Papers by Lucienne Blessing
Proceedings of the Design Society, May 1, 2022
Using 61 stories from design educators from different countries, this paper presents (1) the desi... more Using 61 stories from design educators from different countries, this paper presents (1) the design competencies being fostered at different levels of education, (2) the practices (approaches, techniques, methods and tools) used to facilitate teaching and learning, (3) the 'non-design' competencies being fostered, and (4) the impact of COVID 19. Our findings highlight design education is not only used to teach students how to design, but also to kindle productive attitudes, behaviours and mindsets that give them the ability to address a wide range of challenges.
Countering Concurrent Login Attacks in “Just Tap” Push-based Authentication: A Redesign and Usability Evaluations
In this paper, we highlight a fundamental vulnerability associated with the widely adopted “Just ... more In this paper, we highlight a fundamental vulnerability associated with the widely adopted “Just Tap” push-based authentication in the face of a concurrency attack, and propose the method REPLICATE, a redesign to counter this vulnerability. In the concurrency attack, the attacker launches the login session at the same time the user initiates a session, and the user may be fooled, with high likelihood, into accepting the push notification which corresponds to the attacker's session, thinking it is their own. The attack stems from the fact that the login notification is not explicitly mapped to the login session running on the browser in the Just Tap approach. REPLICATE attempts to address this fundamental flaw by having the user approve the login attempt by replicating the information presented on the browser session over to the login notification, such as by moving a key in a particular direction, choosing a particular shape, etc. We report on the design and a systematic usability study of REPLICATE. Even without being aware of the vulnerability, in general, participants placed multiple variants of REPLICATE in competition to the Just Tap and fairly above PIN-based authentication.
Artificial intelligence for engineering design, analysis and manufacturing, Apr 18, 2016
Design fixation is a phenomenon with important significance to many fields of design due to the p... more Design fixation is a phenomenon with important significance to many fields of design due to the potential negative impacts it may have in design outcomes, especially during the ideation stage of the design process. The present study aims to provide a framework for understanding, or at least probing, design fixation by presenting a review of existing defixation approaches, as well as metrics that have been employed to understand and account for design fixation. This study also describes the results of two design by analogy (DbA) methods, WordTree and SCAMPER, to overcome design fixation in an experiment that involved 97 knowledge-domain experts. The study outcomes are at least twofold: a common framework of metrics and approaches to overcome design fixation in a wide range of design problems and nonintuitive results for DbA approaches in design fixation and other related creativity metrics. The application of WordTree and SCAMPER shows that both methods yield increased novelty compared to a control, where the SCAMPER results are significantly higher than WordTree. It is also found that WordTree mitigates design fixation whereas SCAMPER appears to be ineffective for this purpose but effective to generate an increased quantity of novel ideas. These results demonstrate that both DbA methods provide defixation capabilities and enhance designers' creativity during idea generation.
arXiv (Cornell University), May 11, 2020
Classification of crisis events, such as natural disasters, terrorist attacks and pandemics, is a... more Classification of crisis events, such as natural disasters, terrorist attacks and pandemics, is a crucial task to create early signals and inform relevant parties for spontaneous actions to reduce overall damage. Despite the crises, such as natural disaster, that can be predicted by professional institutions, certain events are first signaled by everyday citizens, i.e., civilians, such as the recent COVID-19 pandemics. Social media platforms such as Twitter often expose firsthand signals on such crises through high volume information exchange. In the case of Twitter, this corresponds to on average over half a billion tweets posted daily. Prior works proposed various crisis embeddings and classification using conventional Machine Learning and Neural Network models. However, none of the works perform crisis embedding and classification using state of the art attention-based deep neural networks models, such as Transformers and document-level contextual embeddings. This work proposes CrisisBERT, an end-to-end transformer-based model for two crisis classification tasks, namely crisis detection and crisis recognition, which shows promising results across accuracy and f1 scores. The proposed model demonstrates superior robustness over various benchmarks, as it shows marginal performance compromise while extending from 6 to 36 events with only 51.4% additional data points. We also propose Crisis2Vec, an attention-based, document-level contextual embedding architecture for crisis embedding, which achieves better performance than conventional crisis embedding methods such as Word2Vec and GloVe. To the best of our knowledge, our works are first to propose using transformer-based crisis classification and document-level contextual crisis embedding in the literature.
