Qasem Obeidat

Software Defects Prediction using Machine Learning Algorithms

2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), Oct 26, 2020

Software development and the maintenance life cycle are lengthy processes. However, the possibili... more Software development and the maintenance life cycle are lengthy processes. However, the possibility of having defects in the software can be high. Software reliability and performance are essential measures of software success, which affects user satisfaction and software cost. Predicting software defects using machine learning (ML) algorithms is one approach in this direction. Implementing this approach in the earlier stages of the software development improves software performance quality and reduces software maintenance cost. Different models and techniques have been implemented in many studies to predict software defects. This investigation implements ML algorithms, such as artificial neural networks (ANNs), random forest (RF), random tree (RT), decision table (DT), linear regression (LR), gaussian processes (GP), SMOreg, and M5P. A new software defect prediction model for software future defect prediction is proposed. The defect prediction is based on historical data. The results showed that a combination of ML algorithms could be used effectively to predict software defects. The SMOreg classifier scored the best performance results, where the ANN classifier scores the worst results.

Empirical Analysis of Object-Oriented Software Test Suite Evolution

International Journal of Advanced Computer Science and Applications, 2019

The software system is evolving over the time, thus, the test suite must be repaired according to... more The software system is evolving over the time, thus, the test suite must be repaired according to the changing code. Updating test cases manually is a time-consuming activity, especially for large test suites, which motivate the recent development of automatically repairing test techniques. To develop an effective automatic repair technique that reduces the effort of development and the cost of evolution, the developer should understand how the test suite evolves in practice. This investigation aims to conduct a comprehensive empirical study on eight Java systems with many versions of these systems and their test suites to find out how the test suite is evolving, and to find the relationship between the change in the program and the corresponding evolution in the test suite. This study showed that the test suite size is mostly increased, where the test suite complexity is stabilized. The increase (or decrease) in the code size will mostly increase (or decrease) the test suite size. However, the increasing or decreasing in the code complexity is offset by stabilizing the test suite complexity. Moreover, the percentage of the code coverage tends to be increased more than decreased, but in the mutation coverage, the opposite is true.

Download

Mining Historical Software Testing Outcomes to Predict Future Results

COMPUSOFT: An International Journal of Advanced Computer Technology, Dec 31, 2019

Software bugs and program defects have significant negative effect on the cost and duration of so... more Software bugs and program defects have significant negative effect on the cost and duration of software development process. Finding such bugs in early stages of the development process will cuts development time and maintenance costs. This investigation presents three different machine learning algorithms: K-Nearest Neighbors (KNN), Random Forest (RF), and Multilayer Perceptron (MLP) to build a new proposed software defect prediction model using different types of software performance metrics. This proposed model was tested on three public datasets obtained from NASA to assess its accuracy and revealed that the KNN was outperforms RF and MLP.

Towards User Experience Based Persuasive Systems

Communications in computer and information science, 2011

Spelling With a Small Mobile Brain-Computer Interface in a Moving Wheelchair

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Nov 1, 2017

Research into Brain-Computer Interfaces (BCIs), which spell words using brain signals, has reveal... more Research into Brain-Computer Interfaces (BCIs), which spell words using brain signals, has revealed that a desktop version of such a speller, the edges paradigm, offers several advantages: This edges paradigm outperforms the benchmark row-column paradigm in terms of accuracy, bitrate, and user experience. It has remained unknown whether these advantages prevailed with a new version of the edges paradigm designed for a mobile device. This paper investigated and evaluated in a rolling wheelchair a mobile BCI, which implemented the edges paradigm on small displays with which visual crowding tends to occur. How the mobile edge paradigm outperforms the mobile row-column paradigm has implications for understanding how principles of visual neurocognition affect BCI speller use in a mobile context. This investigation revealed that all the overall advantages of the edges paradigm over the row-column paradigm prevailed in this setting. However, the reduction in adjacent errors for the edges paradigm was unprecedentedly limited to horizontal adjacent errors. The interpretation offered is that dimensional constraints of visual interface design on a smartphone thus affected the neurocognitive processes of crowding.

