Showing papers presented at "IEEE India Conference in 2014"

Microstrip patch antenna based UHF sensor for detection of Partial Discharge in High Voltage electrical equipments

Abstract: High Voltage (HV) power apparatus are usually, the most critical and costly component in any power system. Sudden failure of such component leads to unwanted interruptions and catastrophic losses. Partial Discharges (PD) are reported as main reason for degradation of insulation system in any HV power apparatus. A successive occurrence of such discharges eventually leads to complete failure of the equipment. Therefore, it becomes important to monitor the PD in all HV power apparatus in order to detect incipient insulation problems, and to prevent further tragic failure. In the work, microstrip patch antenna has been designed in suitable manner for detection of Ultra High Frequency (UHF) signals, emitted due to occurrence of PD in HV power apparatus. An experimental study has been conducted in laboratory environment for testing of proposed sensors. Experimental results also correlated with the standard PD detection system (IEC60270). Result shows that, the proposed microstrip patch antenna can be effectively used as UHF sensor, and PD can be detected in the HV power apparatus in non-contact mode from a long distance. PD measurement with microstrip patch antenna is easy to install and also a cost effective solution for online condition monitoring of HV power apparatus.

Diagnosis of diseases on cotton leaves using principal component analysis classifier

Abstract: This paper addresses the problem of diagnosis of diseases on cotton leaf using Principle Component Analysis (PCA), Nearest Neighbourhood Classifier (KNN). Cotton leaf data analysis aims to study the diseases pattern which are defined as any deterioration of normal physiological functions of plants, producing characteristic symptoms in terms of undesirable color changes mainly occurs upon leaves; caused by a pathogen, which may be any agent or deficiencies. The predictions of diseases on cotton leaves by human assistance may be wrong in some cases. Using machine vision techniques, it is possible to increase scope for detection of various diseases within visible as well invisible wavelength regions. After implementing PCA/KNN multi-variable techniques, it is possible to analyse the statistical data related to the Green (G) channel of RGB image. Green channel is taken into consideration for faithful feature collection since disease or deficiencies of elements are reflected well by green channel. In most of the cases diseases are seen on the leaves of the cotton plant such as Blight, Leaf Nacrosis, Gray Mildew, Alternaria, and Magnesium Deficiency. The classification accuracy of PCA/KNN based classifier observed is 95%.

Hand gesture recognition system with real-time palm tracking

Abstract: Over the years Vision based real time gesture recognition system has witnessed an exponential growth because of its manifoldness applications, ranging from sign language to virtual reality and its ability to interact with system efficiently through HCI. In this paper, we have proposed a hand gesture recognition system for American Sign Language recognition using important features of hand such as fingertips, palm center etc.. The system is capable of recognizing hand gestures even when the fore-arm is involved and it can tolerate a certain rotation of palm and fore-arm. We have implemented principal component analysis to remove ambiguity between two similar types of gestures and given emphasis to detect movement epenthesis by means optical flow technique.

To increase data capacity of QR code using multiplexing with color coding: An example of embedding speech signal in QR code

Abstract: QR codes have become widely popular along with the increased usage and popularity of smart phones. In many areas, QR codes have overtaken the place of linear barcodes because of the obvious advantage of large data capacity and ease of data retrieval. QR code specifications offers many more advantages like reduced space, durability against soil and damage, high data capacity, supported languages are more than other barcodes, supports 360 degree reading, etc over linear barcodes which makes QR codes worth opting. The structural flexibility of QR code architecture opens many more possibilities to stretch the limits of data capacity further away which includes data hiding techniques, multiplexing techniques, use of color QR codes, use of data compression techniques, etc. Proposed technique attempts to increase data capacity by multiplexing several QR codes and generating a color QR code. Experimental results show that this technique offers increase of the data capacity upto 24 times as compared to a standard QR code of same size. To get quicker results while demultiplexing, multiplexing of 12 or less QR codes is advisable with proposed technique. Due to such large capacity offered by proposed technique, embedding of speech signal into a QR code has made possible.

