With the rapid pace of urbanization and the growing complexity of traffic networks, the development of intelligent transportation systems (ITSs) has become increasingly vital for improving traffic efficiency, safety, and management. The You Only Look Once (YOLO) algorithm, a real‐time object detection model known for its high computational efficiency and detection accuracy, has emerged as a prominent tool within ITS applications. This survey presents a comprehensive review of recent advancements in the application of the YOLO algorithm across various ITS domains, including traffic monitoring, vehicle and pedestrian detection, and traffic sign recognition. The paper first outlines the methodology employed for literature selection and categorization, followed by an overview of the YOLO algorithm’s evolution and core technical components. Subsequently, it explores the algorithm’s practical implementations within different ITS scenarios. The review concludes with a synthesis of key findings and proposes future research directions, highlighting emerging trends and potential challenges. This work is aimed at providing researchers and practitioners with a structured understanding of YOLO’s current applications in ITS and at fostering further innovation in this interdisciplinary field.

Target localization (positioning) by the time difference of arrival (TDoA) using previously localized wireless sensor nodes has wide applications. Three‐degree sensing coverage cannot calculate accurate spatial‐temporal information of the target object in two‐dimensional acoustic positioning. In this article, algebraic and geometrical modeling of the two‐dimensional acoustic positioning of the target has been reviewed. By using these models, it is proved that the sensing area with three‐degree sensing coverage can be separated into two different zones. In the Type 1 zone, which is continuous, the target can be precisely positioned. Type 2 zones, which are three separate areas with three‐degree sensing coverage, cannot accurately position the target, and there is a need for four‐degree sensing coverage. Then, a relationship is presented to define the exact boundaries of these two zones. In the following, more features of this relationship have been examined. The results of this article can be used to improve the quality of the service metrics of the wireless sensor network, such as the accuracy of acoustic target positioning and tracking, along with reducing the cost of system implementation and increasing the lifetime of the network by optimal placement of wireless sensor nodes.

Over the past decades, Session Initiation Protocol (SIP) has been commonly utilized in signaling protocol to control and signal multimedia communication sessions for providing various services to users. Video calls and internet telephony over Internet Protocol (IP) are the most common applications on SIP. Generally, the SIP acts as an unsafe communication platform, due to the exchange of information via public channels. Thus, the security of the SIP network should be increased prominently and require secure authentication and key establishment schemes. In this article, a deep learning model fractional lyrebird optimization algorithm–deep stack autoencoder (FLOA‐DSA) is developed for the detection of SIP‐based distributed reflection denial‐of‐service (DRDoS) attacks in SIP network. Here, the authentication process is carried out under different phases based on various mathematical model functionalities. Moreover, the deep stack autoencoder (DSA) model is used to perform intrusion detection in the attack validation phase. The detection performance of DSA is increased by training using the fractional lyrebird optimization algorithm (FLOA); FLOA provides a more effective, reliable, and scalable optimization strategy for training DSAs than traditional algorithms. Its ability to dynamically interact with DSA’s learning dynamics makes it not just a suitable choice, but the optimal optimization choice for this hybrid deep learning system. Further, the detection performance of the FLOA‐DSA is evaluated based on the metrics, such as detection rate, F ‐measure, false positive rate (FPR), memory usage, validation time, conditional privacy, response time, energy efficiency, and latency, and the FLOA‐DSA obtained best results of 90.12%, 91.40%, 9.13%, 6.9 MB, 48.5 s, 3.86 s, 88.88 bits/J, and 2.68 s. The F ‐measure of the proposed method is 9.06%, 6.63%, 4.80%, and 2.61% improved than other existing comparative methods.

In order to solve the highly nonlinear nonconvex problem of the mathematical model in Bluetooth (angle of arrival (AOA)) localization, this paper proposes an alternating minimization algorithm for three‐dimensional AOA localization. The algorithm method converts the solving error minimization solving three‐dimensional coordinate problem in Bluetooth three‐dimensional AOA localization model to solving four single‐variable problems and alternately optimizes each variable to get the global optimal solution, which reduces the complexity of the model solving and achieves the high‐precision localization performance without auxiliary information. The test is carried out in two states: dynamic line of sight (LOS) and static non–line of sight (NLOS), and the results show that the proposed method meets the demand for indoor positioning accuracy with a positioning error of 16 cm in LOS environment and 34 cm in NLOS environment.

