Siamese visual tracking, viewed as a problem of max-similarity matching to the target template, has absorbed increasing attention in computer vision. However, it is a challenge for current Siamese trackers that the demands of balance between accuracy in real-time tracking and robustness in long-time tracking are hard to meet. This work proposes a new Siamese based tracker with a dual-pipeline correlated fusion network (named as ADF-SiamRPN), which consists of one initial template for robust correlation, and the other transient template with the ability of adaptive feature optimal selection for accurate correlation. By the promotion from the learnable correlation-response fusion network afterwards, we are in pursuit of the synthetical improvement of tracking performance. To compare the performance of ADF-SiamRPN with state-of-the-art trackers, we conduct lots of experiments on benchmarks like OTB100, UAV123, VOT2016, VOT2018, GOT-10k, LaSOT and TrackingNet. The experimental results of tracking demonstrate that ADF-SiamRPN outperforms all the compared trackers and achieves the best balance between accuracy and robustness.

In wireless networks, efficient topology improves the performance of network protocols. The previous research mainly focuses on how to construct a cost-efficient network structure from a static and connected topology. Due to lack of continuous connectivity in the underlying topology, most traditional topology control methods are not applicable to the delay or disruption tolerant networks (DTNs). In this paper, we consider the topology control problem in a predictable DTN where the dynamic topology is known a priori or can be predicted over time. First, this dynamic topology is modeled by a directed space-time graph that includes spatial and temporal information. Second, the topology control problem of the predictable DTN is formulated as building a sparse structure. For any pair devices, there is an efficient path connecting them to improve the efficiency of the generated structure. Then, a topology control strategy is proposed for this optimization problem by using a kth shortest paths algorithm. Finally, simulations are conducted on random networks and a real-world DTN tracing date. The results demonstrate that the proposed method can significantly improve the efficiency of the generated structure and reduce the total cost.

Business process similarity measure is required by many applications, such as business process query, improvement, redesign, and etc. Many process behavior similarity measures have been proposed in the past two decades. However, to the best of our knowledge, most existing work only focuses on the direct causality transition relations and totally neglect the concurrent and transitive transition relations that are proved to be equally important when measuring process behavior similarity. In this paper, we take the weakness of existing process behavior similarity measures as a starting point, and propose a comprehensive approach to measure the business process behavior similarity based on the so-called Extended Transition Relation set, ETR-set for short. Essentially, the ETR-set is an ex-tended transition relation set containing direct causal transition relations, minimum concurrent transition relations and transitive causal transition relations. Based on the ETR-set, a novel process behavior similarity measure is defined. By constructing a concurrent reachability graph, our approach finds an effective technique to obtain the ETR-set. Finally, we evaluate our proposed approach in terms of its property analysis as well as conducting a group of control experiments.

The pervasive application of Small Private Online Course (SPOC) provides a powerful impetus for the reform of higher education. During the teaching process, a teacher needs to understand the difficulty of SPOC videos for students in real time to be more focused on the difficulties and key points of the course in a flipped classroom. However, existing educational data mining techniques pay little attention to the SPOC video difficulty clustering or classification. In this paper, we propose an approach to cluster SPOC videos based on the difficulty using video-watching data in a SPOC. Specifically, a bipartite graph that expresses the learning relationship between students and videos is constructed based on the number of video-watching times. Then, the SimRank++ algorithm is used to measure the similarity of the difficulty between any two videos. Finally, the spectral clustering algorithm is used to implement the video clustering based on the obtained similarity of difficulty. Experiments on a real data set in a SPOC show that the proposed approach has better clustering accuracy than other existing ones. This approach facilitates teachers learn about the overall difficulty of a SPOC video for students in real time, and therefore knowledge points can be explained more effectively in a flipped classroom.

Time performance optimization and resource conflict resolution are two important challenges in multiple project management contexts. Compared with traditional project management, multi-project management usually suffers limited and insufficient resources, and a tight and urgent deadline to finish all concurrent projects. In this case, time performance optimization of the global project management is badly needed. To our best knowledge, existing work seldom pays attention to the formal modeling and analyzing of multi-project management in an effort to eliminate resource conflicts and optimizing the project execution time. This work proposes such a method based on PRT-Net, which is a Petri net-based formulism tailored for a kind of project constrained by resource and time. The detailed modeling approaches based on PRT-Net are first presented. Then, resource conflict detection method with corresponding algorithm is proposed. Next, the priority criteria including a key-activity priority strategy and a waiting-short priority strategy are presented to resolve resource conflicts. Finally, we show how to construct a conflict-free PRT-Net by designing resource conflict resolution controllers. By experiments, we prove that our proposed priority strategy can ensure the execution time of global multiple projects much shorter than those without using any strategies.

