Fig 8 - uploaded by Heena Rathore
Content may be subject to copyright.
Source publication
Exploring the symbiotic nature of biological systems can result in valuable knowledge for computer networks. Biologically inspired approaches to security in networks are interesting to evaluate because of the analogies between network security and survival of human body under pathogenic attacks. Wireless Sensor Network (WSN) is a network based on m...
Similar publications
Continuous measurement of temperature profiles on the surface of the human body offers various kinds of information valuable for clinical diagnosis and as a useful guide to take suitable action. In this article, the behavior of a newly developed temperature sensing fabric (TSF) over extended periods of time in a practical application and its compar...
Citations
... Our previous work [3,4] lists the various trust evaluation methods, motivation, and trust evaluation framework in a well-structured way. Although there are several trust modeling approaches such as weightbased, rate-based, fuzzy-based, game theory-based, Machine Learning (ML) algorithms seem to be a cost-effective solution since it provides real-time solutions that maximize resource utilization and improve network lifespan [5]. ML algorithms like Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and Gaussian Naïve Bayes can handle complex data more quickly and accurately. ...
... This section discussed about the existing work [5][6][7][8][9][10][11][12][13][14][15][16]20] on trust models related to autonomous WSNs. Table 1 shows the comparative analysis of various trust schemes used in existing trust models. ...
... Table 1 shows the comparative analysis of various trust schemes used in existing trust models. Rathore et al. [5] suggested an improved security mechanism for WSNs using Machine Learning (ML) and bio-inspirations (immune module) techniques. ML method identifies malicious nodes and the human immune system mitigates (nullify) these selfish nodes by employing antigen and antibody theory to enhance the robustness as well as the accuracy of the suggested scheme. ...
Wireless Sensor Networks (WSNs) are often used for critical applications where trust and security are of
paramount importance. Trust evaluation is one of the key mechanisms to ensure the security and reliability
of WSNs. Traditional trust evaluation schemes rely on fixed, predetermined thresholds, or rules and static
attack models, which may not be suitable for all situations such as dynamic and heterogeneous network
environments with new and unknown attack scenarios as well as have several problems such as limited security
and scalability, limited accuracy, incomplete coverage, lack of adaptability that can limit their effectiveness.
Machine Learning (ML) has been shown to be an effective tool for trust evaluation in WSNs, offering several
benefits over existing schemes such as greater adaptability, scalability, and accuracy since ML algorithms can
analyze and learn from the data collected in real-time from multiple sources (sensor readings, network traffic,
and user behavior) enabling them to dynamically adjust their decision-making criteria based on the current
network conditions. Trust-aware ML-based security mechanisms achieve safety and efficient decision-making
by reducing uncertainty and risk to accomplish real-world tasks. This paper presents a Machine Learning
(ML)-based trust evaluation model in the unattended autonomous WSN environment to achieve reliability,
adaptability, scalability, and accuracy by generating quick and reliable trust values dynamically. The proposed
machine learning algorithm extracts various trust features such as Co-Location Relationship (CLR), Co-Work
Relationship (CWR), Cooperativeness-Frequency-Duration (CFD), and Reward (R) to obtain a robust trust
rating of sensor devices and predict future misbehavior. These trust features are combined to generate a final
trust rating before making any decision about the reliability of any sensor device. Moreover, the projected
trust model (ETDMA) integrate direct communication trust and indirect trust with the help of a logical time
window that periodically records the trustworthy and suspicious interactions. Simulation experiments exhibit
the effectiveness of the proposed trust evaluation method in terms of change in trust values, malicious nodes
detection (94%), FNR (0.9%), F1-Score (0.6), and accuracy (92%) in the presence of 50 malicious nodes.
... Machine learning techniques can improve wireless network security, reduce congestion, and aid in physical layer authentication and error detection [17][18][19]. ML techniques also help analyze WSN packets and identify problematic nodes [26][27][28][29]. ...
... Therefore, machine learning algorithms can help increase security in wireless networks, reduce all forms of congestion problems [17][18][19], and help authentication processes through the physical layer [20][21][22], and error detection [23][24][25]. Furthermore, ML algorithms have a great advantage in analyzing packets as they travel between WSN nodes and detecting suspicious nodes [26]. ...
... In addition, the approach described in [26] used a ML technique to determine whether a benevolent node had turned malevolent. Bio-inspiration can also be used as an immune system to counteract the effects of malevolent nodes. ...
Energy and security are major challenges in a wireless sensor network, and they work
oppositely. As security complexity increases, battery drain will increase. Due to the limited power in wireless sensor networks, options to rely on the security of ordinary protocols embodied in encryption and key management are futile due to the nature of communication between sensors and the ever-changing network topology. Therefore, machine learning algorithms are one of the proposed solutions for providing security services in this type of network by including monitoring and decision intelligence. Machine learning algorithms present additional hurdles in terms of training and the amount of data required for training. This paper provides a convenient reference for wireless sensor network infrastructure and the security challenges it faces. It also discusses the possibility of benefiting from machine learning algorithms by reducing the security costs of wireless sensor networks in several domains; in addition to the challenges and proposed solutions to improving the ability of sensors to identify threats, attacks, risks, and malicious nodes through their ability to learn and self-development using machine learning algorithms. Furthermore, this paper discusses open issues related to adapting machine learning algorithms to the capabilities of sensors in this type of network.
