Subtitle Synchronization Using Whisper ASR Model Thara P, Mohammed Azneed, Muhammad Sanas, Jithu Prakash P M, Harsh P Naik, Divya B 4th International Conference on Power Energy Control and Transmission Systems Harnessing Power and Energy for an Affordable Electrification of India Icpects 2024, 2024 This paper introduces a novel approach to subtitle synchronization using the Whisper ASR (Automatic Speech Recognition) model from OpenAI. The primary aim of this research is to achieve accurate and robust synchronization of subtitles with audio content, even in the presence of uniform or non-uniform delays. The project leverages the capabilities of the Whisper ASR model, which is trained on diverse audio datasets and offers multitasking functionalities including multilingual speech recognition, speech translation, and language identification. Key features of the project include Whisper ASR integration, SRT modification, and accuracy enhancement. The system utilizes FFmpeg for audio extraction and preprocessing, followed by speech recognition using the Whisper ASR model. Preprocessing techniques are applied to enhance the precision of generated timestamps, ensuring precise synchronization. The methodology also involves timestamp adjustment based on text comparison between input and transcribed SRT files, resulting in accurately synchronized subtitles. The project offers a user-friendly interface for input acquisition and interaction, guiding users through the synchronization process. While promising, the system has limitations such as the lack of action detection, character name prediction, and challenges with repetitive word handling. Nonetheless, the Whisper ASR-based Subtitle Synchronization project presents a reliable solution for enhancing subtitle accuracy and accessibility in various video content scenarios.
Border Detection for Fishermen Using IoT Divya B, K. Vijayalakshmi, Alivn Ancy A, P. J, NaveenKrishna B B, Harshavardhan R 4th International Conference on Power Energy Control and Transmission Systems Harnessing Power and Energy for an Affordable Electrification of India Icpects 2024, 2024 At present, the marine security issue includes the protection of fishers and address the rescue in case of illegal border infiltration. To detect the border for fisherman, this study conducted a method of enhancement in border detection essentially utilising the Automatic Identification System (AIS) with the assistance of the Internet of Things (IoT). In the middle sea, to provide boat detection with high precision, the proposed model incorporates Very High Frequency (VHF) communication inspired by X-band radar. The system is able to detect and monitor the boats at sea. To provide the middle sea with a high level of detection and monitoring of boats, system architecture included VHF (Very High Frequency) communication, which was inspired by the X band radar system. The range of AIS was increased using VHF communication. The coastal monitoring stations receive the position and status data from fishing boats with the help of IoT devices. The new AIS technology includes IoT-enabled devices installed on fishing boats. The IoT devices situated on boats send information to coastal monitoring station after sending data. The advanced technology increases the software capabilities of AIS, which will be helpful in the situation where the only AIS information was not enough. The advanced software capabilities improved the range of AIS and the definition capability of the vessels which were identified in the ocean near borders. The Automatic Identification System (AIS) that is being used in the present day has been upgraded and the Internet of Things (IoT) has been introduced. As a result, the system is now capable of much more comprehensive and real-time tracking and monitoring, as well as communication for marine vessels. This combination of technologies strengthens the safety, efficiency, and management of maritime operations by giving ships the Opportunity to connect and exchange data with different sensors, devices, and networks, and thus offering a more detailed and dynamic understanding of vessel activities and environmental conditions.
