Sensor Misalignment-tolerant AUV Navigation with Passive DoA and Doppler Measurements

We present a sensor misalignment-tolerant AUV navigation method that leverages measurements from an acoustic array and dead reckoned information. Recent studies have demonstrated the potential use of passive acoustic Direction of Arrival (DoA) measurements for AUV navigation without requiring ranging measurements. However, the sensor misalignment between the acoustic array and the attitude sensor was not accounted for. Such misalignment may deteriorate the navigation accuracy. This paper proposes a novel approach that allows simultaneous AUV navigation, beacon localization, and sensor alignment. An Unscented Kalman Filter (UKF) that enables the necessary calculations to be completed at an affordable computational load is developed. A Nonlinear Least Squares (NLS)-based technique is employed to find an initial solution for beacon localization and sensor alignment as early as possible using a short-term window of measurements. Experimental results demonstrate the performance of the proposed method.

User-Centric Cell-Free Wireless Networks for 6G: Communication Theoretic Models and Research Challenges

This paper presents a comprehensive communication theoretic model for the physical layer of a cell-free user-centric network, formed by user equipments (UEs), radio units (RUs), and decentralized units (DUs), uniformly spatially distributed over a given coverage area. We consider RUs equipped with multiple antennas, and focus on the regime where the UE, RU, and DU densities are constant and therefore the number of such nodes grows with the coverage area. A system is said scalable if the computing load and information rate at any node in the network converges to a constant as the network size (coverage area) grows to infinity. This imposes that each UE must be processed by a (user-centric) finite-size cluster of RUs, and that such cluster processors are dynamically allocated to the DUs (e.g., as software defined virtual network functions) in order to achieve a balanced computation load. We also assume that the RUs are connected to the DUs through a packet switching network, in order to achieve adaptive routing and load balance. For this model, we define in details the dynamic cluster formation and uplink pilot allocation. As a consequence of the pilot allocation and the scalability constraint, each cluster processor has a partial view of the network channel state information. We define the condition of ``ideal partial CSI'' when the channel vectors that can be estimated are perfectly known (while the ones that cannot be estimated are not know at all). We develop two attractive cluster-based linear receiver schemes for the uplink, and an uplink-downlink duality that allows to reuse such vectors as precoders for the downlink.

Sensor Fusion and Resource Management in MIMO-OFDM Joint Sensing and Communication

This study explores the promising potential of integrating sensing capabilities into multiple-input multiple-output (MIMO)-orthogonal frequency division multiplexing (OFDM)-based networks through innovative multi-sensor fusion techniques, tracking algorithms, and resource management. A novel data fusion technique is proposed within the MIMO-OFDM system, which promotes cooperative sensing among monostatic joint sensing and communication (JSC) base stations by sharing range-angle maps with a central fusion center. To manage data sharing and control network overhead introduced by cooperation, an excision filter is introduced at each base station. After data fusion, the framework employs a three-step clustering procedure combined with a tracking algorithm to effectively handle point-like and extended targets. Delving into the sensing/communication trade-off, resources such as transmit power, frequency, and time are varied, providing valuable insights into their impact on the overall system performance. Additionally, a sophisticated channel model is proposed, accounting for complex urban propagation scenarios and addressing multipath effects and multiple reflection points for extended targets like vehicles. Evaluation metrics, including optimal sub-pattern assignment (OSPA), downlink sum rate, and bit rate, offer a comprehensive assessment of the system's localization and communication capabilities, as well as network overhead.

Multi-Base Station Cooperative Sensing with AI-Aided Tracking

In this work, we investigate the performance of a joint sensing and communication (JSC) network consisting of multiple base stations (BSs) that cooperate through a fusion center (FC) to exchange information about the sensed environment while concurrently establishing communication links with a set of user equipments (UEs). Each BS within the network operates as a monostatic radar system, enabling comprehensive scanning of the monitored area and generating range-angle maps that provide information regarding the position of a group of heterogeneous objects. The acquired maps are subsequently fused in the FC. Then, a convolutional neural network (CNN) is employed to infer the category of the targets, e.g., pedestrians or vehicles, and such information is exploited by an adaptive clustering algorithm to group the detections originating from the same target more effectively. Finally, two multi-target tracking algorithms, the probability hypothesis density (PHD) filter and multi-Bernoulli mixture (MBM) filter, are applied to estimate the state of the targets. Numerical results demonstrated that our framework could provide remarkable sensing performance, achieving an optimal sub-pattern assignment (OSPA) less than 60 cm, while keeping communication services to UEs with a reduction of the communication capacity in the order of 10% to 20%. The impact of the number of BSs engaged in sensing is also examined, and we show that in the specific case study, 3 BSs ensure a localization error below 1 m.

