Search

Video analysis tools such as Tracker are used to study mechanical motion captured by photography. One can also imagine a similar tool for tracking thermal motion captured by thermography. Since its introduction to physics education, thermal imaging has been used to visualize phenomena that are invisible to the naked eye and teach a variety of physics concepts across different educational settings. But thermal cameras are still scarce in schools. Hence, videos recorded using thermal cameras such as those featured in “YouTube Physics” are suggested as alternatives. The downside is that students do not have interaction opportunities beyond playing those videos.

Digital sensors allow people to collect a large quantity of data in chemistry experiments. Using infrared thermography as an example, we show that this kind of data, in conjunction with videos that stream the chemical phenomena under observation from a vantage point, can be used to construct digital twins of experiments to support science education on the cloud in a visual and interactive fashion. Through digital twins, a significant part of laboratory experiences such as observation, analysis, and discussion can be delivered on a large scale. Thus, the technology can potentially broaden participation in experimental chemistry, especially for students and teachers in underserved communities who may lack the expertise, equipment, and supplies needed to conduct certain experiments. With a cloud platform that enables anyone to store, process, and disseminate experimental data via digital twins, our work also serves as an example to illuminate how the movement of open science, which is largely driven by data sharing, may be powered by technology to amplify its impacts on chemistry education.

There are three approaches to studying designers – through their cognitive profile, design behaviors, and design artifacts (e.g., quality). However, past work has rarely considered all three data domains together. Here we introduce and describe a framework for a comprehensive approach to engineering design, and discuss how the insights may benefit engineering design research and education. To demonstrate the proposed framework, we conducted an empirical study with a solar energy system design problem. Forty-six engineering students engaged in a week-long computer-aided design challenge that assessed their design behavior and artifacts, and completed a set of psychological tests to measure cognitive competencies. Using a machine learning approach consisting of k-means, hierarchical, and spectral clustering, designers were grouped by similarities on the psychological tests. Significant differences were revealed between designer groups in their sequential design behavior, suggesting that a designer's cognitive profile is related to how they engage in the design process.

In this paper, we present a predictive and generative design approach for supporting the conceptual design of product shapes in 3D meshes. We develop a target-embedding variational autoencoder (TEVAE) neural network architecture, which consists of two modules: (1) a training module with two encoders and one decoder (E2D network) and (2) an application module performing the generative design of new 3D shapes and the prediction of a 3D shape from its silhouette. We demonstrate the utility and effectiveness of the proposed approach in the design of 3D car body and mugs. The results show that our approach can generate a large number of novel 3D shapes and successfully predict a 3D shape based on a single silhouette sketch. The resulting 3D shapes are watertight polygon meshes with high-quality surface details, which have better visualization than voxels and point clouds, and are ready for downstream engineering evaluation (e.g., drag coefficient) and prototyping (e.g., 3D printing).

This multiple case study focused on the implementation of a computer-aided design (CAD) simulation to help students engage in engineering design to learn science concepts. Our findings describe thr...

Understanding the design process may reveal when and where resources should be focused and how engineers can better use tools, methods, and techniques to enhance the quality of designs and creative performance. The literature suggests the importance of iterative evaluation and reformulation in the engineering design process. The current study collected 111 high school students’ logs of designing an energy-saving house in Energy3D, a computer-aided design environment. Using a cross-lag model, we investigated the reciprocal relationship between students’ evaluation and reformulation behaviors and how these behaviors influence students’ design performance at the early, middle, and final design stages. The results suggest that there is a positive predictive relationship between students’ evaluation and reformulation process; reformulation positively predicts design performance and mediates the relationship between evaluation and design performance across time. These results provide empirical evidence of the importance of iterative evaluation and reformulation in the design process and implications for teachers and system designers to support students’ design.

