Miriyala Aruna Safali
Research Subjects
Miriyala Aruna Safali has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Anupama Anumolu
DVR Dr.HS MIC College of Technology,Department of Mathamatics,Vijayawada,AP,India
1 shared publicationChittineni Suneetha
Associate Professor, Rvr & Jc College Of Engineering, Guntur,India
1 shared publication- Ha Huy Cuong Nguyen
The University of Da Nang
1 shared publication Kbs Sastry
Lecturer, Andhra Loyola College (Autonomous), Vijayawada-8
1 shared publication- Nguyen Trong Tung
Dong A University
1 shared publication - Putti Venkata Siva Teja
Research Scholar, Department of Mechanical Engineering, Annamalai University, Annamalai Nagar, Chidambaram, Tamil Nadu, India
1 shared publication
Latest Publications
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 17-21
Data-Driven Thermal Behavior Prediction Using Machine Learning
This paper investigates the thermal behavior of Titanium-6AI-4V alloy under thermal cycling at 427° C, with cycle counts of $\mathbf{0}, \mathbf{5 0 0}, \mathbf{1 0 0 0}$, and $\mathbf{1 5 0 0}$. Using Differential Scanning Calorimetry (DSC), heat capacity and total heat trends are analyzed across a temperature range of $-100^{\circ} \mathrm{C}$ to 300° C to identify phase transformations and degradation patterns. Machine learning models, including Support Vector Machines, Decision Trees, and Random Forest, predict material behavior for cycles beyond 1500, offering insights into thermal stability and failure temperature estimation. The work demonstrates the feasibility of data-driven approaches in predicting material degradation, reducing reliance on extensive experimental testing, and aiding aerospace material design.- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 17-21
Data-Driven Thermal Behavior Prediction Using Machine Learning
This paper investigates the thermal behavior of Titanium-6AI-4V alloy under thermal cycling at 427° C, with cycle counts of $\mathbf{0}, \mathbf{5 0 0}, \mathbf{1 0 0 0}$, and $\mathbf{1 5 0 0}$. Using Differential Scanning Calorimetry (DSC), heat capacity and total heat trends are analyzed across a temperature range of $-100^{\circ} \mathrm{C}$ to 300° C to identify phase transformations and degradation patterns. Machine learning models, including Support Vector Machines, Decision Trees, and Random Forest, predict material behavior for cycles beyond 1500, offering insights into thermal stability and failure temperature estimation. The work demonstrates the feasibility of data-driven approaches in predicting material degradation, reducing reliance on extensive experimental testing, and aiding aerospace material design.- Open Access
- 1 October 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (5) , 5550-5559
Security and risk analysis in the cloud with software defined networking architecture
Cloud computing has emerged as the actual trend in business information technology service models, since it provides processing that is both cost-effective and scalable. Enterprise networks are adopting software-defined networking (SDN) for network management flexibility and lower operating costs. Information technology (IT) services for enterprises tend to use both technologies. Yet, the effects of cloud computing and software defined networking on business network security are unclear. This study addresses this crucial issue. In a business network that uses both technologies, we start by looking at security, namely distributed denial-of-service (DDoS) attack defensive methods. SDN technology may help organizations protect against DDoS assaults provided the defensive architecture is structured appropriately. To mitigate DDoS attacks, we offer a highly configurable network monitoring and flexible control framework. We present a dataset shift-resistant graphic model-based attack detection system for the new architecture. The simulation findings demonstrate that our architecture can efficiently meet the security concerns of the new network paradigm and that our attack detection system can report numerous threats using real-world network data.
- 1 October 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (5) , 5550-5559
Open AccessSecurity and risk analysis in the cloud with software defined networking architecture
Cloud computing has emerged as the actual trend in business information technology service models, since it provides processing that is both cost-effective and scalable. Enterprise networks are adopting software-defined networking (SDN) for network management flexibility and lower operating costs. Information technology (IT) services for enterprises tend to use both technologies. Yet, the effects of cloud computing and software defined networking on business network security are unclear. This study addresses this crucial issue. In a business network that uses both technologies, we start by looking at security, namely distributed denial-of-service (DDoS) attack defensive methods. SDN technology may help organizations protect against DDoS assaults provided the defensive architecture is structured appropriately. To mitigate DDoS attacks, we offer a highly configurable network monitoring and flexible control framework. We present a dataset shift-resistant graphic model-based attack detection system for the new architecture. The simulation findings demonstrate that our architecture can efficiently meet the security concerns of the new network paradigm and that our attack detection system can report numerous threats using real-world network data.
