Advances in Human-Computer Interaction

Speech imagery is emerging as a significant neuro‐paradigm for designing an electroencephalography (EEG)‐based brain–computer interface (BCI) system for the purpose of rehabilitation, medical neurology, and to aid people with disabilities in interacting with their surroundings. Neural correlates of speech imagery EEG signals are variable and weak as compared to the vocal state; hence, it is challenging to interpret them using machine learning (ML)–based classifiers. The applicability of modern deep learning methods such as convolutional neural networks (CNNs) and bidirectional long short‐term memory (Bi‐LSTM) networks has seen substantial advances in complex EEG signal analysis as compared to ML‐based methods. The objective of this article is to design a firefly‐optimized discrete wavelet transform (DWT) and CNN‐Bi‐LSTM–based imagined speech recognition (ISR) system to interpret imagined speech EEG signals. This study utilizes two publicly available datasets. EEG signal is enhanced using firefly optimization algorithm (FOA)–based optimized soft thresholding of high‐frequency detail components obtained by DWT decomposition. The enhanced EEG signal is augmented using sliding window data augmentation to increase the training data. Frequency‐domain features like power spectral density (PSD), frequency band power (FBP), band ratios, peak frequency, mean frequency, median frequency, spectral entropy, and relative power are extracted from augmented EEG segments. The extracted feature vector is fed to the designed CNN‐Bi‐LSTM classifier such that the EEG data are classified into two‐class, three‐class, and four‐class categories. To achieve optimal performance, the CNN‐Bi‐LSTM model was optimized using the Keras tuner library. The designed CNN consists of one‐dimensional (1‐D) convolutional layers and max pooling layers for familiarizing local associations along with mining hierarchical connections, and the Bi‐LSTM network acquires long‐term dependencies from the features learned by the former CNN. Bi‐LSTM network improves the performance and acquires potentially more affluent representations by looking at the sequence in both forward and reverse ways to capture representations that might be left unexploited by the sequential‐order kind alone. The performance of the designed FOA‐DWT‐CNN‐Bi‐LSTM–based ISR system is assessed using four evaluation measures: accuracy, F 1 score, recall, and precision. It is found that the proposed system achieves the highest classification accuracy of 99.43 ± 2.5%, 94.41 ± 3.31%, and 89.57 ± 4.3% for two‐class, three‐class, and four‐class categories, respectively.

Meenakshi Bisla

Radhey Shyam Anand

Optimized CNN‐Bi‐LSTM–Based BCI System for Imagined Speech Recognition Using FOA‐DWT

基于FOA-DWT的优化CNN-Bi-LSTM脑机接口系统用于想象语音识别

This paper reports a summative evaluation conducted for the educational mobile application called “Qiraat Sab’ah.” The prototype was developed using the Rapid Application Development (RAD) and User Experience (UX) methodologies. The prototype was improved further based on the formative evaluation feedback gathered from students, lecturers, and the public who wish to learn Qiraat through the mobile application. The summative evaluation was focused on the value and usability of the application if it is being used in a real environment. A total of 50 participants were involved in this evaluation. The result shows that most of the participants provide positive feedback on usability. One of the major highlights from the participants is that the application can be used as a supplementary teaching and learning tool for people who wish to learn Qiraat anytime and anywhere. However, further areas of expansion are needed such as including all chapters (surahs) in the Quran and tajweed indicators to the verses before it can be used for real.

Zulkifly Mohd Zaki

Syahidatul Fitriah Ishak

Khairul Anuar Mohamad

User Interface Designs of an Educational Mobile Application: A Study of Qiraat Teaching and Learning

