Search

The current quality assessment for fruits and vegetables relies on subjective human judgment and manual inspection, resulting in inconsistencies and inefficiencies. Due to that, there is a need for a real-time system that can accurately and efficiently assess the quality of fruits and vegetables by analyzing various parameters, such as color, texture, size, and blemishes, to ensure consistency and reduce waste in the food supply chain. This study presents the development of a real-time tomato classification system using a hybrid model that combines convolutional neural network (CNN) and support vector machines (SVMs) deployed on the embedded single-board NVIDIA Jetson TX1. The selected CNN model EfficientNetB0 was used for feature extraction and SVM for classification. Notably, the EfficientNetB0-SVM hybrid model demonstrated impressive efficiency, achieving an average accuracy of 93.54% for classifying static tomato images stored in a board into healthy or reject with a testing time of 0.0216-s per image. Also, during real-time implementation, the proposed hybrid model attained an average inference speed of 15.6 frames per second (15.6 FPS), with an accuracy of 78.57% in classifying actual tomatoes into healthy or reject. The classification decision was taken based on 5 images for each tomato captured at different angles to ensure the detection of any blemishes from almost all sides of the tomato. The performance of the proposed model outperforms that of the state-of-the-art (SOTA) methods in accuracy, testing time per image, and real-time prediction accuracy. [ABSTRACT FROM AUTHOR]

The integration of cloud computing (CC) and Internet of Things (IoT) technologies in the healthcare industry has significantly boosted the importance of real-time remote patient monitoring. The Internet of Medical Things (IoMT) systems facilitate the seamless transfer of health records to data centers, allowing medical professionals and caregivers to analyze, process, and access them. This data is often stored in cloud-based systems. Nevertheless, the transmission of data and execution of computations in a cloud environment may lead to delays and affect the efficiency of real-time healthcare services. In addition, the use of edge computing (EC) layers has become prevalent in performing local data processing and storage to reduce service response times for IoMT applications. The main objective of this article is to develop an adaptive EC infrastructure for IoMT systems, with a specific emphasis on maintaining optimal performance for real-time health services. It also designs a model to predict the server resources required to meet service level agreements (SLAs) regarding response time. Simulation results demonstrate that EC significantly improves service response time for real-time IoMT applications. The proposed model can accurately and efficiently predict the computing resources required for medical data services to achieve SLAs under varying workload conditions. [ABSTRACT FROM AUTHOR]

The advent of 6G communication systems has enabled, through integrated sensing and communications (ISAC), the vision of the intelligent connection of everything. Since such ISAC systems will be utilizing the sub-6-GHz and millimeter-wave (mm-wave) bands, appropriate hybrid, i.e., sensing and communication channel models, are required for their proper operation. This article first presents a comprehensive survey of channel models used in ISAC applications viewed from different modeling perspectives by identifying the challenges encountered in these modeling approaches. A novel hybrid approach for ISAC channel modeling is then introduced wherein the modeling methodology is partitioned into three elements: targets, clutters, and interferences. The advantage of such a flexible modeling approach using these three elements enhances the proposed model’s ability to effectively deal with the specific sensing and communication operational requirements. Finally, further performance enhancement methods, based upon real-time 3D environment reconstruction techniques as well as artificial intelligence (AI), are proposed and discussed. [ABSTRACT FROM AUTHOR]

In the current subsea industry scenario, autonomous underwater vehicles (AUVs) are widely used for expeditions and explorations. However, the mission duration is limited due to the limitations in the battery capacity. To increase the endurance, there is a need for a submerged docking station (DS) to charge the battery, also to update the next mission profile. In this letter, deep learning (DL) technique aided short-range vision guidance is envisaged for a reliable and precise AUV homing operation. Intelligent control algorithms with an efficient DL-based you only look once (YOLO) v5-image processing techniques are used for DS detection and tracking and deployed in an edge computer integrated into AUV prototype. The developed illuminated DS and AUV prototype with high-definition camera has been demonstrated in test tank at depth of 2 m. An analysis was conducted on the DS data set, which comprised 132 images of clear and turbid water, 13 were designated for testing, 40 for validation, and 79 for training purposes. The results were observed that the probability of detecting the DS is 95%, detection range is 5 m, the probability of homing toward the DS is CEP 90 with the position error of 5% in less-turbid waters and in high-turbid waters, 60% is the probability of DS detection with position error up to 25%, detectable range is 1 m. The proposed embedded hardware is extremely useful for underwater reliable homing applications. [ABSTRACT FROM AUTHOR]

Neuromusculoskeletal (NMS) models enable non-invasive estimation of clinically important internal biomechanics. A critical part of NMS modelling is the estimation of musculotendon kinematics, which comprise musculotendon unit lengths, moment arms, and lines of action. Musculotendon kinematics, which are partially dependent on joint angles, define the non-linear mapping of muscle forces to joint moments and contact forces. Currently, real-time computation of musculotendon kinematics requires creation of a per-individual surrogate model. The computational speed and accuracy of these surrogates degrade with increasing number of coordinates. We developed a feed-forward neural network that completely encodes musculotendon kinematics of a target model across a wide anthropometric range, enabling accurate real-time estimates of musculotendon kinematics without need for a priori creation of a per-individual surrogate model. Compared to reference, the neural network had median normalized errors ~0.1% for musculotendon lengths, <0.4% for moment arms, and <0.10° for line of action orientations. The neural network was employed within an electromyogram-informed NMS model to calculate hip contact forces, demonstrating little difference (normalized root mean square error $1.23\pm 0.15$ %) compared to using reference musculotendon kinematics. Finally, execution time was <0.04 ms per frame and constant for increasing number of model coordinates. Our approach to musculoskeletal kinematics may facilitate deployment of complex real-time NMS modelling in computer vision or wearable sensors applications to realize biomechanics monitoring, rehabilitation, and disease management outside the research laboratory. [ABSTRACT FROM AUTHOR]

Recently, pressure-sensing mats have been widely used to capture static and dynamic pressure over sleep for posture recognition. Both a full-size mat with a low-density sensing array for figuring out the structure of the whole body and a miniature scale mat with a high-density sensing array for identifying the local characteristics around the chest have been investigated. However, both of the mat systems may face the challenge in the trade-off between the computational complexity (involving the size, density, etc. of the mat) and the performance of sleep posture recognition, where high performance may requires overcomplex computation and result in time latency in real-time sleep posture monitoring. In this paper, a lightweight neural network named ConcatNet, is proposed to realize sleep postures (supine, left, right, and prone) recognition in real time while maintaining a favorable performance. In ConcatNet, the inception module is proposed to extract the image features under multiple receptive fields, while the multi-layer feature fusion module is utilized to fuse deep and shallow features to enhance the model performance. To further improve the efficiency of the model, the depthwise convolution is adopoted. ConcatNet models in 3 different scales (ConcatNet-S, ConcatNet-M, and ConcatNet-L) are built to explore the impact of the sensor density on sleep posture recognition performance. Experimental results exhibit that ConcatNet-M corresponding to medium sensor density (${16}\times {16}$) achieved the best comprehensive performance, with short-term data cross-validation accuracy at 95.56% and overnight data testing accuracy at 94.68%. The model size is 7.91KB, FLOPs is 56.47K, and the inference time is only 0.38ms, which shows an outstanding performance of real-time sleep posture recognition with minimum consumption, indicating the potential to be deployed in mobile devices. [ABSTRACT FROM AUTHOR]

