Papers by Dr Aghila Rajagopal
AI Based Secure Analytics of Clinical Data in Cloud Environment: Towards Smart Cities and Healthcare
Journal of Advances in Information Technology, Dec 31, 2022

The proposed work explores the interprocess communication across communicating parallel tasks in ... more The proposed work explores the interprocess communication across communicating parallel tasks in a mobile cluster. The process which is linked with specific mobile or static nodes will not be resilient to the changing conditions of the mobile cluster. The proposed Mobile Distributed Pipes (MDP) model enables the location independent intertask communication among the processes executing in static and mobile nodes. This novel approach enables the migration of communicating parallel tasks during runtime, which occurs according to the context and location requirements. A transparent programming model for a parallel solution to Iterative Mobile Grid Computations (IMGC) using MDP is also proposed. The proposed model is resilient to the heterogeneity of nodes such as static or mobile and the changing conditions in the mobile cluster because of mobility. The design of runtime and functional library support for the proposed model is also presented.

A fuzzy content recommendation system using similarity analysis, content ranking and clustering
Journal of Intelligent and Fuzzy Systems, Dec 16, 2021
Recently, the e-learners are drastically increased from the last two decades. Everything is learn... more Recently, the e-learners are drastically increased from the last two decades. Everything is learnt through internet without help of the tutor as well. For this purpose, the e-learners are required more e-learning applications that are able to supply optimal and satisfied data based on their capability. No content recommendation system is available for recommending suitable contents to the learners. For this purpose, this paper proposes a new semantic and fuzzy aware content recommendation system for retrieving the suitable content for the users. In this content recommendation system, we propose two content pre-processing algorithms namely Target Keyword based Data Pre-processing Algorithm (TKDPA) and Intelligent Anova-T Residual Algorithm (IAATRA) for selecting the more relevant features from the document. Moreover, a new Fuzzy rule based Similarity Matching algorithm (FRSMA) is proposed and used in this system for finding the similarity between the two terms and also rank them by using the newly proposed Similarity and Temporal aware Weighted Document Ranking Algorithm (STWDRA). In addition, a content clustering process is also incorporated for gathering relevant content. Finally, a new Fuzzy, Target Keyword and Similarity Score based Content Recommendation Algorithm (FTKSCRA) is also proposed for recommending the more relevant content to the learners accurately. The experiments have been conducted for evaluating the proposed content recommendation system and proved as better than the existing recommendation systems in terms of precision, recall, f-measure and prediction accuracy.

Computer Systems Science and Engineering
Nowadays, the COVID-19 virus disease is spreading rampantly. There are some testing tools and kit... more Nowadays, the COVID-19 virus disease is spreading rampantly. There are some testing tools and kits available for diagnosing the virus, but it is in a limited count. To diagnose the presence of disease from radiological images, automated COVID-19 diagnosis techniques are needed. The enhancement of AI (Artificial Intelligence) has been focused in previous research, which uses Xray images for detecting COVID-19. The most common symptoms of COVID-19 are fever, dry cough and sore throat. These symptoms may lead to an increase in the rigorous type of pneumonia with a severe barrier. Since medical imaging is not suggested recently in Canada for critical COVID-19 diagnosis, computeraided systems are implemented for the early identification of COVID-19, which aids in noticing the disease progression and thus decreases the death rate. Here, a deep learning-based automated method for the extraction of features and classification is enhanced for the detection of COVID-19 from the images of computer tomography (CT). The suggested method functions on the basis of three main processes: data preprocessing, the extraction of features and classification. This approach integrates the union of deep features with the help of Inception 14 and VGG-16 models. At last, a classifier of Multi-scale Improved ResNet (MSI-ResNet) is developed to detect and classify the CT images into unique labels of class. With the support of available open-source COVID-CT datasets that consists of 760 CT pictures, the investigational validation of the suggested method is estimated. The experimental results reveal that the proposed approach offers greater performance with high specificity, accuracy and sensitivity.
A novel hybrid machine learning framework for the prediction of diabetes with context-customized regularization and prediction procedures
Mathematics and Computers in Simulation, 2022

The proposed work explores the interprocess communication across communicating parallel tasks in ... more The proposed work explores the interprocess communication across communicating parallel tasks in a mobile cluster. The process which is linked with specific mobile or static nodes will not be resilient to the changing conditions of the mobile cluster. The proposed Mobile Distributed Pipes (MDP) model enables the location independent intertask communication among the processes executing in static and mobile nodes. This novel approach enables the migration of communicating parallel tasks during runtime, which occurs according to the context and location requirements. A transparent programming model for a parallel solution to Iterative Mobile Grid Computations (IMGC) using MDP is also proposed. The proposed model is resilient to the heterogeneity of nodes such as static or mobile and the changing conditions in the mobile cluster because of mobility. The design of runtime and functional library support for the proposed model is also presented.

