Dr G Manikandan
@kingsedu.ac.in
Professor - IT
KINGS ENGINEERING COLLEGE
RESEARCH INTERESTS
Data Mining, Computer Network
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
G Suresh, G Bhuvaneswari, G Manikandan, and P Shanthakumar
Elsevier BV
G Manikandan, Bui Thanh Hung, Siva Shankar S, and Prasun Chakrabarti
Auricle Technologies, Pvt., Ltd.
Phone Laser Scanner becomes the versatile sensor module that is premised on Lamp Identification and Spanning methodology and is used in a spectrum of uses. There are several prior editorials in the literary works that concentrate on the implementations or attributes of these processes; even so, evaluations of all those inventive computational techniques reported in the literature have not even been performed in the required thickness. At ToAT that finish, we examine and summarize the latest advances in Artificial Intelligence based machine learning data processing approaches such as extracting features, fragmentation, machine vision, and categorization. In this survey, we have reviewed total 48 papers based on an enhanced AI based machine learning model for accurate classification and segmentation methods. Here, we have reviewed the sections on segmentation and classification of images based on machine learning models.
G Suresh, G Manikandan, G Bhuvaneswari, and P Shanthakumar
World Scientific Pub Co Pte Ltd
Steganography refers to hiding a secret message from various sources, such as images, videos, audio and so on. The advantage of steganography is to avoid data hacking in transmission medium during the transmission of information sources. Video steganography is superior to image steganography since the videos can hide a substantial quantity of secret messages more than the image. Hence, this research introduced the video stereography technique, Arnold Transform with SqueezeNet-based Pelican Whale Optimization Algorithm (AT[Formula: see text]SqueezeNet_PWOA), for concealing the secret image on the video. To hide the secret image on the video, the proposed method follows three steps: key frame and feature extraction, pixel prediction and embedding. The extraction of the key frame process is carried out by the Structural Similarity Index Measure (SSIM), and then the neighborhood features and convolutional neural network (CNN) features are extracted from the frame to improve the robustness of the embedding process. Moreover, the pixel prediction is completed by the SqueezeNet model, wherein the learning factors are tuned by the PWOA. In addition, the embedding process is completed by applying the Arnold transform on the predicted pixel, and the transformed regions are combined with the secret image using the embedding function. Likewise, the extraction process extracts the secret image from the embedded video by substituting the predicted pixel and Arnold transform on the embedded video. The proposed method is used to hide chunks of secret data in the form of video sequences and it improves the performance. The Arnold transform used in this work provides security by encrypting the data. The use of SqueezeNet makes the proposed model a simple design and this reduces the computational time. Thus, the AT[Formula: see text]SqeezeNet_PWOA attained better correlation coefficient (CC), peak signal-to-noise ratio (PSNR) and mean square error (MSE) of 0.908, 48.66 and 0.001 dB with the Gaussian noise.
Kathirvel Kalaiselvan, Ragavan Saravanan, Balashanmugham Adhavan, and Gnana Sundaram Manikandan
Springer Science and Business Media LLC
G. Manikandan, G Bhuvaneswari, and M Robinson Joel
IEEE
In order for plants to respond to specific degrees of moisture stress that affect both vegetative development and crop production, circumstances called “drought” must exist. It happens when the amount of moisture that can be held in the soil to suit a specific crop's needs is insufficient. India's drought has two main causes: climate change and a lack of surface water supplies. In some cases, it may be able to pinpoint the direct cause of a drought in a specific area, but this is not always the case. Consequently, it is imperative to establish an effective method for communicating the Standardized Precipitation Index SPI data revealing drought indices to farmers and strengthen drought and climate resilience in order to improve all these services in favour of improving agricultural productivity and decreasing food insecurity in India. Understanding past drought experiences with precise indicators is essential to developing future plans and policies in India's agriculture industry. Since this study would aid in India's agricultural development, it is obvious that a standardised drought index must be used to comprehend how frequently droughts are occurring across the country. The major goal of this study is to establish a suitable baseline for drought index forecasting using Standardized Precipitation Index SPI data. As a result, the project's ultimate result would be a knowledge base from which appropriate forecasting tools and distribution networks for farmers might be updated or established. Also, experiment with the logistic regression algorithm to get the best prediction.
Robinson Joel M, Manikandan G, Bhuvaneswari G, and Shanthakumar P
Informa UK Limited
This research introduces an efficacious model for incremental data clustering using Entropy weighted-Gradient Namib Beetle Mayfly Algorithm (NBMA). Here, feature selection is done based upon support vector machine recursive feature elimination (SVM-RFE), where the weight parameter is optimally fine-tuned using NBMA. After that, clustering is carried out utilizing entropy weighted power k-means clustering algorithm and weight is updated employing designed Gradient NBMA. Finally, incremental data clustering takes place in which centroid matching is carried out based on RV coefficient, whereas centroid is updated based on deep maxout network (DMN). Also, the result shows the better performance of the proposed method..