Under a connected environment, demand information such as vehicle routes in urban networks is accessible. Based on space-time trajectories, this article proposes a real-time network-wide coordinated control strategy within a rolling horizon scheme. A traffic demand framework involving route and arrival and departure times at each intersection is introduced to describe the space-time trajectories of vehicles in the network. In the coordinated control optimization algorithm, the following two steps are iterated: first, the departure time of vehicles with minimal total delay is optimized by a nonfixed intersection signal control model; then, the arrival time is updated according to the departure time and the link travel time. The intersection signal control strategy is composed of a duration division, vehicle aggregates, and an optimization model, where the signal timing plan with minimal delay can be obtained via the departure time. The simulation results indicate that the proposed approach is capable of optimizing the signal timing plan and decreasing vehicle delay given the demand information of vehicles. [ABSTRACT FROM AUTHOR]

We present in this article a simple yet efficient algorithm named you only look once: dynamic and stem (YOLO-DS), which can better complete real-time intelligent transportation detection. YOLO-DS is accomplished based on YOLOv5s through the following primary modifications. First, we apply a dynamic mechanism in the backbone. The dynamic mechanism enables the model to be a multibranch model during training and a single-path model during inference and deployment. Hence, our model can enjoy the benefits of fast speed and economical memory while maintaining excellent performance. Second, the original focus module in the backbone is inefficient. Accordingly, we employ the stem module (built entirely with standard convolution) instead of the focus module in the backbone. Finally, we modify the width and depth of the model and redesign a new, lighter detection head to improve the model further. Compared to the original YOLOv5s, YOLO-DS improves the mean average precision (AP) by 2.7 and 0.2 on the University at Albany DETection and tRACking and the high-speed train fault dataset. In addition, experiments conducted on various devices show that the speed of YOLO-DS is highly impressive, far exceeding previous lightweight neural networks. Specifically, the inference speed of YOLO-DS is twice that of the original YOLOv5s, up to 7.98 times. Moreover, our YOLO-DS-Tiny processes an image with 640 × 640 resolution averaging barely 35 ms on a cellphone (the Honor V20). [ABSTRACT FROM AUTHOR]

To compete with battery electric vehicles, fuel cell (FC) hybrid electric vehicles (FCHEVs) are required to offer better performance in fuel economy and FC durability. To this end, this article proposes a novel real-time adaptive model predictive control (AMPC)-based energy management strategy (EMS) for FCHEVs to improve their fuel efficiency and mitigate the degradation of their onboard FC hybrid systems. First, a linear parameter-varying (LPV) prediction model of the FC hybrid system that considers the system parameter variation is developed. The model offers sufficient accuracy while enabling the real-time implementation capability of the AMPC. Then, an AMPC strategy is proposed to optimally distribute the load current of the FCHEV between the FC and the battery in real time. In each control interval of the AMPC, the LPV prediction model is updated online to adapt to the variations of the battery state of charge. The constrained optimization problem of the AMPC is then formulated to achieve a desired tradeoff among four performance metrics and is further transformed into a quadratic programming problem, which can be solved in real time. Hardware-in-the-loop tests are performed on a downscaled FC hybrid system with the proposed AMPC-based EMS, a commonly used rule-based EMS, an equivalent consumption minimization strategy, and an improved MPC-based EMS, respectively. Results show that among the four real-time EMSs, the AMPC-based EMS achieves the best performance in reducing hydrogen consumption and FC current fluctuation and the smallest optimality gap with respect to an offline dynamic programming-based optimal EMS. [ABSTRACT FROM AUTHOR]

In many popular parallel programming models, e.g., OpenMP (OpenMP, 2013), applications are usually dispatched into several dedicated scheduling entities (named ”threads” in common) for which the processor time of physical platform is provided through the OS schedulers. This behavior requires for a hierarchical scheduling framework, considering each thread as a virtual processor (VP). Moreover, hierarchical scheduling allow separate applications to execute together on a common hardware platform, with each application having the “illusion” of executing on a dedicated component. However, the problem for scheduling parallel real-time tasks on virtual multiprocessor platform has not been addressed yet. An analogous approach to virtual scheduling for parallel real-time tasks is federeted scheudling, where each task exclusively executes on a set of dedicated physical processors. However, federated scheduling suffers significant resource wasting. In this article, we study the scheduling of real-time parallel task on virtual multiprocessors. As a physical processor is shared by virtual processors, tasks effectively share processors with each other. We conduct comprehensive performance evaluation to compare our proposed approach with existing methods of different types. Experiment results show that our approach consistently outperforms existing methods to a considerable extent under a wide range of parameter settings. [ABSTRACT FROM AUTHOR]

The recommendation of taxi pickup locations plays an important role for drivers in carrying passengers efficiently. In addition, the emergence of the Internet of Vehicles provides technical support for it. However, existing recommendation methods do not model dynamic global positioning system information well and in real-time. In this article, we propose a spatio-temporal digraph convolutional network (STDCN) model. First, the pickup and drop-off locations are modeled into a directed spatio-temporal graph as input to the model. The correlation between each node is calculated as a unified edge weight based on the gray relational analysis. Then, the STDCN is used for dynamic spatio-temporal feature extraction. Finally, the edge-cloud collaboration framework is adopted to recommend local taxi pickup locations in real-time. The experimental results show that the proposed method is better than competing methods in terms of effectiveness and efficiency, and it shows good industrial conversion application prospects. [ABSTRACT FROM AUTHOR]

Deep-learning techniques have been widely used in pipeline leakage aperture identification. However, most are designed and implemented for offline data, with problems such as large parameters, high memory consumption, and poor noise immunity. To solve the problem, this article presents a lightweight residual convolutional neural network (L-Resnet) applied to a real-time detection platform to achieve real-time identification of pipeline leakage apertures. First, based on the depth separable technique, two different separable residual modules are constructed to realize the feature extraction of signals; then, a more efficient activation function is applied to the high-dimensional space to enhance the nonlinear capability of the model; after that, a lightweight attention mechanism is used to weight the features to distinguish the importance of different features; finally, the classification results are obtained by a classifier. The real-time detection platform consists of Jetson Nano, the signal acquisition module, and the processing circuit. The results indicated that the method could accurately identify the pipeline leakage apertures in real time. Moreover, the number of parameters is only 14.71 kb, and the model has good computing efficiency and robustness compared to other methods. [ABSTRACT FROM AUTHOR]

