Hussain Azath
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Hussain Azath has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Pandimurugan Vellaisamy
Acharya University, Uzbekistan
2 shared publications A. Jayapradha
Sri Krishna College of Engineering and Technology, Coimbatore, India
1 shared publication- Ananya Das1 shared publication
- D. Beulah David
Saveetha School of Engineering, SIMATS
1 shared publication D. Sivakumar
Raja Rajeswari College of Engineering, Bengaluru, India
1 shared publicationE. Chandra Blessie
Coimbatore Institute of Technology, Coimbatore, India
1 shared publication
Latest Publications
- Open Access
- 9 July 2026
- Published by VFAST Research Platform in VFAST Transactions on Software Engineering
- Vol. 14 (3) , 548-568
Towards Adaptive Energy Intelligence using Deep Learning based Battery Management and Charging Duration Optimization for Electric Vehicles
Electric vehicles (EVs) are central to the shift toward a greener, more sustainable global economy, yet optimal charging-duration prediction and efficient battery management remain persistent challenges. Estimating a battery's remaining life span helps users gauge driving range, while accurately forecasting charging energy needs benefits manufacturers and owners alike improving usage rates, cutting costs, and easing the load on electric grid stations. Station-level energy consumption is also shaped by factors such as EV adoption trends, plug-in timing, random usage patterns, and differences between holidays and working days. To address overcharging, energy wastage, and the broader challenge of managing dispatch stations through data-driven analysis, this paper proposes a Deep Stacking Ensemble for Battery Management and Optimal Charging Duration in Electric Vehicles (DSEBM-OCDEV). The method aims to build an intelligent battery management framework that predicts optimal charging duration using a hybrid ensemble learning approach. Raw battery data are first pre-processed through outlier removal, categorical encoding, and feature scaling for consistency and stability. Correlation-based feature selection then identifies the most informative battery attributes while reducing redundancy and computational overhead. For charging-duration classification, a stacking ensemble combines a variational graph autoencoder, a spiking neural network, and a double deep Q-network, with their outputs merged through a meta-learner optimized using AdamW to improve convergence and generalization. Extensive simulation results confirm that DSEBM-OCDEV consistently outperforms existing methods.
- 9 July 2026
- Published by VFAST Research Platform in VFAST Transactions on Software Engineering
- Vol. 14 (3) , 548-568
Open AccessTowards Adaptive Energy Intelligence using Deep Learning based Battery Management and Charging Duration Optimization for Electric Vehicles
Electric vehicles (EVs) are central to the shift toward a greener, more sustainable global economy, yet optimal charging-duration prediction and efficient battery management remain persistent challenges. Estimating a battery's remaining life span helps users gauge driving range, while accurately forecasting charging energy needs benefits manufacturers and owners alike improving usage rates, cutting costs, and easing the load on electric grid stations. Station-level energy consumption is also shaped by factors such as EV adoption trends, plug-in timing, random usage patterns, and differences between holidays and working days. To address overcharging, energy wastage, and the broader challenge of managing dispatch stations through data-driven analysis, this paper proposes a Deep Stacking Ensemble for Battery Management and Optimal Charging Duration in Electric Vehicles (DSEBM-OCDEV). The method aims to build an intelligent battery management framework that predicts optimal charging duration using a hybrid ensemble learning approach. Raw battery data are first pre-processed through outlier removal, categorical encoding, and feature scaling for consistency and stability. Correlation-based feature selection then identifies the most informative battery attributes while reducing redundancy and computational overhead. For charging-duration classification, a stacking ensemble combines a variational graph autoencoder, a spiking neural network, and a double deep Q-network, with their outputs merged through a meta-learner optimized using AdamW to improve convergence and generalization. Extensive simulation results confirm that DSEBM-OCDEV consistently outperforms existing methods.
- Open Access
- 8 October 2025
- Published by MECS Publisher in International Journal of Wireless and Microwave Technologies
- Vol. 15 (5) , 21-33
Integration of Cyber Threat Hunting and SocioPolitical Risk Assessment for a Hybrid PredictiveModel for Enhanced Global Security
The new and emerging challenges posed by the convergence of cyber threats and socio-political tensions have risen as one of the core formidable threats to the present global security landscape. This paper proposes a hybrid predictive model intended to act against these real-world multidimensional attack vectors. The model integrates cyber threat hunting techniques with socio-political risk assessment methodologies to comprehensively forecast consequent cybersecurity threats to social unrest scenarios. Cyber threat data is collected from sources such as the Offensive Defensive-Intrusion Detection System (OD-IDS2022) and the Aegean Wi-Fi Intrusion Dataset (AWID3), and social terror attack information is gathered from the Global Database of Events, Language, and Tone (GDLET) Project and Armed Conflict Location & Event Data (ACLED) to comprise the bidirectional dataset for the model that contains views from both cyber and socio-political risk landscapes. The model adopts a holistic, robust predictive capability through k-fold cross-validation and feature importance evaluation implementation techniques. This multidisciplinary approach offers a synoptic understanding of emerging and future security threats and enables the execution of proactive measures to secure national and transnational borders.
