People tend to face difficulties while speaking, owing to excessive tension. To relieve this tension, we propose a method to alter their voice such that it appears more confident and feed this voice back to the speaker in real time. As determining the appropriate parameters for voice processing is difficult, we gathered data on the perception of confidence in voices through crowdsourcing and constructed a model for estimating confidence scores from voice-processing parameters. An analysis of the model showed that although the coefficient of determination was not considerably large, the inflection of speech tended to affect the perception of confidence.
The situation of lecture, sometimes we also call presentation, talk, speech especially in business conference, haven't change for long time. Although, there are some unsolved issue, for attending lecture of both speaker and audience, that speaker can't give enough information to each audience and the speaker is needed to control the lecture all by themselves. The audience is having difficulty to get enough information with comfortable environment. Therefore, we developed the VR Lecture System for give necessary and enough information to make audience understand, and support the speaker in the lecture by Chat Bot. The audience can control and get more information, and the speaker can communicate with Chat Bot in VR space. This paper explain about implementation and evaluation of VR Lecture System.
In this paper, we propose a method to automatically assign attributes to guidance information and automatic authoring method of information according to user attributes. This makes it possible to provide an information guidance system with low cost. Also, we describe the problem of "reading" occurring in Japanese and its solution. Our work has not completed yet. We just completed the system development. We are planning to carry out evaluation of our system from now on.
Thumb based interaction is becoming increasingly popular in mobile devices. However, the interaction still remains slow, ambiguous, and error-prone. This paper presents an exploratory user experiment results of one-thumb pointing and dragging task performance, based on three factors: mobile size, target size, and posture (sitting and walking positions). Beside obvious findings, we observed some surprising scenarios, such as the gripping style of most users was casual and did not follow any formal model or structure. We concluded our experiences into design implications with respect to mobile size, posture, and gripping styles.
In this paper, we propose a feeling-sharing system called PICALA, which can register the feelings of audiences during public presentations. We designed and implemented a system in which the colors of the light bulbs near the screen changed by clicking the browser buttons. The proposed system uses a series of four colored lights. To express their feelings, each person in the audience was given a push button unit having four buttons that indicated empathy, amazement, laughter, and query. We conducted experiments in three workshops: WISS 2014, Wakate 2015, and EC 2015. Our subjective assessment using questionnaire surveys proved that the users could successfully share their feelings using PICALA.
People make choice of a keyboard for various features such as key arrangement, repulsion strength, stroke depth, and stroke sound. Currently these features depend on hardware; however, if a physical keyboard can be customized with software, users will be able to arrange it as their preference. In this paper, we propose augmented typing that augments typing experience by adding a visual and sound effect to a physical keyboard. We implemented a prototype system of the proposed system using projection mapping. To determine the effect and the usefulness of the system, in addition, we conducted evaluation experiments. Results of the experiments showed that the evaluation of sound effect was more variable than visual effect; users found that visual effects are beautiful, whereas the sound effects to be annoying.
Giving computers the ability to learn from demonstrations is important for users to perform complex tasks. In this paper, we present an intelligent self-learning interface for dynamic human pose recognition. We capture 20 samples for an unknown pose to train a stable generative adversarial networks (GAN) system which aims to conduct data enhancement, then we adopt a threshold isolation method to distinguish relatively similar poses. A few minutes of learning time is sufficient to train a GAN system to successfully generate qualified pose samples. Our platform provides a feasible scheme for micro-intelligent interface, which can benefit to human-robot interaction greatly.
Cricket is the most popular game in the developing countries of South Asia (India, Pakistan, Bangladesh, Sri Lanka etc) is quickly becoming one of the most widely used form of entertainment in the developing countries of South Asia. As sports are one of the most influential driving forces of a society, use of analytic is perceived to be conducive for creating a more analysis driven society, which is a necessity for developing countries with low rate of literacy. That is how widespread use of technology and analysis in cricket can drive a technological spark in the South Asian developing countries. Cricket is an eleven-member team sport, where the team selection has traditionally been done based on popular reputation of the player and intuition of the management. However, with the recent advent of T20 cricket, which is a shorter version of the game as opposed to the traditional 5-day longer version, the use of data analysis and prediction tools is becoming widespread. The analysis tools mostly analyze a player's skills and past records for team selection. However, unlike other sports, the playing conditions are vital in cricket as the conditions are vastly different from ground to ground. This work takes a novel approach of player selection as we consider the ground characteristics in case of choosing one player over another, where none of the players have prior experience of playing on that ground.