Hardware-in-the-loop systems are a type of Hard real-time system that require a faster than real-time simulation. A method of running hard real-time systems with slower than real-time simulations is devised. Instead of waiting for the real-time subsystem output to a simulation, multiple simulation input predictions are generated and used to run several parallel simulation paths independent of the real-time subsystem. The simulation path results are stored until needed by the real-time subsystem at which time one is selected and returned to it to continue the execution of the system. A test case using a small modular reactor nuclear power plant hardware-in-the-loop system was used to demonstrate the effects of slower than real-time simulations on a hard real-time system and to show that this method allows such a simulation to be used. [ABSTRACT FROM AUTHOR]

The trend toward higher switching frequency and larger scale of power electronic systems poses challenges for real-time simulation. This article presents an event-driven hardware-in-the-loop (ED-HIL) simulation framework that does not rely on the small fixed simulation step-size related to the switching frequency. ED-HIL framework can improve the calculation efficiency by positioning switch events and using variable simulation step-size. Further, a parallel acceleration and circuit partitioning (PACP) solver is proposed based on this framework. The PACP solver partitions the circuit with energy storage elements and ensures that the partitioning does not introduce simulation distortion by using the higher order derivatives of the energy storage elements. Meanwhile, it achieves a process-level paralleling through a shared memory architecture in order to accelerate the simulation. As a result, the proposed PACP solver based on the ED-HIL framework can achieve about three times the simulation scale of a commercial FPGA-based real-time simulator at 1/16 the hardware cost under the same conditions. An accurate real-time HIL example of a power electronic transformer with 32 switches at a switching frequency of 20 kHz has been implemented on a personal computer. The simulation results are analyzed by comparing with experiment, offline software, and commercial real-time simulator. [ABSTRACT FROM AUTHOR]

The introduction of information and communication technologies makes network environments increasingly open, leaving smart-grid control systems incredibly vulnerable to malicious attacks. False data injection (FDI) attacks stealthily tamper with measurement data, resulting in erroneous decisions made by the control center that greatly influence the normal operation of the power system. By taking advantage of real-time data acquisition with edge computing, in this article, we propose a scheme based on classification of predicted residuals (CPRs) for the FDI attack detection. The CPR scheme first predicts the acquired measurement data at the edge of the sensing network via developing an accurate prediction model. Followed the novel real-time classification method under the edge devices supporting, it classifies the predicted residuals independent of the false data to enhance the detection accuracy. Through these two steps, the detection rate of FDI attacks is greatly improved. The proposed scheme is validated in a real microgrid testbed. Experimental results show that the CPR scheme performs well in detecting FDI attacks and remains sensitive in injection attack probability and magnitude. The detection scheme even has effectiveness at low injection attack probability and magnitude (5% and 0.018 per thousand, respectively). Furthermore, it also proves that the proposed scheme has applicability in high real-time requirements at the edge of smart grids. [ABSTRACT FROM AUTHOR]

Prompt online detection of anomalies induced by malicious attacks enhances the efficacy of real-time operation and mitigation of attack, an indispensable part of any cyber-physical system (CPS) management. This article proposes a novel online rapid detection scheme that continuously monitors the data packet stream and infers the sequence of probability distributions, estimated as histograms, and alerts when a change in the histogram is detected, reporting both the attack as well as an estimate of its instant of commencement. A statistical data-driven attack model is proposed and employed that is general enough to represent two ubiquitous types of attacks on CPS: 1) replay and 2) bias-injection. The proposed detection framework relies on the fact that CPSs possess well-defined dynamics that are affected by quasistationary noise, which allows the histogram sequences of the system data packets to converge (to different distributions under the presence of the attack versus the absence of attack). The proposed online scheme detects an attack, and estimates the attack commencement time by relying on the computed distance between real-time estimated histogram versus apriori learned nominal histogram. Our formulation further sheds light on two different attack initiation-time-based subcases, “early” (attack starts before sufficient data of nominal behavior was collected to allow its histogram sequence to be closer to its nominal value) versus “late.” The designed algorithm of our scheme has linear time complexities in the dimension of data packets and algorithm parameters, which makes it suited for rapid detection. The proposed algorithm is implemented and validated on two real supervisory control and data acquisition system datasets, where a low detection delay demonstrates the effectiveness of the scheme. [ABSTRACT FROM AUTHOR]

The real-time coscheduling problem, where tasks may have multiple phases executing on different types of processors, is known to be hard. The (already hard) self-suspending task scheduling simplifies the coscheduling problem by assuming that the latency a task may experience on the other type of processors is naturally bounded, which is unfortunately not true in practice. In this article, we present a novel analysis technique, namely, the vertical view analysis, for analyzing the schedulability of coscheduling sporadic tasks under global earliest-deadline-first (GEDF) on a heterogeneous multiprocessor consisting of two types of processors. We derive both hard (no deadline miss) and soft (bounded response times) real-time utilization-based tests. To the best of our knowledge, these results are the first-of-its-kind for the coscheduling problem and may allow real-time schedulability analysis to be carried out on more practical scenarios under heterogeneous computing. [ABSTRACT FROM AUTHOR]

New generation airborne embedded system has deployed Graphical Processing Units (GPUs) to raise processing capability to meet growing computational demands. Comparing with the cloud system, the airborne embedded system usually has a fixed application set, but strict real-time constraints. Unfortunately, the inherent GPU scheduler does not consider the application priority, which cannot provide the sufficient real-time capability to the airborne embedded system. To meet timeliness requirements, it is necessary to predict timing behaviors of those applications and design a real-time scheduling policy based on priority and deadline. We therefore propose WAMP $^2$ 2 S, a workload-aware GPU performance model based pseudo-preemptive real-time scheduling algorithm for the airborne embedded system. The workload-aware GPU performance model can accurately predict the execution time of an application, which is running concurrently with other applications on GPU. The pseudo-preemptive real-time scheduling algorithm can provide the approximate preemption by dynamically adjusting GPU computing resources for active applications. Unlike previous work on GPU performance model and GPU real-time scheduling, WAMP $^2$ 2 S considers the impact of co-executing workload on the execution time estimation and provides a software-only approach for preemption support. In addition, WAMP $^2$ 2 S implements a prototype GPU scheduler without any source code analysis. We evaluate the proposed GPU performance model and real-time scheduling algorithm in both simulated and realistic application sets. Experimental results illustrate that WAMP $^2$ 2 S can achieve low prediction error and high scheduling success ratio. [ABSTRACT FROM AUTHOR]

