Web Intelligence - Volume 19, issue 1-2

Authors: Viswanathan, Ganesh | J, Prabhu

Article Type: Research Article

Abstract: Threat modeling is an essential activity in the security development lifecycle. To provide security at the design phase of software development, Microsoft introduced threat modeling stride to identify the vulnerabilities and attacks of application. An efficient solution is necessary to deal with these issues in the software development life cycle. In this context, the paper focused on the analysis of threats and attack tree techniques that are traditionally available and frequently used. Automated Threat modeling enables to simulate attacks and visualized the existing vulnerabilities and misconfiguration. A hybrid model is proposed based on system-centric and attacker-centric to identify the threats …in the software application during the software design phase. This model is built by STRIDE by defining security architecture and then analyzed the risks regarding its security characteristics and applied to its real application system. Our model is applied in a case study of the health center management system and shows a better result is identifying the threats and severity in the design phase. And also attack tree defines the stages of threats to understand the severity. Show more

Keywords: Threat modeling, attack tree, software development, vulnerabilities, threats analysis tool, STRIDE

DOI: 10.3233/WEB-210452

Citation: Web Intelligence, vol. 19, no. 1-2, pp. 1-11, 2021

Authors: Yu, Guangxu

Article Type: Research Article

Abstract: In order to overcome the problems of low detection probability, low coverage uniformity and low coverage of current path coverage enhancement methods in wireless sensor networks, a new path coverage enhancement method based on CVT model is proposed in this paper. Firstly, the node perception model and network coverage model are constructed. On the basis of the node awareness model and network coverage model, CVT model is used to adjust the connection mode, density and location of nodes in wireless sensor networks, so as to improve the coverage performance of nodes in the detection area in wireless sensor networks, and …realize the effective enhancement of path coverage in wireless sensor networks. Experimental results show that, compared with the traditional methods, the proposed method has high detection probability, high coverage uniformity and coverage rate, and the highest coverage rate reaches 97%, which has higher practical application performance. Show more

Keywords: CVT model, wireless sensor network, node awareness, coverage performance

DOI: 10.3233/WEB-210455

Citation: Web Intelligence, vol. 19, no. 1-2, pp. 13-25, 2021

Authors: Shu, Wei | He, Dajiang | Shu, Jun

Article Type: Research Article

Abstract: In order to overcome the problems of low channel utilization, low transmission success rate and high data transmission delay in current gateway node reconfiguration methods of IOT, this paper proposes a novel gateway node reconfiguration method of IOT based on hierarchical coding particle swarm optimization. Based on the IOT network model, this paper analyzes the delay characteristics of the IOT, and constructs the object function of the gateway node reconfiguration of IOT. By monotone decreasing inertia weight strategy, the coding particle swarm optimization is optimized, and the reconfiguration objective function of the gateway node of IOT by using the optimized …particle swarm optimization algorithm is solved. Experimental results show that the channel utilization ratio of the proposed method is higher than 90%, the success rate of information transmission is more than 80%, and the data transmission delay is less than 0.5 s, which indicates that the proposed method has high channel utilization, high transmission success rate and low data transmission delay. Show more

Keywords: Hierarchical coding particle swarm optimization, IOT, gateway node, objective function, node reconfiguration

DOI: 10.3233/WEB-210456

Citation: Web Intelligence, vol. 19, no. 1-2, pp. 27-40, 2021

Authors: Nadendla, Hanumantha Rao | Srikrishna, A. | Rao, K. Gangadhara

Article Type: Research Article

Abstract: Image classification is the classical issue in computer vision, machine learning, and image processing. The image classification is measured by differentiating the image into the prescribed category based on the content of the vision. In this paper, a novel classifier named RideSFO-NN is developed for image classification. The proposed method performs the image classification by undergoing two steps, namely feature extraction and classification. Initially, the images from various sources are provided to the proposed Weighted Shape-Size Pattern Spectra for pattern analysis. From the pattern analysis, the significant features are obtained for the classification. Here, the proposed Weighted Shape-Size Pattern Spectra …is designed by modifying the gray-scale decomposition with Weight-Shape decomposition. Then, the classification is done based on Neural Network (NN) classifier, which is trained using an optimization approach. The optimization will be done by the proposed Ride Sunflower optimization (RideSFO) algorithm, which is the integration of Rider optimization algorithm (ROA), and Sunflower optimization algorithm (SFO). Finally, the image classification performance is evaluated using RideSFO-NN based on sensitivity, specificity, and accuracy. The developed RideSFO-NN method achieves the maximal accuracy of 94%, maximal sensitivity of 93.87%, and maximal specificity of 90.52% based on K-Fold. Show more

