Computer and Information Science

Journal Information
ISSN / EISSN : 19138989 / 19138997
Current Publisher: Canadian Center of Science and Education (10.5539)
Total articles ≅ 846
Current Coverage
Archived in

Latest articles in this journal

Chris Lee
Computer and Information Science, Volume 13; doi:10.5539/cis.v13n3p103

The publisher has not yet granted permission to display this abstract.
Shijun Wang, Baocheng Zhu, Chen Li, Mingzhe Wu, James Zhang, Wei Chu, Yuan Qi
Computer and Information Science, Volume 13; doi:10.5539/cis.v13n3p93

The publisher has not yet granted permission to display this abstract.
Andrey Molyakov
Computer and Information Science, Volume 13; doi:10.5539/cis.v13n3p89

The publisher has not yet granted permission to display this abstract.
Esra Eroğlu, Esma Ergüner Özkoç
Computer and Information Science, Volume 13; doi:10.5539/cis.v13n3p82

The publisher has not yet granted permission to display this abstract.
Venkata A. Paruchuri, Bobby C. Granville
Computer and Information Science, Volume 13; doi:10.5539/cis.v13n3p73

The publisher has not yet granted permission to display this abstract.
Rashid Mehdiyev, Jean Nava, Karan Sodhi, Saurav Acharya, Annie Ibrahim Rana
Computer and Information Science, Volume 13; doi:10.5539/cis.v13n3p57

We address the problem of topic mining and labelling in the domain of retail customer communications to summarize the subject of customers inquiries. The performance of two popular topic mining algorithms - Non-Negative Matrix Factorization (NMF) and Latent Dirichlet Allocation (LDA) – were compared, and a novel method to assign topic subject labels to the customer inquiries in an automated way was proposed. Experiments using a retailer’s call center data verify the efficacy and efficiency of the proposed topic labelling algorithm. Furthermore, the evaluation of results from both the algorithms seems to indicate the preference of using Non-Negative Matrix Factorization applied to short text data.
Talal H. Noor, El-Sayed Atlam, Ghada Elmarhomy, Ahmed Abd Elwahab, Rawda Draz, Mahmoud Elmarhoumy
Computer and Information Science, Volume 13; doi:10.5539/cis.v13n3p66

Field association (FA) terms are used to identify the subject of text (document field) by extracting specific words in that text. In this paper we use FA terms to study the effect of time change on specific terms by calculating the frequency of this terms, which associated with the archive field in a specific period. This paper also introduces a new approach for automatic evaluation of the stabilization classes using non-linear approach. The stabilization classes refer to the changing of FA terms with time in a specific period. The new approach improves the performance of decision tree than linear approach by using non-linear approach. The corpus that used in this approach has number of 1,356 files, and it is about 7.49 MB, after comparing the presented approach with the traditional one, we conclusion that the new approach enhanced the F-measure for increment, steady, decrement classes by 7.7%, 3.1%, 2.2%, sequentially.  
Guoguan Wen, Mingliang Zhang, Qingping Dou
Computer and Information Science, Volume 13; doi:10.5539/cis.v13n3p49

Students run code directly without any modification when doing programming experiments. They do not care about the process and do not understand the results. It has always been the pain of the electronic information experiment teaching mentioned by. This article, combines the previous teaching experience, proposes an artificial serial port interruption in the code. The result data returned by the interrupt upload to computer or mobile phone, combined with the experimental principle to allow students to explore the relationship between input and output, so that students can fully participate in the modification of code parameters, and verify the intermediate results. Students connect to the WIFI hotspot configured in the experiment box through their mobile phones, and lunch the online commissioning APP serial port configuration interface to complete the basic serial port settings. The slave MCU needs to download the firmware code compiled in C language in advance. The code contains the serial port output function to calibrate the running position of the code and upload the specified operation results. This article briefly describes the hardware functional chart and the functional flowchart of the interrupt code; focusing on the interface design and interrupt implementation method of online commissioning APP, as well as the test environment setup and specific test results with serial port tools.
Zohair Malki, Elsayed Atlam, Guesh Dagnew, Ahmad Reda Alzighaibi, Elmarhomy Ghada, Ibrahim Gad
Computer and Information Science, Volume 13; doi:10.5539/cis.v13n3p40

The Residual Long Short Term Memory (LSTM) deep learning approach is attracting attension of many researchers due to its efficiency when trained on high dimensional datasets. Nowadays, Human Activity Recognition (HAR) has come with enormous challenges that have to be addressed. In addressing such a problem, one can think of developing an application that can help the elderly people as an assistant when it works in collaboration with other timely technologies such as wearable devices with the help of IoT. Many research works are using a standard dataset in evaluating their proposed method in this regard. The dataset comes with its own challenge such as imbalanced classes. In this work, we propose to apply different machine learning techniques to address the specified problems and the method is validated on a standard dataset. To validate the proposed method, we evaluated using different standard metrics such as classification accuracy, precision, recall, f1-score, and Receiver Operating Characteristic (ROC) curve. The proposed method achieves an Area Under Curve (AUC) of 100%, 97.66% of accuracy, 91.59% precision,  93.75% of recall and 92.66% of F1-score respectively.
M.Redwan Aljannan, Manal A. Ismail, Akram Salah
Computer and Information Science, Volume 13; doi:10.5539/cis.v13n3p16

End-user feedback has an essential role in the requirement’s identification, prioritization, and management of the software evolution process. Several approaches are proposed for utilizing user-pushed feedback collected from social media, forums, and review systems. The collected feedback via the online channels contains a variety of information. Thus, the researchers proposed analytical approaches to classify feedback according to the data it holds. Still, recent results indicate that no single classifier works best for all feedback types and information sources. Also, online feedback does not have a direct mapping to the requirements, and it does not contain user context data. This causes wasting in developers’ effort in understanding and analyzing feedback. On the other hand, online feedback cannot be used to explore user satisfaction and acceptance of the implemented and planned requirements. Likewise, the developer cannot collect feedback from a specific segment of the users. To overcome the deficiency of online feedback, this paper proposes a novel approach that utilizes pulling feedback from users while using the software. The proposed approach consists of a model and process for structuring feedback requests, linking feedback to the requirements, embedding feedback with the user context information, specifying the target audience for the feedback request, analyzing collected feedback depending on predefined interpretation rules, which provide insights that support developers in release planning. The feedback request model and process are implemented by a tool called FeatureEcho which was evaluated in a software company by conducting a case study for upgrading a governmental internet portal. The results indicate that FeatureEcho is a valuable step towards increasing the understanding of the end-users needs which supports the decision-making procedure of software evolution.
Back to Top Top