Hency Juliet A

SAVEETHA UNIVERSITY, Computer Application, Faculty Member

Followers

Following

Public Views

Dr.A.Hency Juliet has Completed her Ph.D, in Computer Science from Bharathiar University, Tamil Nadu, India. She has qualified SET in Computer Science & Application in the year 2016. She has received her M.C.A from Manonmaniam Sundaranar University and M.Phil., degree from Periyar University, she is currently working as a Professor, Department of Computer Applications, Saveetha College of Liberal Arts and Sciences, SIMATS Deemed to be University Thandalam, Chennai. She has 22 years of teaching experience in both UG and PG Level. She has organized various International Conferences and National Seminars. Also, she has organized one Week International FDP with various titles for the faculty members. She organized various Workshops and Seminars to improve the student’s technical skills. Her participation in organizing Conferences, Seminars, intercollegiate events, Workshops etc… proven her potential in Academics. She has also served as an IQAC executive member and Vice Principal. She has delivered various Guest Lectures in different institutions. She has published more than sixteen research articles in various peer-reviewed, Scopus and UGC Journals. She has Filed and published an Indian patent, dated 15.12.2022 with the title Design System of intelligent Healthcare system using IoT driven signals with Machine Learning. The Field of Invention is Bio Medical Engineering. She is an author of FIVE BOOKS (Basics of Data Structure, Network Security, Software Engineering, Research Methodology and Computer Networks and Data communication) in the field of computer science. Her area of specialization is Data mining. She has received 5 Awards. Her positive, kind and calm nature creates a positive and workplace environment.
Phone: +919381745558
Address: No.6, Madha Koil 4th Street
Chinna Nolambur
Maduravaoyal Post

less

Interests

Uploads

Papers by Hency Juliet A

Transforming Shopping with IoT: Exploring the Intelligent Way to Design the Smart Trolley using IoT Principles

The interconnection of commonplace items is revolutionizing people&#39;s daily lives, thanks ... more The interconnection of commonplace items is revolutionizing people&#39;s daily lives, thanks to the Internet of Things (IoT). A smart shopping system, consisting of interconnected products, might one day be a reality in supermarkets. In this Internet of Things system, products may be individually identified using low-cost RFID tags, which, when added to an RFID-enabled smart shopping cart, can be read automatically. This means shoppers won&#39;t have to endure the checkout line at all-billing can be handled right in the cart. The integration of RFID-equipped smart shelving into this system allows for the monitoring of inventory and, perhaps, the update of a central server. The suggested shopping system, which is dubbed IoT Assisted Smart Trolley (IoTAST), is cross-validated with the standard Smart Trolley (ST) model to clearly evaluate its performance. Since an RFID reader can automatically read all objects instead of a labourer physically scanning them, inventory management becomes considerably easier with this sort of technology. We construct a working system to test its functioning, determine the design criteria of a sophisticated purchasing system, and then create a reliable communication mechanism that renders the system feasible. This study validates the viability of the system. This is the first smart shopping system that takes security into account that we are aware of.

An Industrial IoT Driven Approach for Sewage Gas Identification and Reporting System using Intelligent Sensors with Logical Controller

