DuFNet:Dual Flow Network of Real-Time Semantic Segmentation for Unmanned Driving Application of Internet of Things

The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology.Image semantic segmentation can help the unmanned driving system by achieving road accessibility analysis.Semantic segmentation is also a challenging technology for image understanding and scene parsing.We focused on the challenging task of real-time semantic segmentation in this paper.In this paper,we proposed a novel fast architecture for real-time semantic segmentation named DuFNet.Starting from the existing work of Bilateral Segmentation Network(BiSeNet),DuFNet proposes a novel Semantic Information Flow(SIF)structure for context information and a novel Fringe Information Flow(FIF)structure for spatial information.We also proposed two kinds of SIF with cascaded and paralleled structures,respectively.The SIF encodes the input stage by stage in the ResNet18 backbone and provides context information for the feature fusionmodule.Features from previous stages usually contain rich low-level details but high-level semantics for later stages.Themultiple convolutions embed in Parallel SIF aggregate the corresponding features among different stages and generate a powerful global context representation with less computational cost.The FIF consists of a pooling layer and an upsampling operator followed by projection convolution layer.The concise component provides more spatial details for the network.Compared with BiSeNet,our work achieved faster speed and comparable performance with 72.34%mIoU accuracy and 78 FPS on Cityscapes Dataset based on the ResNet18 backbone.

The Design of a Three-Dimensional Physical Modeling System for Real-Time Groundwater Flows

In the past decades,physical modeling has been widely used in hydrogeology for teaching,studying and exhibition purposes.Most of these models are used to illustrate hydrogeological profiles,but few can depict three-dimensional groundwater flows,making it impossible to validate groundwater flows simulated by numerical methods with physical modeling.

Research on fast real-time adaptive audio mixing in multimedia conference

In multimedia conference, the capability of audio processing is basic and requires more for real-time criteria. In this article, we categorize and analyze the schemes, and provide several multipoint speech audio mixing schemes using weighted algorithm, which meet the demand of practical needs for real-time multipoint speech mixing, for which the ASW and AEW schemes are especially recommended. Applying the adaptive algorithms, the high-performance schemes we provide do not use the saturation operation widely used in multimedia processing. Therefore, no additional noise will be added to the output. The above adaptive algorithms have relatively low computational complexity and good hearing perceptibility. The schemes are designed for parallel processing, and can be easily implemented with hardware, such as DSPs, and widely applied in multimedia conference systems.

Real-time Three-Dimensional Color Doppler Flow Imaging： An Improved Technique for Quantitative Analysis of Aortic Regurgitation

The recently introduced real-time three-dimensional color Doppler flow imaging （RT-3D CDFI） technique provides a quick and accurate calculation of regurgitant jet volume （RJV） and fraction. In order to evaluate RT-3D CDFI in the noninvasive assessment of aortic RJV and regurgitant jet fraction （RJF） in patients with isolated aortic regurgitation, real-time three-dimensional echocardiographic studies were performed on 23 patients with isolated aortic regurgitation to obtain LV end-diastolic volumes （LVEDV）, end-systolic volumes （LVESV） and RJV, and then RJF could be calculated. The regurgitant volume （RV） and regurgitant fraction （RF） calculated by two-dimensional pulsed Doppler （2D-PD） method served as reference values. The results showed that aortic RJV measured by the RT-3D CDFI method showed a good correlation with the 2D-PD measurements （r= 0.93, Y=0.89X＋ 3.9, SEE= 8.6 mL, P〈0.001 ）; the mean （SD） difference between the two methods was - 1.5 （9.8） mL. % RJF estimated by the RT-3D CDFI method was also correlated well with the values obtained by the 2D-PD method （r=0.88, Y=0.71X＋ 14.8, SEE= 6.4 %, P〈0. 001）; the mean （SD） difference between the two methods was -1.2 （7.9） %. It was suggested that the newly developed RT-3D CDFI technique was feasible in the majority of patients. In patients with eccentric aortic regurgitation, this new modality provides additional information to that obtained from the two-dimensional examination, which overcomes the inherent limitations of two-dimensional echocardiography by depicting the full extent of the jet trajectory. In addition, the RT-3D CDFI method is quick and accurate in calculating RJV and RJF.

