Iyad Abu Doush

Novel selection schemes for harmony search

Selection is a vital component used in Evolutionary Algorithms (EA) where the fitness value of the solution has influence on the evolution process. Normally, any efficient selection method makes use of the Darwinian principle of natural selection (i.e., survival of the fittest). Harmony search (HS) is a recent EA inspired by musical improvisation process to seek a pleasing harmony. Originally, two selection methods are used in HS: (i) memory consideration selection method where the values of the decision variables are randomly selected from the population (or solutions stored in harmony memory (HM)) to generate a new harmony, and (ii) selecting a new solution in HM whereby a greedy selection is used to update the HM. The memory consideration selection, the focal point of this paper, is not based on natural selection principle which draws heavily on random selection. In this paper, novel selection schemes which replace the random selection scheme in memory consideration are investigated, comprising global-best, fitness-proportional, tournament, linear rank and exponential rank. The proposed selection schemes are individually altered and incorporated in the process of memory consideration and each adoption is realized as a new HS variation. The performance of the proposed HS variations are evaluated and a comparative study is conducted. The experimental results using benchmark functions show that the selection schemes incorporated in memory consideration directly affect the performance of HS algorithm. Finally, a parameter sensitivity analysis of the proposed HS variations is analyzed.

Hybridizing Harmony Search algorithm with different mutation operators for continuous problems

Abstract Harmony Search (HS) is a recent EA inspired by musical improvisation process to seek a pleasing harmony. Mutation is a vital component used in Evolutionary Algorithms (EA) where a value in the population is randomly selected to be altered to improve the evolution process. The original HS algorithm applies an operation similar to mutation during the random consideration operator. During random selection operator a value within the range of the decision variable is selected randomly to explore different areas in the search space. This paper aims at experimentally evaluating the performance of HS algorithm after replacing the random consideration operator in the original HS with five different mutation methods. The different variations of HS are experimented on standard benchmark functions in terms of final obtained solution and convergence speed. The results show that using polynomial mutation improves the performance of the HS algorithm for most of the used functions.

The design of RIA accessibility evaluation tool

Most of the accessibility evaluation tools available check the accessibility of static traditional web pages (e.g., web pages encoded with only HTML) according to the accessibility guidelines (e.g., WCAG). There is an increased need to check the accessibility of Rich Internet Applications (RIAs) using automatic tools. In this paper, we present a conceptual framework for automatic evaluation of accessibility of rich Internet contents. The framework includes: web robot, RIA events controller, WAI-ARIA accessibility specifications, evaluator, and results handler. An example to demonstrate how the framework can be applied has been presented in detail.

Non-visual navigation of spreadsheets

The problem of non-visual navigation of the information in Excel™ spreadsheet is that using current technologies, no overview is available for the user about different components found in the spreadsheet. Several attributes associated with spreadsheets make them not easy to navigate by individuals who are blind. The large amount of information stored in the spreadsheet, the multi-dimensional nature of the contents, and the several features it includes cannot be readily linearized by a screen reader or Braille display (e.g., charts and tables). A user-centered design paradigm is followed to build an accessible system for non-visual navigation of Microsoft Excel™ spreadsheet. The proposed system provides the user with a hierarchical overview of the navigated components in an Excel™ spreadsheet. The system is multi-modal, and it provides the user with different navigation and reading modes for the non-visual navigation of a spreadsheet. This will help the users in adapting the non-visual navigation according to the task the user needs to accomplish.

Annotations, Collaborative Tagging, and Searching Mathematics in E-Learning

This paper presents a new framework for adding semantics into e-learning system. The proposed approach relies on two principles. The first principle is the automatic addition of semantic information when creating the mathematical contents. The second principle is the collaborative tagging and annotation of the e-learning contents and the use of an ontology to categorize the e-learning contents. The proposed system encodes the mathematical contents using presentation MathML with RDFa annotations. The system allows students to highlight and annotate specific parts of the e-learning contents. The objective is to add meaning into the e-learning contents, to add relationships between contents, and to create a framework to facilitate searching the contents. This semantic information can be used to answer semantic queries (e.g., SPARQL) to retrieve information request of a user. This work is implemented as an embedded code into Moodle e-learning system.

