In recent times, security in cloud computing has become a significant part in healthcare services... more In recent times, security in cloud computing has become a significant part in healthcare services specifically in medical data storage and disease prediction. A large volume of data are produced in the healthcare environment day by day due to the development in the medical devices. Thus, cloud computing technology is utilised for storing, processing, and handling these large volumes of data in a highly secured manner from various attacks. This paper focuses on disease classification by utilising image processing with secured cloud computing environment using an extended zigzag image encryption scheme possessing a greater tolerance to different data attacks. Secondly, a fuzzy convolutional neural network (FCNN) algorithm is proposed for effective classification of images. The decrypted images are used for classification of cancer levels with different layers of training. After classification, the results are transferred to the concern doctors and patients for further treatment process. Here, the experimental process is carried out by utilising the standard dataset. The results from the experiment concluded that the proposed algorithm shows better performance than the other existing algorithms and can be effectively utilised for the medical image diagnosis.
The main objective of Internet of Things (IoT) is connecting with different objects via Internet ... more The main objective of Internet of Things (IoT) is connecting with different objects via Internet without human intervention. Wireless Sensor Networks (WSNs) which involves ubiquitous computing through which small sensors are connected to the Internet and are used for collecting data. Significant amount of information flowing in the internet is made up of sensory data. To resolve the storage issues of the huge data generated by IoT, the Hadoop Distributed File System are used that streams data to user applications as required. It is difficult to accomplish analysis of vast amount of data (big data) with existing data processing methods. To avoid redundant and irrelevant data, the data needs to be classified. This work presents the use of Support Vector Machine, and Adaboost classifiers, and modifying Adaboost classifier with Genetic Algorithm (GA), Stochastic Diffusion Search (SDS), and Particle Swarm Optimization (PSO). To avoid redundant classifiers, an ensemble algorithm is proposed in this work, PSO with Adaboost classifier and SDS-GA with Adaboost classifier, that can reinitialize attributes, thus avoiding reaching local optimum, and optimizing the coefficients of Adaboost weak classifiers. The proposed algorithms effectively classify the data gathered from WSN and IoT applications. The outcomes of the experiment showed that the proposed SDS-GA algorithm is efficient over other algorithms with respect to accuracy, precision, recall, f measure and false discovery rate.
International Journal of Advanced Technology and Engineering Exploration, 2021
Automatic handwritten digit recognition provides significant contributions towards many real-time... more Automatic handwritten digit recognition provides significant contributions towards many real-time applications starting from the vehicle’s number plate to doctor’s prescription. However, the real challenge in these applications highly depends on the factors such as accuracy rate and time. Considering this significance, a novel handwritten digit recognition method is proposed without the adoption of any pre-processing steps like noise prediction, segmentation, and feature selection/extraction. The purpose of eliminating these preliminary steps is to reduce the computational complexity as the utilization of the Deep Learning (DL) approach helps to reduce the computational complexity of directly performing classification. Here, a novel Layered Convolutional Neural Networks (LCNN) model with an efficient Squirrel Optimizer (LCNN-SO) is modeled to attain better classification and global solution during the handwritten
The predictions of characters/text/digits from the handwritten images have made the research comm... more The predictions of characters/text/digits from the handwritten images have made the research community spotlight towards recognition. There are enormous applications and ambiguity that made prediction possible with Deep Learning (DL) approaches. Primarily, there are four necessary steps to be carried out with handwriting prediction. First, consideration of a dataset that is more appropriate for DL validation an inefficient manner. Here, Special Database 1 and Special Database 2 are used, which are combined and modified by the National Institute of Standards and Technology (NIST). Next is pre-processing of input handwritten digit recognition data by data normalization, extraction of efficient features which provides better prediction accuracy. The proposed idea uses pixel values as features with the analysis of hyper-parameters to enhance near-human performance. With SVM, non-linear and linear models are built to extract the appropriate features for further processing. The features are separate and placed over the Bag of Features (BoF), which is used by the next processing stage. Finally, a novel Convolutional Neural Network (CNN) is by built modifying the network structure with Orthogonal Learning Particle Swarm Optimization (CNN-OLPSO). This modification is adopted for evolutionarily optimizing the number of hyper-parameters. This proposed optimizer predicts the optimal values from the fitness computation and shows better efficiency when compared to various other conventional approaches. The novelty which relies on CNN adoption is to endeavor a suitable path towards digitalization and preserve the handwritten structure and help automatic feature extraction using CNN by offering better computation accuracy. The optimization approach helps to avoid over-fitting and under-fitting issues. Here, metrics like accuracy, elapsed time, recall, precision, and F-measure are evaluated. The results of CNN-OLPSO give better accuracy, reduced error rate and better execution time (s) compared to other existing methods. Thus, the proposed model shows better tradeoff in the recognition rate of handwritten digits.
A capsule network (CapsNet) is a new neural network model that is recently evolving in the field ... more A capsule network (CapsNet) is a new neural network model that is recently evolving in the field of image classification. Some of the shortcomings of traditional convolutional neural networks (CNNs) are compensated by the characteristics of CapsNet. It has proven to be effective at a variety of tasks, predominantly in medical image recognition with activation capsules. In this paper, image classification using the special designs in CapsNet is examined in depth. An additional reconstruction loss is used in the proposed work to empower the steering capsules and encode the input's instantiation parameters. The active vectors of higher-level capsules are used for the classification mechanism. The calculation at that point remakes the input picture thus utilizing these active vectors. The directing capsule's yield is sent into a decoder with three completely associated layers, which limits the whole of squared disparities between the calculated unit yields and the pixel power. In comparison to a typical CapsNet, the improved CapsNet method incorporates the extra parameters such as the number of measurements in each capsule sort (essential or directing capsules), the number of essential and directing capsules, and the number of channels within the capsule layer that are used for image classification. The experimental results show promising results in image recognition when compared to other CNN model-based algorithms.
