B DHANALAKSHMI

@crescent.education

Associate Professor, Department of Computer Science and Engineering
B.S.Abdur Rahman Crescent Institute of Science and Technology

B DHANALAKSHMI


               Download Compact PDF  
https://researchid.co/dhana.baskaran

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Computer Engineering, Computer Vision and Pattern Recognition, Computer Science Applications
19

Scopus Publications

92

Scholar Citations

4

Scholar h-index

3

Scholar i10-index

Scopus Publications

  • Smart farming with agri CNN-LSTM fusion: leveraging soil suitability analysis using real-time sensor data
    G. Srivarshini, M. Sujithra, B. Dhanalakshmi, K. Selvakumar
    Discover Applied Sciences, 2025
    Agri CNN-LSTM Fusion (Agricultural Convolutional Neural Network—Long Short-Term Memory Fusion) is an advanced model that uses real-time data from soil sensors to evaluate a soil's suitability for crop production. The model aims to resolve the issues with conventional farming methods by offering a data-driven substitute for spontaneity in decision-making. A significant research gap is a lack of an integrated method that incorporates temporal and spatial soil features for accurate classification. A data-intensive preprocessing workflow was used to process soil data obtained from the National Institute of Technology, Trichy field, through various sensors. Complex patterns in soil data are identified by this model, which is essential for a precise evaluation of soil health. Hyperparameter optimization further improves the model, which yields precise and consistent predictions that classify soil as “Fit” or “Not Fit” for crop cultivation. The experimental observations showed that AgriCNN-LSTMFusion attained an accuracy of 98.5%, establishing it as a dependable method for real-time soil suitability analysis. The model allows farmers to make informed decisions and optimize resource use by reducing uncertainty in soil assessment. By combining predictive modeling with soil sensor data, agricultural efficiency can be enhanced and sustainable growth encouraged.
  • Enhancing recruitment processes with brain-computer interface applications
    B. Dhanalakshmi, Nasiba Sherkuziyeva, Hameed Hassan Khalaf, Mohsen Aued Farhan, Melanie Elizabeth Lourens, Mohnish Kumar
    Concepts and Applications of Brain Computer Interfaces, 2025
    The integration of brain-computer interface (BCI) technology into recruitment processes offers a novel approach to assessing candidate suitability with greater precision and objectivity. By leveraging BCI applications, recruiters can gain insights into cognitive and emotional responses during various stages of the hiring process, including interviews, assessments, and simulations. This approach allows for the evaluation of traits such as stress management, cognitive flexibility, and decision-making skills in real-time, thus enabling a more comprehensive understanding of a candidate's potential. Additionally, BCI can help mitigate unconscious bias by focusing on neural responses rather than subjective judgments. This chapter explores the potential of BCI technology to revolutionize recruitment by enhancing the accuracy of candidate evaluations, improving the quality of hires, and ultimately leading to more efficient and effective recruitment strategies.
  • The development of the multi-layer security network authentication system using machine learning
    B. Dhanalakshmi, P. William, Anupama Chadha, Karumuru Venkat Tiru Gopal Reddy, Mohit Tiwari, Tripti Tiwari
    Interdisciplinary Approaches to AI Internet of Everything and Machine Learning, 2024
    Researchers and business owners place significant importance on the security of IoT networks as it directly affects the availability of IoT services and the privacy of connected users. To address this concern, an intrusion detection system is used to identify and thwart attacks and to provide multi-layer security. In this study, a novel system is developed of multi-layer Security network authentication system using machine learning. This approach combines algorithm for security network authentication system. Additionally, an oversampling technique is employed to improve the quality of classification results.Various experiments were conducted with different layers, as well as two distinct techniques for developing authentication system.
