Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

The Cloud technology is now a key component in almost every computing system. It is most widely used in commercial fields. Cloud storage can store almost any type of data. Thus the security of the cloud component is now a major issue. With the increasing amount of cloud users with various different types of requests, the threats faced by the platform are also changing. There is no static threat in the current scenario and thus the need for dynamic security access. This paper deals with this new type of threat which deals with several different constraints and threat levels to come out with an answer to either give access or not, to the cloud perimeter. This paper deals with the very first security layer of the cloud parameter and enhances its performance using the latest artificial intelligence technologies, neural network algorithms and helps in restricting data breach or unauthorized access in a very early stage, preventing an organization or the cloud vendor from huge data losses. The access granted is all labeled and can be further used for taking intelligent decisions to make the parameter more secured. This will have its application across a wide domain of systems and will help in safely storing data anywhere across any cloud platform. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

World University root node

Department of Information Security

School of Computer Science and Engineering

Vellore Campus

Lecture Notes in Networks and Systems

Dynamic Cloud Access Security Broker Using Artificial Intelligence

Therapeutic issues are commonly found in every single person. Tumor is a standout among the most unsafe sicknesses a human can ever had. It is exceptionally hard to distinguish it in its beginning times as its side effects seem just in the progressed stages. Subsequently, the early forecast of lung growth is compulsory for the analysis procedure, and it gives the higher possibilities for fruitful treatment. It is the most difficult approach to upgrade a patient’s possibility for survival. Henceforth, a higher-order neural network system called recurrent neural network with Levenberg–Marquardt model with the help of glowworm swarm optimization algorithm is proposed for managing multimodal disease information. The execution of the proposed strategies is tried with information and the benchmark dataset, and the outcomes demonstrate that the higher-order recurrent neural systems with glowworm swarm optimization give better accuracy of 98% in comparison with customary optimized neural network. © 2018, The Natural Computing Applications Forum.

Department of Software Systems

Neural Computing and Applications

Lung cancer prediction using higher-order recurrent neural network based on glowworm swarm optimization

Machine learning (ML) is an application of AI (artificial intelligence), which deals with the study of capability of a computer to learn from the given data to gain knowledge in making predictions and decisions based on its experience. Such technology can benefit healthcare industry to a great extent. It is the fastest growing industry with high rates of progress in the field of health with new technologies emerging rapidly. These can be extended to a wide range of clinical tasks and prediction tasks since the performance of ML algorithms has been proved to be more than that of humans. Nowadays, all of the patient data has been recorded on computers, and the existing patient data can be used by the doctors and examiners for follow-ups. ML algorithms use this existing data and analyze them to identify patterns that are used to make precise diagnosis and provide better care to patients. With the invention of wearables, all the patient data has been monitored and stored, which is then used by ML for better patient management. ML algorithms are also being used to accurately predict the progress of a disease. This innovation can give chances to improve the proficiency and quality of healthcare. © 2020 Walter de Gruyter GmbH, Berlin/Boston. All rights reserved.

Computational Intelligence for Machine Learning and Healthcare Informatics

Machine learning in healthcare

Quality analysis of the treatment of cancer has been an objective of e-health services for quite some time. The objective is to predict the stage of breast cancer by using diverse input parameters. Breast cancer is one of the main causes of death in women when compared to other tumors. The classification of breast cancer information can be profitable to anticipate diseases or track the hereditary of tumors. For classification, an artificial neural network (ANN) structure was carried out. In the structure, nine training algorithms are used and the proposed is the Levenberg-Marquardt algorithm. For optimizing the hidden layer and neuron, three optimization techniques are used. In the result, the best approval execution is anticipated and the diverse execution evaluation estimation for three optimization algorithms is researched. The correlation execution diagram for an accuracy of 95%, a sensitivity of 98%, and a specificity of 89% of a social spider optimization (SSO) algorithm are shown. © 2019, IGI Global.

International Journal of E-Health and Medical Communications

Healthcare: Prediction of breast cancer stage using social spider-inspired optimization algorithm

VIT Unitversity

Fulltext

Procedia Computer Science

Intrusion Detection in Computer Networks using Lazy Learning Algorithm

2017 International Conference on Intelligent Computing and Control (I2C2)

Performance prediction using modified clustering techniques with fuzzy association rule mining approach for retail

In data mining, association rules are produced in view of solid relations and regularities existing among the variables in extensive exchanges. These association rules go for extricating connections, frequent patterns and associations among the item sets in exchanges. Association rules are connected for use in different zones, for example, media transmission, hazard administration and so forth. One such territory where the association rules are vital is the stock market. In stock marketing, picking the right stock relies on upon the genuine stock quality and the capacity to pick the stock is urgent as it impacts the profit of investors. In this work, the proposed technique develops a novel and effective way to deal with producing optimal stock rules to help in the stock market prediction by utilizing Enhanced Apriori algorithm and Artificial Bee Colony Optimization (ABC) algorithm. In the result profit of PP, EMA, ROC and RSI for min-support 3, 4, 5 and 6 individually in rule mining for HCL stock market dataset is appeared with correlation of GA-Apriori algorithm, AGA- Enhanced Apriori algorithm and ABC- Enhanced Apriori algorithm. From this Artificial Bee Colony (ABC) optimization algorithm is performed when contrasting and different strategies and grant that strong association rules to be produced.

