arXiv subjects
Publications and source records attributed to Weifeng Sun.
Moduli space of the Bogomolny equation on R^3 with certain asymptotic conditions at infinity has been well studied for a long time. This paper studies the moduli space of solutions to the Bogomolny equation on R^3 with a knot singularity. The author hopes such kind of moduli spaces have potential applications in low-dimensional topology and knot theory in the future.
Deep learning for image super-resolution (SR) has been investigated by numerous researchers in recent years. Most of the works concentrate on effective block designs and improve the network representation but lack interpretation. There are also iterative optimization-inspired networks for image SR, which take the solution step as a whole without giving an explicit optimization step. This paper proposes an unfolding iterative shrinkage thresholding algorithm (ISTA) inspired network for interpretable image SR. Specifically, we analyze the problem of image SR and propose a solution based on the ISTA method. Inspired by the mathematical analysis, the ISTA block is developed to conduct the optimization in an end-to-end manner. To make the exploration more effective, a multi-scale exploitation block and multi-scale attention mechanism are devised to build the ISTA block. Experimental results show the proposed ISTA-inspired restoration network (ISTAR) achieves competitive or better performances than other optimization-inspired works with fewer parameters and lower computation complexity.
Adaptive Random Testing (ART) is an enhancement of Random Testing (RT), and aims to improve the RT failure-detection effectiveness by distributing test cases more evenly in the input domain. Many ART algorithms have been proposed, with Fixed-Size-Candidate-Set ART (FSCS-ART) being one of the most effective and popular. FSCS-ART ensures high failure-detection effectiveness by selecting the next test case as the candidate farthest from previously-executed test cases. Although FSCS-ART has good failure-detection effectiveness, it also faces some challenges, including heavy computational overheads. In this paper, we propose an enhanced version of FSCS-ART, Vantage Point Partitioning ART (VPP-ART). VPP-ART addresses the FSCS-ART computational overhead problem using vantage point partitioning, while maintaining the failure-detection effectiveness. VPP-ART partitions the input domain space using a modified Vantage Point tree (VP-tree) and finds the approximate nearest executed test cases of a candidate test case in the partitioned sub-domains -- thereby significantly reducing the time overheads compared with the searches required for FSCS-ART. To enable the FSCS-ART dynamic insertion process, we modify the traditional VP-tree to support dynamic data. The simulation results show that VPP-ART has a much lower time overhead compared to FSCS-ART, but also delivers similar (or better) failure-detection effectiveness, especially in the higher dimensional input domains. According to statistical analyses, VPP-ART can improve on the FSCS-ART failure-detection effectiveness by approximately 50% to 58%. VPP-ART also compares favorably with the KDFC-ART algorithms (a series of enhanced ART algorithms based on the KD-tree). Our experiments also show that VPP-ART is more cost-effective than FSCS-ART and KDFC-ART.
Object detection is a basic and important task in the field of aerial image processing and has gained much attention in computer vision. However, previous aerial image object detection approaches have insufficient use of scene semantic information between different regions of large-scale aerial images. In addition, complex background and scale changes make it difficult to improve detection accuracy. To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): 1) Firstly, multi-scale features are fused and enhanced by a dual relationship module (DRM) with conditional convolution. The dual relationship module learns the potential relationship between features of different scales and learns the relationship between different scenes from different patches in a same iteration. In addition, the dual relationship module dynamically generates parameters to guide the fusion of multi-scale features. 2) Secondly, The bridging visual representations module (BVR) is introduced into the field of aerial images to improve the object detection effect in images with complex backgrounds. Experiments with a publicly available object detection dataset for aerial images demonstrate that the proposed RelationRS achieves a state-of-the-art detection performance.
