The Pending Interest Table (PIT) in Named Data Networking (NDN) plays a crucial role by storing state information of requests within the router, enabling efficient data packet routing back to the requester. However, this mechanism is vulnerable to Interest Flooding Attacks (IFA), where an attacker sends a large number of malicious requests to overwhelm the PIT, disrupting network performance. Previous research primarily focused on offline detection of IFA using selected features and machine learning techniques. In this work, we build on these findings by deploying a trained Artificial Neural Network (ANN) classifier on each NDN router for real-time, online detection of IFA. Additionally, we introduce a novel traceback-based mitigation strategy activated upon detection, significantly improving the network’s resilience against such attacks. Our proposed method demonstrates superior performance in terms of satisfaction ratio and throughput for legitimate consumers compared to existing approach.

Named Data Networking (NDN) aims to fix the flaws of TCP/IP networks. NDN ensures provenance and integrity by requiring publishers to sign each content, which consumers can verify. This makes NDN more secure than TCP/IP. However, NDN is prone to Interest Flooding Attacks (IFA). In IFA, attackers fill the Pending Interest Tables (PITs) of NDN routers with fake entries by requesting non-existent content. Many methods have been proposed to counter IFA. Most of these methods rely on statistical thresholds, which reduce detection accuracy. Our previous work showed that using machine learning improves IFA detection accuracy. This paper introduces a Controller-Based Intelligent Detection and Mitigation (CBIDM) approach for online IFA detection. It deploys a trained Artificial Neural Network (ANN) detector on NDN routers. Additionally, a traceback-based mitigation method is applied using a central controller. The controller collects topology and attack data from each router. Routers then use this data for IFA mitigation. The proposed approach is more efficient than existing methods in terms of data packets received and satisfaction ratio.

The performance of named data networking (NDN) depends on the caching efficiency of routers. Cache pollution attack (CPA) refers to colonization of unpopular contents in the content store (CS) of an NDN router, which leads to declined quality of service (QoS) in NDN. CPA has very few solutions proposed for its mitigation. Most of these solutions are based on the statistics of the router itself. However, an attacker can influence these statistics by requesting unpopular contents repeatedly. This article proposes a new parameter for the detection of CPA, which is based on the number of distinct users requesting interest packets for a content over a period of time. The local popularity of the attackers' content does not affect the proposed approach. The results show that the proposed approach consumes less storage, reduces processing time, and more effectively mitigates the CPA, as compared to the other existing approaches. Compared with the previous approaches, the proposed approach exhibits an improvement of approximately 28.14% to 36.80%.

Heart disease is one of the leading causes of fatality. A reliable and robust prediction system is needed for people to take preventive measures and medication beforehand and develop a proactive lifestyle accordingly. Various vital features determine human heart health, and it is important to recognize the critical ones that could be determining the chances of getting heart disease in the future. The various machine learning algorithms based on the critical features could predict heart disease more accurately. This article employs evolutionary algorithms like Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) for the feature selection to improve the accuracy of machine learning algorithms further. GA and PSO combined with Naïve Bayes (NB), Support Vector Machine (SVM), and J48 have been applied for feature selection. After selecting the significant features, the effectiveness of the feature selection algorithm is evaluated by applying machine learning approaches on the complete dataset and reduced dataset. Five different machine learning approaches, viz., NB, SVM, Decision Tree (DT), Logistic Regression (LR), and Random Forest (RF) algorithm, have been used to predict heart disease and thus measure the effectiveness of the feature selection approaches. The results indicate that the GA has been the most effective algorithm for feature selection as it enhances the prediction accuracy most.

Students face many problems like mental stress, peer pressure, and health issues in college, but they do not report these due to lack of awareness, shy nature, or fear. This article proposes a platform that will unite students and the authority responsible for resolving these problems. The platform's core has a query classifier that uses text classification for categorizing the query. Text classification has already been used widely in many different problems like the chatbot, query categorization, intent, and detection. This is the first attempt to use text classification for categorizing students' queries. The query and category data have been collected from more than 400 students. Data pre-processing is done to convert textual data into numerical data. Dimensionality reduction has been applied in order to minimize the number of features. Five different machine learning (ML) approaches are applied to evaluate the performance of query categorization. K-fold cross-validation has been applied, and the ML approaches have been compared using accuracy, precision, recall, and F1-measure. The results show that Multi-Layer Perception with Back Propagation (MLP with BP) performs better than other classifiers in terms of all the metrics.

Distributed Denial-of-Service (DDoS) attacks have recently increased exponentially in numbers. With the advent of the Internet-of-things (IoT), it becomes easy for attackers to perform a DDoS attack. IoT devices are resource constraints; therefore, their security is compromised. Adversary takes the benefit of compromised security and captures the IoT devices; these captured devices are used to perform a DDoS attack. This article proposes machine learning-based techniques for the detection of DDoS. The research involves performing a DDoS attack in an IoT network and then capturing the attack traffic and regular traffic using Wireshark. The captured traffic is processed to fetch its various features, and machine learning is applied for classification that can distinguish the attack traffic from the regular traffic. Four different machine learning-based approaches have been applied to the collected data to detect malicious traffic. Naïve Bayes turns out to be the better performing algorithm for this purpose.