IEEE Access, 2020
In recent days, unmanned aerial vehicles (UAVs) becomes more familiar because of its versatility,... more In recent days, unmanned aerial vehicles (UAVs) becomes more familiar because of its versatility, automation abilities, and low cost. Dynamic scene classification gained significant interest among the UAV-based surveillance systems, e.g., high-voltage power line and forest fire monitoring, which facilitate the object detection, tracking process and drastically enhances the outcome of visual surveillance. This paper proposes a new optimal deep learning-based scene classification model captured by UAVs. The proposed model involves a residual network-based features extraction (RNBFE) which extracts features from the diverse convolution layers of a deep residual network. In addition, the several parameters in RNBFE lead to many configuration errors due to manual parameter tuning. So, self-adaptive global best harmony search (SGHS) algorithm is employed for tuning the parameters of the RNBFE. The resultant feature vectors undergo classification by the use of latent variable support vector machine (LVSVM) model. The presented optimal RNBFE (ORNBFE) model has been tested using two open access datasets namely UC Merced (UCM) Land Use Dataset and WHU-RS Dataset. The presented technique attains maximum scene classification accuracy over the other recently proposed methods.

A fuzzy content recommendation system using similarity analysis, content ranking and clustering
Journal of Intelligent & Fuzzy Systems, 2021
Recently, the e-learners are drastically increased from the last two decades. Everything is learn... more Recently, the e-learners are drastically increased from the last two decades. Everything is learnt through internet without help of the tutor as well. For this purpose, the e-learners are required more e-learning applications that are able to supply optimal and satisfied data based on their capability. No content recommendation system is available for recommending suitable contents to the learners. For this purpose, this paper proposes a new semantic and fuzzy aware content recommendation system for retrieving the suitable content for the users. In this content recommendation system, we propose two content pre-processing algorithms namely Target Keyword based Data Pre-processing Algorithm (TKDPA) and Intelligent Anova-T Residual Algorithm (IAATRA) for selecting the more relevant features from the document. Moreover, a new Fuzzy rule based Similarity Matching algorithm (FRSMA) is proposed and used in this system for finding the similarity between the two terms and also rank them by u...

International Journal of Satellite Communications and Networking, 2020
SummaryDue to the significant utilization of terrestrial communication, Low Earth Orbit (LEO) sat... more SummaryDue to the significant utilization of terrestrial communication, Low Earth Orbit (LEO) satellite network is a critical part of satellite communication networks owing to its several benefits. But the efficient and trustworthy routing for LEO satellite networks (LSNs) is a difficult process because of dynamic topology, adequate link changes, and imbalanced communication load. This study devises a new hybridization of extreme learning machine (ELM) with multitask beetle antennae search (MBAS) algorithm‐based distributed routing called the MBAS‐ELM model. The proposed model determines the routes based on traffic forecasting with respect to the level of traffic circulation on the earth. The proposed method is employed for traffic forecasting at the satellite nodes (SNs). To identify the optimal routes, mobile agents (MAs) are applied to concurrently and autonomously determine for LSNs and make a decision on routing data. The experimental outcome has showcased the effective perform...

IEEE Access, 2020
This work was supported by Institute for Information & communications Technology Promotion (IITP)... more This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea Government (MSIP) (No. 2020-0-00107, Development of the technology to automate the recommendations for big data analytic models that define data characteristics and problems). ABSTRACT Recently, the increase in inexpensive and compact unmanned aerial vehicles (UAVs) and lightweight imaging sensors has led to an interest in using them in various remote sensing applications. The processes of collecting, calibrating, registering, and processing data from miniature UAVs and interpreting the data semantically are time-consuming. In UAV aerial imagery, learning effective image representations is central to the scene classification process. Earlier approaches to the scene classification process depended on feature coding methods with low-level hand-engineered features or unsupervised feature learning. These methods could produce mid-level image features with restricted representational abilities, which generally yielded mediocre results. The development of convolutional neural networks (CNNs) has made image classification more efficient. Due to the limited resources in UAVs, it is hard to fine-tune the hyperparameters and the trade-offs between classifier results and computation complexity. This paper introduces a new multi-objective optimization model for evolving state-of-the-art deep CNNs for scene classification, which generates the non-dominant solutions in an automated way at the Pareto front. We use a set of two benchmark datasets to test the performance of the scene classification model and make a detailed comparative study. The proposed method attains a very low computational time of 80 sec and maximum accuracy of 97.88% compared to all other methods. The proposed method is found to be appropriate for the effective scene classification of images captured by UAVs. INDEX TERMS Unmanned aerial vehicle, particle swarm optimization, deep learning, convolutional neural networks, machine learning, internet of everything, aerial images, smart environment.