  • Analysing of diverse Stress pattern in ECG using Machine Learning Techniques
    Anbarasi S, Dhanalakshmi B
    Iet Conference Proceedings, 2024
    ECG signals are commonly used to diagnose various cardiac conditions, and the classification of these signals is an important task in Stress identification. With the advancement of ML techniques, several ML models have been developed to classify ECG signals with high accuracy. This paper aims to review recent studies that use ML models for ECG classification, equivalence to the working nature of different prototype, and discuss the challenges and limitations of these models. The study found that deep learning models, such as CNNs and RNNs, outperformed traditional ML models in terms of closeness and validity. The results also showed that the combination of multiple models could improve the classification performance. However, the study also highlighted the need for large annotated ECG datasets and the requirement of domain expertise for feature engineering. Overall, this review provides a complete analysis of the current state of ECG classification using ML models and identifies areas for future research and improvement. Even though the accuracy of ML models in ECG classification is not always perfect, they can still provide valuable information and support to healthcare professionals. In some cases, even a lower accuracy can still be useful, especially in the context of large-scale screening and monitoring programs, where the goal is to identify individuals who require further evaluation. In these cases, the high computational speed and scalability of ML models make them an attractive option, as they can quickly process large amounts of data and provide preliminary results that can be followed up with more comprehensive and accurate tests. Additionally, the results from ML models can also be used as a starting point for further analysis by healthcare professionals, who can use their domain knowledge to interpret the results and make informed decisions. Therefore, despite their limitations, ML models can still play an vital role in the field of Electrocardiogram classification and contribute to improving patient outcomes.
  • Soil Health Intelligence System using Multispectral Imaging and Advanced Deep Learning Techniques (SHIDS-ADLT)
    B. Dhanalakshmi
    Communications on Applied Nonlinear Analysis, 2024
    The Soil Health Intelligence System using Multispectral Imaging and Advanced Deep Learning Techniques (SHIDS-ADLT) is a cutting-edge solution designed to revolutionize the assessment and management of soil health. By leveraging the power of multispectral imaging, this system captures high-resolution data across various wavelengths, providing a comprehensive view of soil properties. Advanced deep learning algorithms are then applied to analyze this data, identifying patterns and insights that are not discernible through traditional methods. This integration of multispectral imaging with deep learning enhances the accuracy and efficiency of soil health monitoring, enabling precise identification of nutrient deficiencies, soil contamination, and other critical parameters that affect agricultural productivity.SHIDS-ADLT offers a scalable and user-friendly platform for farmers, agronomists, and researchers, facilitating informed decision-making and sustainable agricultural practices. The system’s ability to provide real-time analysis and actionable recommendations ensures that soil health is maintained at optimal levels, promoting higher crop yields and reducing the reliance on chemical fertilizers. Moreover, the continuous monitoring capabilities of SHIDS-ADLT help in early detection of soil degradation, allowing for timely interventions. This innovative approach to soil health management represents a significant advancement in agricultural technology, supporting the goal of achieving food security and environmental sustainability.
