MYAIRCARE: A Smart Environmental Health Platform for Outdoor Pollution Tracking, Personalized Risk Prediction, and Real-Time Alert Generation Using IoT and Machine Learning M Mythili, R Bharathi, K Deepika, D Gowshika, K Keerthika Proceedings IEEE 10th International Conference on Smart Structures and Systems Icsss 2025, 2025 MYAIRCARE is an IoT and ML-based environmental health monitoring system that monitors air quality in real-time and sends personalized notifications about the risk of user’s health. The sensors in the system are ESP8266based and detect pollutants (PM2.5, PM10, MQ-7, MQ-131, MQ-135), temperature and humidity (DHT22) to display the current on the global and regional map (OpenAQ). Users may upload their medical reports in the format of images or PDF that are analyzed by a GenAI engine to recognize medical conditions such as asthma, respiratory issues and allergies. All the sensor readings and medical information is stored in the MongoDB and are processed with the assistance of the Random Forest and LightGBM models to provide personal outcomes in the sense of risk predictions. GenAI delivers personalized recommendations and warnings via Twilio on the premise of these predictions. It also contains a format of interactive AQI map and dashboard where users can follow up on their environmental exposure besides receiving health-related notifications.
A Process of Penetration Testing Using Various Tools Dr.K.Deepika kongara, Shivani Krishnama Mesopotamian Journal of Cybersecurity, 2023 In the present world, information and data are the greatest assets one can possess. If one cannot secure their information from cyber-attacks, they would lose everything in the blink of an eye. Penetration testing can help reduce this cyber-risk exposure of clients' data and protect them. Penetration testing (also called "pen testing") is a part of ethical hacking that exposes the weak areas, vulnerabilities, or loopholes in the core of a PC, its networks, and its applications with the purpose of securing the system. The main idea of pen testing is to find vulnerabilities in systems and fix them before attackers can take advantage of them. These vulnerabilities are identified, exploited, and analyzed in five phases: information gathering, scanning, gaining access, maintaining access, and covering tracks. Penetration testing is done regularly in order to maintain high-security standards. As it pertains to any organization’s secrecy and privacy, this testing is also constrained by a number of legal agreements. The work provided by many researchers in the field of penetration (PEN) testing is reviewed and analyzed in this paper. This report gives a detailed description of the process and tools used to conduct penetration testing
Human Action Recognition Using Difference of Gaussian and Difference of Wavelet Gopampallikar Vinoda Reddy, Kongara Deepika, Lakshmanan Malliga, Duraivelu Hemanand, Chinnadurai Senthilkumar, Subburayalu Gopalakrishnan, Yousef Farhaoui Big Data Mining and Analytics, 2023 Human Action Recognition (HAR) attempts to recognize the human action from images and videos. The major challenge in HAR is the design of an action descriptor that makes the HAR system robust for different environments. A novel action descriptor is proposed in this study, based on two independent spatial and spectral filters. The proposed descriptor uses a Difference of Gaussian (DoG) filter to extract scale-invariant features and a Difference of Wavelet (DoW) filter to extract spectral information. To create a composite feature vector for a particular test action picture, the Discriminant of Guassian (DoG) and Difference of Wavelet (DoW) features are combined. Linear Discriminant Analysis (LDA), a widely used dimensionality reduction technique, is also used to eliminate duplicate data. Finally, a closest neighbor method is used to classify the dataset. Weizmann and UCF 11 datasets were used to run extensive simulations of the suggested strategy, and the accuracy assessed after the simulations were run on Weizmann datasets for five-fold cross validation is shown to perform well. The average accuracy of DoG + DoW is observed as 83.6635% while the average accuracy of Discrinanat of Guassian (DoG) and Difference of Wavelet (DoW) is observed as 80.2312% and 77.4215%, respectively. The average accuracy measured after the simulation of proposed methods over UCF 11 action dataset for five-fold cross validation DoG + DoW is observed as 62.5231% while the average accuracy of Difference of Guassian (DoG) and Difference of Wavelet (DoW) is observed as 60.3214% and 58.1247%, respectively. From the above accuracy observations, the accuracy of Weizmann is high compared to the accuracy of UCF 11, hence verifying the effectiveness in the improvisation of recognition accuracy.
A Robust system for disaster detection and management model M. P. Karthikeyan, A. Mani, Indhumathi S, Jothika B, Kongara Deepika 2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023 Numerous advancements are produced as a result of the development of embedded computer systems and the science of sensors. In this research, a unique sensing network framework for the disaster gathering and analysis, comprising data on the actual surroundings and prospective surviving' messages, is discussed. A centralized information server and a large number of sensor devices make up the overall structure. The main database server supervises the sensor devices' internal ZigBee system, which is coordinated by them. For the purpose of being able to deliver comprehensive catastrophic event data globally, the server must be linked to the internet. An automated configuration that can travel to catastrophe sites and assess the viability of an individual's involvement was built into the framework.
Cluster Based Malicious Node Detection System for Mobile Ad-Hoc Network Using ANFIS Classifier Gopalakrishnan Subburayalu, Hemanand Duraivelu, Arun Prasath Raveendran, Rajesh Arunachalam, Deepika Kongara, Chitra Thangavel Journal of Applied Security Research, 2023 Improvement of efficient packet access in a wireless Mobile Ad-Hoc network (MANET) is vital for achieving high speed data rate. The degradation occurs due to identification of malicious node and hence, reducing the severity will be a complex problem due to similar characteristics with trusty nodes in sensing area. In this work, Adaptive Neuro Fuzzy Inference System (ANFIS) classifier based defected node identification system is developed. The conviction parameters to be extract of the reliable and malevolent nodes and these parameters are qualified by ANFIS classifier. Further, the individual nodes in MANET are classified in testing mode of classifier. The network performance will be degraded with the increased number of malicious nodes. Certain conditions like packet delivery ratio, throughput, detection rate, energy consumption, and precision value and link failures occur due to malicious node in the network. The anticipated malicious node detection structure be compare by means of the conservative techniques such as Optimized energy efficient routing protocol (OEERP), Low energy adaptive clustering hierarchy (LEACH), Data routing in network aggregation (DRINA)and Base station controlled dynamic clustering protocol (BCDCP). The proposed ANFIS classifier is designed in Matrix Laboratory (MATLAB) and it can be interfaced with NS2 using “c” programming.
Engineering Education with Tool Based Technical Activity (TBTA) R. Dineshkumar, , M. Kalimuthu, K. Deepika, S. Gopalakrishnan, , , and Journal of Engineering Education Transformations, 2022 The main aim of Engineering education is to impart intellectual development and promote technical skills to engineering students. Teaching methodology plays a major role in the teachinglearning process. The basic goal of engineering students is to nurture knowledge in the relevant areas. Engineering education is technology-oriented; the learners should apply his/her knowledge to a specific application. To develop their technical skills, the students should identify suitable learning styles for their potentialities. The proper teaching methodology is a key point to success in engineering education. The industry expects the students to be high-quality engineers and industry-ready after completing their courses. Due to lagging in technical training and syllabus provided by the university doesn't match with the real- time industry projects. To achieve these outcomes technical-based activity needs to be enhanced in engineering education. In this paper, we proposed a Tool Based Technical Activity (TBTA) teaching method that converges traditional teaching methods which improve the student's attention in learning. Students' feedback with TBTA improves students' learning, communication, technical skills, and knowledge. Ke ywo r d s : Kn owl e d g e , P r e s e n t a t i o n , Communication, Technical, Teaching-learning, Feedback