International Journal of Machine Learning and Networked Collaborative Engineering, 2020
refabricate a proficient search structure is very important due to the current scale of the web. ... more refabricate a proficient search structure is very important due to the current scale of the web. Search engines mine information from the web and a program called a web crawler, which efficiently surfs the web. A distributed crawler belongs to a variant of a web crawler, uses a dispersed computation method. In this paper, we design and implement the concept of Efficient Distributed Web Crawler using enhanced bandwidth and hefty algorithms. Mostly Web Crawler doesn't have any distributed cluster performance system and any implemented algorithm. In this paper, a novel Hefty Algorithm and enhanced bandwidth algorithm are combined for a better-distributed crawling system. The hefty algorithm was implemented to provide efficient and robust surfing results while applying on the drug web search. We also implemented the Enhanced Bandwidth algorithm to improve the efficiency of the proposed crawler.

International Journal of Engineering and Advanced Technology, 2020
Surveillance video is used for security purpose in our daily life in various places. It is used t... more Surveillance video is used for security purpose in our daily life in various places. It is used to observe the unusual activity that is taking place around us. Today in most of the shop owners have CCTV cameras to record, the uncertain activities and even it is used in houses in remote places. A system must be smart enough to detect. This paper uses SIFT and SURF algorithm for detection. Image registration is a development in which more than two images from various imaging equipment are reserved at various angles and at various times from the identical prospect and geometrically aligned for further exploration. Data may be from different sensors, CCTV taken at different times, depths, or perspective. Feature-DetectorDescriptor plays a vital role in feature matching application for selection of feature; this paper presents a comparative analysis of SIFT, SURF, algorithms. Experiments have been conducted on a wide range of images taken from datasets. A quantitative comparison is prese...

Journal of Emerging Technologies in Web Intelligence, 2014
Parallel computing methods decrease the processing time in mobile distributed systems compared to... more Parallel computing methods decrease the processing time in mobile distributed systems compared to the conventional sequential computing techniques. But as they are developed from smaller mobile clusters to extensive mobile grids, they are prone to issues like high latency/jitter, processing speed, communication overhead, and low data transfer rate. So, an efficient and optimized parallel computing paradigm known as Distributed Shared Proxy Object Model (DSPOM) is developed based on Surrogate Object Model (SOM) integrated with Distributed Shared Object (DSO) for mobile grid. SOM is chosen to enhance the resource sharing of mobile grid computing, while DSO is chosen to reduce the computational complexity. The unused computing determinant is utilized by SOM to save the processing time. The transparency of the DSO model in terms of distribution and heterogeneity reduces the computational complexity. DSO also enhances the load adaptability and fault-tolerance to parallel programs on the mobile grid. The DSPO model performs better in terms of query time, query latency, packet loss, load adaptability, and fault-tolerance.
International Journal of Electronic Commerce Studies, 2014
This paper proposes a novel model for Surrogate Object based paradigm in mobile grid environment ... more This paper proposes a novel model for Surrogate Object based paradigm in mobile grid environment for achieving a Fault Tolerance. Basically Mobile Grid Computing Model focuses on Service Composition and Resource Sharing Process. In order to increase the performance of the system, Fault Recovery plays a vital role. In our Proposed System for Recovery point, Surrogate Object Based Checkpoint Recovery Model is introduced. This Checkpoint Recovery model depends on the Surrogate Object and the Fault Recovery is handled by means of Replication Approach. The mobility problem is overcome based on Distributed Surrogate Object model. In our comparison, our proposed fault recovery model proves its efficiency and reliability in Grid Environment.

Applied Sciences, 2021
Data mining is an information exploration methodology with fascinating and understandable pattern... more Data mining is an information exploration methodology with fascinating and understandable patterns and informative models for vast volumes of data. Agricultural productivity growth is the key to poverty alleviation. However, due to a lack of proper technical guidance in the agriculture field, crop yield differs over different years. Mining techniques were implemented in different applications, such as soil classification, rainfall prediction, and weather forecast, separately. It is proposed that an Artificial Intelligence system can combine the mined extracts of various factors such as soil, rainfall, and crop production to predict the market value to be developed. Smart analysis and a comprehensive prediction model in agriculture helps the farmer to yield the right crops at the right time. The main benefits of the proposed system are as follows: Yielding the right crop at the right time, balancing crop production, economy growth, and planning to reduce crop scarcity. Initially, the...

