Air pollution is a severe problem growing over time. A dense air-quality monitoring network is needed to update the people regarding the air pollution status in cities. A low-cost sensor device (LCSD) based dense air-quality monitoring network is more viable than continuous ambient air quality monitoring stations (CAAQMS). An in-field calibration approach is needed to improve agreements of the LCSDs to CAAQMS. The present work aims to propose a calibration method for PM2.5 using domain adaptation technique to reduce the collocation duration of LCSDs and CAAQMS. A novel calibration approach is proposed in this work for the measured PM2.5 levels of LCSDs. The dataset used for the experimentation consists of PM2.5 values and other parameters (PM10, temperature, and humidity) at hourly duration over a period of three months data. We propose new features, by combining PM2.5, PM10, temperature, and humidity, that significantly improved the performance of calibration. Further, the calibration model is adapted to the target location for a new LCSD with a collocation time of two days. The proposed model shows high correlation coefficient values (R2) and significantly low mean absolute percentage error (MAPE) than that of other baseline models. Thus, the proposed model helps in reducing the collocation time while maintaining high calibration performance.

With the development of social media and human-computer interaction, it is essential to serve people by perceiving people's emotional state in videos. In recent years, a large number of studies tackle the issue of emotion recognition based on three most common modalities in videos, that is, face, speech and text. The focus of this paper is to sort out the relevant studies of emotion recognition using facial, speech and textual cues based on deep learning techniques due to the lack of review papers concentrating on the three modalities. In this paper, we firstly introduce widely accepted emotion models for the purpose of interpreting the definition of emotion. Then we introduce the state-of-the-art for emotion recognition based on unimodality including facial expression recognition, speech emotion recognition and textual emotion recognition. For multimodal emotion recognition, we summarize the feature-level and decision-level fusion methods in detail. In addition, the description of relevant benchmark datasets, the definition of metrics and the performance of the state-of-the-art in recent years are also outlined for the convenience of readers to find out the current research progress. Ultimately, we explore some potential research challenges and opportunities to give researchers reference for the enrichment of emotion recognition-related researches.

Current teleguidance methods include verbal guidance and robotic teleoperation, which present tradeoffs between precision and latency versus flexibility and cost. We present a novel concept of “human teleoperation” which bridges the gap between these two methods. A prototype teleultrasound system was implemented which shows the concept’s efficacy. An expert remotely “teloperates” a person (the follower) wearing a mixed reality headset by controlling a virtual ultrasound probe projected into the person’s scene. The follower matches the pose and force of the virtual device with a real probe. The pose, force, video, ultrasound images, and 3-dimensional mesh of the scene are fed back to the expert. In this control framework, the input and the actuation are carried out by people, but with near robot-like latency and precision. This allows teleguidance that is more precise and fast than verbal guidance, yet more flexible and inexpensive than robotic teleoperation. The system was subjected to tests that show its effectiveness, including mean teleoperation latencies of 0.27 seconds and errors of 7 mm and 6◦ in pose tracking. The system was also tested with an expert ultrasonographer and four patients and was found to improve the precision and speed of two teleultrasound procedures.

Intrusion Detection System (IDS) plays a vital role in detecting anomalies and cyber-attacks in networked systems. However, sophisticated attackers can manipulate the IDS’ attacks samples to evade possible detection. In this paper, we present a network-based IDS and investigate the viability of generating interpretable evasion attacks against the IDS through the application of a machine learning technique and an evolutionary algorithm. We employ a genetic algorithm to generate optimal attack features for certain attack categories, which are evaluated against a decision tree-based IDS in terms of their fitness measurements. To demonstrate the feasibility of our approach, we perform experiments based on the NSL-KDD dataset and analyze the algorithm performance.

The Internet of Things (IoT) is a fast-growing concept that involves the embedding of sensors into objects or “things” with the objective of bridging and exchanging data with other “things” over the internet. This concept is utilized in a variety of settings and used to create forms of technology such as wireless inventory trackers, wearable health monitors and even biometric cybersecurity scanners.This review aims to provide a summary of technological evolutions that led to the Internet of Things, and to discuss what the IoT is all about, while explaining its relevance in healthcare and pharmacy practice in particular.

