2022
11.
Ananth Kalyanaraman; Margaret Burnett; Alan Fern; Lav Khot; Joshua Viers
Special report: The AgAID AI institute for transforming workforce and decision support in agriculture Journal Article
In: Computers and Electronics in Agriculture, vol. 197, pp. 106944, 2022, ISSN: 0168-1699.
Abstract | Links | BibTeX | Tags: AI, Education, Farm Ops, Humans, Labor, Water
@article{kalyanaraman_special_2022,
title = {Special report: The AgAID AI institute for transforming workforce and decision support in agriculture},
author = { Ananth Kalyanaraman and Margaret Burnett and Alan Fern and Lav Khot and Joshua Viers},
url = {https://www.sciencedirect.com/science/article/pii/S0168169922002617},
doi = {10.1016/j.compag.2022.106944},
issn = {0168-1699},
year = {2022},
date = {2022-06-01},
urldate = {2022-06-01},
journal = {Computers and Electronics in Agriculture},
volume = {197},
pages = {106944},
abstract = {Tackling the grand challenges of 21st century agriculture (Ag) will require a fundamental shift in the way we envision the role of artificial intelligence (AI) technologies, and in the way we build agricultural AI systems. This shift is needed especially for complex, high-value agricultural ecosystems such as those in the Western U.S., where 300+ crops are grown. Farmers and policy makers in this region face variable profitability, major crop loss and poor crop quality owing to several challenges, including increased labor costs and shortages of skilled workers, weather and management uncertainties, and water scarcity. While AI is expected to be a significant tool for addressing these challenges, AI capabilities must be expanded and will need to account for human input and human behavior \textendash calling for a strong AI-Ag coalition that also creates new opportunities to achieve sustained innovation. Accomplishing this goal goes well beyond the scope of any specific research project or disciplinary silo and requires a more holistic transdisciplinary effort in research, development, and training. To respond to this need, we initiated the AgAID Institute, a multi-institution, transdisciplinary National AI Research Institute that will build new public-private partnerships involving a diverse range of stakeholders in both agriculture and AI. The institute focuses its efforts on providing AI solutions to specialty crop agriculture where the challenges pertaining to water availability, climate variability and extreme weather, and labor shortages, are all significantly pronounced. Our approach to all AgAID Institute activities is being guided by three cross-cutting principles: (i) adoption as a first principle in AI design; (ii) adaptability to changing environments and scales, and (iii) amplification of human skills and machine efficiency. The AgAID Institute is conducting a range of activities including: using agricultural AI applications as testbeds for developing innovative AI technologies and workflows; laying the technological foundations for climate-smart agriculture; serving as a nexus for culturally inclusive collaborative and transdisciplinary learning and knowledge co-production; preparing the next generation workforce for careers at the intersection of Ag and AI technology; and facilitating technology adoption and transfer.},
keywords = {AI, Education, Farm Ops, Humans, Labor, Water},
pubstate = {published},
tppubtype = {article}
}
Tackling the grand challenges of 21st century agriculture (Ag) will require a fundamental shift in the way we envision the role of artificial intelligence (AI) technologies, and in the way we build agricultural AI systems. This shift is needed especially for complex, high-value agricultural ecosystems such as those in the Western U.S., where 300+ crops are grown. Farmers and policy makers in this region face variable profitability, major crop loss and poor crop quality owing to several challenges, including increased labor costs and shortages of skilled workers, weather and management uncertainties, and water scarcity. While AI is expected to be a significant tool for addressing these challenges, AI capabilities must be expanded and will need to account for human input and human behavior – calling for a strong AI-Ag coalition that also creates new opportunities to achieve sustained innovation. Accomplishing this goal goes well beyond the scope of any specific research project or disciplinary silo and requires a more holistic transdisciplinary effort in research, development, and training. To respond to this need, we initiated the AgAID Institute, a multi-institution, transdisciplinary National AI Research Institute that will build new public-private partnerships involving a diverse range of stakeholders in both agriculture and AI. The institute focuses its efforts on providing AI solutions to specialty crop agriculture where the challenges pertaining to water availability, climate variability and extreme weather, and labor shortages, are all significantly pronounced. Our approach to all AgAID Institute activities is being guided by three cross-cutting principles: (i) adoption as a first principle in AI design; (ii) adaptability to changing environments and scales, and (iii) amplification of human skills and machine efficiency. The AgAID Institute is conducting a range of activities including: using agricultural AI applications as testbeds for developing innovative AI technologies and workflows; laying the technological foundations for climate-smart agriculture; serving as a nexus for culturally inclusive collaborative and transdisciplinary learning and knowledge co-production; preparing the next generation workforce for careers at the intersection of Ag and AI technology; and facilitating technology adoption and transfer.