  • Analysis of Network Technologies and Cyber security Assessment for Enhancing Machine Learning, Grid Computing and Cyber-Physical Connectivity Internetwork Effectiveness
    B. Dhanalakshmi, Chaitanya Singh, S. Surya, Atharav Hedage, Shikha Kuchhal, Korakod Tongkachok
    Proceedings of 2nd International Conference on Innovative Practices in Technology and Management Iciptm 2022, 2022
    The fast improvement of the Internet has incredibly worked with individuals spreading information worldwide, prompting the Internet turning into a pivotal apparatus in many fields like science, trade, schooling, etc. With the Internet common in such countless parts of day to day existence, network security has become basic and requests consistent consideration. For this situation, an IDS's motivation is to recognize between real organization associations and possibly hurtful ones. The recommended method in this examination centers around an interruption identification and avoidance system that comprises of Cloudlet Controller (CC), Trust Authority (TA), and Virtual Machine Manager to recognize questionable practices in a cloud climate. Cloud clients are migrated to different regions in the climate, as indicated by our proposed approach. Whenever information bundles from different clients are gathered, network traffic happens. To resolve this issue, we assembled the Cloudlet Controller, which gets bundles from different clients through switch. CC gets parcels until they arrive at their edge level; if the cloudlet is over-burden, the bundles are shipped off inactive cloudlets. In this philosophy, network traffic is decreased, and it is significantly helpful in identifying interruptions in a straightforward way. In this review, a cross breed arrangement based interruption location and counteraction framework on the cloud is worked to distinguish gatecrasher exercises in the framework. A cross breed characterization based interruption location framework is created with a few cloudlets, a cloudlet regulator, a confided in power, and a virtual machine supervisor to distinguish interloper assaults in the framework, as well as a deterrent instrument to safeguard bundles from gatecrashers.
  • Intelligent energy-aware and secured QoS routing protocol with dynamic mobility estimation for wireless sensor networks
    B. Dhanalakshmi, L. SaiRamesh, K. Selvakumar
    Wireless Networks, 2021
  • Role of attribute selection on tuning the learning performance of parkinson’s data using various intelligent classifiers
    K. Alice, Kanimozhi Natesan, B. Dhanalakshmi, K. Jaisharma
    International Journal of Advanced Technology and Engineering Exploration, 2021
    Dr James Parkinson first defined the Parkinson's Disease (PD) as "shaking palsy" in 1817. PD is one of the most common neurological syndromes of the central nervous system. It is a serious disease targeting aged persons above 60 years of age. PD is identified as a brain disorder [1] that causes the nerve cells to be lost or impaired. These impaired or lost nerve cells will stop the dopamine fluid production in the area of Substantia Nigra. Dopamine is an essential chemical fluid in the brain, which makes nerve cells passes the message to other nerve cells. Due to the lack of dopamine, information has to pass to another nerve cell to be stopped.
  • Improving cognitive learning of children with dyspraxia using selection based mid-air gestures in athynos game
    B. Dhanalakshmi, R. Dhanagopal, D. Raguraman, T. Thamdapani
    Proceedings of the 3rd International Conference on Intelligent Sustainable Systems Iciss 2020, 2020
