Search Results (31)

The recent advancements in technologies such as artificial intelligence (AI), computer vision (CV), and Internet of Things (IoT) have significantly extended various fields, particularly in surveillance systems. These innovations enable real-time facial recognition processing, enhancing security and ensuring safety. However, mobile robots are commonly employed in surveillance systems to handle risky tasks that are beyond human capability. In this paper, we present a prototype of a cost-effective mobile surveillance robot built on the Raspberry PI 4, designed for integration into various industrial environments. This smart robot detects intruders using IoT and face recognition technology. The proposed system is equipped with a passive infrared (PIR) sensor and a camera for capturing live-streaming video and photos, which are sent to the control room through IoT technology. Additionally, the system uses face recognition algorithms to differentiate between company staff and potential intruders. The face recognition method combines high-order statistical features and evidence theory to improve facial recognition accuracy and robustness. High-order statistical features are used to capture complex patterns in facial images, enhancing discrimination between individuals. Evidence theory is employed to integrate multiple information sources, allowing for better decision-making under uncertainty. This approach effectively addresses challenges such as variations in lighting, facial expressions, and occlusions, resulting in a more reliable and accurate face recognition system. When the system detects an unfamiliar individual, it sends out alert notifications and emails to the control room with the captured picture using IoT. A web interface has also been set up to control the robot from a distance through Wi-Fi connection. The proposed face recognition method is evaluated, and a comparative analysis with existing techniques is conducted. Experimental results with 400 test images of 40 individuals demonstrate the effectiveness of combining various attribute images in improving human face recognition performance. Experimental results indicate that the algorithm can identify human faces with an accuracy of 98.63%. Full article

This study investigates the genesis of gold mineralization at the Rodruin prospect in the central Eastern Desert (CED) of Egypt, with the aim of constraining the relative contributions of metamorphic and magmatic fluids to ore formation. Gold mineralization at Rodruin is hosted by quartz–carbonate veins emplaced within a shear zone that transects low-grade metasedimentary sequences intruded by Ediacaran post-tectonic granitoids. It exhibits characteristics transitional between orogenic turbidite-hosted and polymetallic vein-type mineralization. Although metamorphic devolatilization is interpreted to have generated the dominant ore-forming fluids, adjacent granitoid intrusions acted primarily as a thermal engine, with only a limited direct input of magmatic-hydrothermal fluids. This interpretation is supported by the occurrence of magmatic-affiliated mineral inclusions (monazite, cassiterite, and zircon) coupled with generally low concentrations of trace elements typically enriched in granitic magmatic-hydrothermal fluids (Sb, Bi, Mo, W, Sn, Nb, and Ta), collectively indicating a subordinate magmatic contribution. Rare earth element (REE) patterns of the ore samples closely resemble those of the nearby granitoids, displaying LREE enrichment; however, a distinct positive Eu anomaly is restricted to the ore assemblages and is attributed to hydrothermal feldspar alteration supporting magmatic involvement in ore formation. Carbon and oxygen isotope compositions (δ¹³C = −6.6 to −2.36‰; δ¹⁸O = +15.7 to +19.7‰), together with REE signatures comparable to primitive mantle values and textural evidence for synchronous sulfide–carbonate precipitation, manifested by rhythmic banding of carbonates and sulfides unequivocally indicate a hydrothermal–metasomatic origin. Collectively, these lines of evidence support a hybrid metamorphic–magmatic model in which gold and associated base metals were predominantly transported by metamorphic fluids, whose mobilization and focusing were enhanced by the thermal influence of Younger granitic intrusions, whereas magmatic-hydrothermal fluids contributed only a minor proportion to the overall metal budget. Full article

This paper addresses the optimal design of a multi-layer security system for protecting borders or sensitive areas against intruders who may deploy decoys. The system comprises successive layers of imperfect sensors and a limited number of mobile response units. Intruders that evade detection or neutralization in one layer proceed to the next. Our objective is to minimize the overall probability of a threat escaping the entire system. We formulate a nonlinear integer programming model within a queuing-theoretic framework to jointly determine the optimal number of security layers and the allocation of sensors and response units across them. A simulated annealing heuristic is proposed to solve this complex optimization problem. Furthermore, we extend the model to analyze the impact of decoys—objects that trigger intentional false alarms—which strategically drain system resources and increase the evasion risk for genuine threats. Numerical experiments demonstrate that the optimized multi-layer configuration significantly reduces the final escape probability compared to a single-layer baseline, validating the efficacy of the proposed framework for enhancing security in resource-constrained environments. Full article

