scholarly journals Image-Based Feature Representation for Insider Threat Classification

2020 ◽  
Vol 10 (14) ◽  
pp. 4945
Author(s):  
R. G. Gayathri ◽  
Atul Sajjanhar ◽  
Yong Xiang
Keyword(s):  
Class Imbalance ◽  
Feature Representation ◽  
Insider Threat ◽  
Deep Convolutional Neural Networks ◽  
Usage Patterns ◽  
Under Sampling ◽  
External Sources ◽  
Internal Sources ◽  
Malicious Insiders ◽  
Access Patterns

Cybersecurity attacks can arise from internal and external sources. The attacks perpetrated by internal sources are also referred to as insider threats. These are a cause of serious concern to organizations because of the significant damage that can be inflicted by malicious insiders. In this paper, we propose an approach for insider threat classification which is motivated by the effectiveness of pre-trained deep convolutional neural networks (DCNNs) for image classification. In the proposed approach, we extract features from usage patterns of insiders and represent these features as images. Hence, images are used to represent the resource access patterns of the employees within an organization. After construction of images, we use pre-trained DCNNs for anomaly detection, with the aim to identify malicious insiders. Random under sampling is used for reducing the class imbalance issue. The proposed approach is evaluated using the MobileNetV2, VGG19, and ResNet50 pre-trained models, and a benchmark dataset. Experimental results show that the proposed method is effective and outperforms other state-of-the-art methods.

scholarly journals Learning rich features with hybrid loss for brain tumor segmentation

2021 ◽  
Vol 21 (S2) ◽  
Author(s):  
Daobin Huang ◽  
Minghui Wang ◽  
Ling Zhang ◽  
Haichun Li ◽  
Minquan Ye ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Brain Tumor ◽  
Class Imbalance ◽  
Feature Representation ◽  
Loss Functions ◽  
Radiotherapy Planning ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Scale Feature ◽  
Multi Scale

Abstract Background Accurately segment the tumor region of MRI images is important for brain tumor diagnosis and radiotherapy planning. At present, manual segmentation is wildly adopted in clinical and there is a strong need for an automatic and objective system to alleviate the workload of radiologists. Methods We propose a parallel multi-scale feature fusing architecture to generate rich feature representation for accurate brain tumor segmentation. It comprises two parts: (1) Feature Extraction Network (FEN) for brain tumor feature extraction at different levels and (2) Multi-scale Feature Fusing Network (MSFFN) for merge all different scale features in a parallel manner. In addition, we use two hybrid loss functions to optimize the proposed network for the class imbalance issue. Results We validate our method on BRATS 2015, with 0.86, 0.73 and 0.61 in Dice for the three tumor regions (complete, core and enhancing), and the model parameter size is only 6.3 MB. Without any post-processing operations, our method still outperforms published state-of-the-arts methods on the segmentation results of complete tumor regions and obtains competitive performance in another two regions. Conclusions The proposed parallel structure can effectively fuse multi-level features to generate rich feature representation for high-resolution results. Moreover, the hybrid loss functions can alleviate the class imbalance issue and guide the training process. The proposed method can be used in other medical segmentation tasks.

scholarly journals PUBLIC DEBT AS A SOURCE OF FINANCING FOR GOVERNMENT EXPENDITURES IN THE PERSPECTIVE OF ISLAMIC SCHOLARS

2019 ◽  
Vol 7 (4) ◽  
pp. 285-290
Author(s):  
Imron Mawardi ◽  
Tika Widiastuti ◽  
Debrina Farrah Anova ◽  
Muhammad Ubaidillah Al Mustofa ◽  
Dewie Saktia Ardiantono ◽  
...  
Keyword(s):  
Public Debt ◽  
Foreign Debt ◽  
General Knowledge ◽  
The Public ◽  
Islamic Perspective ◽  
External Sources ◽  
Internal Sources ◽  
The Government ◽  
State Projects ◽  
Conceptual Research

Purpose of the study: This study aims to examine foreign debt as a source of financing for economic development. This research is expected to provide (1) an overview of debt as a source of funding for state projects, (2) investigate its impacts and (3) offer additional knowledge of its Islamic perspective. Methodology: This research is a qualitative study using the study literature approach. This research is conducted by analysing books, literature, journals, and magazines with themes related to the focus of the discussion on this study. It is expected that the method used can provide insight, general knowledge, and develop the view of Islam in relation to foreign debt. Main Findings: The government has to ensure that the state has the ability to pay off its obligations in the future; guarantee that loans have to be free from interest; prioritize taking loans from internal sources rather than external sources. In Addition, debts are not intended for deferred needs and not taking loans that exceed their needs. Applications of this study: basically the results of this study can be applied to any country that considers the use of public debt, like other Islamic systems. Novelty/Originality of this study: This research is conceptual research in an Islamic perspective. This study successfully examined comprehensively related to the public debt with the Islamic approach.

