Climate change has been identified as one of the most critical threats to human civilization and sustainability. Wildfires, which produce huge amounts of carbon emission, are both drivers and results of climate change. An early and timely wildfire detection system can constrain fires to short and small ones and yield significant carbon reduction. In this paper, we propose to use ground sensor deployment and satellite Internet of Things (IoT) technologies for wildfire detection by taking advantage of satellites' ubiquitous global coverage. We first develop an optimal IoT sensor placement strategy based on fire ignition and detection models. Then, we analyze the uplink satellite communication budget and the bandwidth required for wildfire detection under the narrowband IoT (NB-IoT) radio interface. Finally, we conduct simulations on the California wildfire database and quantify the potential economical benefits by factoring in carbon emission reductions and sensor/bandwidth costs.
Millimeter wave (mmWave) is a key technology for fifth-generation (5G) and beyond communications. Hybrid beamforming has been proposed for large-scale antenna systems in mmWave communications. Existing hybrid beamforming designs based on infinite-resolution phase shifters (PSs) are impractical due to hardware cost and power consumption. In this paper, we propose an unsupervised-learning-based scheme to jointly design the analog precoder and combiner with low-resolution PSs for multiuser multiple-input multiple-output (MU-MIMO) systems. We transform the analog precoder and combiner design problem into a phase classification problem and propose a generic neural network architecture, termed the phase classification network (PCNet), capable of producing solutions of various PS resolutions. Simulation results demonstrate the superior sum-rate and complexity performance of the proposed scheme, as compared to state-of-the-art hybrid beamforming designs for the most commonly used low-resolution PS configurations.
Device-free wireless indoor localization is an essential technology for the Internet of Things (IoT), and fingerprint-based methods are widely used. A common challenge to fingerprint-based methods is data collection and labeling. This paper proposes a few-shot transfer learning system that uses only a small amount of labeled data from the current environment and reuses a large amount of existing labeled data previously collected in other environments, thereby significantly reducing the data collection and labeling cost for localization in each new environment. The core method lies in graph neural network (GNN) based few-shot transfer learning and its modifications. Experimental results conducted on real-world environments show that the proposed system achieves comparable performance to a convolutional neural network (CNN) model, with 40 times fewer labeled data.
Frequent and severe wildfires have been observed lately on a global scale. Wildfires not only threaten lives and properties, but also pose negative environmental impacts that transcend national boundaries (e.g., greenhouse gas emission and global warming). Thus, early wildfire detection with timely feedback is much needed. We propose to use the emerging beyond fifth-generation (B5G) and sixth-generation (6G) satellite Internet of Things (IoT) communication technology to enable massive sensor deployment for wildfire detection. We propose wildfire and carbon emission models that take into account real environmental data including wind speed, soil wetness, and biomass, to simulate the fire spreading process and quantify the fire burning areas, carbon emissions, and economical benefits of the proposed system against the backdrop of recent California wildfires. We also conduct a satellite IoT feasibility check by analyzing the satellite link budget. Future research directions to further illustrate the promise of the proposed system are discussed.
This paper investigates a multiuser downlink communication system with coexisting intelligent reflecting surface (IRS) and classical half-duplex decode-and-forward (DF) relay. In this system, the IRS and the DF relay interact with each other and assist transmission simultaneously. In particular, active beamforming at the base station (BS) and at the DF relay, and passive beamforming at the IRS, are jointly designed to maximize the sum-rate of all users. The sum-rate maximization problem is nonconvex due to the coupled beamforming vectors. We propose an alternating optimization (AO) based algorithm to tackle this complex co-design problem. Numerical validation and discussion on the superiority of the coexistence system and the tradeoffs therein are presented.
This paper proposes a novel multiple-input multiple-output (MIMO) symbol detector that incorporates a deep reinforcement learning (DRL) agent into the Monte Carlo tree search (MCTS) detection algorithm. We first describe how the MCTS algorithm, used in many decision-making problems, is applied to the MIMO detection problem. Then, we introduce a self-designed deep reinforcement learning agent, consisting of a policy value network and a state value network, which is trained to detect MIMO symbols. The outputs of the trained networks are adopted into a modified MCTS detection algorithm to provide useful node statistics and facilitate enhanced tree search process. The resulted scheme, termed the DRL-MCTS detector, demonstrates significant improvements over the original MCTS detection algorithm and exhibits favorable performance compared to other existing linear and DNN-based detection methods under varying channel conditions.
Device-free wireless indoor localization is a key enabling technology for the Internet of Things (IoT). Fingerprint-based indoor localization techniques are a commonly used solution. This paper proposes a semi-supervised, generative adversarial network (GAN)-based device-free fingerprinting indoor localization system. The proposed system uses a small amount of labeled data and a large amount of unlabeled data (i.e., semi-supervised), thus considerably reducing the expensive data labeling effort. Experimental results show that, as compared to the state-of-the-art supervised scheme, the proposed semi-supervised system achieves comparable performance with equal, sufficient amount of labeled data, and significantly superior performance with equal, highly limited amount of labeled data. Besides, the proposed semi-supervised system retains its performance over a broad range of the amount of labeled data. The interactions between the generator, discriminator, and classifier models of the proposed GAN-based system are visually examined and discussed. A mathematical description of the proposed system is also presented.
Device-free Wi-Fi indoor localization has received significant attention as a key enabling technology for many Internet of Things (IoT) applications. Machine learning-based location estimators, such as the deep neural network (DNN), carry proven potential in achieving high-precision localization performance by automatically learning discriminative features from the noisy wireless signal measurements. However, the inner workings of DNNs are not transparent and not adequately understood especially in the indoor localization application. In this paper, we provide quantitative and visual explanations for the DNN learning process as well as the critical features that DNN has learned during the process. Toward this end, we propose to use several visualization techniques, including: 1) dimensionality reduction visualization, to project the high-dimensional feature space to the 2D space to facilitate visualization and interpretation, and 2) visual analytics and information visualization, to quantify relative contributions of each feature with the proposed feature manipulation procedures. The results provide insightful views and plausible explanations of the DNN in device-free Wi-Fi indoor localization using channel state information (CSI) fingerprints.