Event detection in cricket videos using intensity projection profile of Umpire gestures

Abstract: In this paper, a novel method for the detection of events in cricket videos using Umpire hand signals or gestures is proposed. Important events in the game are signaled by Umpire with unique gestures. Scene segmentation of cricket video is initially carried out by the detection of bowling events. Then the Umpire frames are identified from each scene and analyzed using both vertical and horizontal intensity projection profiles. These profiles representing the Umpire gestures in the frame, can be used as features for training an ensemble classifier Random Forest (RF) for the extraction of events-FOUR, SIX, NO BALL, OUT and WIDE in cricket game. The method is tested with recorded video of some international Twenty -Twenty cricket matches and found that event identification using Umpire gestures matches with manually detected events.

Color image watermarking using DWT-SVD and Arnold transform

Abstract: Watermarking technique is used for protecting copyright of digital images. In this paper, we propose a novel technique for watermarking using DWT and SVD. DWT ensures imperceptibility of the watermark and SVD ensures its robustness against attacks. To address the issue of watermark security, we make use of Arnold transform. Watermark extraction is semi-blind, which avoids the need for original image for extraction. Both watermark and cover image are color images. Performance of the system is judged by using PSNR and Correlation Coefficient values. System shows good robustness against noise, JPEG compression, filtering and cropping.

A new morphology based approach for blood vessel segmentation in retinal images

Abstract: Diabetic retinopathy (DR) disease occurs due to leakage of blood and protein from small diseased vessels into retina which serves as main cause of blindness among diabetic patients. The early detection of diabetes in the retinal vessels is useful for the prevention of disease. Therefore, the accurate extraction of blood vessels from retinal images helps in diagnosis of such eye diseases. In this paper a new approach is proposed for the blood vessel detection from digital retinal images. The morphological based approach is used for background elimination and blood vessel enhancement with phase preserving noise removal algorithm. Vessel silhouette is then extracted with fixed threshold scheme. Post-processing is done to remove unwanted regions, eliminate spur pixels and fill gaps within detected vessel. The proposed method is evaluated on two publically available datasets, STARE and DRIVE because both datasets provides the ground truth of retinal images precisely marked by experts. Experimental results show that proposed method is comparable to other state of art techniques due to high detection rate.

Principal features for Indian currency recognition

Abstract: Currency recognition system is one of the fast growing research fields under image processing This paper proposes a novel method for Indian currency recognition Our proposed approach identifies denomination by extracting features like Center Numeral, Shape, RBI Seal, Latent Image and Micro Letter Principal Component Analysis is used to reduce the dimensions and a similarity based classifier is constructed to predict test sample Results are also validated by constructing models using classifier implemented using WEKA and testing with unseen samples not considered in feature extraction Our study demonstrated that center numeral results in an accuracy of 100% with all family of currencies

Defect detection of steel surface using entropy segmentation

Abstract: Today, because of high manufacturing speed in steel industry, there is a need of fast and accurate detection of steel defect for quality assurance of product. Unlike other papers on defect detection of steel surface based on entropy this paper presents a new pre-processing and processing algorithm. The method presented here overcomes the limitations of traditional segmentation method or adaptive segmentation method like Otsu's method. This paper presents a new defect detection algorithm based on entropy. As a pre-processing step illumination compensation of image has been introduced using inverse illumination to remove non-uniformity of light intensity in the image. In the second part Local entropy of image has been used to detect the region of defect. The paper also suggests the concept of dynamic updation which helps to find a good background i.e. ideal steel surface and provides an effective method to classify the defects in its initial stage into defective and non-defective image. Background subtraction method is then used to extract the defective portion of image from the entropy image by comparing the entropy of image with the entropy of background image. Histogram thresholding method has been introduced to separate the background and defective portion in the background subtracted image to get the segmented image. The method was successfully tested on three kinds of defect on steel surface i.e. water droplet, blister and scratch.

Single image fog removal using gamma transformation and median filtering

Abstract: In this paper, a novel and simple restoration-based fog removal approach is proposed. Here, we proposed an approach which is based on gamma transformation method and median filter. Transmission map is refined by the gamma transformation method. Then obtained transmission map is smoothed by a median filter. Qualitative and quantitative analysis demonstrate that proposed algorithm performs well in comparison with bilateral filtering. It can handle color as well as gray images. Proposed algorithm, due to its speed and ability to improve visibility, may be used in many systems, ranging from tracking and navigation, surveillance, consumer electronics, intelligent vehicles to remote sensing.