Artificial Intelligence for Competency Assessment in Design Education: A Review of Literature
Smart innovation, systems and technologies, 2023
An analysis of tiny design: design process for MicroElectroMechanical Systems (MEMS)
Design science, 2022
We review the scholarly contributions that utilise natural language processing (NLP) techniques t... more We review the scholarly contributions that utilise natural language processing (NLP) techniques to support the design process. Using a heuristic approach, we gathered 223 articles that are published in 32 journals within the period 1991-present. We present state-ofthe-art NLP in-and-for design research by reviewing these articles according to the type of natural language text sources: internal reports, design concepts, discourse transcripts, technical publications, consumer opinions and others. Upon summarising and identifying the gaps in these contributions, we utilise an existing design innovation framework to identify the applications that are currently being supported by NLP. We then propose a few methodological and theoretical directions for future NLP in-and-for design research.
Classification of crisis events, such as natural disasters, terrorist attacks and pandemics, is a... more Classification of crisis events, such as natural disasters, terrorist attacks and pandemics, is a crucial task to create early signals and inform relevant parties for spontaneous actions to reduce overall damage. Despite the crises, such as natural disaster, that can be predicted by professional institutions, certain events are first signaled by everyday citizens, i.e., civilians, such as the recent COVID-19 pandemics. Social media platforms such as Twitter often expose firsthand signals on such crises through high volume information exchange. In the case of Twitter, this corresponds to on average over half a billion tweets posted daily. Prior works proposed various crisis embeddings and classification using conventional Machine Learning and Neural Network models. However, none of the works perform crisis embedding and classification using state of the art attention-based deep neural networks models, such as Transformers and document-level contextual embeddings. This work proposes CrisisBERT, an end-to-end transformer-based model for two crisis classification tasks, namely crisis detection and crisis recognition, which shows promising results across accuracy and f1 scores. The proposed model demonstrates superior robustness over various benchmarks, as it shows marginal performance compromise while extending from 6 to 36 events with only 51.4% additional data points. We also propose Crisis2Vec, an attention-based, document-level contextual embedding architecture for crisis embedding, which achieves better performance than conventional crisis embedding methods such as Word2Vec and GloVe. To the best of our knowledge, our works are first to propose using transformer-based crisis classification and document-level contextual crisis embedding in the literature.
Proceedings of the Design Society, May 1, 2022
Design process modelling is well-founded in fields of mechanical engineering, and product design ... more Design process modelling is well-founded in fields of mechanical engineering, and product design and development but not in Building Design (BD). This paper looks at the selection process when choosing appropriate models for specific BD processes. The paper adapts process model selection criteria from Trauer's work and combines it with anecdotal evidence from the authors to select these models. The selection criteria were ranked, categorised, and applied to BD processes explained. Process models related to each selection criteria were then selected from backward snowballing of literature.
User perceptions on the adoption of smart energy management systems in the workplace: Design and policy implications
Energy research and social science, Jun 1, 2022
IOP conference series, Sep 1, 2019
There has been a widely documented phenomenon identifying an energy performance gap between the b... more There has been a widely documented phenomenon identifying an energy performance gap between the building's design and operational phases. This result has been attributed to the stochastic behaviours exhibited by the occupants, who are assumed to follow deterministic and routine schedules. With the recent advancements in smart monitoring technologies, the increasing affordability of wireless sensors has allowed researchers to collect detailed information on the occupants' dynamic behaviours. However, past applications of such technologies have been highly intrusive and limit the validity of the data collected due to the Hawthorne effect. Therefore, this paper proposes a non-intrusive data collection methodology using a comprehensive range of wireless smart meters, Bluetooth beacons, and questionnaires to capture the occupants' movement and appliance interaction patterns. The feasibility of the approach is demonstrated during a two-week data collection effort in a university office. By combining the occupants' presence with appliance energy consumption data, the authors were able to identify the occupants' appliance interaction patterns. An extension of this work includes the use of the data collected to identify different occupancy and appliance interaction profiles, which contributes to the development of an appliance interaction model that addresses the energy performance gap caused by occupants' appliance interaction.
Innovation by Design—A New Post-Graduate Program at SUTD
Smart innovation, systems and technologies, 2021
Design thinking has been gaining importance in training and education worldwide, but mostly in th... more Design thinking has been gaining importance in training and education worldwide, but mostly in the form of short courses and executive education initiatives. Although there is enormous value in short courses and executive education, they often lack the depth required to effectively practice the tools and methods learned and thus to realize design as a strategic investment for both companies and countries. The particular focus of this paper is Singapore. At the Singapore University of Technology and Design, a new Master of Engineering (MEng) program has been set up to address this perceived gap in education. The MEng program in Innovation by Design (MIbD) is a research-based program that takes design thinking and design innovation to the level of other post-graduate programs in other areas worldwide. The organization allows practitioners to participate part-time. Three terms into the program, the balance is extremely positive. The program has been very well received in several presentations to companies. It is expected that these students will either start their own business or easily find jobs in a context that is craving for people with this formal education: a broad view of design and the ability to implement it.