教育移动应用的用户界面设计：古兰经诵读教学与学习研究

Background. Standardized questionnaires are well-known, reliable, and inexpensive instruments to evaluate user experience (UX). Although the structure, content, and application procedure of the three most recognized questionnaires (AttrakDiff, UEQ, and meCUE) are known, there is no systematic literature review (SLR) that classifies how these questionnaires have been used in primary studies reported academically. This SLR seeks to answer five research questions (RQs), starting with identifying the uses of each questionnaire over the years and by geographic region (RQ1) and the median number of participants per study (how many participants is considered enough when evaluating UX?) (RQ2). This work also aims to establish whether these questionnaires are combined with other evaluation instruments and with which complementary instruments are they used more frequently (RQ3). In addition, this review intends to determine how the three questionnaires have been applied in the fields of ubiquitous computing and ambient intelligence (RQ4) and also in studies that incorporate nontraditional interfaces, such as haptic, gesture, or speech interfaces, to name a few (RQ5). Methods. A systematic literature review was conducted starting from 946 studies retrieved from four digital databases. The main inclusion criteria being the study describes a primary study reported academically, where the standardized questionnaire is used as a UX evaluation instrument in its original and complete form. In the first phase, 189 studies were discarded by screening the title, abstract, and keyword list. In the second phase, 757 studies were full-text reviewed, and 209 were discarded due to the inclusion/exclusion criteria. The 548 resulting studies were analyzed in detail. Results. AttrakDiff is the questionnaire that counts the most uses since 2006, when the first studies appeared. However, since 2017, UEQ has far surpassed AttrakDiff in uses per year. The contribution of meCUE is still minimal. Europe is the region with the most extended use, followed by Asia. Within Europe, Germany greatly exceeds the rest of countries (RQ1). The median number of participants per study is 20, considering the aggregated data from the three questionnaires. However, this median rises to 30 participants in journal studies while it stays in 20 in conference studies (RQ2). Almost 4 in 10 studies apply the questionnaire as the only evaluation instrument. The remaining studies used between one and five complementary instruments, among which the System Usability Scale (SUS) stands out (RQ3). About 1 in 4 studies analyzed belong to ubiquitous computing and ambient intelligence fields, in which UEQ increases the percentage of uses when compared to its general percentage, particularly in topics such as IoT and wearable interfaces. However, AttrakDiff remains the predominant questionnaire for studies in smart cities and homes and in-vehicle information systems (RQ4). Around 1 in 3 studies include nontraditional interfaces, being virtual reality and gesture interfaces the most numerous. Percentages of UEQ and meCUE uses in these studies are higher than their respective global percentages, particularly in studies using virtual reality and eye tracking interfaces. AttrakDiff maintains its overall percentage in studies with tangible and gesture interfaces and exceeds it in studies with nontraditional visual interfaces, such as displays in windshields or motorcycle helmets (RQ5).

Ignacio Díaz-Oreiro

Gustavo López

Luis Quesada

Luis A. Guerrero

UX Evaluation with Standardized Questionnaires in Ubiquitous Computing and Ambient Intelligence: A Systematic Literature Review

无处不在计算与环境智能中使用标准化问卷的用户体验评估：一项系统性文献综述

Learning to memorize the Quran presents a challenge. This paper reports the development and alpha testing of a mobile application called “EzHifz” for Quran memorization based on the VARK learning style. The application received positive feedback for user acceptance testing and heuristic testing. The Fleiss kappa coefficient (κ) results for user acceptance testing show a very good level of agreement (κ = 0.850). Heuristic testing results show that κ = 0.731 for content, manual guide, memorization activities, performance information, and tasmik assessment attributes, while κ = 0.727 for presentation design, interactivity, multimedia elements, attraction, and motivation attributes. These results show a good level of agreement, which indicates that the EzHifz application meets the requirements of design and development based on the attributes evaluated. A combination of memorizing techniques in the application helps strengthen the use of preferred VARK learning styles. The techniques support the use of multiple senses that could facilitate the process of memorizing the Quran independently. This study contributes to the novel design and evaluation of the Quran memorization application based on the Quran memorization model. The application supports the teaching and learning of Quran memorization where it allows students to select their preferred VARK learning style with the technique of memorizing the Quran. This mobile application learning approach based on VARK’s learning style has the potential to be implemented in the process of memorizing the Quran as well as retaining memory through the use of memory senses in support of the learning materials developed.

Nor Musliza Mustafa

Mokmin Basri

Sedek Ariffin

Development and Alpha Testing of EzHifz Application: Al-Quran Memorization Tool

EzHifz应用程序的开发与Alpha测试：古兰经背诵工具

Serendipity refers to unexpected encounters with ideas or insights and their intentional application to achieve favorable outcomes. Despite extensive prior studies, the concept lacks theoretical logic and empirical validation regarding the role of an intentional act in the relationship between serendipitous encounters and their favorable outcomes. Drawing from self-determination theory, we develop a model that highlights the role of needs satisfaction in explaining this relationship. Positioning the empirical context to fortunate discoveries of information and social connections in professional use of Twitter, we validate the model by a cross-sectional survey study of 473 users. The model builds on the observation that individuals’ serendipitous encounters are associated with Twitter-enabled innovation, that is, a contextualized form of task innovation. The study findings support the research model revealing that serendipitous encounters are positively associated with needs satisfaction and that needs satisfaction is positively associated with Twitter-enabled innovation. In other words, fortunate discoveries of new information and contacts increase Twitter users’ intent to utilize the platform in new ways to accomplish work when the three key psychological needs of autonomy, competence, and relatedness are satisfied.