Download

Introducing the Edges Paradigm: A P300 Brain–Computer Interface for Spelling Written Words

IEEE Transactions on Human-Machine Systems, Dec 1, 2015

P300-based brain computer interface spellers employ the P300 component, which is derived from sca... more P300-based brain computer interface spellers employ the P300 component, which is derived from scalp measured electroencephalogram (EEG) during the brain's electrical response to a flash denoting an attended target character. The most popular P300 speller, the row column paradigm (RCP), displays characters in a matrix within which rows and columns of characters are flashed eliciting P300 responses when the illuminated row or column contains the attended target character. Despite being a longstanding successful approach, this RCP faces several challenges, including the adjacency and crowding problems. A new P300 speller is introducedthe edges paradigm (EP). Distinct from existing P300 spellers, the EP presents a square adjacent to each column or row in the outer boundary of the matrix. By replacing each flash of a row or column with that square, this EP exhibited attenuated influences of crowding and adjacencyproblems known to perturb the RCP. In the copy-spelling mode, 14 neurologically normal participants demonstrated an improved accuracy of 93.3 ± 2.0% for the EP relative to 81.7 ± 2.8% for the RCP, alongside a faster communication rate. Subjective ratings also indicated that the EP caused significantly less fatigue, while increasing alertness and comfort.

Download

The zigzag paradigm

Brain Computer Interfaces (BCIs) are used to translate the input of Electroencephalogram (EEG), d... more Brain Computer Interfaces (BCIs) are used to translate the input of Electroencephalogram (EEG), digitally-recorded via electrodes on the user's scalp, into output commands that control external devices. A P300-based BCI speller system is based upon visual Event-Related Potentials (ERPs) in response to stimulation, as derived from EEG, and is used to type on a computer screen. The Row-Column speller Paradigm (RCP), utilizing a 6-by-6 character matrix, has been a widely-used successful P300 speller, despite inherent problems of adjacency, crowding, and fatigue. RCP is compared here with a new P300 speller interface, the Zigzag Paradigm (ZP). In the ZP interface every second row of the 6-by-6 character matrix is offset to the right by $d/2$ cm, where $d$ cm is the horizontal distance between two adjacent characters. This shifting addressed the adjacency problem by removing all vertical adjacent characters and increasing the distance between most adjacent characters. This shifting also addressed the crowding problem, for most characters, by reducing the number of other characters surrounding a character; critically the target character. A user study upon neurologically-normal individuals revealed significant improvements in online classification performance with the ZP, as supported the view that ZP effectively addressed adjacency and crowding problems. Subjective ratings also revealed that the ZP was more comfortable and caused less fatigue. Theoretical and practical implications of the applicability of the ZP for patients with neuromuscular diseases are discussed.

On The Design of User Experience Based Persuasive Systems

Computer and Information Science, Jun 30, 2011

Software Defects Prediction using Machine Learning Algorithms

2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), 2020

Software development and the maintenance life cycle are lengthy processes. However, the possibili... more Software development and the maintenance life cycle are lengthy processes. However, the possibility of having defects in the software can be high. Software reliability and performance are essential measures of software success, which affects user satisfaction and software cost. Predicting software defects using machine learning (ML) algorithms is one approach in this direction. Implementing this approach in the earlier stages of the software development improves software performance quality and reduces software maintenance cost. Different models and techniques have been implemented in many studies to predict software defects. This investigation implements ML algorithms, such as artificial neural networks (ANNs), random forest (RF), random tree (RT), decision table (DT), linear regression (LR), gaussian processes (GP), SMOreg, and M5P. A new software defect prediction model for software future defect prediction is proposed. The defect prediction is based on historical data. The results showed that a combination of ML algorithms could be used effectively to predict software defects. The SMOreg classifier scored the best performance results, where the ANN classifier scores the worst results.