12.
Taha Belkhouja; Yan Yan; Janardhan Rao Doppa
Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis Journal Article
In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 6, pp. 6055–6063, 2022, ISSN: 2374-3468, 2159-5399.
Abstract | Links | BibTeX | Tags: AI
@article{belkhouja_training_2022,
title = {Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis},
author = { Taha Belkhouja and Yan Yan and Janardhan Rao Doppa},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/20552},
doi = {10.1609/aaai.v36i6.20552},
issn = {2374-3468, 2159-5399},
year = {2022},
date = {2022-06-01},
urldate = {2022-06-01},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
volume = {36},
number = {6},
pages = {6055--6063},
abstract = {Despite the success of deep neural networks (DNNs) for real-world applications over time-series data such as mobile health, little is known about how to train robust DNNs for time-series domain due to its unique characteristics compared to images and text data In this paper, we fill this gap by proposing a novel algorithmic framework referred as RObust Training for Time-Series (ROTS) to create robust deep models for time-series classification tasks. Specifically, we formulate a min-max optimization problem over the model parameters by explicitly reasoning about the robustness criteria in terms of additive perturbations to time-series inputs measured by the global alignment kernel (GAK) based distance. We also show the generality and advantages of our formulation using the summation structure over time-series alignments by relating both GAK and dynamic time warping (DTW). This problem is an instance of a family of compositional min-max optimization problems, which are challenging and open with unclear theoretical guarantee. We propose a principled stochastic compositional alternating gradient descent ascent (SCAGDA) algorithm for this family of optimization problems. Unlike traditional methods for timeseries that require approximate computation of distance measures, SCAGDA approximates the GAK based distance onthe-fly using a moving average approach. We theoretically analyze the convergence rate of SCAGDA and provide strong theoretical support for the estimation of GAK based distance. Our experiments on real-world benchmarks demonstrate that ROTS creates more robust deep models when compared to adversarial training using prior methods that rely on data augmentation or new definitions of loss functions. We also demonstrate the importance of GAK for time-series data over the Euclidean distance.},
keywords = {AI},
pubstate = {published},
tppubtype = {article}
}
Despite the success of deep neural networks (DNNs) for real-world applications over time-series data such as mobile health, little is known about how to train robust DNNs for time-series domain due to its unique characteristics compared to images and text data In this paper, we fill this gap by proposing a novel algorithmic framework referred as RObust Training for Time-Series (ROTS) to create robust deep models for time-series classification tasks. Specifically, we formulate a min-max optimization problem over the model parameters by explicitly reasoning about the robustness criteria in terms of additive perturbations to time-series inputs measured by the global alignment kernel (GAK) based distance. We also show the generality and advantages of our formulation using the summation structure over time-series alignments by relating both GAK and dynamic time warping (DTW). This problem is an instance of a family of compositional min-max optimization problems, which are challenging and open with unclear theoretical guarantee. We propose a principled stochastic compositional alternating gradient descent ascent (SCAGDA) algorithm for this family of optimization problems. Unlike traditional methods for timeseries that require approximate computation of distance measures, SCAGDA approximates the GAK based distance onthe-fly using a moving average approach. We theoretically analyze the convergence rate of SCAGDA and provide strong theoretical support for the estimation of GAK based distance. Our experiments on real-world benchmarks demonstrate that ROTS creates more robust deep models when compared to adversarial training using prior methods that rely on data augmentation or new definitions of loss functions. We also demonstrate the importance of GAK for time-series data over the Euclidean distance.