Effective emergency resource allocation is essential to guarantee a successful emergency disposal, and it has become a research focus in the area of emergency management. Emergency event logs are accumulated in modern emergency management systems and can be analyzed to support effective resource allocation. This paper proposes a novel approach for efficient emergency resource allocation by mining emergency event logs. More specifically, an emergency event log with various attributes, e.g., emergency task name, emergency resource type (reusable and consumable ones), required resource amount, and timestamps, is first formalized. Then, a novel algorithm is presented to discover emergency response process models, represented as an extension of Petri net with resource and time elements, from emergency event logs. Next, based on the discovered emergency response process models, the minimum resource requirements for both reusable and consumable resources are obtained, and two resource allocation strategies, i.e., the Shortest Execution Time (SET) strategy and the Least Resource Consumption (LRC) strategy, are proposed to support efficient emergency resource allocation decision-making. Finally, a chlorine tank explosion emergency case study is used to demonstrate the applicability and effectiveness of the proposed resource allocation approach.

A narrowband interference (NBI) estimation and mitigation method based on compressive sensing (CS) for communication systems with repeated training sequences is investigated in this letter. The proposed CS-based differential measuring method is performed through the differential operation on the inter-block-interference-free regions of the received adjacent training sequences. The sparse NBI signal can be accurately recovered from a time-domain measurement vector of small size under the CS framework, without requiring channel information or dedicated resources. Theoretical analysis and simulation results show that the proposed method is robust to NBI under multi-path fading channels.

Due to the rapid development of different processors, e.g., x86 and Sunway, software porting between different platforms is becoming more frequent. However, the migrated software's execution efficiency on the target platform is different from that of the source platform, and most of the previous studies have investigated the improvement of the efficiency from the hardware perspective. To the best of our knowledge, this is the first paper to exclusively focus on studying what software factors can result in performance change after software migration. To perform our study, we used SonarQube to detect and measure five software factors, namely Duplicated Lines (DL), Code Smells Density (CSD), Big Functions (BF), Cyclomatic Complexity (CC), and Complex Functions (CF), from 13 selected projects of SPEC CPU2006 benchmark suite. Then, we measured the change of software performance by calculating the acceleration ratio of execution time before (x86) and after (Sunway) software migration. Finally, we performed a multiple linear regression model to analyze the relationship between the software performance change and the software factors. The results indicate that the performance change of software migration from the x86 platform to the Sunway platform is mainly affected by three software factors, i.e., Code Smell Density (CSD), Cyclomatic Complexity (CC), and Complex Functions (CF). The findings can benefit both researchers and practitioners.

In this paper, we consider the signal processing algorithm on each subcarrier for the downlink of Multi-User Multiple-Input Multiple-Output Orthogonal Frequency Division Multiplexing (MU-MIMO OFDM) system. A novel transmit scheme is proposed for the cancellation of Inter-User Interference (IUI) at the Base Station (BS). The improved performance of each user is obtained by optimizing the transmit scheme on each subcarrier, where the Particle Swarm Optimization (PSO) algorithm is employed to solve the constrained nonlinear optimization problem. Compared with the conventional Zero Forcing Dirty Paper Coding (ZF-DPC) having only single receive antenna at each Mobile Station (MS), the proposed scheme also applies the principle of DPC to cancel the IUI, but the MS users can be equipped with multiple receive antennas producing their increased receive SNR's. With the Channel State Information (CSI) being known at the BS and the MS, the eigenvalues for all the user channels are calculated first and then the user with the maximum eigenvalue is selected as the 1-st user. The remaining users are ordered and sequentially processed, where the transmit weights are generated from the previously selected users by the Particle Swarm Optimization (PSO) algorithm which ensures the transmit gain for each user as large as possible. The computational complexity analysis, BER performance and achievable sum-rate analysis of system verify the effectiveness of the proposed scheme.

In this paper, we focus on the cancellation of interference among Destination Users (DU's) and the improvement of achievable sum rate of the nonregenerative multiuser Multiple-Input Multiple-Output (MIMO) relay downlink system. A novel design method of transmit weight is proposed to successively eliminate the interference among DU's, each of which is equipped with multiple receive antennas. We firstly investigate the transmit weight design for the Amplify-and-Forward (AF) relay scheme where the Relay Station (RS) just retransmits the received signals from Base Station (BS), then extend it to the joint design scheme of transmit weights at the both BS and RS. In the proposed joint design scheme, through the comparison of lower bound of achievable rate, an effective DU selection algorithm is proposed to generate the transmit weight at the RS and obtain the multiuser diversity. Dirty Paper Coding (DPC) technique is employed to remove the interference among DU's and ensures the achievable rate of downlink. Theoretical derivation and simulation results demonstrate the effectiveness of the proposed scheme in obtaining the achievable rate performance and BER characteristics.