Globally, most skarn deposits show a direct relationship with magmatic activity, indicating a genetic link between the geochemical composition of causative plutons and the metal content of associated skarns. Therefore, this study investigated the Early–Middle Eocene plutonic rocks and their relationship with Fe-Zn skarn deposits in the Esendemirtepe-Koçak and Horoz areas of south-central Türkiye. Despite the regional significance, previous studies have not adequately addressed the petrogenetic evolution of these intrusions and the geochemical characteristics of the related skarns. In particular, the fluid-aided mobility of elements at the contact between the causative plutons and the volcano-sedimentary country rocks remains poorly understood. Therefore, in this study, field studies, petrographic and mineralogical analysis, and whole-rock geochemical analysis were conducted to investigate the genetic link between the plutonic rocks and the skarn deposits. Field studies reveal that the skarn zones are within volcano-sedimentary sequences and marble-schist units intruded by four distinct plutonic bodies: (1) Esendemirtepe diorite, (2) Koçak diorite, (3) Horoz granodiorite, and (4) Çifteköy monzogabbro. These rocks exhibit calc-alkaline, I-type, and metaluminous signatures, except for the Çifteköy monzogabbro, which shows I-type, tholeiitic, and alkaline characteristics. All the plutonic rocks associated with the skarn formation display steep LREE-enriched REE patterns with minor positive Eu anomalies (Eu/Eu* = 0.98–1.35), suggesting a subduction-related volcanic arc setting similar to other granitoids in the Ulukışla Basin. The Horoz skarn exhibits both endoskarn and exoskarn features, while the Esendemirtepe-Koçak deposit is characterized by typical exoskarn features. Dominant ore minerals in both skarn deposits include magnetite, hematite, sphalerite, chalcopyrite, and pyrite, with minor arsenopyrite, galena, and cobaltite. The mineral composition of the skarn also shows the dominance of Na-rich and Mg-rich minerals in both locations. The geochemical compositions of the I-type, metaluminous Esendemirtepe-Koçak, and Horoz plutonic rocks are compatible with Fe-Zn skarn type deposits based on the moderate MgO (0.36–4.44 wt.%) and K₂O (1.38–7.99 wt.%), and Rb/Zr and Sr/Zr ratios. They also show typical volcanic arc features, and the variation in various trace element concentrations shows similarity with Fe-Zn skarn type granitoids. These findings support a strong genetic relationship between the mineralization and the geochemical and mineralogical characteristics of the associated plutonic rocks. Full article

With the rapid development of Artificial Intelligence, AI-enabled Uncrewed Aerial Vehicles have garnered extensive attention since they offer an accessible and cost-effective solution for executing tasks in unknown or complex environments. However, developing secure and effective AI-based algorithms that empower agents to learn, adapt, and make precise decisions in dynamic situations continues to be an intriguing area of study. This paper proposes a hybrid intelligent control framework that integrates an enhanced Soft Actor–Critic method with a fuzzy inference system, incorporating pre-defined expert experience to streamline the learning process. Additionally, several practical algorithms and approaches within this control system are developed. With the synergy of these innovations, the proposed method achieves effective real-time path planning in unpredictable environments under a model-free setting. Crucially, it addresses two significant challenges in RL: dynamic-environment problems and multi-target problems. Diverse scenarios incorporating actual UAV dynamics were designed and simulated to validate the performance in tracking multiple mobile intruder aircraft. A comprehensive analysis and comparison of methods relying solely on RL and other influencing factors, as well as a controller feasibility assessment for real-world flight tests, are conducted, highlighting the advantages of the proposed hybrid architecture. Overall, this research advances the development of AI-driven approaches for UAV safe autonomous navigation under demanding airspace conditions and provides a viable learning-based control solution for different types of robots. Full article