Most pooling methods in state-of-the-art speaker embedding networks are implemented in the temporal domain. However, due to the high non-stationarity in the feature maps produced from the last frame-level layer, it is not advantageous to use the global statistics (e.g., means and standard deviations) of the temporal feature maps as aggregated embeddings. This motivates us to explore stationary spectral representations and perform aggregation in the spectral domain. In this paper, we propose attentive short-time spectral pooling (attentive STSP) from a Fourier perspective to exploit the local stationarity of the feature maps. In attentive STSP, for each utterance, we compute the spectral representations through a weighted average of the windowed segments within each spectrogram by attention weights and aggregate their lowest spectral components to form the speaker embedding. Because most energy of the feature maps is concentrated in the low-frequency region in the spectral domain, attentive STSP facilitates the information aggregation by retaining the low spectral components only. Moreover, due to the segment-level attention mechanism, attentive STSP can produce smoother attention weights (weights with less variations) than attentive pooling and generalize better to unseen data, making it more robust against the adverse effect of the non-stationarity in the feature maps. Attentive STSP is shown to consistently outperform attentive pooling on VoxCeleb1, VOiCES19-eval, SRE16-eval, and SRE18-CMN2-eval. This observation suggests that applying segment-level attention and leveraging low spectral components can produce discriminative speaker embeddings.

While metasurfaces (MSs) are constructed from deeply-subwavelength unit cells, they are generally electrically-large and full-wave simulations of the complete structure are computationally expensive. Thus, to reduce this high computational cost, non-uniform MSs can be modeled as zero-thickness boundaries, with sheets of electric and magnetic polarizations related to the fields by surface susceptibilities and the generalized sheet transition conditions (GSTCs). While these two-sided boundary conditions have been extensively studied for single sheets of resonant particles, it has not been shown if they can correctly model structures where the two sides are electrically isolated, such as a fully-reflective surface. In particular, we consider in this work whether the fields scattered from a fully reflective metasurface can be correctly predicted for arbitrary field illuminations, with the source placed on either side of the surface. In the process, we also show the mapping of a PEC sheet with a dielectric cover layer to bi-anisotropic susceptibilities. Finally, we demonstrate the use of the susceptibilities as compact models for use in various simulation techniques, with an illustrative example of a parabolic reflector, for which the scattered fields are correctly computed using a integral equation (IE) based solver.

This paper proposes a new optimization framework for NOMA-enabled cooperative vehicular network. In particular, we jointly optimize the vehicle paring, channel assignment, and power allocation at source and relaying vehicles. The objective is to maximize the sum rate of the system subject to the power allocation, minimum rate, relay battery lifetime and successive interference cancellation constraints. To solve the joint optimization problem efficiently, we adopt dual theory followed by Karush-Kuhn-Tucker (KKT) conditions, where the dual variables are iteratively computed through sub-gradient method. Two less complex suboptimal optimization schemes are also presented as the benchmark cooperative vehicular schemes.

In order to solve the problem of searching a radioactive source in a wide area, we developed a mobile CsI detector. This paper presented the performance of the detector during the spectra collection investigation. The 1 s spectrum collected by the detector was low-count spectrum and it is hard to distinguish whether it contains radioactive source signals. A rapid detection method of radioactive source based on low-count gamma spectra was proposed. Principal component analysis (PCA) was the key technology of the method. According to the PCA, the source information was efficiently extracted. With the method, the detect sensitivity and accuracy of the detector were optimized.

This paper presents the first design reconstruction on the Front-End-of-Line and Middle-of-Line layers of a 14 nm node FinFET design. To accomplish this, a large region of interest within a custom designed 14 nm node ASIC device was delayered, imaged, and analyzed to reconstruct the GDSII design file and verify a 100% match to the golden GDSII design. This work leveraged previous developments in each stage of the front half of the cooperative Verification and Validation (V&V) workflow combined with new techniques and processes developed for processing 3D architecture FET devices. We have demonstrated the critical first step to performing a full V&V workflow on an advanced technology node device, starting from the fabricated silicon device to the design extraction. The process development knowledge gained while reaching this milestone will further accelerate future advancements toward providing trusted advanced technology node devices in a timely manner.

