Search

Caching and transcoding at multi-access edge computing (MEC) server and wireless resource allocation in eNodeB interact with each other and together determine the quality of experience (QoE) of dynamic adaptive streaming over HTTP (DASH) clients. However, the relationship among the three factors has not been explored, which has led to limited improvement in clients’ QoE. Therefore, we propose a joint optimization framework of video segment caching and transcoding in MEC servers and resource allocation to improve the QoE of DASH clients. Based on the established framework, we develop an MEC caching management mechanism that consists of the MEC caching partition, video segment deletion, and MEC caching space transfer. Then, a joint optimization algorithm that combines the video segment caching and transcoding in the MEC server and resource allocation is proposed. In the algorithm, the clients’ channel state and the playback status and cooperation among MEC servers are employed to estimate the client's priority, video segment representation switch and continuous playback time. Considering the above four factors, we develop a utility function model of clients’ QoE. Then, we formulate a mixed-integer nonlinear programming mathematical model to maximize the total utility of DASH clients, where the video segment caching and transcoding strategy and resource allocation strategy are jointly optimized. To solve this problem, we propose a low-complexity heuristic algorithm that decomposes the original problem into multiple subproblems. The simulation results show that our proposed algorithms efficiently improve client's throughput, received video quality and hit ratio of video segments while decreasing the playback rebuffering time, video segment representation switch and system backhaul traffic.

In order to overcome the problems of power flow control and fault current limiting in multi-terminal high voltage direct current (MTDC) grids, this paper proposes a modular multi-terminal DC power flow controller (MM-DCPFC) with fault current limiting function. The topology structure, operation principle, and equivalent circuit of MM-DCPFC are introduced, and such a structure has the advantages of modularity and scalability. The power balance mechanism is studied and a hierarchical power balance control strategy is proposed. The results show that MM-DCPFC can achieve internal power exchange, which avoids the use of external power supply. The fault characteristics of MM-DCPFC are analyzed, fault current limiting and self-protection methods are proposed, and the factors affecting the current limiting capability are studied. The simulation models are established in PLECS, and the simulation results verify the effectiveness of MM-DCPFC in power flow control, fault current limiting, and scalability. In addition, a prototype is developed to validate the function and control method of MM-DCPFC.

With the rapid development of wireless communication technology and intelligent mobile devices, unmanned aerial vehicle (UAV) cluster is becoming increasingly popular in both civilian and military applications. Recently, a swarm intelligence-based UAV cluster study, aiming to enable efficient and autonomous collaboration, has drawn lots of interest. However, new security problems may be introduced with such swarm intelligence. In this work, we perform the first detailed security analysis to a kind of flocking-based UAV cluster with 5 policies, an upgrade version of the well-known Boids model. Targeting a realistic threat in a source-to-destination flying task, we design a data spoofing strategy and further perform complete vulnerability analysis. We reveal that such design and implementation are highly vulnerable. After breaking through the authentication of ad hoc on-demand distance vector (AODV) routing protocol by rushing attack, an attacker can masquerade as the first-arrival UAV within a specific scope of destination and generate data spoofing of arrival status to the following UAVs, so as to interfere with their normal flying paths of destination arrival and cause unexpected arrival delays amid urgent tasks. Experiments with detailed analysis from the 5-UAV cluster to the 10-UAV cluster are conducted to show specific feature composition-based attack effect and corresponding average delay. We also discuss promising defense suggestions leveraging the insights from our analysis.

In traditional communication system, information of APP (Application) layer, transport layer and MAC (Media Access Control)layer has not been fully interacted,which inevitably leads to inconsistencies among TCP congestion state, clients'requirements and resource allocation. To solve the problem, we propose a joint optimization framework, which consists of APP layer, transport layer and MAC layer, to improve the video clients'playback experience and system throughput. First, a client requirement aware autonomous packet drop strategy, based on packet importance, channel condition and playback status, is developed to decrease the network load and the probability of rebuffering events. Further, TCP (Transmission Control Protocol) state aware downlink and uplink resource allocation schemes are proposed to achieve smooth video transmission and steady ACK (Acknowledgement) feedback respectively. For downlink scheme, maximum transmission capacity requirement for each client is calculated based on feedback ACK information from transport layer to avoid allocating excessive resource to the client, whose ACK feedback is blocked due to bad uplink channel condition. For uplink scheme, information of RTO (Retransmission Timeout) and TCP congestion window are utilized to indicate ACK scheduling priority. The simulation results show that our algorithm can signficantly improve the system throughput and the clients'playback continuity with acceptable video quality., Comment: 12 pages, 11 figures

Memory and logic in the same device Future artificial intelligence applications and data-intensive computations require the development of neuromorphic systems beyond traditional heterogeneous device architectures. Physical separation between a peripheral signal-processing unit and a memory-operating unit is one of the main bottlenecks of heterogeneous architectures, blocking further improvements in efficient resistance matching, energy consumption, and integration compatibility. Tong et al . present a transistor-memory architecture based on a homogeneous tungsten selenide-on-lithium niobate device array (see the Perspective by Rao and Tao). Analog peripheral signal preprocessing and nonvolatile memory were possible within the same device structure, promising diverse neuromorphic functionalities and offering potential improvements in neuromorphic systems on-chip. —YS

Based on electromagnetic simulation and catfish particle swarm algorithm, a novel method is proposed to design the negative group delay circuit with defected structures. The optimization is developed to increase the efficiency and the accuracy, which is confirmed by the data before and after optimizations. The measured results show that at the frequencies of 5.7 and 7.0 GHz, the insertion loss values achieve −17dB and −7dB, respectively.