Henri Pirkkalainen

Ekaterina Olshannikova

Thomas Olsson

Jukka Huhtamäki

Examining Serendipitous Encounters and Self-Determination in Twitter-Enabled Innovation

探究推特助力创新中的意外发现与自我决定

In this modern era of technology, most of the accessibility issues are handled with the help of smart devices and cutting-edge gadgets. Smartphones play a crucial role in addressing various accessibility challenges, including voice recognition, sign language detection and interpretation, navigation systems, speech-to-text conversion, and vice versa, among others. They are computationally powerful enough to handle and run numerous machine and deep learning applications. Among various accessibility challenges, speech disorders represent a disability where individuals struggle to communicate verbally. Similarly, hearing loss is a disability that impairs an individual’s ability to hear, necessitating reliance on gestures for communication. A significant challenge encountered by people with speech disorders, hearing loss, or both is their inability to effectively convey or receive messages from others. Hence, these individuals heavily depend on the sign language (a gesture-based communication) method, typically involving hand movements and expressions. To the best of our knowledge, there are currently no comprehensive review and/or survey articles available that cover the literature on speech disabilities and sign language detection and interpretation via smartphones utilizing machine learning and/or deep learning approaches. This study fills the gap in the literature by analyzing research publications on speech disabilities, published from 2012 to July 2023. A rigorous search and standard strategy for formulating the literature along with a well-defined theoretical framework for results and findings have been used. The paper has implications for practitioners and researchers working in accessibilities in general and smart/intelligent gadgets and applications for speech-disabled people in specific.

Iftikhar Alam

Abdul Hameed

Riaz Ahmad Ziar

Exploring Sign Language Detection on Smartphones: A Systematic Review of Machine and Deep Learning Approaches

探索智能手机上的手语检测：机器学习和深度学习方法的系统综述

Studies evaluating students’ UX of applications that will influence their continuance use of educational systems in Higher Educational Institutions (HEIs) have not been sufficiently addressed in the African region, specifically in Ghana. Thus, conducting a study on students’ UX of systems in HEIs will enhance students’ interest in continuing to use such systems. Therefore, this study examines students’ user experience (UX) and how it impacts their continued use of the Student Management Information System (SMIS). The study proposed a research model by integrating user experience questionnaire (UEQ) constructs with continuance intention to use. The study adopted an online questionnaire to collect data from 415 students at Koforidua Technical University (KTU). The partial least square-structural equation model (PLS-SEM) method was used to evaluate the proposed model’s reliability, validity, and relationship among the constructs. The UEQ data analysis tool was used in analysing the data. The study’s findings showed that attractiveness, perspicuity, efficiency, stimulation, and novelty significantly influenced students’ continuance intention to use the SMIS. However, dependability did not significantly affect students’ continuance intention to use the SMIS. Also, the study’s findings on the benchmark results showed that attractiveness, perspicuity, and stimulation were categorized as good, while dependability, efficiency, and novelty were categorized as excellent. These findings offer valuable insights for UX designers and developers aiming to create engaging and intuitive SMIS solutions. Also, it will provide students feedback on system UX that can be incorporated into future release updates. Furthermore, this research contributes significantly to the understanding of student UX with SMIS in developing country HEIs and its impact on continued usage.