    Computer-generated graphics are digitally enhanced videos for implementing imagery having virtuality in the real world. Dyspraxia affected children have poor hand-eye synchronization and no improvements in their cognitive skills. Proper guidance and cognitive skill-developing strategies are to be implemented in treating Dyspraxia children. The motor tasks can be performed and improvements can be monitored for children with dyspraxia by playing augmented reality serious games. A new game with augmented reality named Athynos is introduced. Hardware components like sensors(ultrasound sensors) are used to bring the virtuality in the Athynos game through the air selection process. The hand movements of the dyspraxia child are capture by the ultrasound sensor and using the Arduino the captured actions are transfer to the system as the input. The result of the dyspraxia children is analyzed by three or more trials and the report is calculated using the deep learning algorithm (linear regression). Playing active games (Athynos) act as a psychotherapy tool for the dyspraxia disorder children. Athynos games using augmented reality help improving and upgrading the skills that develop cognitive learning and hand-eye synchronization for the children affected with dyspraxia.
  • Automated Vehicle Number Plate Recognition System using Stability Score and K-Means Clustering Algorithm
    B. Dhanalakshmi, R. Ramesh, D. Raguraman, R. Menaka
    Proceedings of the 4th International Conference on Electronics Communication and Aerospace Technology Iceca 2020, 2020
    Due to the increase in vehicle usage, itis a challenging task to monitor, analyze the vehicles by a human for security purposes. There is a need for an automatic vehicle recognition system since various places nowadays have checkpoints for vehicles, to track the stolen vehicles, and to monitor traffic violations. The problem exists when the vehicle number plate is encountered in different formats, different scales, and illumination to number-plates. In the case of an indeterminate situation, identifying vehicle number plates in poor lighting conditions and worse traffic situations can be analyzed using an automatic vehicle number plate recognition system. The vehicle name board edge finding techniques are used to easily identify the vehicle number in the name board. A dataset with 200 license plates has been collected as training datasets for recognition, estimation, and identification, thus improving system accuracy of recognition when compared to existing works. The training input samples include images of vehicle number plates taken from the traffic department. The automated vehicle number recognition system is improvised in terms of accuracy by estimating stability score and using the k-means clustering algorithm.
  • Reduction of water consumption in agriculture smart farms based on internet of things (IoT)
    International Journal of Control and Automation, 2020
  • Adaptive ann-pso algorithm on tensile stress prediction for the dissimilar fsw butt joints of aa6061-az61 alloy
    International Journal of Advanced Science and Technology, 2020
  • Power management strategy and power theft detection using internet of things (Iot)
    International Journal of Advanced Science and Technology, 2020
  • Nourishing Indian Economy-through Curriculum Change in Rural Schools
    M.D. Vijayakumar, V. Dhinakaran, B. Dhanalakshmi, P M Bupathi ram, K. Surendar
    2020 6th International Conference on Advanced Computing and Communication Systems Icaccs 2020, 2020
  • Analyzing student's performance using efficient opinion mining and ranking method with machine learning techniques
    B. Dhanalakshmi, A. Chandrasekar
    Journal of Computational and Theoretical Nanoscience, 2018
  • Optimal neural network to enhance classification accuracy for mining online reviews and opinions using improved PSO
    B. Dhanalakshmi, Arumugam Chandra Sekar
    International Journal of Networking and Virtual Organisations, 2018
  • Clustering based text summarization on comments from hotel services using IncreSTS algorithm
    B Dhanalakshmi, A Chandrasekar
    Journal of Computational and Theoretical Nanoscience, 2017
  • Qualitative risk avoidance methodology for categorization of mined opinions from online reviews
    B. Dhanalakshmi, A. Chandrasekar
    6th International Conference on Advanced Computing Icoac 2014, 2015
  • Fast and efficient opinion mining technique for online reviews using ranking and classification algorithms
    International Review on Computers and Software, 2013