This paper concentrates on tracking multiple targets using an asynchronous network of sensors with different sampling rates. First, a timely fusion approach is proposed for handling measurements from asynchronous sensors. In the proposed approach, the arithmetic average fusion of the estimates provided by local cardinalized probability hypothesis density filters is recursively carried out according to the network-wide sampling time sequence. The corresponding intersensor communication is conducted by a partial flooding protocol, in which either cardinality distributions or intensity functions pertinent to local posteriors are disseminated among sensors. Moreover, both feedback and non-feedback fusion-filtering modes are provided to meet the performance and real-time requirements, respectively. Second, an extension of the timely fusion approach referred to as robust bootstrap approach is presented, which can deal with unknown clutter and detection parameters by exploiting a local bootstrap filtering scheme. Finally, numerical simulations are performed to test the proposed approaches.

Due to the multi-hop, long-distance, and wireless backbone connectivity, provisioning critical and diverse services face challenges such as low latency and reliability. This paper proposes ioFog, an offline fog architecture for achieving reliability and low latency in a large backbone network. Our solution uses a Markov chain-based task prediction model to offer dynamic service requirements with minimal dependency on the Internet. The proposed architecture considers a central Fog Controller (FC) to (i) provide a global status overview and (ii) predict upcoming tasks of Fog Nodes for intelligent offloading decisions. The FC also has the current status of the existing fog nodes in terms of their processing and storage capabilities. Accordingly, it can schedule the possible future offline computations and task allocations. ioFog considers the requirements of individual IoT applications and enables improved fog computing decisions. As compared to the existing offline IoT solutions, ioFog improves service time significantly and service delivery ratio up to 23%.

Power transport theorem (PTT) governing the transport process of the power-flow passing through waveguide is derived. The input power as the source term in PTT is found to be the one for sustaining a stationary power transport, and the corresponding input power operator (IPO) is formulated. The travelling-wave condition satisfied by the travelling-wave modes one-directionally propagating along the waveguide is introduced as a counterpart of the famous Sommerfeld’s radiation condition satisfied by the radiative fields distributing in far zone. Employing the travelling-wave condition and some other necessary conditions, the dependent currents in IPO are effectively eliminated. Under PTT framework, the recently developed decoupling mode theory (DMT) for wave-port-fed antennas is further generalized to waveguides. The PTT-based DMT (PTT-DMT) focuses on constructing a set of energy-decoupled modes (DMs) for any pre-selected objective waveguide by orthogonalizing the IPO with only independent current, and any two different DMs don’t have net energy exchange in an integral period. The PTT-DMT is an effective alternative for classical eigen-mode theory. The alternative realizes an effective unification for waveguide-oriented modal analysis theory and antenna-oriented modal analysis theory, such that the theories can be easily integrated into a single theory for whole waveguide-antenna combined system in the future.

The Covid-19 disease has spread widely over the whole world since the beginning of 2020. Following the epidemic which started in Wuhan, China on January 30, 2020 the World Health Organization (WHO) declared a global health emergency and a pandemic. Researchers of different disciplines work along with public health officials to understand the SARS-CoV-2 pathogenesis and jointly with the policymakers urgently develop strategies to control the spread of this new disease. Recent findings have observed specific image patterns from computed tomography (CT) for patients infected by SARS-CoV-2 which are distinct from the other pulmonary diseases. In this paper, we propose an explainable-by-design that has an integrated image segmentation mechanism based on SLIC that improves the algorithm performance and the interpretability of the resulting model. In order to evaluate the proposed approach, we used the SARS-CoV-2 CT scan dataset that we published recently and has been widely used in the literature. The proposed Super-xDNN could obtain statistically better results than traditional deep learning approaches as DenseNet-201 and Resnet-152. Furthermore, it also improved the explainability and interpretability of its decision mechanism when compared with the xDNN basis approach that uses the whole image as prototype. The segmentation mechanism of Super-xDNN favored a decision structure that is more close to the human logic. Moreover, it also allowed the provision of new insights as a heat-map which highlights the areas with highest similarities with Covid-19 prototypes, and an estimation of the area affected by the disease.