Noble Arden Kuadey

Carlos Ankora

Laurene Adjei

Elikem Krampa

Stephen Oladagba Bolatimi

Lily Bensah

Collinson Colin M. Agbesi

Evaluating Students’ User Experience on Student Management Information Systems

评估学生管理信息系统中学生的用户体验

This paper presents the effects of chat box (C.B.) and video call (V.C.) artificial intelligence applications, which are becoming increasingly common in the banking system in parallel with the development of information systems on the number of digital banking users, and the relationship between the variables is investigated. The data set of the variables consists of a total of 44 observation points between the 1st quarter of 2012 and the 4th quarter of 2022. The cointegration relationship between the variables is examined using the ARDL cointegration test. According to the F statistic results for cointegration hypothesis testing, there is a statistically significant relationship between the variables at a 1% significance level. In the long run, a 1% increase in Chat Box users causes an increase of approximately 0.2% in the number of mobile banking users. A 1% increase in Chat Box users in the short term increases the number of mobile banking users in the current period by approximately 0.03%. A 1% increase in video call users in the long term causes an increase of approximately 0.04% in the number of mobile banking users. A 1% increase in the number of video calls in the current period increases current period mobile banking applications by approximately 0.005%. It has been determined that the effect of chat box applications on mobile banking is higher than that of video call applications. In addition, there is a close correlation between mobile banking and the independent variable chat box, no correlation between mobile banking and video calling, and a moderate correlation between chat box and video calling. All findings mean that artificial intelligence applications positively contribute to the expansion of mobile banking.

Serkan Demirel

Murat Topcu

The Impact of Artificial Intelligence Applications on Digital Banking in Turkish Banking Industry

土耳其银行业中人工智能应用对数字银行的影响

Despite the substantial growth in digital out‐of‐home media and the promising potential of digital place‐based media, there is a limited understanding of this medium at minibus taxi ranks. The scholarly literature mostly neglects transit advertising’s digital transformation, while practitioners are starting to recognize its potential. This paper bridges the academic‐practitioner gap by reviewing digital place‐based media’s potential within minibus taxi ranks. The integrative review process involved defining the issue, detailing contributions and research questions, and synthesizing diverse sources into a conceptual framework. This framework comprehensively portrays the environment, distinguishes traditional and nontraditional media, and explores digital place‐based media features. It offers guidelines for digital marketers, advertisers, and content managers, proposing future research areas in contextual factors, media comparisons, and DPB media features. Multiple aspects for future research are suggested across three distinct areas: contextual factors in transit media; comparative analysis of traditional and nontraditional media, focusing on their image, cost, integration with technologies, and human interaction with media; and examination of DPB media features, encompassing creativity in content creation and delivery, contextually relevant content, and digital programmatic content.

A. T. Roux

E. Wannenburg

T. V. Manetje

The Environment and Features of Digital Place‐Based Media at Minibus Taxi Ranks as Nontraditional Advertising Media

数字基于地点的媒体在小巴出租车候车点的环境和特征作为非传统广告媒体

短名	Adv. Hum. Comput. Interact.
Journal Impact	2.43
国际分区	COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE(Q3)

ISSN	1687-5893, 1687-5907
h-index	29

涉及主题	计算机科学操作系统人工智能心理学人机交互工程类生物哲学数学程序设计语言物理语言学医学经济量子力学地理万维网法学政治学社会学计算机视觉神经科学多媒体统计
出版信息	出版商: Hindawi Limited，出版周期: ，期刊类型: journal，开源期刊: 是
基本数据	创刊年份: 2010，原创研究文献占比: 78.26%，自引率:0.00%， Gold OA占比: 98.00%
期刊费用	$950详情
平均审稿周期	网友分享经验：36 Weeks

Advances in Human-Computer Interaction

期刊引文格式

有 1 位以上作者的期刊

有 2 位作者的期刊

有 3 位作者的期刊

有 5 位以上作者的期刊

书籍引用格式

学位论文引用格式

网页引用格式

专利引用格式

手工熬夜修改参考文献？研飞自动匹配期刊，一键轻松成稿，支持 Word/WPS

投稿经验分享

Optimized CNN‐Bi‐LSTM–Based BCI System for Imagined Speech Recognition Using FOA‐DWT

User Interface Designs of an Educational Mobile Application: A Study of Qiraat Teaching and Learning

UX Evaluation with Standardized Questionnaires in Ubiquitous Computing and Ambient Intelligence: A Systematic Literature Review

Development and Alpha Testing of EzHifz Application: Al-Quran Memorization Tool

Examining Serendipitous Encounters and Self-Determination in Twitter-Enabled Innovation

Exploring Sign Language Detection on Smartphones: A Systematic Review of Machine and Deep Learning Approaches

Evaluating Students’ User Experience on Student Management Information Systems

Optimized CNN‐Bi‐LSTM–Based BCI System for Imagined Speech Recognition Using FOA‐DWT

The Impact of Artificial Intelligence Applications on Digital Banking in Turkish Banking Industry

The Environment and Features of Digital Place‐Based Media at Minibus Taxi Ranks as Nontraditional Advertising Media