Search

In this paper, we present an overview of Nearest neighbour (NN) methods, which are frequently employed for solving classification problems using supervised learning. The article concisely introduces the theoretical background, algorithmic, and implementation aspects along with the key applications. From an application standpoint, this article explores the challenges related to the 5G and beyond wireless networks which can be solved using NN classification techniques.

Grasp classification using data gloves can enable therapists to monitor patients efficiently by providing concise information about the activities performed by these patients. Although, classical machine learning algorithms have been applied in grasp classification, they require manual feature extraction to achieve high accuracy. In contrast, convolutional neural networks (CNNs) have outperformed popular machine learning algorithms in several classification scenarios because of their ability to extract features automatically from raw data. However, they have not been implemented on grasp classification using a data glove. In this study, we apply a CNN in grasp classification using a piezoresistive textile data glove knitted from conductive yarn and an elastomeric yarn. The data glove was used to collect data from five participants who grasped thirty objects each following Schlesinger’s taxonomy. We investigate a CNN’s performance in two scenarios where the validation objects are known and unknown. Our results show that a simple CNN architecture outperformed k-nn, Gaussian SVM, and Decision Tree algorithms in both scenarios in terms of the classification accuracy.

The rising number of technological advanced devices making network coverage planning very challenging tasks for network operators. The transmission quality between the transmitter and the end users has to be optimum for the best performance out of any device. Besides, the presence of coverage hole is also an ongoing issue for operators which cannot be ignored throughout the whole operational stage. Any coverage hole in network operators' coverage region will hamper the communication applications and degrade the reputation of the operator's services. Presently, there are techniques to detect coverage holes such as drive test or minimization of drive test. However, these approaches have many limitations. The extreme costs, outdated information about the radio environment and high time consumption do not allow to meet the requirement competently. To overcome these problems, we take advantage of Unmanned aerial vehicle (UAV) and Q-learning to autonomously detect coverage hole in a given area and then deploy UAV based base station (UAV-BS) by considering wireless back-haul with the core network and users demand. This machine learning mechanism will help the UAV to eliminate human-in-the-loop (HiTL) model. Later, we formulate an optimisation problem for 3D UAV-BS placement at various angular positions to maximise the number of users associated with the UAV-BS. In summary, we have illustrated a cost-effective as well as time saving approach of detecting coverage hole and providing on-demand coverage in this article.

This special issue (SI) aims to present recent advances in the design and analysis of communication interfaces for Industry 4.0. The Industry 4.0 paradigm aims to integrate advanced manufacturing techniques with Industrial Internet-of-Things (IIoT) to create an agile digital manufacturing ecosystem. The main goal is to instrument production processes by embedding sensors, actuators and other control devices which autonomously communicate with each other throughout the value-chain [1] .

The agriculture sector holds paramount importance in Pakistan due to the intrinsic agrarian nature of the economy. Pakistan has its GDP based on agriculture, however it relies on manual monitoring of crops, which is a labour intensive and ineffective method. In contrast to this, several cutting edge technology-based solutions are being employed in the developed countries to enhance the crop yield with the optimal use of resources. To this end, we have proposed an integrated approach for monitoring crop health using IoT, machine learning and drone technology. The integration of these sensing modalities generate heterogeneous data which not only varies in nature (i.e. observed parameter) but also has different temporal fidelity. The spatial resolution of these methods is also different, hence, the optimal integration of these sensing modalities and their implementation in practice are addressed in the proposed system. In our proposed solution, the IoT sensors provide the real-time status of environmental parameters impacting the crop, and the drone platform provide the multispectral data used for generating Vegetation Indices (VIs) such as Normalized Difference vegetation Index (NDVI) for analyzing the crop health. The NDVI provides information about the crop based on the chlorophyll content, which offers limited information regarding the crop health. In order to obtain a rich and detailed knowledge about crop health, the variable length time series data of IoT sensors and multispectral images were converted to a fixed-sized representation to generate crop health maps. A number of machine and deep learning algorithms were applied on the collected data wherein deep neural network with two hidden layers was found to be the most optimal model among all the selected models, providing an accuracy of (98.4%). Further, the health maps were validated through ground surveys and by agriculture experts due to the absence of reference data. The proposed research is basically an indigenous, technology based agriculture solution capable of providing important insights into the crop health by extracting complementary features from multi-modal data set, and minimizing the crop ground survey effort, particularly useful when the agriculture land is large in size.

For the first time, the design and implementation of a fully-integrated wireless information and power transfer system, operating at 24 GHz and enabling battery-less sensor nodes, is presented in this paper. The system consists of an RF power source, a receiver antenna array, a rectifier, and a battery-less sensor node which communicates via backscatter modulation at 868 MHz. The rectifier circuits use commercially available Schottky diodes to convert the RF power to DC with a measured efficiency of up to 35%, an improvement of ten percentage points compared with previously reported results. The rectifiers and the receive antenna arrays were jointly designed and optimised, thereby reducing the overall circuit size. The battery-less sensor transmitted data to a base station realised as a GNU Radio flow running on a bladeRF Software Defined Radio module. The whole system was tested in free-space in laboratory conditions and was capable of providing sufficient energy to the sensor node in order to enable operation and wireless communication at a distance of 0.15 metres.

In this research article, the design and fabrication of a miniaturized flexible rectifier at 24 GHz for wireless power transfer to wearables is presented. The proposed circuit consists of a shunt topology rectifier including a single stub impedance matching network. Conventional PCB fabrication technique is used for the prototyping of the proposed flexible rectifier. It has a total footprint of 5.29 cm2. The proposed rectifier exhibits a good trade-off between compactness and RF-to-DC conversion efficiency. The implementation on a very thin substrate (130 µm) makes it durable for wearables applications. Experimental results of the proposed rectifier show an output DC voltage of 2.0 V across an optimal load resistance of 250 Ω and measured RF-DC conversion efficiency of 23% for an input power of 17 dBm at 24 GHz.