Phase Intensive Global Pattern for periocular recognition

Abstract: Partially constrained human recognition through periocular region has emerged as a new paradigm in biometric security. This article proposes Phase Intensive Global Pattern (PIGP): a novel global feature based on variation of intensity of a pixel-neighbours with respect to different phases. The feature thus extracted is claimed to be rotation invariant and hence useful to identify human from images with face-tilt. The performance of proposed feature is experimented on UBIRISv2 database, which is a very large standard dataset with unconstrained periocular images captured under visible spectrum. The proposed work has been compared with Circular Local Binary Pattern (CLBP), and Walsh Transform, and experimentally found to yield higher accuracy, though with increased computation complexity and increased size of the feature vector.

PAPR reduction in OFDM systems

Abstract: In a communication system, operation of the transmitter power amplifier is limited to linear range. Input signal with an amplitude more than the transmitter power amplifier linear range results in signal distortion. Hence, the input signal to the transmitter should be with low peak to average power ratio. This paper presents a new method of reducing the peak to average power ratio in OFDM system. The proposed method is based on DCT aided successive addition and subtraction of OFDM symbols inside the single OFDM frame. Performance of the proposed method is evaluated and found to be superior to PTS, SLM techniques.

No reference image quality assessment

Abstract: The implementation of algorithm for no reference image quality assessment is presented. Aim of the project is to implement an image quality assessment algorithm which will assess the quality of the test image without any reference and predict the quality score for the test image. No Reference (blind) quality assessment problem is important as well as technically difficult. The algorithm used is a Natural Scene Statistics (NSS) model of discrete cosine transform (DCT) coefficients. NSS model based features are extracted. A regression model of SVM is used to predict image quality scores from certain extracted features. The features are based on an NSS model of the image DCT coefficients. The estimated parameters of the model are utilized to extract features that are indicative of perceptual quality.

Alcoholism diagnosis from EEG signals using continuous wavelet transform

Abstract: Effective working of brain computer interface largely depends upon mental state and vigilance level of human brain. Electroencephalogram signal undergoes for unpredictable changes when vigilance state of human brain alters widely and sometimes cause wrong interpretation by brain computer interface during operation. Hence, brain computer interface needs to investigate subject's brain alertness level frequently to avoid false command generation. In present work, an approach of feature extraction from electroencephalogram signals using continuous wavelet transform is proposed and validated for identification of the two different brain states i.e. alcoholism and normal. The coefficients of continuous wavelet transform exploiting four distinct base wavelets are computed from processed electroencephalogram signals. Further, statistical parameters are calculated for each base wavelet and employed to prepare feature vector from electroencephalogram. The prepared feature vector is used to perform training and validation of the soft computing techniques in present work, which includes support vector machine, neural network and random forest tree classifier. A comparative study is performed for different feature vectors in combination of soft-computing techniques to obtain effective methodology for alcoholism diagnosis.

Implementation of ZigBee/802.15.4 in Smart Grid communication and analysis of power consumption: A case study

Abstract: Communication standards in Smart Grid intend to facilitate reliable exchange of critical data securely. But selection of suitable technology as per the application area is crucial. Communication standards being considered for establishing a network between various substations within the smart grid are WiMAX, Wi-Fi, ZigBee, Bluetooth, GSM, PLCC, UMTS, etc. Smart grid profile requires monitoring of the power and controlling it as per the user demand. As ZigBee is primarily designed for low power, control & monitoring application; it is considered to be the most challenging competitor. This paper presents ZigBee (over IEEE 802.15.4) for smart grid application in Home Area Network (HAN), Neighboring Area Network (NAN) andWide Area Network (WAN). The comparative analysis for power consumption with other standard technologies viz. Wi-Fi & Bluetooth is illustrated. Topologies in ZigBee that support the case study applications are proposed and performance for each is evaluated. Also, the transceiver chip selection criteria on the basis of power utilization is studied and results are illustrated with the help of graphs.

