Learning-enabled spectroscopic analysis, promising for automated real-time analysis of chemicals, is facing several challenges. First, a typical machine learning model requires a large number of training samples that physical systems can not provide. Second, it requires the testing samples to be in range with the training samples, which often is not the case in the real world. Further, a spectroscopy device is limited by its memory size, computing power, and battery capacity. That requires highly efficient learning models for on-site analysis. In this paper, by analyzing multi-gas mixtures and multi-molecule suspensions, we first show that orders of magnitude reduction of data dimension can be achieved as the number of principal components that need to be retained is the same as the independent constituents in the mixture. From this principle, we designed highly compact models in which the essential principal components can be directly extracted from the interrelations between the individual chemical properties and principal components; and only a few training samples are required. Our model can predict the constituent concentrations that have not been seen in the training dataset and provide estimations of measurement noises. This approach can be extended as an effectively standardized method for principle component extraction.

In this article, we investigate deep-learning-based omni intrusion detection system (IDS) for supervisory control and data acquisition (SCADA) networks that are capable of detecting both temporally uncorrelated and correlated attacks. Regarding the IDSs developed in this article, a feedforward neural network (FNN) can detect temporally uncorrelated attacks at an F1 of 99.967±0.005% but correlated attacks as low as 58±2%. In contrast, long short-term memory (LSTM) detects correlated attacks at 99.56±0.01% while uncorrelated attacks at 99.3±0.1%. Combining LSTM and FNN through an ensemble approach further improves the IDS performance with F1 of 99.68±0.04% regardless the temporal correlations among the data packets.

Image based localization is a key block of visual simultaneous localization and mapping (SLAM) system where image data is used to localize the camera relative to an arbitrary reference frame. Although finding the location from one image or between two images is well studied in the literature, few works study the problem of finding the pose of multiple images in videos of different frame lengths. Here, we propose two different architectures to address this problem, one using a combination of 2D convolutional neural network (CNN) and recurrent neural networks (RNN) and the other using 3D CNN. We demonstrate that 3D CNN is better for pose estimation problem than CNN-RNN by visualizing the learned features per layer of both architectures and the accuracy performance. Further, instead of using RGB images as input to the networks, we use SURF descriptors to reduce the image dimension of 480×640×3 by more than 48 folds, making the training time much faster and the learning model less complex. Both architectures show competitive performance in comparison to the state of the art on indoor localization dataset with the ability to generalize to test scenes that are completely different from the training scenes.

We propose SURF-LSTM, a low complexity deep architecture to learn image absolute pose (position and orientation) in indoor environments using SURF descriptors and recurrent neural networks. Given the strongest SURF features descriptors of an input image, we use 2 layers of bidirectional long short term memory (LSTM) to model the sequential relation between them to learn the 6 degrees of freedom absolute pose in an arbitrary reference frame. In addition to achieving competitive performance compared to existing image localization methods, our system can be trained in less than 10 minutes instead of hours by the state of the art. It requires as small as 0.0128 MB to save the image frame rather than 0.08 MB compared to other methods that use the cropped images and the weights file needs 1.5 MB of storage compared to 100 MB of other methods which leads to significant time and space efficiency.

Neural networks-based camera pose estimation systems rely on fine tuning very large networks to regress the camera position and orientation with very complex training procedure. In this paper, we explore the following question: do we need to fine tune and train such complex networks to reach the desired accuracy? We show that we can reach comparable or better accuracy for the single image indoor localization systems with using only one layer of ridge regression and pretrained features of ResNet-50 architecture with training time less than a second on CPU instead of hours of GPU training needed by the state of the art. For outdoor scenes, we show that using only 3 fully connected layers on top of pretrained ResNet50 features without fine-tuning can perform well compared to the state of the art with only minutes of training. For more complexity reduction, we show that downsampling the pretrained ResNet-50 features by more than 10 times using principal component analysis (PCA) has a little effect on the performance but can save both training time and storage space.

As 5G wireless systems and networks are now being globally commercialized and deployed, more diversified application scenarios are emerging, quickly reshaping our societies and paving the road to the beyond 5G (6G) era when terahertz (THz) and unmanned aerial vehicle (UAV) communications may play critical roles. In this paper, aerial channel models under multiple meteorological conditions such as rain, fog and snow, have been investigated at frequencies of interest (from 2 GHz to 900 GHz) for UAV communications. Furthermore, the link budget and the received signal-to-noise ratio (SNR) performance under the existing air-to-ground (A2G) channel models are studied with antenna(s) system considered. The relationship between the 3D coverage radius and UAV altitude under the influence of multiple weather (MW) conditions is simulated. Numerical results show that medium rain has the most effects on the UAV's coverage for UAV communications at millimeter wave (mmWave) bands, while snow has the largest impacts at near THz bands. In addition, when the frequency increases, the corresponding increase in the number of antennas can effectively compensate for the propagation loss introduced by weather factors, while its form factor and weight can be kept to maintain the UAV's payload.

This article proposes recurrent neural networks (RNNs) for the WiFi fingerprinting indoor localization. Instead of locating a mobile user's position one at a time as in the cases of conventional algorithms, our RNN solution aims at the trajectory positioning and takes into account the correlation among the received signal strength indicator (RSSI) measurements in a trajectory. To enhance the accuracy among the temporal fluctuations of RSSI, a weighted average filter is proposed for both input RSSI data and sequential output locations. The results using different types of RNN, including vanilla RNN, long short-term memory (LSTM), gated recurrent unit (GRU), bidirectional RNN (BiRNN), bidirectional LSTM (BiLSTM), and bidirectional GRU (BiGRU) are presented. On-site experiments demonstrate that the proposed structure achieves an average localization error of 0.75 m with 80% of the errors under one meter, which outperforms K-nearest neighbors algorithms and probabilistic algorithms by approximately 30% under the same test environment.

Unmanned aerial vehicles (UAVs) for wireless communications have rapidly grown into a research hotspot as the mass production of high-performance, low-cost, and intelligent UAVs becomes practical. In the meantime, the fifth generation (5G) wireless communication and Internet-of-Things (IoT) technologies are being standardized and planned for global deployment. During this process, UAVs are becoming an important part of 5G and IoT, and expected to play a crucial role in enabling more functional diversity for wireless communications. In this paper, we first present a summary of mainstream UAVs and their use in wireless communications. Then, we propose a hierarchical architecture of UAVs with multilayer and distributed features to facilitate the integration of different UAVs into the next-generation wireless communication networks. Finally, we unveil the design tradeoffs with the consideration of power transfer, wireless communication, and aerodynamic principles. In particular, empirical models and published measurement data are used to analyze power transfer efficiency, and meteorological impacts on UAVs enabled next-generation wireless communications.

Predicting channel state information (CSI) is a fundamental element in wireless communications systems. An accurate CSI estimation and prediction is critical to the system performance. This paper introduces a recurrent neural network (RNN) based approach for real-time prediction in real-world non-stationary channels. It uses the recent history data for online training, followed by prediction employing the trained model, in order to adapt to the changing channel and obtain a more accurate CSI prediction compared to conventional methods. Furthermore, the proposed method needs no additional knowledge, such as the internal properties of the channel itself, or the external features that affect the channel propagation, greatly facilitating its use in practical systems. Simulation results show that the proposed adaptive and parameter free recurrent neural structure (APF-RNS) outperforms the existing methods under a dynamically changing non-stationary environment. Therefore, the proposed online training based RNN approach is a promising method for channel prediction in wireless communications.