The present work derives analytical solutions of advection-dispersion equation (ADE) with temporal coefficients, and a pollutant's point source moving linearly along the axis of a one-dimensional semi-infinite domain. The source is considered a varying and a uniform pulse source, respectively. The dispersion of pollutant originating from a varying pulse source may be supposed to occur along groundwater flow domain, and that from a uniform pulse source in an open medium like air or along a river flow. The location of the input concentration that is the pollutant's concentration emanating from the source in an open medium or that reaching the groundwater domain being infiltrated from its source on the ground, is considered moving linearly along the flow direction. The motion of the source is described through an asymptotically increasing temporal function. The illustration of the analytical solution clearly reflects this feature. It also renders that the concentration pattern of the proposed solution is proximal to that of an existing solution obtained with the stationary source. The pertinent existing solutions may also be derived from the proposed solutions. The proposed solutions are found approximate but it is also found that the error of approximation of one of them is too small to have any effect on the concentration pattern. To get these solutions, firstly, the moving source is reduced into a stationary source at the origin, then the governing equations including the ADE, are made free from the three temporal functions, one occurring in the time-dependent position of the source, and the other two as the coefficients of the ADE. In this process, three new position variables, and a new time variable are introduced using as many coordinate transformations. Then the Laplace Integral Transformation Technique (LITT) is used to get the final solutions. The solution in Laplacian domain with uniform pulse source is obtained as a special case of that with the varying pulse source.

NDN is a futuristic networking model developed to overcome the limitation of TCP/IP. NDN uses the name of the content rather than user ID (such as IP address) for forwarding and routing. In this work, we have tried to compare the performance of NDN based network with the TCP/IP-based network using the ns-3 simulator. Two topologies, i.e., simple topology and XC topology, are used for the simulation, and a comparison has been made based on the average delay

: Heart disease is one of the hugest reasons for mortality on the planet today. Expectation of cardiovascular disease is a basic test in the region of clinical data investigation. Health care field has an enormous proportion of data, for setting up those data certain methods are used. Data mining is one of the strategies routinely used. Heart disease is the Leading purpose behind death around the globe. This System predicts the developing possibilities of Heart Disease. The results of this System give the odds of happening heart disease as far as percentage. The datasets used are classified with respect to clinical parameters. This System assesses those parameters using data mining classification strategy. In this paper, we propose a novel strategy that targets finding noteworthy highlights by applying AI strategies bringing about improving the precision in the forecast of cardiovascular disease. The expectation model is presented with various mixes of highlights and a few known classification methods. The datasets are dealt with in python programming using two major Machine Learning Algorithm to be explicit Random Forest Algorithm and Gradient Boosting Tree Algorithm which shows the best algorithm among these two in regards to precision level of heart disease.

Software‐defined networking (SDN) is one of the most used network architecture that divides the forwarding plane and control plane. The SDN centrally observes and regulates the network through a software control in the control plane, called as controller. Multiple controllers are needed to manage the software‐defined WAN (SD‐WAN) for handling the scalability and reliability issues of the network as one controller is not enough. Deploying numerous controllers efficiently to improve the performance of the network is known as controller placement problem (CPP). This paper proposes a Varna‐based optimization (VBO) for a reliable CPP that minimizes the total average latency of SDN. To the best of our knowledge, the proposed work is a novel approach, which is compared with particle swarm optimization, teacher learning‐based optimization, and Jaya algorithms to solve reliable CPP. The experimental results show that VBO gives better performance than teacher learning‐based optimization (TLBO), PSO, and Jaya algorithms for the popular topologies that are publicly available.

SDN (software defined networks) is a programmable network architecture that divides the forwarding plane and control plane.It can centrally manage the network through a software program, i.e., controller.Multiple controllers are required to manage the current software defined WAN.Placing multiple controllers in a network is known as controller placement problem (CPP).Only one controller is not capable to handle the scalability and reliability issues.To tackle these issues, multiple controllers are required.Efficient deployment of controllers in SDN is used to improve the performance and reliability of the network.To the best of our knowledge, this is the first attempt to minimize the total average latency of reliable SDN along with the implementation of TLBO and PSO algorithms to solve CPP.Our experimental results show that TLBO outperforms PSO for publicly available topologies.