RECENT SCHOLAR PUBLICATIONS

  • Smart farming with agri CNN-LSTM fusion: leveraging soil suitability analysis using real-time sensor data
    G Srivarshini, M Sujithra, B Dhanalakshmi, K Selvakumar
    Discover Applied Sciences 7 (10), 1151 , 2025
    2025
    Citations: 4
  • The Development of the Multi-Layer Security Network Authentication System Using Machine Learning
    B Dhanalakshmi, P William, A Chadha, KVTG Reddy, M Tiwari, T Tiwari
    Interdisciplinary Approaches to AI, Internet of Everything, and Machine … , 2025
    2025
  • Enhancing Recruitment Processes With Brain-Computer Interface Applications
    B Dhanalakshmi, N Sherkuziyeva, HH Khalaf, MA Farhan, ME Lourens, ...
    Concepts and Applications of Brain-Computer Interfaces, 273-286 , 2025
    2025
  • Analysing of diverse stress pattern in ECG using machine learning techniques
    S Anbarasi, B Dhanalakshmi
    2nd International Conference on Computer Vision and Internet of Things … , 2024
    2024
  • Babycare warning system based on IoT and GSM to prevent leaving a child in a parked car
    MA Kumar, FS Mahammad, P Bhaskar, G Vani, B Umamaheswari, ...
    AIP Conference Proceedings 3028 (1), 020071 , 2024
    2024
    Citations: 16
  • Human activity recognition through images using a deep learning approach
    L SaiRamesh, B Dhanalakshmi
    2024
    Citations: 2
  • Soil Health Intelligence System using Multispectral Imaging and Advanced Deep Learning Techniques (SHIDS-ADLT)
    B Dhanalakshmi
    Communications on Applied Nonlinear Analysis , 2024
    2024
    Citations: 4
  • Healthcare therapy for treating teenagers with internet addiction using behavioral patterns and neuro-feedback analysis
    B Dhanalakshmi, K Selvakumar, LS Ramesh
    Advances in Cyber Security and Intelligent Analytics, 249-260 , 2022
    2022
  • Analysis of Network Technologies and Cyber security Assessment for Enhancing Machine Learning, Grid Computing and Cyber-Physical Connectivity Internetwork Effectiveness
    B Dhanalakshmi, C Singh, S Surya, A Hedage, S Kuchhal, K Tongkachok
    2nd International Conference on Innovative Practices in Technology and … , 2022
    2022
  • Role of attribute selection on tuning the learning performance of Parkinson’s data using various intelligent classifiers
    K Alice, K Natesan, B Dhanalakshmi, K Jaisharma
    International Journal of Advanced Technology and Engineering Exploration 8 … , 2021
    2021
    Citations: 3
  • Intelligent energy-aware and secured QoS routing protocol with dynamic mobility estimation for wireless sensor networks
    B Dhanalakshmi, L SaiRamesh, K Selvakumar
    Wireless Networks 27 (2), 1503-1514 , 2021
    2021
    Citations: 47
  • Improving cognitive learning of children with dyspraxia using selection based mid-air gestures in athynos game
    B Dhanalakshmi, R Dhanagopal, D Raguraman, T Thamdapani
    2020 3rd International Conference on Intelligent Sustainable Systems (ICISS … , 2020
    2020
    Citations: 10
  • Automated Vehicle Number Plate Recognition System using Stability Score and K-Means Clustering Algorithm
    B Dhanalakshmi, R Ramesh, D Raguraman, R Menaka
    2020 4th International Conference on Electronics, Communication and … , 2020
    2020
    Citations: 1
  • Design and Performance Analysis of Multi-Leaf Spring Using Glass Fiber Reinforced Plastic-Metal Matrix Composite
    D Raguraman, B Dhanalakshmi, V Dhinakaran, R Ravinder
    Journal of Computational and Theoretical Nanoscience 17 (8), 3694-3700 , 2020
    2020
  • Nourishing Indian Economy-through Curriculum Change in Rural Schools
    MD Vijayakumar, V Dhinakaran, B Dhanalakshmi, K Surendar
    2020 6th International Conference on Advanced Computing and Communication … , 2020
    2020
  • Efficient Resource Utilization by Reducing Broker Cost Using Multi-Objective Optimization
    BK Dhanalakshmi, KC Srikantaiah, KR Venugopal
    Integrated Intelligent Computing, Communication and Security, 533-538 , 2018
    2018
    Citations: 1
  • Analyzing Student's Performance Using Efficient Opinion Mining and Ranking Method with Machine Learning Techniques
    B Dhanalakshmi, A Chandrasekar
    Journal of Computational and Theoretical Nanoscience 15 (2), 480-484 , 2018
    2018
    Citations: 1
  • Optimal neural network to enhance classification accuracy for mining online reviews and opinions using improved PSO
    B Dhanalakshmi, AC Sekar
    International Journal of Networking and Virtual Organisations 18 (4), 338-356 , 2018
    2018
    Citations: 1
  • Clustering Based Text Summarization on Comments from Hotel Services Using IncreSTS Algorithm
    B Dhanalakshmi, A Chandrasekar
    Journal of Computational and Theoretical Nanoscience 14 (9), 4496-4501 , 2017
    2017
  • Qualitative risk avoidance methodology for categorization of mined opinions from online reviews
    B Dhanalakshmi, A Chandrasekar
    2014 Sixth International Conference on Advanced Computing (ICoAC), 167-171 , 2014
    2014