Abstract—Based on a real-time sewage gas level detection and monitoring system, this system seeks... more Abstract—Based on a real-time sewage gas level detection and monitoring system, this system seeks to offer intelligent solutions for the monitoring of toxic sewage gases. An alarm is issued to the observer who is looking at the circumstances from a distance whenever a specific threshold is crossed. Following this, the data is transmitted together with different gas ppm levels, indicating if the worker can clean or operate securely in that region. The suggested solution incorporates both the IoT platform and the remotely located IoT monitoring devices. This necessitates finding the appropriate threshold values for septic plants and facilities, as well as calibrating gas sensors for use in industry. The gear is meant to provide the sewage worker advance notification whenever the concentration of toxic gaseous substances grows over time, ensuring their safety. The presence of gas, temperature, and other factors in sewage may be detected using a variety of sensors. By notifying sewage workers as well as cleaners via SMS whenever the threshold value drops below the observed levels, this technology helps save people from harmful infections, which is a social good. A number of harmful gas concentrations are graphed out for real-time monitoring, and this is how it accomplishes its job. In order to assess the efficacy of the suggested model, this paper cross-validates it with the Conventional Sewage Gas Detection (CSGD) based on GPRS functioning. The goal of the cross-validation is to create an IoT based Sewage Gas Detection (IoTSGD) system that can monitor and analyze toxic gas levels in real-time and notify workers. Firebase receives the measured gas levels. If the levels rise over a certain point, it will notify the authorized individuals working remotely through their linked mobile devices. An SMS message can alert the authorities if the sewage system is likely to overflow. For the purpose of monitoring, an android app was created and connected with the planned system.

Revolutionizing Human Action Prediction and Detection through Extended Transfer Learning: A Novel Approach for Cross-Domain Knowledge Integration

Risks in Amalgamation of Artificial Intelligence with Other Recent Technologies

False - Face Challenge Response Authentication Automated Test Using Anthropomorphic Images

Captcha is the reverse Turing test done by the machine to verify the human online automatically. ... more Captcha is the reverse Turing test done by the machine to verify the human online automatically. This proposed work presents a method to use anthropomorphic (human outer cover morphed with monkey images) images for designing captchas. A set of false-face (morphed) images displayed in the grid with another group of images where the generated human-like pictures need to be as close as possible to human faces but not entirely. Such anthropomorphic captcha secure high score than other captchas while differentiating the human and machine. In the second level, clicked images are replaced by obfuscated, deformed, distorted and noised text images to decrease the machine recognition rate remarkably, compared to previous work while human recognition increased likewise. In addition to that, deep neural network model (proposed False-face model) trained with animal, human, morphed and alphabet images in a powerful way to classify the images. These images are tested with existing face classification algorithms like DeepFace, FaceNet, and TBE-CNN. This algorithm could not produce significant success in the prediction of anthropomorphic images. It helps to improve web security significantly while using this proposed captcha design.

Comparison of Random Forest with K-Nearest Neighbors to Detect Fake News with Improved Accuracy

Smart Forecasting: Harnessing Machine Learning for Accurate CO2 Emission Predictions

This The tenacity of this study is to improve a Machine Learning (ML) model to enhance the precis... more This The tenacity of this study is to improve a Machine Learning (ML) model to enhance the precision of Carbon Dioxide (CO2) emission predictions. This study utilizes the cutting-edge forecasting techniques for a more accurate understanding of environmental impact. This study will harness the power of smart forecasting to inform strategic decision-making in carbon mitigation efforts. In this research, the performance metrics of four commonly used ML classifiers, namely LR, Gaussian Process, MLP and SMOreg have been evaluated to foretell CO2 emissions using the dataset collected from Kaggle. The dataset was pre-processed, and all the algorithms were trained and tested. The number of instances used in this study is 935. The results of this investigation show that machine learning algorithms are capable of producing accurate CO2 emission forecasts. The findings suggest that the SMOreg Classifier is more accurate than the LR (LR), Gaussian Process Regression (GPR) and Multilayer Perceptron (MLP) classifiers for predicting CO2 emissions. This study emphasizes the possibility of using ML algorithms to predict CO2 emissions. The error values such as MSE, RMSE, MAE, Correlation Coefficient and Root relative squared error indicates the performance of SMOreg is a superior classifier for the forecasting, these results have an important implication in climate change for improving prediction models, which could assist in early detection of climate change.

