Previous Issue

Table of Contents

Computers, Volume 8, Issue 3 (September 2019)

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Readerexternal link to open them.
View options order results:
result details:
Displaying articles 1-5
Export citation of selected articles as:
Open AccessArticle
Semantic Features for Optimizing Supervised Approach of Sentiment Analysis on Product Reviews
Received: 26 June 2019 / Revised: 15 July 2019 / Accepted: 16 July 2019 / Published: 19 July 2019
Viewed by 192 | PDF Full-text (1051 KB)
Abstract
The growth of ecommerce has triggered online reviews as a rich source of product information. Revealing consumer sentiment from the reviews through Sentiment Analysis (SA) is an important task of online product review analysis. Two popular approaches of SA are the supervised approach [...] Read more.
The growth of ecommerce has triggered online reviews as a rich source of product information. Revealing consumer sentiment from the reviews through Sentiment Analysis (SA) is an important task of online product review analysis. Two popular approaches of SA are the supervised approach and the lexicon-based approach. In supervised approach, the employed machine learning (ML) algorithm is not the only one to influence the results of SA. The utilized text features also handle an important role in determining the performance of SA tasks. In this regard, we proposed a method to extract text features that takes into account semantic of words. We argue that this semantic feature is capable of augmenting the results of supervised SA tasks compared to commonly utilized features, i.e., bag-of-words (BoW). To extract the features, we assigned the correct sense of the word in reviewing the sentence by adopting a Word Sense Disambiguation (WSD) technique. Several WordNet similarity algorithms were involved, and correct sentiment values were assigned to words. Accordingly, we generated text features for product review documents. To evaluate the performance of our text features in the supervised approach, we conducted experiments using several ML algorithms and feature selection methods. The results of the experiments using 10-fold cross-validation indicated that our proposed semantic features favorably increased the performance of SA by 10.9%, 9.2%, and 10.6% of precision, recall, and F-Measure, respectively, compared with baseline methods. Full article
Open AccessArticle
A Complexity Metrics Suite for Cascading Style Sheets
Received: 6 June 2019 / Revised: 1 July 2019 / Accepted: 8 July 2019 / Published: 10 July 2019
Viewed by 302 | PDF Full-text (2560 KB) | HTML Full-text | XML Full-text
Abstract
We perform a theoretical and empirical analysis of a set of Cascading Style Sheets (CSS) document complexity metrics. The metrics are validated using a practical framework that demonstrates their viability. The theoretical analysis is performed using the Weyuker’s properties−a widely adopted approach to [...] Read more.
We perform a theoretical and empirical analysis of a set of Cascading Style Sheets (CSS) document complexity metrics. The metrics are validated using a practical framework that demonstrates their viability. The theoretical analysis is performed using the Weyuker’s properties−a widely adopted approach to conducting empirical validations of metrics proposals. The empirical analysis is conducted using visual and statistical analysis of distribution of metric values, Cliff’s delta, Chi-square and Liliefors statistical normality tests, and correlation analysis on our own dataset of CSS documents. The results show that five out of the nine metrics (56%) satisfy Weyuker’s properties except for the Number of Attributes Defined per Rule Block (NADRB) metric, which satisfies six out of nine (67%) properties. In addition, the results from the statistical analysis show good statistical distribution characteristics (only the Number of Extended Rule Blocks (NERB) metric exceeds the rule-of-thumb threshold value of the Cliff’s delta). The correlation between the metric values and the size of the CSS documents is insignificant, suggesting that the presented metrics are indeed complexity rather than size metrics. The practical application of the presented CSS complexity metric suite is to assess the risk of CSS documents. The proposed CSS complexity metrics suite allows identification of CSS files that require immediate attention of software maintenance personnel. Full article
(This article belongs to the Special Issue Code Generation, Analysis and Quality Testing)
Figures