Linear modulation techniques (LMTs) of an asymmetrical six-phase machine (ASPM) with two isolated neutral points synthesize the desired voltage vectors by applying at least five switching states. Different choices of applied voltage vectors, sequences in which they are used, distribution of dwell times among the redundant switching states give rise to a large number of possible LMTs. It is desirable that these LMTs avoid more than two transitions of a particular inverter leg within a carrier period. Only a subset of existing LMTs of ASPM follows this rule. Through an innovative approach, this paper finds a way to account for all possible infinitely many LMTs that follow the rule of at most two transitions per leg. Another important criterion for the selection of an LMT is its current-ripple performance. Therefore, through numerical optimization, the paper finds optimal LMTs among the above infinite possible LMTs for all reference voltage vectors in the linear range and for the whole feasible range of a machine parameter. This parameter is related to the leakage inductance of the machine and impacts the current ripple performance of ASPM. An optimal hybrid strategy is proposed with these optimal techniques, which outperforms all existing techniques in terms of the current ripple. The theoretical analysis is validated through simulation in Matlab and experiments performed up to 3.5 kW on a hardware prototype.

Clinical parameter estimation from the electrocardiogram (ECG) is a recurrent field of research. It is debated that ECG parameters estimation by human experts and machines/algorithms is always model-based (implicitly or explicitly). Therefore, all estimation algorithms used in this context have performance bounds in terms of the achievable mean squared error, which are not exceedable. These bounds depend on the adopted data-model, the estimation scheme (least-squares error, maximum likelihood, or Bayesian), and prior assumptions on the model parameters and noise distributions. In this research, we develop a comprehensive theoretical framework for ECG parameter estimation and derive the Cramér-Rao lower bounds (CRLBs) for the most popular signal models used in the ECG modeling literature, namely functional expansions (including polynomials) and sum of Gaussian functions. The developed framework is evaluated over real and synthetic data for three popular applications: T-to-R wave ratio estimation, ST-segment analysis and QT-interval estimation, using the state-of-the-art estimators in each context. The proposed framework and the derived CRLBs provide practical guidelines for the selection of data-models, sampling frequency (beyond the Nyquist rate), modeling segment length, number of beats required for ECG beat averaging, and other factors that influence the accuracy of ECG-based clinical parameter estimation.

Today’s Network Operation Centres (NOC) consist of teams of network professionals responsible for monitoring and taking actions for their network’s health. Most of these NOC actions are relatively complex and executed manually; only the simplest tasks can be automated with rules-based software. But today’s networks are getting larger and more complex. Therefore, deciding what action to take in the face of non-trivial problems has essentially become an art that depends on collective human intelligence of NOC technicians, specialized support teams organized by technology domains, and vendors’ technical support. This model is getting increasingly expensive and inefficient, and the automation of all or at least some NOC tasks is now considered a desirable step towards autonomous and self-healing networks. In this article, we investigate whether such decisions can be taken by Artificial Intelligence instead of collective human intelligence, specifically by the Machine Learning method of Reinforcement Learning (RL), which has been shown in computer games to outperform humans. We build an Action Recommendation Engine (ARE) based on RL, train it with expert rules or by letting it explore outcomes by itself, and show that it can learn new and more efficient strategies that outperform expert rules designed by humans. ARE can be used in face of network problems to either quickly recommend actions to NOC technicians or autonomously take actions for fast recovery. “This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.”

Prior to encoding an input RGB full-color image IRGB, at the server side, performing chroma subsampling on the converted chroma image is a necessary step. After receiving the decompressed subsampled chroma image and luma image at the client side, performing chroma upsampling is also a necessary step for reconstructing the RGB full-color image. In this paper, we consider seven commonly used chroma subsampling methods, denoted by Cs, and four widely used chroma upsampling methods, denoted by Cu. For each combination cs-cu in CsxCu, we first utilize the moment balance law to analyze the coordinate displacement (CD) bias problem occurring in cs. Next, for the combination cs-cu, we analyze the CD bias problem occurring in the transition from the server side to the client side. Then, we explain why the CD bias problem degrades the quality of the reconstructed RGB full-color images in the current coding system. To remedy this CD bias problem, a CD compensationbased (CDC-based) quality enhancement method is proposed to improve the quality of the reconstructed images. To the best of our knowledge, this is the first work in this research direction. Based on the IMAX, Kodak, SCI (screen content images), and Video datasets, the comprehensive experimental results have demonstrated that on the newly released versatile video coding (VVC) platform VTM-12.0, the proposed CDC-based quality enhancement method in our augmented coding system can achieve substantial quality improvement for 17 combinations in CsxCu.