Early Warning System for Endometrial Cancer Prediction in PMB Women Using Novel Ensemble Model

International Journal of Engineering Research and Technology. ISSN 0974-3154 Volume 11, Number 10 (2018), pp. 1533-1544 © International Research Publication House , 2018

It's urge to establish a reliable system with high accuracy and efficiency for early prediction o... more It's urge to establish a reliable system with high accuracy and efficiency for early prediction of cancer. In the present study, a novel ensemble model is developed for the prediction of Endometrial Cancer (EC) in women presenting with post menopausal bleeding. Methodology used: In this approach to improve the performance of the model ensemble model was formed. Four different machine learning models such as K-Nearest Neighbor, Navive bayes, Neural Network and Random Forest are combined to form the ensemble model to predict the accuracy. The performance of the model was compared between ensemble model and Random Forest for before diagnosis and after diagnosis data of the patients. Findings: The ensemble model increases the prediction accuracy. Novel ensemble model produces high accuracy, gini, AUC, specificity and sensitivity. The result shows that the proposed ensemble model is outperforming.

Download

Transforming Shopping with IoT: Exploring the Intelligent Way to Design the Smart Trolley using IoT Principles

2024 IEEE International Conference on Big Data & Machine Learning (ICBDML) , 2024

The interconnection of commonplace items is revolutionizing people's daily lives, thanks to the I... more The interconnection of commonplace items is revolutionizing people's daily lives, thanks to the Internet of Things (IoT). A smart shopping system, consisting of interconnected products, might one day be a reality in supermarkets. In this Internet of Things system, products may be individually identified using low-cost RFID tags, which, when added to an RFID-enabled smart shopping cart, can be read automatically. This means shoppers won't have to endure the checkout line at all-billing can be handled right in the cart. The integration of RFID-equipped smart shelving into this system allows for the monitoring of inventory and, perhaps, the update of a central server. The suggested shopping system, which is dubbed IoT Assisted Smart Trolley (IoTAST), is cross-validated with the standard Smart Trolley (ST) model to clearly evaluate its performance. Since an RFID reader can automatically read all objects instead of a labourer physically scanning them, inventory management becomes considerably easier with this sort of technology. We construct a working system to test its functioning, determine the design criteria of a sophisticated purchasing system, and then create a reliable communication mechanism that renders the system feasible. This study validates the viability of the system. This is the first smart shopping system that takes security into account that we are aware of.

Download

The Future of Data Protection: Empowering Data Security with Identity-centric Blockchain Technology

2024 2nd World Conference on Communication & Computing (WCONF) Raipur, India. Jul 12-14, 2024, 2024

In response to the formidable challenges surrounding data security, particularly in the face of e... more In response to the formidable challenges surrounding data security, particularly in the face of evolving threats and vulnerabilities, this study introduces the Advanced Blockchain-Enhanced Data Security Protocol (ABE-DSP) as a cutting-edge solution. Acknowledging the complexities of safeguarding sensitive information, ABE-DSP is a meticulously crafted and sophisticated framework that aims to fortify the security and integrity of data transactions through the integration of blockchain technology. This protocol addresses the pressing challenge of ensuring robust data security by placing a primary focus on enhancing overall system security and refining user authentication processes. Within the context of these challenges, the study explores the intricacies of ABE-DSP's design and implementation. Furthermore, the proposed method demonstrates its effectiveness by achieving a remarkable success rate, processing 97% of received packets with precision. This high percentage underscores the protocol's efficacy and reliability, positioning it as a robust and advanced tool for overcoming the contemporary challenges associated with data security. This study contributes valuable insights to the ongoing discourse on leveraging blockchain technology for identity-centric data security, offering a promising avenue for addressing and mitigating the challenges faced in the dynamic landscape of information protection.