Cyber attacks pose crucial threats to computer system security, and put digital treasuries at excessive risks. This leads to an urgent call for an effective intrusion detection system that can identify the intrusion attacks with high accuracy. It is challenging to classify the intrusion events due to the wide variety of attacks. Furthermore, in a normal network environment, a majority of the connections are initiated by benign behaviors. The class imbalance issue in intrusion detection forces the classifier to be biased toward the majority/benign class, thus leave many attack incidents undetected. Spurred by the success of deep neural networks in computer vision and natural language processing, in this paper, we design a new system named DeepIDEA that takes full advantage of deep learning to enable intrusion detection and classification. To achieve high detection accuracy on imbalanced data, we design a novel attack-sharing loss function that can effectively move the decision boundary towards the attack classes and eliminates the bias towards the majority/benign class. By using this loss function, DeepIDEA respects the fact that the intrusion mis-classification should receive higher penalty than the attack mis-classification. Extensive experimental results on three benchmark datasets demonstrate the high detection accuracy of DeepIDEA. In particular, compared with eight state-of-the-art approaches, DeepIDEA always provides the best class-balanced accuracy.
The observation of the highly unusual half-quantum vortex (HQV) in a single crystalline superconductor excludes unequivocally the spin-singlet symmetry of the superconducting order parameter. HQVs were observed previously in mesoscopic samples of Sr2RuO4 in cantilever torque magnetometry measurements, thus providing direct evidence for spin-triplet pairing in the material. In addition, it raised important questions on HQV, including its stability and dynamics. These issues have remained largely unexplored, in particular, experimentally. We report in this paper the detection of HQVs in mesoscopic, doubly connected cylinders of single-crystalline Sr2RuO4 of a mesoscopic size and the examination of the effect of the in-plane magnetic field needed for the observation of the HQV by magnetoresistance (MR) oscillations measurements. Several distinct features found in our data, especially a dip and secondary peaks in the MR oscillations seen only in the presence of a sufficiently large in-plane magnetic field as well as a large measurement current, are linked to the formation of the HQV fluxoid state in and crossing of an Abrikosov HQV through the sample. The conclusion is drawn from the analysis of our data using a model of thermally activated vortex crossing overcoming a free-energy barrier which is modulated by the applied magnetic flux enclosed in the cylinder as well as the measurement current. Evidence for the trapping of an HQV fluxoid state in the sample was also found. Our observation of the HQV in mesoscopic Sr2RuO4 provided not only additional evidence for spin-triplet superconductivity in Sr2RuO4 but also insights into the physics of HQV, including its spontaneous spin polarization, stability, and dynamics. Our study also revealed a possible effect of the measurement current on the magnitude of the spontaneous spin polarization associated with the HQV.
Failure region, where failure-causing inputs reside, has provided many insights to enhance testing effectiveness of many testing methods. Failure region may also provide some important information to support other processes such as software debugging. When a testing method detects a software failure, indicating that a failure-causing input is identified, the next important question is about how to identify the failure region based on this failure-causing input, i.e., Identification of Failure Regions (IFR). In this paper, we introduce a new IFR strategy, namely Search for Boundary (SB), to identify an approximate failure region of a numeric input domain. SB attempts to identify additional failure-causing inputs that are as close to the boundary of the failure region as possible. To support SB, we provide a basic procedure, and then propose two methods, namely Fixed-orientation Search for Boundary (FSB) and Diverse-orientation Search for Boundary (DSB). In addition, we implemented an automated experimentation platform to integrate these methods. In the experiments, we evaluated the proposed SB methods using a series of simulation studies andempirical studies with different types of failure regions. The results show that our methods can effectively identify a failure region, within the limited testing resources.
Random testing (RT) is a well-studied testing method that has been widely applied to the testing of many applications, including embedded software systems, SQL database systems, and Android applications. Adaptive random testing (ART) aims to enhance RT's failure-detection ability by more evenly spreading the test cases over the input domain. Since its introduction in 2001, there have been many contributions to the development of ART, including various approaches, implementations, assessment and evaluation methods, and applications. This paper provides a comprehensive survey on ART, classifying techniques, summarizing application areas, and analyzing experimental evaluations. This paper also addresses some misconceptions about ART, and identifies open research challenges to be further investigated in the future work.