An Effective Anti-Money Laundering System Using Block Chain Technology Divya B, Thara P, Kavitha S, Alvin Ancy A, Preethi Sri R, Dhanalakshmi D International Conference on Smart Systems for Electrical Electronics Communication and Computer Engineering Icsseec 2024 Proceedings, 2024 In the developed financial services industry, identity is defined using government-issued identification cards. Nevertheless, the primary obstacles in the consolidation and authentication of these data in connection with large-scale anti-money laundering (AML) requirements have significantly increased the challenges for individuals seeking to enter the financial system. This renders it exceedingly unprofitable and a greater risk for banking systems to engage with developing economies that might lack even the most primitive forms of identification. Furthermore, the process of establishing a banking account is packed with difficulty as a result of protracted processing times, substantial report obligations, and ambiguity surrounding the utilization of confidential customer data. The objective of cash laundering is to return illegal funds to their source; therefore, money launderers typically employ robust financial structures to transport funds. Additionally, the level of money laundering activity may become more geographically concentrated as the amount of money laundered increases. For many years, the financial quarter has been working to reevaluate the concept of identity. Blockchain is an emerging computing structure that enables the integration of disparate data points from authoritative source vendors into a unified digital ledger of validated, unalterable, transparent, and cryptographically protected data. Furthermore, secrecy can be ensured by letting the appropriate person or group control how their identity is shared. A blockchain is a distributed, virtual ledger that is unchangeable and keeps track of transactions in chronological order and close to real time. In order for later transactions to be added to the ledger the community members also known also nodes, must agree on them. This establishes an ongoing management mechanism that oversees issues related to manipulation, errors, and statistics. After dispatch Information contained within a block cannot be altered or tampered with in a sequence, thereby generating a transparent and authentic file for the transaction.
Fire and Smoke Detection Using Deep Learning Divya B, Kavitha S, Muthu Pandeeswari R, Sreenidhi R, Ponvaishnavi Mr, Loshine S Proceedings of the 2nd IEEE International Conference on Networking and Communications 2024 Icnwc 2024, 2024 Of late, wildfires and commercial fires like fires in a shopping complex, firework factories, and industries, continue to cause extensive destruction throughout the world, frequently causing human fatalities. The solution is divided into two systems, where the first system focuses on the wildfire and the second system focuses on commercial fires. Identifying the fire and smoke correctly plays an important role. Gradient-weighted Class Activation Mapping (Grad-CAM) is used to identify the smoke region in the image. This algorithm is used to assure the smoke or fire in the image. The algorithms like ResNet, CNN (Convolutional neural network), and VGG16 (Visual Geometry Group) algorithms are used in transfer learning. This aims to increase the accuracy of the detection of fire and smoke in forests to avoid mishaps. The GradCAM is an algorithm that finds out the positive score in the image. This confirms the smoke in the image using the heat map generation. The ReLU activation function is used to show the positive pixels. The saliency map is also used in finding out the difference between smoke and fog in case of wildfire. In the case of the building fire shopping complex, firework shops, factories, and industries would also require a better solution because the detection is easier but the rescue process is more difficult in such places. The same procedure is followed for detecting and finding the origin of the fire as the wildfire model. The YOLOv8 algorithm is used for real-time analysis of the building. The model constantly looks for the unusual behavior of the environment and this in turns induces the notification. The additional feature is added to the model for rescue purposes. Fire control and evacuation have become more complex and hence the solution to such a problem is not yet brought into consideration. Even after detecting the fire, most of the people die due to the poor rescue process. This is because the rescue team cannot find the people inside the building. Our solution takes that into consideration. Our system uses a camera which could alert the people inside and also help in the rescue process. The camera takes photos and videos of the area if the fire or smoke is detected. Then the De-hazing algorithm is used to clarify the smoky images to identify the core details inside it. This is passed to the rescue team with the video of people inside which is given the most priority for extinguishing purposes. A separate mobile application is made for the rescue team. The extinguish process is also a very complex in case of the building fire. Hence the compression of the surrounding air is used to extinguish the fire. The target to extinguish the fire is detected using the images and videos and the targeted place is considered for the extinguish process and the compressed is given out. In this process the water is not wasted much and this reduces the work of fire rescue team.
A Hybrid Approach to Attendance Monitoring: Combining Geo Location and Facial Verification Divya B, Ramya R, H. S, Abishek B, Thangamuthu E, Harikrishna K L 4th International Conference on Power Energy Control and Transmission Systems Harnessing Power and Energy for an Affordable Electrification of India Icpects 2024, 2024 Attendance management is an important task for an educational institution to cater to faculty accountability and correct tracking of the same. Traditional technique is enhanced by introducing a novel system that uses three separate modules; namely face recognition, geofencing, and real-time notifications. The system can identify when faculty members enter the institution’s appointed area, and it embraces them with a request to complete the attendance process. The faculty members are encouraged to log onto to face detection software, where in they have a set time frame for them to log on and log their attendance using their individual identification number. The mobile application software has additional options - check-in and check-out options to precisely monitor the working hours accurately. It ensures the attendance is not falsified, and only registered within the designated area. The bank offers an elegant interface with sections of home, reports, user details, and announcement. The report sect provides a clear overview of the attendance records, and the user detail section provides comprehensive information about the faculty members, however the announcement section is relevant for the announcement section is the latest updates about the institution. Additionally, with the advanced security on this system, the data privacy and the data integrity is secure and trustworthy to use in this contemporary educational institution. It has not only increased the efficiency of workplace, but has also improved the traditional attendance logging system.