International Conference on Hybrid Intelligent Systems, 2022
Book cover
International Conference on Hybrid Intelligent Systems
HIS 2021: Hybrid Intelligent S... more Book cover International Conference on Hybrid Intelligent Systems
HIS 2021: Hybrid Intelligent Systems pp 76–87Cite as
An Optimized Data Replication Algorithm in Mobile Edge Computing Systems to Reduce Latency in Internet of Things N. Saranya, K. Geetha & C. Rajan Conference paper First Online: 04 March 2022 194 Accesses
Part of the Lecture Notes in Networks and Systems book series (LNNS,volume 420)
Abstract The actual amount of data that was created applying the actuators, the sensors, and some other devices for the Internet of Things (IoT) has been showing a substantial level of increase in recent years. The data of IoT are handled using the cloud utilizing computing resources that are located in the data canters at a distance. As a result, the bandwidth of the network and the latency of communication have become major bottlenecks. The technology is known as Mobile Edge Computing (MEC) primarily seeks at encompassing the abilities of the cloud to the very edge of its radio access network thereby achieving low latency, real-time, and high bandwidth to the resources of the radio network. The IoT has been recognized as a key of the MEC with the ability of the MEC to be able to provide a new cloud platform along with gateway services. The MEC further inspired the progress of several masses of services and applications for a low-latency but high Quality of Service (QoS) owing to the geographical distribution and support for mobility. The MEC enables the applications and services of IoT for real-time operations. Replication of data is also suitable for increasing global traffic and response time and helps in data sharing. The nodes thereby continue to get access to the data replicas. This makes the problem of optimization work with many objectives. Flower Pollination Algorithm (FPA) is used to solve unconstrained optimization problems. Researchers are attracted to this algorithm for its processing speed, ease of modifying based on the requirement, and robustness. In this work, FPA is used to optimize the data replication. Experimental results shows the efficacy of the proposed method.
Machine learning has extensive application in diverse medical fields.With advancements in medical... more Machine learning has extensive application in diverse medical fields.With advancements in medical technologies, access has been given to data for the identification of diseases in theirearly stages. Alzheimer's Disease (AD) is a chronic illnessthat will cause degeneration of the brain cells and ultimately will lead to memoryloss. AD causedcognitive mental problems like forgetfulness and confusion, as well as other symptoms such aspsychologicaland behavioralproblems, are further recommended to undergo test procedures usingneuroimagingtechniques. This work's objective is to utilize the machinelearning algorithms for processing the data acquired via neuroimaging technologies for early-stage AD detection. The framework extracts featuresusingcurvelet transform from MRI brain image. This work will also present the Decision Tree, the Adaptive Boosting (AdaBoost), and the Extreme Gradient Boosting (XGBoost) classifiers. In machine learning, Population-Based Incremental Learning (PBIL) is an optimization algorithm, in spite of being simpler than a conventional genetic algorithm, the PBIL algorithm is able to achieve much better results in several cases.PBIL is used to optimize the AdaBoost and XGBoost classifiers to improve AD classification. The experimental outcomes will demonstrate the proposed approach's superior performance over that of other existing approaches.
Alzheimer's disease (AD) is the most common type of progressive neurological disorder that leads ... more Alzheimer's disease (AD) is the most common type of progressive neurological disorder that leads to the death of brain cells over the time. It causes memory loss and decline in the cognitive skills among the elderly subjects. Early diagnosis of the progressive diseases plays a vital role in the healthcare community. Machine learning (ML) algorithms and various multivariate data exploratory tools are employed in the field of AD research. The main purpose of this work is to analyse the importance of features selection which in turn enhances the classification accuracy of the models. The hyper parameter tuning for Support Vector Machine (SVM) classification and Boruta algorithm for Random Forest (RF) classification are applied for the selection of optimal set of features. In this work, a five-stage ML pipeline with each stage further categorized into different sub-levels is proposed. Initially, the data collected from the Open Access Series of Imaging Studies (OASIS-2) dataset of Magnetic Resonance Imaging (MRI) brain images is explored and pre-processed using the imputation technique. Feature scaling of the pre-processed data is done using the Min-max scaling technique. Then, the classification techniques such as logistic regression, Decision Tree (DT) classification, Random Forest (RF) classification, Support Vector Machine (SVM) classification and AdaBoost Classification are applied to classify the data and finally the performance of the classifiers are compared in terms of accuracy, Area under the curve of the Receiver Operating Characteristic (AUC) curve and recall measures. From the performance analysis, it is concluded that the Random Forest (RF) classifier yields maximum accuracy, recall and AUC values. The hyperparameter tuning and Boruta algorithm added significance to the SVM and RF classification, thereby resulting in a F-score of 91% and 92% respectively.
Alzheimer's Disease (AD) or just Alzheimer's, is a neural condition of the human brain which is g... more Alzheimer's Disease (AD) or just Alzheimer's, is a neural condition of the human brain which is getting to be increasingly notorious for its chronic neurodegenerative capability to disorient the human mind and body completely. AD is getting to be more prevalent among the older people globally. Earlier, physical and mental assessments were the only gauge to find AD, but currently Magnetic Resonance Imaging (MRI), a valuable asset in medicine is getting to be increasingly effective in recognizing and diagnosing this disease. Various techniques have been found to help discern AD and " Mild Cognitive Impairment " (MCI), a brain function syndrome homogeneous to AD, but less severe.The proposed method utilizing a wrapper based feature selection technique for identifying a classification accuracy of an AD and then proposed Social Spider Metaheuristic is used to identify the significant features to diagnose an AD in effectively. Result shows the accuracy of the proposed technique.
Colonoscopy is a technique for examine colon cancer, polyps. In endoscopy, video capsule is unive... more Colonoscopy is a technique for examine colon cancer, polyps. In endoscopy, video capsule is universally used mechanism for finding gastrointestinal stages. But both the mechanisms are used to find the colon cancer or colorectal polyp. The Automatic Polyp Detection sub-challenge conducted as part of the Endoscopic Vision Challenge (http://endovis.grand-challenge.org). Method: Colonoscopy may be primary way of improve the ability of colon cancer detection especially flat lesions. Which otherwise may be difficult to detect. Recently, automatic polyp detection algorithms have been proposed with various degrees of success. Though polyp detection in colonoscopy and other traditional endoscopy procedure based images is becoming a mature field, due to its unique imaging characteristics, detecting polyps automatically in colonoscopy is a hard problem. So the proposed video capsule cam supports to diagnose the polyps accurate and easy to identify its pattern. Existing methodology mainly concentrated on high accuracy and less time consumption and it uses many different types of data mining techniques. To analyse these high resolution video scale image we have to take segmentation of image in pixel level binary pattern with the help of a mid-pass filter and relative gray level of neighbours. This work consists of three major steps to improve the accuracy of video capsule endoscopy such as missing data imputation, high dimensionality reduction or feature selection and classification. The above steps are performed using a dataset called endoscopy polyp disease dataset with 500 patients. Our binary classification algorithm relieves human analyses using the video frames. SVM has given major contribution to process the dataset. Results: In this paper the key aspect of proposed results provide segmentation, binary pattern approach with Genetic Fuzzy based Improved Kernel Support Vector machine (GF-IKSVM) classifier. The segmented images all are mostly round shape. The result is refined via smooth filtering, computer vision methods and thresholding steps. Conclusion: Our experimental result produces 94.4% accuracy in that the proposed fuzzy system and genetic Fuzzy, which is higher than the methods, used in the literature. The GF-IKSVM classifier is well-organized and provides good accuracy results for patched VCE polyp disease diagnosis.
