Cognitive radio (CR) is the trending domain in addressing the inadequate bands for communication, and spectrum sensing is the hectic challenge need to be addressed extensively. In the conventional CRs, the communication is restricted to the secondary users (SUs) in the allocated bands causing the underutilization of the available band. Thus, with the aim to afford higher throughput and spectrum efficiency, this paper introduces the hybrid mixture model for spectrum sensing in the multiple-input–multiple-output (MIMO) systems and the effectiveness is evaluated based on the evaluation parameters, such as detection probability and probability of false alarm. The signal received through the orthogonal frequency-division multiplexing (OFDM) antenna is employed for analyzing the spectral availability for which the energy and Eigen statistics of the signal is generated, which forms the input to the Hybrid mixture model. The developed Hybrid mixture model is the integration of the Gaussian Mixture Model (GMM) and Whale Elephant-Herd Optimization (WEHO). The GMM is subjected to the optimal tuning using the WEHO, which is the modification of the standard Whale Optimization Algorithm (WOA) with the Elephant-Herd Optimization (EHO). The analysis reveals that the proposed spectrum sensing model acquired the maximal detection probability and minimal false alarm probability of 99.9% and 46.4%, respectively. The proposed hybrid mixture model derives the spectrum availability and ensures the effective communication in CR without any interference.

No abstract

Skin cancer is the most serious health problems in the globe because of its high occurrence compared to other types of cancer. Melanoma and non-melanoma are the two most common kinds of skin cancer. One of the most difficult problems in medical image processing is the automatic detection of skin cancer. Skin melanoma is classified as either benign or malignant based on the results of this test. Impediment due to artifacts in dermoscopic images impacts the analytic activity and decreases the precision level. In this research work, an automatic technique including segmentation and classification is proposed. Initially, pre-processing technique called DullRazor tool is used for hair removal process and semi-supervised mean-shift algorithm is used for segmenting the affected areas of skin cancer images. Finally, these segmented images are given to a deep learning classifier called Deep forest for prediction of skin cancer. The experiments are carried out on two publicly available datasets called ISIC-2019 and HAM10000 datasets for the analysis of segmentation and classification. From the outcomes, it is clearly verified that the projected model achieved better performance than the existing deep learning techniques.

No abstract