Brian Lim

National University of Singapore | NUS · Department of Computer Science

Generative AI models have shown impressive ability to produce images with text prompts, which could benefit creativity in visual art creation and self-expression. However, it is unclear how precisely the generated images express contexts and emotions from the input texts. We explored the emotional expressiveness of AI-generated images and developed...

With the increasing pervasiveness of Artificial Intelligence (AI), many visual analytics tools have been proposed to examine fairness, but they mostly focus on data scientist users. Instead, tackling fairness must be inclusive and involve domain experts with specialized tools and workflows. Thus, domain-specific visualizations are needed for algori...

With the increasing pervasiveness of Artificial Intelligence (AI), many visual analytics tools have been proposed to examine fairness, but they mostly focus on data scientist users. Instead, tackling fairness must be inclusive and involve domain experts with specialized tools and workflows. Thus, domain-specific visualizations are needed for algori...

Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic error (bias). Furthermore, the distortions persist despite model fine-tuning on images biased by different fact...

Machine learning models need to provide contrastive explanations, since people often seek to understand why a puzzling prediction occurred instead of some expected outcome. Current contrastive explanations are rudimentary comparisons between examples or raw features, which remain difficult to interpret, since they lack semantic meaning. We argue th...

Self-tracking can improve people's awareness of their unhealthy behaviors to provide insights towards behavior change. Prior work has explored how self-trackers reflect on their logged data, but it remains unclear how much they learn from the tracking feedback, and which information is more useful. Indeed, the feedback can still be overwhelming, an...

Feedback can help crowdworkers to improve their ideations. However, current feedback methods require human assessment from facilitators or peers. This is not scalable to large crowds. We propose Interpretable Directed Diversity to automatically predict ideation quality and diversity scores, and provide AI explanations - Attribution, Contrastive Att...

The successful deployment of artificial intelligence (AI) in many domains from healthcare to hiring requires their responsible use, particularly in model explanations and privacy. Explainable artificial intelligence (XAI) provides more information to help users to understand model decisions, yet this additional knowledge exposes additional risks fo...

Feature attribution is widely used in interpretable machine learning to explain how influential each measured input feature value is for an output inference. However, measurements can be uncertain, and it is unclear how the awareness of input uncertainty can affect the trust in explanations. We propose and study two approaches to help users to mana...

Feature attribution is widely used in interpretable machine learning to explain how influential each measured input feature value is for an output inference. However, measurements can be uncertain, and it is unclear how the awareness of input uncertainty can affect the trust in explanations. We propose and study two approaches to help users to mana...

Crowdsourcing can collect many diverse ideas by prompting ideators individually, but this can generate redundant ideas. Prior methods reduce redundancy by presenting peers' ideas or peer-proposed prompts, but these require much human coordination. We introduce Directed Diversity, an automatic prompt selection approach that leverages language model...

Many choice problems often involve multiple attributes which are mentally challenging, because only one attribute is neatly sorted while others could be randomly arranged. We hypothesize that perceiving approximately monotonic trends across multiple attributes is key to the overall interpretability of sorted results, because users can easily predic...

As data centers proliferate, their energy intensity deserves close attention. Always-on operations and growing usage for cloud and other backend processes make servers the fundamental driver of data center energy use. Yet servers’ power draw under real-world conditions is poorly understood. This paper explores characteristics of volume servers that...

Sparse Mobile Crowdsensing (MCS) has become a compelling approach to acquire and infer urban-scale sensing data. However, participants risk their location privacy when reporting data with their actual sensing positions. To address this issue, we propose a novel location obfuscation mechanism combining $\epsilon $ -differential-privacy and $\de...

This document presents the motivation, objectives and target audience, theme, submissions, structure as well as the expected outcome.

OD bundling is a promising method to identify key origin-destination (OD) patterns, but the bundling can mislead the interpretation of actual trajectories traveled. We present OD Morphing, an interactive OD bundling technique that improves geographical faithfulness to actual trajectories while preserving visual simplicity for OD patterns. OD Morphi...

