Browsing by Author "Sambasivam, G."

Now showing 1 - 8 of 8
  • Thumbnail Image
    Item
    ADSMS: Anomaly Detection Scheme for Mitigating Sink Hole Attack in Wireless Sensor Network
    (IEEE, 2017) Yasin, N. Mohammaed; Balaji, N.; Sambasivam, G.; Basha, M. S. Saleem; Sujatha, P.
    In past years, mobile ad hoc networks (MANETs) widespread use in many applications, including for some mission-critical applications, and has become one of the major concerns such as security MANETs. MANETs due to some unique characteristics, prevention methods are not alone enough to protect them need; Therefore, the detection is possible for an attacker to breach system security, such as the need to add another before. In general, traditional wireless networks, intrusion detection techniques are not well suited for MANETs. In this case, to protect it from attacks MANETs is important to develop more efficient methods of intrusion detection. With improvements in technology and cutting hardware costs, we MANETs expanding into industrial applications are also witnessing a current trend. To cope with such a trend and we believe strongly that it was important for its potential security issues. In this paper, we propose new intrusion detection and specially designed MANETs Improved Acceptance acknowledgment (EAACK) to activate the digital signature system. Compared to contemporary approaches, while not greatly affect network shows EAACK certain conditions demonstrates the high detection rates of malicious behaviour
  • Thumbnail Image
    Item
    Appraisal and Analysis on Diversified Web Service Selection Techniques based on QoS Factors
    (International Journal of Engineering and Technology (IJET), 2013) Balaji, N.; Sambasivam, G.; Murugaiyan, S.R.; Saleem Basha, M.S.; Vengattaraman, T.; Dhavachelvan, P.
    Numerous monumental changes have been made in the existing web service selection to provide quality of services. The quality of service is a major bottle neck in the recent development. Hitherto various QoS based Web Service Selection Techniques exist. But these techniques lacks in functional and non-functional attributes. This paper consists with the following tasks; segregate various QoS based Web Service selection techniques with their respective merits and demerits, an extensive comparative study on different QoS aware service selection techniques with respect to the user requirements and multiple QoS properties and preferences. This paper also evaluates the performance of discussed techniques based on the strength of various QoS aware Web service selection functionalities using a set of evaluation metrics.
  • Thumbnail Image
    Item
    Appraisal and analysis on various web service composition approaches based on QoS factors
    (Journal of King Saud University-Computer and Information Sciences, 2014) Rajeswari, M.; Sambasivam, G.; Balaji, N.; Saleem Basha, M.S.; Vengattaraman, T.; Dhavachelvan, P.
    Web services are the internet enabled applications for performing business needs, considered as the platform-independent and loosely coupled. Web service compositions build new services by organizing a set of existing services by providing reusability and interoperability. The research problem in web service composition is to obtain best effective services with the composition of services based on maximum quality of services (QoS) and satisfy the user’s requirements. This study reveals various challenges in the QoS parameter for Web service composition because it is difficult to recognize. We have illustrated the related technology by analyzing QoS parameters based on existing algorithms with composition patterns and compared the results.
  • Thumbnail Image
    Item
    COVID-19 identification in chest X-ray images using intelligent multi-level classification scenario
    (Computers and Electrical Engineering, 2022) Babukarthik, R.G.; Chandramohan, Dhasarathan; Tripathi, Diwakar; Kumar, Manish; Sambasivam, G.
    COVID-19 is an evolving respiratory transmittable disease, and it holds all daily activity worldwide as a global pandemic. It appeared in the city of Wuhan (China) in November 2019 and slowly started spreading to the rest of the world. The number of cases keeps increasing drastically, leading to a shortage of medical resources and testing kids worldwide. As the physicians facing this problem, several scientists and specialists in Artificial Intelligent (AI) are rendering their support to healthcare professionals in the early detection of COVID-19 using chest X-ray image samples to determine the level of severity at a low cost. This paper proposed Genetic Deep Learning Convolutional Neural Network (GDCNN) architecture that includes Huddle Particle Swarm Optimization as an alternative to Gradient descent. Huddle PSO performs better when clubbed with GDCNN architecture. Based on publicly available datasets, trained chest X-ray images are used to predict and identify various pneumonia diseases. The proposed model performed better with an accuracy of 97.23%, a sensitivity of 98.62%, specificity of 97.0%, and precision of 93.0%. The proposed model act as a tool for earlier detection of COVID-19. In the future, we plan to apply the proposed model for the larger dataset and to predict various lung diseases.
  • Thumbnail Image
    Item
    A Normalized Approach for Service Discovery
    (Procedia Computer Science, 2015) Sambasivam, G.; Ravisankar, V.; Vengattaraman, T.; Baskaran, R.; Dhavachelvan, P.