The zigzag paradigm: a new P300-based brain computer interface

Proceedings of the 15th ACM on International conference on multimodal interaction, 2013

Brain Computer Interfaces (BCIs) are used to translate the input of Electroencephalogram (EEG), d... more Brain Computer Interfaces (BCIs) are used to translate the input of Electroencephalogram (EEG), digitally-recorded via electrodes on the user's scalp, into output commands that control external devices. A P300-based BCI speller system is based upon visual Event-Related Potentials (ERPs) in response to stimulation, as derived from EEG, and is used to type on a computer screen. The Row-Column speller Paradigm (RCP), utilizing a 6-by-6 character matrix, has been a widely-used successful P300 speller, despite inherent problems of adjacency, crowding, and fatigue. RCP is compared here with a new P300 speller interface, the Zigzag Paradigm (ZP). In the ZP interface every second row of the 6-by-6 character matrix is offset to the right by $d/2$ cm, where $d$ cm is the horizontal distance between two adjacent characters. This shifting addressed the adjacency problem by removing all vertical adjacent characters and increasing the distance between most adjacent characters. This shifting also addressed the crowding problem, for most characters, by reducing the number of other characters surrounding a character; critically the target character. A user study upon neurologically-normal individuals revealed significant improvements in online classification performance with the ZP, as supported the view that ZP effectively addressed adjacency and crowding problems. Subjective ratings also revealed that the ZP was more comfortable and caused less fatigue. Theoretical and practical implications of the applicability of the ZP for patients with neuromuscular diseases are discussed.

On The Design of User Experience Based Persuasive Systems

Computer and Information Science, 2011

The objective of persuasive technology researches is to develop persuasive systems that are able ... more The objective of persuasive technology researches is to develop persuasive systems that are able to change or reshape human behavior. Persuasive technology has quickly found a wide range of applications in many fields of research and development like marketing, health, safety and environment. The key element in designing successful persuasive systems is the improvement of the persuasion process. An important factor that should be included in the persuasion process is the user experience. This paper reviews the current trends of persuasive technology and shows some example of the available persuasive systems. The contribution of this paper is proposing a new and promising research direction for building persuasive systems that take the user feedback as a key element in the persuasion process. Some of the systems that follow this approach have been proposed and illustrated.

Download

Towards harnessing based learning algorithms for tweets sentiment analysis

2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies (3ICT), 2020

In the digital era of information, the number of web users and the volume of data being generated... more In the digital era of information, the number of web users and the volume of data being generated and exchanged over the internet has drastically increased. Sentiment analysis and opinion mining are open research fields having various everyday life applications, such as Twitter. Twitter is flooded with opinions, emotions, views and discussions among different communities across the world. Therefore, the tweet is related to various domains, such as stock market, product opinion and political elections. In this study, a classification problem is considered having a given set of tweets with various features and diverse opinions. The goal is to obtain expressions of opinion representing a target feature and to categorize these tweets as positive, neutral, or negative sentiment using different machine learning techniques. The dataset sentiment140 (STSTest) is preprocessed and very commonly used for research purposes. The studied machine learning classifiers are random Forest, libSVM, IBk...

Mining Historical Software Testing Outcomes to Predict Future Results

Software bugs and program defects have significant negative effect on the cost and duration of so... more Software bugs and program defects have significant negative effect on the cost and duration of software development process. Finding such bugs in early stages of the development process will cuts development time and maintenance costs. This investigation presents three different machine learning algorithms: K-Nearest Neighbors (KNN), Random Forest (RF), and Multilayer Perceptron (MLP) to build a new proposed software defect prediction model using different types of software performance metrics. This proposed model was tested on three public datasets obtained from NASA to assess its accuracy and revealed that the KNN was outperforms RF and MLP.