Aiming at analyzing the temporal structures in evolutionary networks, we propose a community detection algorithm based on graph representation learning. The proposed algorithm employs a Laplacian matrix to obtain the node relationship information of the directly connected edges of the network structure at the previous time slice, the deep sparse autoencoder learns to represent the network structure under the current time slice, and the K-means clustering algorithm is used to partition the low-dimensional feature matrix of the network structure under the current time slice into communities. Experiments on three real datasets show that the proposed algorithm outperformed the baselines regarding effectiveness and feasibility.

With the continuous Internet development, network information amount has increased significantly. In this way, users faced with extensive network information cannot quickly find information that meets their needs, leading to decreased efficiency in network information usage. Accordingly, personalized recommendation system should be an important part of the electronic platform system as recommendation efficiency directly affects the user experience and the use of electronic platforms. In recent years, the data of electronic platforms presents a trend of massive growth, resulting in decreased accuracy in system recommendations, increased errors, and decreased efficiency. Therefore, it is particularly necessary to study and analyze personalized recommendation algorithms. Based on the research and application of latent factor model in short video recommendation algorithm, this paper aims to recommend users with video content that truly meets user needs and interests.

Human activity recognition (HAR) has been a vital human–computer interaction service in smart homes. It is still a challenging task due to the diversity and similarity of human actions. In this paper, a novel hierarchical deep learning-based methodology equipped with low-cost sensors is proposed for high-accuracy device-free human activity recognition. ESP8266, as the sensing hardware, was utilized to deploy the WiFi sensor network and collect multi-dimensional received signal strength indicator (RSSI) records. The proposed learning model presents a coarse-to-fine hierarchical classification framework with two-level perception modules. In the coarse-level stage, twelve statistical features of time–frequency domains were extracted from the RSSI measurements filtered by a butterworth low-pass filter, and a support vector machine (SVM) model was employed to quickly recognize the basic human activities by classifying the signal statistical features. In the fine-level stage, the gated recurrent unit (GRU), a representative type of recurrent neural network (RNN), was applied to address issues of the confused recognition of similar activities. The GRU model can realize automatic multi-level feature extraction from the RSSI measurements and accurately discriminate the similar activities. The experimental results show that the proposed approach achieved recognition accuracies of 96.45% and 94.59% for six types of activities in two different environments and performed better compared the traditional pattern-based methods. The proposed hierarchical learning method provides a low-cost sensor-based HAR framework to enhance the recognition accuracy and modeling efficiency.

Part information has been proven to be resistant to occlusions and viewpoint changes, which are main difficulties in car parsing and reconstruction. However, in the absence of datasets and approaches incorporating car parts, there are limited works that benefit from it. In this paper, we propose the first part-aware approach for joint part-level car parsing and reconstruction in single street view images. Without labor-intensive part annotations on real images, our approach simultaneously estimates pose, shape, and semantic parts of cars. There are two contributions in this paper. First, our network introduces dense part information to facilitate pose and shape estimation, which is further optimized with a novel 3D loss. To obtain part information in real images, a class-consistent method is introduced to implicitly transfer part knowledge from synthesized images. Second, we construct the first high-quality dataset containing 348 car models with physical dimensions and part annotations. Given these models, 60K synthesized images with randomized configurations are generated. Experimental results demonstrate that part knowledge can be effectively transferred with our class-consistent method, which significantly improves part segmentation performance on real street views. By fusing dense part information, our pose and shape estimation results achieve the state-of-the-art performance on the ApolloCar3D and outperform previous approaches by large margins in terms of both A3DP-Abs and A3DP-Rel.

This survey paper focuses on the estimation schemes in molecular communication (MC) systems. The existing studies in estimation schemes can be divided into parameter estimation (e.g., distance, diffusion coefficient, and flow velocity) and channel estimation. In this paper, we present, for the first time, a comprehensive survey on i) distance estimation, since distance is the most widely estimated parameter in current studies, ii) estimation of other parameters (i.e. the parameters excluding distance), and iii) channel estimation that focuses on the channel impulse response (CIR). Moreover, we examine the noise that may impact on the estimation performance and the metrics applied to evaluate the performance of different estimation schemes. Numerical results are provided to compare the performance of different distance estimation schemes. In addition, future research directions in parameter estimation and channel estimation are identified and discussed., Accepted at Digital Signal Processing

Video transmission over the backhaul link in cloud-edge collaborative networks usually suffers security risks, which is ignored in most of the existing studies. The characteristics that video service can flexibly adjust the encoding rates and provide acceptable encoding qualities, make the security requirements more possible to be satisfied but tightly coupled with video encoding by introducing more restrictions on edge caching. In this paper, by considering the interaction between video encoding and edge caching, we investigate the quality of experience (QoE)-driven cross-layer optimization of secure video transmission over the wireless backhaul link in cloud-edge collaborative networks. First, we develop a secure transmission model based on video encoding and edge caching. By employing this model as the security constraint, then we formulate a QoE-driven joint optimization problem subject to limited available caching capacity. To solve the optimization problem, we propose two algorithms: a near-optimal iterative algorithm (EC-VE) and a greedy algorithm with low computational complexity (Greedy EC-VE). Simulation results show that our proposed EC-VE can greatly improve user QoE within security constraints, and the proposed Greedy EC-VE can obtain the tradeoff between QoE and computational complexity., 14 pages, 8 figures

Traditional image recognition is mainly based on shallow neural networks, mainly including artificial networks, but these shallow neural networks have limited feature extraction capabilities. This paper can speed up the operation efficiency of the model, eliminate over-fitting, and improve the recognition accuracy by adding batch normalization layers to the neural network. The experiments are based on the MNIST data set, and have fully verified the recognition ability depth model proposed in this article.