Wireless rechargeable sensor network (WRSN) has become the most effective solution to the energy problem in wireless sensor networks (WSNs) by introducing mobile chargers (MCs) to replenish energy for energy‐starved sensor nodes. In the studies of WRSN, there has been growing interest in using lightweight unmanned aerial vehicles (UAVs) as MCs to overcome geographical constraints. Recently, automatic landing pads (PADs) have been introduced in the UAV‐based WRSN, enabling the UAV to automatically replenish energy during the charging flight. Consequently, the UAV’s service range is enlarged, and the UAV can now perform large‐scale charging services. In this paper, we investigate the periodic charging scheduling problem in this novel form of WRSN with the goal of minimizing the charging delay. We present the problem’s definition and model and prove it is NP‐hard. To address this problem, we propose two periodic charging schemes: SNBC (sensor‐node‐based charging scheme) and PBC (PAD‐based charging scheme). We extensively simulated our proposed schemes in a UAV‐based WRSN with PADs, evaluating them based on two key metrics: charging delay and UAV replenishment frequency. The results indicate the efficiency of our approaches. SNBC averaged a 7.2 × 104 s charging delay, while PBC outperformed it with a 14.01% reduction in charging delay and a 13.66% decrease in replenishment frequency.

In opportunistic network, the regular connectivity of nodes and their individual conditions significantly influence message transmission. To address this, we propose an improved spray and wait routing algorithm based on stable transmission capacity evaluation of nodes (referred to as STCESW), which is derived from traditional Prophet and spray and wait algorithms but surpasses them. STCESW incorporates network models that consider node connection stability and transmission capacity, aiming to enhance the update and punishment formulas for node delivery probability. Furthermore, it combines the residual message buffer size of nodes with the angle between motion directions of nodes to determine more efficient and extensive message spraying in the network. The simulation results clearly indicate that STCESW significantly outperforms the other three enhanced algorithms in both SPMBM and RWP. It demonstrates its robust performance in terms of delivery probability, showing an increase ranging from 2% to 87% across diverse node buffer sizes or simulation time intervals. Additionally, it compromises slightly on delivery latency while maintaining relatively stable message latency and buffer time.

This paper proposed a model to estimate sensor spacing and a new deployment geometry and evaluates the performance of an ultrasonic sensor array according to the deployment geometry. The proposed spacing estimation model is based on the probability of false detection alarms, the aperture angle, and the sensor range. A design technique has been proposed for elliptical deployment geometry, giving expressions for its parameters to help designers of experimental prototypes to reduce errors related to sensor disposition. A practical method for calibrating ultrasonic sensors has been designed to reduce measurement errors. An experiment was conducted, and the data were analysed using a statistical significance test. An evaluation of the performance of an ultrasonic sensor array with linear and circular deployment geometry with and without our method was done and then compared to our proposed deployment geometry which was combined with the proposed method. The result of the statistical significance test shows that elliptical deployment geometry combined with the suggested strategy works better than circular and linear geometry. This applies to performance such as linear correlation, RMSE, MAPE, and standard deviation. These results show the importance of the choice of deployment geometry for application.

This paper proposes a blockchain-based identity authentication (BA) scheme for IoT devices to solve the authentication security problem of IoT devices. The BA scheme uses hashing and digital signature algorithms to achieve integrity and nonrepudiation of authentication messages. Blockchain technology is used to achieve decentralised and distributed storage and management of authentication data. Besides, the BA scheme uses the idea of trust domains and trust credentials to establish a master-slave connection between IoT devices. The BA scheme is then compared with the existing four schemes and analysed from six perspectives to show that the BA scheme has better security. Also, the results show that the BA scheme has reasonable computational and storage overhead. Finally, the advantages of the BA scheme over traditional centralised and existing blockchain-based authentication schemes are compared and analysed. The results show that it can perfectly solve the problem of overreliance on trusted third parties in traditional authentication schemes.

Maize flour obtained from the dried corn is one of the most consumed foods in Rwanda. It is imperative that this should be healthy and risk-free for a safe consumption. Therefore, it is vital to keep track of the environmental conditions during the drying process and the characteristics that exist inside maize storage containers. In Rwanda, traditional methods are most commonly used by maize farmers for drying and storage purposes, where no smart system is being used to monitor the environmental conditions under which the maize grains are dried and stored. This mostly affects the quality of maize and flour being produced which will finally affect food security. In this research, temperature, humidity, and light sensors are deployed in the grain storage containers for environmental parameter detection purposes to achieve the primary goal of providing practical, secure, and easily accessible storage in inclement weather. Temperature and humidity are two factors that have an impact on grain quality while in storage. The ThingSpeak platform has been used to help farmers monitor the drying and storing conditions of the maize on a real-time basis. A global system for mobile (GSM) communication module is used to notify farmers by sending a short message in case of critical drying or storing environmental parameters under which the maize grains are stored. The result is shown in the form of humidity, temperature, and light graphs which are displayed on the ThingSpeak platform in real-time mode.