... Based on data traffic, machine learning differentiates between IoT and non-IoT computers [164]. f) Protection with Machine Learning using Bio-Inspiration The authors used machine learning with Bio-inspiration to remove the impact of malicious nodes [165]. Two clusters were created by the k-means algorithm: a regular cluster and a faulty cluster, and SVM were used to create a decision block comprising three regions: a normal zone, a fault region, and a border area. ...
Wireless Sensor Network (WSN) is an innovative technology with a broad range of applications and highly attractive benefits, such as low cost of implementation and data transmission, unmonitored access to the network, autonomous and long-term operation. With extensive demand for the advancement of related technologies (cloud computing, near-field communications and cellular mobile networks), the Internet of Things (IoT) is becoming a very exciting paradigm. By using communication technologies in sensors and sensing features in web devices, WSNs have begun interaction with the Iot devices. IoT provides access to a large amount of information gathered by WSNs. However, the security of WSN and IoT comes at a cost, mainly due to privacy management issues. Therefore, this paper offers a comprehensive analysis of security threats against WSN and IoT, along with the strategies for preventing, detecting and mitigating those threats. The related defense mechanisms can help in building a safe IoT expansion and widespread understanding by getting familiar with the details of these attacks. The aim of this paper is to address and demonstrate the impact of the security problems on WSNs from the viewpoint of the IoT and its applications. In the analysis carried out for this work, a classification of available attacks and threats against these requirements has also been included.
... In [7], generator coherence groups were obtained using the Partitioning Around Medoids (PAM) approach and it was compared with K-means in [8]. The K-means clustering approach is simple to employ and is fast [9], [10]. Nevertheless, the K-means technique has trouble clustering data without the selection of preliminary centroids or the number of clusters and iterations required to determine the clusters [11,12]. ...
Coherent groups of generators, i.e., machines with perfectly correlated rotor angles, play an important role in power system stability analysis. This paper introduces a real-time methodology based on hierarchical clustering techniques for discovering the degree of coherency among generators using the synchronization coefficient and the correlation coefficient of the generators' rotor angle as the coherency index. Furthermore, the Power Transient Stability Indices (PTSI) were employed to examine the versatile response of the power system. The method uses power systems transients Stability indices, i.e., power Connectivity Factor (CF) index which presents coherently strong generators within the groups, the power Separation Factor (SF) index which unveils to the extent that the generators in different groups tend to swing against the other groups in the event of a disturbance, and the overall system separation index which demonstrates the overall system separation status (CF/SF). The approach is assessed on an IEEE-39 test system with a fully dynamic model. The simulation results presented in this paper demonstrate the efficiency of the proposed approach.
... K-means is an unsupervised machine learning method which works on the principle of finding a structure from an unlabeled dataset by grouping the data into clusters [33]. It has two major tasks as follows (repeat these steps till convergence): ...
Athletes represent the apex of physical capacity filling in a social picture of performance and build. In light of the fundamental contrasts in athletic capacities required for different games, each game demands an alternate body type standard. Because of the decent variety of these body types, each can have an altogether different body standard. Nowadays, a large number of athletes participate in assessments and a large number of human hours are spent on playing out these assessments every year. These assessments are performed to check the physical strength of athletes and evaluate them for different games. This paper presents a machine learning approach to the physical assessment of athletes known as NueroFATH. The proposed NueroFATH approach relies on neuro-fuzzy analytics that involves the deployment of neural networks and fuzzy c-means techniques to predict the athletes for the potential of winning medals. This can be achieved using athletes’ physical assessment parameters. The goal of this study is not only to identify the athletes based on which group they fall into (gold/silver/bronze), but also to understand which physical characteristic is important to identify them and categorize them in a medal group. It was determined that features, namely height, body mass, body mass index, 40 m and vertical jump are the most important for achieving 98.40% accuracy for athletes to classify them in the gold category when they are in the bronze category. Unsupervised learning showed that features, namely body mass, body mass index, vertical jump, med ball, 40 m, peak oxygen content, peak height velocity have the highest variability. We can achieve upto 97.06% accuracy when features, i.e., body mass, body mass index, vertical jump, med ball, 40 m, peak oxygen content, peak height velocity were used.
... Some ML-based approaches are also used to detect and eliminate malicious nodes. Rathore et al. [13] used biological inspirations and ML to identify fraudulent nodes. An enhanced trust model based on the radial base artificial neural network (RBANN) was presented by Yasin et al. [14] to predict each node's future behavior and detect malicious nodes. ...