With the rapid rise of digitalization in the global economy, home security systems have become increasingly important for personal comfort and property protection. The collaboration between humans, the Internet of Things (IoT), and smart homes can be highly efficient. Interaction considers convenience, efficiency, security, responsiveness, and automation. This study aims to develop and assess IoT-based home security systems utilizing passive infrared (PIR) sensors to improve user interface, security, and automation controls using voice commands and buttons across different communication protocols. The proposed system incorporates controls for lighting and intrusion monitoring, as well as assessing both the functionality of voice commands and the precision of intruder detection via the PIR sensors. Intelligent light control and PIR intruder detection with a variable delay time for response detection are unified into the research methodology. The test outcomes examine the average effective response time in-depth, revealing performance distinctions among wireless fidelity (Wi-Fi) and fourth- and fifth-generation mobile connections. The outcomes illustrate the reliability of voice-activated light control via Google Assistant, with response accuracy rates of 83 percent for Thai voice commands and 91.50 percent for English voice commands. Moreover, the Blynk mobile application provided exceptional precision regarding operating light-button commands. The PIR motion detectors have a one hundred percent detection accuracy, and a 2.5 s delay is advised for PIR detection. Extended PIR detection delays result in prolonged system response times. This study examines the intricacies of response times across various environmental conditions, considering different degrees of mobile communication quality. This study ultimately advances the field by developing an IoT system prepared for efficient integration into everyday life, holding the potential to provide improved convenience, time-saving effectiveness, cost-efficiency, and enhanced home security protocols. Full article

Due to the rapid advancement of social media, a huge amount of data is generated daily. Due to this great spread and expansion of the data at the social or professional level, the risks of securing the information become a challenging job. In this regard, we conducted an in-depth interview to gather specific information about how infected users may be provided with information about recovering their hacked social networking accounts. Further, we have introduced a complete solution to help social network users to improve the idea of using different applications from one appropriate platform. In order to build this secure platform for accessing the security applications such as bank accounts, etc., we set various security methods to access social network websites, such as sending an OTP to their respective mobile devices, email or by fingerprint. Further, we also added a camera to identify the wrong or fake registration process of an intruder. The camera captures an image of the intruder registering to a social network website using the legitimate user’s information. In addition, the application also has a solution for forgetting the password or security questions that are sent to the user via email. Finally, the application saves the password, which can be recovered when the user forgets it. Full article

Barrier coverage is a fundamental application in wireless sensor networks, which are widely used for smart cities. In applications, the sensors form a barrier for the intruders and protect an area through intrusion detection. In this paper, we study a new branch of barrier coverage, namely warning barrier coverage (WBC). Different from the classic barrier coverage, WBC has the inverse protect direction, which moves the sensors surrounding a dangerous region and protects any unexpected visitors by warning them away from the dangers. WBC holds a promising prospect in many danger keep out applications for smart cities. For example, a WBC can enclose the debris area in the sea and alarm any approaching ships in order to avoid their damaging propellers. One special feature of WBC is that the target region is usually dangerous and its boundary is previously unknown. Hence, the scattered mobile nodes need to detect the boundary and form the barrier coverage themselves. It is challenging to form these distributed sensor nodes into a barrier because a node can sense only the local information and there is no global information of the unknown region or other nodes. To this end, in response to the newly proposed issue of the formation of barrier cover, we propose a novel solution AutoBar for mobile sensor nodes to automatically form a WBC for smart cities. Notably, this is the first work to trigger the coverage problem of the alarm barrier, wherein the regional information is not pre-known. To pursue the high coverage quality, we theoretically derive the optimal distribution pattern of sensor nodes using convex theory. Based on the analysis, we design a fully distributed algorithm that enables nodes to collaboratively move toward the optimal distribution pattern. In addition, AutoBar is able to reorganize the barrier even if any node is broken. To validate the feasibility of AutoBar, we develop the prototype of the specialized mobile node, which consists of two kinds of sensors: one for boundary detection and another for visitor detection. Based on the prototype, we conduct extensive real trace-driven simulations in various smart city scenarios. Performance results demonstrate that AutoBar outperforms the existing barrier coverage strategies in terms of coverage quality, formation duration, and communication overhead. Full article