Recently, convolutional neural network (CNN) has been widely investigated to decode human intentions using surface Electromyography (sEMG) signals. However, a pre-trained CNN model usually suffers from severe degradation when testing on a new individual, and this is mainly due to domain shift where characteristics of training and testing sEMG data differ substantially. To enhance inter-subject performances of CNN in the wrist kinematics estimation, we propose a novel regression scheme for supervised domain adaptation (SDA), based on which domain shift effects can be effectively reduced. Specifically, a two-stream CNN with shared weights is established to exploit source and target sEMG data simultaneously, such that domain-invariant features can be extracted. To tune CNN weights, both regression losses and a domain discrepancy loss are employed, where the former enable supervised learning and the latter minimizes distribution divergences between two domains. In this study, eight healthy subjects were recruited to perform wrist flexion-extension movements. Experiment results illustrated that the proposed regression SDA outperformed fine-tuning, a state-of-the-art transfer learning method, in both single-single and multiple-single scenarios of kinematics estimation. Unlike fine-tuning which suffers from catastrophic forgetting, regression SDA can maintain much better performances in original domains, which boosts the model reusability among multiple subjects.

This paper reports on the design and three-dimensional (3D) integration of low-cost, low-loss and easy-to-fabricate 3D-printed integrated lens antennas (ILAs) for 5G broadband wireless communications in the 28 GHz frequency range. The ILA designs consist of an extended hemispherical lens, fed by two different types of source antennas, a substrate integrated waveguide (SIW) slot antenna array and a microstrip patch antenna (MPA) array. Results from comprehensive parametric analyses of the infill pattern and density of the 3D printed dielectric lenses are also intensively investigated and characterized for their electromagnetic properties, e.g., electric-field distribution. The ILAs are fabricated using polylactic acid (PLA) as the fused deposition modelling (FDM) polymer with an optimized infill density of 50%, which speeds up prototyping time and decreases the relative permittivity, dielectric loss, manufacturing cost, and overall mass of the lens. These features are illustrated through experimental verification and characterization of at least three samples. From the measurement results, the ILAs achieve a fractional bandwidth of 10.7%, ranging from 26.5 to 29.4 GHz with a maximum gain of 15.6 dBi at boresight and half power beam-width of approximately 58° and 75° in the E and H planes, respectively.

Security is always an important issue in wireless communications. Physical layer encryption (PLE) is an effective way to enhance wireless communication security and prevent eavesdropping. Rather than replacing cryptography at higher layers, PLE's benefit is to enable using lightweight cryptosystems or provide enhanced security at the signal level. The upper cryptography is faced with a noise-free channel, and the processing object is bit data. In PLE, the effects of channel and noise can be exploited to enhance security and prevent deciphering. In addition, since the processing object is complex vector signals, there are more operational functions to select and design for PLE. The mathematical models, design frameworks, and cryptographic primitives of PLE are established. Two design frameworks are proposed: stream PLE and block PLE. For stream PLE, a new 3D security constellation mapping is derived. For block PLE, two types of sub-transforms are defined: isometry transformations and stochastic transformations. Furthermore, a practical system operation mode PLE-block chaining (PBC) is proposed to enhance the practical system security. The proposed PLE framework can resist known plaintext attacks and chosen-plaintext attacks. The simulation shows that the proposed isometry transformation method has good performances in terms of bit error ratio (BER) penalty and confusion degree.

Both the water and telecommunications sectors in the UK have an extensive pipe and duct network that has evolved over the last hundred years. Any given section of these networks is likely to be made from vitrified clay, cast iron or different types of plastic. In the Pipebots project, we are investigating robots that can inspect and, where possible, unblock or repair the pipes in-situ, with the aim of dramatically reducing the need for excavation works. This would require robots with the ability to wirelessly communicate with one another, as well as with the outside world, to realise the vision of an autonomous, cooperative swarm that continuously monitors, reports on, and repairs the pipes and ducts from within. The pipe environments in which the robots will operate vary significantly and this requires a custom solution that incorporates more than one method of communication. This paper describes the results of a study of the trade-off between data transmission bandwidth and Size, Weight, and Power (SWaP) requirements for acoustic, RF and optical communications systems.

In human-machine interfaces (HMI), deep learning (DL) techniques such as convolutional neural networks (CNN), long-short term memory networks (LSTM) and the hybrid CNN-LSTM framework have been exploited for hand kinematics estimation using surface electromyography (sEMG). However, these DL techniques only capture the relationship between sEMG and hand kinematics, but ignores the prior knowledge of the system. By contrast, Kalman filter (KF) can apply Kalman gain to combine the internal transition model and the observation model effectively. To this end, we propose a novel architecture named deep Kalman filter network (DKFN), in which we utilize CNN to extract high-level features from sEMG and employ a LSTM-based Kalman filter process (LSTM-KF) to conduct sequential regression. In particular, LSTM-KF adopts the computational graph of KF but estimates parameters of the transition/observation model and the Kalman gain from data using LSTM modules. With this process, the advantages of KF and LSTM can be exploited jointly. Experimental results demonstrate that the proposed DKFN can outperform CNN and CNN-LSTM in the sequential regression for wrist/fingers kinematics estimation.

Data gloves are the optimal data acquisition devices in hand-based gesture classification. Gesture classification involves the interpretation of the acquired raw data into defined gestures by applying machine learning techniques. Recently, the application of deep learning algorithms has improved the accuracy obtained in glove-based gesture classification. This chapter will review these deep learning approaches. In particular, we analyze their current performance, advantages over classical machine learning algorithms and limitations in certain classification scenarios. Furthermore, we present other deep learning approaches that may outperform current algorithms. This chapter will provide readers with an all-encompassing review that will enable a clear understanding of the current trends in glove-based gesture classification and provide new ideas for further research.