Integrating engineering design into K-12 curricula is increasingly important as engineering has been incorporated into many STEM education standards. However, the ill-structured and open-ended nature of engineering design makes it difficult for an instructor to keep track of the design processes of all students simultaneously and provide personalized feedback on a timely basis. This study proposes a Bayesian network model to dynamically and automatically assess students’ engagement with engineering design tasks and to support formative feedback. Specifically, we applied a Bayesian network to 111 ninth-grade students’ process data logged by a computer-aided design software program that students used to solve an engineering design challenge. Evidence was extracted from the log files and fed into the Bayesian network to perform inferential reasoning and provide a barometer of their performance in the form of posterior probabilities. Results showed that the Bayesian network model was competent at predicting a student’s task performance. It performed well in both identifying students of a particular group (recall) and ensuring identified students were correctly labeled (precision). This study also suggests that Bayesian networks can be used to pinpoint a student’s strengths and weaknesses for applying relevant science knowledge to engineering design tasks. Future work of implementing this tool within the computer-aided design software will provide instructors a powerful tool to facilitate engineering design through automatically generating personalized feedback to students in real time.

In this paper, we demonstrate how machine learning could be used to quickly assess a student’s multimodal representational thinking. Multimodal representational thinking is the complex construct that encodes how students form conceptual, perceptual, graphical, or mathematical symbols in their mind. The augmented reality (AR) technology is adopted to diversify student’s representations. The AR technology utilized a low-cost, high-resolution thermal camera attached to a smartphone which allows students to explore the unseen world of thermodynamics. Ninth-grade students (N = 314) engaged in a prediction–observation–explanation (POE) inquiry cycle scaffolded to leverage the augmented observation provided by the aforementioned device. The objective is to investigate how machine learning could expedite the automated assessment of multimodal representational thinking of heat energy. Two automated text classification methods were adopted to decode different mental representations students used to explain their haptic perception, thermal imaging, and graph data collected in the lab. Since current automated assessment in science education rarely considers multilabel classification, we resorted to the help of the state-of-the-art deep learning technique—bidirectional encoder representations from transformers (BERT). The BERT model classified open-ended responses into appropriate categories with higher precision than the traditional machine learning method. The satisfactory accuracy of deep learning in assigning multiple labels is revolutionary in processing qualitative data. The complex student construct, such as multimodal representational thinking, is rarely mutually exclusive. The study avails a convenient technique to analyze qualitative data that does not satisfy the mutual-exclusiveness assumption. Implications and future studies are discussed.

Research on self-regulated learning (SRL) in engineering design is growing. While SRL is an effective way of learning, however, not all learners can regulate themselves successfully. There is a lac...

Background/objectives Acral lentiginous melanoma (ALM) is a melanoma subtype associated with atypical locations on the hands and feet and advanced disease at diagnosis. There is a limited understanding of whether the survival is similar for nail, non-nail, lower limb and upper limb ALM patients. We therefore explored clinicopathologic characteristics and melanoma-specific survival of ALM patients according to tumour location. Methods A prospectively collected cohort study was performed of all primary invasive cutaneous acral lentiginous melanomas with known thickness and tumour location reviewed at a tertiary referral centre over 21 years. Results A total of 101 ALM patients were reviewed from 1994 until 2016. The majority of cases (82/101) occurred on the feet. Hand ALMs were thicker and more likely to be ulcerated than feet ALMs (P = 0.05 and 0.02, respectively); however, survival was not statistically different between these two groups (univariate HR 0.48 P = 0.11, 95% CI, 0.20-1.17; multivariate HR 0.67 P = 0.40, 95% CI, 0.27-1.69, respectively). Non-nail ALM patients had longer survival when compared to nail ALM on univariate analysis (HR 0.40, 95% CI, 0.17 to 0.90) which was accounted for by Breslow thickness and ulceration (multivariate HR 0.56, 95% CI, 0.24 to 1.34). Conclusions The reduced melanoma-specific survival in nail ALM patients was likely due to their greater thickness and ulceration. Although hand ALMs are thicker and more frequently ulcerated, this is likely due to the higher proportion of nail ALMs present in this location.

Infrared (IR) thermography renders invisible infrared radiation with intuitive coloration in images and videos taken of objects, reactions, and processes. Educators can take advantage of this technology to extend students’ sensory perception of chemical reactions or processes that absorb or release heat in rich detail. In theory, IR thermography can be applied essentially universally for such analysis given that any change in thermal energy must result in, or from, the change of potential energy due to the interactions among atoms, molecules, and photons. Through the use of IR thermography, students can visualize otherwise invisible evidence of what is occurring on the molecular level in a variety of chemical process such as evaporative cooling, phase change, dissolution, titration, and enzymatic reactions. While not new, IR cameras are rapidly becoming affordable with models that connect easily with smartphones and tablets. The price decrease has opened the door for large-scale implementation in the chem...

