The cellular wireless networks are evolving towards acquiring newer capabilities, such as sensing, which will support novel use cases and applications. Many of these require indoor sensing capabilities, which can be realized by exploiting the perturbation in the indoor channel. In this work, we conduct an indoor channel measurement campaign to study these perturbations and develop AI-based algorithms for estimating sensing parameters. We develop several AI methods based on convolutional neural networks (CNNs) and tree-based ensemble architectures for sensing. We show that the presence of a passive target like a person can be detected from the channel perturbation of a single link with more than 90 % accuracy with a simple CNN based AI algorithm. However, sensing the position of a passive target is far more challenging requiring more complex AI algorithms and deployments. We show that the position of the human in the indoor room can be estimated within the average position error of 0.7 m with a deployment having three links and employing complex AI architecture for position estimation. We also compare the results with the baseline algorithm to demonstrate the utility of the proposed method.

Positioning measurements that are performed in cellular networks under non line-of-sight (NLOS) conditions can degrade the positioning performance heavily. In this paper we show that the problem can be mitigated by robust positioning methods based on the RANSAC algorithm. Starting with a basic implementation of RANSAC for the TDOA positioning problem, we propose several enhancements based on probabilistic analysis. The methods perform particularly well in dense network deployments with multiple transmission/reception points (TRP), even when the fraction of LOS measurements is low. In simulations on standardized 5G test-scenarios for industrial internet-of-things, the best algorithm achieves an accuracy on par with what is achieved when LOS/NLOS conditions are known by the estimator.

We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system. Though we train using 70% spoken-form data, our teacher models perform comparably to XLM-R and mT5 when evaluated on the written-form Cross-lingual Natural Language Inference (XNLI) corpus. We perform a second stage of pretraining on our teacher models using in-domain data from our system, improving error rates by 3.86% relative for intent classification and 7.01% relative for slot filling. We find that even a 170M-parameter model distilled from our Stage 2 teacher model has 2.88% better intent classification and 7.69% better slot filling error rates when compared to the 2.3B-parameter teacher trained only on public data (Stage 1), emphasizing the importance of in-domain data for pretraining. When evaluated offline using labeled NLU data, our 17M-parameter Stage 2 distilled model outperforms both XLM-R Base (85M params) and DistillBERT (42M params) by 4.23% to 6.14%, respectively. Finally, we present results from a full virtual assistant experimentation platform, where we find that models trained using our pretraining and distillation pipeline outperform models distilled from 85M-parameter teachers by 3.74%-4.91% on an automatic measurement of full-system user dissatisfaction.

The combination of fifth generation (5G) cellular technologies and Global Navigation Satellite Systems (GNSS) is envisaged to pave the way of fulfilling high-accuracy positioning requirements in future use cases. However, these positioning technologies are typically evaluated with independent simulations of statistical channel models for satellite and terrestrial links, which limit the applicability of the performance results. To circumvent this limitation, the proposed simulation method is based on using three-dimensional (3D) city maps to coherently determine the line-of-sight (LoS) conditions of the available satellite and cellular links. These consistent LoS measurements are then considered to assess a hybrid 5G round-trip time (RTT) and multi-constellation GNSS solution in a deep urban canyon. The combination of only one 5G RTT measurement with the GNSS observables significantly improves stand-alone GNSS solutions in terms of horizontal positioning accuracy and availability, achieving below 10 m in 80% of cases over deep urban conditions.

Clock synchronization and ranging over a wireless network with low communication overhead is a challenging goal with tremendous impact. In this paper, we study the use of time-to-digital converters in wireless sensors, which provides clock synchronization and ranging at negligible communication overhead through a sawtooth signal model for round trip times between two nodes. In particular, we derive Cramér-Rao lower bounds for a linearitzation of the sawtooth signal model, and we thoroughly evaluate simple estimation techniques by simulation, giving clear and concise performance references for this technology.

