In order to classify linearly non-separable data, neurons are typically organized into multi-layer neural networks that are equipped with at least one hidden layer. Inspired by some recent discoveries in neuroscience, we propose a new neuron model along with a novel activation function enabling learning of non-linear decision boundaries using a single neuron. We show that a standard neuron followed by the novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy. Furthermore, we conduct experiments on three benchmark data sets from computer vision and natural language processing, i.e. Fashion-MNIST, UTKFace and MOROCO, showing that the ADA and the leaky ADA functions provide superior results to Rectified Liner Units (ReLU) and leaky ReLU, for various neural network architectures, e.g. 1-hidden layer or 2-hidden layers multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs) such as LeNet, VGG, ResNet and Character-level CNN. We also obtain further improvements when we change the standard model of the neuron with our pyramidal neuron with apical dendrite activations (PyNADA).

This paper describes the design and modus of operation of a neuromorphic robotic system based on SpiNNaker platform, and its implementation on the goalkeeper task. The robotic system utilizes an Address Event Representation (AER) type of camera (DVS) to capture features of a moving ball, and a servo motor to position the goalkeeper to intercept the incoming ball. At the backbone of the system is a microprocessor (Arduino Due) which facilitates the communication between different robot parts. A spiking neural network, which is running on SpiNNaker, predicts the location of arrival of the moving ball and decides where to place the goalkeeper. In our setup, the maximum data transmission speed of the closed-loop system is approximately 3000 packets per second for both uplink and downlink, and the robot can intercept balls whose speed is up to 1 m/s starting from the distance of about 0.8 m. The interception accuracy is 85%, the response latency is 6.5 ms and the maximum power consumption is 7.15 W. A demo video of the robot goalie is available on YouTube: https://www.youtube.com/watch?v=135fH21QXtg .

There is a rise of interest within the applied physics and engineering electromagnetics community in exploring the topological structure of various systems and devices. This paper provides an outline for a new approach to microwave circuit theory via Lie theory emphasizing the deep topological structure of transmission lines and is expected to shed light on related issues like nano-EM and MTMs.

Robust attitude and heading estimation with respect to a known reference is an essential component for indoor localization in robotic applications. Affordable Attitude and Heading Reference Systems (AHRS) are typically using 9-axis solid-state MEMS-based sensors. The accuracy of heading estimation on such a system depends on the Earth’s magnetic field measurement accuracy. The measurement of the Earth’s magnetic field using MEMS-based magnetometer sensors in an indoor environment, however, is strongly affected by external magnetic perturbations. This paper presents a novel approach for robust indoor heading estimation based on skewed-redundant magnetometer fusion. A tetrahedron platform based on Hall-effect magnetic sensors is designed to determine the Earth’s magnetic field with the ability to compensate for external magnetic field anomalies. Additionally, a correlation-based fusion technique is introduced for perturbation mitigation using the proposed skewed-redundant configuration. The proposed fusion technique uses a correlation coefficient analysis for determining the distorted axis and extracts the perturbation-free Earth’s magnetic field vector from the redundant magnetic measurement. Our experimental results show that the proposed scheme is able to successfully mitigate the anomalies in the magnetic field measurement and estimates the Earth’s true magnetic field. Using the proposed platform, we achieve a Root Mean Square Error of 12.74$\degree$ for indoor heading estimation without using an additional gyroscope.

This is the accepted version of our article in IEEE EMC Magazine: R. Asadi, H.  Aliakbarian, G. Khayambashi and P. Majdolashrafi, “A case-study on the  effect of averaging duration on RF dosimetry of general public  environments,” in IEEE Electromagnetic Compatibility Magazine, vol. 9, no. 3, pp. 45-54, 3rd Quarter 2020, doi: 10.1109/MEMC.2020.9241551.

Falling down is prevalent among elderly persons resulting to to injuries, disability and even death. United Nations predicts a double increase in population of persons aged 65 and above by 2050 hence a need to research on methods for detecting and preventing falls from occurring. This paper presents a theoretical proposal on detecting and preventing a fall using RFID and wearable technologies.

Currently, there are hundreds of Bitcoin exchanges on the market, so choosing a reliable exchange is a critical issue for users. We know that the amount of Bitcoin holdings is an essential indicator for evaluating an exchange, but people have very few ways to access this information. Besides, many reports indicate that the trading volumes of most Bitcoin exchanges do not match their real situations, and the fake volume has become an unspoken rule of the whole industry. It causes the public to doubt the actual amount of Bitcoin owned by each exchange. To solve the problem of information asymmetry between users and exchanges, we propose a method for tagging Bitcoin addresses of exchanges. Through vertical, forward, and backward address mining, the method can utilize only one or several addresses of an exchange to find out all its addresses and distinguish different address types: deposit wallet, hot wallet, and cold wallet. Then the balance and transfers of the exchange can be further obtained through these addresses, helping users understand the real Bitcoin holdings of the exchange. Several experiments are conducted to evaluate the effectiveness of the proposed Bitcoin address tagging method. Our method has very little dependence on off-chain information. Only one address is needed for each exchange as a seed to find out all the other addresses. Such a seed address can be easily obtained by depositing some Bitcoin into the exchange or withdrawing some from it, which makes our method feasible for all exchanges.

