient secure framework for smart agriculture are required. In this paper, a Cyber Secured Framework for Smart Agriculture (CSFSA) is proposed. The proposed CSFSA presents a robust and tamper resistant authentication scheme for IoT devices using Constrained Application Protocol (CoAP) to ensure the data integrity and authenticity. The proposed CSFSA is demonstrated in Contiki NG simulation tool and greatly reduces packet size, communication overhead and power consumption. The performance of proposed CSFSA is computationally efficient and is resilient against various cyber security attacks i.e., replay attacks, Denial of Service (DoS) attacks, resource exhaustion.
The Internet of Things (IoT) supports human endeavors by creating smart environments. Although the IoT has enabled many human comforts and enhanced business opportunities, it has also opened the door to intruders or attackers who can exploit the technology, either through attacks or by eluding it. Hence, security and privacy are the key concerns for IoT networks. To date, numerous intrusion detection systems (IDS) have been designed for IoT networks, using various optimization techniques. However, with the increase in data dimensionality, the search space has expanded dramatically, thereby posing significant challenges to optimization methods, including particle swarm optimization (PSO). In light of these challenges, this paper proposes a method called improved dynamic sticky binary particle swarm optimization (IDSBPSO) for feature selection, introducing a dynamic search space reduction strategy and a number of dynamic parameters to enhance the searchability of sticky binary particle swarm optimization (SBPSO). Through this approach, an IDS was designed to detect malicious data traffic in IoT networks. The proposed model was evaluated using two IoT network datasets: IoTID20 and UNSW-NB15. It was observed that in most cases, IDSBPSO obtained either higher or similar accuracy even with less number of features. Moreover, IDSBPSO substantially reduced computational cost and prediction time, compared with conventional PSO-based feature selection methods.
Artificial Intelligence (AI) and Machine Learning (ML) are envisaged to play key roles in 5G networks. Efficient radio resource management is of paramount importance for network operators. With the advent of newer technologies, infrastructure, and plans, spending significant radio resources on estimating channel conditions in mobile networks poses a challenge. Automating the process of predicting channel conditions can efficiently utilize resources. To this point, we propose an ML-based technique, i.e., an Artificial Neural Network (ANN) for predicting SINR (Signal-to-Interference-and-Noise-Ratio) in order to mitigate the radio resource usage in mobile networks. Radio resource scheduling is generally achieved on the basis of estimated channel conditions, i.e., SINR with the help of Sounding Reference Signals (SRS). The proposed Non-Linear Auto Regressive External/Exogenous (NARX)-based ANN aims to minimize the rate of sending SRS and achieves an accuracy of R = 0.87. This can lead to vacating up to 4% of the spectrum, improving bandwidth efficiency and decreasing uplink power consumption.
In cognitive networks, efficient spectrum sensing is of great importance for communication of unlicensed secondary users (SU) without interfering with the communication of licensed primary users (PU). Such spectrum sensing requires robust and reliable communication between the SUs to sense the spectrum efficiently under different network circumstances and to make a quick decision for the data transmission. In this paper, we are proposing a decentralized cooperative algorithm for efficient sensing of spectrum in the networked cognitive radios. The proposed algorithm is investigated under crash and Byzantine failure environments to study their behavior and efficiency for consensus. Energy detector module is modeled for each cooperating SU in cognitive radio network for sensing the presence of PU in a dedicated spectrum. Moreover, SU is modeled as agents connected through undirected graphs to simulate communication among them related to the spectrum availability. Multiple simulation scenarios, based on autonomous SU using the proposed distributed consensus algorithm are presented to demonstrate the theoretical development of proposed algorithm to be visualized in real scenarios. The simulation results reveal that the proposed method provides a significant improvement in convergence rate, reliability, and in terms of various key performance indicators.
The ever-growing Internet of Things (IoT) data traffic is one of the primary research focuses of future mobile networks. 3rd Generation Partnership Project (3GPP) standards like Long Term Evolution-Advanced (LTE-A) have been designed for broadband services. However, IoT devices are mainly based on narrowband applications. Standards like LTE-A might not provide efficient spectrum utilization when serving IoT applications. The aggregation of IoT data at an intermediate node before transmission can answer the issues of spectral efficiency. The objective of this work is to utilize the low cost 3GPP fixed, inband, layer-3 Relay Node (RN) for integrating IoT traffic into 5G network by multiplexing data packets at the RN before transmission to the Base Station (BS) in the form of large multiplexed packets. Frequency resource blocks can be shared among several devices with this method. An analytical model for this scheme, developed as an r-stage Coxian process, determines the radio resource utilization and system gain achieved. The model is validated by comparing the obtained results with simulation results.