We present a structured portfolio optimization framework with sparse inverse covariance estimation and an attention-based LSTM network that exploits machine learning (deep learning) techniques. We shrink Wishart volatility towards a Graphical Lasso initial covariance estimator and solve the portfolio optimization using a fast coordinate descent algorithm with regularization determined using a genetic algorithm. We further introduce a novel portfolio shrinkage rule using an attention-based Long-Short-Term-Memory (LSTM) network, allowing a formal selection of reference portfolios where the network forecasts future performance based on predetermined out-of-sample monthly certainty equivalent return. We reduce the dimension of successful candidates and then linearly combine them. When nested within a minimum-variance, Bayes-Stein shrinkage, Black-Litterman portfolio framework with four types of weight constraints based on no-short-selling, upper, lower-generalized variance-based restrictions, our approach delivers a clear improvement over the baseline sample-based minimum-variance portfolio and claims superiority over 11 GARCH models used to forecast covariances, as well as a minimum-variance combination of all dynamic optimization models. We provide an illustrative example based on optimal diversification across hedge fund strategies. Robustness checks show our application of sparse covariance dominates the use of a dimension reduction algorithm for Wishart covariance forecasting.

Identifying vital nodes in complex networks is of paramount importance in understanding and controlling the spreading dynamics. Currently, this study is facing great challenges in dealing with big data in many real-life applications. With the deepening of the research, scholars began to realize that the analysis on traditional graph model is insufficient because many nodes in a multilayer network share connections among different layers. To address this problem both efficiently and effectively, a novel algorithm for identifying vital nodes in both monolayer and multilayer networks is proposed in this paper. Firstly, a node influence measure is employed to determine the initial leader of a local community. Subsequently, the community structures are revealed via the Maximum Influential Neighbors Expansion (MINE) strategy. Afterward, the communities are regarded as super-nodes for an iteratively folding process till convergence, in order to identify influencers hierarchically. Numerical experiments on 32 real-world datasets are conducted to verify the performance of the proposed algorithm, which shows superiority to the competitors. Furthermore, we apply the proposed algorithm in the graph of adjacencies derived from the maps of China and USA. The comparison and analysis of the identified provinces (or states) suggest that the proposed algorithm is feasible and reasonable on real-life applications.

The influence maximization problem (IMP) in complex networks is to address finding a set of key nodes that play vital roles in the information diffusion process, and when these nodes are employed as &rdquo, seed nodes&rdquo, the diffusion effect is maximized. First, this paper presents a refined network centrality measure, a refined shell (RS) index for node ranking, and then proposes an algorithm for identifying key node sets, namely the reject neighbors algorithm (RNA), which consists of two main sequential parts, i.e., node ranking and node selection. The RNA refuses to select multiple-order neighbors of the seed nodes, scatters the selected nodes from each other, and results in the maximum influence of the identified node set on the whole network. Experimental results on real-world network datasets show that the key node set identified by the RNA exhibits significant propagation capability.

This paper discusses the finite-time synchronization of fractional-order Chen chaotic systems with different orders. Based on the properties of fractional calculus, fractional-order systems with different orders are transformed into problems of the same order, and a finite-time controller is designed by using the definition of finite-time synchronization, which makes the value of synchronization error system tend to zero in finite time, and then the finite-time synchronization of fractional-order chaotic systems with different orders is realized. The numerical simulation results verify the effectiveness and feasibility of the designed controller.

This paper focuses on the research of diversified e-commerce activities in e-commerce platform, mapping various business activities into the framework of resource allocation. When a certain number of users access the platform concurrently, the system allocates resources. This paper abandons the traditional simple filtering mode to analyze the historical data of e-commerce platform, abstracts the user commodity binary network and divides the user communities according to the attribute information of users and commodities and the purchase logs of users. By analyzing the community of users, we can allocate resources reasonably. In the binary network of users and goods, there are still many problems in user based clustering. For example, the sparseness of user attribute information, the proportion of intersection between users' purchasing goods is too small and so on. According to the characteristics of data and the existing problems, this paper selects the SimRank algorithm and improves it. In this paper, a combined similarity index based on user attributes and network structure is proposed to improve the accuracy of user clustering, and a reasonable scheme of resource allocation is proposed by using the community division of users, which increases the accuracy of user clustering, achieves the expected design goals, and improves work efficiency.

The scarcity of labelled time-series data can hinder a proper training of deep learning models. This is especially relevant for the growing field of ubiquitous computing, where data coming from wearable devices have to be analysed using pattern recognition techniques to provide meaningful applications. To address this problem, we propose a transfer learning method based on attributing sensor modality labels to a large amount of time-series data collected from various application fields. Using these data, our method firstly trains a Deep Neural Network (DNN) that can learn general characteristics of time-series data, then transfers it to another DNN designed to solve a specific target problem. In addition, we propose a general architecture that can adapt the transferred DNN regardless of the sensors used in the target field making our approach in particular suitable for multichannel data. We test our method for two ubiquitous computing problems&mdash, Human Activity Recognition (HAR) and Emotion Recognition (ER)&mdash, and compare it a baseline training the DNN without using transfer learning. For HAR, we also introduce a new dataset, Cognitive Village-MSBand (CogAge), which contains data for 61 atomic activities acquired from three wearable devices (smartphone, smartwatch, and smartglasses). Our results show that our transfer learning approach outperforms the baseline for both HAR and ER.

