Papers by Dr. Senthil Athithan
2023 World Conference on Communication & Computing (WCONF)
2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)
Now a day’s our smart gadgets are not only devices but true friends of human-being. Social-Networ... more Now a day’s our smart gadgets are not only devices but true friends of human-being. Social-Networking, one from them provides us a virtual home far from home, where everyone feels connected even from thousand miles is one of the brighter sides of new era. The dark side of this coin is equally the worst, as this also increases the vulnerability of young people to threatening situations online.This Paper is divided into three main tasks, as a very first task, we explored various forms of Cyber-Crime, reviewed Cyber-Bullying, its forms, methods, effects, and the available recent research to detect and prevent it. Secondly, for the experimental purpose, we have collected data of Twitter’s 35000+ tweets, prepared/wrangled that data to fed it to various smart machine learning algorithms, then applied five important ML algorithms to those tweets for classification and prediction into two main classes ‘offensive’ or ‘non-offensive’. Finally, a comparison has been done among those ML algorithms based on several performance metrics.
Journal of Computational Environmental Sciences, Feb 12, 2014
Epidemiology is the study of spread of diseases among the group of population. If not controlled ... more Epidemiology is the study of spread of diseases among the group of population. If not controlled properly, the epidemic would cause an enormous number of problems and lead to pandemic situation. Here in this paper we consider the situation of populated areas where people live in patches. A dynamic cellular automata model for population in patches is being proposed in this paper. This work not only explores the computing power of cellular automata in modeling the epidemic spread but also provides the pathway in reduction of computing time when using the dynamic cellular automata model for the patchy population when compared to the static cellular automata which is used for a nonpatchy homogeneous population. The variation of the model with movement of population among the patches is also explored which provides an efficient way for evacuation planning and vaccination of infected areas.
Indian journal of science and technology, Feb 1, 2015
This paper is focused on a cellular automata based computational model for the spread of disease ... more This paper is focused on a cellular automata based computational model for the spread of disease named Leptospirosis using voting rules. Leptospirosis is most commonly found in bovine rats and the humans get infected when they come into contact with them. The disease spread is modelled in terms of Susceptible-Infective-Recovered-Susceptible (SIRS) model through one of the efficient computational modeling tool-Cellular Automata (CA); and requires strategic change in the rule set of the traditional CA. An idea of voting based rule on the neighborhood environment is studied for modeling the Leptospirosis and compared with real data of such infection in Thailand during the year 2000 and 2001. The simulation of the model is done with real data of Leptospirosis infection in Thailand during 2000 and 2001 and the results yielded from this model were closely in match with the real time data.
Journal of Computational Environmental Sciences, Nov 12, 2014
The world without a disease is a dream of any human being. The disease spread if not controlled c... more The world without a disease is a dream of any human being. The disease spread if not controlled could cause an epidemic situation to spread and lead to pandemic. To control an epidemic we need to understand the nature of its spread and the epidemic spread model helps us in achieving this. Here we propose an epidemic spread model which considers not only the current infective population around the population but also the infective population which remain from the previous generations for computing the next generation infected individuals. A pushdown cellular automata model which is an enhanced version of cellular automata by adding a stack component is being used to model the epidemic spread and the model is validated by the real time data of H1N1 epidemic in Abu Dhabi.
2023 International Conference on Computer Communication and Informatics (ICCCI)
Sensors
Data centers are producing a lot of data as cloud-based smart grids replace traditional grids. Th... more Data centers are producing a lot of data as cloud-based smart grids replace traditional grids. The number of automated systems has increased rapidly, which in turn necessitates the rise of cloud computing. Cloud computing helps enterprises offer services cheaply and efficiently. Despite the challenges of managing resources, longer response plus processing time, and higher energy consumption, more people are using cloud computing. Fog computing extends cloud computing. It adds cloud services that minimize traffic, increase security, and speed up processes. Cloud and fog computing help smart grids save energy by aggregating and distributing the submitted requests. The paper discusses a load-balancing approach in Smart Grid using Rock Hyrax Optimization (RHO) to optimize response time and energy consumption. The proposed algorithm assigns tasks to virtual machines for execution and shuts off unused virtual machines, reducing the energy consumed by virtual machines. The proposed model i...
2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)
2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)
2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)
2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)
Security and Communication Networks
The smart manufacturing system can become a linked network with the help of the Internet of Thing... more The smart manufacturing system can become a linked network with the help of the Internet of Things (IoT). Devices connected to the IoT are susceptible to various attacks and assaults. An effective protection plan is needed to ensure that the billions of IoT nodes are protected from these hazards. The security mechanisms on IoT devices are ineffective due to resource limitations. As a result, the academic community has recently paid attention to the cloud-, fog-, and edge-based IoT systems. A robust cloud provider is in the cloud or fog to perform computationally demanding activities, including safety, data analysis, decision-making process, and monitoring. Hash identities and upgraded Rivest–Shamir–Adleman (RSA) have been used to secure the IoT device’s data. A four-prime integer of 512 bits makes up the proposed security algorithm. A hash signature is used to provide device authentication. An effective clustering method for sensing devices based on the node level, separation from t...