Weft knitted conductive fabrics can act as excellent textile strain sensors for human motion capture. The loop architecture dictates the overall electrical properties of weft knit strain sensors. Therefore, research into loop architecture is relevant for comprehensively investigating the design space of e-textile sensors. There are three main types of knit stitches, Knitted loop stitch, Miss stitch, and Tuck stitch. Nevertheless, most of the research into weft knit strain sensors has largely focused on fabrics with only knitted loop stitches. Miss and tuck stitches will affect the contact points in the sensor and, consequently, its piezoresistivity. Therefore, this paper investigates the impact of incorporating miss and tuck stitches on the piezoresistivity of a weft knit sensor. Particularly, the electromechanical models of a miss stitch and a tuck stitch in a weft knit sensor are proposed. These models were used in order to develop loop configurations of sensors that consist of various percentages of miss or tuck stitches. Subsequently, the developed loop configurations were simulated while using LTspice and MATLAB software, and, verified experimentally through a tensile test. The experimental results closely agree with the simulated results. Furthermore, the results reveal that increases in the percentage of tuck or miss stitches in weft knit sensor decrease the initial and average resistance of the sensor. In addition, it was observed that, although the piezoresistivity of a sensor with tuck or miss stitches is best characterised as a quadratic polynomial, increases in the percentage of tuck stitches in the sensor increase the linearity of the sensor&rsquo, s piezoresistivity.

Software Defined Networking (SDN) provides us with the capability of collecting network traffic information and managing networks proactively. Therefore, SDN facilitates the promotion of more robust and secure networks. Recently, several Machine Learning (ML)/Deep Learning (DL) intrusion detection approaches have been proposed to secure SDN networks. Currently, most of the proposed ML/DL intrusion detection approaches are based on supervised learning approach that required labelled and well-balanced datasets for training. However, this is time intensive and require significant human expertise to curate these datasets. These approaches cannot deal well with imbalanced and unlabeled datasets. In this paper, we propose a hybrid unsupervised DL approach using the stack autoencoder and One-class Support Vector Machine (SAE-1SVM) for Distributed Denial of Service (DDoS) attack detection. The experimental results show that the proposed algorithm can achieve an average accuracy of 99.35 % with a small set of flow features. The SAE-1SVM shows that it can reduce the processing time significantly while maintaining a high detection rate. In summary, the SAE-1SVM can work well with imbalanced and unlabeled datasets and yield a high detection accuracy.

Urban centers across the globe are under immense environmental distress due to an increase in air pollution, industrialization, and elevated living standards. The unmanageable and mushroom growth of industries and an exponential soar in population has made the ascent of air pollution intractable. To this end, the solutions that are based on the latest technologies, such as the Internet of things (IoT) and Artificial Intelligence (AI) are becoming increasingly popular and they have capabilities to monitor the extent and scale of air contaminants and would be subsequently useful for containing them. With centralized cloud-based IoT platforms, the ubiquitous and continuous monitoring of air quality and data processing can be facilitated for the identification of air pollution hot spots. However, owing to the inherent characteristics of cloud, such as large end-to-end delay and bandwidth constraint, handling the high velocity and large volume of data that are generated by distributed IoT sensors would not be feasible in the longer run. To address these issues, fog computing is a powerful paradigm, where the data are processed and filtered near the end of the IoT nodes and it is useful for improving the quality of service (QoS) of IoT network. To further improve the QoS, a conceptual model of distributed fog computing and a machine learning based data processing and analysis model is proposed for the optimal utilization of cloud resources. The proposed model provides a classification accuracy of 99% while using a Support Vector Machines (SVM) classifier. This model is also simulated in iFogSim toolkit. It affords many advantages, such as reduced load on the central server by locally processing the data and reporting the quality of air. Additionally, it would offer the scalability of the system by integrating more air quality monitoring nodes in the IoT network.

Software Defined Networking (SDN) is developing as a new solution for the development and innovation of the Internet. SDN is expected to be the ideal future for the Internet, since it can provide a controllable, dynamic, and cost-effective network. The emergence of SDN provides a unique opportunity to achieve network security in a more efficient and flexible manner. However, SDN also has original structural vulnerabilities, which are the centralized controller, the control-data interface and the control-application interface. These vulnerabilities can be exploited by intruders to conduct several types of attacks. In this paper, we propose a deep learning (DL) approach for a network intrusion detection system (DeepIDS) in the SDN architecture. Our models are trained and tested with the NSL-KDD dataset and achieved an accuracy of 80.7% and 90% for a Fully Connected Deep Neural Network (DNN) and a Gated Recurrent Neural Network (GRU-RNN), respectively. Through experiments, we confirm that the DL approach has the potential for flow-based anomaly detection in the SDN environment. We also evaluate the performance of our system in terms of throughput, latency, and resource utilization. Our test results show that DeepIDS does not affect the performance of the OpenFlow controller and so is a feasible approach.

With the rapid development of wireless communication technology and the emergence of the Industrial Internet of Things (IIoT)s applications, high-precision Indoor Positioning Services (IPS) are urgently required. While the Global Positioning System (GPS) has been a key technology for outdoor localization, its limitation for indoor environments is well known. UltraWideBand (UWB) can help provide a very accurate position or localization for indoor harsh propagation environments. This paper focuses on improving the accuracy of the UWB indoor localization system including the Line-of-Sight (LoS) and NonLine-of-Sight (NLoS) conditions by developing a Machine Learning (ML) algorithm. In this paper, a Naive Bayes (NB) ML algorithm is developed for UWB IPS. The performance of the developed algorithm is evaluated by Receiving Operating Curves (ROC)s. The results indicate that by employing the NB based ML algorithm significantly improves the localization accuracy of the UWB system for both the LoS and NLoS environment.

