Malkapuram Ramya,Mrs. J. Shilpa 03 06 The escalating frequency of natural and manmade disasters demands intelligent automated frameworks capable of detecting emergencies in real time This paper presents the Unified Emergency Condition Detection UECD system an integrated platform that fuses Internet of Things IoT sensor networks convolutional neural networks CNN and deep neural networks DNN to detect classify and communicate diverse emergency conditions including fires gas leaks seismic events health crises and vehicular accidents The proposed architecture employs a hybrid CNNDNN model trained on structured multisensor datasets encompassing temperature smoke vibration heartrate and gasconcentration readings achieving a detection accuracy of 967 with a false alarm rate below 18 A Random Forest baseline achieves 934 accuracy while the hybrid deep model surpasses it by leveraging both spatial feature extraction and sequential decision boundaries Sensor data fusion across heterogeneous modalities substantially reduces ambiguity and false positives The system generates geotagged severityranked alerts distributed via SMS email and mobile push notifications to relevant authorities within subsecond latency An experimental Flaskbased web interface demonstrates realtime prediction dataset management and model loading capabilities Experimental results indicate that the UECD system achieves superior performance compared to stateoftheart singlemodality emergency detection approaches The system is scalable to smart city deployments healthcare environments and industrial facilities representing a significant advancement toward fully autonomous emergency management infrastructure Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026