R. AROUL CANESSANE
Verified @gmail.com
professor/computer science and engineering
sathyabama
RESEARCH INTERESTS
software engineering, networking, AI , ML, IOT, Drones
Scopus Publications
Scopus Publications
R. Dhanalakshmi, B. Muthukumar, and R. Aroulcanessane
Springer Science and Business Media LLC
Rajesh Kumar C and Aroul Canessane R
IEEE
Cloud computing has emerged as a technology behemoth with applications in a wide range of fields. When data is being migrated from offline data centres and stored in multiple cloud environments part of the control is always with the Cloud Service Providers(CSPs) leads to security concerns. The data stored in the cloud may sometimes be compromised even though the CSPs may take precautions to avoid such situations. In this paper, we discuss securely storing the data using the data dispersion technique by breaking the data into multiple segments and combining it with encryption along with replication. The division of data and storing it in the cloud helps in protecting the complete data even if an attacker tries to access the data it will not be easy for him to make sense of the retrieved data because the data is already being encrypted and combined with dispersion and replication adds to the complexity of retrieval. Security is achieved as the dispersed data is spread across multiple locations which makes it difficult for an attacker to get all the segments. In most scenarios be able it depends on traditional encryption techniques alone to protect the data. Here, We propose focusing more on how data is stored in the cloud to relieve the system of costly computational methodologies. In this strategy, the trade-off between security and the data retrieval time must also be considered.
Anitha Ponraj and Aroul Canessane
Science Publications
Anitha Ponraj and R.Aroul Canessane
IEEE
In the modern era, cancer is a major public health concern. Breast cancer is one of the leading causes of death among women. Breast cancer is becoming the top cause of death in women worldwide. Early identification of breast cancer allows patients to receive proper treatment, improving their chances of survival. The proposed Generative Adversarial Networks (GAN) approach is designed to aid in the detection and diagnosis of breast cancer. GANs are deep learning algorithms that generate new data instances that mimic the training data. GAN is made up of two parts: a generator that learns to generate false data and a discriminator that learns from this false data. Furthermore, the histogram of oriented gradients (HOG) is utilized as a feature descriptor in image processing and other computer vision techniques. Gradient orientation in the detection window and region of interest is determined by the histogram of oriented gradients descriptor approach. Using an image dataset and deep learning techniques, the proposed research (GAN-HOG) aims to improve the efficiency and performance of breast cancer diagnosis. The deep learning method is used here to analyze image data by segmenting and classifying the input photographs from the dataset. Unlike many existing nonlinear classification models, the proposed method employs a conditional distribution for the outputs. The proposed model GAN-HOG had an accuracy of 98.435%, a ResNet50 accuracy of 87.826%, a DCNN accuracy of 92.547%, a VGG16 accuracy of 89.453%, and an SVM accuracy of 95.546%.
Anitha Ponraj and R. Aroul Canessane
Springer Science and Business Media LLC
B Sandhiya and R.Aroul Canessane
IEEE
The proliferation of IoT has resulted in a rise in the demand for services provided by the fog layer, a novel dispersed computing pattern that supplements cloud computing. The fog system enables location awareness and mobility assistance by extending storage and multiplication to the network’s edge, dramatically reducing the issue of service computing in delay-sensitive applications. More requests from more users means more stress for the VMs running in the fog layer. When it comes to fog networks, Load Balancing (LB) is crucial since it prevents some fog nodes from being under- or overworked. Fairly dividing up the fog layer’s burden across the available virtual machines (VMs) is now an absolute must. LB can enhance quality-of-service metrics including cost, response time, performance, and energy ingesting. Although there has been limited investigation of load complementary techniques in fog networks in recent years, no comprehensive analysis has been conducted to compile this information. This article takes a systematic look at the various load-balancing procedures in fog computing, categorizing it as either approximate, precise, fundamental, or hybrid. In addition, the study explores (Load Balancing) LB metrics, including the benefits and drawbacks of the techniques used for fog networks. There is also an examination of the methods and instruments used in the aforementioned evaluations of each research under consideration. The most unanswered questions and emerging tendencies for these algorithms are also covered. In the final section, the study suggests potential avenues for further research.
L. Jenila and R. Aroul Canessane
Agora University of Oradea
Video transmission using sensor networks plays a most significant role in industrial and surveillance applications. Multimedia transmission is also a challenging task in case of guaranteeing quality of service in conditions like limited bandwidth, high congestion, multi-hop routing, etc. Cross layer approach is carried out to handle multimedia transmission over sensor networks for improving network adaptivity. Cross layer based energy aware and packet scheduling algorithm is proposed here to reduce congestion ratio and to improve link quality between the routing nodes. Link quality estimation among nodes is done using Semi-Markov process. Node congestion rate is determined for identifying node’s data channel rate. Packet scheduling process determines the highly prioritized packets by using queue scheduler component thereby the active nodes are selected through link quality process and the packets are transmitted to sink based on prioritize level. Simulation analysis is carried out and the efficiency of the proposed mechanism is proved to be better while comparing with the conventional schemes.