An intelligent surveillance with cloud storage for home security

Abstract: In the present days, mobile devices like smart phones and iPads are being used to handle daily tasks that traditional desktop and laptop computers once handled. Home automation can be defined as accessing or controlling many of our home appliances, security, climate, and video monitoring from a remote or centralized location. A home automation system allows us to check in on our home from a remote location, giving us true peace of mind. Some systems will let us interact with the home security system, providing the ability to arm and disarm our home remotely. Some complete home automation systems will alert us by phone, text or email if there is any unusual movements within our home. Cheaper rates of cameras and different accessible network technologies have made remote home monitoring more effective enabling us to control everything from our cell phone. In this paper, we present the design and implementation of a home security system to detect an intruder at home when nobody is present. This low-cost security system uses a small Pyroelectric Infrared (PIR) module and a Infrared (IR) sensor, and is built around ARM7 microcontroller. Presence of individual is detected when the system senses the signal generated by many sensors. The system sends a message to the user through GSM modem after detecting the presence of unauthorized person. The user then monitors the intrusion from anywhere, on an Internet enabled device by using IP address of the installed IP webcam of mobile in home, and alerts the neighbors and police. The user can also save the images and record the videos, which can be stored in a public cloud for later use. Preparatory experiments have shown encouraging results.

Duct fan based wall climbing robot for concrete surface crack inspection

Abstract: Degradation inspection of inaccessible parts of concrete structures is always a difficult task. An efficient and low cost solution is the use of wall climbing robots in such areas. In this paper, we propose a duct fan based wall climbing robot for the crack inspection on concrete wall surfaces. The thrust force provided by the duct fan holds the robot on to the wall. This wireless robot moves like a four wheeled vehicle on the wall surface and captures images of the wall under inspection using a camera mounted on it. Cracks are detected from these images using percolation method of image processing.

Design of PID controller for inverted pendulum using stability boundary locus

Abstract: In this paper, PID controller has been designed for cart inverted pendulum system. The proposed approach is based on newly developed concept of stability boundary locus. The main advantage of this approach is that the cart oscillations has been minimized and angle of pendulum is stabilizes with minimum settling time. The results are also compared with the recently proposed approach of PID and LQR controller. The results are simulated in Matlab environment.

A SOGI-FLL based control algorithm for single phase grid interfaced multifunctional SPV under non ideal distribution system

Abstract: This paper deals with a single phase grid interfaced SPV (Solar Photo Voltaic) system. The proposed multifunctional system also helps in power quality improvement in single phase distribution system. A two stage system is used in the presented work. The first stage is a boost converter, which serves the purpose of MPPT (Maximum Power Point Tracking). The second stage is a VSC (Voltage Source Converter), which performs reactive power compensation, harmonics elimination and feeding solar energy into the grid. A SOGI-FLL (Second Order Generalized Integrator with Frequency Lock Loop) based control algorithm is proposed for control of VSC. A feed forward term for solar contribution is used to improve the dynamic response. A PI controller is used to regulate the DC link voltage to desired value. A wide range of simulation studies are carried out to show all features of proposed system. The system is tested considering realistic non-ideal grid conditions. The performance of proposed system is found satisfactory for wide variation in grid voltage. The THD of grid current is well under IEEE-519 standard.

Feature selection using RapidMiner and classification through probabilistic neural network for fault diagnostics of power transformer

Abstract: The diagnosis of incipient fault is important for power transformer condition monitoring. The incipient faults are monitored by conventional and artificial intelligence based models. The key gases, percentage value of gases and ratio of Doernenburg, Roger, IEC methods are input variables to artificial intelligence (AI) models which affects the accuracy of incipient fault diagnosis so selection of most influencing relevant input variable is an important research area. With this main objective, RapidMiner software is applied to IEC TC 10 and related datasets having different operating life to find most influencing input variables for incipient fault diagnosis in AI models. The RapidMiner identifies %CH 4 , %C 2 H 2 , %H 2 , %C 2 H 6 , C 2 H 4 /C 2 H 6 , C 2 H 2 /CH 4 , C 2 H 2 /H 2 and CH 4 /H 2 as the most relevant input variables in incipient fault diagnosis and it is used for fault diagnosis using different artificial intelligence (AI) approach i.e. fuzzy-logic (FL) and . The compared results shows that AI models give better results at proposed input variables used as an input vector. PNN gives highest accuracy of 98.28, proving proposed input variables can be used in transformer fault diagnosis research.