The motivation of image compression technique is to reduce the irrelevance and redundancy of the ... more The motivation of image compression technique is to reduce the irrelevance and redundancy of the image data in order to store or pass data in an efficient way from one place to another place. There are several types of compression methods available. Without the help of compression technique, the file size is knowingly larger, usually several megabytes, but by doing the compression technique, it is possible to reduce file size up to 10% as of the original without noticeable loss in quality. Image compression can be lossless or lossy. The compression technique can be applied to images, audio, video and text data. This research work mainly concentrates on methods of encoding, DCT, compression methods, security, etc. Different methodologies and network simulations have been analyzed here. Various methods of compression methodologies and its performance metrics has been investigated and presented in a table manner.
Mobile Ad Hoc Network (MANET) nodes are small, low cost, limited capable and mobile nodes with no... more Mobile Ad Hoc Network (MANET) nodes are small, low cost, limited capable and mobile nodes with no centralized administration control. All the nodes communicate using wireless channel with multi-hop paths. As the usage of small size portable devices are increasing day by day, all the future networks will be only the MANET. Mobility of the nodes creates the major challenge in routing and providing Quality of Service (QoS) to the applications of MANET. Multicasting is used to send the information to all the nodes of a group only. Maintaining or finding new locations of the nodes in a group is necessary for every multicast communication. Introducing multicasting in existing routing protocols solves the problem. This work proposes hybrid algorithm based on Genetic algorithm (GA) and Particle swarm optimization (PSO) for selecting optimal routes to multicasting group nodes. Simulations are done by varying number of mobile nodes and results are compared with multicast AODV (MAODV) protocol using the parameters such as jitter, delay and packet delivery ratio. Numeric results proved that packet delivery ratio is improved by 5 %, delay is decreased up to 25 % and jitter is reduced by 50 % in the proposed hybrid algorithm when compared to MAODV routing protocol.
Colonoscopy is currently the best technique available for the detection of colon cancer or colore... more Colonoscopy is currently the best technique available for the detection of colon cancer or colorectal polyps or other precursor lesions. Computer aided detection (CAD) is based on very complex pattern recognition. Local binary patterns (LBPs) are strong illumination invariant texture primitives. Histograms of binary patterns computed across regions are used to describe textures. Every pixel is contrasted relative to gray levels of neighbourhood pixels. In this study, colorectal polyp detection was performed with colonoscopy video frames, with classification via J48 and Fuzzy. Features such as color, discrete cosine transform (DCT) and LBP were used in confirming the superiority of the proposed method in colorectal polyp detection. The performance was better than with other current methods.
Mobile Ad hoc Network (MANET) is established for a limited period, for special extemporaneous ser... more Mobile Ad hoc Network (MANET) is established for a limited period, for special extemporaneous services related to mobile applications. This ad hoc network is set up for a limited period, in environments that change with the application. While in Internet the TCP/IP protocol suite supports a wide range of application, in MANETs protocols are tuned to specific customer/application. Multicasting is emerging as a popular communication format where the same packet is sent to multiple nodes in a network. Routing in multicasting involves maintaining routes and finding new node locations in a group and is NP-complete due to the dynamic nature of the network. In this paper, a Hybrid Genetic Based Optimization for Multicast Routing algorithm is proposed. The proposed algorithm uses the best features of Genetic Algorithm (GA) and particle swarm optimization (PSO) to improve the solution. Simulations were conducted by varying number of mobile nodes and results compared with Multicast AODV (MAODV) protocol, PSO based and GA based solution. The proposed optimization improves jitter, end to end delay and Packet Delivery Ratio (PDR) with faster convergence.
The motivation of image compression technique is to reduce irrelevance and redundancy of the imag... more The motivation of image compression technique is to reduce irrelevance and redundancy of the image data in order to be able to store or pass data in an efficient way from one place to another place. During the transmission of this compressed medical image faces many problems until it reach its destination. The major problems are data rate and security. Various kinds of medium is used to transfer a medical image. This paper presents the problem of secure transmission of medical images in wireless networks. Remote healthcare system is widely used in developed and developing countries. There are many reviewed algorithms which are applied to images. In this paper a study of various papers is done, and in the reviewed papers the patient information is embedded in the medical image and after applying encryption sends the message to the receiver. The study in this paper show how different methods provide security to medical imagery during transmission, and also once this digital data is received.
Telemedicine is a combination of Information Technology and Medical Sciences. Telemedicine is use... more Telemedicine is a combination of Information Technology and Medical Sciences. Telemedicine is used to provide medical information, healthcare services and medical consultations to the patients. One of the wireless networks that can be efficiently deployed during disaster recovery is known as wireless ad-hoc network (WANET). A WANET consists of several nodes which can communicate with each other nodes. Every node has been designed in order to send and receive data among several nodes. In this paper, we study the different compressing methods and efficient transmission in network environment. Many conventional image compression techniques and routing protocols have been analysed.
Mobile ad hoc networks (MANETs) include wireless communication and mobile nodes. High node mobil... more Mobile ad hoc networks (MANETs) include wireless communication and mobile nodes. High node mobility and limited wireless communication range mean that nodes have to cooperate in order to ensure networking, with the network changing to meet needs continually. Protocols’ dynamic nature enables MANET operation to ensure deployment in extreme/volatile circumstances. Hence, MANETs are very popular research topics and have been used in areas like tactical operations, rescue operations and environmental monitoring. This paper proposes a method to mitigate malicious nodes forming Denial of service attacks in associativity based ad hoc network. It is divided into two phases: detection before route establishment and avoiding malicious nodes in data forwarding. Simplicity and effectively detecting malicious nodes are the main points of the proposed scheme.