Trend driven retail industries such as fashion, launch substantial new products every season. In such a scenario, an accurate demand forecast for these newly launched products is vital for efficient downstream supply chain planning like assortment planning and stock allocation. While classical time-series forecasting algorithms can be used for existing products to forecast the sales, new products do not have any historical time-series data to base the forecast on. In this paper, we propose and empirically evaluate several novel attention-based multi-modal encoder-decoder models to forecast the sales for a new product purely based on product images, any available product attributes and also external factors like holidays, events, weather, and discount. We experimentally validate our approaches on a large fashion dataset and report the improvements in achieved accuracy and enhanced model interpretability as compared to existing k-nearest neighbor based baseline approaches.

Positioning of people and things is now being considered as one vital feature for many applications. The positioning support in cellular networks started with the regulatory requirements for emergency call, and has been enhanced over time to provide support with higher accuracy and better coverage including even deep indoor areas. Devices and use cases are not limited to regular users with mobile handsets, but include also very low cost, power and complexity devices on one hand, and advanced devices like robots, autonomous vehicles and factory equipments on the other. This paper aims to provide an overview of the positioning methods that have been introduced in the Third Generation Partnership Project (3GPP) up to the currently developed release (Rel.15), as well as different considered scenarios and deployment conditions. Also, the ambition is to describe use cases for and requirements on positioning in emerging and future cellular networks such as 5G.

In this paper we have proposed clock error mitigation from the measurements in the scheduled based self localization system. We propose measurement model with clock errors while following a scheduled transmission among anchor nodes. Further, RLS algorithm is proposed to estimate clock error and to calibrate measurements of self localizing node against relative clock errors of anchor nodes. A full-scale experimental validation is provided based on commercial off-the-shelf UWB radios under IEEE-standardized protocols.

The multiple access scheduling decides how the channel is shared among the nodes in the network. Typically scheduling algorithms aims at increasing the channel utilization and thereby throughput of the network. This paper describes several algorithms for generating an optimal schedule in terms of channel utilization for multiple access by utilizing range information in a fully connected network. We also provide detailed analysis for the proposed algorithms performance in terms of their complexity, convergence, and effect of non-idealities in the network. The performance of the proposed schemes are compared with non-aided methods to quantify the benefits of using the range information in the communication. The proposed methods have several favorable properties for the scalable systems. We show that the proposed techniques yields better channel utilization and throughput as the number of nodes in the network increases. We provide simulation results in support of this claim. The proposed methods indicate that the throughput can be increased on average by 3-10 times for typical network configurations.

Clock synchronization is ubiquitous in wireless systems for communication, sensing, and control. In this paper, we design a scalable system in which an indefinite number of passively receiving wireless units can synchronize to a single master clock at the level of discrete clock ticks. Accurate synchronization requires an estimate of the node positions to compensate the time-of-flight transmission delay in line-of-sight environments. If such information is available, the framework developed here takes position uncertainties into account. In the absence of such information, as in indoor scenarios, we propose an auxiliary localization mechanism. Furthermore, we derive the Cramer-Rao bounds for the system, which show that it enables synchronization accuracy at sub-nanosecond levels. Finally, we develop and evaluate an online estimation method, which is statistically efficient.

In this paper, we propose fusion of dynamic time of arrival (TOA) from multiple low complexity detectors like energy detectors operating at sub-Nyquist rate through Kalman filtering. We show that by having a multi-channel sub-Nyquist receiver with each channel having an energy detector can match the performance of a single channel digital receiver with matched filter. We derive analytical expression for number of sub-Nyquist energy detector channels needed to achieve the performance of digital implementation with matched filter and demonstrate in simulation the validity of our analytical approach. Results indicate that number of energy detectors needed will be high at low SNRs and converge to a constant number as the SNR increases. We also study the performance of the proposed strategy using IEEE 802.15.4a CM1 multipath channel model and show in simulation that two sub-Nyquist detectors are sufficient to match the performance of digital matched filter.