Optimization of feature selection method for high dimensional data using fisher score and minimum spanning tree

Abstract: For classification of High Dimensional data, feature selection is the most important step for obtaining optimal result with respect to processing power required and time taken. Feature selection is a method by which the most relevant feature is selected from a set of features containing redundant and irrelevant features thereby reducing the load on the classification algorithm. This paper proposes an implementation of this method in a two tier structure. In the first step, a high ranking feature is selected using the well-known filter based algorithm - Fisher Score. This algorithm selects the relevant feature from the feature set based on a preset threshold. The second step generates a cluster of redundant features utilizing MST (Minimum Spanning Tree) algorithm, which are then filtered out to preserve the most relevant features out of each cluster. This increases the classification accuracy as well as running time and hence the computation cost. The efficacy of the presented approach was validated by comparing the same with other well-known feature selection algorithms: Fisher Score, CFS and ConsSF with respect to three classifiers: IB1, C4.5, and Naive Bayes. The presented approach achieved higher Classification accuracy and lower run time.

Statistical analysis of various kernel parameters on SVM based multimodal fusion

Abstract: Biometric systems accurately recognise/authenticate an individual to access his confidential data/accounts. When multiple traits are fused together at feature/ score/ decision level, it results into highly accurate multimodal systems. This system improvise rate of recognizing an individual. Multiple biometric traits cannot be cloned simultaneously and hence it is highly secured system. The match scores of different persons are sufficient enough to recognise them and differentiate them from each other. The match scores do not require higher storage capacity as well as higher computational complexity. Hence, match score fusion is highly preferable to recognize an individual. Fusion at match score level has been carried out by several researchers with various state of arts namely weighted sum rule, product rule, majority voting rule, Support vector machine (SVM), Bayesian fusion, fuzzy rule method, etc. In this paper SVM based fusion of match scores for face and fingerprint biometric trait is implemented. Main research focus of this paper is on statistical analysis of different kernel methods namely Polynomial kernel, Radial Basis Function (RBF) kernel and Multilayer perceptron (MLP) kernel used for training SVM. The statistical analysis is based on training time required for training SVM using all three kernel methods as well upon the performance curve in terms of recognition rates i.e. Genuine Acceptance Rate (GAR) and False Acceptance Rate (FAR) of SVM fused system. SVM fusion has been implemented in MATLAB software and the results reveal that RBF kernel based SVM fused system requires the lowest training time as compared to other kernel methods. Even the recognition performance of RBF based SVM system is higher as compared to other kernel based systems i.e. GAR of RBF fused system increases and is better as compared to other kernel based SVM systems.

Modification of Floyd-Warshall's algorithm for Shortest Path routing in wireless sensor networks

Abstract: Wireless sensor networks consist of nodes among which beaconing of data occurs through routing. There are a number of routing protocols and algorithms existing based on different criteria. There are a number of shortest path algorithms available, some of which are applicable in case of shortest path routing in wireless sensor networks. Shortest path routing algorithms aim at consumption of minimum amount of energy in a WSN. Generally, Dijkstra's Algorithm is followed for routing through shortest path in a WSN. The Floyd-Warshall's Algorithm is again used for computing shortest paths between different nodes in an ordinary graph but this algorithm is not exactly applicable for routing in wireless networks because of the absence of handshaking mode. In this work, the Floyd-Warshall's Shortest Path Algorithm has been modified and a new algorithm has been proposed for routing in the wireless sensor networks. The proposed algorithm computes the shortest path available taking into consideration a directed graph and presence of acknowledgement path of every traversed path. Code has been developed to simulate the algorithm in Turbo C. This algorithm helps to obtain all the available shortest paths from every node to the other at a time.

Adaptive backstepping control for DC-DC buck converters using Chebyshev neural network

Abstract: This paper proposes a novel control technique for the Buck type DC-DC converters using adaptive backstepping control and Chebyshev neural network. To enhance the transient performance of both the capacitor voltage and the inductor current under nominal conditions, input voltage fluctuations and load variations, this control algorithm has been proposed. The systematic design of backstepping controller has been improvised by incorporating the approximation of unknown load resistance parameter by a single layer Chebyshev neural network. Results have been compared with a recently developed adaptive terminal sliding mode control technique. The proposed method significantly improves voltage and current transient performances.