International Journal of Intelligent Engineering and Systems

Performance Evaluation of Association Rule Mining with Enhanced Apriori Algorithm Incorporated with Artificial Bee Colony Optimization Algorithm

The main aim of the proposed method is to remove cyclic repeated patterns in sequential pattern mining. Initially the input dataset is fed to the clustering process, in which fuzzy c means clustering algorithm is used to cluster the available data based on the similar sequential pattern. This approach is able to mine the patterns with the help of association rule mining, here two major tasks are present one is frequent item set generation and rule generation. In frequent item set generation, support and confidence value is evaluated for each pattern. Based on that, the rules are generated in rule generation. After the mining process, the threshold is fixed and based on that repeated cyclic patterns are removed and stored to the database. The performance of the suggested method is evaluated by means of execution time, memory and database difference ratio. The implementation is done with the help of JAVA platform.

Cyclic Repeated Patterns in Sequential Pattern Mining Based on the Fuzzy C-Means Clustering and Association Rule Mining Technique

Automation plays a major role for improving the test efficiency of software test organization in software engineering. Projects use more people for manual testing or use automation tools or techniques to improve the level of test automation for ensuring test coverage satisfaction and thereby reducing risk. The choice of selection depends on reduction in project cycle time or reduction in time for test. This paper discusses about software automation steps and explains an algorithm for addressing the issues faced in system management automation of various services like DHCP,DNS,and Firewall etc. © 2016,International Journal of Pharmacy and Technology. All rights reserved.

International Journal of Pharmacy and Technology

Development of genetic algorithms to improve test case generation in software engineering

In health sciences, prescribing drugs for the patients depends on the diagnosis conducted by the doctors or experts. As the world is moving toward the automation of diagnosis using computers, the prediction of diseases in the human can be automated by using machine learning algorithms which perform the task of classification/ prediction when given the patient details. To predict the patient diseases, a set of historical data is passed to the machine learning algorithms and the algorithm is trained to learn for prediction. Among several machine algorithms, decision tree is the prominent technique to understand how the decision is taken as it represents the classification knowledge in hierarchical form. As decision trees take crisp decision, it is not possible to handle fuzziness which is common in real world data, so fuzzy decision trees emerged. In this paper, we present an empirical study of fuzzy decision trees (FDTs) towards the classification of several medical datasets so as to facilitate an intelligent system to predict the disease and further it can lead to an option of automatic prescription of drugs for the patients as per the predictions made by the machine learning algorithm which can later be verified by the experts if desired. © 2016, International Journal Of Pharmacy and Technology. All rights reserved.

Department of Information Technology

School of Information Technology and Engineering

An empirical study of fuzzy decision trees for predicting the patients medical behaviour

Compilers have many optimization sequences to be run on a program IR (Intermediate Representation). Applying all optimization sequence leads to degradation of performance. It needs a best optimization set from optimization sequence for every program to improve performance. The literature addresses standard universal optimization sequences set derived from set of program spaces. Retrieving best optimization sequences form this set consumes more time. This paper proposes a sequence selection approach that reduces time for selecting best optimal sequence set and further it reduces runtime of a program space. The experimental results showed improved performance on different program spaces in different bench mark suites. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

Improving optimization sequence of compilers by using sequence selection approach

The process of achieving single fused image by combining relevant information from more images is image fusion. The resultant image will have more information when compared to the given input images. Image fusion has become a regulation for huge number of applications to derive the formal solutions in many fields like Aerial and Satellite imaging, Medical imaging, Robotic vision, Multi-focus image fusion, Digital camera application etc. Medical image fusion is very much essential for diagnosing diseases efficiently using multidimensional, multi-parameter image types. The objective of this paper is to design a multi modality medical image fusion system using different fusion methods with quantitative analysis. In this system, initially, images having different modalities can be considered as input such as CT (anatomical information) and MRI (functional information). Then the fusion methods viz., Contourlet Transform method, fusion tool methods (Average, Contrast Pyramid, Discrete Wavelet Transform (DWT), Filter-Subtraction-Decimate Pyramid (FSD), Gradient Pyramid, Laplacian Pyramid, Maximum, Minimum, Morphological Pyramid, Principal Component Analysis (PCA), Ratio Pyramid, and Shift Invariant Discrete Wavelet Transform Pyramid (SIDWT)) are applied and further resultant image is analyzed using various quantitative metrics such as Standard Deviation (SD), Entropy (EN), and Power Signal to Noise Ratio (PSNR) for performance evaluation. From the experimental results, it is observed that the Contourlet Transform method perform well than the fusion tool methods are proved through all metrics. © 2016, International Journal of Pharmacy and Technology. All rights reserved.