Abstract—Artificial Intelligence (AI)-Based Security Intelligence Modelling can be used to prevent, detect, and manage cyber threats. Data-driven AI solutions are currently undergoing rigorous research and design in their own field, but few scholars or practitioners frame Authorised Push Payment (APP) Scams as a unique cybersecurity concern, or tailor technical solutions based on the local regulatory context. Drawing on a recent consultation publication by the UK Payment Systems Regulator on APP scams (November 2021), this paper shows how AI can be leveraged to manage APP scams and explores some of the opportunities and risks one should consider when adopting such an approach. We highlight three scenarios: 1) Liability on Payment Service Provider; 2) Liability on Payor; and 3) Liability on Payor with Substantial Public Sector Involvement. These examples illustrate how socio-technical systems can play a design role, and consequently assist industry leaders and engineering management in prioritizing investment focus, strategic approaches, and technical solutions.

In this work, we optimize the 3D trajectory of an unmanned aerial vehicle (UAV)-based portable access point (PAP) that provides wireless services to a set of ground nodes (GNs).  Moreover, as per the Peukert effect, we consider pragmatic non-linear battery discharge for UAV’s battery. Thus, we formulate the problem in a novel manner that represents the maximization of a fairness-based energy efficiency metric and is named fair energy efficiency (FEE). The FEE metric defines a system that lays importance on both the per-user service fairness and the PAP’s energy efficiency. The formulated problem takes the form of a non-convex problem with non-tractable constraints. To obtain a solution we represent the problem as a Markov Decision Process (MDP) with continuous state and action spaces. Considering the complexity of the solution space, we use the twin delayed deep deterministic policy gradient (TD3) actor-critic deep reinforcement learning (DRL) framework to learn a policy that maximizes the FEE of the system. We perform two types of RL training to exhibit the effectiveness of our approach: the first (offline) approach keeps the positions of the GNs the same throughout the training phase; the second approach generalizes the learned policy to any arrangement of GNs by changing the positions of GNs after each training episode. Numerical evaluations show that neglecting the Peukert effect overestimates the air-time of the PAP and can be addressed by optimally selecting the PAP’s flying speed. Moreover, the user fairness, energy efficiency, and hence the FEE value of the system can be improved by efficiently moving the PAP above the GNs. \color{black}As such, we notice massive FEE improvements over baseline scenarios of up to 88.31%, 272.34%, and 318.13% for suburban, urban, and dense urban environments, respectively.

In this study, an advanced energy harvesting interface called synchronized switch harvesting on inductor (SSHI) has been integrated with a piezoelectric energy harvester on a plate-like structure for multimode energy harvesting purposes. To the best of author’s knowledge, this type of energy harvesting system has not been studied in the literature before. Analytical solution has been developed to predict the power output of the harvester. Besides, experiments have been performed to validate the analytical model predictions and evaluate performance of the circuit. The experimental results showed that the SSHI circuit has three different switching behaviour, namely, no switching, single switching, and multi-switching. Power output of the SSHI circuit has been compared with AC-DC rectifier. It was shown that the SSHI circuit improves the power output of the harvester for the first two vibration modes of structure in the single switching case. The SSHI circuit acts as a rectifier in no switching case. Finally, multi-switching dissipates the available energy of harvester and reduces the output voltage and power of the harvester.

Currently different reference  models are used to manage cybersecurity, although practically none are  applicable “as is” to lower levels as they do not detail specific  procedural aspects for them. However, they urge organizations to develop  a methodological foundation to manage cybersecurity at those levels.  Although they allow organizations to adhere to a recognized standard at  the strategic level, this advantage vanishes when organizations must  define specific low-level procedures, allowing the appearance of  inconsistency at tactical and operational levels between departments of  the same organization or between organizations. The design of these  elements with the required holism and homogeneity is difficult, and this  is why generic processes focused on getting certified regarding a  standard are usually originated, but they are insufficient to obtain  effective cybersecurity because they are not focused on dealing with  real cyber threats. Because of the great responsibility of lower levels  to achieve effective cybersecurity, this lack of methodological  definition makes it difficult to adapt cybersecurity to the highly  dynamic cyber context with the required holism and strategic alignment.  Our proposal provides CyberTOMP, a process for managing cybersecurity at  lower levels, as well as a set of methodological elements that support  it. The novelty of these contributions is that they complement the  strategic standard selected by the organization, providing it with a set  of procedural elements ready to be used out of the box, contributing  those aspects required by high-level frameworks to manage cybersecurity  at lower levels, for which there is no alternative with a managerial  approach.

