AGNEL LIVINGSTON L G X

EDUCATION

Bachelor of Engineering in Electronics and Communication Engineering,
Master of Engineering in Computer Science and Engineering,
Master of Business Administration in Human Resources

RESEARCH, TEACHING, or OTHER INTERESTS

Multidisciplinary, Multidisciplinary, Multidisciplinary, Multidisciplinary

Scopus Publications

A reliable character recognition model based on hybrid feed forward back-propagation neural network and adaptive cuckoo search optimization algorithm
L G X Agnel Livingston, D Judson, Prasanth Aruchamy
Sadhana Academy Proceedings in Engineering Sciences, 2025
Effect of tunicated Allium cepa bulb leaf activated biochar on polyvinyl alcohol composite shielding material for electronics applications
V. Vijimon Moni, D. Judson, L. G. X. Agnel Livingston, A. Annie Portia
Biomass Conversion and Biorefinery, 2024
Low-complexity joint equalization and CFO compensation in uplink SC-FDMA NOMA system under different power allocation strategies
Judson D, A. Annie Portia, L. G. X. Agnel Livingston
Transactions on Emerging Telecommunications Technologies, 2023
Abstract In current wireless systems, the claim for rapid data services has become unavoidable in broadband communication. Single carrier frequency division multiple access (SC‐FDMA) has remained a multiple access (MA) technique with low peak‐to‐average power ratio (PAPR) in 4G systems. Non‐orthogonal multiple access (NOMA) is a complimentary MA technique in the fifth generation (5G) new radio with the capability of using similar frequency elements for multiuser communication within a single cellular system. In SC‐FDMA NOMA systems the carrier frequency offsets (CFO) destroy the orthogonal behavior in multiple carriers during transmission leading to inter‐carrier interference (ICI) and multiple access interference (MAI). Furthermore, the power allocated for each user in the NOMA cluster exhibits a noticeable part in enhancing the performance of the system. In this article, we propose a joint low‐complexity linear regularized zero forcing (JLC‐LRZF) for SC‐FDMA NOMA system and investigate its performance using discrete Fourier transform (DFT) and discrete cosine transform (DCT). The proposed JLC‐LRZF equalization algorithm is capable of performing equalization and CFO compensation with low‐complexity with banded‐matrix approximation (BMA). Additionally, we investigate the effectiveness of SC‐FDMA NOMA system in achieving improved performance with different values of CFO and power allocation policies in uniform random multipath channels.
Blockchain security using secure multi-party computation
Jenila Livingston L. M., Ashutosh Satapathy, Agnel Livingston L. G. X., Merlin Livingston L. M.
Opportunities and Challenges for Blockchain Technology in Autonomous Vehicles, 2020
In secure multi-party computation (SMC), multiple distributed parties jointly carry out the computation over their confidential data without compromising data security and privacy. It is a new emerging cryptographic technique used in huge applications such as electronic auction bidding, electronic voting, protecting personal information, secure transaction processing, privacy preserving data mining, and privacy preserving cooperative control of connected autonomous vehicles. This chapter presents two model paradigms of SMC (i.e., ideal model prototype and real model prototype). It also deals with the type and applications of adversaries, properties, and the techniques of SMC. The three prime types of SMC techniques such as randomization, cryptographic techniques using oblivious transfer, and anonymization methods are discussed and illustrated by protective procedures with suitable examples. Finally, autonomous vehicle interaction leveraged with blockchain technology to store and use vehicle data without any human interaction is also discussed.
Prediction of top tourist attraction spots using learning algorithms
Sagar Gupta*, , Jenila Livingston L.M., Agnel Livingston L.G.X., , and
International Journal of Recent Technology and Engineering, 2019
Dealing with the growing amount of user posted content like preferences, responses, comments, past experiences and beliefs spread through social media is a vital but challenging task. Being applied in several domains, recommender systems are used to find solutions and suggestions based on users interests including tourism-related opinion detection and tourist-attraction spot identification. Tourists can access and analyze this information for making decisions and predicting best tourist places. This study aims to predict tourist attraction spots and their related information by analyzing the data from social media (Facebook, Twitter etc.) which in turns help the tourist industry by deliberating what kind of attractions tourists can have and how to obtain their preferences. For this purpose four algorithms such as Kernel Density Estimation, K- Nearest Neighbor, Random forest and XG Boost have been used. The findings revealed that XG Boost yields better results in terms of accuracy than other three algorithms.
Multiclass Single Label Model for Web Page Classification
Aakash Kag, Livingston L. M. Jenila, Livingston L. M. Merlin, Livingston L. G.X Agnel
2019 International Conference on Recent Advances in Energy Efficient Computing and Communication Icraecc 2019, 2019
Web is a huge repository of information and there is a need of categorization of web pages to facilitate better search and retrieval of pages. Web page classification has become a challenging task due to the exponential growth of the World Wide Web and this study augments classification model with a general facility for automatically assigning class label (e.g., sport, news) to web pages based on the output of a Naive Bayes classifier. For the purpose of build classification model, yahoo Open Directory Project (ODP) data set has been used for create training and testing set. In this research work web page classification was done using Uniform Resource Locator (URL) features, Meta data, Meta keywords, Internal Links and text, which gives better result than URLs based method.
Personalized Tutoring System for Elearning
L.M. Jenila Livingston, L.M. Merlin Livingston, L.G.X Agnel Livingston, A Annie Portia
2019 International Conference on Recent Advances in Energy Efficient Computing and Communication Icraecc 2019, 2019
Educational data mining is an advanced interdisciplinary research which is concerned for developing methods to analyze the performance of the students in order to improve the quality of learning. In this study, the academic, non-behavioral and behavioral features are used for analyzing the performance of the students. The students were formed as clusters based on their similar characteristics for providing remedial measures to improve their academic achievement. Finally from the output obtained, Personalized Tutoring System is used for customizing instruction based on the needs of individual learner cluster. The Knowledge based tutor will suggest appropriate e-learning resources from the resource pool.
Processing of images and videos for extracting text information from clustered features using graph wavelet transform
Merlin L. M. Livingston, Agnel L. G. X. Livingston
Journal of Computational and Theoretical Nanoscience, 2019
Image processing is an interesting domain for extracting knowledge from real time video and images for surveillance, automation, robotics, medical and entertainment industries. The data obtained from videos and images are continuous and hold a primary role in semantic based video analysis, retrieval and indexing. When images and videos are obtained from natural and random sources, they need to be processed for identifying text, tracking, binarization and recognising meaningful information for succeeding actions. This proposal defines a solution with assistance of Spectral Graph Wave Transform (SGWT) technique for localizing and extracting text information from images and videos. K Means clustering technique precedes the SGWT process to group features in an image from a quantifying Hill Climbing algorithm. Precision, Sensitivity, Specificity and Accuracy are the four parameters which declares the efficiency of proposed technique. Experimentation is done from training sets from ICDAR and YVT for videos.