This paper presents the performance of Integrated
Bacterial Foraging Optimization and Particle Sw... more This paper presents the performance of Integrated Bacterial Foraging Optimization and Particle Swarm Optimization (IBFO_PSO) technique in MANET routing. The BFO is a bioinspired algorithm, which simulates the foraging behavior of bacteria. It is effectively applied in improving the routing performance in MANET. In results, it is proved that the PSO integrated with BFO reduces routing delay, energy consumption and communication overhead.
Routing in MANET is extremely challenging because of MANETs dynamic features, its limited bandwid... more Routing in MANET is extremely challenging because of MANETs dynamic features, its limited bandwidth, frequent topology changes caused by node mobility and power energy consumption. In order to efficiently transmit data to destinations, the applicable routing algorithms must be implemented in mobile ad-hoc networks. Thus we can increase the efficiency of the routing by satisfying the Quality of Service (QoS) parameters by developing routing algorithms for MANETs. The algorithms that are inspired by the principles of natural biological evolution and distributed collective behavior of social colonies have shown excellence in dealing with complex optimization problems and are becoming more popular. This paper presents a survey on few meta-heuristic algorithms and naturally-inspired algorithms.
In recent times, security in cloud computing has become a significant part in healthcare services... more In recent times, security in cloud computing has become a significant part in healthcare services specifically in medical data storage and disease prediction. A large volume of data are produced in the healthcare environment day by day due to the development in the medical devices. Thus, cloud computing technology is utilised for storing, processing, and handling these large volumes of data in a highly secured manner from various attacks. This paper focuses on disease classification by utilising image processing with secured cloud computing environment using an extended zigzag image encryption scheme possessing a greater tolerance to different data attacks. Secondly, a fuzzy convolutional neural network (FCNN) algorithm is proposed for effective classification of images. The decrypted images are used for classification of cancer levels with different layers of training. After classification, the results are transferred to the concern doctors and patients for further treatment process. Here, the experimental process is carried out by utilising the standard dataset. The results from the experiment concluded that the proposed algorithm shows better performance than the other existing algorithms and can be effectively utilised for the medical image diagnosis.
The main objective of Internet of Things (IoT) is connecting with different objects via Internet ... more The main objective of Internet of Things (IoT) is connecting with different objects via Internet without human intervention. Wireless Sensor Networks (WSNs) which involves ubiquitous computing through which small sensors are connected to the Internet and are used for collecting data. Significant amount of information flowing in the internet is made up of sensory data. To resolve the storage issues of the huge data generated by IoT, the Hadoop Distributed File System are used that streams data to user applications as required. It is difficult to accomplish analysis of vast amount of data (big data) with existing data processing methods. To avoid redundant and irrelevant data, the data needs to be classified. This work presents the use of Support Vector Machine, and Adaboost classifiers, and modifying Adaboost classifier with Genetic Algorithm (GA), Stochastic Diffusion Search (SDS), and Particle Swarm Optimization (PSO). To avoid redundant classifiers, an ensemble algorithm is proposed in this work, PSO with Adaboost classifier and SDS-GA with Adaboost classifier, that can reinitialize attributes, thus avoiding reaching local optimum, and optimizing the coefficients of Adaboost weak classifiers. The proposed algorithms effectively classify the data gathered from WSN and IoT applications. The outcomes of the experiment showed that the proposed SDS-GA algorithm is efficient over other algorithms with respect to accuracy, precision, recall, f measure and false discovery rate.
International Journal of Advanced Technology and Engineering Exploration, 2021
Automatic handwritten digit recognition provides significant contributions towards many real-time... more Automatic handwritten digit recognition provides significant contributions towards many real-time applications starting from the vehicle’s number plate to doctor’s prescription. However, the real challenge in these applications highly depends on the factors such as accuracy rate and time. Considering this significance, a novel handwritten digit recognition method is proposed without the adoption of any pre-processing steps like noise prediction, segmentation, and feature selection/extraction. The purpose of eliminating these preliminary steps is to reduce the computational complexity as the utilization of the Deep Learning (DL) approach helps to reduce the computational complexity of directly performing classification. Here, a novel Layered Convolutional Neural Networks (LCNN) model with an efficient Squirrel Optimizer (LCNN-SO) is modeled to attain better classification and global solution during the handwritten
The predictions of characters/text/digits from the handwritten images have made the research comm... more The predictions of characters/text/digits from the handwritten images have made the research community spotlight towards recognition. There are enormous applications and ambiguity that made prediction possible with Deep Learning (DL) approaches. Primarily, there are four necessary steps to be carried out with handwriting prediction. First, consideration of a dataset that is more appropriate for DL validation an inefficient manner. Here, Special Database 1 and Special Database 2 are used, which are combined and modified by the National Institute of Standards and Technology (NIST). Next is pre-processing of input handwritten digit recognition data by data normalization, extraction of efficient features which provides better prediction accuracy. The proposed idea uses pixel values as features with the analysis of hyper-parameters to enhance near-human performance. With SVM, non-linear and linear models are built to extract the appropriate features for further processing. The features are separate and placed over the Bag of Features (BoF), which is used by the next processing stage. Finally, a novel Convolutional Neural Network (CNN) is by built modifying the network structure with Orthogonal Learning Particle Swarm Optimization (CNN-OLPSO). This modification is adopted for evolutionarily optimizing the number of hyper-parameters. This proposed optimizer predicts the optimal values from the fitness computation and shows better efficiency when compared to various other conventional approaches. The novelty which relies on CNN adoption is to endeavor a suitable path towards digitalization and preserve the handwritten structure and help automatic feature extraction using CNN by offering better computation accuracy. The optimization approach helps to avoid over-fitting and under-fitting issues. Here, metrics like accuracy, elapsed time, recall, precision, and F-measure are evaluated. The results of CNN-OLPSO give better accuracy, reduced error rate and better execution time (s) compared to other existing methods. Thus, the proposed model shows better tradeoff in the recognition rate of handwritten digits.