- 2 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1639-1643
A Hybrid-Layered Framework for Detection and Diagnosis of Alzheimer’s Disease (AD) from Fundus Images
Alzheimer’s disease (AD) is the most common disease that can cause a brain disorder in a human aged above 65. Detecting and diagnosing AD becomes a more complicated and complex task by using various manual processes. DL and ML algorithms are most widely used to analyze the complex features from the medical data used to detect AD from various samples. Several types of sample formats are used to detect AD. This paper mainly focused on detecting the AD from the retinal fundus images. Analyzing the early symptoms of AD can prevent the patient’s life from permanent eye loss. ML algorithms are having various drawbacks that use complex computations and more computation time for the processing of data. The AD prediction is done by using the fundus color images collected from the Kaggle dataset. ML follows various steps to complete the task such as training, pre-processing and algorithm implementation. In the existing approaches, a limited number of parameters are used. Another disadvantage of the traditional algorithms shows the low accuracy and unmatched results. This paper introduced the hybrid-layered framework is developed to detect the AD from the fundus images dataset. Several performance metrics such as precision, recall, F1-score, and accuracy are used to show the results.
- 2 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1639-1643
A Hybrid-Layered Framework for Detection and Diagnosis of Alzheimer’s Disease (AD) from Fundus Images
Alzheimer’s disease (AD) is the most common disease that can cause a brain disorder in a human aged above 65. Detecting and diagnosing AD becomes a more complicated and complex task by using various manual processes. DL and ML algorithms are most widely used to analyze the complex features from the medical data used to detect AD from various samples. Several types of sample formats are used to detect AD. This paper mainly focused on detecting the AD from the retinal fundus images. Analyzing the early symptoms of AD can prevent the patient’s life from permanent eye loss. ML algorithms are having various drawbacks that use complex computations and more computation time for the processing of data. The AD prediction is done by using the fundus color images collected from the Kaggle dataset. ML follows various steps to complete the task such as training, pre-processing and algorithm implementation. In the existing approaches, a limited number of parameters are used. Another disadvantage of the traditional algorithms shows the low accuracy and unmatched results. This paper introduced the hybrid-layered framework is developed to detect the AD from the fundus images dataset. Several performance metrics such as precision, recall, F1-score, and accuracy are used to show the results.
- Open Access
- 1 May 2019
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1228 (1) , 012009
Ensemble feature analysis classifier for sentiment analysis using convolutional neural networks
Text mining is the worldwide fast growing domain in research. Sentiment analysis is the one of the sub domain in the text mining to extract the sentiment from the various texts available in the internet and from other sources. Various existing systems are implemented to get the sentiment analysis with the migration of natural language processing algorithms (NLP) and artificial intelligence algorithms.Various issues identified in the text mining with sentiment analysis are solved very rarely. According to the previous research, deep-learning and artificial intelligencebased TSA prediction method that comprises of a stacked auto encoder (SAE) model that is used to learn generic linguistic and text semantic features But the system not reached up to the mark. In this paper, Ensemble Feature Analysis Classifier to incorporate the new domain dimension within the rating and text based sentiment analyzer. Implementation of this proposed prototype validates our claim and highlights our efficiency in supporting multiple dimensions during sentiment analysis.
- 1 May 2019
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1228 (1) , 012009
Open AccessEnsemble feature analysis classifier for sentiment analysis using convolutional neural networks
Text mining is the worldwide fast growing domain in research. Sentiment analysis is the one of the sub domain in the text mining to extract the sentiment from the various texts available in the internet and from other sources. Various existing systems are implemented to get the sentiment analysis with the migration of natural language processing algorithms (NLP) and artificial intelligence algorithms.Various issues identified in the text mining with sentiment analysis are solved very rarely. According to the previous research, deep-learning and artificial intelligencebased TSA prediction method that comprises of a stacked auto encoder (SAE) model that is used to learn generic linguistic and text semantic features But the system not reached up to the mark. In this paper, Ensemble Feature Analysis Classifier to incorporate the new domain dimension within the rating and text based sentiment analyzer. Implementation of this proposed prototype validates our claim and highlights our efficiency in supporting multiple dimensions during sentiment analysis.
- Open Access
- 1 May 2019
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1228 (1) , 012010
A. Amalgamative sentiment analysis framework on social networking site
Sentiment analysis is the most widely used in many applications. Knowing the sentiment analysis for any of the dataset becomes most important to know the sentiment for the given inputs. In this paper, the amalgamative sentiment analysis framework developed for dividing the positive and negative emotions taken from the user’s tweets. In this system, an integrated social networking is developed which is integrated with ASAF. Results show the classification of these tweets.
- 1 May 2019
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1228 (1) , 012010
Open AccessA. Amalgamative sentiment analysis framework on social networking site
Sentiment analysis is the most widely used in many applications. Knowing the sentiment analysis for any of the dataset becomes most important to know the sentiment for the given inputs. In this paper, the amalgamative sentiment analysis framework developed for dividing the positive and negative emotions taken from the user’s tweets. In this system, an integrated social networking is developed which is integrated with ASAF. Results show the classification of these tweets.