Agriculture holds paramount significance in Pakistan due to its high impact on gross domestic product (GDP). However, there is huge gap between actual production and estimated production in agriculture due to manual farming system, which is time-consuming, inefficient, and labor-intensive. As of today, ultra-modern technology such as Internet of Things (IoT) can assist in acquiring timely and accurate crop information essential for the success of precision agriculture technology. Towards such ends, the authors propose an IoT-based crop health monitoring system comprised of different sensors used in agricultural fields. Additionally, low altitude remote sensing platforms, such as drones, are used to capture the spectral imagery of the entire crop field of the study region. The development of such a system can be instrumental for crop status monitoring and localizing the areas under stress to maximize the agricultural output by leveraging the IoT technology.

This paper presents the design and implementation of efficient & compact flexible rectennas (antenna + rectifier) for wireless power transfer to wearable IoT sensor nodes at 24 GHz. Two different rectifier configurations i.e. shunt and voltage doubler have been analyzed for performance comparison. Experimental results of complete rectenna have also been demonstrated for conformal surfaces. The proposed flexible rectifiers is fabricated through conventional PCB manufacturing method. Measured RF-DC conversion efficiency of 31% and DC voltage of up to 2.4 V is achieved for 20 dBm input power across an optimal load resistance of 300Ω at 24 GHz.

The increased deployment of robots to automate repetitive, high precision, and difficult tasks is a key enabler for the Industry 4.0 paradigm. Robots and autonomous systems (RAS) provide significant productivity gains by allowing flexible production lines that can be dynamically reconfigured to manufacture highly customized products. However, such flexibility can only be harnessed when RAS are intelligent enough to adapt, communicate, and interact with one another and the operators, regardless of the operational environment.

The Khyber-Pakhtunkhwa government is about to pass a legislation (Police Bill 2016) to replace the colonial police law. Moreover, the provincial police administration has already taken certain measures to introduce modern information technology in the policing system. These measures were taken in the larger backdrop of provincial government’s interest in introducing egovernance in the province. In this article we discuss these measures with a focus on whether the police performance and human rights conditions have improved with them.

While stochastic geometric models based on Poisson point processes (PPPs) provide a tractable approach for the analysis of uniform two-tier network deployments, the performance evaluation of a non-uniform deployment remains an open issue, which we address in this paper. This is due to the fact that smaller cells can be more efficiently deployed in areas where the QoS of traditional macro base stations is poor. Therefore, in this paper, we introduce Stienen’s model, which allows us to analyse such non-uniform deployment. In contrast to traditional PPP-based analysis, performance characterization under the Stienen model is more challenging due to location and density dependencies. However, we demonstrate that the performance can be approximated in a tractable manner. The developed statistical framework is employed to characterize the gains in terms of energy efficiency (EE) for non-uniform deployments. Results show an achievable 19% to 124% improvement in the macrocell coverage as compared to a uniform deployment, while the femtocell coverage and system EE are of the same order of magnitude for both deployments. These results are complemented with the fact that OPEX and CAPEX are reduced due to a lesser number of FAPs deployed.

In this paper we consider the problem in which a single antenna mobile robot (MR) is required to maintain reliable communication with a base station (BS) while following a given trajectory. The wireless communication channel is assumed to experience time-varying small-scale fading with time-varying coherence time. To achieve high reliability and low latency of the communication link, compensation for the small-scale fading is required. Since the MR has to stay on the predefined trajectory, we propose to compensate for the fading by continuously adjusting the position of the antenna on a revolving platform on-board the MR. This is done by a closed-loop antenna controller which optimises the position of the antenna at all times without modifying the trajectory to be followed by the MR. Results show that this technique can effectively compensate for the small-scale fading without introducing delays in data reception.

Internet of Things (IoT)-based automation of agricultural events can change the agriculture sector from being static and manual to dynamic and smart, leading to enhanced production with reduced human efforts. Precision Agriculture (PA) along withWireless Sensor Network (WSN) are the main drivers of automation in the agriculture domain. PA uses specific sensors and software to ensure that the crops receive exactly what they need to optimize productivity and sustainability. PA includes retrieving real data about the conditions of soil, crops and weather from the sensors deployed in the fields. High-resolution images of crops are obtained from satellite or air-borne platforms (manned or unmanned), which are further processed to extract information used to provide future decisions. In this paper, a review of near and remote sensor networks in the agriculture domain is presented along with several considerations and challenges. This survey includes wireless communication technologies, sensors, and wireless nodes used to assess the environmental behaviour, the platforms used to obtain spectral images of crops, the common vegetation indices used to analyse spectral images and applications of WSN in agriculture. As a proof of concept, we present a case study showing how WSN-based PA system can be implemented. We propose an IoT-based smart solution for crop health monitoring, which is comprised of two modules. The first module is a wireless sensor network-based system to monitor real-time crop health status. The second module uses a low altitude remote sensing platform to obtain multi-spectral imagery, which is further processed to classify healthy and unhealthy crops. We also highlight the results obtained using a case study and list the challenges and future directions based on our work.

Backscatter communication has recently emerged as a promising technology to enable the passive sensing-based Internet-of-things (IoT) applications. In a backscatter communication network, uplink transmissions of multiple nodes are usually multiplexed in time- or frequency-domain to avoid collisions, yet it is desirable to improve the uplink capacity further. In this paper, we study a wireless-powered backscatter communication system, where the sensors use a hybrid channel access scheme by combining time division multiplexing access (TDMA) with power-domain non-orthogonal multiple access (PD-NOMA) to enhance the system performance in terms of outage probability and throughput. Our analysis shows that the proposed PD-NOMA increases both the spectrum efficiency and the throughput of the system.

