This paper proposes recurrent neural networks (RNNs) for 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 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 KNN algorithms and probabilistic algorithms by approximately 30% under the same test environment.

We demonstrate a highly sensitive nanoparticle and virus detection method by using a thermal-stabilized reference interferometer in conjunction with an ultrahigh-Q microcavity. Sensitivity is sufficient to resolve shifts caused by binding of individual nanobeads in solution down to a record radius of 12.5 nm, a size approaching that of single protein molecules. A histogram of wavelength shift versus nanoparticle radius shows that particle size can be inferred from shift maxima. Additionally, the signal-to-noise ratio for detection of Influenza A virus is enhanced to 38∶1 from the previously reported 3∶1. The method does not use feedback stabilization of the probe laser. It is also observed that the conjunction of particle-induced backscatter and optical-path-induced shifts can be used to enhance detection signal-to-noise.

Label-free bio-sensing is a critical functionality underlying a variety of health- and security-related applications. Micro-/nano-photonic devices are well suited for this purpose and have emerged as promising platforms in recent years. Here we propose and demonstrate an approach that utilizes the optical spring effect in a high-Q coherent optomechanical oscillator to dramatically enhance the sensing resolution by orders of magnitude compared with conventional approaches, allowing us to detect single bovine serum albumin proteins with a molecular weight of 66 kDa at a signal-to-noise ratio of 16.8. The unique optical spring sensing approach opens up a distinctive avenue that not only enables biomolecule sensing and recognition at individual level, but is also of great promise for broad physical sensing applications that rely on sensitive detection of optical cavity resonance shift to probe external physical parameters.

This paper proposes a soft range limited K nearest neighbours (SRL-KNN) localization fingerprinting algorithm. The conventional KNN determines the neighbours of a user by calculating and ranking the fingerprint distance measured at the unknown user location and the reference locations in the database. Different from that method, SRL-KNN scales the fingerprint distance by a range factor related to the physical distance between the user’s previous position and the reference location in the database to reduce the spatial ambiguity in localization. Although utilizing the prior locations, SRL-KNN does not require knowledge of the exact moving speed and direction of the user. Moreover, to take into account of the temporal fluctuations of the received signal strength indicator (RSSI), RSSI histogram is incorporated into the distance calculation. Actual on-site experiments demonstrate that the new algorithm achieves an average localization error of 0:66 m with 80% of the errors under 0:89 m, which outperforms conventional KNN algorithms by 45% under the same test environment.

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 F ₁ 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 F ₁ of 99.68±0.04% regardless the temporal correlations among the data packets.

This article proposes a universal activation function (UAF) that achieves near optimal performance in quantification, classification, and reinforcement learning (RL) problems. For any given problem, the gradient descent algorithms are able to evolve the UAF to a suitable activation function by tuning the UAF’s parameters. For the CIFAR-10 classification using the VGG-8 neural network, the UAF converges to the Mish like activation function, which has near optimal performance $$F_{1}=0.902\pm 0.004$$F1=0.902±0.004 when compared to other activation functions. In the graph convolutional neural network on the CORA dataset, the UAF evolves to the identity function and obtains $$F_1=0.835\pm 0.008$$F1=0.835±0.008 . For the quantification of simulated 9-gas mixtures in 30 dB signal-to-noise ratio (SNR) environments, the UAF converges to the identity function, which has near optimal root mean square error of $$0.489\pm 0.003~\mu {\mathrm{M}}$$0.489±0.003μM . In the ZINC molecular solubility quantification using graph neural networks, the UAF morphs to a LeakyReLU/Sigmoid hybrid and achieves RMSE= $$0.47\pm 0.04$$0.47±0.04 . For the BipedalWalker-v2 RL dataset, the UAF achieves the 250 reward in $${961\pm 193}$$961±193 epochs with a brand new activation function, which gives the fastest convergence rate among the activation functions.