The Internet of Things (IoT) is an indispensable part of the healthcare system since it creates a link between the doctor and the patient for remote medical consultations. IoT-based seizure prediction detects the seizures and monitors the health of patients remotely. The disease seizure is categorized with the sudden and repeated malfunction of the neurons of the brain. To protect patient's lives, it's critical to recognise the risk of an epileptic seizure. In this research a hybrid cuckoo finch optimization is proposed tuned Deep-CNN (Deep-Convolutional Neural Network) classifier recognize and predict the occurrence of epileptic seizure using the electroencephalogram (EEG) signal data obtained through IoT. Initially, the gathered data is pre-processed and subjected to frequency band generation. Then there are the notable characteristics, such as Statistical features, Wavelet features, Entropy-based features, Spectral features, CPR (Common Spatial Patterns) and Logarithmic band power are extracted and concatenated. The optimal electrode selection is done by using the proposed hybrid cuckoo finch optimization that inherits characteristics of the intrusive and attentive search agents. The data is finally normalized and fed to proposed hybrid cuckoo finch optimization tuned Deep-CNN to classify the seizure disease. The specificity, accuracy and sensitivity of the proposed model is attained as 92.5212%, 97.7648%, and 95.6324%, which demonstrates efficient performance of the proposed seizure prediction model.