Skip to content
Log in

Author

K. Ashwini

h-index 0 View on Semantic Scholar

We have 3 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Jul 2026

GAS LEAKAGE AND FIRE DETECTION AND FIRE DETECTION +SMR NOTIFICATION

Gas leakage and fire accidents represent major safety threats in residential buildings, commercial establishments, industrial facilities, laboratories, kitchens, warehouses, and other enclosed environments where combustible gases and ignition sources are present. Conventional safety mechanisms frequently depend on isolated smoke alarms, manual inspection, fixed threshold detectors, or locally activated buzzers that may fail to provide timely remote information when occupants or responsible personnel are away from the affected location. Delayed identification of liquefied petroleum gas leakage, combustible gas accumulation, abnormal temperature rise, smoke formation, or open flame can lead to explosions, structural damage, environmental contamination, financial loss, severe injury, and loss of life. This research proposes an intelligent Gas Leakage and Fire Detection with SMS Notification System that integrates gas sensing, flame detection, temperature monitoring, embedded processing, local alarm generation, actuator control, and GSM-based remote notification within a unified real-time safety architecture. The proposed framework continuously acquires environmental information through an MQ-series combustible gas sensor, flame sensor, and temperature sensor. Sensor readings are processed by a microcontrollerbased decision unit that performs signal conditioning, threshold evaluation, multi-sensor event correlation, and hazard classification. The system categorizes environmental conditions into Normal, Gas Leakage Alert, Fire Warning, and Critical Emergency states according to the detected combination of gas concentration, flame presence, and abnormal temperature behavior. When hazardous gas accumulation is identified, the system activates a local buzzer, warning indicator, ventilation or exhaust mechanism, and GSM communication module to transmit an SMS notification to registered users or emergency personnel. When fire-related indicators are detected, the framework generates an immediate high-priority alarm and sends location-aware emergency information through SMS. The proposed architecture consists of five interconnected layers: Environmental Sensing and Data Acquisition, Signal Processing and Hazard Intelligence, Embedded Decision and Event Classification, Alert and Emergency Response, and User and Monitoring layers. The framework is designed to provide continuous monitoring, rapid hazard recognition, local and remote notification, improved response coordination, and practical deployment across homes, industries, laboratories, warehouses, kitchens, and commercial facilities. Illustrative conceptual evaluation demonstrates that the proposed system can achieve improved detection accuracy, alert reliability, multi-sensor hazard recognition, and lower response latency compared with conventional standalone gas alarms, smoke-only detectors, and isolated threshold-based systems. The proposed framework provides a scalable foundation for intelligent environmental safety monitoring and timely emergency communication.

M. Venkatesh, K. Ashwini, Punnapuredd Y Roja et al. · 0 citations
Conference Jul 2026

Efficient Machine Learning Approaches for Intrusion Detection Systems in Cyber Security

The rapid expansion and spread of networked systems and digital services has tremendously expanded the complexity and frequency of cyberattacks, and conventional security tools are no longer relevant to contemporary cyber threats. Intrusion Detection Systems (IDS) are very important in detection of malicious activities, but the traditional signature based and rule-based IDS are limited in that they have high false-positive, cannot be able to detect the attacks of the zeroday, and fail to be adapted to changing patterns of threats. The recent developments in machine learning (ML) have brought intelligent and adaptive methods that can learn the complicated patterns based on large volumes of network traffic data. This paper provides an in-depth analysis of effective machine learning methods to intrusion detection system in cybersecurity. The paper compares the efficacy of supervised, unsupervised and ensemble-based ML algorithms that conduct intrusion detection with enhanced accuracy, lowered computation load, and improved scalability. It focuses on the feature selection, dimensionality reduction, and model optimization to enhance the detecting performance and retain the capability of running it in real-time. In the results, the hybrid and ensemble models of machine learning prove to be much more efficient than the conventional IDS methods and provide a strong protection against the current cyber threats. This research contributes toward developing intelligent, adaptive, and efficient IDS frameworks suitable for contemporary and future cybersecurity infrastructures.

K. Ashwini, M. Supriya · 0 citations
#edge computing Open access Aug 2026

Post quantum blockchain framework using probabilistic hidden state deep learning for smart IoT systems

Scalability analysis demonstrates that the proposed Post-Quantum Probabilistic Hidden-State Deep Learning framework, evaluated with run on IoT networks with over 1000 nodes, exhibits significant performance.

T. G. Keshavamurthy, S. Guruprasad, K. Hareesh et al. · 0 citations