Regression test case prioritization (RTCP) aims to improve the rate of fault detection by executing more important test cases as early as possible. Various RTCP techniques have been proposed based on different coverage criteria. Among them, a majority of techniques leverage code coverage information to guide the prioritization process, with code units being considered individually, and in isolation. In this paper, we propose a new coverage criterion, code combinations coverage, that combines the concepts of code coverage and combination coverage. We apply this coverage criterion to RTCP, as a new prioritization technique, code combinations coverage based prioritization (CCCP). We report on empirical studies conducted to compare the testing effectiveness and efficiency of CCCP with four popular RTCP techniques: total, additional, adaptive random, and search-based test prioritization. The experimental results show that even when the lowest combination strength is assigned, overall, the CCCP fault detection rates are greater than those of the other four prioritization techniques. The CCCP prioritization costs are also found to be comparable to the additional test prioritization technique. Moreover, our results also show that when the combination strength is increased, CCCP provides higher fault detection rates than the state-of-the-art, regardless of the levels of code coverage.
Previously, Cristofaro-Gardiner, Hutchings and Ramos have proved that embedded contact homology (ECH) capacities can recover the volume of a contact 3-manifod in their paper "the asymptotics of ECH capacities" . There were two main steps to proving this theorem: The first step used an estimate for the energy of min-max Seiberg-Witten Floer generators. The second step used embedded balls in a certain symplectic four manifold. In this paper, stronger estimates on the energy of min-max Seiberg-Witten Floer generators are derived. This stronger estimate implies directly the "ECH capacities recover volume" theorem (without the help of embedded balls in a certain symplectic four manifold), and moreover, gives an estimate on its speed.
Broadcast routing has become an important research field for vehicular ad-hoc networks (VANETs) recently. However, the packet delivery rate is generally low in existing VANET broadcast routing protocols. Therefore, the design of an appropriate broadcast protocol based on the features of VANET has become a crucial part of the development of VANET. This paper analyzes the disadvantage of existing broadcast routing protocols in VANETs, and proposes an improved algorithm (namely ODAM-C) based on the ODAM (Optimized Dissemination of Alarm Messages) protocol. The ODAM-C algorithm improves the packet delivery rate by two mechanisms based on the forwarding features of ODAM. The first distance-based mechanism reduces the possibility of packet loss by considering the angles between source nodes, forwarding nodes and receiving nodes. The second mechanism increases the redundancy of forwarding nodes to guarantee the packet success delivery ratio. We show by analysis and simulations that the proposed algorithm can improve packet delivery rate for vehicular networks compared against two widely-used existing protocols.
Even though channel assignment has been studied for years, the performance of most IEEE 802.11-based multi-hop wireless networks such as wireless sensor network (WSN), wireless mesh network (WMN), mobile ad hoc network (MANET) is limited by channel interference. Properly assigning orthogonal channels to wireless links can improve the throughput of multi-hop networks. To solve the dynamic channel assignment problem, a routing-based channel assignment algorithm called R-CA is proposed. R-CA can allocate channels for wireless nodes when needed and free channels after data transmission. Thus more channel resource can be explored by wireless nodes. Simulation results show that R-CA can effectively enhance the network throughput and packet delivery rate.
Wireless body sensors are becoming popular in healthcare applications. Since they are either worn or implanted into human body, these sensors must be very small in size and light in weight. The energy consequently becomes an extremely scarce resource, and energy conservation turns into a first class design issue for body sensor networks (BSNs). This paper deals with this issue by taking into account the unique characteristics of BSNs in contrast to conventional wireless sensor networks (WSNs) for e.g. environment monitoring. A prediction-based data transmission approach suitable for BSNs is presented, which combines a dual prediction framework and a low-complexity prediction algorithm that takes advantage of PID (proportional-integral-derivative) control. Both the framework and the algorithm are generic, making the proposed approach widely applicable. The effectiveness of the approach is verified through simulations using real-world health monitoring datasets.