During the execution of software, tremendous amounts of data can be recorded. By exploiting the execution data, one can discover behavioral models to describe the actual software execution. As a well-known open-source process mining toolkit, ProM integrates quantities of process mining techniques and enjoys a variety of applications in a broad range of areas. How to develop a better ProM software, both from user experience and software performance perspective, are of vital importance. To achieve this goal, we need to investigate the real execution behavior of ProM which can provide useful insights on its usage and how it responds to user operations. This paper aims to propose an effective approach to solve this problem. To this end, we first instrument existing ProM framework to capture execution logs without changing its architecture. Then a two-layered framework is introduced to support accurate ProM behavior discovery by characterizing both user interaction behavior and plug-in calling behavior separately. Next, detailed discovery techniques to obtain user interaction behavior model and plug-in calling behavior model are proposed. All proposed approaches have been implemented.

This paper proposes a design of high-speed interconnection between optical modules and electrical modules via bonding-wires and coplanar waveguide transmission lines on printed circuit boards for 400 Gbps 4-channel optical communication systems. In order to broaden the interconnection bandwidth, interdigitated capacitors were integrated with GSG pads on chip for the first time. Simulation results indicate the reflection coefficient is below -10 dB from DC to 53 GHz and the insertion loss is below 1 dB from DC to 45 GHz. Both indicators show that the proposed interconnection structure can effectively satisfy the communication bandwidth requirements of 100-Gbps or even higher data-rate PAM4 signals.

During the execution of software systems, their execution data can be recorded. By fully exploiting these data, software practitioners can discover behavioral models describing the actual execution of the underlying software system. The recorded unstructured software execution data may be too complex, spanning over several days, etc. Applying existing discovery techniques results in spaghetti-like models with no clear structure and no valuable information for comprehension. Starting from the observation that a software system is composed of a set of logical components, Liu et al. propose to decompose the software behavior discovery problem into smaller independent ones by discovering a behavioral model per component in [1]. However, the effectiveness of the proposed approach is not fully evaluated and compared with existing approaches. In this paper, we evaluate the quality (in terms of understandability/complexity) of discovered component behavior models in a quantitative manner. Based on evaluation, we show that this approach can reduce the complexity of the discovered model and gives a better understanding.

Service mining aims to use process mining for the analysis of services, making it possible to discover, analyze, and improve service processes. In the context of Web services, the recording of all kinds of events related to activities is possible, which can be used to extract new information of service processes. However, the distributed nature of the services tends to generate large-scale service event logs, which complicates the discovery and analysis of service processes. To solve this problem, this research focus on the existing large-scale service event logs, a hybrid genetic service mining based on a trace clustering population method (HGSM) is proposed. By using trace clustering, the complex service system is divided into multiple functionally independent components, thereby simplifying the mining environment; And HGSM improves the mining efficiency of the genetic mining algorithm from the aspects of initial population quality improvement and genetic operation improvement, makes it better handle large service event logs. Experimental results demonstrate that compare with existing state-of-the-art mining methods, HGSM has better characteristics to handle large service event logs, in terms of both the mining efficiency and model quality.

Visual object tracking is always a challenging task in computer vision. During the tracking, the shape and appearance of the target may change greatly, and because of the lack of sufficient training samples, most of the online learning tracking algorithms will have performance bottlenecks. In this paper, an improved real-time algorithm based on deep learning features is proposed, which combines multi-feature fusion, multi-scale estimation, adaptive updating of target model and re-detection after target loss. The effectiveness and advantages of the proposed algorithm are proved by a large number of comparative experiments with other excellent algorithms on large benchmark datasets.

Non-orthogonal multipe access based multiple-input multiple-output system (MIMO-NOMA) has been widely used in improving user's achievable rate of millimeter wave (mmWave) communication. To meet different requirements of each user in multi-user beams, this paper proposes a power allocation algorithm to satisfy the quality of service (QoS) of head user while maximizing the minimum rate of edge users from the perspective of max-min fairness. Suppose that the user who is closest to the base station (BS) is the head user and the other users are the edge users in each beam in this paper. Then, an optimization problem model of max-min fairness criterion is developed under the constraints of users' minimum rate requirements and the total transmitting power of the BS. The bisection method and Karush-Kuhn-Tucher (KKT) conditions are used to solve this complex non-convex problem, and simulation results show that both the minimum achievable rates of edge users and the average rate of all users are greatly improved significantly compared with the traditional MIMO-NOMA, which only consider max-min fairness of users.