With the introduction of spectrum sharing and het-erogeneous services in next-generation networks, the base stations need to sense the wideband spectrum and identify the spectrum resources to meet the quality-of-service, bandwidth, and latency constraints. Sub-Nyquist sampling (SNS) enables digitization for sparse wideband spectrum without needing Nyquist speed analog-to-digital converters. However, SNS demands additional signal processing algorithms for spectrum reconstruction, such as the well-known orthogonal matching pursuit (OMP) algorithm. OMP is also widely used in other compressed sensing applications. The first contribution of this work is efficiently mapping the OMP algorithm on the Zynq system-on-chip (ZSoC) consisting of an ARM processor and FPGA. Experimental analysis shows a significant degradation in OMP performance for sparse spectrum. Also, OMP needs prior knowledge of spectrum sparsity. We address these challenges via deep-learning-based architectures and efficiently map them on the ZSoC platform as second contribution. Via hardware-software co-design, different versions of the proposed architecture obtained by partitioning between software (ARM processor) and hardware (FPGA) are considered. The resource, power, and execution time comparisons for given memory constraints and a wide range of word lengths are presented for these architectures.

Reconfigurable intelligent surfaces (RISs) are a recent yet revolutionary development in communications systems. Particularly applicable to millileter wave (mmWave) systems, these surfaces can increase localization performance and decrease vulnerability to environmental influences, all by  adjusting the incoming signals’ phase. At the same time, manufacturing ideal hardware to be deployed at the transceivers is not feasible nor practical. These non-linearities in hardware, collectively known hardware impairments (HWIs), cause signal degradation and adversely affect localization. In this paper, the effect of HWIs on RIS-aided localization is examined. Towards that, the mean squared error (MSE) of the user’s position is found through a maximum likelihood estimator (MLE) and its functionality is verified by the position error bounds (PEB),  derived from Cramer-Rao lower bounds (CRLB). Our numerical results show that active RISs mitigate the deteriorating effect of HWIs on the user’s PEB. Based on our outcome, increasing the inter-RISs space generally creates more resolvable paths and leads to improved localization.

There are a total of three publicly accessible datasets used, including the Boston Children’s Hospital–MIT (CHB-MIT) dataset from the U.S. and the Freiburg (FB) and EPILEPSIAE intracranial EEG (iEEG) datasets from Germany.

This paper presents a practical approach for Q/V-band modeling for low Earth orbit satellite channels based on tools from machine learning and statistical modeling. The developed Q/V-band LEO satellite channel model is presented in two folds; (i) a real-time forecasting method using model-based deep learning, intended for real-time operation of satellite terminals, and (ii) a statistical channel simulator that generates the path loss as a time-series random process, intended for system design and research. The provided approach capitalizes on real satellite measurements that are obtained from AlphaSat’s Q/V-band transmitter at different geographic latitudes, to model the radio channel. The results show that model-based deep learning forecasting can outperform conventional statistically derived prediction methods for varying rain and elevation angle profiles. Moreover, it can also provide more accuracy in long-term prediction in comparison to current state-of-the-art machine learning approaches for radio channel prediction. Results for the statistical channel simulator is shown to produce synthetic radio excess path loss values for varying satellite passes by capitalizing on empirical statistical models obtained from real measurements.

P vs NP problem turns out to be P=NP in quantum computing but remains questions of optimization in classical computing.

An accurate and robust perception system is key to understanding the driving environment of autonomous driving and robots. Autonomous driving needs 3D information about objects, including the object’s location and pose, to understand the driving environment clearly. A camera sensor is widely used in autonomous driving because of its richness in color, texture, and low price. The major problem with the camera is the lack of 3D information, which is necessary to understand the 3D driving environment. Additionally, the object’s scale change and cclusion make 3D object detection more challenging. Many deep learning-based methods, such as depth estimation, have been developed to solve the lack of 3D information. This survey presents the image 3D object detection 3D bounding box encoding techniques, feature extraction techniques, and evaluation metrics of 3D object detection. The image-based methods are categorized based on the technique used to estimate an image’s depth information, and insights are added to each method. Then, state-of-the-art (SOTA) monocular and stereo camera-based methods are summarized. We also compare the performance of the selected 3D object detection models and present challenges and future directions in 3D object detection.