    In today’s world web services are the known perception to all the users who uses the internet. The Web Service process involves service discovery, selection and ranking. Discovery is the process of matchmaking of user query with advertisements in the repository. Our motivation is to develop a model for web service discovery with the combined approach of service selection and ranking. In this paper, we have proposed a technique for web service discovery process, combining the keyword search and semantic search and ranking the services. The implementation results show that the proposed model performs better for the web service discovery process.
  • Thumbnail Image
    Item
    A predictive machine learning application in agriculture: Cassava disease detection and classification with imbalanced dataset using convolutional neural networks
    (Egyptian informatics journal, 2021) Sambasivam, G.; Opiyo, Geoffrey Duncan
    This work is inspired by Kaggle competition which was part of the Fine-Grained Visual Categorization workshop at CVPR 2019 (Conference on Computer Vision and Pattern Recognition) we participated in. It aimed at detecting cassava diseases using 5 fine-grained cassava leaf disease categories with 10,000, labeled images collected during a regular survey in Uganda. Traditionally, this detection is done mostly through physical inspection and supervision of cassava plants in the garden by farmers or agricultural extension workers from NAADS (National Agricultural Advisory Services) and then reported to NARO (National Agricultural Advisory Services) for further analysis. However, this can be tiresome, capital intensive, and lacks the ability to detect cassava infection timely to help farmers apply preventive techniques to the non-infected cassava plants in order to improve on yields which subsequently increases African food basket leading to food security which fights famine. Using the dataset provided to train CNNs (Convolutional Neural Networks) to achieve high accuracy was very challenging due to two reasons: the dataset was small in size and has high-class imbalance being heavily biased towards CMD (Cassava Mosaic Disease) and CBB (Cassava Brown Streak Virus Disease) classes. Class imbalance is problematic in machine learning and exists in many domains. Note that, not all world data is balanced, in fact, most of the time you will not be extremely lucky to get a perfectly balanced real-world dataset, in recent years, a lot of research has been done for two-class problems such as fraudulent credit card and tumor detection among others. Interestingly, class imbalance in multi-class image datasets has received little attention. This paper, therefore, focused on techniques to achieve an accuracy score of over 93% with class weight, SMOTE (Synthetic Minority Over-sampling Technique) and focal loss with deep convolutional neural networks from scratch. The goal was to counter high-class imbalance so that the model can accurately predict underrepresented classes.
  • Thumbnail Image
    Item
    A Predictive Performance Analysis of Vitamin D Deficiency Severity Using Machine Learning Methods
    (IEEE Access, 2020) Sambasivam, G.; Amudhavel, J.; Sathya, G.
    Vitamin D Deficiency (VDD) is one of the most significant global health problem and there is a strong demand for the prediction of its severity using non-invasive methods. The primary data containing serum Vitamin D levels were collected from a total of 3044 college students between 18-21 years of age. The independent parameters like age, sex, weight, height, body mass index (BMI), waist circumference, body fat, bone mass, exercise, sunlight exposure, and milk consumption were used for prediction of VDD. The study aims to compare and evaluate different machine learning models in the prediction of severity in VDD. The objectives of our approach are to apply various powerful machine learning algorithms in prediction and evaluate the results with different performance measures like Precision, Recall, F1-measure, Accuracy, and Area under the curve of receiver operating characteristic (ROC). The McNemar’s test was conducted to validate the empirical results which is a statistical test. The final objective is to identify the best machine learning classifier in the prediction of the severity of VDD. The most popular and powerful machine learning classifiers like K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), AdaBoost (AB), Bagging Classifier (BC), ExtraTrees (ET), Stochastic Gradient Descent (SGD), Gradient Boosting (GB), Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP) were implemented to predict the severity of VDD. The final experimentation results showed that the Random Forest Classifier achieves better accuracy of 96 % and outperforms well on training and testing Vitamin D dataset. The McNemar’s statistical test results support that the RF classifier outperforms than the other classifiers.
  • Thumbnail Image
    Item
    An QoS based multifaceted matchmaking framework for web services discovery
    (Future Computing and Informatics Journal, 2018) Sambasivam, G.; Amudhavel, J.; Vengattaraman, T.; Dhavachelvan, P.
    With the increasing demand, the web service has been the prominent technology for providing good solutions to the interoperability of different kind of systems. Web service supports mainly interoperability properties as it is the major usage of this promising technology. Although several technologies had been evolved before web service technology and this has more advantage of other technologies. This paper has concentrated mainly on the Multifaceted Matchmaking framework for Web Services Discovery using Quality of Services parameters. Traditionally web services have been discovered only with the functional properties like input, output, precondition and effect. Nowadays there is an increase in number of service providers leads to increase in the web services with same functionality. So user need to discover the best services so Quality of Service factors has been evolved. The traditional discovery supports only few quality parameters and so the discovery is easy in retrieval of services. As the parameter increases the matchmaking will be complex during service discovery. So in this proposed work, we have identified 21 QoS parameters which are suitable for service discovery. The information retrieval techniques are used to evaluate the results and results show that the proposed framework is better.