Emotions are integral to the social media user experience; we express our feelings, react to posted content and communicate with emoji. This may lead to emotional contagion and undesirable behaviors such as cyberbullying and flaming. Nearly real-time negative emotion detection during the use of social media could mitigate these behaviors, but existing techniques rely on corpora of aggregated user-generated data - posted comments or social graph structure. This paper explores how live data extracted from smartphone sensors can predict binary affect, valence and arousal during the typical social media tasks of browsing content and chatting. Results show that momentary emotion can be predicted, using features from screen touches and device motions, with peak F1-scores of 0.86, 0.86, 0.88 for affect, valence and arousal.
Video comparison is a common task that people engage in when interacting with video contents, for instance, in video browsing and video editing. However, there exists little guidance to prompt and assist designers about a comparison task when designing user interfaces and interactions for a video application. To develop the guidance, we are synthesizing relevant knowledge from related research areas and our own prototypes into a theoretical model that pertains key elements and their relationships that characterise the interaction of video comparison. Here, we present a design originated from this model and an informal user study that helped us test and refine the model. The case study demonstrates the model's potential in shedding new lights on how applications that support video comparison could be designed better and also in offering avenues for future research in applications that depend on video comparison, regardless of domain areas.
Among the barriers of many developing countries, one of the major problems is that a huge portion of women are still confined within the boundary of their home. A nation can in no way progress without the contribution of such a huge portion of population towards the economy. In spite of having potential, many women remain under-utilized just due to lack of necessary support, such as, capital, partners, workers, work-space and social security. In this age of technology numerous applications of Information and Communication Technology (ICT) has been introduced in homes and workplaces, changing the way we live, how we work, and what we are able to do. As a part of technology revolution ICT tools are becoming increasingly accessible to the rural underprivileged people. Technology is also essential for women's economic advancement and can help women in developing countries to increase their productivity, create new entrepreneurial ventures and access new income-generating pursuits. ICT is rapidly changing the global landscape and becoming a necessary tool for running a competitive business. The range of potential benefits ICTs offer is extensive; ensure better access to information crucial to business development, market and pricing information, production technologies, compliance, forecasts and training. ICT can also enable entrepreneurs to communicate better along the value chain as well as their administration more efficient. Since information and services increasingly becoming digital in both public and private sector, entrepreneurs without using technology have an obvious disadvantage.
Therefore a bridge between these two buzzwords `Entrepreneurship' and `Technology' can contribute to accelerate both the streams. Keeping pace with this motivation, we present the gender divide and ICT usage in entrepreneurship in context of Bangladesh and propose a study and platform which will help user to find complementary business partners, financers, information, services even in nearest locality. Though the problem is mainly explored focusing females in developing counties; gender based requirements of the environment, social context, customized design approaches, will be an interesting investigation. Study of this cross country topic can bridge the gender divide and its real-life implementation can surely contribute to raise the overall social and economic growth of any developing country.
Socio-educational background plays an influential role in the success of a studentś engineering schooling. These socio-educational backgrounds are of more diverse nature in developing countries like Bangladesh. The fact that, tertiary education is given in a foreign language adds another dimension to challenge of imparting a successful engineering education. If the students could be grouped according to their socio-educational features, then it would have been easier to anticipate the needs of students coming from diverse backgrounds. In this work, we classify the students (N=237) of the department of Computer Science and Engineering of a university in the Bangladeshi capital of Dhaka based on their socio-educational features using K-means clustering and then propose a classifier that could work as a predictor that could work as a predictor for predicting student needs coming from different backgrounds.
Commitment devices-a self-imposed contract that helps an individual stick to a plan of action-have been widely used to make a positive influence on one's behavior change. We analyze commitment contract posts in StickK.com, an online behavior change support system to characterize the types of target behaviors and the effectiveness of different commitment devices for behavioral changes. We provide several practical implications for designing behavior change support systems that could inform further directions for research in behavioral economics and psychology.
The public's ever-growing interest in health has led the well-being industry to explosive growth over the years. This propelled activity trackers as one of the trendiest items among the current day wearable devices. Seeking new opportunities for effective data utilization, we present a participatory design method that explores the fusion of activity data with entertainment application. In this method we spur participants to design by mix-and-matching activity tracker data attributes to existing entertainment application features to produce new concepts.
We report two cases of method implementation and further discuss the opportunities of activity tracker data as means for entertainment application design.