Vehicular networks improve quality of life, security, and safety, making them crucial to smart city development. With the rapid advancement of intelligent vehicles, the confidentiality and security concerns surrounding vehicular ad hoc networks (VANETs) have garnered considerable attention. VANETs are intrinsically more vulnerable to attacks than wired networks due to high mobility, common network medium, and lack of centrally managed security services. Intrusion detection (ID) servers are the first protection layer against cyberattacks in this digital age. The most frequently used mechanism in a VANET is intrusion detection systems (IDSs), which rely on vehicle collaboration to identify attackers. Regrettably, existing cooperative IDSs get corrupted and cause the IDSs to operate abnormally. This article presents an approach to intrusion detection based on the distributed federated learning (FL) of heterogeneous neural networks for smart cities. It saves time and resources by using the most efficient intruder detection approach. First, vehicles use a federated learning technique to develop local, deep learning-based IDS classifiers for VANET data streams. They then share their locally learned classifiers upon request, significantly reducing communication overhead with neighboring vehicles. Then, an ensemble of federated heterogeneous neural networks is constructed for each vehicle, including locally and remotely trained classifiers. Finally, the global ensemble model is again shared with local devices for their updating. The effectiveness of the suggested method for intrusion detection in VANETs is evaluated using performance indicators such as attack detection rates, classification accuracy, precision, recall, and F1 scores over a ToN-IoT data stream. The ID model shows 0.994 training and 0.981 testing accuracy. Full article

The integration of artificial intelligence (AI) technology into the Internet of Vehicles (IoV) has provided smart services for intelligent connected vehicles (ICVs). However, due to gradually upgrading to ICVs, an increasing number of external communications interfaces exposes the in-vehicle networks (IVNs) to malicious network intrusion. The malicious intruders can take over the compromised ICVs and mediately intrude into the ICVs connected through IoV. Therefore, it is urgent to develop IVN intrusion detection methods for IoV security protection. In this paper, a ConvLSTM-based IVN intrusion detection method is developed by leveraging the periodicity of the network message ID. For training the ConvLSTM model, a federated learning (FL) framework with client selection is proposed. The fundamental FL framework works in the client-server mode. ICVs are the local clients, and mobile edge computing (MEC) servers connected to base stations (BSs) function as the parameter servers. Based on the framework, a proximal policy optimization (PPO)-based federated client selection (FCS) scheme is further developed to optimize the model accuracy and system overhead of federated ConvLSTM model training. Simulations are conducted by the exploitation of real-world IoV scenario settings and IVN datasets. The results indicate that by exploiting the ConvLSTM, the model size and convergence time are dramatically reduced, and the 95%-beyond detection accuracy is maintained. The results also unveil that the PPO-based FCS scheme outperforms the benchmarks on the convergence rate, model accuracy, and system overhead. Full article

In this work, a Detect and Avoid system is presented for the autonomous navigation of Unmanned Aerial Vehicles (UAVs) in Urban Air Mobility (UAM) applications. The current implementation is designed for the operation of multirotor UAVs in UAM corridors. During the operations, unauthorized flying objects may penetrate the corridor airspace posing a risk to the aircraft. In this article, the feasibility of using a solid-state LiDAR (Light Detecting and Ranging) sensor for detecting and positioning these objects was evaluated. For that purpose, a commercial model was simulated using the specifications of the manufacturer along with empirical measurements to determine the scanning pattern of the device. With the point clouds generated by the sensor, the system detects the presence of intruders and estimates their motion to finally compute avoidance trajectories using a Second Order Cone Program (SOCP) in real time. The method was tested in different scenarios, offering robust results. Execution times were of the order of 50 milliseconds, allowing the implementation in real time on modern onboard computers. Full article

This study integrates path planning, fuzzy theory, neural networks, image processing, range sensors, webcam, global navigation satellite system (GNSS), and real-time kinematic (RTK) positioning system into an intelligent wheeled mobile robot (WMR) for outdoor patrolling. The robot system uses ultrasound sensors, laser sensors, and fuzzy controllers to detect obstacles and avoid them. The starting position and the goal position of the WMR in an outdoor environment are given by the GNSS RTK positioning system. Real-time position correction of the robot is performed through the differential global positioning system. The robot system applies the ant algorithm and the Dijkstra algorithm to find the shortest path for patrol tasks. The convolutional neural network image processing is utilized to identify intruders that are appearing in the patrol path. When the WMR detects an intruder by the face detection and recognition methods, the robot captures the photo of this person by the webcam and acquires the location information of this person by the RTK positioning system. Then the WMR sends the location and photo of the intruder to the control center by Wi-Fi and asks for help. Full article