Internal and external search strategies of innovative firms: the role of the target market

2018 ◽  
Vol 24 (3) ◽  
pp. 495-518 ◽  
Author(s):  
Guillermo Ruiz-Pava ◽  
Clemente Forero-Pineda
Keyword(s):  
International Markets ◽  
Search Strategies ◽  
Local Market ◽  
Target Market ◽  
Local Markets ◽  
Content Type ◽  
Innovative Firms ◽  
External Sources ◽  
Internal Sources

Purpose This paper aims to develop the concept of internal search of ideas to show the contrast between search strategies adopted by firms that introduce new products into local and international markets. Design/methodology/approach Based on data from 2,652 innovative firms, the paper uses factor analysis to explore and confirm appropriate groups of sources of innovative ideas. The analysis differentiates between internal and two types of external sources. Logistic and bivariate regressions reveal different search strategies for innovation in local and international markets. Findings Firms reporting products new to international markets exhibit search strategies combining ideas from internal sources with ideas from other firms. Firms reporting products new to local market reveal a search strategy centered on ideas from other firms. Practical implications Managers and policymakers wishing to promote innovations for international markets should concentrate their resources on developing the organizations’ capacity to generate ideas internally while monitoring other firms’ ideas. Managers targeting local markets may focus their efforts on intelligence over ideas coming from other firms. Originality/value Clarifying the relationship between knowledge and ideas, the paper finds that search strategies of firms are more effective for innovation depending on the target market. Firms searching for ideas among other firms generate ideas that might trigger innovation in products new to local markets. Firms searching both for internal and external ideas generate ideas leading to products new to international markets.

Big Data Architecture Components

2018 ◽  
pp. 10-31
Keyword(s):  
Big Data ◽  
Missing Values ◽  
Noise Removal ◽  
Data Sources ◽  
Data Types ◽  
Layer Analysis ◽  
External Sources ◽  
Internal Sources ◽  
High Level

The previous chapter overviewed big data including its types, sources, analytic techniques, and applications. This chapter briefly discusses the architecture components dealing with the huge volume of data. The complexity of big data types defines a logical architecture with layers and high-level components to obtain a big data solution that includes data sources with the relation to atomic patterns. The dimensions of the approach include volume, variety, velocity, veracity, and governance. The diverse layers of the architecture are big data sources, data massaging and store layer, analysis layer, and consumption layer. Big data sources are data collected from various sources to perform analytics by data scientists. Data can be from internal and external sources. Internal sources comprise transactional data, device sensors, business documents, internal files, etc. External sources can be from social network profiles, geographical data, data stores, etc. Data massage is the process of extracting data by preprocessing like removal of missing values, dimensionality reduction, and noise removal to attain a useful format to be stored. Analysis layer is to provide insight with preferred analytics techniques and tools. The analytics methods, issues to be considered, requirements, and tools are widely mentioned. Consumption layer being the result of business insight can be outsourced to sources like retail marketing, public sector, financial body, and media. Finally, a case study of architectural drivers is applied on a retail industry application and its challenges and usecases are discussed.

Identifying Users Stereotypes for Dynamic Web Pages Customization

2010 ◽  
pp. 284-306
Author(s):  
Sandro José Rigo
Keyword(s):  
Web Applications ◽  
User Profile ◽  
Semantic Knowledge ◽  
Web Pages ◽  
Adaptive Hypermedia ◽  
Important Concern ◽  
Adaptive Hypermedia Systems ◽  
Dynamic Web ◽  
Usage Patterns ◽  
Access Patterns

Adaptive Hypermedia is an effective approach to automatic personalization that overcomes the difficulties and deficiencies of traditional Web systems in delivering the appropriate content to users. One important issue regarding Adaptive Hypermedia systems is the construction and maintenance of the user profile. Another important concern is the use of Semantic Web resources to describe Web applications and to implement adaptation mechanisms. Web Usage Mining, in this context, allows the generation of Websites access patterns. This chapter describes the possibilities of integration of these usage patterns with semantic knowledge obtained from domain ontologies. Thus, it is possible to identify users’ stereotypes for dynamic Web pages customization. This integration of semantic knowledge can provide personalization systems with better adaptation strategies.