With the development of learning-based embedding models, embedding vectors are widely used for analyzing and searching unstructured data. As vector collections exceed billion-scale, fully managed and horizontally scalable vector databases are necessary. In the past three years, through interaction with our 1200+ industry users, we have sketched a vision for the features that next-generation vector databases should have, which include long-term evolvability, tunable consistency, good elasticity, and high performance. We present Manu, a cloud native vector database that implements these features. It is difficult to integrate all these features if we follow traditional DBMS design rules. As most vector data applications do not require complex data models and strong data consistency, our design philosophy is to relax the data model and consistency constraints in exchange for the aforementioned features. Specifically, Manu firstly exposes the write-ahead log (WAL) and binlog as backbone services. Secondly, write components are designed as log publishers while all read-only analytic and search components are designed as independent subscribers to the log services. Finally, we utilize multi-version concurrency control (MVCC) and a delta consistency model to simplify the communication and cooperation among the system components. These designs achieve a low coupling among the system components, which is essential for elasticity and evolution. We also extensively optimize Manu for performance and usability with hardware-aware implementations and support for complex search semantics., Comment: 14 pages, 13 figures

Design thinking is essential to the success of a design process as it helps achieve the design goal by guiding design decision-making. Therefore, fundamentally understanding design thinking is vital for improving design methods, tools and theories. However, interpreting design thinking is challenging because it is a cognitive process that is hidden and intangible. In this paper, we represent design thinking as an intermediate layer between human designers’ thought processes and their design behaviors. To do so, this paper first identifies five design behaviors based on the current design theories. These behaviors include design action preference, one-step sequential behavior, contextual behavior, long-term sequential behavior, and reflective thinking behavior. Next, we develop computational methods to characterize each of the design behaviors. Particularly, we use design action distribution, first-order Markov chain, Doc2Vec, bi-directional LSTM autoencoder, and time gap distribution to characterize the five design behaviors. The characterization of the design behaviors through embedding techniques is essentially a latent representation of the design thinking, and we refer to it as design embeddings. After obtaining the embedding, an X-mean clustering algorithm is adopted to each of the embeddings to cluster designers. The approach is applied to data collected from a high school solar system design challenge. The clustering results show that designers follow several design patterns according to the corresponding behavior, which corroborates the effectiveness of using design embedding for design behavior clustering. The extraction of design embedding based on the proposed approach can be useful in other design research, such as inferring design decisions, predicting design performance, and identifying design actions identification.

Recently, there has been a pressing need to manage high-dimensional vector data in data science and AI applications. This trend is fueled by the proliferation of unstructured data and machine learning (ML), where ML models usually transform unstructured data into feature vectors for data analytics, e.g., product recommendation. Existing systems and algorithms for managing vector data have two limitations: (1) They incur serious performance issue when handling large-scale and dynamic vector data; and (2) They provide limited functionalities that cannot meet the requirements of versatile applications. This paper presents Milvus, a purpose-built data management system to efficiently manage large-scale vector data. Milvus supports easy-to-use application interfaces (including SDKs and RESTful APIs); optimizes for the heterogeneous computing platform with modern CPUs and GPUs; enables advanced query processing beyond simple vector similarity search; handles dynamic data for fast updates while ensuring efficient query processing; and distributes data across multiple nodes to achieve scalability and availability. We first describe the design and implementation of Milvus. Then we demonstrate the real-world use cases supported by Milvus. In particular, we build a series of 10 applications (e.g., image/video search, chemical structure analysis, COVID-19 dataset search, personalized recommendation, biological multi-factor authentication, intelligent question answering) on top of Milvus. Finally, we experimentally evaluate Milvus with a wide range of systems including two open source systems (Vearch and Microsoft SPTAG) and three commercial systems. Experiments show that Milvus is up to two orders of magnitude faster than the competitors while providing more functionalities. Now Milvus is deployed by hundreds of organizations worldwide and it is also recognized as an incubation-stage project of the LF AI & Data Foundation. Milvus is open-sourced at https://github.com/milvus-io/milvus.