A capsule network (CapsNet) is a new neural network model that is recently evolving in the field ... more A capsule network (CapsNet) is a new neural network model that is recently evolving in the field of image classification. Some of the shortcomings of traditional convolutional neural networks (CNNs) are compensated by the characteristics of CapsNet. It has proven to be effective at a variety of tasks, predominantly in medical image recognition with activation capsules. In this paper, image classification using the special designs in CapsNet is examined in depth. An additional reconstruction loss is used in the proposed work to empower the steering capsules and encode the input's instantiation parameters. The active vectors of higher-level capsules are used for the classification mechanism. The calculation at that point remakes the input picture thus utilizing these active vectors. The directing capsule's yield is sent into a decoder with three completely associated layers, which limits the whole of squared disparities between the calculated unit yields and the pixel power. In comparison to a typical CapsNet, the improved CapsNet method incorporates the extra parameters such as the number of measurements in each capsule sort (essential or directing capsules), the number of essential and directing capsules, and the number of channels within the capsule layer that are used for image classification. The experimental results show promising results in image recognition when compared to other CNN model-based algorithms.
International Conference on Hybrid Intelligent Systems, 2022
Book cover
International Conference on Hybrid Intelligent Systems
HIS 2021: Hybrid Intelligent S... more Book cover International Conference on Hybrid Intelligent Systems
HIS 2021: Hybrid Intelligent Systems pp 76–87Cite as
An Optimized Data Replication Algorithm in Mobile Edge Computing Systems to Reduce Latency in Internet of Things N. Saranya, K. Geetha & C. Rajan Conference paper First Online: 04 March 2022 194 Accesses
Part of the Lecture Notes in Networks and Systems book series (LNNS,volume 420)
Abstract The actual amount of data that was created applying the actuators, the sensors, and some other devices for the Internet of Things (IoT) has been showing a substantial level of increase in recent years. The data of IoT are handled using the cloud utilizing computing resources that are located in the data canters at a distance. As a result, the bandwidth of the network and the latency of communication have become major bottlenecks. The technology is known as Mobile Edge Computing (MEC) primarily seeks at encompassing the abilities of the cloud to the very edge of its radio access network thereby achieving low latency, real-time, and high bandwidth to the resources of the radio network. The IoT has been recognized as a key of the MEC with the ability of the MEC to be able to provide a new cloud platform along with gateway services. The MEC further inspired the progress of several masses of services and applications for a low-latency but high Quality of Service (QoS) owing to the geographical distribution and support for mobility. The MEC enables the applications and services of IoT for real-time operations. Replication of data is also suitable for increasing global traffic and response time and helps in data sharing. The nodes thereby continue to get access to the data replicas. This makes the problem of optimization work with many objectives. Flower Pollination Algorithm (FPA) is used to solve unconstrained optimization problems. Researchers are attracted to this algorithm for its processing speed, ease of modifying based on the requirement, and robustness. In this work, FPA is used to optimize the data replication. Experimental results shows the efficacy of the proposed method.
Machine learning has extensive application in diverse medical fields.With advancements in medical... more Machine learning has extensive application in diverse medical fields.With advancements in medical technologies, access has been given to data for the identification of diseases in theirearly stages. Alzheimer's Disease (AD) is a chronic illnessthat will cause degeneration of the brain cells and ultimately will lead to memoryloss. AD causedcognitive mental problems like forgetfulness and confusion, as well as other symptoms such aspsychologicaland behavioralproblems, are further recommended to undergo test procedures usingneuroimagingtechniques. This work's objective is to utilize the machinelearning algorithms for processing the data acquired via neuroimaging technologies for early-stage AD detection. The framework extracts featuresusingcurvelet transform from MRI brain image. This work will also present the Decision Tree, the Adaptive Boosting (AdaBoost), and the Extreme Gradient Boosting (XGBoost) classifiers. In machine learning, Population-Based Incremental Learning (PBIL) is an optimization algorithm, in spite of being simpler than a conventional genetic algorithm, the PBIL algorithm is able to achieve much better results in several cases.PBIL is used to optimize the AdaBoost and XGBoost classifiers to improve AD classification. The experimental outcomes will demonstrate the proposed approach's superior performance over that of other existing approaches.
Alzheimer's disease (AD) is the most common type of progressive neurological disorder that leads ... more Alzheimer's disease (AD) is the most common type of progressive neurological disorder that leads to the death of brain cells over the time. It causes memory loss and decline in the cognitive skills among the elderly subjects. Early diagnosis of the progressive diseases plays a vital role in the healthcare community. Machine learning (ML) algorithms and various multivariate data exploratory tools are employed in the field of AD research. The main purpose of this work is to analyse the importance of features selection which in turn enhances the classification accuracy of the models. The hyper parameter tuning for Support Vector Machine (SVM) classification and Boruta algorithm for Random Forest (RF) classification are applied for the selection of optimal set of features. In this work, a five-stage ML pipeline with each stage further categorized into different sub-levels is proposed. Initially, the data collected from the Open Access Series of Imaging Studies (OASIS-2) dataset of Magnetic Resonance Imaging (MRI) brain images is explored and pre-processed using the imputation technique. Feature scaling of the pre-processed data is done using the Min-max scaling technique. Then, the classification techniques such as logistic regression, Decision Tree (DT) classification, Random Forest (RF) classification, Support Vector Machine (SVM) classification and AdaBoost Classification are applied to classify the data and finally the performance of the classifiers are compared in terms of accuracy, Area under the curve of the Receiver Operating Characteristic (AUC) curve and recall measures. From the performance analysis, it is concluded that the Random Forest (RF) classifier yields maximum accuracy, recall and AUC values. The hyperparameter tuning and Boruta algorithm added significance to the SVM and RF classification, thereby resulting in a F-score of 91% and 92% respectively.
Alzheimer's Disease (AD) or just Alzheimer's, is a neural condition of the human brain which is g... more Alzheimer's Disease (AD) or just Alzheimer's, is a neural condition of the human brain which is getting to be increasingly notorious for its chronic neurodegenerative capability to disorient the human mind and body completely. AD is getting to be more prevalent among the older people globally. Earlier, physical and mental assessments were the only gauge to find AD, but currently Magnetic Resonance Imaging (MRI), a valuable asset in medicine is getting to be increasingly effective in recognizing and diagnosing this disease. Various techniques have been found to help discern AD and " Mild Cognitive Impairment " (MCI), a brain function syndrome homogeneous to AD, but less severe.The proposed method utilizing a wrapper based feature selection technique for identifying a classification accuracy of an AD and then proposed Social Spider Metaheuristic is used to identify the significant features to diagnose an AD in effectively. Result shows the accuracy of the proposed technique.