The present work aims to improve the communication security of Internet of Vehicles (IoV) nodes in intelligent transportation through studying the safety of IoV in smart transportation based on Blockchain (BC). An IoV DTs model is built by combining big data with Digital Twins (DTs). Then, regarding the current IoV communication security issues, a secure communication architecture for the IoV system is proposed based on the immutable and trackable BC data. Besides, Wasserstein Distance Based Generative Adversarial Network (WaGAN) model constructs the IoV node risk forecast model. Because the WaGAN model calculates the loss function through Wasserstein distance, the learning rate of the model accelerates remarkably. After ten iterations, the loss rate of the WaGAN model is close to zero. Massive in-vehicle devices in IoV are connected simultaneously to the base station, causing network channel congestion. Therefore, a Group Authentication and Privacy-preserving (GAP) scheme is put forward. As users increase during authentication, the GAP scheme performs better than other authentication access schemes. In summary, the Intelligent Transportation System driven by DTs can promote intelligent transportation management. Besides, introducing BC into IoV can improve access control’s accuracy and response efficiency. The research reported here has significant value for improving the security of the information sharing of the IoV. [ABSTRACT FROM AUTHOR]

Estimating when pedestrians cross the street is essential for intelligent transportation systems. Accurate, real-time prediction is critical to ensure the safety of the most vulnerable road users while improving passenger comfort. In the present work, we developed a model called Pedestrian Graph +, an improvement of our previous work, Pedestrian Graph, which predicts pedestrian crossing action in urban areas based on a Graph Convolution Network. We integrated two convolutional modules in the new model that provide additional context information (cropped images, cropped segmentation maps, ego-vehicle velocity data) to the main Graph Convolutional module, thus increasing accuracy. Our model is faster and smaller than other state-of-the-art models, achieving equivalent accuracy. Our model is faster than state-of-the-art models, with an inference time of 6 ms (on a GTX 1080) and low memory consumption (0.3 MB). We tested our model on two datasets, Joint Attention in Autonomous Driving (JAAD) and Pedestrian Intention Estimation (PIE), achieving 86% and 89% accuracy, respectively. Another contribution of our work is the ability to dynamically process almost any input size in the time domain without significant loss of accuracy. It is possible due to the fully convolutional property of ConvNets. Our models and results are available at https://github.com/RodrigoGantier/Pedestrian_graph_plus. [ABSTRACT FROM AUTHOR]

The rapid development of urbanization has raised challenges for existing parking facilities to serve increasing parking demand. Being constrained by the limited urban land resources for newly constructed parking facilities, improving the efficiency of existing parking infrastructures relies more on an advanced parking management strategy. Video-based parking surveillance technology, with abundant information, easy installation, and powerful algorithms, is the most popular method to provide real-time parking information as the required data feed for a parking management system. Meanwhile, deep learning-based algorithms gradually replace traditional computer vision methods for video processing since the detection accuracy has been increased considerably by learning fine-grained features. However, the excessive computational complexity of deep learning-based algorithms occupies considerable computational resources, which certainly hurts the entire system’s efficiency. Due to the limited computing power of edge devices, most parking surveillance systems deploy video processing algorithms on a server or cloud platform, which raises concerns about data transmission latency and central computation pressure. Deploying efficient algorithms on an edge-side device is a potential solution to solve these problems. This article proposes an edge computing parking occupancy detection system with a quantized deep learning model. Model quantization is employed to boost the inference speed while maintaining accuracy. In addition, knowledge distillation is applied to improve the quantized model’s training performance. Experiments are conducted to demonstrate the model’s superiority compared to state-of-the-art algorithms and the feasibility of edge computing. The proposed method can improve the accuracy and efficiency of parking surveillance systems. It is a systematic solution for obtaining parking information with limited computational resources. [ABSTRACT FROM AUTHOR]

In practice, the operation of high-speed trains is often affected by adverse weather conditions or equipment failures, which result in delays and even cancellations of train services. In this article, a novel two-layer hierarchical model predictive control (MPC) model is proposed for on-line high-speed railway delay management and train control for minimizing train delays and cancellations. The upper layer manages the global objectives of the train operation, that is, minimizing the total train delays and providing guidance for the speed control in the lower layer. The objectives of the lower layer are to satisfy the running time requirements given by the upper layer and to save energy at the same time. The optimization problems in both levels of the hierarchical MPC framework are formulated as small-scale mixed integer linear programming problems, which can be solved efficiently by existing solvers. Particularly, the train control problem is solved in a distributed way for each train. Simulation analysis based on the real-life data of the Beijing–Shanghai high-speed railway shows that the proposed hierarchical MPC framework can meet the real-time requirements and reduce train delays effectively when compared with widely accepted strategies, for example, first-scheduled-first-serve and first-come-first-serve. Moreover, the proposed hierarchical MPC framework also provides good robustness performance for different disturbance scenarios. [ABSTRACT FROM AUTHOR]

It is appealing but challenging to achieve real-time deep neural network (DNN) inference on mobile devices, because even the powerful modern mobile devices are considered as “resource-constrained” when executing large-scale DNNs. It necessitates the sparse model inference via weight pruning, i.e., DNN weight sparsity, and it is desirable to design a new DNN weight sparsity scheme that can facilitate real-time inference on mobile devices while preserving a high sparse model accuracy. This paper designs a novel mobile inference acceleration framework GRIM that is General to both convolutional neural networks (CNNs) and recurrent neural networks (RNNs) and that achieves Real-time execution and high accuracy, leveraging fine-grained structured sparse model Inference and compiler optimizations for Mobiles. We start by proposing a new fine-grained structured sparsity scheme through the Block-based Column-Row (BCR) pruning. Based on this new fine-grained structured sparsity, our GRIM framework consists of two parts: (a) the compiler optimization and code generation for real-time mobile inference; and (b) the BCR pruning optimizations for determining pruning hyperparameters and performing weight pruning. We compare GRIM with Alibaba MNN, TVM, TensorFlow-Lite, a sparse implementation based on CSR, PatDNN, and ESE (a representative FPGA inference acceleration framework for RNNs), and achieve up to $14.08\times$ 14. 08 × speedup. [ABSTRACT FROM AUTHOR]

The progress of industrial development naturally leads to the demand for more electrical power. Unfortunately, due to the fear of the safety of nuclear power plants, many countries have relied on thermal power plants, which will cause more air pollutants during the process of coal burning. This phenomenon as well as increased vehicle emissions around us, have constituted the primary factors of serious air pollution. Inhaling too much particulate air pollution may lead to respiratory diseases and even death, especially PM $_{2.5}$ 2. 5 . By predicting the air pollutant concentration, people can take precautions to avoid overexposure to air pollutants. Consequently, accurate PM $_{2.5}$ 2. 5 prediction becomes more important. In this study, we propose a PM $_{2.5}$ 2. 5 prediction system, which utilizes the dataset from EdiGreen Airbox and Taiwan EPA. Autoencoder and Linear interpolation are adopted for solving the missing value problem. Spearman’s correlation coefficient is used to identify the most relevant features for PM $_{2.5}$ 2. 5 . Two prediction models (i.e., LSTM and LSTM based on K-means) are implemented which predict PM $_{2.5}$ 2. 5 value for each Airbox device. To assess the performance of the model prediction, the daily average error and the hourly average accuracy for the duration of a week are calculated. The experimental results show that LSTM based on K-means has the best performance among all methods. Therefore, LSTM based on K-means is chosen to provide real-time PM $_{2.5}$ 2. 5 prediction through the Linebot. [ABSTRACT FROM AUTHOR]