MOST CITED SCHOLAR PUBLICATIONS

  • Intelligent energy-aware and secured QoS routing protocol with dynamic mobility estimation for wireless sensor networks
    B Dhanalakshmi, L SaiRamesh, K Selvakumar
    Wireless Networks 27 (2), 1503-1514 , 2021
    2021
    Citations: 47
  • Babycare warning system based on IoT and GSM to prevent leaving a child in a parked car
    MA Kumar, FS Mahammad, P Bhaskar, G Vani, B Umamaheswari, ...
    AIP Conference Proceedings 3028 (1), 020071 , 2024
    2024
    Citations: 16
  • Improving cognitive learning of children with dyspraxia using selection based mid-air gestures in athynos game
    B Dhanalakshmi, R Dhanagopal, D Raguraman, T Thamdapani
    2020 3rd International Conference on Intelligent Sustainable Systems (ICISS … , 2020
    2020
    Citations: 10
  • Smart farming with agri CNN-LSTM fusion: leveraging soil suitability analysis using real-time sensor data
    G Srivarshini, M Sujithra, B Dhanalakshmi, K Selvakumar
    Discover Applied Sciences 7 (10), 1151 , 2025
    2025
    Citations: 4
  • Soil Health Intelligence System using Multispectral Imaging and Advanced Deep Learning Techniques (SHIDS-ADLT)
    B Dhanalakshmi
    Communications on Applied Nonlinear Analysis , 2024
    2024
    Citations: 4
  • Role of attribute selection on tuning the learning performance of Parkinson’s data using various intelligent classifiers
    K Alice, K Natesan, B Dhanalakshmi, K Jaisharma
    International Journal of Advanced Technology and Engineering Exploration 8 … , 2021
    2021
    Citations: 3
  • Human activity recognition through images using a deep learning approach
    L SaiRamesh, B Dhanalakshmi
    2024
    Citations: 2
  • Automated Vehicle Number Plate Recognition System using Stability Score and K-Means Clustering Algorithm
    B Dhanalakshmi, R Ramesh, D Raguraman, R Menaka
    2020 4th International Conference on Electronics, Communication and … , 2020
    2020
    Citations: 1
  • Efficient Resource Utilization by Reducing Broker Cost Using Multi-Objective Optimization
    BK Dhanalakshmi, KC Srikantaiah, KR Venugopal
    Integrated Intelligent Computing, Communication and Security, 533-538 , 2018
    2018
    Citations: 1
  • Analyzing Student's Performance Using Efficient Opinion Mining and Ranking Method with Machine Learning Techniques
    B Dhanalakshmi, A Chandrasekar
    Journal of Computational and Theoretical Nanoscience 15 (2), 480-484 , 2018
    2018
    Citations: 1
  • Optimal neural network to enhance classification accuracy for mining online reviews and opinions using improved PSO
    B Dhanalakshmi, AC Sekar
    International Journal of Networking and Virtual Organisations 18 (4), 338-356 , 2018
    2018
    Citations: 1
  • Enhanced Discoverability of content through linked data for online reviews using classification and ranking techniques
    B Dhanalakshmi, AC Sekar
    IJCA Proceedings on National Conference on Recent Advances in Information … , 2014
    2014
    Citations: 1
  • Managing risk and enhancing discoverability of opinion from online reviews using Classification Algorithm
    B Dhanalakshmi, AC Sekar
    International Journal of Emerging Technology and Advanced Engineering 4 (2 … , 2014
    2014
    Citations: 1
  • The Development of the Multi-Layer Security Network Authentication System Using Machine Learning
    B Dhanalakshmi, P William, A Chadha, KVTG Reddy, M Tiwari, T Tiwari
    Interdisciplinary Approaches to AI, Internet of Everything, and Machine … , 2025
    2025
  • Enhancing Recruitment Processes With Brain-Computer Interface Applications
    B Dhanalakshmi, N Sherkuziyeva, HH Khalaf, MA Farhan, ME Lourens, ...
    Concepts and Applications of Brain-Computer Interfaces, 273-286 , 2025
    2025
  • Analysing of diverse stress pattern in ECG using machine learning techniques
    S Anbarasi, B Dhanalakshmi
    2nd International Conference on Computer Vision and Internet of Things … , 2024
    2024
  • Healthcare therapy for treating teenagers with internet addiction using behavioral patterns and neuro-feedback analysis
    B Dhanalakshmi, K Selvakumar, LS Ramesh
    Advances in Cyber Security and Intelligent Analytics, 249-260 , 2022
    2022
  • Analysis of Network Technologies and Cyber security Assessment for Enhancing Machine Learning, Grid Computing and Cyber-Physical Connectivity Internetwork Effectiveness
    B Dhanalakshmi, C Singh, S Surya, A Hedage, S Kuchhal, K Tongkachok
    2nd International Conference on Innovative Practices in Technology and … , 2022
    2022
  • Design and Performance Analysis of Multi-Leaf Spring Using Glass Fiber Reinforced Plastic-Metal Matrix Composite
    D Raguraman, B Dhanalakshmi, V Dhinakaran, R Ravinder
    Journal of Computational and Theoretical Nanoscience 17 (8), 3694-3700 , 2020
    2020
  • Nourishing Indian Economy-through Curriculum Change in Rural Schools
    MD Vijayakumar, V Dhinakaran, B Dhanalakshmi, K Surendar
    2020 6th International Conference on Advanced Computing and Communication … , 2020
    2020