Taxi sharing is a promising approach to reducing energy consumptions, utilizing limited taxi resources efficiently while preserving the interest of individuals. Only a few studies introduce meeting points that allow passengers to walk a short distance in order to reduce detour distances. These studies fail to locate a pick-up/drop-off point for eac...

Activity trackers are being deployed in large-scale physical activity intervention programs, but analyzing their data is difficult due to the large data size and complexity. As such large datasets of steps become more available, it is paramount to develop analysis methods to deeply interpret them to understand the variety and changing nature of hum...

From healthcare to criminal justice, artificial intelligence (AI) is increasingly supporting high-consequence human decisions. This has spurred the field of explainable AI (XAI). This paper seeks to strengthen empirical application-specific investigations of XAI by exploring theoretical underpinnings of human decision making, drawing from the field...

Smart systems that apply complex reasoning to make decisions and plan behavior are often difficult for users to understand. While research to make systems more explainable and therefore more intelligible and transparent is gaining pace, there are numerous issues and problems regarding these systems that demand further attention. The ExSS 2019 works...

We determined the relative strengths of association between 23 most commonly ordered laboratory tests and the adverse outcome as indicators of relative criticalness. The lowest and highest results for 23 most commonly ordered laboratory tests, 24 hours prior to death during critical care unit (CCU) stay or discharge from CCU were extracted from a p...

Support from family members is an important determinant of health. In this work, we probe opportunities for facilitating family support with TableChat, a chat-based mobile application for food journaling. Leveraging food as a test case of family support, TableChat virtually extends the experience of bonding over the dinner table. We surveyed 158 pe...

Recent studies in recommendation systems emphasize the significance of modeling latent features behind temporal evolution of user preference and item state to make relevant suggestions. However, static and dynamic behaviors and trends of users and items, which highly influence the feasibility of recommendations, were not adequately addressed in pre...

This paper proposes a novel task allocation framework, PSTasker, for participatory sensing (PS), which aims to maximize the overall system utility on PS platform by coordinating the allocation of multiple tasks. While existing studies mainly optimize the task allocation from the perspective of the task organizer (e.g., maximizing coverage or minimi...

Advances in artificial intelligence, sensors and big data management have far-reaching societal impacts. As these systems augment our everyday lives, it becomes increasing-ly important for people to understand them and remain in control. We investigate how HCI researchers can help to develop accountable systems by performing a literature analysis o...

Food logging can help users understand their food choices and encourage healthier eating habits. However, current apps still pose many usability challenges, including tedious manual text entry of food names. Recently, advances in computer vision and deep learning are enabling automatic food recognition for instant and convenient logging. However, a...

With this workshop, we seek to provide a forum for exchanging design principles, programming techniques, toolkits and insights derived from real world studies towards building intelligible and user-controllable pervaive computing systems. Drawing upon the state-of-the-art, our goal is to refine existing and identify new directions for research in i...

Smart environments are improving their performance and services by increasingly using ubiquitous sensing and complex inference mechanisms. However, this comes at a cost of reduced intelligibility, user trust and control. The Intelligibility Toolkit was developed to support the automatic generation and provision of explanations to help users underst...

Ubiquitous applications and smart environment technologies are complex to deploy, manage and use. Intelligibility, in ubiquitous computing applications, explains to users what a system did (outputs) and why it did it (inputs or contextual information). Making software more intelligible can reduce the complexity of a system for users. This paper pre...

conclusions, or recommendations expressed in this material are those of the author and do not necessarily reflect Intelligibility has been proposed to help end-users understand context-aware applications with their complex inference and implicit sensing. Usable explanations can be generated and designed to improve user understanding. However, will...

