Advanced Search
Displaying 1-10 on page 1 of 34. Per Page  

Articles / Online

  • Semantic Link Network Based Knowledge Graph Representation and Construction
  • Abstract A knowledge graph consists of a set of interconnected typed entities and their attributes, which shows a better performance to organize, manage and understand knowledge. However, because knowledge graphs contain a lot of knowledge triples, it is difficult to directly display to researchers. Semantic Link Network is an attempt, and it can deal with the construction, representation and reasoning of semantics naturally. Based on the Semantic Link Network, this paper explores the representation and construction of knowledge graph, and develops an academic knowledge graph prototype system to realize the representation, construction and visualization of knowledge graph.
  • More
  •   Views:285       Downloads:269        Download PDF
  • Hybrid Efficient Convolution Operators for Visual Tracking
  • Abstract Visual tracking is a classical computer vision problem with many applications. Efficient convolution operators (ECO) is one of the most outstanding visual tracking algorithms in recent years, it has shown great performance using discriminative correlation filter (DCF) together with HOG, color maps and VGGNet features. Inspired by new deep learning models, this paper propose a hybrid efficient convolution operators integrating fully convolution network (FCN) and residual network (ResNet) for visual tracking, where FCN and ResNet are introduced in our proposed method to segment the objects from backgrounds and extract hierarchical feature maps of objects, respectively. Compared with the traditional VGGNet,…
  • More
  •   Views:296       Downloads:279        Download PDF
  • Evaluation Model of Farmer Training Effect Based on AHP–A Case Study of Hainan Province
  • Abstract On the basis of studying the influencing factors of training effect evaluation, this paper constructs an AHP-fuzzy comprehensive evaluation model for farmers’ vocational training activities in Hainan Province to evaluate farmers’ training effect, which overcomes the limitations of traditional methods. Firstly, the content and index system of farmer training effect evaluation are established by analytic hierarchy process, and the weight value of each index is determined. Then, the fuzzy comprehensive evaluation (FCE) of farmer training effect is carried out by using multi-level FCE. The joint use of AHP and FCE improves the reliability and effectiveness of the evaluation process and…
  • More
  •   Views:319       Downloads:261        Download PDF
  • A Generation Method of Letter-Level Adversarial Samples
  • Abstract In recent years, with the rapid development of natural language processing, the security issues related to it have attracted more and more attention. Character perturbation is a common security problem. It can try to completely modify the input classification judgment of the target program without people’s attention by adding, deleting, or replacing several characters, which can reduce the effectiveness of the classifier. Although the current research has provided various methods of perturbation attacks on characters, the success rate of some methods is still not ideal. This paper mainly studies the sample generation of optimal perturbation characters and proposes a characterlevel…
  • More
  •   Views:395       Downloads:319        Download PDF
  • Exploring Hybrid Genetic Algorithm Based Large-Scale Logistics Distribution for BBG Supermarket
  • Abstract In the large-scale logistics distribution of single logistic center, the method based on traditional genetic algorithm is slow in evolution and easy to fall into the local optimal solution. Addressing at this issue, we propose a novel approach of exploring hybrid genetic algorithm based large-scale logistic distribution for BBG supermarket. We integrate greedy algorithm and hillclimbing algorithm into genetic algorithm. Greedy algorithm is applied to initialize the population, and then hill-climbing algorithm is used to optimize individuals in each generation after selection, crossover and mutation. Our approach is evaluated on the dataset of BBG Supermarket which is one of the…
  • More
  •   Views:321       Downloads:262        Download PDF
  • PS-Fuzz: Efficient Graybox Firmware Fuzzing Based on Protocol State
  • Abstract The rise of the Internet of Things (IoT) exposes more and more important embedded devices to the network, which poses a serious threat to people’s lives and property. Therefore, ensuring the safety of embedded devices is a very important task. Fuzzing is currently the most effective technique for discovering vulnerabilities. In this work, we proposed PS-Fuzz (Protocol State Fuzz), a gray-box fuzzing technique based on protocol state orientation. By instrumenting the program that handles protocol fields in the firmware, the problem of lack of guidance information in common protocol fuzzing is solved. By recording and comparing state transition paths, the…
  • More
  •   Views:421       Downloads:300        Download PDF
  • An Anomaly Detection Method of Industrial Data Based on Stacking Integration
  • Abstract With the development of Internet technology, the computing power of data has increased, and the development of machine learning has become faster and faster. In the industrial production of industrial control systems, quality inspection and safety production of process products have always been our concern. Aiming at the low accuracy of anomaly detection in process data in industrial control system, this paper proposes an anomaly detection method based on stacking integration using the machine learning algorithm. Data are collected from the industrial site and processed by feature engineering. Principal component analysis (PCA) and integrated rule tree method are adopted to…
  • More
  •   Views:310       Downloads:276        Download PDF
  • An Adversarial Attack System for Face Recognition
  • Abstract Deep neural networks (DNNs) are widely adopted in daily life and the security problems of DNNs have drawn attention from both scientific researchers and industrial engineers. Many related works show that DNNs are vulnerable to adversarial examples that are generated with subtle perturbation to original images in both digital domain and physical domain. As a most common application of DNNs, face recognition systems are likely to cause serious consequences if they are attacked by the adversarial examples. In this paper, we implement an adversarial attack system for face recognition in both digital domain that generates adversarial face images to fool…
  • More
  •   Views:374       Downloads:345        Download PDF
  • Clustering Algorithms: Taxonomy, Comparison, and Empirical Analysis in 2D Datasets
  • Abstract Because of the abundance of clustering methods, comparing between methods and determining which method is proper for a given dataset is crucial. Especially, the availability of huge experimental datasets and transactional and the emerging requirements for data mining and the like needs badly for clustering algorithms that can be applied in various domains. This paper presents essential notions of clustering and offers an overview of the significant features of the most common representative clustering algorithms of clustering categories presented in a comparative way. More specifically the study is based on the numerical type of the data that the algorithm supports,…
  • More
  •   Views:584       Downloads:729        Download PDF
  • A Learning Framework for Intelligent Selection of Software Verification Algorithms
  • Abstract Software verification is a key technique to ensure the correctness of software. Although numerous verification algorithms and tools have been developed in the past decades, it is still a great challenge for engineers to accurately and quickly choose the appropriate verification techniques for the software at hand. In this work, we propose a general learning framework for the intelligent selection of software verification algorithms, and instantiate the framework with two state-of-the-art learning algorithms: Broad learning (BL) and deep learning (DL). The experimental evaluation shows that the training efficiency of the BL-based model is much higher than the DL-based models and…
  • More
  •   Views:497       Downloads:353        Download PDF
Displaying 1-10 on page 1 of 34. Per Page