Advanced Computational Approaches to Gun Detection with CNN-SVM Model

This study tries to marry Convolutional Neural Networks (CNN) and Support Vector Machine (SVN) techniques to form a very advanced gun identification system. The system's unique feature is that it is designed to see five categories of weapons. This was done by carefully evaluating the validity of the model using various performance parameters tailored according to individual classes, which demonstrated the ability of the model to withstand and its precise nature. The model's performance for Class 1 was as follows: An accuracy of 89.91%, a recall of 88.29%, and an F1-score of 89.09%. In class 2, an accuracy rate of 91.64%, a recall of 91.08%, and a mean value of the F1-score of 91.36% were obtained. The combination of parameters classifying Class 3 was corroborated with an accuracy of 93.84%, a completeness of 94.96%, and an F1-score of 94.40%. The accuracy rate for Class 4 was 96.69%, the recall rate was 95.38%, and the F1 score was 96.03%. The experimental results of class 5 showed excellent precision of 97.70%, recall of 99%, and F1-score of 98.35%. We used the macro, micro, and weighted averages to help us evaluate the performance of all the classes. The macro averages for precision, recall, and F1-score were 93.96, 93.74, and 93.85%, respectively. It should be noted that the weighted averaged results showed firm persuasion with the accuracy, precision, and F scores of 1-94.90%,94.92%, and 94.91%, respectively. With subsequent micro-averages, accuracy, recall, and over-equal scores, they remained at 94.92%, reflecting the model's consistent performance in all classes. Our model performed interestingly, with a total system accuracy value of 94.9185%. The results highlight the accuracy achieved in perceiving guns in these CNN-SVM hybrid models and suggest that such advanced systems may have further benefits for the protection and security of the general population. Our study's robust methodology and impeccable weapon detection achieve optimal results, making it one of the first research trends in weapons detection technology.