We present a 4-port Multiple-Input-Multiple-Output (MIMO) antenna array operating in the mm-wave band for 5G applications. An identical two-element array excited by the feed network based on a T-junction power combiner/divider is introduced in the reported paper. The array elements are rectangular-shaped slotted patch antennas, while the ground plane is made defected with rectangular, circular, and a zigzag-shaped slotted structure to enhance the radiation characteristics of the antenna. To validate the performance, the MIMO structure is fabricated and measured. The simulated and measured results are in good coherence. The proposed structure can operate in a 25.5–29.6 GHz frequency band supporting the impending mm-wave 5G applications. Moreover, the peak gain attained for the operating frequency band is 8.3 dBi. Additionally, to obtain high isolation between antenna elements, the polarization diversity is employed between the adjacent radiators, resulting in a low Envelope Correlation Coefficient (ECC). Other MIMO performance metrics such as the Channel Capacity Loss (CCL), Mean Effective Gain (MEG), and Diversity gain (DG) of the proposed structure are analyzed, and the results indicate the suitability of the design as a potential contender for imminent mm-wave 5G MIMO applications.

This work demonstrates an integrated multiple-input multiple-output (MIMO) antenna solution for Long Term Evolution (LTE) and Millimeter-Wave (mm-wave) 5G wireless communication services. The proposed structure is comprised of a two-element LTE MIMO antenna, and a four-element 5G MIMO configuration with rectangular and circular defects in the ground plane. For experimental validation, the proposed structure is fabricated on a Rogers RO4350B substrate with 0.76 mm thickness. The overall substrate dimensions are 75 mm × 110 mm. The proposed structure is capable of operating at 5.29–6.12 GHz (LTE 46 and 47 bands) and 26–29.5 GHz (5G mm-wave) frequency bands. Additionally, the measured peak gain of 5.13 and 9.53 dB is attained respectively for the microwave and mm-wave antennas. Furthermore, the analysis of the MIMO performance metrics demonstrates good characteristics, and excellent field correlation performance across the operating bands. Furthermore, the analysis of the Specific Absorption Rate (SAR) and Power Density (PD) at the lower frequency band (5.9 GHz) and PD only at mm-Wave frequency band (28 GHz) verifies that the proposed antenna system satisfies the international human safety standards. Therefore, the proposed integrated MIMO antenna configuration ascertains to be a potential contender for the forthcoming communication applications.

Much attention has been paid to the recognition of human emotions with the help of electroencephalogram (EEG) signals based on machine learning technology. Recognizing emotions is a challenging task due to the non-linear property of the EEG signal. This paper presents an advanced signal processing method using the deep neural network (DNN) for emotion recognition based on EEG signals. The spectral and temporal components of the raw EEG signal are first retained in the 2D Spectrogram before the extraction of features. The pre-trained AlexNet model is used to extract the raw features from the 2D Spectrogram for each channel. To reduce the feature dimensionality, spatial, and temporal based, bag of deep features (BoDF) model is proposed. A series of vocabularies consisting of 10 cluster centers of each class is calculated using the k-means cluster algorithm. Lastly, the emotion of each subject is represented using the histogram of the vocabulary set collected from the raw-feature of a single channel. Features extracted from the proposed BoDF model have considerably smaller dimensions. The proposed model achieves better classification accuracy compared to the recently reported work when validated on SJTU SEED and DEAP data sets. For optimal classification performance, we use a support vector machine (SVM) and k-nearest neighbor (k-NN) to classify the extracted features for the different emotional states of the two data sets. The BoDF model achieves 93.8% accuracy in the SEED data set and 77.4% accuracy in the DEAP data set, which is more accurate compared to other state-of-the-art methods of human emotion recognition.