Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2019 | Book

Distributed Query Processing Optimization in Wireless Sensor Network Using Artificial Immune System Read chapter Read first chapter

Computational Intelligence in Sensor Networks

Editors: Bijan Bihari Mishra, Dr. Satchidanand Dehuri, Dr. Bijaya Ketan Panigrahi, Ajit Kumar Nayak, Prof. Dr. Bhabani Shankar Prasad Mishra, Dr. Himansu Das

Publisher: Springer Berlin Heidelberg

Book Series : Studies in Computational Intelligence

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

This book discusses applications of computational intelligence in sensor networks. Consisting of twenty chapters, it addresses topics ranging from small-scale data processing to big data processing realized through sensor nodes with the help of computational approaches. Advances in sensor technology and computer networks have enabled sensor networks to evolve from small systems of large sensors to large nets of miniature sensors, from wired communications to wireless communications, and from static to dynamic network topology. In spite of these technological advances, sensor networks still face the challenges of communicating and processing large amounts of imprecise and partial data in resource-constrained environments. Further, optimal deployment of sensors in an environment is also seen as an intractable problem. On the other hand, computational intelligence techniques like neural networks, evolutionary computation, swarm intelligence, and fuzzy systems are gaining popularity in solving intractable problems in various disciplines including sensor networks. The contributions combine the best attributes of these two distinct fields, offering readers a comprehensive overview of the emerging research areas and presenting first-hand experience of a variety of computational intelligence approaches in sensor networks.