In this paper, we tackle the design issue of optimal deployment of low power wide area network (LPWAN) Internet of Things (IoT) gateways (GWs). We classify GW deployment problem into two different categories, i.e., network-aware and network-agnostic. In network-aware GW deployment, precise location of IoT end devices (EDs) is known and thus the design questions are: 1) where to place GWs, i.e., to maximize received signal strength and 2) given received signal strength which GW should the ED be associated with to balance the network load. For, Network-agnostic GW deployment, same questions are answered in the absence of precise knowledge for the locations of EDs. For the network-aware deployment we borrow tools from machine-learning such as ${K}$ -means clustering for determination of optimal GW location. Subsequently, the link assignment problem is presented as an integer linear programming optimization. We prove that the network-agnostic GW deployment principle of placement of GWs at highest altitudes, if applied automatically, may lead to very deteriorated network performance increasing the network operational costs. Consequently, we introduce the concept of network-agnostic GW placement algorithm whereby the location of GWs can be estimated without prior knowledge of specific locations of EDs and we use it as a guiding principle to design spatial algorithm for finding GW locations. We show that spatial algorithm can, in principle, provide effective GW placement suggestions compared to a network-aware method such as ${K}$ -means clustering. We show that using a computational method for GW placement like ${K}$ -means or spatial algorithm, has a potential of creating competitive network performance using just the same number of GWs, thus cutting down the financial costs of the network and increasing its sustainability.

In this paper, we establish a cryptographic primitive for wireless communications. An asymmetric physical layer encryption (PLE) scheme based on elliptic curve cryptography is proposed. Compared with the conventional symmetric PLE, asymmetric PLE avoids the need of key distribution on a private channel, and it has more tools available for processing complex-domain signals to confuse possible eavesdroppers when compared with upper-layer public key encryption. We use quantized information entropy to measure the constellation confusion degree. The numerical results show that the proposed scheme provides greater confusion to eavesdroppers and yet does not affect the bit error rate (BER) of the intended receiver (the information entropy of the constellation increases to 17.5 for 9-bit quantization length). The scheme also has low latency and complexity [O(N2.37), where N is a fixed block size], which is particularly attractive for implementation.

Convolutional neural network (CNN) has been widely exploited for simultaneous and proportional myoelectric control due to its capability of deriving informative, representative, and transferable features from surface electromyography (sEMG). However, muscle contractions have strong temporal dependencies, but conventional CNN can only exploit spatial correlations. Considering that the long short-term memory (LSTM) neural network is able to capture long-term and nonlinear dynamics of time-series data, in this article, we propose a CNN-LSTM hybrid model to fully explore the temporal–spatial information in sEMG. First, CNN is utilized to extract deep features from the sEMG spectrum, and then, these features are processed via LSTM-based sequence regression to estimate wrist kinematics. Six healthy participants are recruited for the participatory collection and motion analysis under various experimental setups. Estimation results in both intrasession and intersession evaluations illustrate that CNN-LSTM significantly outperforms CNN, LSTM, and several representative machine learning approaches, particularly when complex wrist movements are activated.

Software Defined Networking (SDN) is emerging as a key technology for future Internet. SDN provides a global network along with the capability to dynamically control network flow. One key advantage of SDN, as compared to the traditional network, is that by virtue of centralized control it allows better provisioning of network security. Nevertheless, the flexibility provided by SDN architecture manifests several new network security issues that must be addressed to strengthen SDN network security. So, in this paper, we propose a Gated Recurrent Unit Recurrent Neural Network (GRU-RNN) enabled intrusion detection system for SDN. The proposed approach was tested using the NSL-KDD and CICIDS2017 dataset, and we achieved an accuracy of 89% and 99% respectively with low dimensional feature sets that can be extracted at the SDN controller. We also evaluated network performance of our proposed approach in terms of throughput and latency. Our test results show that the proposed GRU-RNN model does not deteriorate the network performance. Through extensive experimental evaluation, we conclude that our proposed approach exhibits a strong potential for intrusion detection in the SDN environments.

As a response to serious transmission security problems in wireless communications, physical layer encryption (PLE) provides an effective security measure which is very different from upper layer cryptography technologies. PLE can take advantage of the effects of channel and noise and the processing objects are complex vector signals, which are essentially different from Boolean algebra based traditional cryptography. This paper establishes mathematical models, design frameworks and cryptographic primitives for PLE. Two design frameworks are proposed: stream PLE and block PLE. For stream PLE, a new 3D security constellation mapping is derived. For block PLE, two types of sub-transforms are defined: isometry transformations and stochastic transformations. The proposed PLE framework has a large cipher signal space and key space; it provides more freedom in design and can resist known plaintext attacks and chosen-plaintext attacks.

In this work, we address the antenna tilt optimization problem for a two-tier cellular network consisting of macrocells and femtocells, where both tiers share the same spectrum and their positions are modeled via two independent Poisson point processes (PPPs). First, we derive the coverage probability for a traditional cellular network consisting only of macrocells and obtain the optimum tilt angle that maximizes the overall energy efficiency (EE). Gains of up to 400% in EE were found for a scenario (approximately) equivalent to a hexagonal cell deployment with cell radius of 200 m when the optimum tilt was selected. We then proceed to model the heterogeneous network (HetNet) scenario where femtocells are also deployed in the network’s area. We observe that the macrousers performance is highly sensitive to the interference emanating from the femtocell tier. In order to circumvent this issue, interference coordination employing a guard zone for the macrocell user is proposed. Subsequently, we formulate a joint optimization problem where we derive both, the radius of a guard zone protecting the macrouser and the tilt angle that maximize the EE of the network.