This paper addresses wearable-based recognition of Activities of Daily Living (ADLs) which are composed of several repetitive and concurrent short movements having temporal dependencies. It is improbable to directly use sensor data to recognize these long-term composite activities because two examples (data sequences) of the same ADL result in largely diverse sensory data. However, they may be similar in terms of more semantic and meaningful short-term atomic actions. Therefore, we propose a two-level hierarchical model for recognition of ADLs. Firstly, atomic activities are detected and their probabilistic scores are generated at the lower level. Secondly, we deal with the temporal transitions of atomic activities using a temporal pooling method, rank pooling. This enables us to encode the ordering of probabilistic scores for atomic activities at the higher level of our model. Rank pooling leads to a 5&ndash, 13% improvement in results as compared to the other popularly used techniques. We also produce a large dataset of 61 atomic and 7 composite activities for our experiments.

SiCf-SiCm composites are being actively developed as fuel cladding for improving accident tolerance of light water reactor fuel. Online monitoring of the degradation process in SiCf-SiCm composites is of great importance to ensure the safety of the nuclear reactor system. The degradation monitoring task can be mapped as a classification problem: given the Acoustic Emission(AE) events at a given timeslot, the model is expected to predict which one of the following three stages the material is in: elastic, matrix-driven and fiber-driven cracking. In this paper, degradation tests on SiCf-SiCm composite tubes were conducted using a bladder-based internal pressure technique with AE monitoring. We then trained a deep learning based end-to-end convolutional neural network (CNN) model for online monitoring of the damage progression process of SiCf-SiCm composite tubes using the AE data as the raw input. As a comparison, we also applied Random Forest (RF) with expert-crafted audio event features to the damage stage prediction problem. Experimental results show that both RF and CNN models yield good results but on average our end-to-end CNN models outperform the RF models due to its high-level feature extraction capability. The CNN model with single events can reach an average prediction accuracy of 84.4% compared to 74% of the RF models. Combining multiple audio samples typically improves the accuracy of the models with RF accuracy reaching 82.8% and CNN accuracy reaching 86.6%.

Studies from the literature show that the prevalence of sleep disorder in children is far higher than that in adults. Although much research effort has been made on sleep stage classification for adults, children have significantly different characteristics of sleep stages. Therefore, there is an urgent need for sleep stage classification targeting children in particular. Our method focuses on two issues: The first is timestamp-based segmentation (TSS) to deal with the fine-grained annotation of sleep stage labels for each timestamp. Compared to this, popular sliding window approaches unnecessarily aggregate such labels into coarse-grained ones. We utilize DeConvolutional Neural Network (DCNN) that inversely maps features of a hidden layer back to the input space to predict the sleep stage label at each timestamp. Thus, our DCNN can yield better classification performances by considering labels at numerous timestamps. The second issue is the necessity of multiple channels. Different clinical signs, symptoms or other auxiliary examinations could be represented by different Polysomnography (PSG) recordings, so all of them should be analyzed comprehensively. We therefor exploit multivariate time-series of PSG recordings, including 6 electroencephalograms (EEGs) channels, 2 electrooculograms (EOGs) channels (left and right), 1 electromyogram (chin EMG) channel and two leg electromyogram channels. Our DCNN-based method is tested on our SDCP dataset collected from child patients aged from 5 to 10 years old. The results show that our method yields the overall classification accuracy of 84.27% and macro F1-score of 72.51% which are higher than those of existing sliding window-based methods. One of the biggest advantages of our DCNN-based method is that it processes raw PSG recordings and internally extracts features useful for accurate sleep stage classification. We examine whether this is applicable for sleep data of adult patients by testing our method on a well-known public dataset Sleep-EDFX. Our method achieves the average overall accuracy of 90.89% which is comparable to those of state-of-the-art methods without using any hand-crafted features. This result indicates the great potential of our method because it can be generally used for timestamp-level classification on multivariate time-series in various medical fields. Additionally, we provide source codes so that researchers can reproduce the results in this paper and extend our method.

Prognosis techniques for prediction of remaining useful life (RUL) are of crucial importance to the management of complex systems for they can lead to appropriate maintenance interventions and improvements in reliability. While various data-driven methods have been introduced to predict the remaining useful life (RUL) of machinery systems or batteries, no research has been reported on the remaining useful strength (RUS) prediction of silicon carbide fiber reinforced silicon carbide matrix (SiCf-SiCm) materials with pivotal role in its potential usage as a structural material in nuclear reactors and turbine engines. Knowledge of its degradation process is of the utmost importance to the manufacturers. For this purpose, two approaches based on the machine-learning techniques of random-forest (RF) and convolutional neural network (CNN) are proposed to predict the RUS of SiCf-SiCm using only acoustic emission (AE) signals generated during the material&rsquo, s stress applying process. Experimental results show that the CNN models achieved better predictive performance than the RF models but the latter with expert-engineered features achieves better prediction for AE signals in the early stage of degradation. Additionally, our results demonstrate that both models can correctly predict the SiCf-SiCm RUS as evaluated by our robust testing method from which the best average root mean square error (RMSE) and Pearson correlation coefficient of 3.55 ksi units and 0.85 were obtained.