M. Robinson Joel, G. Manikandan, and G Bhuvaneswari
IEEE
The term "Internet of things (IoT) security" refers to the software industry concerned with protecting the IoT and connected devices. Internet of Things (IoT) is a network of devices connected with computers, sensors, actuators, or users. In IoT, each device has a distinct identity and is required to automatically transmit data over the network. Allowing computers to connect to the Internet exposes them to a number of major vulnerabilities if they are not properly secured. IoT security concerns must be monitored and analyzed to ensure the proper working of IoT models. Protecting personal safety while ensuring accessibility is the main objective of IoT security. This article has surveyed some of the methods and techniques used to secure data. Accuracy, precision, recall, f1 score, and area under the Receiver Operating Characteristic Curve are the assessment metrics utilized to compare the performance of the existing techniques. Further the utilization of machine learning algorithms like Decision Tree, Random Forest, and ANN tests have resulted in an accuracy of 99.4%. Despite the results, Random Forest (RF) performs significantly better. This study will help to gain more knowledge on the smart home automation and its security challenges.
G. Manikandan, D. Karunkuzhali, D. Geetha, and V. Kavitha
AIP Publishing
Dr.Manikandan G. and Dr.Bhuvaneswari G.
ENGG Journals Publications
AI to help researchers in analyzing larger data sets and providing faster and more accurate diagnoses of prostate cancer lesions. This research work finds AdaBoost M1 model gives an optimal results. This research work finds Ada Boost M1 of ensemble model gives an optimal results. The highest accuracy value is 89% of accuracy which is produced by Filtered Classifier. The least accuracy value is 83% of accuracy which is produced by Iterative Classifier Optimizer algorithm. The highest positive predictive value is 0.90 of positive predictive value which is produced by Filtered Classifier. The least positive predictive value is 0.83 of positive predictive value which is produced by Iterative Classifier Optimizer algorithm. The highest true positive rate value is 0.89 of true positive rate which is produced by Filtered Classifier. The least true positive rate is 0.83 of true positive rate which is produced by Iterative Classifier Optimizer algorithm. The highest F1-Score value is 0.89 of F1-Score value which is produced by Filtered Classifier. The least F1-Score value is 0.83 of F1-Score value which is produced by Iterative Classifier Optimizer algorithm. . The highest phi coefficient value is 0.77 of phi coefficient value which is produced by Filtered Classifier. The least phi coefficient is 0.65 of phi coefficient value which is produced by Iterative Classifier Optimizer algorithm. The highest AUC value is 0.91 of ACU-ROC value which is produced by Iterative Classifier Optimizer algorithm. The least AUC is 0.65 of ACU-ROC value which is produced by Attribute Selected Classifier and Filtered Classifier. The highest AUC-PR value is 0.89 of ACU-ROC value which is produced by Iterative Classifier Optimizer algorithm, Bagging and Classification via Regression models. The least AUC-PR is 0.80 of AUC-PR value which is produced by Attribute Selected Classifier and Filtered Classifier. This work concludes that the Ada Boost M1 Classifier gives best outcomes compare with other models.
D Karunkuzhali, D Geetha, G Manikandan, J. Manikandan, and V Kavitha
IEEE
In this study, wireless technology is used to provide a bridge security checking framework based on IoT. The robotized continuous scaffold wellness checking framework was developed with the assistance of breakthroughs in sensor technology. This method will help CEOs plan for and recover from disasters. The Wireless Technology is employed in the development of an IOT-based bridge security checking framework. Remote sensor hubs can collect several forms of data, such as vibration, water level, and bridge weight. These particulars would also be relevant for verification and observation. The primary purpose of this research is to develop a system that can detect and avoid flyover and extension mistakes, as well as underlying disasters. This study provides an overview of the various techniques used to screen the states of the scaffolds and proposes a framework for assessing constant designs as well as a water level sensor for monitoring the water level in the stream in order to keep traffic away from flood situations using AI calculations. If a crisis occurs, the Bridge’s doors will close as a result. The collected data is delivered to the server and data set, allowing managers to monitor the extension situation using portable telecom devices.
V Kavitha, D Geetha, D Karunkuzhali, and G Manikandan
IOP Publishing
Abstract The time capsule that would be opened in the future without third-party intervention was always a difficult issue. Although many researchers work on various systems, there are potential limitations, such as unreliable decryption period not entirely decentralised, which are difficult to estimate the needed data resources. In this post, we introduced a protocol and a safe cryptographic way to open a timely message in an advanced, decentralised environment to match in with several computing power conditions. The methodology also allows participants to gain extensive benefits of adding their computing resources, making our system more suited for applications in real life.