Disasters are constantly affecting Asia. To minimize the damage, it is important to have an immediate and effective response, which requires multiple stakeholders of the disaster scenarios to communicate. After identifying stakeholders and their needs through personas and scenarios illustrating earthquake situations, we evaluated existing mobile applications with the needs for disaster responses, earthquake in particular. The findings of this study suggest design implications for creating mobile applications to support multiple stakeholders for disaster responses.
Technology intervention can play an important role during natural disasters. Flash flood, a major natural disaster taking place in Bangladesh, can be supported by continuous water level monitoring and notification based system. A low-cost sensor based system to handle flash flood required consideration of policy and local community support at its infancy. Later the system was designed using community inputs and deployed using authority support where the entire team worked with researchers cooperatively to have the ownership of the problem as well as the technology intervention.
The purpose of paper is to improve the limitations of current augmented reality technology in traditional handicraft learning. We propose a traditional handcraft mobile learning mode based on WebAR technology. Firstly, we analyzed that the current situation of traditional handicraft learning based on augmented reality technology and summarized the characteristics and application advantages of Web AR. Secondly, we develop a framework of traditional handcraft mobile learning system based on Web AR technology in traditional handicraft learning. Finally developed a mobile interactive prototype with Cantonese Porcelain as a practical case for the user interaction experience test. Interactive prototype with Cantonese Porcelain as a practical case for the user interaction experience test. The results show that the traditional handicraft learning model based on WebAR is more effective than the application limitations of traditional augmented reality devices. This contribution is highly relevant for users that aim for learning and creativity in different contexts that bring to new forms of traditional handicraft learning.
Online abusive or hateful speech detection in different languages on Social Networking Sites (SNS) have drawn the attention of researchers recently. Hateful comments in public Facebook pages ignite social mishaps in Bangladesh. In this paper, we have discussed the development and annotation of the corpus of hateful speech in the Bengali language on public Facebook pages. We have classified hateful comments into six major classes based on the social aspects of Bangladesh. The corpus (4753 comments) is the maiden contribution as a publicly available data set that can be enhanced and utilized for future hate speech research in SNS.
The critical steps of knowledge sharing process in hospital is to change tacit knowledge into explicit knowledge (externalization) and use that explicit knowledge to improve tacit knowledge (internalization). As we know technology in the medical field is growing rapidly. Therefore, hospitals will be successful if they consistently create new knowledge and disseminate it to all of stakeholders in their organizations and quickly adopt their latest technologies and services, especially in the medical field.
Challenges faced by the Indonesian tertiary education in implementing mobile learning are mainly related to pedagogical problems rather than technological ones. This preliminary study has identified several problems faced by the tertiary students in their learning. This insight should inform how the design of a sustainable mobile learning ecosystem can be implemented in Indonesia.
In this paper, we highlighted the importance of User Experience (UX) sketching as one of the skillsets required for UX researchers in project development especially in low participatory design awareness countries like Malaysia. This is due to the results from UX research activities that are not perceived to be impactful by developers, designers and other stakeholders in digital transformation projects especially by the government that has been suffering from vendor-centric Request for Proposal (RFP) tender for the past 60 years. In consequences, time taken by developers to code from requirements captured by business analysts is longer than visual representation produced by UX or UI designers, which shortens the requirement gathering process. In conclusion, we found that UX sketching that produces visual representation of user needs to be effective especially in participatory design approach and to reduce user frustrations.
This paper introduces our early work on designing a remote application for tuberculous (TB) treatment. By using contextual inquiry, we obtain information and insights about the Directly Observed Therapy Short Course (DOTS) treatment for TB patients to understand their experiences during the treatment, together with the emotional states and feelings. We discuss how these findings help us in designing technological solutions for these patients.
This paper presents a multi-mobile system that allows users to come together with their mobile devices in an ad-hoc manner, and integrates together as one seamless display surface with multi-touch capabilities. Typically, gaps and bezels between the display causes inherent design problems to the multi-display structures. Two user studies have been conducted with two versions of prototypes design by observing groups of students performing an interactive drawing task. Solution for the bezels was implemented into an iterative prototype. The findings show gaps and disjointed objects were observed in the drawing outcomes, with the implementation of the Continuous Spatial Configuration, the gaps and spaces between the screens were eliminated.
Our research team developed a test question browser app for test-takers with print disabilities. This technology had to fully overcome three challenges: (1) the characteristic rigorousness and fairness demanded of East Asian university entrance exams, (2) problems inherent in assistive technologies for persons with print disabilities, and (3) the unique demands of the Japanese language in accurately displaying text and reading it aloud.