In the present study, analytical solutions of the advection dispersion equation (ADE) with spatially dependent concave and convex dispersivity are obtained within the fractal and the Euclidean frameworks by using the extended Fourier series method. The dispersion coefficient is considered to be proportional to the n th power of a non-homogeneous quadratic spatial function, where the index n is considered to vary between 0 and 1.5 so that the spatial dependence of dispersivity remains within the limit to describe the heterogeneity in the fractal framework. Real values like n = 0.5 and 1.5 are considered to delineate heterogeneity of the aquifer in the fractal framework, whereas integral values like n = 1 represent the same in the Euclidean sense. A concave or convex variation is free from demanding a limiting value as in the case of linear variation, hence it is more appropriate in the ambience of many disciplines in which ADE is used. In this study, concentration at the source site remains uniform until the source is present and becomes zero once it is annihilated forever. The analytical solutions, validated through the respective numerical solutions, are obtained in the form of an extended Fourier series with only first five terms. They are convergent to the desired concentration pattern and are stable with the Peclet number. It has been possible because of the formulation of a new Sturm–Liouville problem with advective information. The analytical solutions obtained in this paper are novel.

Contents such as audios, videos, and images, contribute most of the Internet traffic in the current paradigm. Secure content sharing is a tedious issue. The existing security solutions do not secure data but secure the communicating endpoints. Named data networking (NDN) secures the data by enforcing the data publisher to sign the data. Any user can verify the data by using the public key of the publisher. NDN is resilient to most of the probable security attacks in the TCP/IP model due to its new architecture. However, new types of attacks are possible in NDN. This article surveys the most significant security attacks in NDN such as interest flooding attacks, cache privacy attacks, cache pollution attacks, and content poisoning attacks. Each attack is classified according to their behavior and discussed for their detection techniques, countermeasures, and the affected parameters. The article is an attempt to help new researchers in this area to gather the domain knowledge of NDN. The article also provides open research issues that could be addressed by researchers.

Interest flooding attack (IFA) is one of the most severe attacks in named data networking (NDN). Due to IFA, the pending interest table (PIT) of NDN routers get filled with entries of malicious requests making it unavailable for legitimate users. Statistical approaches detect IFA using one or two features, but they cannot handle the variation of more than two features. To overcome this limitation a machine learning-based model has been proposed for the detection of IFA. First, we model IFA and collect features. Next, we select the most prominent features based on information gain-based ranking. Last, we use these features for the detection of IFA using machine learning approaches. Experimental results show that machine learning-based approaches perform better than statistical approaches regarding accurate detection.

NDN is one of the most prominent candidates for the future network. It has a data-centric network architecture in which fetching of content, forwarding requests, and routing is done through the name of the content. Content caching is an essential feature in NDN as its performance depends upon its efficiency of caching contents. Cache in NDN is open for all types of requesters. An attacker can probe an interest packet and find out whether the content corresponding to the interest packet is cached or not by observing the time difference between the timestamps at which the content is received and the request is sent. This attack is called timing-based attack (TBA). Existing solutions for TBA are based on securing individual contents. Therefore, they use large size table, which have data related to each content. Managing these large tables is expensive in terms of space and time. Also, the existing approaches fail to mitigate TBA or can be attacked by the attacker. To counter these limitations a Namespace-Based Privacy (NBP) approach has been proposed for content generation and handling its privacy. Additionally, an approach is proposed which detects the attack pattern at the gateway router itself and triggers the countermeasure in case of attack. The results prove that the proposed approach is better than the existing eminent approaches.

A spatio-temporal continuum model is developed for avascular tumor growth in two dimensions using fractional advection-diffusion equation as the transportation in biological systems is heterogeneous and anomalous in nature (non-Fickian). The model handles skewness with a suitable parameter. We study the behavior of this model with a set of parameters, and suitable initial and boundary conditions. It is found that the fractional advection-diffusion equation based model is more realistic as it provides more insightful information for tumor growth at the macroscopic level.

This paper presents an analytical solution of the advection-dispersion equation (ADE) with the dispersion coefficient and velocity being directly proportional to the spatial linear nonhomogeneous function. It is one of the solutions obtained in two particular cases in which the dispersion coefficient and velocity are (1)spatially dependent and (2)temporally dependent. These analytical solutions, particularly the one addressed here, which are of great importance in the existing hydrological theories, had been elusive. These theories assert the spatio-temporal dependence of the transport coefficients of the ADE to frame pollutant transport in aquifers in real situations. This study is carried out in an infinite medium for instantaneous and continuous point sources. The source of the pollutant's solute mass is defined through a nonhomogeneous production term in the ADE. Darcy velocity is considered to be spatio-temporally dependent in nondegenerate form. According to hydrodynamic dispersion theory, the dispersion coefficient is proportional to the nth power of the velocity, where n varies from 1 to 2. This paper compares solute transport problems for n=1 and n=2 and obtains expected results. Green's function method (GFM) is used to obtain an analytical solution in general form, from which those for instantaneous and continuous sources in different combinations of spatial and temporal dependence are derived. The spatial dependence is considered linear, whereas temporal dependence is considered asymptotic, exponential, and sinusoidal. To use GFM, a moving coordinate transformation equation is developed which reduces the ADE into a solvable form. The analytical solutions of known dispersion problems are derived as particular cases. The effect of spatial and temporal dependence of the transport parameters on the solute transport is shown through illustrations.