Table of Contents

Frontmatter
Chapter 1. Distributed Query Processing Optimization in Wireless Sensor Network Using Artificial Immune System
Abstract
With the great advancement in wireless technology, number of wireless sensor network applications have increased in which different sensor nodes communicates with each other via sending data among themselves. Query for communication among sensor nodes can be framed in different forms leading into different computation cost. So, the generation and selection of query plan of minimum cost becomes combinatorial in nature which cannot be solved in polynomial time to achieve global optimal cost of data communication. One of the solution to address this problem is nature inspired algorithms. These algorithms have served to number of real life intricate problems. Amidst of all algorithms, bio-inspired algorithms have largely accepted to assist such problems. Artificial immune system (AIS), one of bio-inspired algorithm is inspired from natural human immune system has been explored here. Clonal selection process, one of AIS approach has been discussed in this chapter to generate optimal distributed query plans in distributed wireless sensor network.
Ruby Rani
Chapter 2. Computational Intelligence Techniques for Localization in Static and Dynamic Wireless Sensor Networks—A Review
Abstract
This chapter describes one of the major challenges in technology advancement of Wireless Sensor Networks (WSNs), i.e., Localization in WSNs. In recent years, sensor node localization is an emerging research area in WSNs. The sensor data become useless, if we do not know the location of the reporting node. Coordinates determination of the sensor node is a challenging problem and it is referred as localization problem. The nodes which has unknown coordinates is termed as target Nodes. Various localization methods can be utilized to find out the location of sensor nodes, those coordinates are not known in a system/network. Efficient WSN localization can be treated as multi-dimensional optimization problem which can be addressed through population based stochastic techniques, which involves the minimization of a function of differences between Euclidean and measured distance between sensor nodes. In this chapter various connectivity, range information and mobility based localization algorithms have been discussed. For optimizing the results of these algorithms, various computational intelligence (CI) based optimizing algorithms like Particle Swarm Optimization, Biogeography Based Optimization, Firefly Algorithm and Genetic Algorithm have been discussed. A choice between these algorithm is influenced by the localization accuracy expected to be and convergence rate.
Singh Parulpreet, Khosla Arun, Kumar Anil, Khosla Mamta
Chapter 3. Nature Inspired Algorithm Approach for the Development of an Energy Aware Model for Sensor Network
Abstract
The unique and strong characteristics of Wireless Sensor Network (WSN) have paved a way to many real time applications. Nevertheless, the WSN has their own set of challenges likewise data redundancy, resource constraints, security, packet errors and variable-link capacity etc. Among all, management of energy resource is of high importance as the efficient energy mechanism increases the lifespan of the network. Thereby providing good Quality of Service (QoS) demanded by the application. In WSN even though the energy is required for data acquisition (sensing), processing and communication, more energy are consumed during communication where transmission and retransmission of packets are quite often. In WSN data is transmitted from source to destination where at the destination site the data are analyzed using appropriate data mining techniques to convert data into useful information, and knowledge is extracted from that information to aid the user in efficient decision making. The transmission of data can be either through a single hop or via multiple hops. In single hop, a node is just a router where as in multi hop the node acts as both data originator and router. Thus, consuming more amount of energy and in a multi hop if any of the nodes fails it leads to many large retransmissions thus making a system highly susceptible for energy consumption. Many researchers have dedicated and devoted their time, energy and resources in order to come up with better solutions to answer this problem. This chapter is one such effort to provide a better solution to reduce the energy consumption of sensors. Here, the beauty of DBSCAN clustering technique has been fully exploited in order to develop a spatiotemporal relational model of sensor nodes, followed by the selection of representative subset using measure trend strategy and finally meeting the criteria for identifying the best optimal path for transmission of data using few nature inspired algorithms like Ant Colony Optimization (ACO), Bees Colony Optimization (BCO), and Simulated Annealing (SA).
Srinivas Narasegouda, M. Umme Salma, Anuradha N Patil
Chapter 4. Routing Protocols
Abstract