Low-Power Wide Area Networking (LPWAN) technology offers long-range communication, enabling new types of services for Internet-of-Things (IoT). While LPWAN solutions are proliferating verticals at tremendous pace, little attention has been paid to scalability and performance analysis of such networks. Hence, it is of utmost importance to analyze how well these technologies will scale as the number of connected devices grows in future. Several technologies are associated with LPWANs, but Longe Range WAN (LoRaWAN) is the most adopted LPWAN technology worldwide. It promises ubiquitous connectivity in outdoor IoT applications while keeping network structures and management as simple as possible. Consequently LORAWAN has received a lot of attention in recent time from network providers. In this letter, we first perform the system level outage analysis of a single LoRa gateway by using the chirp spectrum modulation scheme . We then extend our investigation to multiple gateway scenario and show that the coverage probability reduces exponentially when the number of gateways increases due to the presence of more interfering signals from different nodes using the same spreading sequence. We conclude that this fundamental limiting factor is perhaps more significant towards LoRa scalability. Our derivations for co-spreading factor interference found in multiple LoRa gateways enables demand of scalability analysis of such networks.

Software Defined Networking (SDN) has emerged as a key enabler for future agile Internet architecture. Nevertheless, the flexibility provided by SDN architecture manifests several new design issues in terms of network security. These issues must be addressed in a unified way to strengthen overall network security for future SDN deployments. Consequently, in this paper, we propose a Gated Recurrent Unit Recurrent Neural Network (GRU-RNN) enabled intrusion detection systems for SDNs. The proposed approach is tested using the NSL-KDD dataset, and we achieve an accuracy of 89% with only six raw features. Our experiment results also show that the proposed GRU-RNN does not deteriorate the network performance. Through extensive experiments, we conclude that the proposed approach exhibits a strong potential for intrusion detection in the SDN environments.

Small scale fading makes the wireless channel gain vary significantly over small distances and in the context of classical communication systems it can be detrimental to performance. But in the context of mobile robot (MR) wireless communications, we can take advantage of the fading using a mobility diversity algorithm (MDA) to deliberately locate the MR at a point where the channel gain is high. There are two classes of MDAs. In the first class, the MR explores various points, stops at each one to collect channel measurements and then locates the best position to establish communications. In the second class the MR moves, without stopping, along a continuous path while collecting channel measurements and then stops at the end of the path. It determines the best point to establish communications. Until now, the shape of the continuous path for such MDAs has been arbitrarily selected and currently there is no method to optimize it. In this paper, we propose a method to optimize such a path. Simulation results show that such optimized paths provide the MDAs with an increased performance, enabling them to experience higher channel gains while using less mechanical energy for the MR motion., 5 pages, 26th European Signal Processing Conference (EUSIPCO 2018)

Ambitious targets for aggregate throughput, energy efficiency and ubiquitous user experience are propelling the advent of ultra- dense networks. Intercell interference and high energy consumption in an ultra-dense network are the prime hindering factors in pursuit of these goals. To address the aforementioned challenges, in this paper, we propose a novel user-centric network orchestration solution for Cloud RAN based ultra-dense deployments. In this solution, a cluster (virtual disc) is created around users depending on their service priority. Within the cluster radius, only the best remote radio head (RRH) is activated to serve the user, thereby decreasing interference and saving energy. We follow a stochastic geometry based approach to quantify the area spectral efficiency (ASE) and RRH power consumption models to quantity energy(EE) efficiency of the proposed user-centric Cloud RAN (UCRAN). Through extensive analysis, we observe that the cluster sizes that yield optimal ASE and EE are quite different. Subsequently, we propose a game theoretic self-organizing network (GT-SON) framework that can orchestrate the network between ASE and EE focused operational modes in real-time in response to changes in network conditions and the operator's revenue model, to achieve a Pareto optimal solution. A bargaining game is modeled to investigate the ASE-EE tradeoff through adjustment in the exponential efficiency weightage in the Nash bargaining solution (NBS). Results show that compared to current non user-centric network design, the proposed solution offers the flexibility to operate the network at multiple folds higher ASE or EE along with significant improvement in user experience.

In this paper, the energy efficiency (EE) of different MIMO diversity schemes is analyzed for the downlink of a two-tier network consisting of both macro- and femto-cells. The locations of the base stations (BSs) in both tiers are modeled by spatial Poisson point processes (PPPs). The EE of the system in b/J/Hz is obtained for different antenna configurations under various diversity schemes. Adaptive modulation is employed to maximize both the throughput and the EE across both tiers. Borrowing well established tools from stochastic geometry, we obtain closed-form expressions for the coverage, throughput, and power consumption for a two tier rate adaptive cellular network. Building on the developed analytical framework, we formulate the resource allocation problem for each diversity scheme with the aim of maximizing the network-wide EE while satisfying a minimum QoS in each tier. We consider that both the number of antennas and the spectrum allocated to each tier constitute the network resource which must be efficiently selected for both tiers to maximize network-wide performance. The best performance in terms of the EE is provided by the schemes which strike a good balance between the achievable maximum throughput and the consumed power (both increasing with the number of RF chains used). In addition, the potential savings in EE by using femto-cells with sleeping mode capabilities are analyzed. It is observed that, when the density of active co-channel femto-cells exceeds a certain threshold, the EE of the system can be significantly improved by sleep scheduling.