Figure 1

Open AccessArticle
IVAN: An Interactive Herlofson’s Nomogram Visualizer for Local Weather Forecast
Received: 15 April 2019 / Revised: 7 June 2019 / Accepted: 13 June 2019 / Published: 1 July 2019
Viewed by 410 | PDF Full-text (13671 KB) | HTML Full-text | XML Full-text
Abstract
In 1947, N. Herlofson proposed a modification to the 1884 Heinrich Hertz’s Emagram with the goal of getting more precise hand-made weather forecasts providing larger angles between isotherms and adiabats. Since then, the Herlofson’s nomogram has been used every day to visualize the [...] Read more.
In 1947, N. Herlofson proposed a modification to the 1884 Heinrich Hertz’s Emagram with the goal of getting more precise hand-made weather forecasts providing larger angles between isotherms and adiabats. Since then, the Herlofson’s nomogram has been used every day to visualize the results of about 800 radiosonde balloons that, twice a day, are globally released, sounding the atmosphere and reading pressure, altitude, temperature, dew point, and wind velocity. Relevant weather forecasts use such pieces of information to predict fog, cloud height, rain, thunderstorms, etc. However, despite its diffusion, non-technical people (e.g., private gliding pilots) do not use the Herlofson’s nomogram because they often consider it hard to interpret and confusing. This paper copes with this problem presenting a visualization based environment that presents the Herlofson’s nomogram in an easier to interpret way, allowing the selection of the right level of detail and at the same time inspection of the sounding row data and the plotted diagram. Our visual environment was compared with the classic way of representing the Herlofson’s nomogram in a formal user study, demonstrating the higher efficacy and better comprehensibility of the proposed solution. Full article
(This article belongs to the Special Issue REMS 2018: Multidisciplinary Symposium on Computer Science and ICT)
Figures

Figure 1

Open AccessArticle
MRI Breast Tumor Segmentation Using Different Encoder and Decoder CNN Architectures
Received: 18 June 2019 / Revised: 27 June 2019 / Accepted: 28 June 2019 / Published: 29 June 2019
Viewed by 467 | PDF Full-text (2974 KB) | HTML Full-text | XML Full-text
Abstract
Breast tumor segmentation in medical images is a decisive step for diagnosis and treatment follow-up. Automating this challenging task helps radiologists to reduce the high manual workload of breast cancer analysis. In this paper, we propose two deep learning approaches to automate the [...] Read more.
Breast tumor segmentation in medical images is a decisive step for diagnosis and treatment follow-up. Automating this challenging task helps radiologists to reduce the high manual workload of breast cancer analysis. In this paper, we propose two deep learning approaches to automate the breast tumor segmentation in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) by building two fully convolutional neural networks (CNN) based on SegNet and U-Net. The obtained models can handle both detection and segmentation on each single DCE-MRI slice. In this study, we used a dataset of 86 DCE-MRIs, acquired before and after two cycles of chemotherapy, of 43 patients with local advanced breast cancer, a total of 5452 slices were used to train and validate the proposed models. The data were annotated manually by an experienced radiologist. To reduce the training time, a high-performance architecture composed of graphic processing units was used. The model was trained and validated, respectively, on 85% and 15% of the data. A mean intersection over union (IoU) of 68.88 was achieved using SegNet and 76.14% using U-Net architecture. Full article
Figures

Figure 1

Open AccessArticle
A Hybrid Scheme for an Interoperable Identity Federation System Based on Attribute Aggregation Method
Received: 3 June 2019 / Revised: 21 June 2019 / Accepted: 24 June 2019 / Published: 26 June 2019
Viewed by 401 | PDF Full-text (3270 KB) | HTML Full-text | XML Full-text
Abstract
Several countries have invested in building their identity management systems to equip citizens with infrastructures and tools to benefit from e-services. However, current systems still lack the interoperability requirement, which is the core issue that could lower the wide benefits of having an [...] Read more.
Several countries have invested in building their identity management systems to equip citizens with infrastructures and tools to benefit from e-services. However, current systems still lack the interoperability requirement, which is the core issue that could lower the wide benefits of having an identity management system. In fact, in the existing systems, the user is allowed to choose only one partial identity from an identity provider (IdP) during a single session with a service provider (SP). However, in some scenarios, an SP needs to retrieve information about user’s identities managed by multiple IdPs. The potential method to tackle these shortcomings is attribute aggregation from multiple identity providers. A number of initiatives and projects on attribute aggregation have been explored. Nevertheless, these constructions do not fulfill some identity management requirements. This paper describes a new flexible model that aims to provide the necessary mechanisms to ensure attribute aggregation in order to meet the interoperability challenges of current identity management systems. The proposed scheme is a scalable solution, based on identity federation technologies, that introduces a new IdP called an account linking provider (ALP). The purpose of this ALP is to link together different accounts, holding end users’ attributes, whenever more than one source of data is needed to grant access to the requested web resource in a single session. Furthermore, the proposed identity federation system is based on a streamlined, cost-effective, and interoperable architecture, which makes this model suitable for large-scale identity federation environments. Full article
(This article belongs to the Special Issue Computer Technologies for Human-Centered Cyber World)
Figures

Figure 1

Computers EISSN 2073-431X Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top