REAL-TIME LICENSING MANAGEMENT OF SECURE MULTIMEDIA CONTENT DELIVE RY

Media Commerce is now becoming a new trend which results fr om faster development of network bandwidth and high availability of multimedia t echnologies, how to protect media content from being used in a right-violated w ay is one of most important issues to take into account. In this paper, a novel and efficient authorization and authentication Digital Rights Management (DRM) s chema is proposed firstly for secure multimedia delivery, then based on the sche ma, a real-time digital signature algorithm built on Elliptic Curve Cryptograph y (ECC) is adopted for fast authentication and verification of licensing managem ent, thus secure multimedia delivery via TCP/RTP can efficiently work with real -time transaction response and high Quality of Service (QoS) . Performance eval uations manifest the proposed schema is secure, available for real-time media s tream authentication and authorization without much effected of QoS. The propose d schema is not only available for Client/Server media service but can be easily extended to P2P and broadcasting network for trusted rights management.

A Parallel Approach for Real-Time Power Flow in Distribution Networks

The new reality of smart distribution systems with use of generation sources of small and medium sizes brings new challenges for the operation of these systems. The complexity and the large number of nodes requires use of methods which can reduce the processing time of algorithms such as power flow, allowing its use in real time. This paper presents a known methodology for calculating the power flow in three phases using backward/forward sweep method, and also considering other network elements such as voltage regulators, shunt capacitors and sources of dispersed generation of types PV （active power and voltage） and PQ （active and reactive power）. After that, new elements are introduced that allow the parallelization of this algorithm and an adequate distribution of work between the available processors. The algorithm was implemented using a multi-tiered architecture; the processing times were measured in many network configurations and compared with the same algorithm in the serial version.

Real-Time Traffic Signal Timing for Urban Road Multi-Intersection

this paper develops a real-time traffic signal timing model which is to be integrated into a single intersection for urban road, thereby solving the problem of traffic congestion. We analyze the current situation of the traffic flow with release matrix firstly, and then put forward the basic models to minimize total delay time of vehicles at the intersection. The optimal real-time signal timing model (non-fixed cycle and non-fixed split) is built with the Webster split optimal model. At last, the simulated results, which are compared with conventional model, manifest the promising properties of proposed model.

Operational guidance for aeration and flow augmentation for the Chicago Area Waterway System—A case study

The Chicago Area Waterway System(CAWS)is a 133.9 km branching network of navigable waterways controlled by hydraulic structures,in which the majority of the flow is treated wastewater effluent and there are periods of substantial combined sewer overflows.The CAWS comprises a network of effluent dominated streams.More stringent dissolved oxygen(DO)standards and a reduced flow augmentation allowance have been recently applied to the CAWS.Therefore,a carefully calibrated and verified one-dimensional flow and water quality model was applied to the CAWS to determine emission-based real-time control guidelines for the operation of flow augmentation and aeration stations.The goal of these guidelines was to attain DO standards at least 95%of the time.The“optimal”guidelines were tested for representative normal,dry,and wet years.The finally proposed guidelines were found in the simulations to attain the 95%target for nearly all locations in the CAWS for the three test years.The developed operational guidelines have been applied since 2018 and have shown improved attainment of the DO standards throughout the CAWS while at the same time achieving similar energy use at the aeration stations on the Calumet River system,greatly lowered energy use on the Chicago River system,and greatly lowered discretionary diversion from Lake Michigan,meeting the recently enacted lower amount of allowed annual discretionary diversion.This case study indicates that emission-based real-time control developed from a well calibrated model holds potential to help many receiving water bodies achieve high attainment of water quality standards.

An artificial neural network visible mathematical model for real-time prediction of multiphase flowing bottom-hole pressure in wellbores

Accurate prediction of multiphase flowing bottom-hole pressure(FBHP)in wellbores is an important factor required for optimal tubing design and production optimization.Existing empirical correlations and mechanistic models provide inaccurate FBHP predictions when applied to real-time field datasets because they were developed with laboratory-dependent parameters.Most machine learning(ML)models for FBHP prediction are developed with real-time field data but presented as black-box models.In addition,these ML models cannot be reproduced by other users because the dataset used for training the machine learning algorithm is not open source.These make using the ML models on new datasets difficult.This study presents an artificial neural network(ANN)visible mathematical model for real-time multiphase FBHP prediction in wellbores.A total of 1001 normalized real-time field data points were first used in developing an ANN black-box model.The data points were randomly divided into three different sets;70%for training,15%for validation,and the remaining 15%for testing.Statistical analysis showed that using the Levenberg-Marquardt training optimization algorithm(trainlm),hyperbolic tangent activation function(tansig),and three hidden layers with 20,15 and 15 neurons in the first,second and third hidden layers respectively achieved the best performance.The trained ANN model was then translated into an ANN visible mathematical model by extracting the tuned weights and biases.Trend analysis shows that the new model produced the expected effects of physical attributes on FBHP.Furthermore,statistical and graphical error analysis results show that the new model outperformed existing empirical correlations,mechanistic models,and an ANN white-box model.Training of the ANN on a larger dataset containing new data points covering a wider range of each input parameter can broaden the applicability domain of the proposed ANN visible mathematical model.