Maximum Yield—Minimal Time: Successful Strategies for Structured Interviews with the Public to Gain Design Insights
Smart innovation, systems and technologies, 2023
Plug-Mate: An IoT-based occupancy-driven plug load management system in smart buildings
Building and Environment, Sep 1, 2022
arXiv (Cornell University), Nov 27, 2021
We review the scholarly contributions that utilise Natural Language Processing (NLP) techniques t... more We review the scholarly contributions that utilise Natural Language Processing (NLP) techniques to support the design process. Using a heuristic approach, we gathered 223 articles that are published in 32 journals within the period 1991-present. We present state-of-the-art NLP in-and-for design research by reviewing these articles according to the type of natural language text sources: internal reports, design concepts, discourse transcripts, technical publications, consumer opinions, and others. Upon summarizing and identifying the gaps in these contributions, we utilise an existing design innovation framework to identify the applications that are currently being supported by NLP. We then propose a few methodological and theoretical directions for future NLP in-and-for design research.
Journal of Big Data, Sep 3, 2022
Occupational data mining and analysis is an important task in understanding today's industry and ... more Occupational data mining and analysis is an important task in understanding today's industry and job market. Various machine learning techniques are proposed and gradually deployed to improve companies' operations for upstream tasks, such as employee churn prediction, career trajectory modelling and automated interview. Job titles analysis and embedding, as the fundamental building blocks, are crucial upstream tasks to address these occupational data mining and analysis problems. A relevant occupational job title dataset is required to accomplish these tasks and towards that effort, we present the Industrial and Professional Occupations Dataset (IPOD). The IPOD dataset contains over 475,073 job titles based on 192,295 user profiles from a major professional networking site. To further facilitate these applications of occupational data mining and analysis, we propose Title2vec, a contextual job title vector representation using a bidirectional Language Model approach. To demonstrate the effectiveness of Title2vec, we also define an occupational Named Entity Recognition (NER) task and proposed two methods based on Conditional Random Fields (CRF) and bidirectional Long Short-Term Memory with CRF (LSTM-CRF). Using a large occupational job title dataset, experimental results show that both CRF and LSTM-CRF outperform human and baselines in both exact-match accuracy and F1 scores. The dataset and pre-trained embeddings have been made publicly available at https:// www. github. com/ junhua/ ipod.
This research investigates the effects of using stimuli, such as patents, on ideation outcomes, t... more This research investigates the effects of using stimuli, such as patents, on ideation outcomes, through the research questions: (a) What is the effect of stimuli on ideation outcomes? and (b) What is the effect of stimuli distance on ideation outcomes? An experiment to address these questions entails an ideation exercise involving 105 participants generating 226 concepts without or with patents and other resources. Significant findings are: (a) more concepts are generated with patents than without patents, (b) more concepts are generated with patents identified by participants on their own than using pre-chosen patents, (c) more concepts are generated using both patents and other resources than other degrees of stimulation, (d) concepts developed using both patents and other resources have higher novelty and quality than concepts generated without any stimuli, and (e) no significant correlations are observed between the proximity of stimuli to problem domains with novelty and quality of concepts. These results have practical implications on using stimuli to improve ideation outcomes for designers, design teams, and organisations, and motivate investigation into the stimuli used.
Knowledge-based Systems
Springer eBooks, 2009
Design-by-Analogy (DbA) is the process of developing solutions for design problems through the ma... more Design-by-Analogy (DbA) is the process of developing solutions for design problems through the mapping of attributes, relations and purposes that a source problem or situation may share (or at least partially share) with an existing target solution or situation. There is a range of available DbA methods that have been developed to assist designers during the ideation stage to identify potentially useful analogies to solve design problems. However, generally these methods have been developed and applied in the product domain rather than in the service and product service systems domains. The purpose of this article is to identify the characteristics and nature of products, services and product service systems; to provide an overview of existing DbA methods and their drivers to evaluate the potential transferability of DbA across domains.
Proceedings of the Design Society, Jun 19, 2023
Performance assessment plays a crucial role in engineering education. Yet most instructor assessm... more Performance assessment plays a crucial role in engineering education. Yet most instructor assessment focuses on student outcomes to analyse achievements. Although there is extensive research analysing student productions, however, few studies have explored assessment from instructor perspectives, especially when reporting their assessment practice. This study examines instructors' assessment of student performance through the lens of course review reports (CRRs). The CRRs were collected from 5 core undergraduate courses submitted for annual review and were related to the mappings of the measurable outcomes to performance indicators, assessment methods, and level of engagement. Regardless of the variability in reporting the student design experience, instructors' assessment and potential gaps, as well as strong existing correlations between some indicators and associated assessment methods, the study showed that the CRR may be a powerful and complementary approach to investigate the complexity of multidisciplinary design and design assessment.
Uploads
Papers by Lucienne Blessing