The real-world emission factors of gaseous and particulate air pollutants emitted from in-use vehicles, can be rapidly estimated using monitoring data of their concentration profiles from inside roadway tunnels using a mobile laboratory equipped with fast monitoring instruments. The concentrations of CO₂ and particle-bound polycyclic aromatic hydrocarbons (PM-PAHs) and NO_x, were observed to increase linearly with traveling distance inside two successive roadway tunnels: the Hongjimun Tunnel and the Jeongneung Tunnel on the Naebu Express Way in Seoul, Korea, except for a small region of decrease. In the decreasing regions, within a few hundred meters of the entrance and before the exit, outside background air with low concentrations of air pollutants was thought to have intruded. From the slopes of the linear regression between distance and concentrations, a fleet-averaged (light-, medium-, and heavy-duty vehicles with 54%, 36%, and 10%, respectively) emission factor of CO₂, PM-PAHs, and NO_x at an average speed of ~60 km h⁻¹ could be calculated as 197 ± 38 g km⁻¹, 4.2 ± 0.8 × 10⁻⁴ g km⁻¹, and 0.530 ± 0.230 g km⁻¹, respectively, which are within the ranges of values reported in the literature. For each tunnel, the emission factors of CO₂, PM-PAHs, and NO_x estimated on days with higher-than-normal fractions of heavy-duty vehicles, were higher than those on other days. From these results, the new fast method proposed in this study is considered useful for estimating real-world emission factors of air pollutants by using a mobile laboratory as a complementary tool to traditional tunnel studies. This method can be used to rapidly make emission maps at roadway tunnels in mega-cities like Seoul, Korea, for urban air-quality management. Full article

The increasing availability of mobile devices and applications, the progress in virtualisation technologies, and advances in the development of cloud-based distributed data centres have significantly stimulated the growing interest in the use of software-defined networks (SDNs) for both wired and wireless applications. Standards-based software abstraction between the network control plane and the underlying data forwarding plane, including both physical and virtual devices, provides an opportunity to significantly increase network security. In this paper, to secure SDNs against intruders’ actions, we propose a comprehensive system that exploits the advantages of SDNs’ native features and implements data mining to detect and classify malicious flows in the SDN data plane. The architecture of the system and its mechanisms are described, with an emphasis on flow rule generation and flow classification. The concept was verified in the SDN testbed environment that reflects typical SDN flows. The experiments confirmed that the system can be successfully implemented in SDNs to mitigate threats caused by different malicious activities of intruders. The results show that our combination of data mining techniques provides better detection and classification of malicious flows than other solutions. Full article

Mobile ad-hoc networks (MANETs) have great potential applications in military missions or emergency rescue due to their no-infrastructure, self-organizing and multi hop capability characteristics. Obviously, it is important to implement a low-cost and efficient mechanism of anti-invasion, anti-eavesdropping and anti-attack in MANETs, especially for military scenarios. The purpose of intruding or attacking a MANET is usually different from that of wired Internet networks whose security mechanism has been widely explored and implemented. For MANETs, moving target defense (MTD) is a suitable mechanism to enhance the network security, whose basic idea is to continuously and randomly change the system parameters or configuration to create inaccessibility for intruders and attackers. In this paper, a two-layer IP hopping-based MTD approach is proposed, in which device IP addresses or virtual IP addresses change or hop according to the network security status and requirements. The proposed MTD scheme based on the two-layer IP hopping has two major advantages in terms of network security. First, the device IP address of each device is not exposed to the wireless physical channel at all. Second, the two-layer IP hops with individual interval and rules to obtain enhanced security of MANET while maintaining relatively low computational load and communication cost for network control and synchronization. The proposed MTD scheme is implemented in our developed MANET terminals, providing three level of network security: anti-intrusion in normal environment, intrusion detection in offensive environment and anti-eavesdropping in a hostile environment by combining the data encryption technology. Full article