Autonomous Drone-Based Fire Detection and Suppression Using YOLOv8 and 2D Blueprint Mapping for Industrial Applications K Vijayalakshmi, Bose Divya, Prabahar Godwin James T, S Sourav, Soundaraj Dineshkumar, et al. 4th International Conference on Power Energy Control and Transmission Systems Harnessing Power and Energy for an Affordable Electrification of India Icpects 2024, 2024 Lately, spotting and controlling fires quickly has become more vital than ever to limit damage and save lives. Traditional methods often suffer from delayed response times and limited coverage, making them less effective in preventing the escalation of fires. In this paper, we focus on developing and implementing an autonomous drone system that enhances the efficiency of fire detection and firefighting efforts. The system integrates advanced machine learning techniques with live CCTV camera feeds to detect the presence of fire accurately. Upon detection, the system pinpoints the precise location of the fire and autonomously navigates a drone equipped with fire extinguishing tools, such as the AFO (Auto Fire Off) ball, to the affected area. Our proposed solution leverages a convolutional neural network (CNN) to process real-time video footage and accurately identify fire. The drone’s navigation system employs a combination of GPS and computer vision to traverse the environment and reach the fire site quickly and efficiently. Integrating these technologies ensures a rapid and reliable response to fire incidents. This study explores the design, implementation, and testing the autonomous drone platform, highlighting the challenges encountered and the solutions developed to address them. The findings suggest that integrating machine learning and autonomous navigation in fire response systems can lead to more effective and timely interventions, ultimately reducing the impact of fires on communities and infrastructure.
VoteChain: Promising a Secure and Transparent Election using Blockchain and Biometrics Vivekanandan G, Prabahar Godwin James T, Divya B, Madhav V Tejas, Naveen Karthick T K, Yuvanesh P 4th International Conference on Power Energy Control and Transmission Systems Harnessing Power and Energy for an Affordable Electrification of India Icpects 2024, 2024 Democratic voting is one of the significant aspects of governance that has various complications which are as follows; Complication arising from transparency Complication arising from low voter turnout Complication arising from vulnerability to the manipulation of the elections Complication arising from low confidence in the election process Complication arising from forgery of voter id cards Complication arising from delays in the announcement of the results Complication arising from security breach. All these issues erode the credibility of elections and public faith. To them, blockchain has a perfect solution in that it is decentralized, secure, transparent, and cannot be tampered with technology. To realize our e-voting system, we built an evoting application as a smart contract on the Ethereum platform using digital wallets and solidity. A given voter is assigned tokens (gas) which are utilized every time they cast their vote in order to eliminate vote forgeries and other undesirable incidents. This blockchain-based system does not require physical polling stations; also, voting is scalable and secure with flexible consensus algorithms, cryptographic hashing, and measures in response to a 51% attack. It also incorporates fingerprint scanning, to further discourage fraud and make sure that the process is completely secure and transparent. Since these records are stored in a blockchain, the ability of a single unscrupulous agency trying to manipulate the records is very hard given that records are validated by the nodes in the network, making the voting process more secure and credible.