Intelligent reflecting surface (IRS)-enabled communication systems provide higher system capacity and spectral efficiency by reflecting the incident signals from transmitters in a low-cost passive reflecting way. However, it poses new challenges in resource allocation due to surrounding interference and phase shift, especially when IRS is employed in heterogeneous networks (HetNets). In this paper, a joint power allocation and phase shift optimization problem is studied for the downlink IRS-enabled HetNet, in which the IRS is deployed to enhance the communications between small cell users (SCUs) and associated base station (BS). The signal-to-interference-plus-noise ratio (SINR) received at the SCU is maximized by jointly optimizing the transmit power of the small-cell BS and the phase shift of the IRS, subject to the constraints on the minimum SINR requirement of the macro-cell user (MCU) and the phase shift. Although the formulated problem is non-convex, we develop an optimal power allocation and the IRS’s passive array coefficient solution for the single-user scenario. For the multi-user scenario, we propose an iterative algorithm to maximize the total rates of SCUs for obtaining a suboptimal solution by an alternating iteration manner, where the sum of multiple-ratio fractional programming problem is converted into a convex semidefinite program (SDP) problem. Simulation results show that the proposed algorithm significantly improves the achieved transmission rates of SCUs compared to the case without the IRS.

Grid-tied inverters are widely used for interfacing renewable energy sources or storage devices to low-voltage electrical power distribution systems. Lately, a number of different control techniques have been proposed to address the emerging requirements of the smart power system scenario, in terms of both functionalities and performance. This paper reviews the techniques proposed for the implementation of current-controlled or voltage-controlled inverters in microgrids. By referring to a voltage source inverter with LCL output filter, the different control architectures are classified as single-, double-, and triple- loop. Then, the functionalities that are needed or recommended in the grid-connected, islanded, and autonomous operating modes of the grid-tied inverter are identified and their implementation in the different control structures is discussed. To validate the analysis and to better illustrate the merits and limitations of the most effective solutions, six control strategies are finally implemented and experimentally compared on a single-phase, grid-connected inverter setup.

In this paper, a diffusion maximum correntropy criterion (DMCC) algorithm with adaption kernel width is proposed, denoting as DMCC$_{\rm adapt}$ algorithm, to find out a solution for dynamically choosing the kernel width. The DMCC$_{\rm adapt}$ algorithm chooses small kernel width at initial stage to improve its convergence speed rate, and uses large kernel width at completion stage to reduce its steady-state error. To render the proposed DMCC$_{\rm adapt}$ algorithm suitable for sparse system identifications, the DMCC$_{\rm adapt}$ algorithm based on proportional coefficient adjustment is realized and named as diffusion proportional maximum correntropy criterion (DPMCC$_{\rm adapt}$). The theoretical analysis and simulation results are presented to show that the DPMCC$_{\rm adapt}$ and DMCC$_{\rm adapt}$ algorithms have better convergence than the traditional diffusion AF algorithms under impulse noise and sparse systems.

Automatic modulation recognition (AMR) plays an important role in various communications systems. It has the ability of adaptive modulation and can adapt to various complex environments. Automatic modulation recognition is also widely used in orthogonal frequency division multiplexing (OFDM) systems. However, because the recognition accuracy of traditional methods to extract the features of OFDM signals is very limited. In order to solve these problems, many deep learning based AMR methods have been proposed to improve the recognition performance. However, most of these AMR methods neglect the harmful effect by carrier phase offset (PO) which often appears in real communications systems. Hence it is required to consider the PO effect for designing the OFDM system. Unlike conventional methods, we propose a convolutional neural network (CNN) based AMR method for considering PO in the OFDM system. The proposed method is used to eliminate the PO to achieve the high classification accuracy. Experiment results are provided to confirm the proposed method when comparing to conventional methods.

With the increasing penetration of renewable resources such as wind and solar, especially in terms of large-scale integration, the operation and planning of power systems are faced with great risks due to the inherent stochasticity of natural resources. Although this uncertainty can be anticipated, the timing, magnitude, and duration of fluctuations cannot be predicted accurately. In addition, the outputs of renewable power sources are correlated in space and time, and this brings further challenges for predicting the characteristics of their future behavior. To address these issues, this paper describes an unsupervised distribution learning method for renewable scenario forecasts that considers spatiotemporal correlation based on generative adversarial network (GAN), which has been shown to generate realistic time series for stochastic processes. We first utilize an improved GAN to learn unknown data distributions and model the dynamic processes of renewable resources. We then generate a large number of forecasted scenarios using stochastic constrained optimization. For validation, we use power generation data from the National Renewable Energy Laboratory wind and solar integration datasets. The simulation results show that the generated trajectories not only reflect the future power generation dynamics, but also correctly capture the temporal, spatial, and fluctuant characteristics of the real power generation processes. The experimental comparisons verify the superiority of the proposed method and indicate that it can reduce at least 50% of the training iterations of the generative model for scenario forecasts.