In this paper, we investigate multicell-coordinated beamforming for large-scale multiple-input multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) communications with low-resolution data converters. In particular, we seek to minimize the total transmit power of the network under received signal-to-quantization-plus-interference-and-noise ratio constraints while minimizing per-antenna transmit power. Our primary contributions are (1) formulating the quantized downlink (DL) OFDM antenna power minimax problem and deriving its associated dual problem, (2) showing strong duality and interpreting the dual as a virtual quantized uplink (UL) OFDM problem, and (3) developing an iterative minimax algorithm to identify a feasible solution based on the dual problem with performance validation through simulations. Specifically, the dual problem requires joint optimization of virtual UL transmit power and noise covariance matrices. To solve the problem, we first derive the optimal dual solution of the UL problem for given noise covariance matrices. Then, we use the solution to compute the associated DL beamformer. Subsequently, using the DL beamformer we update the UL noise covariance   matrices via subgradient projection. Finally, we propose an iterative algorithm by repeating the steps for optimizing DL beamformers. Simulations validate the proposed algorithm in terms of the maximum antenna transmit power and peak-to-average-power ratio.

Future communication networks must address the scarce spectrum to accommodate extensive growth of heterogeneous wireless devices. Efforts are underway to address spectrum coexistence, enhance spectrum awareness, and bolster authentication schemes. Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, secure communications, among others. Consequently, comprehensive spectrum awareness on the edge has the potential to serve as a key enabler for the emerging beyond 5G (fifth generation) networks. State-of-the-art studies in this domain have (i) only focused on a single task - modulation or signal (protocol) classification - which in many cases is insufficient information for a system to act on, (ii) consider either radar or communication waveforms (homogeneous waveform category), and (iii) does not address edge deployment during neural network design phase. In this work, for the first time in the wireless communication domain, we exploit the potential of deep neural networks based multi-task learning (MTL) framework to simultaneously learn modulation and signal classification tasks while considering heterogeneous wireless signals such as radar and communication waveforms in the electromagnetic spectrum. The proposed MTL architecture benefits from the mutual relation between the two tasks in improving the classification accuracy as well as the learning efficiency with a lightweight neural network model. We additionally include experimental evaluations of the model with over-the-air collected samples and demonstrate first-hand insight on model compression along with deep learning pipeline for deployment on resource-constrained edge devices. We demonstrate significant computational, memory, and accuracy improvement of the proposed model over two reference architectures. In addition to modeling a lightweight MTL model suitable for resource-constrained embedded radio platforms, we provide a comprehensive heterogeneous wireless signals dataset for public use.

In this letter, a compact frequency reconfigurable beam-switching antenna based on a single-layer frequency selective face (FSS) is proposed. The proposed antenna consists of a dual-band omnidirectional antenna and a hexagonal single-layer FSS. The dual-band omnidirectional antenna is designed as a radiation source and surrounded by the FSS. Each FSS unit consists of two crossed patches and diodes. Frequency reconfigurable characteristics at 2.4 or 5 GHz are achieved by switching the states of the diodes on the single-layer FSS. With specific combinations of FSS units, the omnidirectional radiation patterns can be transformed into directional ones scanning along the entire azimuth plane. To validate the design, a prototype is fabricated and measured. The results show that the proposed single-layer FSS antenna can perform a 12-step scan along the azimuth plane at 2.4 and 5 GHz, respectively