Colonoscopy is a technique for examine colon cancer, polyps. In endoscopy, video capsule is unive... more Colonoscopy is a technique for examine colon cancer, polyps. In endoscopy, video capsule is universally used mechanism for finding gastrointestinal stages. But both the mechanisms are used to find the colon cancer or colorectal polyp. The Automatic Polyp Detection sub-challenge conducted as part of the Endoscopic Vision Challenge (http://endovis.grand-challenge.org). Method: Colonoscopy may be primary way of improve the ability of colon cancer detection especially flat lesions. Which otherwise may be difficult to detect. Recently, automatic polyp detection algorithms have been proposed with various degrees of success. Though polyp detection in colonoscopy and other traditional endoscopy procedure based images is becoming a mature field, due to its unique imaging characteristics, detecting polyps automatically in colonoscopy is a hard problem. So the proposed video capsule cam supports to diagnose the polyps accurate and easy to identify its pattern. Existing methodology mainly concentrated on high accuracy and less time consumption and it uses many different types of data mining techniques. To analyse these high resolution video scale image we have to take segmentation of image in pixel level binary pattern with the help of a mid-pass filter and relative gray level of neighbours. This work consists of three major steps to improve the accuracy of video capsule endoscopy such as missing data imputation, high dimensionality reduction or feature selection and classification. The above steps are performed using a dataset called endoscopy polyp disease dataset with 500 patients. Our binary classification algorithm relieves human analyses using the video frames. SVM has given major contribution to process the dataset. Results: In this paper the key aspect of proposed results provide segmentation, binary pattern approach with Genetic Fuzzy based Improved Kernel Support Vector machine (GF-IKSVM) classifier. The segmented images all are mostly round shape. The result is refined via smooth filtering, computer vision methods and thresholding steps. Conclusion: Our experimental result produces 94.4% accuracy in that the proposed fuzzy system and genetic Fuzzy, which is higher than the methods, used in the literature. The GF-IKSVM classifier is well-organized and provides good accuracy results for patched VCE polyp disease diagnosis.
The motivation of image compression technique is to reduce the irrelevance and redundancy of the ... more The motivation of image compression technique is to reduce the irrelevance and redundancy of the image data in order to store or pass data in an efficient way from one place to another place. There are several types of compression methods available. Without the help of compression technique, the file size is knowingly larger, usually several megabytes, but by doing the compression technique, it is possible to reduce file size up to 10% as of the original without noticeable loss in quality. Image compression can be lossless or lossy. The compression technique can be applied to images, audio, video and text data. This research work mainly concentrates on methods of encoding, DCT, compression methods, security, etc. Different methodologies and network simulations have been analyzed here. Various methods of compression methodologies and its performance metrics has been investigated and presented in a table manner.
Mobile Ad Hoc Network (MANET) nodes are small, low cost, limited capable and mobile nodes with no... more Mobile Ad Hoc Network (MANET) nodes are small, low cost, limited capable and mobile nodes with no centralized administration control. All the nodes communicate using wireless channel with multi-hop paths. As the usage of small size portable devices are increasing day by day, all the future networks will be only the MANET. Mobility of the nodes creates the major challenge in routing and providing Quality of Service (QoS) to the applications of MANET. Multicasting is used to send the information to all the nodes of a group only. Maintaining or finding new locations of the nodes in a group is necessary for every multicast communication. Introducing multicasting in existing routing protocols solves the problem. This work proposes hybrid algorithm based on Genetic algorithm (GA) and Particle swarm optimization (PSO) for selecting optimal routes to multicasting group nodes. Simulations are done by varying number of mobile nodes and results are compared with multicast AODV (MAODV) protocol using the parameters such as jitter, delay and packet delivery ratio. Numeric results proved that packet delivery ratio is improved by 5 %, delay is decreased up to 25 % and jitter is reduced by 50 % in the proposed hybrid algorithm when compared to MAODV routing protocol.
Colonoscopy is currently the best technique available for the detection of colon cancer or colore... more Colonoscopy is currently the best technique available for the detection of colon cancer or colorectal polyps or other precursor lesions. Computer aided detection (CAD) is based on very complex pattern recognition. Local binary patterns (LBPs) are strong illumination invariant texture primitives. Histograms of binary patterns computed across regions are used to describe textures. Every pixel is contrasted relative to gray levels of neighbourhood pixels. In this study, colorectal polyp detection was performed with colonoscopy video frames, with classification via J48 and Fuzzy. Features such as color, discrete cosine transform (DCT) and LBP were used in confirming the superiority of the proposed method in colorectal polyp detection. The performance was better than with other current methods.
Mobile Ad hoc Network (MANET) is established for a limited period, for special extemporaneous ser... more Mobile Ad hoc Network (MANET) is established for a limited period, for special extemporaneous services related to mobile applications. This ad hoc network is set up for a limited period, in environments that change with the application. While in Internet the TCP/IP protocol suite supports a wide range of application, in MANETs protocols are tuned to specific customer/application. Multicasting is emerging as a popular communication format where the same packet is sent to multiple nodes in a network. Routing in multicasting involves maintaining routes and finding new node locations in a group and is NP-complete due to the dynamic nature of the network. In this paper, a Hybrid Genetic Based Optimization for Multicast Routing algorithm is proposed. The proposed algorithm uses the best features of Genetic Algorithm (GA) and particle swarm optimization (PSO) to improve the solution. Simulations were conducted by varying number of mobile nodes and results compared with Multicast AODV (MAODV) protocol, PSO based and GA based solution. The proposed optimization improves jitter, end to end delay and Packet Delivery Ratio (PDR) with faster convergence.