Wireless Sensor Network is one of the most emerging technologies that consist of the small and low-cost sensor node to sense various kinds of environmental condition and statistics. In most of its applications, the sensors nodes are initially deployed randomly and then they are expected to self-organize themselves using protocols or algorithms. Routing protocol ensures an optimum path connecting source and destination node either in a single path or multipath communication. Since the sensor nodes are equipped with limited power and communication bandwidth, researchers aim to find an energy efficient routing protocols for WSN application. Routing protocols are broadly classified into seven different categories such as Location-based Protocols, Data-centric Protocols, Hierarchical Protocols, Multipath-based Protocols, Heterogeneity-based Protocols and QoS-based protocols. Routing algorithms may differ depending on application or the sensor network architecture, but the main design criterion of any WSN will be to keep the nodes functioning as long as possible in order to enhance the network lifetime with a limited expenditure of energy. As clustering is by far the best approach for efficient energy utilization, hierarchical protocols such as LEACH, TEEN, SEP, PEGASIS, DEEC, HEED, APTEEN are some of the widely used protocols for transferring data from node to sink or base station. In this chapter, various types of routing protocols, their advantages, and disadvantages along with the field of application will be discussed in brief.
T. M. Behera, U. C. Samal, S. K. Mohapatra
Chapter 5. Distance Based Enhanced Threshold Sensitive Stable Election Routing Protocol for Heterogeneous Wireless Sensor Network
Abstract
The technological advancements have led to the revolution in sensing technology. Wireless Sensor Network (WSN) has been one of the important researched areas which have attracted attention of various researchers. The battery constraints have led to the development of energy efficient routing protocols. Past studies ignore the importance of distance factor for the selection of Cluster Head (CH), which led to inefficient energy consumption in the network. In this chapter, Distance based Enhance Threshold Sensitive Stable Election Protocol (DETSSEP) has been proposed in which CH selection is based on networks average energy, nodes remaining energy and distance between nodes and Base Station (BS). Dual hop communication is used between distant CHs and BS to achieve uniform energy consumption in the network. It is observed through the simulation analysis that DETSSEP outperforms Enhance Threshold Sensitive Stable Election Protocol (ETSSEP) in various performance matrices viz. stability period, throughput, lifetime and remaining energy of the network.
Richa Rani, Deepti Kakkar, Parveen Kakkar, Ashish Raman
Chapter 6. Deployment Strategies in Wireless Sensor Networks
Abstract
Deployment in a wireless sensor network is the first step towards constructing a network topology. There are existing techniques using the conventional approaches of geometry or simply random positions. However, with the advancement in Wireless sensor network technologies, it is now proved that efficient sensor node placement is essential for quality of service enhancements of such networks be it in terms of battery conservation, lifetime improvement, interference or simply efficient communications.
Itu Snigdh
Chapter 7. Cross-Layer Designs in Wireless Sensor Networks
Abstract
Ever growing penetration of wireless networks in our day-to-day lives underline new challenges in the design of communication protocols. Traditional reference models designed for wired networks follow strict layered doctrine. But by changing times, a paradigm shift from wired to wireless networks, opened a plethora of both options and challenges before us. However, lack of communication among adjacent layers of these reference models, limits the performance of wireless networks especially wireless sensor networks to great extent. To overcome such limitations, optimization of these layers through cross-layer approach has been proposed. This chapter outlines requirements, prevalent practices and presents challenges in standardized architecture. Afterwards a cross-layer solution through inter and intra layer communication and optimization of layers and a framework for next generation wireless networks has been proposed.
Karuna Babber, Rajneesh Randhawa
Chapter 8. A Meta-heuristic Based Hybrid Predictive Model for Sensor Network Data
Abstract
Many prediction algorithms and techniques are used in data mining to predict the outcome of the response variable with respect to the values of input variables. However from literature, it is confirmed that a hybrid approach is always better in performance than a single algorithm. This is because the hybridization leads to combine all the advantages of the individual approaches, leading to the production of more effective and much improved results. Thus, making the model a productive one, which is far better than model proposed using individual techniques or algorithms. The purpose behind this chapter is to provide information to the users on how to build and investigate a hybrid Feed-forward Neural Network (FNN) using nature inspired meta heuristic algorithms such as the Gravitational Search Algorithm (GSA), Binary Bat Algorithm (BBAT), and hybrid BBATGSA algorithm for the prediction of sensor network data. Here, FNN is trained using a hybrid BBATGSA algorithm for predicting temperature data in sensor network. The data is collected using 54 sensors in a controlled environment of Intel Berkeley Research lab. The developed predictive model is evaluated by comparing it with existing two meta heuristic models such as FNNGSA and FNNBBAT. Each model is tested with three different V-shaped transfer functions. The experimental results and comparative study reveal that the developed FNNBBATGSA shows best performance in terms of accuracy. The FNNBBATGSA under three different V-shaped transfer functions produced an accuracy of 91.1, 98.5, and \(91.2\%\).
M. Umme Salma, Srinivas Narasegouda, Anuradha N. Patil
Chapter 9. Extensive Study of Pocket Switched Network Protocols
Abstract
