A5021374414- COVID-19 diagnosis using AI
- Artificial Intelligence in Healthcare
- Network Security and Intrusion Detection
- Information and Cyber Security
- Online Learning and Analytics
- Advanced Malware Detection Techniques
- Face recognition and analysis
- EEG and Brain-Computer Interfaces
- Face and Expression Recognition
- Anomaly Detection Techniques and Applications
- Non-Invasive Vital Sign Monitoring
- Smart Systems and Machine Learning
- Digital Marketing and Social Media
- Internet of Things and AI
- Industrial Vision Systems and Defect Detection
- Energy Efficient Wireless Sensor Networks
- Digital Transformation in Industry
- Imbalanced Data Classification Techniques
- IoT-based Smart Home Systems
- Traffic Prediction and Management Techniques
- Consumer Retail Behavior Studies
- Human Mobility and Location-Based Analysis
- Online and Blended Learning
- AI in Service Interactions
- Cloud Data Security Solutions
Koneru Lakshmaiah Education Foundation
2022-2025
Manipur University
2025
Shri Jagdishprasad Jhabarmal Tibrewala University
2023
University of Mumbai
2019-2021
Dr. Sarvepalli Radhakrishnan Rajasthan Ayurved University
2018
Emotion and gender recognition are important areas of research in the field computer vision human-computer interaction. The proposed CNN architecture is designed to extract features from facial images classify them into six basic emotions (happy, sorrow, anger, fear, surprise, disgust) two genders (male female) real-time. To categorize characteristics photographs, suggested consists convolutional layers, pooling fully connected layers. system performs at cutting edge for both emotion tasks...
Customer Churn prediction is one of the key problems for businesses trying to retain their valuable customers and want increase profitability. This study used XGBoost, an effective Machine Learning code, create a customer churn model with historical behavioural data. The delivers balanced high performing across all metrics accommodate accuracy 91.50%, as well precision, recall F1-scores non-churn class. Feature importance analysis identified features contributing including tenure, monthly...
The loan approval process has undergone changes with the evolution of financial technology, which necessitates an economic approach to decision making (efficient and accurate for underwriters) equitable one as well. Abstract —This paper is a fitting introduction machine learning (ML) techniques when goal improve prediction approvals. Integrating this information state-of-the-art algorithms data analytics, we have developed strong framework that lends credibility applications on basis various...
In this research article the researcher emphasized on rapid expansion of digital landscape, security networked systems has become a paramount concern. Network intrusions, which involve unauthorized access and malicious activities, pose significant threats to confidentiality, integrity, availability sensitive information. To counter these threats, intrusion detection (IDS) play crucial role in identifying mitigating such intrusions. recent times, machine learning algorithms have gained...
Introduction: In this research article the researcher proposed a gender-based Text-to-Speech (TTS) system that uses specific voices to simulate either male or female speech, offering variety of and accents match user's needs. These systems can be integrated into various applications create more natural-sounding, customized speech outputs. The main goal is make synthetic eminently plausible natural sounding, closer human in terms suitability for context sound quality. Objectives: This study...
In this research article the researcher emphasized Network threats and hazards are evolving at a high-speed rate in recent years. Many mechanisms (such as firewalls, anti-virus, anti-malware, spam filters) being used security tools to protect networks. An intrusion detection system (IDS) is also an effective powerful network detect unauthorized abnormal traffic flow. This presents review of trends network-based systems (NIDS), their approaches, most common datasets evaluate IDS Models. The...
Manual vulnerability evaluation tools produce erroneous data and lead to difficult analytical thinking. Such security concerns are exacerbated by the variety, imperfection, redundancies of modern repositories. These problems were common traits producers public disclosures, which make it more identify flaws through direct analysis Internet Things (IoT). Recent breakthroughs in Machine Learning (ML) methods promise new solutions each these infamous diversification asymmetric information...
Automation and robotics have advanced significantly with the introduction of Industry 4.0, revolutionizing manufacturing environment. This study examines evolution product quality in context concentrating on how robotic AI-driven automation technologies help to increase productivity. systems can efficiently analyze enormous volumes data by integrating AI algorithms machine learning capabilities, allowing for real-time monitoring production process optimization. Utilizing automation,...
Reliability is a crucial performance metric for wireless sensor networks (WSNs) because it ensures network functionality even with degraded nodes and connections. Due to the limited availability of power resources associated nodes, their efficacy reduced. In addition, parameters such as number neighbours, packet success rate, size, node capacity have significant impact on how function. Similarly, inter-node distance signal-to-noise ratio (SNR) greatest influence functioning communications in...
Purpose The uncertainty of getting admission into universities/institutions is one the global problems in an academic environment. students are having good marks with highest credential, but they not sure about their universities/institutions. In this research study, researcher builds a predictive model using Naïve Bayes classifiers – machine learning algorithm to extract and analyze hidden pattern students’ records credentials. main purpose study reduce for based on previous credentials...
In order to properly control rabbles, we shall investigate computer vision and mechanical aid technologies with lending devices here. Machine intelligence, commonly referred as AI, or algorithms, enables software improve prediction performance while requiring a deliberate goal do so. Machine-learning algorithms anticipate new output using historical data their input. Since information is so crucial, creating novel approaches for effectively administering the neighbourhood, pervasive...
Businesses can offer support to customers outside of usual business hours and across time zones by employing chatbots, which provide round-the-clock support. Chatbots react user inquiries quickly, reducing wait times improving customer satisfaction. It becomes challenging for the chatbot differentiate between two queries that users pose carry same meaning, making it harder understand appropriately. The aim this research is develop a capable understanding semantic meaning questions as well...
In the contemporary landscape of multi-service computing, optimizing Quality Service (QoS) is paramount for ensuring both user satisfaction and system efficiency. Traditional methods QoS optimization often fall short in dynamically adapting to complexities service-oriented architectures. This paper introduces a novel approach utilizing Egret Swarm Optimization (ESO) automated extraction values service correlation mapping. The proposed method leverages unique characteristics ESO efficiently...
Classification, preprocessing, feature extraction, and segmentation are all parts of the planned study that will be utilized to categories detect brain tumor pictures. Magnetic resonance imaging (MRI) gives direct information about anatomical structures as well possibly abnormal tissues where patients being watched by physicians, making identification not much simpler for clinical diagnosis. This suggested system utilizes a machine learning strategy identify, tumors known gliomas. Kirsch's...
With the integration of Internet Things (IoT) devices and demand for effective decision-making methods, cyber-physical systems (CPS) are getting more complicated. In CPS, machine learning (ML) has become a potent technique processing analyzing massive volumes data. The problem remains in optimizing ML algorithms to accomplish quick accurate decision-making. To overcome this difficulty, we provide novel strategy paper that integrates with Particle Swarm Optimisation (PSO) IoT. suggested...
Due to the fast advancement of technology, cybercrime is also increasing in frequency and complexity. Since a variety attacks evolves regularly with complex patterns varied signatures task securing cyberspace becomes more difficult challenging. To minimize impact through early detection intrusions, network activity terms traffic, monitored real-time thus accumulating huge data which sometimes erroneous. In order create efficient security algorithms for attack detection, it crucial combine...