- 8 October 2025
- Published by MECS Publisher in International Journal of Wireless and Microwave Technologies
- Vol. 15 (5) , 21-33
Open AccessIntegration of Cyber Threat Hunting and SocioPolitical Risk Assessment for a Hybrid PredictiveModel for Enhanced Global Security
The new and emerging challenges posed by the convergence of cyber threats and socio-political tensions have risen as one of the core formidable threats to the present global security landscape. This paper proposes a hybrid predictive model intended to act against these real-world multidimensional attack vectors. The model integrates cyber threat hunting techniques with socio-political risk assessment methodologies to comprehensively forecast consequent cybersecurity threats to social unrest scenarios. Cyber threat data is collected from sources such as the Offensive Defensive-Intrusion Detection System (OD-IDS2022) and the Aegean Wi-Fi Intrusion Dataset (AWID3), and social terror attack information is gathered from the Global Database of Events, Language, and Tone (GDLET) Project and Armed Conflict Location & Event Data (ACLED) to comprise the bidirectional dataset for the model that contains views from both cyber and socio-political risk landscapes. The model adopts a holistic, robust predictive capability through k-fold cross-validation and feature importance evaluation implementation techniques. This multidisciplinary approach offers a synoptic understanding of emerging and future security threats and enables the execution of proactive measures to secure national and transnational borders.
- 9 July 2025
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 44 (12) , 9154-9179
LC-VVC: Design of Low-Cost Versatile Video Coding Standard Based on Optimized Motion Estimation and Transform Blocks
- 9 July 2025
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 44 (12) , 9154-9179
LC-VVC: Design of Low-Cost Versatile Video Coding Standard Based on Optimized Motion Estimation and Transform Blocks
- RetractedOpen Access
- 2 March 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-11
A Versatile and Ubiquitous IoT-Based Smart Metabolic and Immune Monitoring System
In the present medical age, the focus on prevention and prediction is achieved using the medical internet of things. With a broad and complete framework, effective behavioral, environmental, and physiological criteria are necessary to govern the major healthcare sectors. Wearables play an essential role in personal health monitoring data measurement and processing. We wish to design a variable and flexible frame for broad parameter monitoring in accordance with the convenient mode of wearability. In this study, an innovative prototype with a handle and a modular IoT portal is designed for environmental surveillance. The prototype examines the most significant parameters of the surroundings. This strategy allows a bidirectional link between end users and medicine via the IoT gateway as an intermediate portal for users with IoT servers in real time. In addition, the doctor may configure the necessary parameters of measurements via the IoT portal and switch the sensors on the wearables as a real-time observer for the patient. Thus, based on goal analysis, patient situation, specifications, and requests, medications may define setup criteria for calculation. With regard to privacy, power use, and computation delays, we established this system’s performance link for three common IoT healthcare circumstances. The simulation results show that this technique may minimize processing time by 25.34%, save energy level up to 72.25%, and boost the privacy level of the IoT medical device to 17.25% compared to the benchmark system.
- 2 March 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-11
RetractedOpen AccessA Versatile and Ubiquitous IoT-Based Smart Metabolic and Immune Monitoring System
In the present medical age, the focus on prevention and prediction is achieved using the medical internet of things. With a broad and complete framework, effective behavioral, environmental, and physiological criteria are necessary to govern the major healthcare sectors. Wearables play an essential role in personal health monitoring data measurement and processing. We wish to design a variable and flexible frame for broad parameter monitoring in accordance with the convenient mode of wearability. In this study, an innovative prototype with a handle and a modular IoT portal is designed for environmental surveillance. The prototype examines the most significant parameters of the surroundings. This strategy allows a bidirectional link between end users and medicine via the IoT gateway as an intermediate portal for users with IoT servers in real time. In addition, the doctor may configure the necessary parameters of measurements via the IoT portal and switch the sensors on the wearables as a real-time observer for the patient. Thus, based on goal analysis, patient situation, specifications, and requests, medications may define setup criteria for calculation. With regard to privacy, power use, and computation delays, we established this system’s performance link for three common IoT healthcare circumstances. The simulation results show that this technique may minimize processing time by 25.34%, save energy level up to 72.25%, and boost the privacy level of the IoT medical device to 17.25% compared to the benchmark system.