Renewable and Nonrenewable Energy Flow Resiliency for Day-to-Day Production and Consumption

Energy resilience is about ensuring a business and end-use consumers have a reliable,regular supply of energy and contingency measures in place in the event of a power failure,generating a source of power such as electricity for daily needs from an uninterrupted source of energy no matter either renewable or nonrenewable.Causes of resilience issues include power surges,weather,natural disasters,or man-made accidents,and even equipment failure.The human operational error can also be an issue for grid-power supply to go down and should be factored into resilience planning.As the energy landscape undergoes a radical transformation,from a world of large,centralized coal plants to a decentralized energy world made up of small-scale gas-fired production and renewables,the stability of electricity supply will begin to affect energy pricing.Businesses must plan for this change.The challenges that the growth of renewables brings to the grid in terms of intermittency mean that transmission and distribution costs consume an increasing proportion of bills.With progress in the technology of AI(Artificial Intelligence)integration of such progressive technology in recent decades,we are improving our resiliency of energy flow,so we prevent any unexpected interruption of this flow.Ensuring your business is energy resilient helps insulate against price increases or fluctuations in supply,becoming critical to maintaining operations and reducing commercial risk.In the form short TM(Technical Memorandum),this paper covers this issue.

CROSS-CORRELATION MEASURING SYSTEM FOR MEASURING VELOCITY OF BULK MATERIAL FLOW IN PIPE LINE

In this paper the cross correlation technique for measuring velocity of bulk material flow in pipe line was investigated and a new capacitance transducer with converter has been introduced. The system was controlled by single chip computer with a real-time cross correlation cumputing software. Computing time reaches 1 sec and velocity measuring error is less than 1%.

大数据技术在多媒体信息安全检测中的应用

阐述在操作系统运行时,对各个互联网使用者的网络通信进行安全检测,检测用户多媒体设备运行、空闲、重启或升级期间的数据流,实现对网络中的多媒体信息进行实时监控。

基于多媒体传感网络的实验教学环境监测方法

为了有效提高实验教学监控方法的适应性,研究了基于多媒体传感网络的实验教学环境监测方法。通过传感网络提取当前教学环境可测监控信息流作为前导性数据,以节点和门为单位构建检测关系分析模型,导出监控关系分析矩阵,最后引入信息流和超差环境数据,获取最终实验教学环境监控结果。实验结果表明,常规环境下该监控方法的反应速率提高了32%,复杂环境下其反应速率提高了28%,整体适应性更强。

REAL-TIME FLOOD FORECASTING METHOD WITH 1-D UNSTEADY FLOW MODEL

A real-time forecasting method coupled with the I-D unsteady flow model with the recursive least-square method was developed. The 1-D unsteady flow model was modified by using the time-variant parameter and revising it dynamically through introducing a variable weighted forgetting factor, such that the output of the model could be adjusted for the real time forecasting of floods. The application of the new real time forecasting model in the reach from Yichang to Luoshan of the Yangtze River was demonstrated. Computational result shows that the forecasting accuracy of the new model is much higher than that of the original 1-D unsteady flow model. The method developed is effective for flood forecasting, and can be used for practical operation in the flood forecasting.

A Time Pattern-Based Intelligent Cache Optimization Policy on Korea Advanced Research Network