CRC Press eBooks, Nov 9, 2022
MDPI, 2022
An expert performs bone fracture diagnosis using an X-ray image manually, which is a time-consumi... more An expert performs bone fracture diagnosis using an X-ray image manually, which is a time-consuming process. The development of machine learning (ML), as well as deep learning (DL), has set a new path in medical image diagnosis. In this study, we proposed a novel multi-scale feature fusion of a convolution neural network (CNN) and an improved canny edge algorithm that segregate fracture and healthy bone image. The hybrid scale fracture network (SFNet) is a novel two-scale sequential DL model. This model is highly efficient for bone fracture diagnosis and takes less computation time compared to other state-of-the-art deep CNN models. The innovation behind this research is that it works with an improved canny edge algorithm to obtain edges in the images that localize the fracture region. After that, grey images and their corresponding canny edge images are fed to the proposed hybrid SFNet for training and evaluation. Furthermore, the performance is also compared with the state-of-the-art deep CNN models on a bone image dataset. Our results showed that SFNet with canny (SFNet + canny) achieved the highest accuracy, F1-score and recall of 99.12%, 99% and 100%, respectively, for bone fracture diagnosis. It showed that using a canny edge algorithm improves the performance of CNN.
Sensors
An expert performs bone fracture diagnosis using an X-ray image manually, which is a time-consumi... more An expert performs bone fracture diagnosis using an X-ray image manually, which is a time-consuming process. The development of machine learning (ML), as well as deep learning (DL), has set a new path in medical image diagnosis. In this study, we proposed a novel multi-scale feature fusion of a convolution neural network (CNN) and an improved canny edge algorithm that segregate fracture and healthy bone image. The hybrid scale fracture network (SFNet) is a novel two-scale sequential DL model. This model is highly efficient for bone fracture diagnosis and takes less computation time compared to other state-of-the-art deep CNN models. The innovation behind this research is that it works with an improved canny edge algorithm to obtain edges in the images that localize the fracture region. After that, grey images and their corresponding canny edge images are fed to the proposed hybrid SFNet for training and evaluation. Furthermore, the performance is also compared with the state-of-the-...
In today’s world, the detection and disposal of landmines is one of the most difficult and intrac... more In today’s world, the detection and disposal of landmines is one of the most difficult and intractable problem faced in ground conflict. The presently used techniques of detection mainly work on the content of metal in mines which takes more time in searching the landmines. The aim is to detect those mines which contain less metallic contents. So, the points which are taken into account in developing the model for searching the landmines in optimal time are checking the metal of landmine with battery content, heat generation of those portions of land where the landmines exists, determine the optimized path from source to destination along with the detection of landmines and generation of transition rule of cellular automata. Therefore, we develop a deterministic algorithm with the help of an optimization technique i.e. Particle Swarm Optimization (PSO) and Cellular Automata (CA) which will optimize the search of landmines, searching both locally and globally, in much less time as compared to any other method and also limiting the chances of PSO of getting trapped in the local optima. The main work is to simulate the algorithm to solve the problem of detection of landmines.
Epidemics is very important area of concern for most our living being family in the world. Any ep... more Epidemics is very important area of concern for most our living being family in the world. Any epidemic situation when properly not controlled could lead to a disaster when large amount of human population is involved. Here we propose a fundamental model of computation in terms of non-deterministic finite automata (NFA) for the Susceptible-Infectives-Recovered (SIR) model. Through this model we could prove there could be certain languages which are epidemic regular since it could be compared with the normal regular languages for which we can have NFA or regular grammar. If we could classify how the epidemic model could behave then we could better develop strategies that could tackle a similar epidemic situation in future. This model has been tested with the data of H1N1 obtained from CDC USA.
Indian Journal of Science and Technology, 2015
This paper is focused on a cellular automata based computational model for the spread of disease ... more This paper is focused on a cellular automata based computational model for the spread of disease named Leptospirosis using voting rules. Leptospirosis is most commonly found in bovine rats and the humans get infected when they come into contact with them. The disease spread is modelled in terms of Susceptible-Infective-Recovered-Susceptible (SIRS) model through one of the efficient computational modeling tool-Cellular Automata (CA); and requires strategic change in the rule set of the traditional CA. An idea of voting based rule on the neighborhood environment is studied for modeling the Leptospirosis and compared with real data of such infection in Thailand during the year 2000 and 2001. The simulation of the model is done with real data of Leptospirosis infection in Thailand during 2000 and 2001 and the results yielded from this model were closely in match with the real time data.
Journal of Computational Environmental Sciences, 2014
Epidemiology is the study of spread of diseases among the group of population. If not controlled ... more Epidemiology is the study of spread of diseases among the group of population. If not controlled properly, the epidemic would cause an enormous number of problems and lead to pandemic situation. Here in this paper we consider the situation of populated areas where people live in patches. A dynamic cellular automata model for population in patches is being proposed in this paper. This work not only explores the computing power of cellular automata in modeling the epidemic spread but also provides the pathway in reduction of computing time when using the dynamic cellular automata model for the patchy population when compared to the static cellular automata which is used for a nonpatchy homogeneous population. The variation of the model with movement of population among the patches is also explored which provides an efficient way for evacuation planning and vaccination of infected areas.
Uploads
Papers by Dr. Senthil Athithan