Integrating semantic web and folksonomies to improve e-learning accessibility

The purpose of this project is to investigate ways of leveraging the collaborative and multi-user nature of modern Learning Management Systems (LMSs) to enhance accessibility of online courses for individuals with visual disabilities. The underlying principle of the project is the generation of semantics annotation for all components of an online course--that can be used to guide assistive devices. The semantic information can be added in a three different forms (a predefined ontology class, user tags, and annotations). This semantic information is used by assistive technologies (e.g., screen readers) to help visually impaired students when they acquire knowledge from the on-line course materials.

Harmony search with multi-parent crossover for solving IEEE-CEC2011 competition problems

Harmony search algorithm (HSA) is a recent evolutionary algorithm used to solve several optimization problems. The algorithm mimic the improvisation behaviour of a group of musicians to find a good harmony. Several variations of HSA has been proposed to enhance its performance. In this paper, a new variation of HSA that uses multi-parent crossover is proposed (HSA-MPC). In this technique three harmonies are used to generate three new harmonies that will replace the worst three solution vectors in the harmony memory (HM). The algorithm has been applied to solve a set of eight real world numerical optimization problems (1-8) introduced for IEEE-CEC2011 evolutionary algorithm competition. The experiemental results of the proposed algorithm is compared with the original HSA, and two variations of HSA: global best HSA and tournament HSA. The HSA-MPC almost always shows superiority on all test problems.

Detecting and recognizing tables in spreadsheets

Detecting tables in a spreadsheet is the first step needed to make spreadsheet documents accessible to individuals with visual disabilities. Techniques to enable aural presentation and navigation of tables have been proposed, but they assume a thorough knowledge of the structure of the table; on the other hand, boundaries and structure of tables in a spreadsheet are not evident without a visual exploration. This paper presents an algorithm for table recognition in spreadsheets. The algorithm uses three types of cells as its basis: title cell, header cell, and data cell. Different attributes of the cells are used to identify the cell type within a spreadsheet. Hierarchical clustering is used to aggregate cells to compose the functional components of a table. The algorithm has been evaluated on a diverse set of benchmarks with very encouraging results.

ISAB: Integrated Indoor Navigation System for the Blind

Generally, indoor navigation is considered as a challenging task, especially when people navigate through an unfamiliar place (e.g. a university or a mall). It is even a more challenging endeavor for the visually impaired and blind community. This paper presents an innovative approach to the precise indoor navigation challenge for the blind individuals using a multi-tier solution with the help of an intuitive smartphone interface. We utilize a set of different communication technologies (WiFi, Bluetooth and radio-frequency identification) to help users reach an object with high accuracy. As a proof of concept, we deploy a fully functional testbed and we evaluate our entire solution inside our university library by helping blind users find a specific book. Our results demonstrate the high accuracy of the proposed system to reach an object with accuracy up to 10 cm. The intuitive smartphone interface provides step-by-step navigation voice instructions of the least hazardous path for the blind users while minimizing the cognitive load on their short-term memory. In addition, we show that our iterative improvements on our smartphone’s interface has improved the system’s efficiency and its accuracy in reaching specific objects successfully.

Hybridizing Harmony Search Algorithm with Multi-Parent Crossover to Solve Real World Optimization Problems

Harmony search algorithm (HSA) is a recent evolutionary algorithm used to solve several optimization problems. The algorithm mimics the improvisation behaviour of a group of musicians to find a good harmony. Several variations of HSA have been proposed to enhance its performance. In this paper, a new variation of HSA that uses multi-parent crossover is proposed (HSA-MPC). In this technique three harmonies are used to generate three new harmonies that will replace the worst three solution vectors in the harmony memory (HM). The algorithm has been applied to solve a set of eight real world numerical optimization problems (1-8) introduced for IEEE-CEC2011 evolutionary algorithm competition. The experimental results of the proposed algorithm are compared with the original HSA, and two variations of HSA: global best HSA and tournament HSA. The HSA-MPC almost always shows superiority on all test problems.