Mobile ad hoc network (MANET) is a collection of autonomous mobile nodes forming an ad hoc network without fixed infrastructure. Dynamic topology property of MANET may degrade the performance of the network. However, multipath selection is a great challenging task to improve the network lifetime. We proposed an energy-aware multipath routing scheme based on particle swarm optimization (EMPSO) that uses continuous time recurrent neural network (CTRNN) to solve optimization problems. CTRNN finds the optimal loop-free paths to solve link disjoint paths in a MANET. The CTRNN is used as an optimum path selection technique that produces a set of optimal paths between source and destination. In CTRNN, particle swarm optimization (PSO) method is primly used for training the RNN. The proposed scheme uses the reliability measures such as transmission cost, energy factor, and the optimal traffic ratio between source and destination to increase routing performance. In this scheme, optimal loop-free paths can be found using PSO to seek better link quality nodes in route discovery phase. PSO optimizes a problem by iteratively trying to get a better solution with regard to a measure of quality. The proposed scheme discovers multiple loop-free paths by using PSO technique.

/pdf/energy-aware-multipath-routing-scheme-based-on-particle-44ruf5b8je.pdf

Energy-Aware Multipath Routing Scheme Based on Particle Swarm Optimization in Mobile Ad Hoc Networks.

Swarm intelligence for clustering — A systematic review with new perspectives on data mining

Vehicular ad hoc network (VANET) assists in improving road safety, traveller comfort, and intelligent transportation systems to a great extent Dedicated short-range communications technology is specially designed for VANET to form communication among vehicles and vehicles to infrastructure The lack of router devices in the flat vehicle-to-vehicle network structure of VANET may raise complicated issues like scalability, resource scarcity, reliability, and hidden terminal problem inside the network The concept of vehicle clustering is introduced in VANET to improve network performance by handling all such issues This paper provides an in-depth classification of clustering protocols in VANET based on their design objectives Two broad categories, generalized and application dependent, are considered to review on clustering protocols in VANET In generalized clustering protocol, cluster design aims to achieve their primary objective, ie, the formation of a robust cluster having a long sustainable life, While in application dependent clustering protocols, cluster design aims to improve the performance of specific applications (ie, target tracking, traffic estimation, misbehaviour detection, privacy preservation, certificate revocation, etc) on various performance metrics After this, the paper explores essential research contributions of each category comprehensively Detailed analysis of existing research contributions is also provided after comparing them on many important metrics Finally, the merits and demerits of existing protocols are also listed Our attempt to encourage researchers of the concerned field by providing an extensive analysis of clustering in VANET

State-of-the-art approach to clustering protocols in VANET: a survey

Vehicular Ad hoc NETworks (VANETs) possess a dominant role in the development of Intelligent Transport Systems (ITS). VANETs, due to the rapid mobility of vehicles are a highly dynamic network. In order to make the network topology suitable for effective communication, clustering algorithms are widely used. Clustering algorithms enable VANET to efficiently handle the changing topology for Medium Access Control (MAC), routing and several other applications. In this work we put forward a Reputation based Weighted Clustering protocol (RWCP) for VANETs. The RWCP is framed by taking the direction of vehicles, position, velocity, number of nearby vehicles, lane ID, and the reputation of each node into consideration for stabilizing the VANET topology. On the other hand, dealing with diverse control parameters of RWCP makes optimizing a challenging task. The work employs a multi-objective problem which takes the RWCP’s parameters as the input and aims at providing enhanced cluster lifetime, Improved packet delivery ratio and reduced cluster overhead. Multi Objective Firefly Algorithm (MOFA), an evolutionary approach is used for optimizing the RWCP’s parameters. Simulations were done using the TETCOS NetSim simulator and MOEA framework for optimization. The results are evaluated with similar evolutionary optimization techniques. Experiments were conducted with realistic maps from OpenStreet Maps and its results were compared with other multi-objective optimization techniques: Multi-objective Particle Swarm Optimization (MOPSO) and Comprehensive learning Particle Swarm Optimization (CL-PSO). The investigation proposes that, the proposed methodology performs well concerning the Mean Cluster Lifetime, Packet Delivery Ratio and Control Packer Overhead.

A Reputation based Weighted Clustering Protocol in VANET: A Multi-objective Firefly Approach

In the context of wireless mobile ad hoc networks, node clustering is a well-known solution for handling the scalability issue. While existing work focused on unstructured (i.e., flat) networks, this paper investigates a clustering algorithm to handle stable size-restricted clusters for structured (i.e., group-based) networks. In addition, we have identified that the ad hoc network clustering literature lacks a theoretical framework. This paper fills this gap by proposing to use coalition game theory, identifying coalitions to clusters and players to nodes. This theoretical framework allows us to derive a novel generic distributed node clustering algorithm. The algorithm is proved to converge to Nash-stable partitions. It is based on the concept of switch operations, where nodes take decision whether to leave or not their current coalition based on the coalition values. These decisions are made independently on any node individual payoff, meaning that the coalition formation game has a transferable utility. This generic algorithm is then tailored to both structured and unstructured networks, by defining judiciously the value functions and the heuristics dedicated to selecting suitable switch operations. Based on extensive simulations, we show that our proposed solutions outperform the existing ones especially in terms of cluster size and stability.