The motivation of image compression technique is to reduce irrelevance and redundancy of the imag... more The motivation of image compression technique is to reduce irrelevance and redundancy of the image data in order to be able to store or pass data in an efficient way from one place to another place. During the transmission of this compressed medical image faces many problems until it reach its destination. The major problems are data rate and security. Various kinds of medium is used to transfer a medical image. This paper presents the problem of secure transmission of medical images in wireless networks. Remote healthcare system is widely used in developed and developing countries. There are many reviewed algorithms which are applied to images. In this paper a study of various papers is done, and in the reviewed papers the patient information is embedded in the medical image and after applying encryption sends the message to the receiver. The study in this paper show how different methods provide security to medical imagery during transmission, and also once this digital data is received.
Telemedicine is a combination of Information Technology and Medical Sciences. Telemedicine is use... more Telemedicine is a combination of Information Technology and Medical Sciences. Telemedicine is used to provide medical information, healthcare services and medical consultations to the patients. One of the wireless networks that can be efficiently deployed during disaster recovery is known as wireless ad-hoc network (WANET). A WANET consists of several nodes which can communicate with each other nodes. Every node has been designed in order to send and receive data among several nodes. In this paper, we study the different compressing methods and efficient transmission in network environment. Many conventional image compression techniques and routing protocols have been analysed.
Mobile ad hoc networks (MANETs) include wireless communication and mobile nodes. High node mobil... more Mobile ad hoc networks (MANETs) include wireless communication and mobile nodes. High node mobility and limited wireless communication range mean that nodes have to cooperate in order to ensure networking, with the network changing to meet needs continually. Protocols’ dynamic nature enables MANET operation to ensure deployment in extreme/volatile circumstances. Hence, MANETs are very popular research topics and have been used in areas like tactical operations, rescue operations and environmental monitoring. This paper proposes a method to mitigate malicious nodes forming Denial of service attacks in associativity based ad hoc network. It is divided into two phases: detection before route establishment and avoiding malicious nodes in data forwarding. Simplicity and effectively detecting malicious nodes are the main points of the proposed scheme.
This paper presents the performance of Integrated
Bacterial Foraging Optimization and Particle Sw... more This paper presents the performance of Integrated Bacterial Foraging Optimization and Particle Swarm Optimization (IBFO_PSO) technique in MANET routing. The BFO is a bioinspired algorithm, which simulates the foraging behavior of bacteria. It is effectively applied in improving the routing performance in MANET. In results, it is proved that the PSO integrated with BFO reduces routing delay, energy consumption and communication overhead.
Routing in MANET is extremely challenging because of MANETs dynamic features, its limited bandwid... more Routing in MANET is extremely challenging because of MANETs dynamic features, its limited bandwidth, frequent topology changes caused by node mobility and power energy consumption. In order to efficiently transmit data to destinations, the applicable routing algorithms must be implemented in mobile ad-hoc networks. Thus we can increase the efficiency of the routing by satisfying the Quality of Service (QoS) parameters by developing routing algorithms for MANETs. The algorithms that are inspired by the principles of natural biological evolution and distributed collective behavior of social colonies have shown excellence in dealing with complex optimization problems and are becoming more popular. This paper presents a survey on few meta-heuristic algorithms and naturally-inspired algorithms.
Traditional gaining knowledge of strategies is being changed with agile, collaborative, and techn... more Traditional gaining knowledge of strategies is being changed with agile, collaborative, and technology-primarily based totally training. Education with the most up-to-date school room technology permits present-day gaining knowledge of environments, bridging the virtual divide, and putting together college students for the future. Internet of Things (IoT) in hand with Internet does this wonder. A top-notch technological switch is being achieved with IoT. IoT is withinside the system of transmuting many fields of our ordinary lives. IoT is utilized in all sectors, linking the Internet with gadgets like computers, smartphones, and each different gadget. As Internet has rooted itself into our schools, E-getting to know is becoming a now no longer unusual place exercising throughout the globe.
Uploads
Papers by Dr.Rajan C
International Conference on Hybrid Intelligent Systems
HIS 2021: Hybrid Intelligent Systems pp 76–87Cite as
An Optimized Data Replication Algorithm in Mobile Edge Computing Systems to Reduce Latency in Internet of Things
N. Saranya, K. Geetha & C. Rajan
Conference paper
First Online: 04 March 2022
194 Accesses
Part of the Lecture Notes in Networks and Systems book series (LNNS,volume 420)
Abstract
The actual amount of data that was created applying the actuators, the sensors, and some other devices for the Internet of Things (IoT) has been showing a substantial level of increase in recent years. The data of IoT are handled using the cloud utilizing computing resources that are located in the data canters at a distance. As a result, the bandwidth of the network and the latency of communication have become major bottlenecks. The technology is known as Mobile Edge Computing (MEC) primarily seeks at encompassing the abilities of the cloud to the very edge of its radio access network thereby achieving low latency, real-time, and high bandwidth to the resources of the radio network. The IoT has been recognized as a key of the MEC with the ability of the MEC to be able to provide a new cloud platform along with gateway services. The MEC further inspired the progress of several masses of services and applications for a low-latency but high Quality of Service (QoS) owing to the geographical distribution and support for mobility. The MEC enables the applications and services of IoT for real-time operations. Replication of data is also suitable for increasing global traffic and response time and helps in data sharing. The nodes thereby continue to get access to the data replicas. This makes the problem of optimization work with many objectives. Flower Pollination Algorithm (FPA) is used to solve unconstrained optimization problems. Researchers are attracted to this algorithm for its processing speed, ease of modifying based on the requirement, and robustness. In this work, FPA is used to optimize the data replication. Experimental results shows the efficacy of the proposed method.
used mechanism for finding gastrointestinal stages. But both the mechanisms are used to find the colon cancer or
colorectal polyp. The Automatic Polyp Detection sub-challenge conducted as part of the Endoscopic Vision Challenge
(http://endovis.grand-challenge.org). Method: Colonoscopy may be primary way of improve the ability of colon
cancer detection especially flat lesions. Which otherwise may be difficult to detect. Recently, automatic polyp detection
algorithms have been proposed with various degrees of success. Though polyp detection in colonoscopy and other
traditional endoscopy procedure based images is becoming a mature field, due to its unique imaging characteristics,
detecting polyps automatically in colonoscopy is a hard problem. So the proposed video capsule cam supports to diagnose
the polyps accurate and easy to identify its pattern. Existing methodology mainly concentrated on high accuracy and
less time consumption and it uses many different types of data mining techniques. To analyse these high resolution
video scale image we have to take segmentation of image in pixel level binary pattern with the help of a mid-pass filter
and relative gray level of neighbours. This work consists of three major steps to improve the accuracy of video capsule
endoscopy such as missing data imputation, high dimensionality reduction or feature selection and classification.