Detection of Plant Diseases and Recommendation of Plant Cycle using Machine Learning Divya B, Alivn Ancy A, Vivekanandan G, Swapna A, Kaniha P, Indhu Priyadharshini S 4th International Conference on Power Energy Control and Transmission Systems Harnessing Power and Energy for an Affordable Electrification of India Icpects 2024, 2024 Plant diseases create significant challenges to productivity in agriculture, food security, and ecological stability. Pathogens and environmental variables interact to cause plant diseases. Pathogens include various microorganisms like bacteria, fungi, and viruses, each with unique modes of spread. Environmental conditions such as temperature, humidity, and soil quality impact disease development and severity. The impacts of plant diseases are far-reaching. It affects crop yields and quality. Outbreaks of plant diseases can lead to economic losses, and food shortages which ultimately lead to hunger and poverty. Effective management of plant diseases requires an integrated approach that combines detection, preventive measures, cultural practices, and chemical interventions. The solution has two modules. The first module focuses on detection of plant diseases and its management. The second module focuses on recommendations of the plant cycle. Our proposed system utilizes CNN algorithms trained on a large amount of datasets. Using image analysis the features are extracted and patterns are recognized. Therefore, the system can quickly identify the disorders.. The system also includes suggestions for preventive measures. The system integrates modules for recommending optimal plant cycles to the farmers and gardeners. It generates personalized recommendations for planting schedules and crop varieties. This system increases crop yields and decreases the risk of disease outbreaks. Our solution offers a holistic approach to plant health monitoring and management.
An IoT Enabled Smart Home Automation Using Augmented Reality in Computer Vision Senthil G. A, Divya B, R M Asha, Thara P, R Prabha, Rajesh Kanna. R International Conference on Self Sustainable Artificial Intelligence Systems Icssas 2023 Proceedings, 2023 Home Automation (HR) is the process of using technology to automate the various systems and appliances within a home. This technology is becoming more popular as it allows for greater convenience, efficiency, and safety within a household. In recent years, the introduction of Augmented Reality (AR) and an Internet of Things (IoT) technology enabled the development of even more innovative home automation solutions. This research article an overview of the advanced methodology of smart home automation enabled by AR and IoT. First, the article discusses the mechanisms and components that enable AR and IoT to be used for home automation. Next, the paper considers the potential applications of AR and IoT in home automation, such as home security, energy efficiency, and convenience. Furthermore, the paper reviews the challenges and opportunities associated with the use of AR and IoT in home automation. Finally, the paper provides some conclusions and proposals for further research. Overall, this paper demonstrates that the use of AR and IoT in home automation has the potential to revolutionize the way people live in their homes. The combination of AR and IoT in home automation also enhances safety and security, such as monitoring the home through IoT-enabled security cameras and smart locks and identifying potential security threats through AR. The integration of AR and IoT in home automation is transforming the way people live and work, making homes smarter, more efficient, and safer. This research work has proposed and implemented an IoT module to control home appliances using AR applications with the help of virtual buttons.
Indoor Navigation Using Ultra Wide Band Divya B, T Veeramakali, S Revathi, Harisharajan R R, Adhirooban D, Ebishdon G V 2023 Intelligent Computing and Control for Engineering and Business Systems Iccebs 2023, 2023
Network Traffic Analysis of cloud data centre Subbiah Sankari, Perumal Varalakshmi, Boopathi Divya Proceedings of the International Conference on Computing and Communications Technologies Iccct 2015, 2015
RECENT SCHOLAR PUBLICATIONS