Data is growing quickly due to a significant increase in social media applications.Today,billions of people use an enormous amount of data to access the Internet.The backbone network experiences a substantial load as a result of an increase in users.Users in the same region or company frequently ask for similar material,especially on social media platforms.The subsequent request for the same content can be satisfied from the edge if stored in proximity to the user.Applications that require relatively low latency can use Content Delivery Network(CDN)technology to meet their requirements.An edge and the data center con-stitute the CDN architecture.To fulfill requests from the edge and minimize the impact on the network,the requested content can be buffered closer to the user device.Which content should be kept on the edge is the primary concern.The cache policy has been optimized using various conventional and unconventional methods,but they have yet to include the timestamp beside a video request.The 24-h content request pattern was obtained from publicly available datasets.The popularity of a video is influenced by the time of day,as shown by a time-based video profile.We present a cache optimization method based on a time-based pat-tern of requests.The problem is described as a cache hit ratio maximization pro-blem emphasizing a relevance score and machine learning model accuracy.A model predicts the video to be cached in the next time stamp,and the relevance score identifies the video to be removed from the cache.Afterwards,we gather the logs and generate the content requests using an extracted video request pattern.These logs are pre-processed to create a dataset divided into three-time slots per day.A Long short-term memory(LSTM)model is trained on this dataset to forecast the video at the next time interval.The proposed optimized caching policy is evaluated on our CDN architecture deployed on the Korean Advanced Research Network(KOREN)infrastructure.Our findings demonstrate how add-ing time-based request patterns impacts the system by increasing the cache hit rate.To show the effectiveness of the proposed model,we compare the results with state-of-the-art techniques.

Real-time adaptive particle image velocimetry for accurate unsteady flow field measurements

Almost all conventional open-loop particle image velocimetry(PIV) methods employ fixed-interval-time optical imaging technology and the time-consuming cross-correlation-based PIV measurement algorithm to calculate the velocity field.In this study,a novel real-time adaptive particle image velocity(RTA-PIV) method is proposed to accurately measure the instantaneous velocity field of an unsteady flow field.In the proposed closed-loop RTA-PIV method,a new correlation-filter-based PIV measurement algorithm is introduced to calculate the velocity field in real time.Then,a Kalman predictor model is established to predict the velocity of the next time instant and a suitable interval time can be determined.To adaptively adjust the interval time for capturing two particle images,a new high-speed frame-straddling vision system is developed for the proposed RTA-PIV method.To fully analyze the performance of the RTA-PIV method,we conducted a series of numerical experiments on ground-truth image pairs and on real-world image sequences.

Real-Time Hybrid Flow Shop Scheduling Approach in Smart Manufacturing Environment

Smart manufacturing in the“Industry 4.0”strategy promotes the deep integration of manufacturing and information technologies,which makes the manufacturing system a ubiquitous environment.However,the real-time scheduling of such a manufacturing system is a challenge faced by many decision makers.To deal with this challenge,this study focuses on the real-time hybrid flow shop scheduling problem(HFSP).First,the characteristic of the hybrid flow shop in a smart manufacturing environment is analyzed,and its scheduling problem is described.Second,a real-time scheduling approach for the HFSP is proposed.The core module is to employ gene expression programming to construct a new and efficient scheduling rule according to the real-time status in the hybrid flow shop.With the scheduling rule,the priorities of the waiting job are calculated,and the job with the highest priority will be scheduled at this decision time point.A group of experiments are performed to prove the performance of the proposed approach.The numerical experiments show that the real-time scheduling approach outperforms other single-scheduling rules and the back-propagation neural network method in optimizing most objectives for different size instances.Therefore,the contribution of this study is the proposal of a real-time scheduling approach,which is an effective approach for real-time hybrid flow shop scheduling in a smart manufacturing environment.

Real-time solution of nonlinear potential flow equations for lifting rotors

Analysis of rotorcraft dynamics requires solution of the rotor induced flow field.Often,the appropriate model to be used for induced flow is nonlinear potential flow theory（which is the basis of vortex-lattice methods）.These nonlinear potential flow equations sometimes must be solved in real time––such as for real-time flight simulation,when observers are needed for controllers,or in preliminary design computations.In this paper,the major effects of nonlinearities on induced flow are studied for lifting rotors in low-speed flight and hover.The approach is to use a nonlinear statespace model of the induced flow based on a Galerkin treatment of the potential flow equations.

A REAL-TIME MATHEMATICAL MODEL FOR TWO DIMENSIONAL TIDAL FLOW AND WATER QUALITY

A real-time mathematical model for two dimensional tidal flow and water quality is presented in this paper. The control-volume-based-finite-difference method and the 'power interpolation distribution' advocated by Patankar [4] have been employed, and new boundary condition for tidal flow is recommended. The model is un- conditionally stable and convergent, and able to deal with irregular estuarine topography and movable boundary problems. Practical application of the model is illustrated by an example for the Swatou Bay. A fair agreement be- tween the values measured and computed demonstrates the validity of the model developed.