Limits are methods and tools for studying functions. In practical teaching, students do not understand the precise definition of limits and cannot grasp the essence of the definition. Therefore, the teacher introduced the concept with a practical example, and integrated the ideological and political elements into the ultimate teaching to solve what the limit of number series is. It can help students deepen their understanding of ideological and political education, fully mobilize the enthusiasm of students to study independently, improve their understanding and interest, and promote the overall development of students.

In this study, the authors focus on segment characteristic analysis and joint optimisation of modulation and coding scheme (MCS) selection, resource block (RB) assignment and the block error ratio (BLER) determination and segment adaptation scheme to satisfy dynamic adaptive streaming over HTTP (DASH) clients over wireless networks. First, the authors define a utility function as the continuous playback time that the packets scheduled with the allocated resource can support. Then, the authors formulate the MCS selection, RB assignment and BLER determination into a mathematical model. The relationship among the above three factors can be explored instead of performing MCS selection and RB assignment with the fixed BLER. By decomposing the original problem into some sub-problems, the authors can get a solution to the original problem with low complexity. At the client level, the authors develop an adaptive segment request strategy based on the playback information, the segments' characteristics and the estimated transmission rate. To decrease the influence of the inaccurate estimations, an adaptive guard time interval based on the real playback information and transmission information of the previous segments is introduced. Simulation results show that the proposed algorithm can efficiently improve playback continuity and video quality over the existing algorithms.

Recently, discriminative correlation filter based trackers have achieved extremely successful results in many competitions and benchmarks. These methods utilise a periodic assumption of the training samples to efficiently learn a classifier. However, this assumption will produce unwanted boundary effects which severely degrade the tracking performance. Correlation filters with limited boundaries and spatially regularised discriminative correlation filters were proposed to reduce boundary effects. However, their methods use the fixed scale mask or pre-designed weights function, respectively, which are unsuitable for large-scale variation. In this study, the authors proposed multiscale spatially regularised correlation filters (MSRCF) for visual tracking. The authors' augmented objective can reduce the boundary effect even in large-scale variation, leading to more discriminative model. The proposed multiscale regularisation matrix makes MSRCF fast convergence. The authors' online tracking algorithm performs favourably against state-of-the-art trackers on OTB-2013 and OTB-2015 Benchmark in terms of efficiency, accuracy and robustness.

Artificial potential field (APF), a concept from physic field, has been successfully adopted for path planning of unmanned aerial vehicle (UAV). The cooperation between the expulsion against obstacle and the gravity from target, ensures a global planning optimization considering obstacle avoidance. Unfortunately, under different UAV-to-UAV distance conditions, the APF also has a weakness unable to support swarm path planning for multiple UAVs due to the highly dynamic shift between the repulsion and the gravity. To utilize APF to realize robust swarm planning, we redesign the APF and embed it into the swarm avoidance mechanism from bird intelligence involving group collision avoidance (GCA) and individual collision avoidance (ICA), forming two kinds of a APF-based swarm planning respectively: GCA-APF and ICA-APF. We then propose an adapt switch mechanism for dynamically choosing GCA-APF or ICA-APF in contexts of different obstacle environment. Experiments show the effectiveness of our approach, 15.25% higher planning efficiency than that of original GCA and avoiding certain polynomial cost increase from original ICA.

For in-vehicle application, the vehicles with different speeds have different delay requirements. However, vehicle speeds have not been extensively explored, which may cause mismatching between vehicle speed and its allocated computation and wireless resource. In this paper, we propose a vehicle speed aware task offloading and resource allocation strategy, to decrease the energy cost of executing tasks without exceeding the delay constraint. First, we establish the vehicle speed aware delay constraint model based on different speeds and task types. Then, the delay and energy cost of task execution in VEC server and local terminal are calculated. Next, we formulate a joint optimization of task offloading and resource allocation to minimize vehicles' energy cost subject to delay constraints. MADDPG method is employed to obtain offloading and resource allocation strategy. Simulation results show that our algorithm can achieve superior performance on energy cost and task completion delay., Comment: 8 pages, 6 figures, Accepted by IEEE International Conference on Edge Computing 2020

This paper proposes a novel imperfect spherical transmitter (TX) model, namely the membrane fusion (MF)-based TX, that adopts MF between a vesicle and the TX membrane to release molecules encapsulated within the vesicle. For the MF-based TX, the molecule release probability and the fraction of molecules released from the TX membrane are derived. Incorporating molecular degradation and a fully-absorbing receiver (RX), the end-to-end molecule hitting probability at the RX is also derived. A simulation framework for the MF-based TX is proposed, where the released point on the TX membrane and the released time of each molecule are determined. Aided by the simulation framework, the derived analytical expressions are validated. Simulation results verify that a low MF probability or low vesicle mobility slows the release of molecules from the TX, extends time required to reach the peak release probability, and reduces the end-to-end molecule hitting probability at the RX., Comment: 6 pages, 5 figures, accepted at IEEE ICC 2021

This paper investigates the estimation of different parameters, e.g., propagation distance and flow velocity, by utilizing two fully-absorbing receivers (RXs) in a one-dimensional (1D) environment. The time-varying number of absorbed molecules at each RX and the number of absorbed molecules in a time interval as time approaches infinity are derived. Noisy molecules in this environment, that are released by sources in addition to the transmitter, are also considered. A novel estimation method, namely difference estimation (DE), is proposed to eliminate the effect of noise by using the difference of received signals at the two RXs. For DE, the Cramer-Rao lower bound (CRLB) on the variance of estimation is derived. Independent maximum likelihood estimation is also considered at each RX as a benchmark to show the performance advantage of DE. Aided by particle-based simulation, the derived analytical results are verified. Furthermore, numerical results show that DE attains the CRLB and is less sensitive to the change of noise than independent estimation at each RX., Comment: 7 pages, 5 figures, accepted by Globecom 2020