Keywords: Image classification, Weighted Shape-Size Pattern Spectra, Rider optimization algorithm, Sunflower optimization algorithm, neural network

DOI: 10.3233/WEB-210454

Citation: Web Intelligence, vol. 19, no. 1-2, pp. 41-61, 2021

Authors: Sotirakou, Catherine | Trilling, Damian | Germanakos, Panagiotis | Sinis, Dimitrios Alexandros | Mourlas, Constantinos

Article Type: Research Article

Abstract: This article aims to explain the perceived quality of online news articles. Discovering which elements of a news story influence readers’ perceptions could drive online popularity, which is the paramount factor of digital news readership. This work explores an approach to use tree-based machine learning algorithms to address this problem based on selected characteristics, which measure engagement, drawn from prior research mostly developed by communication scientists. A proposed extended model is used to examine the association between the engagement features and perceived quality concerning all the articles depending mainly on their genre. To demonstrate the capacity of using predictive analytics …to facilitate journalistic news writing the proposed methodology is applied on a novel data set with 200K articles in total constructed from a blog site. The results of phase A, indicate interesting correlations between the features and the perceived quality of the articles. In stage B, the paper seeks to extract a set of rules that can be used as guidelines for authors in the writing of their next articles, indicating the probability of popularity that their articles may gain if these rules are taken into consideration. Show more

Keywords: Natural language processing, news, computational journalism, computer-assisted content analysis, machine learning

DOI: 10.3233/WEB-210457

Citation: Web Intelligence, vol. 19, no. 1-2, pp. 63-86, 2021

Authors: Nakagawa, Hiromi | Iwasawa, Yusuke | Matsuo, Yutaka

Article Type: Research Article

Abstract: Recent advancements in computer-assisted learning systems have caused an increase in the research in knowledge tracing , wherein student performance is predicted over time. Student coursework can potentially be structured as a graph. Incorporating this graph-structured nature into a knowledge tracing model as a relational inductive bias can improve its performance; however, previous methods, such as deep knowledge tracing, did not consider such a latent graph structure. Inspired by the recent successes of graph neural networks (GNNs), we herein propose a GNN-based knowledge tracing method, i.e., graph-based knowledge tracing. Casting the knowledge structure as a graph enabled us to reformulate …the knowledge tracing task as a time-series node-level classification problem in the GNN. As the knowledge graph structure is not explicitly provided in most cases, we propose various implementations of the graph structure. Empirical validations on two open datasets indicated that our method could potentially improve the prediction of student performance and demonstrated more interpretable predictions compared to those of the previous methods, without the requirement of any additional information. Show more

Keywords: Knowledge tracing, graph neural network, educational data mining, learning sciences