Background: A computational grid is to flexibly handle computation management, data movement, sto... more Background: A computational grid is to flexibly handle computation management, data movement, storage management and other infrastructure that manifest to access many systems without restricting themselves to specific hardware and requirements. Fault tolerance and scheduling are expected to be vital challenges in Grid computing. It is because the dependability of individual Grid resources might not be guaranteed; also as resources are used outside of organizational boundaries, different scheduling instances for arbitrary Grid resources are supported. In existing system, rollback recovery techniques are used. But it was not resilient to all possible failure configurations. Our paper aims to provide an analysis of fault tolerant mechanism. The Primary ingredient of Grid Checkpoint Recovery service is recoverability of jobs among heterogeneous Grid resources. In essence, resources on which jobs are check pointed need not be of the same type as those on which the jobs are recovered, as long as the application code operating on the check pointing resource can be built for and run on the recovery platform. However there can be some circumstances even if the checkpoint failures there arises a question on recovery. Our paper provides a strategic solution for handling this erroneous situation of Checkpoint Failure. Objective: An Analysis On Checkpoint Mechanism For Grid Computing. Results: As discussed earlier, the factors that are to be considered while focusing on checkpoint algorithm are checkpoint overhead, control information, domino effect, orphan message, scalability, memory consumption, contention in accessing the stable storage etc. Conclusion: In this paper, we provided a brief introduction to the research field concerned with Checkpoint. As we observed, all the Existing Checkpoint Based Recovery Mechanism depends on the checkpoints stored. If the storage goes off, the performance of the system degrades. Here we come out with a solution. Our idea is to maintain a replica for the checkpoint. Though the solution is simple, it addresses the severe problem. Further Research is needed to consolidate the conceptual foundations of this approach.

Wireless technology together with a huge computing power resulted in a paradigm called as Mobile ... more Wireless technology together with a huge computing power resulted in a paradigm called as Mobile Grid. Mobile devices play a vital role in day-today activities. The paper proposes a novel model for Mobile Grid environment on considering the mobile device constraints using an Object Based Model. Object Model is a method which acts on behalf of mobile device and caches the frequent data and it reduces the communication overhead and increases the performance of the system. An experimental result proves the reliability of the proposed model and showcases its importance against disconnection of mobile devices. Results: To project our Proposed model, we have conducted an experimental to exhibit the usefulness of Surrogate Object with and without, in a Mobile Grid. Figure 3 shows the speed up of the model by comparing it over the memory and proves that the proposed model is effective due to data caching at the surrogate object. Figure 4 shows that the completion time gets reduced when the number of nodes increases. The proposed model shows a better completion time by the introduction of Surrogate Object and distributed pipe. Figure 5 shows that errors get reduced due to connectivity issue as Surrogate object acts as a proxy for mobile devices. Conclusion: In this paper, we have proposed a new model called Surrogate Object with distributed pipe (SODP) which overcomes the mobile devices found in several other techniques. The proposed model uses the distributed pipe for data transfer and the surrogate object which acts as a proxy for mobile devices and also acts as a data cache for storing data. Thus when compared to the existing techniques, the proposed model 1) reduces the completion time 2) speed up the processes and 3) it also reduces the error due to connectivity issues. We have conducted experimental results for both with and without Surrogate Object and showcase their effectiveness over the existing methods. The proposed technique shows a better performance than the existing technique.

International Journal of Future Computer and Communication, 2013
The Mobile Grid Environment has the dynamic structure in which the position and location of grid ... more The Mobile Grid Environment has the dynamic structure in which the position and location of grid changes vigorously. It compounds the pervasive ingression methods of mobile computing and coalition of computational resources from multiple domains to attain a common task. Due to mobility, failure of nodes, disconnection and network partitioning in networks, resource allocation and scheduling is being the demanding problems. We endow with solutions to the above-mentioned problems by implementing pipes in the Mobile grid environment. It is conspicuous that pipes are the collection of segments or processes that are connected in a series which can execute its process concurrently with the other segments or processes in a successive manner. We contrive temporal clusters in our Distributed Pipes Enforcement (DPE) methodology with the determination of demand bound functions and induce master/slave conceits with that in order to augment the efficiency in task completion and abate the resource dissipation. With this, the chances to get erroneous result can be probably avoided. Our approach caters for performance optimization, flexible deployment and consistency.
Uploads
Papers by Dr Aghila Rajagopal