Download

Beyond Reality: Crafting Logical Systems for Autonomous Vehicles through Virtual Reality

2024 2nd World Conference on Communication & Computing (WCONF) Raipur, India. Jul 12-14, 2024, 2024

The current paradigm for advancing autonomous driving functionalities on public roads predominant... more The current paradigm for advancing autonomous driving functionalities on public roads predominantly operates within the tangible realm. Autonomous vehicles (AVs) are equipped with an array of sensors, including Lidar, cameras, radar, GPS, and on-boardunit (OBU) modems, each actively collecting data about the surrounding environment. This data is then processed through sophisticated algorithms, enhancing the vehicle's situational awareness. In our pursuit of refining autonomous driving capabilities, we leverage the AVTSC Simulator as our chosen Autonomous Vehicle (AV) simulation environment. Notably, this simulator stands out for its ability to replicate realistic urban settings and seamlessly integrate with widely used platforms such as Apollo and ROS. By harnessing the capabilities of this simulation environment, we aim to bridge the gap between real-world testing and simulated scenarios. This abstract encapsulates the essence of our strategy, emphasizing the integration of advanced sensor technologies and simulation environments for the development of autonomous driving features. Preliminary results indicate a promising 94% success rate for the proposed methodology, showcasing the efficacy of our approach in enhancing the robustness and reliability of autonomous systems.

Download

An Industrial IoT Driven Approach for Sewage Gas Identification and Reporting System using Intelligent Sensors with Logical Controller

Abstract—Based on a real-time sewage gas level detection and monitoring system, this system seek... more Abstract—Based on a real-time sewage gas level detection and
monitoring system, this system seeks to offer intelligent solutions
for the monitoring of toxic sewage gases. An alarm is issued to
the observer who is looking at the circumstances from a distance
whenever a specific threshold is crossed. Following this, the data
is transmitted together with different gas ppm levels, indicating
if the worker can clean or operate securely in that region. The
suggested solution incorporates both the IoT platform and the
remotely located IoT monitoring devices. This necessitates
finding the appropriate threshold values for septic plants and
facilities, as well as calibrating gas sensors for use in industry.
The gear is meant to provide the sewage worker advance
notification whenever the concentration of toxic gaseous
substances grows over time, ensuring their safety. The presence
of gas, temperature, and other factors in sewage may be detected
using a variety of sensors. By notifying sewage workers as well
as cleaners via SMS whenever the threshold value drops below
the observed levels, this technology helps save people from
harmful infections, which is a social good. A number of harmful
gas concentrations are graphed out for real-time monitoring,
and this is how it accomplishes its job. In order to assess the
efficacy of the suggested model, this paper cross-validates it with
the Conventional Sewage Gas Detection (CSGD) based on
GPRS functioning. The goal of the cross-validation is to create
an IoT based Sewage Gas Detection (IoTSGD) system that can
monitor and analyze toxic gas levels in real-time and notify
workers. Firebase receives the measured gas levels. If the levels
rise over a certain point, it will notify the authorized individuals
working remotely through their linked mobile devices. An SMS
message can alert the authorities if the sewage system is likely to
overflow. For the purpose of monitoring, an android app was
created and connected with the planned system.

Download

False -Face Challenge Response Authentication Automated Test Using Anthropomorphic Images

2023 International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT) , 2023

Download

Deep Learning Model Design for Blood Cancer Prediction through AI-Driven Strategies

2024 7th International Conference on Contemporary Computing and Informatics (IC3I) , 2024

The study seeks to create and utilize sophisticated deep learning model namely Convolutional Neur... more The study seeks to create and utilize sophisticated deep learning model namely Convolutional Neural Network (CNN) designed for image classification purposes. It's a custom CNN architecture tailored for the task, to classify images of blood cells into eight distinct categories. It comprises several layers, starting with convolutional layers followed by max-pooling layers, and fully connected layers empowered by AI technique, aiming to precisely forecast different forms of blood cancer using a dataset comprising images of blood cells. Ensuring the consistency and quality of input data, especially in medical imaging datasets susceptible to variations affecting model performance, poses a significant challenge; improving the interpretability and explainability of deep learning models is crucial for their reliable incorporation into clinical decisionmaking processes for blood cancer prediction. Utilize sophisticated deep learning model design methodologies guided by Artificial Intelligence approaches, tailored to address the unique characteristics of the blood cell image dataset, in order to surmount the outlined challenges. The suggested system provides improved precision and effectiveness in predicting blood cancer by employing advanced deep learning models guided by customized Artificial Intelligence techniques. Throughout the span of 50 epochs, the model's performance was assessed based on its training and validation accuracy, gradually enhancing until reaching final rates of about 90.31% for training and 90% for validation.

