摘要
由一名新闻记者兼机器人与机器学习每日新闻编辑每日新闻-关于人工智能ce的详细数据已经呈现。根据NewsRx记者在埃及班哈的新闻报道，研究称，“射频(RF)能量采集已被用于为无线和低功耗设备供电。然而，射频能量采集在根据信号可用性收集的电量方面存在局限性。”新闻记者引用了本哈大学的一篇研究文章：“能量预测对于提高能量收集电路的性能至关重要。以前的研究主要集中在改进能量收集策略或理论上估计能量收集。很少有研究将射频信号作为时间序列数据使用真实的射频测量进行预测。而且，本文提出了一套完整的蜂窝频段射频能量预测模型,并利用软件无线电技术对不同频段的射频能量进行实时测量,利用四种人工智能技术对不同频段的射频能量进行实时测量。此外，我们提出了一个具有增强损耗函数的优化模型，使模型对异常具有更强的适应性，节省了计算功耗和数据清理时间。在1960 MHz频段的数值结果表明，长短期记忆法的预测精度最高，其次是DeepAR算法，预测精度分别为95.76%和95.02%。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Data detailed on Artificial Intelligen ce have been presented. According to news reporting originating in Banha, Egypt, by NewsRx journalists, research stated, “Radio Frequency (RF) energy harvesting has been used to power wireless and low-powered devices. However, RF energy har vesting has limitations in terms of the amount of power that can be collected ba sed on signal availability.” The news reporters obtained a quote from the research from Benha University, “He nce, energy prediction is essential to improve energy harvesting circuits ‘ perf ormance. Previous research has mainly focused on improving power harvesting poli cies or theoretically estimating the harvested energy. Very few works have consi dered the prediction of the RF signal as time series data using real RF measurem ents. Moreover, challenges such as the power consumed by the circuit ‘ s harvest ing decisions and the impact of outliers on the model performance haven ‘ t been addressed yet. This paper presents a complete pipeline for developing the best predictive model for RF energy in cellular frequency bands. Real -time measureme nts are taken in different frequency bands using software-defined radio technolo gy. We use four artificial intelligence techniques to model the RF energy signal . Additionally, we propose an optimized model with an enhanced loss function, wh ich makes the model more resilient to anomalies, saving computational power and time consumed in cleaning the data. The four algorithms are investigated, and th eir prediction accuracies are compared. The average power of a period of 5 min i s accurately forecasted. Numerical results in the 1960 MHz band show that long s hort -term memory has the best performance, followed by the DeepAR algorithm wit h prediction accuracies of 95.76% and 95.02%, respect ively.”
NETL
NSTL