In this paper, we propose a more refined video segment based Mobile Edge Computing (MEC) enhanced cache update strategy, which takes into account the client's playback status and transmission state, MEC cache capacity and the popularity of each segment, to improve the quality of experience (QoE) of clients and the use ratio of MEC cache. In each cache update period, the segments which cannot bring significant QoE improvement will be deleted and meanwhile more suitable representations of the segments will be cahed instead. First, we divide the MEC cache space into three parts based on segment popularity and segment importance level. In addition, the size of different cache parts can be transformed to each other to further exploit the MEC cache space. For different parts, the corresponding deleted strategy and caching strategy are formulated, where the deleted strategy combines the requested times of segment and transmission capability of clients, and the caching strategy utilizes the playback state of clients to calculate the caching priority. Furthermore, we formulate the cache update problem to maximize the utility function of clients subject to the constraint of MEC cache size and transmission capacity. The brand and branch method is emplyed to obatain the optimal solution. Simulation results show that our proposed algorithm can improve system throughput and hit ratio of video segment, and at the same time decrease playback frozen time and system backhaul traffic compared with other existing algorithms.

We develop a new framework to analyze the average block error rate (BLER) of using short-packet communications in a non-orthogonal multiple access (NOMA) system. In this system, the N-antenna base station (BS) designs its transmission weight as per the instantaneous channel knowledge from the BS to either the near user or the far user. Incorporating the unique relationship of the finite blocklength and the achievable rate from the BS to two users, we derive new closed-form expressions for the average BLER for arbitrary signal-to-noise ratios (SNRs). We also derive simple expressions for the asymptotic average BLER at high SNRs, based on which we determine the optimal power allocation and minimum blocklength for satisfying the average BLER targets at two users. We demonstrate that the user, whose channel knowledge is used for weight design, achieves a lower BLER than the other. We further show that NOMA leads to a lower latency than orthogonal multiple access given the same average BLER targets. Notably, this latency advantage is more profound when the average BLER target ratio between the near user and the far user increases.

Wearable VR/AR devices provide users with fully immersive experience in a virtual environment, enabling possibilities to reshape the forms of entertainment and telepresence. While the body language is a crucial element in effective communication, wearing a head-mounted display (HMD) could severely hinder the eye contact and block facial expressions. We present a novel headset removal technique that enables high-quality occlusion-free communication in virtual environment. In particular, our solution synthesizes photoreal faces in the occluded region with faithful reconstruction of facial expressions and eye movements. Towards this goal, we develop a novel capture setup that consists of two near-infrared (NIR) cameras inside the HMD for eye capturing and one external RGB camera for recording visible face regions. To enable realistic face synthesis with consistent illuminations, we propose a data-driven approach to fuse the narrow-field-of-view NIR images with the RGB image captured from the external camera. In addition, to generate pho-torealistic eyes, a dedicated algorithm is proposed to colorize the NIR eye images and further rectify the color distortion caused by the non-linear mapping of IR light sensitivity. Experimental results demonstrate that our framework is capable to synthesize high-fidelity unoccluded facial images with accurate tracking of head motion, facial expression and eye movement.

This paper described a three-level circuit for a power distribution system used in intelligent micro-grid and combines an ordinary T-type three-level circuit with an RBIGBT. The topology of the circuit was firstly introduced in this paper, then the author introduces the modulation method and double closed-loop control strategy of the T-type three-level circuit based on RB-IGBT, afterwards the model for simulation was built. The losses of the RB-IGBT T-type three-level circuit, T-type three-level circuit based on common IGBT and two-level circuit were analyzed, including the calculation method of conduction and switching loss in detail. Then the losses of the three circuits were calculated. Finally, the efficiency of the circuit was compared under different switching frequencies and different output powers, so as to analyze the influence of the two factors of switching frequency and output power on different circuits.

Stem cells are very original cells that can differentiate into other cells, tissues and organs, which play a very important role in biomedical treatments. Because of the importance of stem cells, in this paper we propose a full-automatic computer aided clustering system to assist scientists to explore potential co-occurrence relations between the cell differentiation and their morphological information in phenotype. In this proposed system, a multi-stage Content-based Microscopic Image Analysis (CBMIA) framework is applied, including image segmentation, feature extraction, feature selection, feature fusion and clustering techniques. First, an Improved Supervised Normalized Cuts (ISNC) segmentation algorithm is newly introduced to partition multiple stem cells into individual regions in an original microscopic image, which is the most important contribution in this paper. Then, based on the segmented stem cells, 11 different feature extraction approaches are applied to represent the morphological characteristics of them. Thirdly, by analysing the robustness and stability of the extracted features, Hu and Zernike moments are selected. Fourthly, these two selected features are combined by an early fusion approach to further enhance the properties of the feature representation of stem cells. Finally, k -means clustering algorithm is chosen to classify stem cells into different categories using the fused feature. Furthermore, in order to prove the effectiveness and usefulness of this proposed system, we carry out a series of experiments to evaluate our methods. Especially, our ISNC segmentation obtains 92.4% similarity, 96.0% specificity and 107.8% ration of accuracy, showing the potential of our work.