Providing connectivity to around half of the world population living in rural or underprivileged areas is a tremendous challenge, but also a unique opportunity. Access to the internet would provide the population living in these areas a possibility to progress on the educational, health, environment, and business levels. In this paper, a survey of technologies for providing connectivity to rural areas, and that can help address this challenge, is provided. Although access/fronthaul and backhaul techniques are discussed in the paper, it is noted that the major limitation for providing connectivity to rural and underprivileged areas is the cost of backhaul deployment. In addition, energy requirements and cost efficiency of the studied technologies are analyzed. In fact, the challenges faced for deploying an electricity network, as a prerequisite for deploying communication networks, are huge in these areas and they are granted an important share of the discussions in this paper. Furthermore, typical application scenarios in rural areas are discussed, and several country-specific use cases are surveyed. The main initiatives by key international players aiming to provide rural connectivity are also described. Moreover, directions for future evolution of rural connectivity are outlined in the paper. Although there is no single solution that can solve all rural connectivity problems, building gradually on the current achievements in order to reach ubiquitous connectivity, while taking into account the particularities of each region and tailoring the solution accordingly, seems to be the most suitable path to follow.

We investigate the use of ultrasound images as prior structural information (also known as ultrasound spatial priors) to guide microwave breast imaging so as to enhance its achievable complex permittivity images. In the main approach considered herein, the edges within the discretized ultrasound compressibility image are fed as spatial priors into a microwave imaging algorithm. It is shown that this method requires minimal post-processing of the ultrasound image and can enhance the achievable microwave image accuracy. It is also demonstrated that small tumours can still go undetected in microwave breast imaging using this method if their edges are missing from the spatial priors.

With the emergence of Internet of Things that allows communications and local computations, and with the vision of Industry 4.0, a foreseeable transition is from centralized system planning and operation toward decentralization with interacting components and subsystems, e.g., self-optimizing factories. In this paper, a new “price-based” decomposition and coordination methodology is developed to efficiently coordinate subsystems such as machines and parts, which are described by Mixed-Integer Linear Programming (MILP) formulations, in a distributed and asynchronous way. To ensure low communication requirements, exchanges between the “coordinator” and subsystems are limited to “prices” (Lagrangian multipliers) broadcast by the coordinator, and to subsystem solutions sent to the coordinator. Asynchronous coordination, however, may lead to convergence difficulties since the order in which subsystem solutions arrive at the coordinator is not predefined as a result of uncertainties in communication and solving times. Under realistic assumptions of finite communication and solve times, convergence of our method is proved by innovatively extending Lyapunov Stability Theory. Numerical testing of generalized assignment problems through simulation demonstrates that the method converges fast and provides near-optimal results, paving the way for self-optimizing factories in the future.

We present a smart Service Manager whose role is to direct user requests (such as those coming from IoT devices) at the edge towards appropriate servers where the services they request can be satisfied, when services can be housed at different Fog locations, and the system is subject to variations in workload. The approach we propose is based on using an SDN controller as a decision element, and to incorporate measurement data based machine learning that uses Reinforcement Learning to make the best choices. The system we have developed is illustrated with experimental results on a test-bed in the presence of time-varying loads at the servers. The experiments confirm the ability of the system to adapt to significant changes in system load so as to preserve the QoS perceived by end users.

In this paper, we investigate the two-way communication between two users assisted by a re-configurable intelligent surface (RIS). The scheme that two users communicate simultaneously in the same time slot over Rayleigh fading channels is considered. The channels between the two users and RIS can either be reciprocal or non-reciprocal. For reciprocal channels, we determine the optimal phases at the RIS to maximize the signal-to-interference-plus-noise ratio (SINR). We then derive exact closed-form expressions for the outage probability and spectral efficiency for single-element RIS. By capitalizing the insights obtained from the single-element analysis, we introduce a gamma approximation to model the product of Rayleigh random variables which is useful for the evaluation of the performance metrics in multiple-element RIS. Asymptotic analysis shows that the outage decreases at $\left(\log(\rho)/\rho\right)^L$ rate where $L$ is the number of elements, whereas the spectral efficiency increases at $\log(\rho)$ rate at large average SINR $\rho$. For non-reciprocal channels, the minimum user SINR is targeted to be maximized. For single-element RIS, closed-form solutions are derived whereas for multiple-element RIS the problem turns out to be non-convex. The latter is relaxed to be a semidefinite programming problem, whose optimal solution is achievable and serves as a sub-optimal solution.

In this paper, we propose a distributed solution for3D human pose estimation using a RGBD camera network. Thekey feature of our method is a dynamic hybrid consensus filter(DHCF) is introduced to fuse the multiple view informationof cameras. In contrast to the centralized fusion solution,the DHCF algorithm can be used in a distributed network,which requires no central information fusion center. Therefore,the DHCF based fusion algorithm can benefit from manyadvantages of distributed network. We also show that theproposed fusion algorithm can handle the occlusion problemseffectively, and achieve higher action recognition rate comparedto the ones using only single view information.