Download

Deciphering Social Media Sentiment for Enhanced Analytical Accuracy: Leveraging Random Forest, KNN, and Naive Bayes

2024 10th International Conference on Communication and Signal Processing (ICCSP), 2024

The research aims to determine the most effective algorithm for social media sentiment analysis, ... more The research aims to determine the most effective algorithm for social media sentiment analysis, evaluating Random Forest, K-Nearest Neighbor (KNN), and Naive Bayes models. This investigation holds importance as it seeks to unveil the key factors influencing sentiment analysis on social media using rigorous methodologies. Employing a dataset obtained from Kaggle, the study examined the predictive capabilities of Random Forest, KNN, and Naive Bayes in accurately predicting social media sentiment. Notably, Naive Bayes emerged as the most precise predictor of social media sentiment compared to Random Forest and KNN algorithms. The study's results highlight the potential of machine learning algorithms in providing accurate predictions for social media sentiment analysis. A statistically significant level of p=0.04, where p<0.05, further underscores the significance of the study, indicating notable variations among the three algorithms. With mean accuracies of 86.06% for Random Forest, 89.28% for KNN, and 92.01% for Naive Bayes, the findings affirm Naive Bayes' superior performance over the Random Forest-KNN combination, emphasizing its superior predictive accuracy.

Download

Smart Forecasting: Harnessing Machine Learning for Accurate CO2 Emission Predictions

2024 11th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) Amity University, Noida, India. Mar 14-15, 2024, 2024

Download

IoT Enhanced Resilience: Advanced AI Technique for Leak Detection and Predictive Maintenance in Oil and Gas Pipeline

2024 10th International Conference on Communication and Signal Processing (ICCSP), 2024

The study seeks to investigate how the implementation of IoT-driven advanced AI methods can bolst... more The study seeks to investigate how the implementation of IoT-driven advanced AI methods can bolster the robustness of oil and gas pipelines by improving strategies for detecting leaks and conducting predictive maintenance. The implementation of IoT in oil and gas pipelines poses challenges, such as the need for strong cybersecurity measures to safeguard sensitive data, addressing complexities in integrating IoT devices and advanced AI technologies, and requiring seamless coordination among diverse components, potentially leading to difficulties in compatibility, interoperability, and overall system integration. Addressing the obstacles in deploying IoT for oil and gas pipelines involves utilizing advanced AI methods like federated learning to enhance data privacy and adopting a modular integration approach, offering solutions to ensure strong cybersecurity, smooth coordination, and enhanced compatibility and interoperability throughout the infrastructure. Overcoming challenges in implementing IoT for oil and gas pipelines includes the application of advanced AI techniques, such as federated learning for improved data privacy, and adopting a modular integration strategy, providing solutions to ensure robust cybersecurity, seamless coordination, and increased compatibility and interoperability across the infrastructure.

CoroNet: Predicting Coronary Artery Disease using Deep Convolutional Neural Networks and Ensemble Model for Enhanced Diagnostic Precision

2024 10th International Conference on Communication and Signal Processing (ICCSP), 2024

The coronary artery disease (CAD) is a cardiovascular ailment marked by the constriction or obstr... more The coronary artery disease (CAD) is a cardiovascular ailment marked by the constriction or obstruction of the coronary arteries, hindering the circulation of blood to the heart muscle and potentially causing chest pain, heart attacks, or other complications in the cardiac system. Forecasting Coronary Artery Disease with deep learning encounters difficulties including scarce and unbalanced data due to privacy issues and the infrequency of certain conditions, alongside the imperative for transparency and comprehensibility in the decision-making of robust yet inscrutable models such as Deep Convolutional Neural Networks (CNNs). In mitigating the constraints posed by limited and imbalanced data in the prediction of CAD, sophisticated deep learning approaches, including the utilization of Ensembles of Deep CNNs and implementing Transfer Learning with Pre-trained Models, are utilized to improve the resilience and adaptability of the models. The suggested system, utilizing advanced Deep CNN techniques, provides increased predictive precision by utilizing ensemble models and transfer learning, thereby improving resilience through the use of pre-trained models for optimal feature extraction. This study indicates that the Deep CNN technique attained an 81.97% accuracy, while Ensembles of Deep CNNs showcased a marginally superior accuracy of 83.61.% in predicting coronary artery disease, emphasizing the subtle distinctions in their predictive capabilities.