Channel state information (CSI) estimation is one of the key techniques for improving the performance of wireless communication systems. Meanwhile, the fifth generation wireless communication systems require higher accuracy and lower latency for CSI estimation. In this paper, the methods of noise modeling and online learning are combined to improve the accuracy and reduce the latency. The complex noise environment (considering noise and interference together) is modeled as a specific mixture of Gaussian (MoG) distribution because of its widely approximation capability to any continuous distribution. The MoG CSI estimation (MoG-CE) model and expectation maximization (EM) algorithm are introduced as one of the baseline methods. Further, the parameters of the model can be updated in real time based on the prior knowledge of historical information. Therefore, the online MoG CSI estimation (O-MoG-CE) model and online MoG dynamic CSI estimation (O-MoG-D-CE) model are proposed for time-invariant and time-varying CSI estimations, respectively. The above models can not only self-adapt to various complex communication scenarios robustly but also achieve online and dynamic CSI estimation to improve the accuracy and reduce the latency significantly. In addition, the proposed models can be formulated as standard maximum a posteriori estimations and efficient online expectation maximization (OEM) algorithms are applied for the estimations in a pure machine learning fashion. Comparing with baseline methods, the simulation results demonstrate the superiority of the proposed methods in terms of the accuracy, latency and computation consumption. [ABSTRACT FROM AUTHOR]

Vehicle trajectory prediction is essential for enabling safety-critical intelligent transportation systems (ITS) applications used in management and operations. While there have been some promising advances in the field, there is a need for modern deep learning algorithms that allow real-time trajectory prediction on embedded IoT devices. This article presents DeepTrack, a novel deep learning algorithm customized for real-time vehicle trajectory prediction and monitoring applications in arterial management, freeway management, traffic incident management, and work zone management for high-speed incoming traffic. In contrast to previous methods, the vehicle dynamics are encoded using Temporal Convolutional Networks (TCNs) to provide more robust time prediction with less computation. DeepTrack also uses depthwise convolution, which reduces the complexity of models compared to existing approaches in terms of model size and operations. Overall, our experimental results demonstrate that DeepTrack achieves comparable accuracy to state-of-the-art trajectory prediction models but with smaller model sizes and lower computational complexity, making it more suitable for real-world deployment. [ABSTRACT FROM AUTHOR]

For deployment on an embedded processor for distracted driver classification, the model should satisfy the demand for both high accuracy, real-time inference, and limited storage resources. Conventional deep CNN models such as VGG, ResNet, DenseNet, often aim for high accuracy, making their model heavy for an embedded system with limited memory space and computing resources. In contrast, lightweight models are greatly compressed but at a significant sacrifice of accuracy. To bridge this gap, we propose an instance-specific multi-teacher knowledge distillation model (IsMt-KD) to learn more accurate, speedy, and lightweight CNNs for distracted driver posture classification. Specifically, in multi-teacher knowledge distillation, most of the current approaches either randomly select a teacher model and apply the prediction of such teacher model as the soft-label or allocate an equal weight to every teacher model and average all the predictions of the teachers as the soft label. In this paper, we observe that, when facing the same instance, the outputs of different teachers vary greatly, in which some teachers can predict it right whereas the others may give pretty high probabilities to the irrelevant classes. Thus, it is inappropriate to set fixed weights or the same weights for teachers. To this end, a simple yet effective instance-specific teacher grading module is designed to dynamically assign weights to teacher models based on individual instances. In this way, we can dynamically distill the knowledge from multiple teachers by considering both instance-specific high-level and instance-specific intermediate-level information. Our extensive experimental results on AUC and StateFarm datasets, and our implementation on edge hardware platforms including HUAWEI MediaPad c5 and Nvidia Jetson TX2, verify the effectiveness and feasibility of our approach. [ABSTRACT FROM AUTHOR]

Aiming at the shortcomings of the current YOLOv3 model, such as large size, slow response speed, and difficulty in deploying to real devices, this paper reconstructs the target detection model YOLOv3, and proposes a new lightweight target detection network YOLOv3-promote: Firstly, the G-Module combined with the Depth-Wise convolution is used to construct the backbone network of the entire model, and the attention mechanism is introduced and added to perform weighting operations on each channel to get more key features and remove redundant features, thereby strengthening the identification ability of feature network model’s to distinguish target objects among background; Secondly, in order to delete some less important channels to achieve the effect of compressing the model size and improving the calculation speed, the size of the scaling factor gamma in the batch normalization layer is used; Finally, based on NVIDIA’s TensorRT framework model conversion and half-precision acceleration were carried out, and the accelerated model was successfully deployed on the embedded platform Jetson Nano. The performed KITTI experimental results show that the inference speed of our proposed method is about 5 times that of the original model, the parameter volume is reduced to one tenth, the mAP is increased from 86.1% of the original model to 93.1%, and the FPS reaches 25.5fps, realizing the requirements of real-time detection with high precision. [ABSTRACT FROM AUTHOR]

With the prevalence of embedded GPUs on mobile devices, power-efficient rendering has become a widespread concern for graphics applications. Reducing the power consumption of rendering applications is critical for extending battery life. In this paper, we present a new real-time power-budget rendering system to meet this need by selecting the optimal rendering settings that maximize visual quality for each frame under a given power budget. Our method utilizes two independent neural networks trained entirely by synthesized datasets to predict power consumption and image quality under various workloads. This approach spares time-consuming precomputation or runtime periodic refitting and additional error computation. We evaluate the performance of the proposed framework on different platforms, two desktop PCs and two smartphones. Results show that compared to the previous state of the art, our system has less overhead and better flexibility. Existing rendering engines can integrate our system with negligible costs. [ABSTRACT FROM AUTHOR]

In the context of Industry 4.0, intelligent manufacturing services put forward the requirement of rapid response in the remaining useful life (RUL) of machinery. To achieve fast-responding and highly accurate RUL prediction services while mining the intra-kernel correlations of the sensor monitoring data, a deep learning-based cloud–edge collaboration framework was proposed in this article. We encapsulated a cloud prediction engine (Cloud-PE) with a deep prediction model in the cloud service layer and an edge prediction engine (Edge-PE) with a shallow prediction model in the edge service layer. The Cloud-PE assisted the Edge-PE in achieving fast and highly accurate RUL prediction by sharing depth model parameters. Both prediction models were constructed on the basis of a novel blueprint separable convolution neural network. To continuously improve the performance of Edge-PE in a context-aware manner, we adopted an update method for the Edge-PE with the assistance of the Cloud-PE. The experimental results demonstrated that the proposed framework can provide more accurate RUL prediction than existing data-driven prediction methods, and the training time of the prediction model is also significantly reduced. [ABSTRACT FROM AUTHOR]