At the beginning, all the communication methods were mostly end-to-end contact based. But with the advancements in futuristic technologies and expansion of human mobility horizon, the previously mentioned communication scheme was less likely to fulfil the needs of the new modernized world. People are constantly moving and with this human mobility nature, the network has become sparser as well as intermittently connected. To deal with this nature of loosely connected human nodes Pocket Switched Network (PSN) which is a unique kind of Delay Tolerant Network (DTN) has been instigated. PSN mostly works in an Ad-hoc manner and it does not rely on any fixed infrastructure nor need the help of any Third party like telephone service providers. With the leaps of time and ever-changing technologies, researchers have provided many routing protocols in the field of PSN. This book chapter holds a brief discussion about all these routing protocols which have helped us to get to this level of successful communication through PSN where we are successful in sharing essential information in the event of any kind of natural disasters, war situations, environmental monitoring, urban sensing etc. even in the space with the help of wireless technologies (WiFi, Bluetooth). We have discussed the challenges faced in the PSN environment that are yet to overcome and its future application domain.
Mahrin Tasfe, Amitabha Chakrabarty
Chapter 10. Routing Protocols in Wireless Sensor Networks
Abstract
Due to dynamic topology, resource constraints and the distributed nature of WSNs, several requirements of routing protocols needs to be fulfilled. Wireless sensor networks comprise of huge number of spatially distributed, low-power, low-cost and intelligent autonomous sensors with one or more base stations which cooperatively monitor environment or physical conditions such as pressure, temperature, sound or motion. Efficiency of any routing protocol is governed by two main factors that is network lifetime and energy conservation. Another challenging issue in WSNs is the QoS support and therefore QoS aware routing protocol have gained much attention in the recent few years. In this article we first discuss several challenging factors and issues that affects the WSNs routing protocol design. In this paper we categorize various routing protocols in WSNs into three major categories namely the flat networks routing protocols, the hierarchical networks routing protocols and the QoS aware routing protocols. The article explores the flat networks routing protocols as Re-active, Pro-active and Hybrid Protocols and hierarchical networks routing protocols as chain-based, grid-based, tree-based and area-based protocols. The article also discusses the various types of QoS routing protocols in WSNs. Finally we present certain open issues regarding the design of routing protocols in WSNs.
Bharat Bhushan, G. Sahoo
Chapter 11. Energy Efficiency
Abstract
The work presented in this chapter focuses on the impact of sensor node parameters on the lifetime of the battery. Electrochemical discharge characteristics of the battery viz. rate capacity effect and recovery effect play the vital role in efficient discharge of the battery. An improper selection of the sensor node parameters viz. sampling interval and transmission power level of the data packets will lead to pronounced effects of rate capacity and recovery effect. These, in turn, will lead to premature exhaustion of the battery. Two algorithms are designed to find the optimum sampling interval and optimum transmission power level which would minimize the rate capacity and recovery effect of the battery. Experimental results have shown an increase of 18 and 22% improvement in the lifetime of the battery with optimum sampling interval and optimum transmission power level of data packets respectively. However, by using the optimum sampling interval and optimum transmission power level, the achieved improvement in the lifetime of the battery is 35.14%. Further, a thorough investigation is carried out to analyze the effect of ambient temperature on the sensor node. To circumvent the premature death of the battery at colder temperature, the data compression and optimum sampling interval strategies have been adopted. The improvement in the lifetime is found to be 24.81%.
Satyanarayana Chanagala, Z. J. Khan
Chapter 12. Application Specific Sensor-Cloud: Architectural Model
Abstract
In recent years, the sensor cloud infrastructure dawns a huge advancement in many real time applications. The major drawback of Wireless Sensor Network (WSN) is its limited processing capability, bandwidth scarcity, insufficient memory, etc. In reality, the sensors (EEG, ECG, and so on) continuously sense the highly sensitive data, and send to the medical server leading to numerous challenges. The integration of cloud computing and WSNs with internet enables to cover and provide a service to the entire world, and also to overcome the deficiency of the WSNs. This chapter gives a prelude on the integration of cloud computing with WSNs and discusses the functional architectures, design issues, benefits and the applications of the sensor cloud infrastructure. In addition, we also developed a general architectural model for precision agriculture application and farmers awareness using sensor cloud.
V. Bhanumathi, K. Kalaivanan
Chapter 13. Big Data and Deep Learning for Stochastic Wireless Channel
Abstract
Continuous advances in wireless communication technology and the proliferation of hand held multimedia devices have been instrumental in the enormous expansion in the data-driven environments. A significant impact of a symbiotic linkage of analytical tool and learning based approaches is to be observed in increasing link reliability of mobile devices due to the application of big data and learning aided mechanisms. In this paper, we analyze the trends of big data and deep learning techniques to handle large data volumes and explore the ways and means for their application while handling the stochastic wireless channel. We formulate certain learning based approach which is expected to contribute towards spectrum conservation and achieve better link reliability. This work focuses on some of the emerging issues involving big data and the roles played by the capabilities of 5G and the advantages that could be achieved due to the use of deep learning.