Context-aware applications use sensing and inference to attempt to determine users' contexts, and take appropriate action. However, they are prone to uncertainty, and this may compromise the trust users have in them. Providing intelligibility has been proposed to help explain to users how context-aware applications work in order to improve user imp...

Context-aware applications are increasingly complex and autonomous, and research has indicated that explanations can help users better understand and ultimately trust their autonomous behavior. However, it is still unclear how to effectively present and provide these explanations. This work builds on previous work to make context-aware applications...

We present Pediluma, a shoe accessory that tracks and visualizes the wearer's physical activity by varying the intensity of a lighted enclosure. In particular, the more physically active the wearer is, the more the device glows. We hoped the desire to maintain a positive, "glowing" state would encourage users to engage in more physical activity. We...

Since context-aware applications use implicit sensing and increasingly complex decision making, they may make mistakes or users may misunderstand their actions. This may hinder trust and adoption of context-aware applications. We hypothesize that making these applications intelligible by explaining themselves to users would help counter this lack o...

Context-aware applications should be intelligible so users can better understand how they work and improve their trust in them. However, providing intelligibility is non-trivial and requires the developer to understand how to generate explanations from application decision models. Furthermore, users need different types of explanations and this com...

In order to study the effect supporting awareness of a colleague's activity on a collaborator's communication intentions, we developed ActivitySpotter. It is a research tool and awareness display that determines a user's current activity through a semantic analysis of documents s/he accesses and shares this information with collaborators. We ran a...

Intelligibility can help expose the inner workings and inputs of context-aware applications that tend to be opaque to users due to their implicit sensing and actions. However, users may not be interested in all the information that the applications can produce. Using scenarios of four real-world applications that span the design space of context-aw...

Advances in electronics have brought the promise of wear- able computers to near reality. Previous research has inves- tigated where computers can be located on the human body - critical for successful development and acceptance. How- ever, for a location to be truly useful, it needs to not only be accessible for interaction, socially acceptable, c...

Intercultural collaboration is often hampered by the manner in which teams communicate, or fail to com-municate, their ideas, concerns, and feelings. Computer-mediated communication and the virtual nature of collaboration tend to exacerbate such communication issues into problems of conversation dominance, misattribution, and group conflict. New co...

Context-aware intelligent systems employ implicit inputs, and make decisions based on complex rules and machine learning models that are rarely clear to users. Such lack of system intelligibility can lead to loss of user trust, satisfaction and acceptance of these systems. However, automatically providing explanations about a system"s decision proc...

Wireless hotspots are permeating the globe bringing interesting services and spontaneous connectivity to mobile users. In order to enable the elderly and disabled to be fully integrated into the society, it's of paramount importance to build a pervasive assistive environment where assistive services can be automatically discovered and easily access...

People have the desire to be always informed by the information to their importance everywhere and anytime. However, for some casual and relaxing occasions such as in home environment, information access and exhibition should be offered in a non-distracting and non-disruptive manner. To facilitate this goal and make use of embedded displays in smar...

With mobile devices and wireless hotspots becoming more prevalent, customers can desire greater access to media and services that can be achieved from the marrying of these two technologies. However, often existing devices need to be augmented with hardware and software to achieve this connectivity, and the existing services are heterogeneous and i...

Many physical spaces such as homes, museums, airports and shopping malls are being augmented with computers, sensors, wireless hotspots to provide digital content and services. However, often specialized hardware and software are needed to access the services available in a particular space. This paper proposes a lightweight service framework which...

Wireless hotspots are permeating the globe bringing interesting services and spontaneous connectivity to mobile users. In order to enable the elderly and disabled to be fully integrated into the society, it’s of paramount importance to build a pervasive assistive environment where assistive services can be automatically discovered and easily access...

The solving for the shape of a raindrop, as reported by [1] is repeated in this project. Its governing equations are derived from basic equations, and the resulting solutions provided by numerical computations. The computer program procedure is also discussed. A comparison of the resulting model is done against the original paper [1] and with a pho...