In order to accurately predict the change trend of enterprise assets, this paper proposes a prediction method of enterprise return on net assets based on improved random forest algorithm. Firstly, this paper analyzes the research background and significance of the enterprise net income rate prediction, and on this basis, it considers to use the random forest algorithm to achieve the prediction. In view of the shortcomings of the algorithm, the paper introduces the simulated annealing algorithm to improve the random forest algorithm and optimizes the prediction performance of the algorithm in the direction of feature selection, parameter optimization and weight setting, finally establishes the prediction model of enterprise return on net assets. In this paper, the proposed algorithm is compared with other algorithms and results show that the method proposed in this paper has a good prediction effect on the enterprise return on net assets, which is helpful for the capital market to evaluate the asset value and profitability of enterprises.

Node embedding is a representation learning technique that maps network nodes into lower-dimensional vector space. Embedding nodes into vector space can benefit network analysis tasks, such as community detection, link prediction, and influential node identification, in both calculation and richer application scope. In this paper, we propose a two-step node embedding-based solution for the social influence maximization problem (IMP). The solution employs a revised network-embedding algorithm to map input nodes into vector space in the first step. In the second step, the solution clusters the vector space nodes into subgroups and chooses the subgroups&rsquo, centers to be the influential spreaders. The proposed approach is a simple but effective IMP solution because it takes both the social reinforcement and homophily characteristics of the social network into consideration in node embedding and seed spreaders selection operation separately. The information propagation simulation experiment of single-point contact susceptible-infected-recovered (SIR) and full-contact SIR models on six different types of real network data sets proved that the proposed social influence maximization (SIM) solution exhibits significant propagation capability.

Simulation systems have become an essential component in the development and validation of autonomous driving technologies. The prevailing state-of-the-art approach for simulation is to use game engines or high-fidelity computer graphics (CG) models to create driving scenarios. However, creating CG models and vehicle movements (e.g., the assets for simulation) remains a manual task that can be costly and time-consuming. In addition, the fidelity of CG images still lacks the richness and authenticity of real-world images and using these images for training leads to degraded performance. In this paper we present a novel approach to address these issues: Augmented Autonomous Driving Simulation (AADS). Our formulation augments real-world pictures with a simulated traffic flow to create photo-realistic simulation images and renderings. More specifically, we use LiDAR and cameras to scan street scenes. From the acquired trajectory data, we generate highly plausible traffic flows for cars and pedestrians and compose them into the background. The composite images can be re-synthesized with different viewpoints and sensor models. The resulting images are photo-realistic, fully annotated, and ready for end-to-end training and testing of autonomous driving systems from perception to planning. We explain our system design and validate our algorithms with a number of autonomous driving tasks from detection to segmentation and predictions. Compared to traditional approaches, our method offers unmatched scalability and realism. Scalability is particularly important for AD simulation and we believe the complexity and diversity of the real world cannot be realistically captured in a virtual environment. Our augmented approach combines the flexibility in a virtual environment (e.g., vehicle movements) with the richness of the real world to allow effective simulation of anywhere on earth.

As a more complicated network model, multilayer networks provide a better perspective for describing the multiple interactions among social networks in real life. Different from conventional community detection algorithms, the algorithms for multilayer networks can identify the underlying structures that contain various intralayer and interlayer relationships, which is of significance and remains a challenge. In this paper, aiming at the instability of the label propagation algorithm (LPA), an improved label propagation algorithm based on the SH-index (SH-LPA) is proposed. By analyzing the characteristics and deficiencies of the H-index, the SH-index is presented as an index to evaluate the importance of nodes, and the stability of the SH-LPA algorithm is verified by a series of experiments. Afterward, considering the deficiency of the existing multilayer network aggregation model, we propose an improved multilayer network aggregation model that merges two networks into a weighted single-layer network. Finally, considering the influence of the SH-index and the weight of the edge of the weighted network, a community detection algorithm (MSH-LPA) suitable for multilayer networks is exhibited in terms of the SH-LPA algorithm, and the superiority of the mentioned algorithm is verified by experimental analysis.

Person re-identification (Re-ID) is an important technique for video surveillance and security systems. Most existing Re-ID methods assume fixed size of training data and the models have to be re-trained from scratch given newly collected data, which is time-consuming. Accelerating the training speed with ever-increasing data is desired and critical for Re-ID. In this work, we propose to apply incremental learning to address this problem. We build the Re-ID model based on the null Foley-Sammon transform (NFST) method. Our idea is to extract new information from newly-added data and integrate it with the existing NFST trained model by an efficient updating scheme. We derived the incremental learning algorithm for both the non-kernelized and kernelized version of NFST. Extensive experiments have been carried on three public datasets, including VIPeR, PRID2011 and CUHK01. The results show that our proposed method can achieve comparable accuracy to the batch learning method while significantly reduces the computational complexity.

Community structure is one of the most common and important topological properties of complex networks and community detection provides crucial significance to the study of network characteristics. In the paper, incorporating the information entropy theory, the similarity between nodes and community is redefined, and a heuristic community detection algorithm is proposed, which is called Community Detection Algorithm Based on Information Entropy Similarity (referred as IES algorithm for short). Experimental results demonstrate that the proposed IES algorithm outperforms three traditional methods GN, Fast Newman and CPM algorithm on the karate clubs networks, dolphin social networks and football networks: the modularity value $Q$ of IES algorithm is obviously higher than the other three algorithms, the time complexity and space complexity of IES algorithm are lower than both GN and Fast Newman algorithms, and the efficiency of community partition is also higher. Compared with IE algorithm which is also based on information entropy similarity, the experimental results on Scientists Collaborate Networks further prove that the IES algorithm is more reasonable in the convergence and the community detection rationality.

