Artificial Intelligence
Mahmut Dirik
Abstract
Fire, a natural calamity, poses a severe threat to human existence and is typically combated utilizing traditional measures. However, due to the limitations and potential environmental damage associated with these conventional strategies, there is a compelling need to devise innovative firefighting techniques. ...
Read More
Fire, a natural calamity, poses a severe threat to human existence and is typically combated utilizing traditional measures. However, due to the limitations and potential environmental damage associated with these conventional strategies, there is a compelling need to devise innovative firefighting techniques. Among these emergent strategies, fire suppression systems utilizing sound wave technologies present a promising alternative.In the present investigation, a comprehensive compilation of data harvested from a series of experimental trials focused on sound wave-based extinguishment was employed. Utilizing these data, a fire suppression model predicated on sound wave technologies was architectured, integrating five distinct fuzzy logic methodologies. These include Fuzzy Rough Set (FRS), Fuzzy K-nearest neighbors (FNN), Fuzzy ownership K-nearest neighbors (FONN), Fuzzy-rough K-nearest neighbors (FRNN), and Vaguely quantified K-nearest neighbors (VQNN).The ultimate goal of these models is to accurately discern between the extinguished and non-extinguished state of the flame. This classification is based on a variety of input parameters intrinsic to the model, such as fuel type, flame size, decibel level, frequency, airflow, and distance parameters.Evaluation of the models' classification efficacy was carried out through a combination of various statistical methods including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), kappa statistic (KP), and Mean Squared Error (MSE).The analysis yielded encouraging results, with FRS, FNN, FONN, FRNN, and VQNN models demonstrating classification accuracies of 93.12%, 96.66%, 95.56%, 96.35%, and 96.89% respectively. Hence, it was concluded that the proposed model exhibits high accuracy in classifying firefighting data, affirming its applicability.
Artificial Intelligence
Mehmet Karahan; Furkan Lacinkaya; Kaan Erdonmez; Eren Deniz Eminagaoglu; Cosku Kasnakoglu
Abstract
In recent years, development of the machine learning algorithms has led to the creation of intelligent surveillance systems. Thanks to the machine learning, it is possible to perform intelligent surveillance by recognizing people's facial features, classifying their age and gender, and detecting objects ...
Read More
In recent years, development of the machine learning algorithms has led to the creation of intelligent surveillance systems. Thanks to the machine learning, it is possible to perform intelligent surveillance by recognizing people's facial features, classifying their age and gender, and detecting objects around instead of ordinary surveillance. In this study, a novel algorithm has been developed that classifies people's age and gender with a high accuracy rate. In addition, a novel object recognition algorithm has been developed that detects objects quickly and with high accuracy. In this study, age and gender classification was made based on the facial features of people using Convolutional Neural Network (CNN) architecture. Secondly, object detection was performed using different machine learning algorithms and the performance of the different machine learning algorithms was compared in terms of median average precision and inference time. The accuracy of the age and gender classification algorithm was tested using the Adience dataset and the results were graphed. The experimental results show that age and gender classification algorithms successfully classify people's age and gender. Then, the performances of object detection algorithms were tested using the COCO dataset and the results were presented in graphics. The experimental results stress that machine learning algorithms can successfully detect objects.