In this article, we demonstrate how a generative neural network enables the inverse design of a real-time beamforming structure that consists of simply eight rotatable dielectric slabs but involves high nonlinearity. The determination of the optimal architecture and the detailed training process is discussed, and the advantage of the proposed method over some conventional numerical methods is shown. The system is realized and measured with a platform controlled by a low-cost system-on-a-chip (SoC) computer to verify its real-time design capability. We showcase the proposed neural network as a competitive candidate for complex real-time reconfigurable EM designs. [ABSTRACT FROM AUTHOR]

The quantification of heating, ventilation, and air condition (HVAC) system flexibility is critical to the operations of both the grid and buildings in demand response (DR) programs. However, the flexibility quantification is challenging due to the non-linearity and non-convexity of thermal dynamics associated with HVAC components. This paper proposes a novel HVAC flexibility quantification method based on a semidefinite programming (SDP) formulation. The SDP is reformulated from the non-convex problem of HVAC power optimization, and can be solved efficiently in real-time. The physics-based HVAC model is incorporated to ensure the reliability and accuracy of solutions. The quantification results are organized into an HVAC flexibility table that can provide response strategies on adjusting HVAC setpoints in response to the grid signals received. The developed response strategies minimize occupant discomfort while satisfying grid requirements. A case study of a test building model is carried out to illustrate the flexibility quantification framework and compares the performance of two DR strategies. [ABSTRACT FROM AUTHOR]

This article presents general modeling approaches to achieve an accurate real-time simulation (RTS) of high switching frequency converters.The proposed methods are based on the direct mapped method (DMM) and make use of decoupling techniques when appropriate. The DMM links state variables to diode statuses and provides an exact and noniterative solution to network equations. An electric vehicle battery charger test case comprised of a full-bridge rectifier, an interleaved boost, and a three-phase LLC is used to demonstrate the high accuracy achieved by the proposed methods compared to a conventional approach. Field-programmable gate array (FPGA) implementations are proposed and shown to achieve from 75- to 175-ns RTS time steps for this test case circuit, allowing its accurate simulation while switched at 200 kHz. To further validate the effectiveness of the FPGA-based simulator, a resonant boost converter is also implemented and simulated in real time. [ABSTRACT FROM AUTHOR]

In this article, a parallel and gradient-free strategy is presented for autonomous navigation of a quadrotor with a limited field of view (FOV). The FOV constraint is nonlinear and noncontinuous in general and involves higher order dynamics of the vehicle. Planning problems with such constraints are difficult to solve, especially with the real-time requirement. The proposed method first constructs an environment map by integrating the measurement of a limited-FOV sensor in a parallel process. Based on the map, it then selects a feasible local goal from a global path and generates a constraint-free nominal control sequence. Finally, a stochastic optimal control problem is solved to satisfy the limited FOV constraint, the dynamic constraint, and the collision-free conditions at the same time. The objective functions are nonlinear and noncontinuous and involves dynamic of MAV. A parallel-gradient-free algorithm is used to address these problems. Both the sensing and planning problems are solved parallelly on a lightweight graphics processing unit. The effectiveness of the proposed strategy is demonstrated through both simulation and real-flight experiments. [ABSTRACT FROM AUTHOR]

Energy-efficient solar insecticidal lamp (SIL) management is an important way to promote the full deployment and application of SILs in intelligent farms. To improve processing latency and precision, an edge computing-based energy-efficient SILs management architecture (ECEEM-SIL) is presented. Considering architecture matching, an SILs management mechanism based on edge computing referring to real-time information of pests and energy (ECEEM-SIL-RRIPE) is proposed. Firstly, considering different weather conditions, the pest distribution model and its update method based on edge computing are established. Secondly, the scheduling strategy based on the maximum coverage of active pest periods with the minimum number of working SILs (MaxCAP-MinNWS) is proposed to address the turning on and off scheduling of SILs, while considering the joint optimization of energy consumption and insecticidal efficiency. Simulation results show that compared with the existing preset working period scheduling and unified scheduling strategies, the proposed strategy can improve utilization of energy resources in insecticidal by up to 20%. In addition, the energy supply and consumption of SILs can be more balanced, and the battery deep discharging of SILs can be relieved. [ABSTRACT FROM AUTHOR]

We consider a signalized intersection under a partially connected automated vehicle (CAV) environment. There is a control center for the control zone that needs to predict the trajectories of human driving vehicles (HDVs) and control the trajectories of CAVs. By adopting model predictive control, we propose a real-time eco-driving strategy for the control center. In the proposed strategy, the Gipps’ car-following model is selected to update the acceleration of HDV and an optimal control problem (OCP) is proposed to optimize the trajectory of each CAV based on real-time travel information. The control objective is to minimize the total fuel consumption of each CAV during the current control period. Pontryagin’s minimum principle is employed to derive necessary optimality conditions under different scenarios. With the necessary optimality conditions, a numerical method is developed to solve the proposed OCP. Finally, numerical examples are provided to illustrate the performance of the proposed eco-driving strategy. [ABSTRACT FROM AUTHOR]

The fault diagnosis of complex timed discrete event systems remains a relevant and challenging problem in industry. As systems degrade, the synchronization required for normal operation associated with timed event sequences deteriorate. However, existing discrete event approaches cannot handle complexity well as there may be potentially hundreds of event sequences that still result in normal system behavior, and they do not scale well due to the state explosion problem. To circumvent these issues, a new data-driven augmented intelligence framework called EveSyncIAI is proposed that uses a Timed Petri Net of the normal process to enable selective extraction of discriminating time delay features, which are then used alongside machine learning for fault diagnosis. The developed methodology is applied to a case study of an operational discrete manufacturing system in the semiconductor industry. Multiclass machine learning approaches as well as binary anomaly detection algorithms with varying levels of supervision are directly compared with and without EveSyncIAI-extracted features. With precision, recall, and F1-score values above 0.90 being achieved for multi-fault classification and AUC scores exceeding 0.98 for semi-supervised and unsupervised anomaly detection approaches, the framework presented is promising for the fault diagnosis of timed sequence-sensitive systems. [ABSTRACT FROM AUTHOR]