CTT-Net: A Multi-view Cross-token Transformer for Cataract Postoperative Visual Acuity Prediction

Surgery is the only viable treatment for cataract patients with visual acuity (VA) impairment. Clinically, to assess the necessity of cataract surgery, accurately predicting postoperative VA before surgery by analyzing multi-view optical coherence tomography (OCT) images is crucially needed. Unfortunately, due to complicated fundus conditions, determining postoperative VA remains difficult for medical experts. Deep learning methods for this problem were developed in recent years. Although effective, these methods still face several issues, such as not efficiently exploring potential relations between multi-view OCT images, neglecting the key role of clinical prior knowledge (e.g., preoperative VA value), and using only regression-based metrics which are lacking reference. In this paper, we propose a novel Cross-token Transformer Network (CTT-Net) for postoperative VA prediction by analyzing both the multi-view OCT images and preoperative VA. To effectively fuse multi-view features of OCT images, we develop cross-token attention that could restrict redundant/unnecessary attention flow. Further, we utilize the preoperative VA value to provide more information for postoperative VA prediction and facilitate fusion between views. Moreover, we design an auxiliary classification loss to improve model performance and assess VA recovery more sufficiently, avoiding the limitation by only using the regression metrics. To evaluate CTT-Net, we build a multi-view OCT image dataset collected from our collaborative hospital. A set of extensive experiments validate the effectiveness of our model compared to existing methods in various metrics. Code is available at: https://github.com/wjh892521292/Cataract OCT.

Learning Quantization in LDPC Decoders

Finding optimal message quantization is a key requirement for low complexity belief propagation (BP) decoding. To this end, we propose a floating-point surrogate model that imitates quantization effects as additions of uniform noise, whose amplitudes are trainable variables. We verify that the surrogate model closely matches the behavior of a fixed-point implementation and propose a hand-crafted loss function to realize a trade-off between complexity and error-rate performance. A deep learning-based method is then applied to optimize the message bitwidths. Moreover, we show that parameter sharing can both ensure implementation-friendly solutions and results in faster training convergence than independent parameters. We provide simulation results for 5G low-density parity-check (LDPC) codes and report an error-rate performance within 0.2 dB of floating-point decoding at an average message quantization bitwidth of 3.1 bits. In addition, we show that the learned bitwidths also generalize to other code rates and channels.

GMM-based Codebook Construction and Feedback Encoding in FDD Systems

We propose a precoder codebook construction and feedback encoding scheme which is based on Gaussian mixture models (GMMs). In an offline phase, the base station (BS) first fits a GMM to uplink (UL) training samples. Thereafter, it designs a codebook in an unsupervised manner by exploiting the GMM's clustering capability. We design one codebook entry per GMM component. After offloading the GMM-but not the codebook-to the mobile terminal (MT) in the online phase, the MT utilizes the GMM to determine the best fitting codebook entry. To this end, no channel estimation is necessary at the MT. Instead, the MT's observed signal is used to evaluate how responsible each component of the GMM is for the signal. The feedback consists of the index of the GMM component with the highest responsibility and the BS then employs the corresponding codebook entry. Simulation results show that the proposed codebook design and feedback encoding scheme outperforms conventional Lloyd clustering based codebook design algorithms, especially in configurations with reduced pilot overhead.

Closed-form max-min power control for some cellular and cell-free massive MIMO networks

Many common instances of power control problems for cellular and cell-free massive MIMO networks can be interpreted as max-min utility optimization problems involving affine interference mappings and polyhedral constraints. We show that these problems admit a closed-form solution which depends on the spectral radius of known matrices. In contrast, previous solutions in the literature have been indirectly obtained using iterative algorithms based on the bisection method, or on fixed-point iterations. Furthermore, we also show an asymptotically tight bound for the optimal utility, which in turn provides a simple rule of thumb for evaluating whether the network is operating in the noise or interference limited regime. We finally illustrate our results by focusing on classical max-min fair power control for cell-free massive MIMO networks.

LSTM-Autoencoder based Anomaly Detection for Indoor Air Quality Time Series Data

Anomaly detection for indoor air quality (IAQ) data has become an important area of research as the quality of air is closely related to human health and well-being. However, traditional statistics and shallow machine learning-based approaches in anomaly detection in the IAQ area could not detect anomalies involving the observation of correlations across several data points (i.e., often referred to as long-term dependences). We propose a hybrid deep learning model that combines LSTM with Autoencoder for anomaly detection tasks in IAQ to address this issue. In our approach, the LSTM network is comprised of multiple LSTM cells that work with each other to learn the long-term dependences of the data in a time-series sequence. Autoencoder identifies the optimal threshold based on the reconstruction loss rates evaluated on every data across all time-series sequences. Our experimental results, based on the Dunedin CO2 time-series dataset obtained through a real-world deployment of the schools in New Zealand, demonstrate a very high and robust accuracy rate (99.50%) that outperforms other similar models.

IGRF-RFE: A Hybrid Feature Selection Method for MLP-based Network Intrusion Detection on UNSW-NB15 Dataset

The effectiveness of machine learning models is significantly affected by the size of the dataset and the quality of features as redundant and irrelevant features can radically degrade the performance. This paper proposes IGRF-RFE: a hybrid feature selection method tasked for multi-class network anomalies using a Multilayer perceptron (MLP) network. IGRF-RFE can be considered as a feature reduction technique based on both the filter feature selection method and the wrapper feature selection method. In our proposed method, we use the filter feature selection method, which is the combination of Information Gain and Random Forest Importance, to reduce the feature subset search space. Then, we apply recursive feature elimination(RFE) as a wrapper feature selection method to further eliminate redundant features recursively on the reduced feature subsets. Our experimental results obtained based on the UNSW-NB15 dataset confirm that our proposed method can improve the accuracy of anomaly detection while reducing the feature dimension. The results show that the feature dimension is reduced from 42 to 23 while the multi-classification accuracy of MLP is improved from 82.25% to 84.24%.