D Geetha, V Kavitha, G Manikandan, and D Karunkuzhali
IOP Publishing
Abstract The analytical data of project management was established. In a stereolithography method, the APC system was already implemented in essential dimensions and overlays. Productivity and system efficiency have been enhanced. The new APC, however, is created on the inspection information where the method anomalies are blended with the fluctuation of the system and which have to evaluate very small quantities, and it has the impact cap. The inspection data for the CD, overlay and log information of the acquaintance tool in ainteractive data base have been compiled and processed. We have also investigated how the earlier in this thread problem can be paid and resolved. First of all, in the enormous tool log data we have extracted ties between inspection informationbesides several parameters, particularly factor loadings. We then discussed problems with big relationships and have, thus, gathered valuable knowledge which did not come out of the traditional system. In order to show the stabilising machine fluctuation effect, we developed, along with APC, a second-generationinformation mining system.
G. Manikandan, G. Bhuvaneswari, Suhasini, K.G. Saravanan, M. Parameswari, and D.Sterlin Rani
IEEE
Consistent versatility the board is a capacity to offer the different types of assistance during the correspondence in remote heterogeneous organizations. Because of the irregular versatility of the portable terminals, the availability between various cell phones gets lost. To give the lossless network between the cell phones, the handover from the purpose of current connection to another point is fundamental. To improve the Seamless portability the board and traffic signal, an effective model called Generalized Light Gradient Boost Decision Tree-based Traffic-Aware Seamless Mobility (GLGBDT-TASM) model is presented in the heterogeneous organization. At the point when a portable hub in the organization moves out of its correspondence range, the sign strength of the hubs is determined. In view of the sign strength assessment, the Generalized Light Gradient Boost Decision Tree classifier orders the versatile hubs into the feeble and solid sign strength with the limit esteem. The boosting calculation at first develops' frail students for example double choice tree to distinguish the frail sign strength of the portable hub. At that point the group classifier joins the consequences of frail students and limits the speculation mistake. This assists with playing out the handover just with the powerless sign strength of the hub coming about in limits the repetitive handover. Furthermore, the powerless sign strength of the portable hub from the current connection point handover towards the closest accessible connection highlight improve the consistent information conveyance. Followed by, transmission capacity accessibility is estimated for diminishing the bundle misfortune because of the organization traffic coming about in improves the consistent information conveyance between the hubs. The reenactment is completed to assess the exhibition of the GLGBDT-TASM model with two related methodologies. The outcomes show that the GLGBDT-TASM model viably improved traffic-mindful consistent versatility in a heterogeneous organization with least deferral and bundle misfortune just as a higher information conveyance rate when contrasted with best in class techniques.
S. Suhasini, J. M. SheelaLavanya, M. Parameswari, G. Manikandan, and S. Gracia Nissi
IEEE
Reconfigurable engineering can dynamically assign the assets during runtime. It tends to be adequately utilized in computationally escalated applications like media processing. In media processing, video compression is one of the most computationally intensive applications. ME is the basic undertaking in video pressure as it devours enormous measure of computational time for finding the best block match by calculating Sum of Absolute Difference (S AD) of different blocks in successive video frames. To overcome this problem, its inherent parallel execution nature is analysed and mapped into customized parallel reconfigurable engineering to adequately deal with the force and asset usage by unique reconfiguration. Application of reconfigurations in the hardware for block matching and comparator modules based on the level of motion in the input video can produce substantial optimization in terms of power and resource utilization.
G. Bhuvaneswari and G. Manikandan
Springer Science and Business Media LLC
G. Bhuvaneswari and G. Manikandan
Springer Science and Business Media LLC
Manikandan
Science Publications
Mining co-location patterns from spatial databases may disclose the types of spatial features which ar e likely located as neighbors’ in space. Accordingly, we present an algorithm previously for mining spat ially co-located moving objects using spatial data mining techniques and Prim’s Algorithm. In the previous technique, the scanning of database to mine the spa tial co-location patterns took much computational c ost. In order to reduce the computation time, in this st udy, we make use of R-tree that is spatial data str ucture to mine the spatial co-location patterns. The importan t step presented in the approach is that the transf ormation of spatial data into the compact format that is wel l-suitable to mine the patterns. Here, we have adap ted the R-tree structure that converts the spatial data wit h the feature into the transactional data format. T hen, the prominent pattern mining algorithm, FP growth is us ed to mine the spatial co-location patterns from th e converted format of data. Finally, the performance of the proposed technique is compared with the prev ious technique in terms of time and memory usage. From the results, we can ensure that the proposed techniq ue outperformed of about more than 50% of previous algorithm in time and memory usage.