In this letter, we introduce the concept of cloud empowered heterogeneous networks. We propose a simple yet efficient association mechanism for the selection of a serving remote radio head (RRH) for a desired mobile user (MU). We introduce the concept of user centric clustering which improves the user throughput by contributing on several fronts. Employing well established tools from stochastic geometry, we characterize the downlink coverage probability for the MU. The coverage probability is in turn employed to characterize the attainable throughput at a certain desired reliability constraint. Simulation results are presented to indicate the gains experienced by employing additional tiers in a cloud radio access network(C-RAN). Such gains are attributed to the distributed diversity which provides a power gain and hence increases the effective received SNR.

In this article, we present a unified perspective on the cognitive internet of things (CIoT). It is noted that within the CIoT design we observe the convergence of energy harvesting, cognitive spectrum access and mobile cloud computing technologies. We unify these distinct technologies into a CIoT architecture which provides a flexible, dynamic, scalable and robust network design road-map for large scale IoT deployment. Since the prime objective of the CIoT network is to ensure connectivity between things, we identify key metrics which characterize the network design space. We revisit the definition of cognition in the context of IoT networks and argue that both the energy efficiency and the spectrum efficiency are key design constraints. To this end, we define a new performance metric called the ‘overall link success probability’ which encapsulates these constraints. The overall link success probability is characterized by both the self-sustainablitiy of the link through energy harvesting and the availability of spectrum for transmissions. With the help of a reference scenario, we demonstrate that well-known tools from stochastic geometry can be employed to investigate both the node and the network level performance. In particular, the reference scenario considers a large scale deployment of a CIoT network empowered by solar energy harvesting deployed along with the centralized CIoT device coordinators. It is assumed that CIoT network is underlaid with a cellular network, i.e., CIoT nodes share spectrum with mobile users subject to a certain co-existence constraint. Considering the dynamics of both energy harvesting and spectrum sharing, the overall link success probability is then quantified. It is shown that both the self-sustainability of the link, and the availability of transmission opportunites, are coupled through a common parameter, i.e., the node level transmit power. Furthermore, provided the co-existence constraint is satisfied, the link level success in the presence of both the inter-network and intra-network interference is an increasing function of the transmit power. We demonstrate that the overall link level success probability can be maximized by employing a certain optimal transmit power. Characterization of such an optimal operational point is presented. Finally, we highlight some of the future directions which can benefit from the analytical framework developed in this paper.

International audience; In this article, we investigate how the performance of Massive MIMO cellular systems can be enhanced by introducing D2D communication. We consider a scenario where the base station (BS) is equipped with large, but finite number of antennas and the total number of UEs is kept fixed. The key design question is that what fraction of users should be offloaded to D2D mode in order to maximize the aggregate cell level throughput. We demonstrate that there exists an optimal user offload fraction, which maximizes the overall capacity. This fraction is strongly coupled with the network parameters such as the number of antennas at the BS, D2D link distance and the transmit SNR at both the UE and the BS and careful tuning of the offload fraction can provide up to 5× capacity gains.

Direct device-to-device (D2D) communication presents as an effective technique to reduce the load at the base station (BS) while ensuring reliable localized communication. In this paper, we propose a large-scale M2M data Aggregation and Trunking (MAT) scheme, whereby the user equipments (UEs) aggregate M2M data from the nearby MTDs and trunk this data along with their own data to the BS in the cellular uplink. We develop a comprehensive stochastic geometry framework by considering a Poisson hard sphere model for UE coverage. The main motivation of this model is to capture the fact that a UE can gather data from short range, low-power MTDs located only in its close proximity while ensuring that an MTD is associated to at most one UE. We explore the inherent trade-off between the time reserved for aggregation and successful trunking of data to the BS and compare our results with the baseline case where no aggregation mechanism is used. We show that while the baseline case of connecting a bulk of MTDs directly with the BS is prohibitive, MAT scheme can efficiently gather data from selected MTDs in a distributed manner.

IEEE 802.11ah has recently emerged as a promising standard for enabling massive machine-to-machine (M2M) communication. In order to support uplink data transmission from dense machine type clients (such as smart meters, IoT end nodes etc.), 802.11ah relies upon the restricted access window (RAW) based Medium Access Control (MAC) protocol. The underlying motivation behind this protocol is to reduce the contention for spectrum access among a large number of devices. The nodes contend with each other in their assigned RAW slot using Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA). In each RAW slot, the throughput depends upon the number of nodes. Current studies have suggested that the duration of each RAW slot should be the same in the entire RAW frame. However in this paper, we argue that the duration of each RAW slot should be chosen according to the size of the group. We present a model where a RAW frame is divided into two sub-frames and the duration of RAW slots in each sub-frame is chosen according to the size of the group. With the help of an analytical framework, we demonstrate that the throughput under our proposed scheme can be significantly enhanced when compared to a conventional implementation.

In this article, we develop a comprehensive analytical framework to characterize the area spectral efficiency of a large scale Poisson cognitive underlay network. The developed framework explicitly accommodates channel, topological and medium access uncertainties. The main objective of this study is to launch a preliminary investigation into the design considerations of underlay cognitive networks. To this end, we highlight two available degrees of freedom, i.e., shaping medium access or transmit power. While from the primary user's perspective tuning either to control the interference is equivalent, the picture is different for the secondary network. We show the existence of an area spectral efficiency wall under both adaptation schemes. We also demonstrate that the adaptation of just one of these degrees of freedom does not lead to the optimal performance. But significant performance gains can be harnessed by jointly tuning both the medium access probability and the transmission power of the secondary networks. We explore several design parameters for both adaptation schemes. Finally, we extend our quest to more complex point-to-point and broadcast networks to demonstrate the superior performance of joint tuning policies.