The paper addresses a real-time optimization-based reference calculation integrated with a control structure for Modular Multilevel Converters (MMC) operating under normal and constrained situations (where it has reached current and/or voltage limitations, as it may occur during system faults). Firstly, a nonlinear optimization problem has been developed in which it prioritizes to satisfy the AC grid current set-points imposed by the transmission System Operator (TSO). The constrained nonlinear optimization problem is formulated based on the steady-state model of the MMC, whereby the prioritization is achieved through distinct weights defined in the Objective Function’s (OF) terms. The resultant optimization problem, however, is highly nonlinear requiring high computation burden to be solved in real-time. To cope with this issue, this paper applies a Linear Time-Varying (LTV) approximation, which permits to represent the nonlinear dynamics of the system as constant parameters, while a Linear Time-Invariant (LTI) system is used to formulate the optimization constraints. The converter’s current references are determined in real-time by solving a constrained linearized optimization problem at each control time step, which considers the TSO’s demands, the current MMC operating point and its physical limitations. Theoretical analyses comparing the responses of the linear and nonlinear optimization problems are performed to validate the accuracy of the LTV approximation. Finally, the linearized-optimization problem is integrated with the MMC controllers, evaluated under different AC and DC network conditions and compared with conventional control strategies, where it is shown that the presented method can be potentially employed to obtain the MMC current references for distinct network scenarios. [ABSTRACT FROM AUTHOR]

In this article, time-varying matrix equation problems, including the Lyapunov equation, matrix inversion, and generalized matrix inversion are investigated in a future (or say, discrete time-varying) perspective. Then, in order to develop a unified solution model for the above three future problems, a future matrix equation (FME) is investigated. The discrete-time unified solution (DTUS) model, which is based on the zeroing neural dynamics (ZND) method and a new nine-instant Zhang et al. discretization (ZeaD) formula, is thus proposed and termed the nine-instant DTUS (9IDTUS) model. Meanwhile, theoretical analyses on the stability and precision of the 9IDTUS model are provided. In addition, conventional DTUS models obtained from the Euler forward formula, Taylor–Zhang discretization formula, and a seven-instant discretization formula are also presented for comparisons. Furthermore, numerical experiments including the robot motion generation, are conducted and analyzed to substantiate the efficacy and superiority of the proposed 9IDTUS model. [ABSTRACT FROM AUTHOR]

Differing from the common linear matrix equation, the future different-level linear matrix system is considered, which is much more interesting and challenging. Because of its complicated structure and future-computation characteristic, traditional methods for static and same-level systems may not be effective on this occasion. For solving this difficult future different-level linear matrix system, the continuous different-level linear matrix system is first considered. On the basis of the zeroing neural network (ZNN), the physical mathematical equivalency is thus proposed, which is called ZNN equivalency (ZE), and it is compared with the traditional concept of mathematical equivalence. Then, on the basis of ZE, the continuous-time synthesis (CTS) model is further developed. To satisfy the future-computation requirement of the future different-level linear matrix system, the 7-instant discrete-time synthesis (DTS) model is further attained by utilizing the high-precision 7-instant Zhang et al. discretization (ZeaD) formula. For a comparison, three different DTS models using three conventional ZeaD formulas are also presented. Meanwhile, the efficacy of the 7-instant DTS model is testified by the theoretical analyses. Finally, experimental results verify the brilliant performance of the 7-instant DTS model in solving the future different-level linear matrix system. [ABSTRACT FROM AUTHOR]

Three filtering-based approaches to freeway traffic state estimation are studied using measurements from connected vehicles and also a minimum number of fixed detectors. These approaches are: Method 1 based on EKF and the second-order traffic flow model METANET, Methods 2 and 3 based on KF and the conservation equation that is driven by mean speed data of connected vehicles under a speed-uniformity assumption. Each method is capable of estimating segment traffic flow variables (speeds, densities, and flows) as well as segment market penetration rates (MPRs) of connected vehicles. The three methods are evaluated and compared in depth using NGSIM data with respect to their traffic state estimator design, data requirements, capabilities, limitations in the mixed sensing case. Recommendations are given about the choice of methods over the range of MPR. [ABSTRACT FROM AUTHOR]

Connected vehicle (CV) systems are subject to potential cyber attacks because of increasing connectivity between its different components, such as vehicles, roadside infrastructure, and traffic management centers. However, it is a challenge to detect security threats in real-time and develop appropriate or effective countermeasures for a CV system because of the dynamic behavior of such attacks, high computational power requirement, and a historical data requirement for training detection models. To address these challenges, statistical models, especially change point models, have potentials for real-time anomaly detection. Thus, the objective of this study is to investigate the efficacy of two change point models; Expectation Maximization (EM) and two forms of Cumulative Summation (CUSUM) algorithms (i.e., typical and adaptive), for real-time vehicle-to-infrastructure (V2I) cyber attack detection in a CV Environment. To prove the efficacy of these models, we evaluated these two models for three different types of cyber attack, denial of service (DOS), impersonation, and false information, using basic safety messages (BSMs) generated from CVs through simulation. Results from numerical analysis revealed that EM, CUSUM, and adaptive CUSUM (aCUSUM) could detect these cyberattacks, such as DOS, impersonation, and false information with low false positives. [ABSTRACT FROM AUTHOR]

We present H-TD2: Hybrid Temporal Difference Learning for Taxi Dispatch, a model-free, adaptive decision-making algorithm to coordinate a large fleet of automated taxis in a dynamic urban environment to minimize expected customer waiting times. Our scalable algorithm exploits the natural transportation network company topology by switching between two behaviors: distributed temporal-difference learning computed locally at each taxi and infrequent centralized Bellman updates computed at the dispatch center. We derive a regret bound and design the trigger condition between the two behaviors to explicitly control the trade-off between computational complexity and the individual taxi policy’s bounded sub-optimality; this advances the state of the art by enabling distributed operation with bounded-suboptimality. Additionally, unlike recent reinforcement learning dispatch methods, this policy estimation is adaptive and robust to out-of-training domain events. This result is enabled by a two-step modelling approach: the policy is learned on an agent-agnostic, cell-based Markov Decision Process and individual taxis are coordinated using the learned policy in a distributed game-theoretic task assignment. We validate our algorithm against a receding horizon control baseline in a Gridworld environment with a simulated customer dataset, where the proposed solution decreases average customer waiting time by 50% over a wide range of parameters. We also validate in a Chicago city environment with real customer requests from the Chicago taxi public dataset where the proposed solution decreases average customer waiting time by 26% over irregular customer distributions during a 2016 Major League Baseball World Series game. [ABSTRACT FROM AUTHOR]

The problems of bus bunching mitigation and the energy management of groups of vehicles have traditionally been treated separately in the literature and been formulated in two different frameworks. The present work bridges this gap by formulating the optimal control problem of the bus line eco-driving and regularity control as a smooth, multi-objective nonlinear program. Since this nonlinear program has only a few coupling variables, it is shown how it can be solved in parallel aboard each bus, such that only a marginal amount of computations need to be carried out centrally. This procedure leverages the structure of the bus line by enabling parallel computations and reducing the communication loads between the buses, which makes the problem resolution scalable in terms of the number of buses. Closed-loop control is then achieved by embedding this procedure in a model predictive control. Stochastic simulations based on real passengers and travel times data are realized for several scenarios with different levels of bunching for a line of electric buses. Our method achieves fast recoveries to regular headways as well as energy savings of up to 9.3% when compared with traditional holding or speed control baselines. [ABSTRACT FROM AUTHOR]