- 28 January 2022
- Published by Springer Nature in Wireless Personal Communications
- Vol. 123 (3) , 2227-2243
Identification of IoT Device From Network Traffic Using Artificial Intelligence Based Capsule Networks
- 28 January 2022
- Published by Springer Nature in Wireless Personal Communications
- Vol. 123 (3) , 2227-2243
Identification of IoT Device From Network Traffic Using Artificial Intelligence Based Capsule Networks
- 11 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 221-225
BoT-IoT based Denial of Service Detection with Deep Learning
With a sharp rise in the number of internet connected devices, the internet has turned into a necessity for human life. Everyday human life and activities are becoming dependent on Internet of Things (IoT) devices in particular. However, the challenges faced by these IoT devices in terms of data security have been increasing with no well-defined solutions. With the increasing security challenges, several techniques are developed to ensure safe data transfer over IoT networks. Despite these efforts, data breach is observed on a regular basis. The use of machine learning schemes is an optimal solution to enhance the data security in IoT networks. Several deep-learning and machine-learning schemes are discussed in this paper along with standard datasets that may be used for enhancing the IoT network security performance. A deep learning algorithm-based model is developed in this paper for detection of denial-of-service (DoS) attacks. Seaborn, TensorFlow, and scikit-learn python packages are used for this purpose. Efficient attack mitigation and improved accuracy is observed using the proposed model on IoT networks.
- 11 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 221-225
BoT-IoT based Denial of Service Detection with Deep Learning
With a sharp rise in the number of internet connected devices, the internet has turned into a necessity for human life. Everyday human life and activities are becoming dependent on Internet of Things (IoT) devices in particular. However, the challenges faced by these IoT devices in terms of data security have been increasing with no well-defined solutions. With the increasing security challenges, several techniques are developed to ensure safe data transfer over IoT networks. Despite these efforts, data breach is observed on a regular basis. The use of machine learning schemes is an optimal solution to enhance the data security in IoT networks. Several deep-learning and machine-learning schemes are discussed in this paper along with standard datasets that may be used for enhancing the IoT network security performance. A deep learning algorithm-based model is developed in this paper for detection of denial-of-service (DoS) attacks. Seaborn, TensorFlow, and scikit-learn python packages are used for this purpose. Efficient attack mitigation and improved accuracy is observed using the proposed model on IoT networks.
- Open Access
- 14 April 2021
- Published by Institution of Engineering and Technology (IET) in IET Software
- Vol. 15 (3) , 230-238
Enhanced framework for ensemble effort estimation by using recursive‐based classification
Service‐oriented software engineering is a software engineering methodology focussed on the development of software systems. The systematic application of technological and scientific knowledge depends on the methodology, experience, design for obtaining efficient implementation, testing and software documentation. Software effort estimation (SEE) plays an essential role in reusable service for ensembling the effort estimation of the software development. Effort estimation is the most efficient process applied in software engineering for the prediction of effort. SEE methods are utilised to achieve the effort, cost and human resources with the assistance of the dataset. It is hard to predict the cost, effort, size and schedule consistently through SEE and hence it causes damage to software enterprises. To overwhelm these limitations, an enhanced support vector regression algorithm is used that extracts the features and delivers the relevant features. This algorithm is used to standardise for main features and is related to the supervised learning algorithms. From this, the best features are extracted followed by the elimination of weakest features using the enhanced recursive elimination algorithm. From the selected features, an enhanced random forest classification is used to classify the results. The outcomes are executed to offer the best accuracy and thereby providing efficient prediction of effort estimation. Finally, the performance is measured with parameters such as Magnitude of Balanced Relative Error (MBRE), mean absolute residual, mean inverted balanced relative error, mean magnitude of error relative and mean magnitude of relative error. On comparing the existing methodologies, it is concluded that the proposed work offers better efficiency.
- 14 April 2021
- Published by Institution of Engineering and Technology (IET) in IET Software
- Vol. 15 (3) , 230-238
Open AccessEnhanced framework for ensemble effort estimation by using recursive‐based classification
Service‐oriented software engineering is a software engineering methodology focussed on the development of software systems. The systematic application of technological and scientific knowledge depends on the methodology, experience, design for obtaining efficient implementation, testing and software documentation. Software effort estimation (SEE) plays an essential role in reusable service for ensembling the effort estimation of the software development. Effort estimation is the most efficient process applied in software engineering for the prediction of effort. SEE methods are utilised to achieve the effort, cost and human resources with the assistance of the dataset. It is hard to predict the cost, effort, size and schedule consistently through SEE and hence it causes damage to software enterprises. To overwhelm these limitations, an enhanced support vector regression algorithm is used that extracts the features and delivers the relevant features. This algorithm is used to standardise for main features and is related to the supervised learning algorithms. From this, the best features are extracted followed by the elimination of weakest features using the enhanced recursive elimination algorithm. From the selected features, an enhanced random forest classification is used to classify the results. The outcomes are executed to offer the best accuracy and thereby providing efficient prediction of effort estimation. Finally, the performance is measured with parameters such as Magnitude of Balanced Relative Error (MBRE), mean absolute residual, mean inverted balanced relative error, mean magnitude of error relative and mean magnitude of relative error. On comparing the existing methodologies, it is concluded that the proposed work offers better efficiency.
