Some bands in the frequency spectrum have become overloaded and others underutilized due to the considerable increase in demand and user allocation policy. Cognitive radio applies detection techniques to dynamically allocate unlicensed users. Cooperative spectrum sensing is currently showing promising results. Therefore, in this work, we propose a cooperative spectrum detection system based on a residual neural network architecture combined with feature extractor and random forest classifier. The objective of this paper is to propose a cooperative spectrum sensing approach that can achieve high accuracy in higher levels of noise power density with less unlicensed users cooperating in the system. Therefore, we propose to extract features of the sensing information of each unlicensed user, then we use a random forest to classify if there is a presence of a licensed user in each band analyzed by the unlicensed user. Then, information from several unlicensed users are shared to a fusion center, where the decision about the presence or absence of a licensed user is accomplished by a model trained by a residual neural network. In our work, we achieved a high level of accuracy even when the noise power density is high, which means that our proposed approach is able to recognize the presence of a licensed user in of the cases when the evaluated channel suffers a high level of noise power density ( dBm/Hz). This result was achieved with the cooperation of 10 unlicensed users.
Frequency spectrum allocation has been a subject of dispute in recent years. Cognitive radio dynamically allocates users to spectrum holes using various sensing techniques. Noise levels and distances between users can significantly impact the efficiency of cognitive radio systems. Designing robust communication systems requires accurate knowledge of these factors. This paper proposes a method for predicting noise levels and distances based on spectrum sensing signals using regression machine learning models. The proposed methods achieved correlation coefficients of over and for noise and distance predictions, respectively. Accurately estimating these parameters enables adaptive resource allocation, interference mitigation, and improved spectrum efficiency, ultimately enhancing the performance and reliability of cognitive radio networks.
In communication systems, noise is almost invariably present, originating from a multitude of sources and variables. These sources include thermal effects, interference, quantization, and channel imperfections, contributing to the random nature of noise. Determining noise levels is crucial and remains a pervasive challenge in communication systems, especially in recent times when better utilization of spectrum sensing is required. In this paper, we propose a noise estimation method based on deep learning using spectrograms extracted from wireless signals. The proposed method achieved promising results using several state-of-art computer vision architectures.
Manufacturing TVs and monitors requires an effective method to detect the dead pixels. These defects are usually identified by operators manually. However, manual inspection is susceptible to failure due to human fatigue and generate a high cost for production process. In this work, conducted by three partners (UFAM/CETELI, ICTS and ENVISION/TPV), we propose three methods for automated detection of dead pixels. Two proposed methods were based on machine learning (ML) techniques, random forest (RF) and support vector machine (SVM) algorithms. The third method was based in digital image processing (DIP), Harris algorithm. As result, the SVM obtained the better performance with 92.1% of precision in two of three used image database.
The frequency spectrum allocation has been a subject of dispute in recent years. Cognitive Radio dynamically allocates users to spectrum holes using various sensing techniques. Noise levels and distances between users can significantly impact the efficiency of cognitive radio systems. Designing robust communication systems requires accurate knowledge of these factors. This paper proposes a method for predicting noise levels and distances based on spectrum sensing signals using regression machine learning models. The proposed methods achieved correlation coefficients of over 0.98 and 0.82 for noise and distance prediction, respectively. Accurately estimating these parameters enables adaptive resource allocation, interference mitigation, and improved spectrum efficiency, ultimately enhancing the performance and reliability of cognitive radio networks.