In this work, we present a digital power amplifier (DPA) and a signal-optimized control technique suitable for the amplification of orthogonal frequency division multiplexing (OFDM). OFDM is a high peak-to-average power ratio (PAPR) signal that is naturally arising from high spectrum efficiency modulations. A 3-bit DPA is implemented with three power-scaled transistors which are turned on and off based on the signal amplitude, while phase modulation is restored using the RF input signal. The unavoidable non-linearities at the DPA output due to the PA switching are minimized by accounting for the OFDM signal probability density function (PDF). This PDF is a priori knowledge to design an optimal quantizer that minimizes distortion by distributing the DPA power levels where the signal amplitude is more similar to the original one. Back-off efficiency within 2^3=8 possible states is then optimized by implementing a load-modulating power combiner. Theory and an example design of the combiner network are provided and demonstrated for this DPA. The reported DPA prototype operates at 1.5 GHz with a 3-bit control and achieves a maximum power-added efficiency (PAE) of 64.3% and maintains a drain efficiency greater than 47% over the output power range from 36.6 to 45.2dBm (8.6dB range).

The microscopy research at the Bionanoprobe (currently at beamline 9-ID and later 2-ID after APS-U) of Argonne National Laboratory focuses on applying synchrotron X-ray fluorescence (XRF) techniques to obtain trace elemental mappings of cryogenic biological samples to gain insights about their role in critical biological activities. The elemental mappings and the morphological aspects of the biological samples, in this instance, the bacterium Escherichia coli (E. coli), also serve as label-free biological fingerprints to identify differently treated samples via fuzzy clustering. The key limitations of achieving good identification performance is the extraction of cells from raw XRF measurement via binary conversion, definition of features based on domain knowledge, dwell time and proportion of differently treated cells in the measurement.

During the outbreak of COVID - 19 in the last 2020, the traditional face - to - face in - campus has shifted to different learning modalities (synchronous, asynchronous, modified asynchronous, etc.)  among basic educational institutions in the hope of continuing learners’ learning experiences amidst the pandemic. New datasets potential for mining and knowledge discovery emerged during this time. In this study, the learner’s enrollment and survey form (LESF) from the data repository of a private high school in the Philippines is analyzed and mined. The dataset contains learners’ information relating to the present COVID - 19 crisis, which is bound to be utilized for strategic classification of each to student to their corresponding learning modality. The dataset includes major categories of information pertaining to learners’ demographic profile, parent/guardian information, household capacity, school proximity and transportaion information, and access to distance learning.  We present in this paper a machine learning (ML) method called multilayer perceptron neural network (MLP NN) for classifying learner’s learning modality as an alternative to the recommended algorithm for learning modalities delivery (ALDM) by the Department of Education (DepEd). The MLP NN model is trained using learners’ LESF information as input features. Prior to model development, Boruta algorithm (BA) is conducted to determine important features for the learning modality classification problem. We further investigate the sensitivities for each feature with respect to each learning modality using partial derivatives method.

Secondary propulsion methods for high-speed hyperloop transportation are sparsely researched. Secondary propulsion methods are essential to quickly, efficiently, and safely get a hyperloop pod up to its target speed from a stationary state. In this paper, we propose and analyze the feasibility of a form of electromagnetic secondary hyperloop propulsion, called a railgun, commonly used in modern-day artillery technology for high-speed ammunition launching. We assess the feasibility of two different materials and three different geometries for a railgun armature to propel a hyperloop pod. Inverse design of multiphysics simulation of multibody dynamics, magnetic fields, and electric currents are used for material selection of the armature that minimizes rail current energy requirements and the armature geometry that maximizes structural integrity.

Grid-forming (GFM) inverters are recognized as a viable solution to increase the penetration of renewable energy in bulk power systems. However, they are physically different from synchronous generators in terms of overcurrent capability. To protect the power semiconductor devices and support the power grid under severe symmetrical disturbances, the GFM control systems should be able to achieve the following requirements: current magnitude limitation, fault current contribution, and fault recovery capability. Various current-limiting control methods are reported in the literature to fulfill these goals, including current limiters, virtual impedance, and voltage limiters. This paper presents an overview of those methods. Emerging challenges that need to be addressed, including temporary overcurrent, unspecified output current vector angle, undesired current saturation, and transient overvoltage, are pointed out. Comparative simulations are conducted to demonstrate the performance of different methods under grid voltage drops and phase jumps. Finally, open issues of current-limiting control methods for GFM inverters, including transient stability assessment, voltage source behavior under overcurrent conditions, and windup of voltage controllers, are shared.