Ankumoni Bora, Kandarpa Kumar Sarma
Chapter 14. Integrated Sensor Networking for Estimating Ground Water Potential in Scanty Rainfall Region: Challenges and Evaluation
Abstract
Ground water potential and its evaluation, is a challenge for operating Sensor Networks (SN) field and its integration. Certainly, growing water demand from ground water and a obscurity to right of entry is observed at the moment in a number of countries, and enough conservation policy have to be applied in direct to go with the client desires and keep away from non-ecological slaughter. Starting vision, the latest SN technologies is the feasible solution to achieve the water boundary and tidy measuring of water expenditure to carry the civic utilization not only in guarantee but translucent check to the nation and is to optimize the accessible ground water resources for a longer sustainable allocation. In this work, at attempt has been made to find out the gap associated with sensor networks and integrated neural network algorithms by maximizing life span uses, and their function to envelop monitoring circumstances for ground water sustainability. An outline of the efficient technology and relevant techniques related to the issue are presented. Ultimately a sensible case study for the ground water availability is proposed. A transmission of sensor network is used to search data availability. Back Propagation Neural Network (BPNN) and Radial Basis Neural Network (RBNN) are proposed in terms of optimization of sensor data to model the sensitivity of ground water availability in arid region. It is found that BPNN is suitable for optimizing and searching ground water in arid region.
Dillip K. Ghose, Sandeep Samantaray
Chapter 15. Overview of Computational Intelligence (CI) Techniques for Powered Exoskeletons
Abstract
There is an emerging need to synchronise wearable function with user intention as many exoskeletons reported in current literature have limited capability to predict user intention. In order to achieve good synchronization, closed loop feedback is required. Overcoming these limitations necessitates an architecture composed of networked sensors and actuators with smart control algorithms to fuse sensor data and create smooth actuation. This review chapter discusses the growing need to deploy computational intelligence (CI) techniques as well as machine learning (ML) algorithms so that exoskeletons are able to predict the user intentions and consequently operate in parallel with human intention. A comprehensive review of major portable, active exoskeletons are provided for both upper and lower limbs with a focus on the need for smart algorithms integration to drive them. The application areas include rehabilitation and human performance augmentation.
Abdelrahman Zaroug, Jasmine K. Proud, Daniel T. H. Lai, Kurt Mudie, Dan Billing, Rezaul Begg
Chapter 16. FPGA Based Power Saving Technique for Sensor Node in Wireless Sensor Network (WSN)
Abstract
The demand for high-performance WSN is increasing and its power consumption has threatened the life of the WSN. In WSN, different factors are affecting the power consumption like sensor node, communication protocols and packet data transfer. After power analysis of WSN, it is identified that reduction in power consumption of sensor nodes is vital in WSN. Nowadays, FPGA configurable architecture becomes attractive solutions to design the sensor node due to its advanced features. The proposed system presents the design and implementation of power saving technique for wireless sensor node with power management unit (DVFS + Clock gating) controlled by cooperative custom unit with parallel execution capability on FPGA. The customizable cooperative unit is based on customization of Operating System (OS) acceleration using dedicated hardware and apply it to soft core processor. This unit will reduce OS CPU overhead involved in processor based sensor node implementation. The power management unit performs functionalities like control the clock of the soft processor, hardware peripherals and put them in proper state based on hardware requirement of application (tasks) under execution. Additionally, there is a need to dynamically scale the voltage and frequency by considering control signals from cooperative custom unit. In this proposed work, the performance and power consumption of FPGA-based power saving technique for sensor node can be compared with the power consumption in the processor based implementation of sensor nodes. The proposed work aims to design efficient power saving techniques for wireless sensor node using FPGA configurable architecture.
Vilabha S. Patil, Yashwant B. Mane, Shraddha Deshpande
Chapter 17. Particle Swarm Optimisation Method for Texture Image Retrieval
Abstract