Recently fast arbitrary-shaped text detection has become an attractive research topic. However, most existing methods are non-real-time, which may fall short in intelligent systems. Although a few real-time text methods are proposed, the detection accuracy is far behind non-real-time methods. To improve the detection accuracy and speed simultaneously, we propose a novel fast and accurate text detection framework, namely CM-Net, which is constructed based on a new text representation method and a multi-perspective feature (MPF) module. The former can fit arbitrary-shaped text contours by concentric mask (CM) in an efficient and robust way. The latter encourages the network to learn more CM-related discriminative features from multiple perspectives and brings no extra computational cost. Benefiting the advantages of CM and MPF, the proposed CM-Net only needs to predict one CM of the text instance to rebuild the text contour and achieves the best balance between detection accuracy and speed compared with previous works. Moreover, to ensure that multi-perspective features are effectively learned, the multi-factor constraints loss is proposed. Extensive experiments demonstrate the proposed CM is efficient and robust to fit arbitrary-shaped text instances, and also validate the effectiveness of MPF and constraints loss for discriminative text features recognition. Furthermore, experimental results show that the proposed CM-Net is superior to existing state-of-the-art (SOTA) real-time text detection methods in both detection speed and accuracy on MSRA-TD500, CTW1500, Total-Text, and ICDAR2015 datasets. [ABSTRACT FROM AUTHOR]

Indirect methods for visual SLAM are gaining popularity due to their robustness to environmental variations. ORB-SLAM2 (Mur-Artal and Tardós, 2017) is a benchmark method in this domain, however, it consumes significant time for computing descriptors that never get reused unless a frame is selected as a keyframe. To overcome these problems, we present FastORB-SLAM which is light-weight and efficient as it tracks keypoints between adjacent frames without computing descriptors. To achieve this, a two stage descriptor-independent keypoint matching method is proposed based on sparse optical flow. In the first stage, we predict initial keypoint correspondences via a simple but effective motion model and then robustly establish the correspondences via pyramid-based sparse optical flow tracking. In the second stage, we leverage the constraints of the motion smoothness and epipolar geometry to refine the correspondences. In particular, our method computes descriptors only for keyframes. We test FastORB-SLAM on TUM and ICL-NUIM RGB-D datasets and compare its accuracy and efficiency to nine existing RGB-D SLAM methods. Qualitative and quantitative results show that our method achieves state-of-the-art accuracy and is about twice as fast as the ORB-SLAM2. [ABSTRACT FROM AUTHOR]

To achieve real-time abundance estimation of hyperspectral images and improve the accuracy and efficiency of estimation, this article proposes a new band processing approach for abundance estimation, to be called sequential band fusion (SBF). To achieve SBF, a new band priority mechanism is proposed. It is derived from the concept of orthogonal subspace projection (OSP) by orthogonalizing undesired targets using projection while minimizing the variance resulting from the background. By taking advantage of OSP, the interfering effects caused by all undesired targets can be eliminated, and then, the detector produced by a target of interest can be further used as a measure of prioritizing bands as well as a means of searching bands for this particular target. As a result, two ranking-based band priority criteria (RP), called maximum OSP-based RP (MaxOSP-RP) and minimum OSP-based RP (MinOSP-RP), and two searching-based band priority criteria (SP), called sequential feedforward band search (SFBS) and sequential backward band search (SBBS), can be derived. We provide a detailed theoretical description and formula derivation of the SBF and combine it with band sequence (BSQ), RP, and SP to propose three different fusion mechanisms: SBF based on BSQ (SBF-BSQ), SBF based on RP (SBF-RP), and SBF with SP (SBF-SP) to make the fusion mechanism applied to different scenarios. Experimental results show that the proposed methods perform well for abundance estimation. [ABSTRACT FROM AUTHOR]

This paper proposes a real-time schedule model of a microgrid (MG) for maximizing battery energy storage (BES) utilization. To this end, a BES life model is linearized using piece-wise linearization and big-M method to assess the BES life loss (BLL) in a real-time manner. The cost-effective schedule model of the MG with multiple energy resources aims to maximize BES utilization while ensuring its sufficient lifespan. Corresponding to the optimization model, approximate dynamic programming (ADP) for maximizing BES utilization (ADP-MBU) in the real-time schedule is proposed to optimize the system under stochastic environments. In ADP-MBU, a new value function approximation method employing the BES cumulative life loss (BCLL) is developed to improve the optimality and applicability. The proposed ADP-MBU algorithm can achieve satisfactory approximate optimality while reflecting the variation of real-time BLL. Case studies validate the applicability of the proposed MG schedule model and the advantages of the proposed ADP-MBU algorithm. [ABSTRACT FROM AUTHOR]

360-degree video streaming provides users with immersive experience by letting users determine their field-of-views (FoVs) in real time. To efficiently utilize the limited bandwidth resources, recent works have proposed a viewport adaptive 360-degree video streaming model by exploiting the bitrate adaptation in spatial and temporal domains. In this paper, under this video streaming model, we propose an online bitrate selection algorithm to enhance the user’s quality of experience (QoE). This is achieved by characterizing the user’s personalized FoV and real-time downloading capacity in an online fashion. We address the unknown user-specific FoV by introducing the reference FoV and design an online bitrate selection algorithm to learn the difference between the user’s actual FoV and the reference FoV. We prove that as the number of video segments increases, the performance of the proposed online algorithm approaches the optimal performance asymptotically, with a bounded error. We perform trace-driven simulations with real-world datasets. Simulation results show that under the scenario where the available video bitrates are relatively high, our proposed algorithm can improve the user’s viewing quality level between $4.2\!-\!29.4$ 4. 2 - 29. 4 percent and reduce the average intra-segment quality switch by at least 12.4 percent when compared with several existing methods. [ABSTRACT FROM AUTHOR]

With the development of communication technology and artificial intelligence of things (AIoT), transportation systems have become much smarter than ever before. However, the volume of vehicles and traffic flows have rapidly increased. Optimizing and improving urban traffic signal control is a potential way to relieve traffic congestion. In general, traffic signal control is a sequential decision process that conforms to the characteristics of reinforcement learning, in which an agent constantly interacts with its environment, thus providing strategy for optimizing behavior in accordance with feedback in response. In this paper, we propose multiagent reinforcement learning for traffic signals (MARL4TS) to support the control and deployment of traffic signals. First, information on traffic flows and multiple intersections is formalized as input environments for performing reinforcement learning. Second, we design a new reward function to continuously select the most appropriate strategy as control during multiagent learning to track actions for traffic signals. Finally, we use a supporting tool, Simulation of Urban MObility (SUMO), to simulate the proposed traffic signal control process and compare it with other methods. The experimental results show that our proposed MARL4TS method is superior to the baselines. In particular, our method can reduce vehicle delay. [ABSTRACT FROM AUTHOR]