A Coalition Formation Game for Distributed Node Clustering in Mobile Ad Hoc Networks

Today's pandemic situation has transformed the way of educating a student. Education is undertaken remotely through online platforms. In addition to the way the online course contents and online teaching, it has also changed the way of assessments. In online education, monitoring the attendance of the students is very important as the presence of students is part of a good assessment for teaching and learning. Educational institutions have adopting online examination portals for the assessments of the students. These portals make use of face recognition techniques to monitor the activities of the students and identify the malpractice done by them. This is done by capturing the students' activities through a web camera and analyzing their gestures and postures. Image processing algorithms are widely used in the literature to perform face recognition. Despite the progress made to improve the performance of face detection systems, there are issues such as variations in human facial appearance like varying lighting condition, noise in face images, scale, pose etc., that blocks the progress to reach human level accuracy. The aim of this study is to increase the accuracy of the existing face recognition systems by making use of SVM and Eigenface algorithms. In this project, an approach similar to Eigenface is used for extracting facial features through facial vectors and the datasets are trained using Support Vector Machine (SVM) algorithm to perform face classification and detection. This ensures that the face recognition can be faster and be used for online exam monitoring.

Design of face detection and recognition system to monitor students during online examinations using Machine Learning algorithms

In India, tea is the most consumed and popular beverage, all over the world too. It is one of the popular and widely cultivated perennial plantation crop in our state. Their productions are heavily affected and destroyed by different diseases. Deep learning is a machine learning technique that teaches a computer with the help of pre-existing data and enables the system to do what comes naturally to humans. The main challenge faced in deep learning is that it needs a large amount of training data. In this model, we are going to propose a unique idea to detect and classify diseases in tea leaves by incorporating deep learning techniques. The critical processes in this tea leaf disease classification are health monitoring and disease detection and are essential for sustainable agriculture. Manually observing the tea leaf diseases is a tedious and time taking processthat requires skilled workers, extra time, and manpower with knowledge about tea leaf diseases. Hence, image processing models were widely utilized for these kinds of disease detections. In this proposed work, we have applied the Convolutional Neural Network(CNN) model with 1 input layer, 4 convolution layers, and 2 fully connected layers. The image is passed to the input layer. The convolution layers mainly extract features from the input image in the dataset and the output layer classifies the given image to 8 classes such as the normal leaf, Algal leaf spot, Gray blight, White spot, Brown blight, Red scab, Bud blight, and Grey blight.

Automatic Detection of Tea Leaf Diseases using Deep Convolution Neural Network

Agriculture has become an important thing in everyday life. Among this, fruits are a great thing in every day life. Classification of fruits based on their accuracy is a decent approach to all the fruit sellers. There is many parallelism between apple and cherry and various kinds of similarities are present in many types of fruits, so the classification plays an important role. However, there are troubles in fruit classification using machine learning algorithms like Support Vector Machine (SVM) and Convolutional Neural Network(CNN). So, the methods of CNN, pooling layers and fully connected network have been applied to overcome the problems. The CNN and pooling layers have been applied to extract the features of the fruits. To expose this scheme, various fruits such as Apple, Blueberry, Cherry, Grape blue, Guava, Kiwi, Lemon, Papaya, Strawberry, Plum, Tomato and Mango are considered. By implementing this project, the accuracy of fruit classification is increased.

Automatic Fruit Detection System using Multilayer Deep Convolution Neural Network

Alzheimer's disease is one amongst the progressive disorder that cruelly affects the brain cells. It causes the death of nerve cells and tissue loss in brain. It usually tends to star ...

Diagnosis of Alzheimer's Disease from Brain Magnetic Resonance Imaging Images using Deep Learning Algorithms

“Mobile Ad Hoc Network” (MANET) is a form of ad hoc network in which the devices are dynamic and configure themselves during the fly. Hence, for an energy efficient and stable communication to be established among the nodes, the nodes must be organized into groups called clusters. Associativity is one among the good metrics that can configure the speed of a node with respect to its neighbour. In the proposed work, along with associativity, residual energy and nodes degree are the multiple metrics that are been considered to elect the clusterheads. Optimal clustering of nodes in dynamic MANET is an NP-Hard problem that can be solved by tools that include evolutionary computation, swarm optimization, etc. Among the swarm optimization methods, genetic algorithm (GA) and particle swarm optimization (PSO) techniques were been proved to be the efficient and promising methodologies for solving the optimization problems. These techniques are finding their popularity in wide range due to their adaptable nature and ability to optimize even large complex search spaces applied to non-differentiable cost functions. Hence, the main objective of the proposed work is to select stable clusterhead by considering multiple metrics that are used to frame the fitness function for GA and PSO. Since the proposed work includes energy as one of the metrics, it can be used in distributed MANET environment with nodes having different energy levels. Since, the associativity of nodes reflects the stability with their neighbours, the proposed system can also be used in dynamic and static environment. The proposed work has been simulated with both GA and PSO, and the results have shown that PSO resulted with better performance compared to GA, in terms of clusterhead count under various simulation environments.

R.S. Latha

Papers

Design of face detection and recognition system to monitor students during online examinations using Machine Learning algorithms

Automatic Detection of Tea Leaf Diseases using Deep Convolution Neural Network

Automatic Fruit Detection System using Multilayer Deep Convolution Neural Network

Diagnosis of Alzheimer's Disease from Brain Magnetic Resonance Imaging Images using Deep Learning Algorithms

Adaptive cluster formation in MANET using particle swarm optimization