There are two important tasks in texture image retrieval systems namely, feature extraction and similarity measurements. Two essential requirements of texture image retrieval system are immense retrieval precision and reduced computational complication. Several efficient methods for texture feature extraction and similarity measure methods exist. Objective of the present chapter is to propose efficient texture feature extraction algorithms which should have high retrieval accuracy. Different orthogonal moment can represent an image with almost zero information redundancy. Calculation complexity and approximation error with Zernike moment is very high. So in our work to extract feature Exact Legendre Moment (ELM) has been used. In the present chapter a new search algorithm using particle swarm optimisation (PSO) has been presented. Out of global best and local best model of PSO global best model has been considered here. The proposed method has been compared with energy, standard deviation and energy + standard deviation based retrieval method. To improve the performance of search method different modifications have been proposed. Four texture image searching algorithms have been provided using four of these modifications namely adaptive inertia weight PSO, guaranteed PSO, improved PSO and attractive repulsive PSO in this chapter. These modified methods have been compared with some existing retrieval methods like M-band wavelet, Cosine modulated Wavelet based texture image retrieval system.
Ivy Majumdar, B. N. Chatterji, Avijit Kar
Chapter 18. AOR-ID-KAP: An Authenticated One-Round Identity-Based Key Agreement Protocol for Wireless Sensor Network
Abstract
Today, Wireless sensor network has large applications in different areas such as home appliances, healthcare, defenses, submarine, weather forecasting, etc. Sensor node gathers data, processes it and transmits data to the other node in the sensor network. To enable two nodes that communicated, they need a secret key which protects them over the public wireless network. Since the resource-constrained sensor node in WSN has insufficient memory that incapable to store secret keys. So, there is a need for the distribution of key over the network. The keys distribution on resource-constraints sensor nodes in the WSN is the challenging area of interest. Though, the resource constraints behavior of sensor node restricts to manage a lot of keys in WSN. Many solutions have been proposed for WSN recently. In this article, we demonstrate how public key cryptography, especially, identity-based encryption gives the right approach for key distribution on WSN without interacting the nodes in the network. Besides, we inspect several highly optimized, energy and memory efficient, and scalable variant of Elliptic curve cryptography that is quickly and flexible to integrate on WSN. Further, we examine another light-weight pairing based cryptography implementation and show the feasibility of pairing-based cryptography in WSN. We then proposed a one-round identity-based key agreement protocol (AOR-ID-KAP) based on the light-weight pairing-based cryptosystem. We show that our proposed scheme AOR-ID-KAP is authenticated and scalable to large network size, and secure against man-in-middle-attack, and node capture. In terms of computational cost, bandwidth cost and message exchange, our proposed system performed better as compare to the other related schemes.
Mahender Kumar
Chapter 19. A Comparative Analysis of Centralized and Distributed Spectrum Sharing Techniques in Cognitive Radio
Abstract
In the existing scenario, the radio spectrum is allocated and divided between unlicensed and licensed frequencies. Due to this policy, some portions of the spectrum remain unused. To cope with this situation, a new communication paradigm is introduced, known as Cognitive Radio (CR). One of the main challenges in Cognitive Radio Network (CRN) is the sharing of spectrum. Spectrum sharing allows several CR nodes for transmission by using vacant spectrum resources. It can be conducted in both distributed and centralized environment. Centralized spectrum sharing can be impractical with the severe increase in spectrum demand. But distributed spectrum sharing along with consumer devices having Cognitive Radio capabilities, provides a realistic spectrum sharing solution. There are three spectrum sharing techniques in dynamic spectrum access (DSA), i.e., underlay, overlay and interweave. Major spectrum sharing challenges are: Common Control Channel and Dynamic Radio Range. There are many other challenging issues still need additional investigations, thus, making Cognitive Radio an open research area. In this chapter, we present a detail survey on different spectrum sharing techniques in CRN. This chapter also presents different performance evaluation parameters to ensure the quality of the spectrum sharing technique. At last it presents various challenges and issues associated with spectrum sharing and the future research opportunities in this area. This will present a clear vision to the young researchers to carry out their research in this domain by knowing the future scope from it.
Subhashree Mishra, S. S. Singh, Bhabani Shankar Prasad Mishra
Chapter 20. Sedimentation Process and Its Assessment Through Integrated Sensor Networks and Machine Learning Process
Abstract
Capacity of suspended sediment is an important phenomenon for soil conservation structure. Sediment concentration is measured using sensors in a river reach. Sediment transport is basically in two forms, bed load and suspended load. The amount of load carried in suspension by a river mainly depends on the volume and velocity of the stream. Actual sedimentation patterns and depths are extremely difficult to evaluate. The main contribution of the research is the development of flow and sedimentation prediction models for each month of monsoon period using artificial neural networks. The frame work is tested on the river Mahanadi.
Dillip K. Ghose, Sandeep Samantaray
Metadata
Title
Computational Intelligence in Sensor Networks
Editors
Bijan Bihari Mishra
Dr. Satchidanand Dehuri
Dr. Bijaya Ketan Panigrahi
Ajit Kumar Nayak
Prof. Dr. Bhabani Shankar Prasad Mishra
Dr. Himansu Das
Copyright Year
2019
Publisher
Springer Berlin Heidelberg
Electronic ISBN
978-3-662-57277-1
Print ISBN
978-3-662-57275-7
DOI
https://doi.org/10.1007/978-3-662-57277-1

Premium Partner

    Image Credits