Block Chain-Driven Secure Transaction & Settlement Network S Kavitha, B Divya International Journal of Advanced Research in Computer Science & Technology … , 2026 2026
An Analysis of Preprocessing Techniques for Disaster Management J Samraj, B Divya Proceedings of International Conference on Recent Innovations in Computing … , 2026 2026
Extended Reality in Healthcare K Anandan, P Kumar, B Divya, S Saranya, SR Lakshmi 2026
Hybrid brain computer interface structures to control drone in 3D B Divya, S Bharathi, GRM Babu, K Rajalakshmi, N Mohan International Journal of Medical Engineering and Informatics 18 (3), 207-216 , 2026 2026
Object Recognition for Visually Impaired Individuals Using Machine Learning with Feedback Mechanism in Real-Time B Divya, V Ananthi, AP Madhumidhaa, R Abinaya, S Poojasri 2025 IEEE 1st International Conference on Recent Trends in Computing and … , 2025 2025
BRAIN–COMPUTER INTERFACE USING P-300 SPELLER IN TAMIL LANGUAGE B Divya, A Kavitha, S Ragunathan, A Swetha Journal of Mechanics in Medicine and Biology, 2540112 , 2025 2025
Bridging the Yield Gap in Chilli Cultivation: Performance of Arka Harita Hybrid in Farmer's Field. B DIVYA, DK SURESH, NT NARESH, S PAVITHRA Mysore Journal of Agricultural Sciences 59 (4) , 2025 2025
Comparative Analysis of Realistic 3D Models for Vr Based Knee Surgery Simulation B Divya, A Kavitha, S Pravin Kumar, R Subathira 2025 3rd International Conference on Artificial Intelligence and Machine … , 2025 2025
AR-Guided Liver Surgery with Real Time Tool Tracking Approach P Kumar, A Kavitha, B Divya, P Sreeniveatha 2025 3rd International Conference on Artificial Intelligence and Machine … , 2025 2025 Citations: 1
Border Detection for Fishermen Using IoT B Divya, K Vijayalakshmi, J Priyadharshini, BB NaveenKrishna, ... 2024 International Conference on Power, Energy, Control and Transmission … , 2024 2024
Detection of Plant Diseases and Recommendation of Plant Cycle using Machine Learning B Divya, G Vivekanandan, A Swapna, P Kaniha, S Indhu Priyadharshini 2024 International Conference on Power, Energy, Control and Transmission … , 2024 2024
Votechain: Promising a secure and transparent election using blockchain and biometrics G Vivekanandan, B Divya, VT Madhav, TK Naveen Karthick, P Yuvanesh 2024 International Conference on Power, Energy, Control and Transmission … , 2024 2024 Citations: 2
Autonomous drone-based fire detection and suppression using YOLOv8 and 2D blueprint mapping for industrial applications K Vijayalakshmi, B Divya, T Prabahar Godwin James, S Sourav, ... 2024 International Conference on Power, Energy, Control and Transmission … , 2024 2024 Citations: 4
Subtitle Synchronization Using Whisper ASR Model P Thara, M Azneed, M Sanas, JP PM, HP Naik, B Divya 2024 International Conference on Power, Energy, Control and Transmission … , 2024 2024
A Hybrid Approach to Attendance Monitoring: Combining Geo Location and Facial Verification B Divya, R Ramya, S Hariharan, B Abishek, E Thangamuthu, ... 2024 International Conference on Power, Energy, Control and Transmission … , 2024 2024 Citations: 3
An Analysis of Preprocessing Techniques for Disaster Management with CNN-LSTM Model J Samraj, B Divya The International Conference on Recent Innovations in Computing, 123-140 , 2024 2024
Phytochemical and Pharmacological screening of Cosmos sulphureus, Ruellia simplex and Hibiscus rosa sinensis Flower Extracts for Antinociceptive activity Z Banu, A Qhursheed, A Alekya, B Shirisha, BV Mounika, B Divya Research Journal of Pharmacy and Technology 17 (7), 3399-3404 , 2024 2024 Citations: 9
An Effective Anti-Money Laundering System Using Block Chain Technology B Divya, P Thara, S Kavitha, A Alvin Ancy, R Preethi Sri, D Dhanalakshmi 2024 International Conference on Smart Systems for Electrical, Electronics … , 2024 2024 Citations: 1
Comparative analysis of deep learning algorithms integrated with blockchain for flood risk management B Divya, J Samraj 2024 2nd International Conference on Networking and Communications (ICNWC), 1-11 , 2024 2024 Citations: 1
AGE-BASED COMPARISON OF RESTING-STATE BRAIN ACTIVITY IN AUTISM SPECTRUM DISORDER: AN FMRI STUDY TV SANTHOSHIYA, R SOWMYA, BS SNEHA, A KAVITHA, B DIVYA INTERNATIONAL JOURNAL 1 (1) , 2024 2024
MOST CITED SCHOLAR PUBLICATIONS