Secure communication for advance metering infrastructure in smart grid

Abstract: The electrical power industry is in the process of integration with bidirectional information and power flow infrastructure commonly called smart grid. Advance metering infrastructure (AMI) is an important component of the smart grid in which data and signal is transferred from consumer smart meter to smart grid and vice versa. Cyber security is to be considered before implementing AMI applications. For delivering Smart meter data and manage message securely, there is a need of a unique security mechanism to ensure the integration of availability and privacy. In such security mechanisms, the cryptographic overhead, including certificates and signatures, is quite significant for an embedded device like a smart meter in smart grid AMI compared to normal personal computers in a regular enterprise network. Additionally, cryptographic operations contribute significant computational cost, when recipient end verifies the message in each communication. We proposed a light and flexible protocol for secure communication between smart meters and smart grid infrastructure. The proposed protocol authenticate both control center and smart meter and also securely exchange secret key (session key) between two entities for secure communication between them. Proposed protocol help to mitigate several types of attacks on smart grid by identifying the origin of attacks against AMI. The proposed protocol is tested for security and no attack was found. Its performance is also found to be better than existing mechanism.

Performance study of Mine Blast Algorithm for automatic voltage regulator tuning

Abstract: Proportional Integral Derivative (PID) controllers are extensively used in industry for process instrumentation application. PID controllers have also found widespread application in Power System Control. To achieve effective control optimal tuning of PID gains of the controller is necessary. This controller gain tuning problem is a multimodal non-convex optimization problem. This paper proposes a tuning strategy based on Mine Blast Algorithm (MBA); a population based algorithm for tuning the controller. This algorithm is a newly developed optimization technique. The motivation of this study is to determine if MBA presents a better alternative than traditional soft computing based optimization methods. The algorithm simulates the behavior of exploding mines in a mine field. This algorithm has been used to find optimal values of PID gains. The performance of MBA is compared with results obtained from Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). All the codes have been developed in house in Matlab environment. MBA has demonstrated up to 40% reduction in computational burden while maintaining controllers output characteristics.

Condition monitoring of overhead line insulator by measuring surface leakage current

Abstract: Transmission and distribution power network commonly use porcelain insulator for the isolation i.e. insulation between line conductors and supporting structure. Most of the insulators are mounting in open-air applications. So, gradually contamination is deposited in the surface of the insulator and reduced the voltage withstand capability of the insulator. This voltage withstands capability of the insulator measured in terms of surface flashover. This hampers the reliable operation of the power network. Hence condition monitoring of insulator is needed in order to maintain smooth and uninterrupted power supply. Surface leakage current of the insulator provides the meaningful information about the surface contamination as well as flashover voltage level of the polluted insulators. Considering the above mentioned fact, an experimental setup has been made in the laboratory for recording the leakage current of porcelain insulators. Using this setup, surface leakage current of an 11 kV Disc insulator has been measured in contaminated condition.

A novel approach for elimination of rogue access point in wireless network

Abstract: Now a day's wireless LAN is widely used in many public spaces. Wireless access points expand wired network. It provides more flexibility to the users. There is a big risk that users connect to rogue access point (Rogue AP). Detection of rogue AP is a challenge for network administrator. Undetected rogue APs are serious threats which steal sensitive information from the network. There are many techniques used for detection of fake AP. But these solutions are expensive and not applicable for many scenarios. We need an effective solution which provides a high success rate for detection of rogue AP. In this paper we have discussed existing techniques for detection of rogue AP with its effectiveness and weaknesses. And also describe our solution for this major concern in wireless network.

Optimization of 2.5 Gbps WDM-FSO link range under different rain conditions in Ahmedabad

Abstract: This paper describe design and simulation of Wavelength Division Multiplexing (WDM) based Free Space Optical (FSO) link for different rain conditions in Ahmedabad and analyses the performance of the system by using parametric optimization. Here OptiSystem is used as simulation tool to simulate the link for the data-rate of 2.5 Gbps and wavelength of 1550 nm. The minimum value of Bit Error Rate (BER) achieved is greater or equal to 10−9 for optimized link range. The optimized link range for light rain, medium rain and heavy rain is achieved as 15.6 km, 6.1 km and 3 km.

A modified diagonal mesh interconnection network

Abstract: Mesh and its variants are most simple and popular interconnection networks in the research community. Based on the 2D diagonal mesh a new interconnection topology called a modified diagonal mesh interconnection network (MDMIN) has been proposed. The proposed topology performs better than the simple 2D Mesh and diagonal (toroidal) mesh interconnection networks and also overcomes its drawbacks.