Download

Advancing Retinal Image Analysis for Neurodegenerative Disease Prediction and Detection Using Advanced Deep Learning Techniques

2024 7th International Conference on Contemporary Computing and Informatics (IC3I) , 2024

Retinal lesion disease encompasses various pathological states impacting the retina, marked by at... more Retinal lesion disease encompasses various pathological states impacting the retina, marked by atypical alterations or injury to tissue, frequently resulting in vision impairment or loss. Two obstacles in progressing retinal image analysis for predicting and detecting neurodegenerative diseases using sophisticated deep learning methods include dealing with variations in data, which makes it challenging to create universally applicable models due to disparities in image quality, patient characteristics, and disease manifestations, and addressing interpretability and validation concerns, where the absence of clear model interpretation and the complexities of real-world validation impede the comprehension and practical use of deep learning predictions. To address the mentioned constraints, a strategy involving the amalgamation of VGG16, ResNet50, and InceptionV3 models is utilized for analyzing the retinal image dataset. The ensemble method incorporating VGG16, ResNet50, and InceptionV3 models enhances predictive accuracy and robustness through synergizing the unique capabilities of each architecture, resulting in superior system performance overall. VGG16 demonstrates remarkable training accuracy of 100% by the fourth epoch, while ResNet50 and InceptionV3 achieve peak training accuracies of 100% and 92.86%, respectively. However, validation accuracies fluctuate, with VGG16 and ResNet50 maintaining accuracies of 50% and 25%, respectively, whereas InceptionV3 maintains consistent performance with a validation accuracy of 50%.

Download

A Novel Method to Identify and Recover the Fault Nodes over 5G Wireless Sensor Network Environment

2024 Asia Pacific Conference on Innovation in Technology (APCIT) Mysuru, India. Jul 26-27, 2024, 2024

The significance of communication networks is growing in tandem with the proliferation of communi... more The significance of communication networks is growing in tandem with the proliferation of communication technologies. Present methods for maintaining 5G Wireless Sensor Networks are still restricted to routine maintenance and post-maintenance tasks. They lack a comprehensive function for monitoring the network's status, are unable to assess the network's health, and are difficult to maintain before the 5G-based WSNs seriously degrade. 5G Wireless Sensor Network faults can only be resolved by highly trained technicians due to low maintenance efficiency. As a result, errors cannot be detected or located promptly or accurately, leading to forced repairs that incur the expense of new network cables. First, the article lays forth the basics of network fault analysis. Then, it uses deep learning to simulate communication network problem diagnosis. Lastly, the experimental section compares various methodologies and analyses the findings of fault location. The results of the simulation demonstrate that the suggested approach mitigates the created model's flaws to a certain degree while simultaneously enhancing the network fault detection model's accuracy, universality, and robustness. A novel approach to autonomous placement, the Fault Node Recovery Protocol is described in this study. It is implemented in 5G mobile communications to detect faulty data according to wireless sensor network standards, and it is made to fix the problems with conventional techniques, such poor positioning precision and lengthy running time. The automated localization model for 5G mobile communication fault data, constructed using the suggested FNRP approach, is presented in this work. By comparing it to the standard Adhoc On-Demand Distance Vector Routing protocol, we can see how well the suggested system performs.

Download

Hency Juliet A

Uploads

Papers by Hency Juliet A

Log In