When a wireless sensor node’s wireless communication fails after being deployed in an inaccessible area, the lost node cannot be repaired through a debugging interaction that relies on that communication. Visible light communication (VLC) as a supplement of radio wave communication can improve the transmission security at the physical layer due to its unidirectional propagation characteristic. Therefore, we implemented a VLC-based hybrid communication debugging system (HCDS) based on VLC using smartphone and sensor node. For the system’s downlink, the smartphone is taken as the VLC gateway and sends the debugging codes to the sensor node by the flashlight. To improve the transmission efficiency of the downlink, we also propose a new coding method for source coding and channel coding, respectively. For the source coding, we analyze the binary instructions and compress the operands using bitmask techniques. The average compression rate of the binary structure reaches 84.11%. For the channel coding, we optimize dual-header pulse interval (DH-PIM) and propose overlapped DH-PIM (ODH-PIM) by introducing a flashlight half-on state. The flashlight half-on state can improve the representation capability of individual symbols. For the uplink of HCDS, we use the onboard LED of the sensor node to transmit feedback debugging information to the smartphone. At the same time, we design a novel encoding format of DH-PIM to optimize uplink transmission. Experimental results show that the optimized uplink transmission time and BER are reduced by 10.71% and 22%, compared with the original DH-PIM.
... One approach is to completely shut-down the access of the device to that user. The other approach would be to gradually scale down the access rights to that user using exponential scaling techniques as described in [26]. ...
Internet of Medical Things (IoMTs) is fast emerging, thereby fostering rapid advances in the areas of sensing, actuation and connectivity to significantly improve the quality and accessibility of health care for everyone. Implantable medical device (IMD) is an example of such an IoMT-enabled device. IMDs treat the patient’s health and give a mechanism to provide regular remote monitoring to the healthcare providers. However, the current wireless communication channels can curb the security and privacy of these devices by allowing an attacker to interfere with both the data and communication. The privacy and security breaches in IMDs have thereby alarmed both the health providers and government agencies. Ensuring security of these small devices is a vital task to prevent severe health consequences to the bearer. The attacks can range from system to infrastructure levels where both the software and hardware of the IMD are compromised. In the recent years, biometric and cryptographic approaches to authentication, machine learning approaches to anomaly detection and external wearable devices for wireless communication protection have been proposed. However, the existing solutions for wireless medical devices are either heavy for memory constrained devices or require additional devices to be worn. To treat the present situation, there is a requirement to facilitate effective and secure data communication by introducing policies that will incentivize the development of security techniques. This paper proposes a novel electrocardiogram authentication scheme which uses Legendre approximation coupled with multi-layer perceptron model for providing three levels of security for data, network and application levels. The proposed model can reach up to 99.99% testing accuracy in identifying the authorized personnel even with 5 coefficients.
... In dark entire assault a vindictive node endeavors to follow and draw in the rush hour gridlock in the network, when the adversary can get to, convey and partake in the network the whole readings could be influenced particularly in the hierarchal network topologies where information is transmitted going through a few nodes. Hi flood assault is fused by a remote foe who can flood hi solicitation to any real node in the network and break the security system, while in wormhole assault the assailant record the packets and forward to another area, at least one phony nodes are utilized with a course between them, when the malevolent node begins its work a phony course is utilized to give a way that is shorter than the first one, and subsequently the information is burrowed inside the unfortunate course [9]. ...
WSN offers a down to earth arrangement of conveyed detecting, preparing, communication and control while ANN's self-adaptively and nonlinear mapping capacity make it progressively invaluable in displaying nonlinear framework or framework with obscure dynamics. We feel that the blend of WSN and ANN can be an incredible demonstrating arrangement. First, a trainable ANN demonstrate assembled itself from test information, subsequently, adequate information sources are important to acquire a precise ANN show. The rich sensor information from WSN consequently can be utilized in preparing the ANN. Likewise, WSN information based ANN displaying has high down to earth esteems: the conduct of certain framework is exceptionally perplexing and hard to examine, particularly when numerous nonlinear and time-differing impacts are available.
... Figure 1 shows the layer model of security in wireless sensor networks. [15] Security in the Wireless Sensor Networks has various difficulties, some common are: dynamically changing topology, wireless communication among the sensor nodes, infrastructure-less framework, and limited physical resources like energy source, memory capacity and very low communication bandwidth [11] [13]. Numerous analysts proposed so many threats handling models and diverse security protocols for secure data communication and routing in WSN. ...
Wireless Sensor Networks (WSNs) are formed by
deploying as large number of sensor nodes in an area for the
surveillance of generally remote locations. A typical sensor node
is made up of different components to perform the task of
sensing, processing and transmitting data. WSNs are used for
many applications in diverse forms from indoor deployment to
outdoor deployment. The basic requirement of every application
is to use the secured network. Providing security to the sensor
network is a very challenging issue along with saving its energy.
Many security threats may affect the functioning of these
networks. WSNs must be secured to keep an attacker from
hindering the delivery of sensor information and from forging
sensor information as these networks are build for remote
surveillance and unauthorized changes in the sensed data may
lead to wrong information to the decision makers. This paper
studies the various security issues and security threats in WSNs.
Also, gives brief description of some of the protocols used to
achieve security in the network. This paper also compares the
proposed methodologies analytically and demonstrates the
findings in a table. These findings can be used further by other
researchers or Network implementers for making the WSN
secure by choosing the best security mechanism.
Keywords: WSN, Security, Threats, Security Protocols.