- Open Access
- 10 January 2018
- Published by Walter de Gruyter GmbH in Journal of Intelligent Systems
- Vol. 29 (1) , 251-263
Software Effort Estimation Using Modified Fuzzy C Means Clustering and Hybrid ABC-MCS Optimization in Neural Network
In a software development process, effective cost estimation is the most challenging activity. Software effort estimation is a crucial part of cost estimation. Management cautiously considers the efforts and benefits of software before committing the required resources to that project or order for a contract. Unfortunately, it is difficult to measure such preliminary estimation, as it has only little information about the project at an early stage. In this paper, a new approach is proposed; this is based on reasoning by the soft computing approach to calculate the effort estimation of the software. In this approach, rules are generated based on the input dataset. These rules are then clustered for better estimation. In our proposed method, we use modified fuzzy C means for clustering the dataset. Once the clustering is done, various rules are obtained and these rules are given as the input to the neural network. Here, we modify the neural network by incorporating optimization algorithms. The optimization algorithms employed here are the artificial bee colony (ABC), modified cuckoo search (MCS), and hybrid ABC-MCS algorithms. Hence, we obtain three optimized sets of rules that are used for the effort estimation process. The performance of our proposed method is investigated using parameters such as the mean absolute relative error and mean magnitude of relative error.
- 10 January 2018
- Published by Walter de Gruyter GmbH in Journal of Intelligent Systems
- Vol. 29 (1) , 251-263
Open AccessSoftware Effort Estimation Using Modified Fuzzy C Means Clustering and Hybrid ABC-MCS Optimization in Neural Network
In a software development process, effective cost estimation is the most challenging activity. Software effort estimation is a crucial part of cost estimation. Management cautiously considers the efforts and benefits of software before committing the required resources to that project or order for a contract. Unfortunately, it is difficult to measure such preliminary estimation, as it has only little information about the project at an early stage. In this paper, a new approach is proposed; this is based on reasoning by the soft computing approach to calculate the effort estimation of the software. In this approach, rules are generated based on the input dataset. These rules are then clustered for better estimation. In our proposed method, we use modified fuzzy C means for clustering the dataset. Once the clustering is done, various rules are obtained and these rules are given as the input to the neural network. Here, we modify the neural network by incorporating optimization algorithms. The optimization algorithms employed here are the artificial bee colony (ABC), modified cuckoo search (MCS), and hybrid ABC-MCS algorithms. Hence, we obtain three optimized sets of rules that are used for the effort estimation process. The performance of our proposed method is investigated using parameters such as the mean absolute relative error and mean magnitude of relative error.
- 10 August 2012
- Published by Institution of Engineering and Technology (IET) in IET Software
- Vol. 6 (4) , 335-341
Efficient effort estimation system viz. function points and quality assurance coverage
Software development effort estimation is important for quality management in the software development industry, yet its automation still remains a challenging issue. Accurate estimation of software effort is critical in software engineering. Existing methods for software cost estimation will use very few quality factors for the estimation. So, in order to overcome this drawback, the authors proposed an efficient effort estimation system based on quality assurance coverage. This study is a basis for the improvement of software effort estimation research through a series of quality attributes along with constructive cost model (COCOMO). The classification of software system for which the effort estimation is to be calculated based on COCOMO classes. For this quality assurance ISO 9126 quality factors are used and for the weighing factors the function point metric is used as an estimation approach. Effort is estimated for MS word 2007 using the following models: Albrecht and Gaffney model, Kemerer model, SMPEEM model (Software Maintenance Project Effort Estimation Model and FP Matson, Barnett and Mellichamp model.
- 10 August 2012
- Published by Institution of Engineering and Technology (IET) in IET Software
- Vol. 6 (4) , 335-341
Efficient effort estimation system viz. function points and quality assurance coverage
Software development effort estimation is important for quality management in the software development industry, yet its automation still remains a challenging issue. Accurate estimation of software effort is critical in software engineering. Existing methods for software cost estimation will use very few quality factors for the estimation. So, in order to overcome this drawback, the authors proposed an efficient effort estimation system based on quality assurance coverage. This study is a basis for the improvement of software effort estimation research through a series of quality attributes along with constructive cost model (COCOMO). The classification of software system for which the effort estimation is to be calculated based on COCOMO classes. For this quality assurance ISO 9126 quality factors are used and for the weighing factors the function point metric is used as an estimation approach. Effort is estimated for MS word 2007 using the following models: Albrecht and Gaffney model, Kemerer model, SMPEEM model (Software Maintenance Project Effort Estimation Model and FP Matson, Barnett and Mellichamp model.