The above steps are performed using a dataset called endoscopy polyp disease dataset with 500 patients. Our binary
classification algorithm relieves human analyses using the video frames. SVM has given major contribution to process
the dataset. Results: In this paper the key aspect of proposed results provide segmentation, binary pattern approach
with Genetic Fuzzy based Improved Kernel Support Vector machine (GF-IKSVM) classifier. The segmented images
all are mostly round shape. The result is refined via smooth filtering, computer vision methods and thresholding steps.
Conclusion: Our experimental result produces 94.4% accuracy in that the proposed fuzzy system and genetic Fuzzy,
which is higher than the methods, used in the literature. The GF-IKSVM classifier is well-organized and provides good
accuracy results for patched VCE polyp disease diagnosis.
proposed scheme.
Bacterial Foraging Optimization and Particle Swarm Optimization (IBFO_PSO) technique in MANET routing. The BFO is a bioinspired algorithm, which simulates the foraging behavior of bacteria. It is effectively applied in improving the routing performance in MANET. In results, it is proved that the PSO integrated with BFO reduces routing delay, energy consumption and communication overhead.
topology changes caused by node mobility and power energy
consumption. In order to efficiently transmit data to destinations, the applicable routing algorithms must be implemented in mobile ad-hoc networks. Thus we can increase the efficiency of the routing by satisfying the Quality of Service (QoS) parameters by developing routing algorithms for MANETs. The algorithms that are inspired by the principles of natural biological evolution and distributed
collective behavior of social colonies have shown excellence in dealing with complex optimization problems and are becoming more popular. This paper presents a survey on few meta-heuristic algorithms and naturally-inspired algorithms.
International Conference on Hybrid Intelligent Systems
HIS 2021: Hybrid Intelligent Systems pp 76–87Cite as
An Optimized Data Replication Algorithm in Mobile Edge Computing Systems to Reduce Latency in Internet of Things
N. Saranya, K. Geetha & C. Rajan
Conference paper
First Online: 04 March 2022
194 Accesses
Part of the Lecture Notes in Networks and Systems book series (LNNS,volume 420)
Abstract
The actual amount of data that was created applying the actuators, the sensors, and some other devices for the Internet of Things (IoT) has been showing a substantial level of increase in recent years. The data of IoT are handled using the cloud utilizing computing resources that are located in the data canters at a distance. As a result, the bandwidth of the network and the latency of communication have become major bottlenecks. The technology is known as Mobile Edge Computing (MEC) primarily seeks at encompassing the abilities of the cloud to the very edge of its radio access network thereby achieving low latency, real-time, and high bandwidth to the resources of the radio network. The IoT has been recognized as a key of the MEC with the ability of the MEC to be able to provide a new cloud platform along with gateway services. The MEC further inspired the progress of several masses of services and applications for a low-latency but high Quality of Service (QoS) owing to the geographical distribution and support for mobility. The MEC enables the applications and services of IoT for real-time operations. Replication of data is also suitable for increasing global traffic and response time and helps in data sharing. The nodes thereby continue to get access to the data replicas. This makes the problem of optimization work with many objectives. Flower Pollination Algorithm (FPA) is used to solve unconstrained optimization problems. Researchers are attracted to this algorithm for its processing speed, ease of modifying based on the requirement, and robustness. In this work, FPA is used to optimize the data replication. Experimental results shows the efficacy of the proposed method.
used mechanism for finding gastrointestinal stages. But both the mechanisms are used to find the colon cancer or
colorectal polyp. The Automatic Polyp Detection sub-challenge conducted as part of the Endoscopic Vision Challenge
(http://endovis.grand-challenge.org). Method: Colonoscopy may be primary way of improve the ability of colon
cancer detection especially flat lesions. Which otherwise may be difficult to detect. Recently, automatic polyp detection
algorithms have been proposed with various degrees of success. Though polyp detection in colonoscopy and other
traditional endoscopy procedure based images is becoming a mature field, due to its unique imaging characteristics,
detecting polyps automatically in colonoscopy is a hard problem. So the proposed video capsule cam supports to diagnose
the polyps accurate and easy to identify its pattern. Existing methodology mainly concentrated on high accuracy and
less time consumption and it uses many different types of data mining techniques. To analyse these high resolution
video scale image we have to take segmentation of image in pixel level binary pattern with the help of a mid-pass filter
and relative gray level of neighbours. This work consists of three major steps to improve the accuracy of video capsule
endoscopy such as missing data imputation, high dimensionality reduction or feature selection and classification.
The above steps are performed using a dataset called endoscopy polyp disease dataset with 500 patients. Our binary
classification algorithm relieves human analyses using the video frames. SVM has given major contribution to process
the dataset. Results: In this paper the key aspect of proposed results provide segmentation, binary pattern approach
with Genetic Fuzzy based Improved Kernel Support Vector machine (GF-IKSVM) classifier. The segmented images
all are mostly round shape. The result is refined via smooth filtering, computer vision methods and thresholding steps.
Conclusion: Our experimental result produces 94.4% accuracy in that the proposed fuzzy system and genetic Fuzzy,
which is higher than the methods, used in the literature. The GF-IKSVM classifier is well-organized and provides good
accuracy results for patched VCE polyp disease diagnosis.
proposed scheme.
Bacterial Foraging Optimization and Particle Swarm Optimization (IBFO_PSO) technique in MANET routing. The BFO is a bioinspired algorithm, which simulates the foraging behavior of bacteria. It is effectively applied in improving the routing performance in MANET. In results, it is proved that the PSO integrated with BFO reduces routing delay, energy consumption and communication overhead.
topology changes caused by node mobility and power energy
consumption. In order to efficiently transmit data to destinations, the applicable routing algorithms must be implemented in mobile ad-hoc networks. Thus we can increase the efficiency of the routing by satisfying the Quality of Service (QoS) parameters by developing routing algorithms for MANETs. The algorithms that are inspired by the principles of natural biological evolution and distributed
collective behavior of social colonies have shown excellence in dealing with complex optimization problems and are becoming more popular. This paper presents a survey on few meta-heuristic algorithms and naturally-inspired algorithms.