Engineering design plays an important role in education. However, due to its open nature and complexity, providing timely support to students has been challenging using the traditional assessment m...

Phase transitions are everyday occurring phenomena, but students often find them difficult to comprehend, not least in terms of the principles of thermal physics. To be able to explain phase transitions in primary school, teachers need to understand various concepts and phenomena, such as condensation, evaporation, energy, and temperature. As energy is absorbed or released during phase transitions, changes in temperature can occur. Infrared (IR) cameras can thus be utilized to visually observe and explore surface phenomena such as condensation and evaporation. In line with the resources framework, we have designed a teaching sequence which involves both everyday experiences and observations through IR cameras, and which is designed to encourage students to leverage common resources associated with evaporation and condensation. In testing our teaching sequence, we presented three thermal phenomena to a group of pre-service teacher students. Two of these phenomena, namely, walking out of a shower and sitting in a sauna, were anchored in embodied experiences to hopefully activate the students' resources and to make the students pay attention to the thermally relevant aspects. The third phenomenon was less familiar, involving the condensation of water on a piece of paper. The result shows that the students managed to carry out the sequence with the three phenomena and applied an explanatory model across all three to consistently explain evaporation. However, the lack of a more general model of chemical bonding and an overreliance on the second law of thermodynamics seem to have acted as barriers for the students' forming of a coherent understanding of both evaporation and condensation.Phase transitions are everyday occurring phenomena, but students often find them difficult to comprehend, not least in terms of the principles of thermal physics. To be able to explain phase transitions in primary school, teachers need to understand various concepts and phenomena, such as condensation, evaporation, energy, and temperature. As energy is absorbed or released during phase transitions, changes in temperature can occur. Infrared (IR) cameras can thus be utilized to visually observe and explore surface phenomena such as condensation and evaporation. In line with the resources framework, we have designed a teaching sequence which involves both everyday experiences and observations through IR cameras, and which is designed to encourage students to leverage common resources associated with evaporation and condensation. In testing our teaching sequence, we presented three thermal phenomena to a group of pre-service teacher students. Two of these phenomena, namely, walking out of a shower and sittin...

In engineering systems design, designers iteratively go back and forth between different design stages to explore the design space and search for the best design solution that satisfies all design constraints. For complex design problems, human has shown surprising capability in effectively reducing the dimensionality of design space and quickly converging it to a reasonable range for algorithms to step in and continue the search process. Therefore, modeling how human designers make decisions in such a sequential design process can help discover beneficial design patterns, strategies, and heuristics, which are essential to the development of new algorithms embedded with human intelligence to augment the computational design. In this paper, we develop a deep learning-based approach to model and predict designers’ sequential decisions in the systems design context. The core of this approach is an integration of the function-behavior-structure (FBS) model for design process characterization and the long short-term memory unit (LSTM) model for deep leaning. This approach is demonstrated in two case studies on solar energy system design, and its prediction accuracy is evaluated benchmarking on several commonly used models for sequential design decisions, such as the Markov Chain model, the Hidden Markov Chain model, and the random sequence generation model. The results indicate that the proposed approach outperforms the other traditional models. This implies that during a system design task, designers are very likely to rely on both short-term and long-term memory of past design decisions in guiding their future decision-making in the design process. Our approach can support human–computer interactions in design and is general to be applied in other design contexts as long as the sequential data of design actions are available.

Augmented reality (AR) has great potential to radically change science education by making abstract science concepts visible and interactive. In this paper, we describe initial investigations into high school students' perceptions of learning science with an AR technology (i.e., SmartIR) through analyzing semi-structured interviews. SmartIR is an app that supports the investigation of science, such as thermodynamics. Specifically, it can show changes in thermal imaging over time and provides a data analytics function that visualizes data for analyzing and interpreting the changes. Our analysis of 31 interviews shows that students perceived the exploration of science phenomena with "fine details", including a full vision of second-by-second changes in thermal imaging, as helpful and engaging to understand science concepts. In future work, these findings will be triangulated with logging data of their interactions with SmartIR and student-generated lab reports.

