Hybrid estimation of distribution algorithms for solving a keyboard layout problem

Pradeepmon, T.G.; Panicker, Vinay V.; Sridharan, R.

doi:10.1080/21681015.2018.1508080

Cited by 6 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 summarizes some of the existing studies on the optimization of the single-pointer keyboard. As discussed above, it can be noticed that the majority of the studies focused on optimizing the keyboard for the English language [6,[19][20][21][22]. For the Arabic language, the majority of the research was dedicated to multifinger keyboard optimization [25][26][27].…”

Section: Summary and Discussionmentioning

confidence: 99%

“…Recently, Pradeepmon et al [6] tackled the same problem and proposed a layout for the single-finger keyboard that was optimized using a variant of Genetic Algorithm, namely, the Estimation of Distribution Algorithm.…”

Section: Single-finger Text Entrymentioning

confidence: 99%

“…Designing a keyboard where only one pointer is used for text input, either for severely disabled people using gazecontrolled typing or people using handheld mobile devices, is a prospering research area. Several research studies [3][4][5][6] were conducted to enhance the interface design of virtual keyboards in order to improve the comfort and typing speed of the end-users. In fact, even a small modification in the key arrangement may lead to a significant enhancement in typing performance since the improvement is accumulated in a repetitive task like text typing.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Usability Evaluation of Optimized Single-Pointer Arabic Keyboards Using Eye Tracking

Najjar

Al-Wabil

Hosny

et al. 2021

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

This paper presents the design and usability evaluation of an Arabic keyboard for applications that predominantly use single-pointer input device. Such applications are particularly used in mobile devices like Portable Data Assistants (PDAs) and smartphones. They are also valuable in gaze-controlled interfaces that constitute a growing mode of communication and that particularly empower people with mobility impairments. A special focus is given to the optimization of the key arrangement based on the movement time and character transition frequencies. An optimization model as well as a Simulated Annealing algorithm are presented. Then, the performance of the optimized layout is assessed showing that it outperforms the commonly used Arabic keyboard in terms of the estimated typing speed. However, the main limitation that the new layout might face is that a new arrangement of keys may not be adopted by users, even if the currently used layouts are not optimum. Therefore, a usability evaluation of the optimized layouts was conducted using eye-tracking and task-based testing involving the end-users and considering both objective and subjective measures of usability. Implications for the design are also discussed.

show abstract

Section: Summary and Discussionmentioning

confidence: 99%

Section: Single-finger Text Entrymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Usability Evaluation of Optimized Single-Pointer Arabic Keyboards Using Eye Tracking

Najjar

Al-Wabil

Hosny

et al. 2021

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

show abstract

“…Zhang et al presented an hybrid approach of guided local search and a first marginal based EDA for the QAP [66]. Pradeepmon et al [56] applied a hybrid EDA to the keyboard layout problem, which is modeled as a QAP problem. Previous EDA references use hybridization techniques to improve the performance of the algorithms, nevertheless, the probability models used are simplistic and are not suited to the characteristics of the QAP.…”

Section: Introductionmentioning

confidence: 99%

Kernels of Mallows Models under the Hamming Distance for solving the Quadratic Assignment Problem

Arza

Pérez

Irurozki

et al. 2020

Swarm and Evolutionary Computation

View full text Add to dashboard Cite

The Quadratic Assignment Problem (QAP) is a well-known permutation-based combinatorial optimization problem with real applications in industrial and logistics environments. Motivated by the challenge that this NP-hard problem represents, it has captured the attention of the optimization community for decades. As a result, a large number of algorithms have been proposed to tackle this problem. Among these, exact methods are only able to solve instances of size n < 40. To overcome this limitation, many metaheuristic methods have been applied to the QAP. In this work, we follow this direction by approaching the QAP through Estimation of Distribution Algorithms (EDAs). Particularly, a non-parametric distance-based exponential probabilistic model is used. Based on the analysis of the characteristics of the QAP, and previous work in the area, we introduce Kernels of Mallows Model under the Hamming distance to the context of EDAs. Conducted experiments point out that the performance of the proposed algorithm in the QAP is superior to (i) the classical EDAs adapted to deal with the QAP, and also (ii) to the specific EDAs proposed in the literature to deal with permutation problems.

show abstract

“…Not limited to the previous approaches, Estimation of Distribution Algorithms (EDAs) [32] have also been used to solve the QAP. For instance, in [52,43,49] EDA-based algorithms were proposed. In this paper, we propose a new EDA with properties that are specially suited to deal with the QPA.…”

Section: Introductionmentioning

confidence: 99%

Kernels of Mallows Models under the Hamming Distance for solving the Quadratic Assignment Problem

Arza,

Perez,

Irurozki

et al. 2019

Preprint

View full text Add to dashboard Cite

The Quadratic Assignment Problem (QAP) is a well-known permutation-based combinatorial optimization problem with real applications in industrial and logistics environments. Motivated by the challenge that this NP-hard problem represents, it has captured the attention of the evolutionary computation community for decades. As a result, a large number of algorithms have been proposed to optimize this algorithm. Among these, exact methods are only able to solve instances of size n < 40, and thus, many heuristic and metaheuristic methods have been applied to the QAP.In this work, we follow this direction by approaching the QAP through Estimation of Distribution Algorithms (EDAs). Particularly, a non-parametric distance-based exponential probabilistic model is used. Based on the analysis of the characteristics of the QAP, and previous work in the area, we introduce Kernels of Mallows Model under the Hamming distance to the context of EDAs. Conducted experiments point out that the performance of the proposed algorithm in the QAP is superior to (i) the classical EDAs adapted to deal with the QAP, and also (ii) to the specific EDAs proposed in the literature to deal with permutation problems.

show abstract

Hybrid estimation of distribution algorithms for solving a keyboard layout problem

Cited by 6 publications

References 23 publications

Usability Evaluation of Optimized Single-Pointer Arabic Keyboards Using Eye Tracking

Usability Evaluation of Optimized Single-Pointer Arabic Keyboards Using Eye Tracking

Kernels of Mallows Models under the Hamming Distance for solving the Quadratic Assignment Problem

Kernels of Mallows Models under the Hamming Distance for solving the Quadratic Assignment Problem

Contact Info

Product

Resources

About