M.S. Minu and R. Aroul Canessane
Elsevier BV
Priyadharshini K. and R. Aroul Canessane
IGI Global
Presently, the technological developments in the field of human-computer interaction (HCI) have shown that developers are developing cognitive vision systems that provide normal and effective operating mechanism for smart sensors, and the privacy should be maintained in the course of data transfer. Blockchain technology received significant interest to remove third-party business providers, to introduce HCI rapidly, and for secure information sharing in the network. Therefore this paper presents blockchain assisted cognitive vision systems for human-computer interaction and secured data sharing (BCVS-DS) framework. Cognitive vision systems use the information from various sensors that is used to handle and joined by blending techniques. The secured data sharing (SDS) method is flexible and efficiently manages permission by spreading various user characteristics to multiple authorization centers. Experimental results are tested for BCVS-DS by AVEC dataset. BCVS-DS achieves the highest classification accuracy of 94.32%.
R. Dhanalakshmi, B. Muthukumar, and R. Aroul Canessane
World Scientific Pub Co Pte Ltd
Data mining is a method that gives valuable information where we can improve and achieve the goal. Existing data mining techniques are applied in education for analyzing the performance of students, classes, and institutions. This helps the teachers and management to identify where they lag and improvise. Some mining techniques are used to predict and identify special children’s categories. In this paper, data mining techniques are applied for the special children to predict the achievement in special school study for child categories like Mental Retardation (MR), autism, and cerebral palsy using the collected assessment detail. Vocational training is considered an essential aspect for special school children for their future survival. Data mining methods are applied to mine the most achievable and essential training factors as a pattern by apriori rule mining and high utility pattern mining algorithms, based on their assessment achieved from the age 10–14, where Madras developmental programming scale is followed in special schools. We can predict which category children are achieving necessary factors, which helps identify the alternate methods to train the particular activity. Essential factors that cannot achieve at the same level will be trained in the next prevocational level to reach their vocational training. The prediction that we have made will be helpful for the teachers to train the children concerning their achievements.
Minu M S, Aroul Canessane R, and Subashka Ramesh S S
International Information and Engineering Technology Association
In present times, unmanned aerial vehicles (UAVs) are widely employed in several real time applications due to their autonomous, inexpensive, and compact nature. Aerial image classification in UAVs has gained significant interest in surveillance systems that assist object detection and tracking processes. The advent of deep learning (DL) models paves a way to design effective aerial image classification techniques in UAV networks. In this view, this paper presents a novel optimal Squeezenet with a deep neural network (OSQN-DNN) model for aerial image classification in UAV networks. The proposed OSQN-DNN model initially enables the UAVs to capture images using the inbuilt imaging sensors. Besides, the OSQN model is applied as a feature extractor to derive a useful set of feature vectors where the coyote optimization algorithm (COA) is employed to optimally choose the hyperparameters involved in the classical SqueezeNet model. Moreover, the DNN model is utilized as a classifier that aims to allocate proper class labels to the applied input aerial images. Furthermore, the usage of COA for hyperparameter tuning of the SqueezeNet model helps to considerably boost the overall classification performance. For examining the enhanced aerial image classification performance of the OSQN-DNN model, a series of experiments were performed on the benchmark UCM dataset. The experimental results pointed out that the OSQN-DNN model has resulted in a maximum accuracy of 98.97% and a minimum running time of 1.26mts.
Priyadharshini K. and Aroul Canessane R.
IGI Global
With the recent trends in the integration of blockchain with the internet of things (IoT), individuals are more concerned about security issues such as user privacy and confidentiality. Public key cryptography is the commonly used scheme for encryption of blockchain data. Since IoT integrates multiple devices, tracking the origin of any problem is a major issue of these systems. Moreover, IoT market system is highly unregulated. This leads to security as the biggest concern of the blockchain intersected IoT devices. To overcome these issues, in this work we propose a new encryption methodology called Chaotic-Rivest–Shamir–Adleman (C-RSA) algorithm. In this methodology, the chaotic systems are integrated with the RSA algorithm. Chaotic sequences are extremely sensitive to initial conditions and control parameters. They also exhibit extreme random behavior. This system achieved high average PSNR of 52.24 and very low MSE of 0.085. Moreover, the key space attained by this system was as high as (2)600.
