The paradigm shift from “connected things” to “connected intelligence” is anticipated to be made possible by the sixth-generation wireless systems, which typically use millimeter wave beamforming to mitigate the significant propagation loss. However, beamforming design in millimeter wave communications poses many different challenges owing to the large antenna arrays with the limitation of radio frequency chains and analog beamforming architectures. To circumvent this problem, deep learning models have recently been utilized as a disruptive method for solving difficult optimization problems in sixth-generation mobile systems, such as maximizing spectral efficiency. However, it is still unclear how to produce high-performance deep learning models which require considering appropriate hyperparameters. This study proposes a metaheuristics-based approach for optimizing hyperparameters that are used to build optimized deep learning models to maximize spectral efficiency. The research results demonstrate that the proposed approach-based models establish higher spectral efficiency than the state-of-the-art approach-based models and the reference model whose hyperparameters are based on empirical trials.
1 November 2024 in IEEE Wireless Communications Letters
This letter addresses a multivariate optimization problem for linear movable antenna arrays (MAAs). Particularly, the position and beamforming vectors of the under-investigated MAA are optimized simultaneously to maximize the minimum beamforming gain across several intended directions, while ensuring interference levels at various unintended directions remain below specified thresholds. To this end, a swarm-intelligence-based firefly algorithm (FA) is introduced to acquire an effective solution to the optimization problem. Simulation results reveal the superior performance of the proposed FA approach compared to the state-of-the-art approach employing alternating optimization and successive convex approximation. This is attributed to the FA’s effectiveness in handling non-convex multivariate and multimodal optimization problems without resorting approximations.
This paper introduces the conceptual operation of a simple multi-line rate (MLR) transponder having two bit-rate options and thereby proposes a novel protection scheme based on rate-adaptive operation. The MLR transponder is proposed to operate at lower rate to handle working capacity and in case of failure event, it could be temporarily tuned to higher rate to support protection capacity. We formulate the network design with shared mesh protection considering our new proposal as integer linear programming problem. Extensive simulation over numerous traffic matrices and common network topologies are performed to investigate efficiency of our protection proposal compared to traditional approach in terms of total transponder count, cost issues and energy consumption.
This paper presents a capacitively coupled chopper instrumentation amplifier (CCIA) with ultra-low power consumption and programmable bandwidth for biomedical applications. To achieve a flexible bandwidth from 0.2 to 10 kHz without additional power consumption, a programmable Miller compensation technique was proposed and used in the CCIA. By using a Squeezed inverter amplifier (SQI) that employs a 0.2-V supply, the proposed CCIA addresses the primary noise source in the first stage, resulting in high noise power efficiency. The proposed CCIA is designed using a 0.18 µm CMOS technology process and has a chip area of 0.083 mm2. With a power consumption of 0.47 µW at 0.2 and 0.8 V supply, the proposed amplifier architecture achieves a thermal noise of 28 nV/√Hz, an input-related noise (IRN) of 0.9 µVrms, a closed-loop gain (AV) of 40 dB, a power supply rejection ratio (PSRR) of 87.6 dB, and a common-mode rejection ratio (CMRR) of 117.7 dB according to post-simulation data. The proposed CCIA achieves a noise efficiency factor (NEF) of 1.47 and a power efficiency factor (PEF) of 0.56, which allows comparison with the latest research results.
1 January 2023 in International Journal of Environmental Science and Development
PM2.5 (Particulate Matter) and PM10 are the most common pollutants, and the increasing of concentration in the air will threaten people’s health. The machine learning method has recently been of particular interest to many researchers due to its effectiveness in air quality prediction models. Many solutions employing deep learning-based techniques such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and hybrid CNN-LSTM models to enhance air quality prediction accuracy have been developed. This paper proposes a hybrid Encoder STM model for predicting the next day to the next five days’ PM2.5 and PM10 concentrations in Hanoi. Additionally, we proposed five extended features to increase the accuracy of prediction. Then other models, namely the LSTM model and the Bidirectional LSTM model, are also considered for PM2.5 and PM10 concentration prediction. Our results show that the proposed approaches outperform other state-of-the-art deep learning-based methods on both Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) due to low error and the small number of features.
10 April 2020 in Advances in Intelligent Systems and Computing