Software Defects Prediction using Machine Learning Algorithms

2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), 2020

Software development and the maintenance life cycle are lengthy processes. However, the possibili... more Software development and the maintenance life cycle are lengthy processes. However, the possibility of having defects in the software can be high. Software reliability and performance are essential measures of software success, which affects user satisfaction and software cost. Predicting software defects using machine learning (ML) algorithms is one approach in this direction. Implementing this approach in the earlier stages of the software development improves software performance quality and reduces software maintenance cost. Different models and techniques have been implemented in many studies to predict software defects. This investigation implements ML algorithms, such as artificial neural networks (ANNs), random forest (RF), random tree (RT), decision table (DT), linear regression (LR), gaussian processes (GP), SMOreg, and M5P. A new software defect prediction model for software future defect prediction is proposed. The defect prediction is based on historical data. The resul...

Towards Improving P300-based Brain-Computer Interfaces: From Desktop to Mobile

A brain-computer interface (BCI) enables a paralyzed user to interact with an external device thr... more A brain-computer interface (BCI) enables a paralyzed user to interact with an external device through brain signals. A BCI measures identifies patterns within these measured signals, translating such patterns into commands. The P300 is a pattern of a scalp potentials elicited by a luminance increment of an attended target rather than a non-target character of an alphanumeric matrix. The Row-Column Paradigm (RCP) can utilize responses to series of illuminations of matrix target and non-target characters to spell out alphanumeric strings of P300-eliciting target characters, yet this popular RCP speller faces three challenges. The adjacent problem concerns the proximity of neighboring characters, the crowding problem concerns their number. Both adjacent and crowding problems concern how these factors impede BCI performance. The fatigue problem concerns how RCP use is tiring. This dissertation addressed these challenges for both desktop and mobile platforms. A new P300 speller interface...

Download

Fault-Proneness of Open Source Systems: An Empirical Analysis

Developing quality software is a very complex job considering the complexity and size of software... more Developing quality software is a very complex job considering the complexity and size of software developed these days. Early prediction of software quality assists in optimizing testing resources. Many fault prediction models have been developed using several internal attributes and different machine learning techniques. However, the open-source community still lacks a concise knowledge about what types of internal attributes affect the software quality the most. In this work, an empirical investigation is conducted to explore the relationships between internal attributes of open-source systems and their fault-proneness. The results of the empirical analysis showed that by selecting only nine internal attributes, the fault prediction models accuracy did not decrease significantly. This indicates that only a subset of these internal attributes is worth collection and investigation. By focusing on a small set of internal attributes, the quality assurance team can save time and resour...

Download

Empirical Analysis of Object-Oriented Software Test Suite Evolution

International Journal of Advanced Computer Science and Applications

Spelling with a Small Mobile Brain-Computer Interface in a Moving Wheelchair

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society, Nov 2, 2017

Research into Brain-Computer Interfaces (BCIs), which spell words using brain signals, has reveal... more Research into Brain-Computer Interfaces (BCIs), which spell words using brain signals, has revealed that a desktop version of such a speller, the edges paradigm, offers several advantages: This edges paradigm outperforms the benchmark row-column paradigm in terms of accuracy, bitrate, and user experience. It has remained unknown whether these advantages prevailed with a new version of the edges paradigm designed for a mobile device. This paper investigated and evaluated in a rolling wheelchair a mobile BCI, which implemented the edges paradigm on small displays with which visual crowding tends to occur. How the mobile edge paradigm outperforms the mobile row-column paradigm has implications for understanding how principles of visual neurocognition affect BCI speller use in a mobile context. This investigation revealed that all the overall advantages of the edges paradigm over the row-column paradigm prevailed in this setting. However, the reduction in adjacent errors for the edges p...

ICMI-Poster-id 223

Towards User Experience Based Persuasive Systems

Communications in Computer and Information Science, 2011

Uploads

Papers by Qasem Obeidat

Log In