This paper presents a novel approach to the design and fabrication of low-cost and high-gain aperture-coupled microstrip patch antenna (AC-MPA) arrays with improved radiation pattern for millimetre-wave applications such as simultaneous wireless information and power transfer (SWIPT) and Internet-of-Things (IoT) device connectivity. A higher-order mode substrate integrated waveguide (SIW) cavity is used to feed the MPA arrays through aperture coupling. The improved design approach is introduced and discussed in detail. Simulation and experimental results for 2x2 and 4x4 arrays are presented, demonstrating excellent agreement. Key performance metrics are side-lobe levels of less than -24 dB and -29 dB in the E-plane and -22 dB and -26 dB in the H-plane and realized gain of 11 dBi and 15 dBi for the 2x2 and 4x4 arrays respectively, at a design frequency of 30 GHz.

In a recent letter, Guo et al. developed a novel method for inferring the wireless activity of other users by measuring the passive aggregate interference power received on a mobile device. The key objective of their study is to develop a non-intrusive method for activity sensing which does not rely on measurements from a live network. The proposed mobile crowd sensing mechanism relies on the analytical computation of the median of the aggregate interference, to estimate the activity levels in an OFDMA based communication system. A closed form expression for the median is obtained from the computation of the cumulative distribution function (CDF) for the aggregate co-channel interference. In this letter, we highlight that the expressions for the probability density function (PDF) and CDF of the aggregate interference obtained by inversion of the moment generating function (MGF) in Guo and Wang (Eqs. (5) and (6)) are only valid for $\alpha\!=\!4$ and they do not hold in general. Moreover, it is observed that authors employ the median of the aggregate interference, as the expectation of the interference power does not converge. In this letter, we show that this issue can be circumvented by using a non-singular path-loss model.

In this article, we quantify the achievable spatial throughput of a multi-antenna Poisson cognitive radio network (CRN) collocated with a Poisson multi-antenna primary network. CR users employ Slotted-ALOHA medium access control. The success probability (SP) of a primary link is quantified in the presence of the secondary and primary interferers. It is demonstrated that two fold gains are experienced by employing multiple antennas at primary, i.e., (i) the fixed high desired SP threshold is met; (ii) CRs can also be accommodated without QoS deterioration. Further in this paper, the maximum permissible medium access probability (MAP) for CRN is derived from the link SP and primary users QoS constraint. The impact of the number of antennas and modulation employed at the primary on the permissible MAP of the CRN is also explored. Assuming that CR users employ multi-hop communication, QoS aware relaying with a radian sector forwarding area is studied. The average forward progress (AFP) and isolation probability for a CR user with QoS based connectivity is characterized under the permissible MAP. The spatial throughput for the CRN is quantified by the analysis of the AFP and the permissible MAP. It is shown that there exists an optimal MAP which maximizes the spatial throughput of the CRN. This optimal MAP is coupled with the permissible MAP, density of users, number of antennas and modulation schemes employed in both primary and secondary networks. Lastly, a few important design questions are investigated for multi-hop MIMO underlay CRNs.

Software Defined Networking (SDN) has recently emerged to become one of the promising solutions for the future Internet. With the logical centralization of controllers and a global network overview, SDN brings us a chance to strengthen our network security. However, SDN also brings us a dangerous increase in potential threats. In this paper, we apply a deep learning approach for flow-based anomaly detection in an SDN environment. We build a Deep Neural Network (DNN) model for an intrusion detection system and train the model with the NSL-KDD Dataset. In this work, we just use six basic features (that can be easily obtained in an SDN environment) taken from the forty-one features of NSL-KDD Dataset. Through experiments, we confirm that the deep learning approach shows strong potential to be used for flow-based anomaly detection in SDN environments.

In this paper, the downlink performance of two-tier heterogenous network is investigated. We consider a scenario where the macro-tier is empowered by massive antenna-array thus allowing for Massive multiple-input multiple-output (MIMO) transmission scheduling. The small cellular network complements the macro-tier capacity. We propose a novel channel allocation mechanism which optimally splits the spectral resources to maximize network level throughput and energy efficiency. Our proposed channel allocation mechanism is robust to the topological and channel variations. More specifically, the proposed scheme is designed by capturing the random locations of the users in both tiers by a Poisson Point Process (PPP). The channel uncertainty is captured by considering Rayleigh fading complemented by large scale power law path-loss. Our analysis shows that there exists an optimal split which maximizes the network wide throughput and energy efficiency. We also demonstrate that there exists an optimal transmit power which maximizes the energy efficiency for the network. Under different scenarios, massive MIMO plays a vital role in improving sum rate capacity as compared to single antenna femtocells. Finally, using implementation parameters, we obtain the optimal configurations that improve system capacity and energy efficiency.

Resilient communication networks, which can continue operations even after a calamity, will be a central feature of future smart cities. Recent proliferation of drones propelled by the availability of cheap commodity hardware presents a new avenue for provisioning such networks. In particular, with the advent of Google's Sky Bender and Facebook's internet drone, drone empowered small cellular networks (DSCNs) are no longer fantasy. DSCNs are attractive solution for public safety networks because of swift deployment capability and intrinsic network reconfigurability. While DSCNs have received some attention in the recent past, the design space of such networks has not been extensively traversed. In particular, co-existence of such networks with an operational ground cellular network in a post-disaster situation has not been investigated. Moreover, design parameters such as optimal altitude and number of drone base stations, etc., as a function of destroyed base stations, propagation conditions, etc., have not been explored. In order to address these design issues, we present a comprehensive statistical framework which is developed from stochastic geometric perspective. We then employ the developed framework to investigate the impact of several parametric variations on the performance of the DSCNs. Without loss of any generality, in this article, the performance metric employed is coverage probability of a down-link mobile user. It is demonstrated that by intelligently selecting the number of drones and their corresponding altitudes, ground users coverage can be significantly enhanced. This is attained without incurring significant performance penalty to the mobile users which continue to be served from operating ground infrastructure.