L. Jenila and R. Aroul Canessane
FOREX Publication
The data traffic volume is generally huge in multimedia networks since it comprises multimodal sensor nodes also communication takes place with variable capacity during video transmission. The data should be processed in a collision free mode. Therefore, the packets should be scheduled and prioritized dynamically. Dynamic traffic scheduling and optimal routing protocol with cross layer design is proposed here to select the energy efficient nodes and to transmit the scheduled data effectively. At first, the optimal routes are discovered by selecting the best prime nodes then the packets are dynamically scheduled on the basis of severity of data traffic. The proposed method works in two stages such as (i) Selection of chief nodes and (ii) Dynamic packet scheduling. The first stage of this mechanism is chief node selection and these chief nodes are selected for optimal routing. Selection of chief nodes is done by estimating the distance between the nodes, and energy value of the nodes. This stage makes the network energy efficient. The second stage is involved with dynamic scheduling of packets and sending the packets with respect to the Packet Priority of queue index key value. Real-time data packets (PQP1) have very high priority and it is scheduled using Earliest Deadline First Scheduling (EDFS) algorithm when compared to non-real time data packets (PQP2 and PQP3) which is scheduled on basis of First Come First Serve (FCFS) manner. This process minimizes the congestion and avoids the unnecessary transmission delay. Therefore, the results are analyzed through the simulation process and the efficiency of the proposed methodology is 56% better than the existing methodologies.
Vyash Natarajan, Yogeshwaran M, and Aroul Canessane
IEEE
The world is overwhelmed by its new technologies and inventions. Recent years witness that, every part of the world is integrating with technology to become more productive and powerful. To contribute more to this technology driven society, this research study attempts to propose an automated model for the blind stick used by blind people to assist and establish a safe and secure environment for the blind population as a part of this generation's dedication to contributing more to society through technology. This model has been successfully developed with the concept of Internet of Things [IoT] by integrating necessary sensors and Arduino UNO processor.
Priyadharshini Kaliyamoorthy and Aroul Canessane Ramalingam
Springer Science and Business Media LLC
K. Priyadharshini and R. Aroul Canessane
Wiley
Shilpa P. Khedkar and Aroul Canessane Ramalingam
International Information and Engineering Technology Association
The Internet of Things (IoT) is a rising infrastructure of 21st century. The classification of traffic over IoT networks is attained significance importance due to rapid growth of users and devices. It is need of the hour to isolate the normal traffic from the malicious traffic and to assign the normal traffic to the proper destination to suffice the QoS requirements of the IoT users. Detection of malicious traffic can be done by continuously monitoring traffic for suspicious links, files, connection created and received, unrecognised protocol/port numbers, and suspicious Destination/Source IP combinations. A proficient classification mechanism in IoT environment should be capable enough to classify the heavy traffic in a fast manner, to deflect the malevolent traffic on time and to transmit the benign traffic to the designated nodes for serving the needs of the users. In this work, adaboost and Xgboost machine learning algorithms and Deep Neural Networks approach are proposed to separate the IoT traffic which eventually enhances the throughput of IoT networks and reduces the congestion over IoT channels. The result of experiment indicates a deep learning algorithm achieves higher accuracy compared to machine learning algorithms.
Shiela David and Aroul Canessane
IEEE
Electric power networks are evolving rapidly across the globe. In order to deliver energy to the end users, traditional systems had to rely heavily on a centralized network, which led to increased cyber-attacks against the power systems, causing instability and serious problems such as blackouts. In this paper, by providing high protection to the modern power system using block chain technology, the outlined triggers can be solved by maintaining essential records through the decentralized ledger that magnifies the firmness of the electric power system. The key operational data are encapsulated in the form of blocks and hashed to create a unique value. The paper flow begins from the collection of information where the basic data is obtained. The encryption and decryption of the information is then carried out using the SHA-256 algorithm. In addition, there is a method of data validation with the assistance of the Byzantine Fault Tolerance algorithm, which allows all nodes to achieve consensus agreement. In addition, after efficient validation of the blocks by the miners who validate it using mathematical problem, the linking of blocks occurs to find the nonce, which is nothing but the solution for adding up the consecutive blocks. Finally, attack classification takes place where the daily electrical use dataset is pre-processed, conditioned and evaluated.
Shilpa P. Khedkar and Aroul Canessane Ramalingam
International Information and Engineering Technology Association
Traffic classification is very important field of computer science as it provides network management information. Classification of traffic become complicated due to emerging technologies and applications. It is used for Quality of Service (QoS) provisioning, security and detecting intrusion in a system. In the past used of port, inspecting packet, and machine learning algorithms have been used widely, but due to the sudden changes in the traffic, their accuracy was diminished. In this paper a Multi-Layer Perceptron model with 2 hidden layers is proposed for traffic classification and target traffic classify into different categories. The experimental results indicate that proposed classifier efficiently classifies traffic and achieves 99.28% accuracy without feature engineering.
