scispace - formally typeset
Search or ask a question
Institution

KCG College of Technology

About: KCG College of Technology is a based out in . It is known for research contribution in the topics: Adsorption & Diesel fuel. The organization has 427 authors who have published 381 publications receiving 2193 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: An improved version of the RCV model is developed which is expected to achieve satisfactory segmentation performance, irrespective of the initial selection of the contour, and the precision of locating boundaries is improved greatly and requires only a reduced number of iterations for convergence compared to the traditional RCV models.
Abstract: The structure of an early fetal heart provides essential information for the diagnosis of fetus defects. Accurate segmentation of anatomical structure is a major challenging task because of the small size, low signal-to-noise ratio, and rapid movement of the ultrasound images. In recent years, active contour methods have found applications to ultrasound image segmentation. The familiar region-based Chan–Vese (RCV) model is a strong and flexible technique that is able to segment many types of images compared to other active contours. However, the solution trapping in local minima is the main drawback determined on the RCV model with the exposure of improper initial contours. Also, the RCV model showed poor results with this situation. More probably, the images having large intensity differences between global and local structures usually suffered from this problem. To solve this issue, we develop an improved version of the RCV model which is expected to achieve satisfactory segmentation performance, irrespective of the initial selection of the contour. We have formulated a new and hybrid meta-heuristic optimization algorithm namely global pollination–based CAT swarm (GPCATS) optimizer to solve the fitting energy minimization problem. In the GPCATS method, the global pollination step of the flower pollination algorithm (FPA) is used for improving the distance averaging of the CATS algorithm. The performance of the proposed method was analyzed on different fetal heart ultrasound videos acquired from 12 subjects. Each frame of each video was manually annotated in order to provide labels for training and validating the model. Experimental results of the proposed model proved that the precision of locating boundaries is improved greatly and requires only a reduced number of iterations (75% less) for convergence compared to the traditional RCV model. This proposed method also proved that our model not only enhances the accuracy of locating boundaries but also works stronger robustness than some other active contour methods.

3 citations

Journal ArticleDOI
TL;DR: An efficient algorithm called Enhanced Candidate Generation for Frequent item set Generation (ECG for FIG) for finding frequent item sets from large databases by representing the transactions in the database with decimal numbers instead of binary values and strings is introduced.
Abstract: Frequent item sets is one of the most investigated fields of data mining. The significant feature is to find new techniques to reduce candidate item sets in order to generate frequent item sets efficiently. This paper introduces an efficient algorithm called Enhanced Candidate Generation for Frequent item set Generation (ECG for FIG) for finding frequent item sets from large databases. The existing algorithm for frequent item set generation scan the original database more than once, use more storage space, take more processing time. The proposed algorithm gives a solution to this by representing the transactions in the database with decimal numbers instead of binary values and strings. The original database is scanned only once and is converted into an equivalent decimal value to reduce the storage space. The subset generation concept is used to generate frequent item sets. Thus the proposed algorithm reduces the scanning time, processing time and the storage space respectively. When compared with the existing algorithms, the proposed algorithm takes very less execution time and memory. When implemented the algorithm using java and tested with WEKA tool, for 400 transactions of twenty five items, ECG for FIG is taking only 800 bytes of memory and 2000000000 ns (two seconds), whereas all the other above mentioned algorithms are taking 20800 bytes of memory and more than two seconds.

3 citations

Proceedings ArticleDOI
07 Oct 2021
TL;DR: In this article, a portable application that can get the information from the client's savvy band or smartwatch for prompt forecasts is presented. But, the application is limited to the use of a smartwatch and not suitable for wearables.
Abstract: Heart sickness is a main source for a lot of passings around the globe, and it is fundamental for each person to take great consideration of their heart. Cardiovascular infections (CVDs) turned into a significant reason for casualty in India. More than 54.5 million individuals experiencing CVDs in 2016 and one out of 4 passings are presently because of coronary illness. This task adds to conveying the expectation model for a coronary illness or respiratory failure utilizing AI and to make an easy to understand portable application that can get the information from the client’s savvy band or smartwatch for prompt forecasts. This tells individuals their coronary illness well and takes adequate measures to forestall heart absconds ahead of time. An alternate organic and actual boundaries like age, sex, pulse, circulatory strain, cholesterol level and chest torment locale can be utilized to estimate. The preparation and examination dataset, which comprises 14 distinct ascribes, was downloaded from kaggle.com. Managed calculations in AI will in general focus on information and the outcomes show that the proficiency of the proposed calculation method is contrasted and the high exactness with accuracy.

3 citations

Book ChapterDOI
06 May 2020
TL;DR: The hybrid encryption technique is combined with an LDPC coder for efficient information between the sender and receiver and improves the hiding capacity by 11.36% than SISO, 48.48% than OFDM, and 68.96% than MIMO.
Abstract: Medical identity theft is more common since it is easy to steal the patient’s record details and sell it for illegal medical trades. It happens in medical track records, personal healthcare accounts, recorded online insurance services, social security numbers, and other personally identifiable information (PII) which are disguised and used in the name of others. In this research, the proposed approach combines data hiding with hybrid encryption algorithms such as Modified Elliptic Curve Cryptography (MECC) encryption based on MIMO-OFDM framework. The hybrid encryption technique is combined with an LDPC coder for efficient information between the sender and receiver. Thereby, it improves the hiding capacity by 11.36% than SISO, 48.48% than OFDM, and 68.96% than MIMO. The sensitivity values are measured through the parameter number of pixels changes rate (NPCR) and unified average changing intensity (UACI) and obtained as 99.70 and 33.48 respectively. Correlation between adjacent pixels (CP) is increased compared to previous works. For SNR (Signal to Noise Ratio) at 30 dB CP is obtained as 0.9985. Simulation is carried out in MATLAB 2019a.

3 citations


Authors

Showing all 427 results

NameH-indexPapersCitations
G. Nagarajan462757004
Raghavan Murugan331263838
B. Nagalingam22292255
G. V. Uma201081357
V. Edwin Geo18631023
R. Lakshmipathy1230442
Sellappan Palaniappan1129803
M. Kannan1028309
B. Vidhya1046399
S. Ramesh948503
R. Gladwin Pradeep921190
T. Ravi823153
K. Vijayaraja815133
C. Clement Raj78212
Maya Joby712309
Network Information
Related Institutions (5)
Amrita Vishwa Vidyapeetham
11K papers, 76.1K citations

79% related

National Institute of Technology, Rourkela
10.7K papers, 150.1K citations

78% related

Thapar University
8.5K papers, 130.3K citations

77% related

National Institute of Technology, Karnataka
7K papers, 70.3K citations

77% related

National Institute of Technology, Tiruchirappalli
8K papers, 111.9K citations

77% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
20221
2021102
202039
201957
201839
201741