Optimal detection of ultra wideband (UWB) pulses in a UWB transceiver employing multiple detector types is proposed and analyzed in this paper. To enable the transceiver to be used for multiple applications, the designers have different types of detectors such as energy detector, amplitude detector, etc., built in to a single transceiver architecture. We propose several fusion techniques for fusing decisions made by individual IR-UWB detectors. In order to get early insight into theoretical achievable performance of these fusion techniques, we assess the performance of these fusion techniques for commonly used detector types like matched filter, energy detector and amplitude detector under Gaussian assumption. These are valid for ultra short distance communication and in UWB systems operating in millimeter wave (mmwave) band with high directivity gain. In this paper, we utilize the performance equations of different detectors, to device distinct fusion algorithms. We show that the performance can be improved approximately by 4 dB in terms of signal to noise ratio (SNR) for high probability of detection of a UWB signal (> 95%), by fusing decisions from multiple detector types compared to a standalone energy detector, in a practical scenario.

We investigate the range estimate between two wireless nodes without time stamps exchanging. Considering practical aspects of oscillator clocks, we propose a new model for ranging in which the measurement errors include the sum of two distributions, namely, uniform and Gaussian. We then derive an approximate maximum likelihood estimator (AMLE), which poses a difficult global optimization problem. To avoid the difficulty in solving the complex AMLE, we propose a simple estimator based on the method of moments. Numerical results show a promising performance for the proposed technique.

In this paper, we develop a new technique for estimating fine clock errors and range between two nodes simultaneously by two-way time-of-arrival measurements using impulse-radio ultrawideband signals. Estimators for clock parameters and the range are proposed, which are robust with respect to outliers. They are analyzed numerically and by means of experimental measurement campaigns. The technique and derived estimators achieve accuracies below 1 Hz for frequency estimation, below 1 ns for phase estimation, and 20 cm for range estimation, at a 4-m distance using 100-MHz clocks at both nodes. Therefore, we show that the proposed joint approach is practical and can simultaneously provide clock synchronization and positioning in an experimental system.

We investigate a wireless network localization scenario in which the need for synchronized nodes is avoided. It consists of a set of fixed anchor nodes transmitting according to a given sequence and a self-localizing receiver node. The setup can accommodate additional nodes with unknown positions participating in the sequence. We propose a localization method which is robust with respect to uncertainty of the anchor positions and other system parameters. Further, we investigate the Cramér-Rao bound for the considered problem and show through numerical simulations that the proposed method attains the bound.

This paper proposes a power estimation methodology which presents low complexity when implemented in hardware. Power estimation is done in digital and the radio signals are digitized using a 1-bit quantizer. An algorithm to estimate power is proposed. Power estimation of the signal is done while varying the threshold of the 1-bit quantizer. It is also shown that the proposed architecture can be used to estimate power of wideband radio channels.

We determine the optimal allocation of power between the analog and digital sections of an RF receiver, while meeting the BER constraint. Unlike conventional RF receiver designs, we treat the SNR at the output of the analog front end (SNRAD) as a design parameter rather than a specification to arrive at this optimal allocation. We first determine the relationship of the SNRAD to the resolution and operating frequency of the digital section. We then use power models for the analog and digital sections to solve the power minimization problem. As an example, we consider a 802.15.4 compliant low-IF receiver operating at 2.4 GHz in 0.13μm technology with 1.2 V power supply. We find that the overall receiver power is minimized by having the analog front end provide an SNR of 1.3dB and the ADC and the digital section operate at 1-bit resolution with 18MHz sampling frequency while achieving a power dissipation of 7mW.

A new divide-and-conquer scheme has been proposed with adaptive modulation in CDMA system to improve the spectrum efficiency of the wireless communication system. The proposed method results in increase in average throughput achieved and simultaneously decrease in the outage probability of the system when the user density is high. The proposed scheme is compared with the existing algorithms and the advantage of the scheme is evident from the results obtained.