Although reflection is a key behaviour of expert designers, it is often a challenging task for new designers. In addition, research on the reflectivity of student designers is limited. The purpose of this study is twofold: (1) to identify the levels of reflectivity while designing, and (2) to study the relationship between reflectivity and conceptions of informed design. We collected data from high school students engaged in an engineering design project. We developed a coding protocol to score levels of reflectivity in student reflections at three levels (low, medium, and high), and used the conceptions of design test to assess changes in student understanding of design activities. Using Wilcoxon signed-rank tests, we determined if students tended to select more ‘key’ design activities and fewer ‘distractors’ within each reflection group. We also performed McNemar’s tests to determine which specific design activities were important within each reflection group after the design project. The result...

This paper investigates iteration and fixation in design by mining digital footprints left by designers. High school students used computer-aided design software to create buildings in an urban area, with the goal of applying passive solar design techniques to ensure optimal solar gains of the buildings throughout a year. Students were required to complete three different designs. Fine-grained data including design actions, intermediate artifacts, and reflection notes were logged. Computational analytics programs were developed to mine the logs through three indicators: (a) frequency of the action of using energy analysis tools; (b) solar performance of the final designs; and (c) difference in solar performance between the prototype and final designs. Triangulating results from the indicators suggests three types of iteration—efficacious, inadequate and ineffective. Over half of the participants were detected as being efficacious iterative during the first design and becoming more and more fixated toward the end of the project, which resonates with previous findings on fixation effect among college students and professional designers. Overall the results demonstrate the power of applying computational analytics to investigate complex design processes. Findings from this work shed light on how to quantitatively assess and research student performance and processes during design projects.

Many pedagogical innovations aim to integrate engineering design and science learning. However, students frequently show little attempt or have difficulties in connecting their design projects with the underlying science. Drawing upon the Cultural-Historical Activity Theory, we argue that the design tools available in a learning environment implicitly shape knowledge development as they mediate students’ design actions. To explore the roles of tools in design-science integrated learning environments, this study investigated how secondary students’ tool-mediated design actions were linked with their science learning in a tool-rich design environment with minimal explicit guidance. Eighty-three ninth-grade students completed an energy-efficient home design challenge in a simulated environment for engineering design supported by rich design tools. Results showed that students substantially improved their knowledge as a result of designing with the tools. Further, their learning gains were positively associated with three types of design actions—representation, analysis, and reflection—measured by the cumulative counts of relevant computer logs. In addition, these design actions were linked with learning gains in ways that were consistent with their theoretical impacts on knowledge development. These findings suggest that, instead of being passive components in a learning environment, tools considerably shape design processes, and learning paths. As such, tools offer possibilities to help bridge the design-science gap. © 2017 The Authors. Journal of Research in Science Teaching Published by Wiley Periodicals, Inc. J Res Sci Teach 9999:1049–1096, 2017

Design thinking is often hidden and implicit, so empirical approach based on experiments and data-driven methods has been the primary way of doing such research. In support of empirical studies, design behavioral data which reflects design thinking becomes crucial, especially with the recent advances in data mining and machine learning techniques. In this paper, a research platform that supports data-driven design thinking studies is introduced based on a computer-aided design (cad) software for solar energy systems, energy3d, developed by the team. We demonstrate several key features of energy3d including a fine-grained design process logger, embedded design experiment and tutorials, and interactive cad interfaces and dashboard. These features make energy3d a capable testbed for a variety of research related to engineering design thinking and design theory, such as search strategies, design decision-making, artificial intelligent (AI) in design, and design cognition. Using a case study on an energy-plus home design challenge, we demonstrate how such a platform enables a complete research cycle of studying designers” sequential decision-making behaviors based on fine-grained design action data and unsupervised clustering methods. The results validate the utility of energy3d as a research platform and testbed in supporting future design thinking studies and provide domain-specific insights into new ways of integrating clustering methods and design process models (e.g., the function–behavior–structure model) for automatically clustering sequential design behaviors.