M. S. Minu and R. Aroul Canessane
IEEE
Unmanned aerial vehicles (UAVs) typically fly at low altitudes for capturing high-resolution images covering smaller areas. Since short flights also and high-resolution cameras lead to the generation of massive gigabytes (GBs) of data regions, image compression is essential to compress the data to a compact form resulted in shorter file size without any loss of quality. The vector quantization (VQ) is an effective type of image compression and the conventionally employed technique namely Linde-Buzo-Gray (LBG) algorithm continually created local optimal codebook. The codebook design process can be considered as a high dimensional optimization problem and can be resolved by the use of swarm intelligence algorithms. This paper designs a novel squirrel search algorithm (SSA) with LBG based image compression technique, called SSA-LBG for UAVs. The SSA is applied for the construction of codebooks for VQ and it makes use of LBG model as the initialization of the SSA for VQ. The application of SSA-LBG results in effective compression with low computation time (CT) and high peak signal to noise ratio (PSNR). An extensive set of simulations were performed on benchmark test images and the results are examined with respect to CT and PSNR undervarying bit rates and codebook sizes.
K. Priyadharshini and R.Aroul Canessane
IEEE
This manuscript describes since the resources are heterogeneous, a smart city is vulnerable to several security attacks, and to devise an effective response, it is necessary to recognize certain risks and their potential implications. The framework is responsible for the data transfer security issues in the smart city to incorporate and maintain physical, social, and industrial systems to provide high-quality secure data transmission to its residents. The proposed method of integrating the Blockchain and Internet of Things (IoT) with a consensus algorithm framework (BCIoT-CAF) to overcome the issues and secure data sharing in smart cities. The data security is enforced by splitting the blockchain network into separate networks, with any channel consisting of a limited number of approved entities, the data stored in the cloud gate server, and analysis of data achieved by IoT applications. The consensus algorithm plays an important role in retaining the blockchain’s speed, protection, and performance. Using an appropriate security algorithm, blockchain applications may greatly improve their performance. The modeling simulation of this research improves the speed, protection, and efficiency of 96% and tolerance error as 55%. The integrated evaluation results suggest that the proposed system integrates blockchain with IoT to provide a shielded communication platform in smart cities.
Shilpa P. Khedkar, R. Aroul Canessane, and Moslem Lari Najafi
Hindawi Limited
An IoT is the communication of sensing devices linked to the Internet in order to communicate data. IoT devices have extremely critical reliability with an efficient and robust network condition. Based on enormous growth in devices and their connectivity, IoT contributes to the bulk of Internet traffic. Prediction of network traffic is very important function of any network. Traffic prediction is important to ensure good system efficiency and ensure service quality of IoT applications, as it relies primarily on congestion management, admission control, allocation of bandwidth to the system, and the identification of anomalies. In this paper, a complete overview of IoT traffic forecasting model using classic time series and artificial neural network is presented. For prediction of IoT traffic, real network traces are used. Prediction models are evaluated using MAE, RMSE, and R -squared values. The experimental results indicate that LSTM- and FNN-based predictive models are highly sensitive and can therefore be used to provide better performance as a timing sequence forecast model than the conventional traffic prediction techniques.
Minu M. S. and Aroul Canessane R.
ENGG Journals Publications
Unmanned aerial vehicles (UAVs) normally fly at low altitudes to acquire high-resolution images covering small regions. The applicability of commercial UAVs finds useful in different domains such as asset management, construction management, real estate, property assessment, as well as disaster response. Security is a major issue exist in the design of UAV networks and can be resolved by the use of effective image encryption technique. In this view, this paper focuses on the design of multiple share creation (SC) scheme with social spider optimization (SSO) based optimal elliptic curve cryptography (ECC) technique, called SC-SSOECC for secure image transmission scheme in UAVs. The SC-SSOECC technique initially separates the color bands (R, G, and B) for every image. Then, the generation of multiple shares takes place for every image which turns to be complex for the hackers to retrieve the original image. In addition, the secrecy of the images can be increased by the use of ECC technique where the optimal key generation process in ECC takes place using SSO algorithm. The SC-SSOECC algorithm is found to be highly secure and useful for practical image encryption in real time systems. An extensive experimental analysis stated the proficient performance of the SC-SSOECC model and the results are examined interms of mean square error (MSE), peak signal to noise ratio (PSNR), and correlation coefficient (CC).
Shilpa P Khedkar and R. AroulCanessane
IEEE
In today's world, it becomes very important to improve network security as well as the quality of service (QoS). Internets of Things (IoT) with machine learning techniques are used to provide services to users with a classification of the network traffic. So it is very important to separate malicious traffic from normal traffic. After detecting malicious traffic it has to be blocked and forwarded the normal traffic to the specified nodes for serving the users requirements. Here, presents machine learning algorithms for classifying the network traffic, for controlling the congestion in the network.