Identifying Users Stereotypes for Dynamic Web Pages Customization

2011 ◽  
pp. 1388-1410
Author(s):  
Sandro José Rigo ◽  
José M. Palazzo de Oliveira ◽  
Leandro Krug Wives
Keyword(s):  
Web Applications ◽  
User Profile ◽  
Semantic Knowledge ◽  
Web Pages ◽  
Adaptive Hypermedia ◽  
Important Concern ◽  
Adaptive Hypermedia Systems ◽  
Dynamic Web ◽  
Usage Patterns ◽  
Access Patterns

Adaptive Hypermedia is an effective approach to automatic personalization that overcomes the difficulties and deficiencies of traditional Web systems in delivering the appropriate content to users. One important issue regarding Adaptive Hypermedia systems is the construction and maintenance of the user profile. Another important concern is the use of Semantic Web resources to describe Web applications and to implement adaptation mechanisms. Web Usage Mining, in this context, allows the generation of Websites access patterns. This chapter describes the possibilities of integration of these usage patterns with semantic knowledge obtained from domain ontologies. Thus, it is possible to identify users’ stereotypes for dynamic Web pages customization. This integration of semantic knowledge can provide personalization systems with better adaptation strategies.

scholarly journals Semantic Image Segmentation with Deep Convolutional Neural Networks and Quick Shift

Symmetry ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 427 ◽  
Author(s):  
Sanxing Zhang ◽  
Zhenhuan Ma ◽  
Gang Zhang ◽  
Tao Lei ◽  
Rui Zhang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Image Segmentation ◽  
Convolutional Neural Networks ◽  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Input Image ◽  
Feature Representation ◽  
Segmentation Algorithm ◽  
Deep Convolutional Neural Networks ◽  
Semantic Image Segmentation

Semantic image segmentation, as one of the most popular tasks in computer vision, has been widely used in autonomous driving, robotics and other fields. Currently, deep convolutional neural networks (DCNNs) are driving major advances in semantic segmentation due to their powerful feature representation. However, DCNNs extract high-level feature representations by strided convolution, which makes it impossible to segment foreground objects precisely, especially when locating object boundaries. This paper presents a novel semantic segmentation algorithm with DeepLab v3+ and super-pixel segmentation algorithm-quick shift. DeepLab v3+ is employed to generate a class-indexed score map for the input image. Quick shift is applied to segment the input image into superpixels. Outputs of them are then fed into a class voting module to refine the semantic segmentation results. Extensive experiments on proposed semantic image segmentation are performed over PASCAL VOC 2012 dataset, and results that the proposed method can provide a more efficient solution.

An Investigation of Imbalanced Ensemble Learning Methods for Cross-Project Defect Prediction

2019 ◽  
Vol 33 (12) ◽  
pp. 1959037 ◽  
Author(s):  
Shaojian Qiu ◽  
Lu Lu ◽  
Siyu Jiang ◽  
Yang Guo
Keyword(s):  
Ensemble Learning ◽  
Class Imbalance ◽  
Training Data ◽  
Defect Prediction ◽  
Class Imbalance Problem ◽  
Learning Methods ◽  
Imbalance Problem ◽  
Intelligent Software ◽  
Under Sampling ◽  
Cross Project

Machine-learning-based software defect prediction (SDP) methods are receiving great attention from the researchers of intelligent software engineering. Most existing SDP methods are performed under a within-project setting. However, there usually is little to no within-project training data to learn an available supervised prediction model for a new SDP task. Therefore, cross-project defect prediction (CPDP), which uses labeled data of source projects to learn a defect predictor for a target project, was proposed as a practical SDP solution. In real CPDP tasks, the class imbalance problem is ubiquitous and has a great impact on performance of the CPDP models. Unlike previous studies that focus on subsampling and individual methods, this study investigated 15 imbalanced learning methods for CPDP tasks, especially for assessing the effectiveness of imbalanced ensemble learning (IEL) methods. We evaluated the 15 methods by extensive experiments on 31 open-source projects derived from five datasets. Through analyzing a total of 37504 results, we found that in most cases, the IEL method that combined under-sampling and bagging approaches will be more effective than the other investigated methods.

Sign in / Sign up

Export Citation Format

Share Document