DOI: 10.3233/WEB-210458

Citation: Web Intelligence, vol. 19, no. 1-2, pp. 87-102, 2021

Authors: Mao, Xuetao | Duan, Wei | Li, Lin | Zhang, Jianwei

Article Type: Research Article

Abstract: The legal judgments are always based on the description of the case, the legal document. However, retrieving and understanding large numbers of relevant legal documents is a time-consuming task for legal workers. The legal judgment prediction (LJP) focus on applying artificial intelligence technology to provide decision support for legal workers. The prison term prediction(PTP) is an important task in LJP which aims to predict the term of penalty utilizing machine learning methods, thus supporting the judgement. Long-Short Term Memory(LSTM) Networks are a special type of Recurrent Neural Networks(RNN) that are capable of handling long term dependencies without being affected by …an unstable gradient. Mainstream RNN models such as LSTM and GRU can capture long-distance correlation but training is time-consuming, while traditional CNN can be trained in parallel but pay more attention to local information. Both have shortcomings in case description prediction. This paper proposes a prison term prediction model for legal documents. The model adds causal expansion convolution in general TextCNN to make the model not only limited to the most important keyword segment, but also focus on the text near the key segments and the corresponding logical relationship of this paragraph, thereby improving the predicting effect and the accuracy on the data set. The causal TextCNN in this paper can understand the causal logical relationship in the text, especially the relationship between the legal text and the prison term. Since the model uses all CNN convolutions, compared with traditional sequence models such as GRU and LSTM, it can be trained in parallel to improve the training speed and can handling long term. So causal convolution can make up for the shortcomings of TextCNN and RNN models. In summary, the PTP model based on causality is a good solution to this problem. In addition, the case description is usually longer than traditional natural language sentences and the key information related to the prison term is not limited to local words. Therefore, it is crucial to capture substantially longer memory for LJP domains where a long history is required. In this paper, we propose a Causality CNN-based Prison Term Prediction model based on fact descriptions, in which the Causal TextCNN method is applied to build long effective history sizes (i.e., the ability for the networks to look very far into the past to make a prediction) using a combination of very deep networks (augmented with residual layers) and dilated convolutions. The experimental results on a public data show that the proposed model outperforms several CNN and RNN based baselines. Show more

Keywords: Prison term prediction, TextCNN, LJP, long historical information

DOI: 10.3233/WEB-210459

Citation: Web Intelligence, vol. 19, no. 1-2, pp. 103-113, 2021

Authors: Huang, Haiyang | Shang, Zhanlei

Article Type: Research Article

Abstract: In the traditional network heterogeneous fault-tolerant data mining process, there are some problems such as low accuracy and slow speed. This paper proposes a fast mining method based on K-means clustering for network heterogeneous fault-tolerant data. The confidence space of heterogeneous fault-tolerant data is determined, and the range of motion of fault-tolerant data is obtained; Singular value decomposition (SVD) method is used to construct the classified data model to obtain the characteristics of heterogeneous fault-tolerant data; The redundant data in fault-tolerant data is deleted by unsupervised feature selection algorithm, and the square sum and Euclidean distance of fault-tolerant data clustering …center are determined by K-means algorithm. The discrete data clustering space is constructed, and the objective optimal function of network heterogeneous fault-tolerant data clustering is obtained, Realize fault-tolerant data fast mining. The results show that the mining accuracy of the proposed method can reach 97%. Show more

Keywords: K-means clustering, network heterogeneous fault-tolerant data, fast mining, redundancy, unsupervised feature selection algorithm

DOI: 10.3233/WEB-210460

Citation: Web Intelligence, vol. 19, no. 1-2, pp. 115-124, 2021

Authors: Chen, Chen | Yang, Li | Jia, Xunan

Article Type: Research Article

Abstract: In order to overcome the problems of poor timeliness and low accuracy of mining existing in traditional methods, this paper designs a bit-object based maximum frequent pattern mining method for intensive cloud computing data. After judging the support number according to the bit object of the maximum frequent pattern, the intensive cloud computing data is accurately collected according to the difference between the load value of cloud data and the true value of load, so as to improve the accuracy of subsequent mining results, and then the maximum frequent pattern of data is accurately mined by combining the bit object. …Experimental results show that the maximum time to generate mining results is only 4.6 s, the maximum bit error rate of output results is only 7%, and the maximum memory occupancy is only 3.90%. The above results show that this method is more suitable for practical excavation. Show more

Keywords: Intensive cloud computing data, maximum frequency mode, bit object, data acquisition, frequent tree, frequent pattern mining

DOI: 10.3233/WEB-210461

Citation: Web Intelligence, vol. 19, no. 1-2, pp. 125-133, 2021

Authors: Sun, Ruohan | Hu, Meihui | Cao, Jinping | Xiao, Wanxing | Guo, Xinying

Article Type: Research Article

Abstract: In this paper, a window function based feature mining method for the operation and maintenance of big data in information system is proposed. The time clustering feature vector is combined with window function to reduce the dimension of operation and maintenance data of high-dimensional information system. The operation and maintenance data feature subset is segmented according to the similar feature level, and the redundant features of operation and maintenance data are removed to complete the information system operation and maintenance big data feature mining. The simulation results show that the proposed method has better clustering effect, fewer iterations and shorter …mining time. Show more

Keywords: Window function, information system, operation and maintenance big data, feature mining

DOI: 10.3233/WEB-210462

Citation: Web Intelligence, vol. 19, no. 1-2, pp. 135-145, 2021