Anti–ulcer activity of Ficus religiosa leaf ethanolic extract M Gregory, B Divya, RA Mary, MMH Viji, VK Kalaichelvan, V Palanivel Asian Pacific journal of tropical biomedicine 3 (7), 554-556 , 2013 2013 Citations: 101
Garden pea improvement in India N Mohan, TS Aghora, MA Wani, B Divya Journal of Horticultural Sciences 8 (2), 125-164 , 2013 2013 Citations: 35
Cognitive attention in autism using virtual reality learning tool S Vidhusha, B Divya, A Kavitha, RV Narayanan, D Yaamini 2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive … , 2019 2019 Citations: 24
Classification of low-functioning and high-functioning autism using task-based EEG signals B Divya, N Udayakumar, R Yuvaraj, A Kavitha Biomedical Signal Processing and Control 85, 105074 , 2023 2023 Citations: 20
Analysis of cognitive emotional and behavioral aspects of Alzheimer's disease using hybrid CNN model R Prabha, GA Senthil, P Suganthi, D Boopathi, M Razmah, A Lazha 2022 International Conference on Computer, Power and Communications (ICCPC … , 2022 2022 Citations: 19
LSTM method for human activity recognition of video using PSO algorithm M Razmah, R Prabha, A Naveen 2022 International Conference on Power, Energy, Control and Transmission … , 2022 2022 Citations: 17
Phytochemical and Pharmacological screening of Cosmos sulphureus, Ruellia simplex and Hibiscus rosa sinensis Flower Extracts for Antinociceptive activity Z Banu, A Qhursheed, A Alekya, B Shirisha, BV Mounika, B Divya Research Journal of Pharmacy and Technology 17 (7), 3399-3404 , 2024 2024 Citations: 9
Task specific brain synchronization in eeg based speech and speech imagery procedures R Anandha Sree, B Divya, A Kavitha Journal of Physics: Conference Series 1937 (1), 012044 , 2021 2021 Citations: 9
Effect of virtual reality on the EEG sub-band frequency powers of autistic and control groups S Chrisilla, A Masciantonio, B Divya, S Vidhusha, A Kavitha 2020 sixth international conference on bio signals, images, and … , 2020 2020 Citations: 8
Network traffic analysis of cloud data centre S Sankari, P Varalakshmi, B Divya 2015 International Conference on Computing and Communications Technologies … , 2015 2015 Citations: 8
Recognition of medicine using cnn for visually impaired R Monica, K Nirmala, B Divya, L Suganthi 2020 International Conference on Communication and Signal Processing (ICCSP … , 2020 2020 Citations: 7
Classification of credit card transactions using machine learning GA Senthil, R Prabha, RM Priya, D Boopathi, S Sridevi, P Suganthi 2022 International Conference on Computer, Power and Communications (ICCPC … , 2022 2022 Citations: 6
An empirical analysis and challenging era of blockchain in green society. Communication and intelligent systems. ICCIS 2022 B Divya, A Sathya Lecture Notes in Networks and Systems 689 , 2023 2023 Citations: 5
IoT based early flood detection using machine learning R Byali, B Divya, SV Maskikar, N Chitrashree, SH Bhonsle International Journal of Research Publication and Reviews 3 (7), 3780-3783 , 2022 2022 Citations: 5
SVM-based pest classification in agriculture field B Divya, M Santhi Int. J. Recent Technol. Eng 7, 150-155 , 2019 2019 Citations: 5
Autonomous drone-based fire detection and suppression using YOLOv8 and 2D blueprint mapping for industrial applications K Vijayalakshmi, B Divya, T Prabahar Godwin James, S Sourav, ... 2024 International Conference on Power, Energy, Control and Transmission … , 2024 2024 Citations: 4
An IoT Enabled Smart Home Automation Using Augmented Reality in Computer Vision B Divya, RM Asha, P Thara, R Prabha 2023 International Conference on Self Sustainable Artificial Intelligence … , 2023 2023 Citations: 4
Automatic Detection and Classification of Insects Using Hybrid FF-GWO-CNN Algorithm. B Divya, M Santhi Intelligent Automation & Soft Computing 36 (2) , 2023 2023 Citations: 4
An empirical analysis and challenging era of blockchain in green society GA Senthil, R Prabha, B Divya, A Sathya International Conference on Communication and Intelligent Systems, 195-206 , 2022 2022 Citations: 4
Quantitative measurements of brain activations in virtual reality environments B Divya, A Kavitha 2022 IEEE International Symposium on Medical Measurements and Applications … , 2022 2022 Citations: 4