Scene parsing aims to assign a class (semantic) label for each pixel in an image. It is a comprehensive analysis of an image. Given the rise of autonomous driving, pixel-accurate environmental perception is expected to be a key enabling technical piece. However, providing a large scale dataset for the design and evaluation of scene parsing algorithms, in particular for outdoor scenes, has been difficult. The per-pixel labelling process is prohibitively expensive, limiting the scale of existing ones. In this paper, we present a large-scale open dataset, ApolloScape, that consists of RGB videos and corresponding dense 3D point clouds. Comparing with existing datasets, our dataset has the following unique properties. The first is its scale, our initial release contains over 140K images - each with its per-pixel semantic mask, up to 1M is scheduled. The second is its complexity. Captured in various traffic conditions, the number of moving objects averages from tens to over one hundred (Figure 1). And the third is the 3D attribute, each image is tagged with high-accuracy pose information at cm accuracy and the static background point cloud has mm relative accuracy. We are able to label these many images by an interactive and efficient labelling pipeline that utilizes the high-quality 3D point cloud. Moreover, our dataset also contains different lane markings based on the lane colors and styles. We expect our new dataset can deeply benefit various autonomous driving related applications that include but not limited to 2D/3D scene understanding, localization, transfer learning, and driving simulation.

Autonomous driving has attracted tremendous attention especially in the past few years. The key techniques for a self-driving car include solving tasks like 3D map construction, self-localization, parsing the driving road and understanding objects, which enable vehicles to reason and act. However, large scale data set for training and system evaluation is still a bottleneck for developing robust perception models. In this paper, we present the ApolloScape dataset [1] and its applications for autonomous driving. Compared with existing public datasets from real scenes, e.g. KITTI [2] or Cityscapes [3], ApolloScape contains much large and richer labelling including holistic semantic dense point cloud for each site, stereo, per-pixel semantic labelling, lanemark labelling, instance segmentation, 3D car instance, high accurate location for every frame in various driving videos from multiple sites, cities and daytimes. For each task, it contains at lease 15x larger amount of images than SOTA datasets. To label such a complete dataset, we develop various tools and algorithms specified for each task to accelerate the labelling process, such as 3D-2D segment labeling tools, active labelling in videos etc. Depend on ApolloScape, we are able to develop algorithms jointly consider the learning and inference of multiple tasks. In this paper, we provide a sensor fusion scheme integrating camera videos, consumer-grade motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robust self-localization and semantic segmentation for autonomous driving. We show that practically, sensor fusion and joint learning of multiple tasks are beneficial to achieve a more robust and accurate system. We expect our dataset and proposed relevant algorithms can support and motivate researchers for further development of multi-sensor fusion and multi-task learning in the field of computer vision., Comment: Version 4: Accepted by TPAMI. Version 3: 17 pages, 10 tables, 11 figures, added the application (DeLS-3D) based on the ApolloScape Dataset. Version 2: 7 pages, 6 figures, added comparison with BDD100K dataset

Complex network is a kind of system structure, which widely exists in human society and nature. It can be used to capture and describe the evolution law, evolution mechanism, and dynamic behaviors. We study the model of entity growth in complex networks, achieve the single node growth model, block growth model and degree of communication difficulty based growth model, then carry out the theoretical analysis and experimental simulation, it is concluded that the entity growth model holds the characteristics of high robustness, high clustering coefficient and low average path. According to the growth model, this paper analyzes the basic idea and implementation process of the self-organizing community discovery algorithm based on information entropy, experimental results show that it is structurally reasonable and has important significance in practical application.

As a kind of typical complex network, bipartite network has already received many specialized research. Local community detection is very useful for bipartite network, but it has not yet been systematically researched. To guarantee equivalent partitioning (obtaining coincident community structure starting from arbitrary node) for two category nodes in bipartite network, a centrality-based bipartite local community detection (CBLCD) algorithm is proposed inspired by water surface undulation. The algorithm first gets local centralized subgraphs/subnetworks according to resource allocation index R defined in this paper, and then expands and combines these subnetworks, until the ultimate local communities are detected. The experimental results on some typical network datasets show that the algorithm achieved both good accuracy and stability.

Hubs identification is important for the stability and attack tolerance of complex networks. This paper focuses on public transit hubs identification, and it is useful for the optimization, design, and evaluation of public transit systems. Three public transit hubs identification methods are proposed in this paper. The first one is based on comprehensive effects of stations on the distance and the transfer, and the second one is based on preferences of passengers Transfer – Shortest Path, and the third one is based on preferences of passengers Shortest Path – Transfer. Three employed methods are applied in the Shenyang (the capital of Liaoning province of China) bus transit system, and experimental results show that they are available and especially feasible for finding those potential nodes who play key roles in the network but are not commonly regarded as important nodes in practice, and it is beneficial for traffic policy making.

Cross-camera pedestrian re-identification (re-ID) is of paramount importance for surveillance tasks. Although considerable progress has been made to improve the re-ID accuracy, real-time pedestrian detection and re-ID remains a challeging problem. In this work, first, we proposed an enhanced aggregated channel features (ACF+) based on the ACF pedestrian detector [1] for real-time pedestrian detection and re-ID; Second, to further improve the representation power of the combined multiple channel features, we proposed a novel hybrid distance metric learning method. Extensive experiments have been carried on two public datasets, including VIPeR, and PRID2011. The experimental results show that our proposed method can achieve state-of-the-art accuracy while being computational efficient for real-time applications. The proposed hybrid distance metric learning is general, thus can be applied to any metric learning approaches.