Performance Enhancement of Precoded Point to Point Massive MIMO Systems Using Uniform and Non-uniform Quantized ADC/DACs

2024-01-08T18:01:05+08:00

this paper investigates the spectral and energy efficiency of a Precoded point-to-point massive MIMO system with low-resolution ADCs/DACs, using both uniform and non-uniform quantization while considering the quantization noise. The authors propose an iterative alternating minimization algorithm to obtain the optimal hybrid precoder matrix and explore the trade-off between spectral and energy efficiency. The proposed system considers a single user point-to-point massive MIMO system with a base station and receiver equipped with low-resolution DACs/ADCs, respectively, and a narrow-band Rayleigh-fading channel. The simulation results show that the proposed hybrid precoding algorithm improves the spectral and energy efficiency of the massive MIMO system compared to a fully digital precoded system, with both Uniform and Non-Uniform Quantization. Transmit precoding is used to improve the downlink performance and simplify the receiver design in massive MIMO systems. However, this study shows that hybrid precoding with low-resolution ADCs/DACs can achieve similar or better performance than fully digital precoding, with significant reductions in hardware complexity and power consumption. The results suggest that hybrid precoding can be a promising solution for future wireless communication systems. Future work could explore other channel models, different quantization schemes, and multi-user scenarios to further enhance the performance of hybrid precoding in massive MIMO systems.

Deep Learning-Based Approach for Tomato Classification in Complex Scenes

2024-02-25T20:51:18+08:00

Tracking ripening tomatoes is time consuming and labor intensive. Artificial intelligence technologies combined with those of computer vision can help users optimize the process of monitoring the ripening status of plants. To this end, we have proposed a tomato ripening monitoring approach based on deep learning in complex scenes. The objective is to detect mature tomatoes and harvest them in a timely manner. Firstly, the images of the scene are transmitted to the pre-processing layer. This layer is responsible for processing the images and segmenting the regions corresponding to the tomatoes according to methods such as grayscale conversion, gamma correction and subdivision into superpixels. This process allows the detection of areas of interest (area of the image containing tomatoes). Then, these images are used as input to the maturity detection layer. This layer, based on a deep neural network learning algorithm, classifies the tomato thumbnails provided to it in one of the following five categories: green, brittle, pink, pale red, mature red. The experimental results of the maturity detection layer on a dataset composed of images of tomatoes taken under the extreme conditions, gave a good classification rate.

International Journal of Computer Theory and Engineering

Performance Enhancement of Precoded Point to Point Massive MIMO Systems Using Uniform and Non-uniform Quantized ADC/DACs

Deep Learning-Based Approach for Tomato Classification in Complex Scenes