13.
Mariam Guizani; Igor Steinmacher; Jillian Emard; Abrar Fallatah; Margaret Burnett; Anita Sarma
How to Debug Inclusivity Bugs? A Debugging Process with Information Architecture Inproceedings
In: 2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering in Society (ICSE-SEIS), pp. 90–101, IEEE Computer Society, 2022, ISBN: 978-1-66549-594-3.
Abstract | Links | BibTeX | Tags: Human-Computer Interaction
@inproceedings{guizani_how_2022,
title = {How to Debug Inclusivity Bugs? A Debugging Process with Information Architecture},
author = { Mariam Guizani and Igor Steinmacher and Jillian Emard and Abrar Fallatah and Margaret Burnett and Anita Sarma},
url = {https://www.computer.org/csdl/proceedings-article/icse-seis/2022/959400a090/1EmrhU2EkcE},
doi = {10.1109/ICSE-SEIS55304.2022.9794009},
isbn = {978-1-66549-594-3},
year = {2022},
date = {2022-05-01},
urldate = {2022-05-01},
booktitle = {2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering in Society (ICSE-SEIS)},
pages = {90--101},
publisher = {IEEE Computer Society},
abstract = {Although some previous research has found ways to find inclusivity bugs (biases in software that introduce inequities), little attention has been paid to how to go about fixing such bugs. Without a process to move from finding to fixing, acting upon such findings is an ad-hoc activity, at the mercy of the skills of each individual developer. To address this gap, we created Why/Where/Fix, a systematic inclusivity debugging process whose inclusivity fault localization harnesses Information Architecture(IA)-the way user-facing information is organized, structured and labeled. We then conducted a multi-stage qualitative empirical evaluation of the effectiveness of Why/Where/Fix, using an Open Source Software (OSS) project\'s infrastructure as our setting. In our study, the OSS project team used the Why/Where/Fix process to find inclusivity bugs, localize the IA faults behind them, and then fix the IA to remove the inclusivity bugs they had found. Our results showed that using Why/Where/Fix reduced the number of inclusivity bugs that OSS newcomer participants experienced by 90\%. Diverse teams have been shown to be more productive as well as more innovative. One form of diversity, cognitive diversity - differences in cognitive styles - helps generate diversity of thoughts. However, cognitive diversity is often not supported in software tools. This means that these tools are not inclusive of individuals with different cognitive styles (e.g., those who like to learn through process vs. those who learn by tinkering), which burdens these individuals with a cognitive \“tax\” each time they use the tool. In this work, we present an approach that enables software developers to: (1) evaluate their tools, especially those that are information-heavy, to find \“inclusivity bugs\”- cases where diverse cognitive styles are unsupported, (2) find where in the tool these bugs lurk, and (3) fix these bugs. Our evaluation in an open source project shows that by following this approach developers were able to reduce inclusivity bugs in their projects by 90\%.},
keywords = {Human-Computer Interaction},
pubstate = {published},
tppubtype = {inproceedings}
}
Although some previous research has found ways to find inclusivity bugs (biases in software that introduce inequities), little attention has been paid to how to go about fixing such bugs. Without a process to move from finding to fixing, acting upon such findings is an ad-hoc activity, at the mercy of the skills of each individual developer. To address this gap, we created Why/Where/Fix, a systematic inclusivity debugging process whose inclusivity fault localization harnesses Information Architecture(IA)-the way user-facing information is organized, structured and labeled. We then conducted a multi-stage qualitative empirical evaluation of the effectiveness of Why/Where/Fix, using an Open Source Software (OSS) project's infrastructure as our setting. In our study, the OSS project team used the Why/Where/Fix process to find inclusivity bugs, localize the IA faults behind them, and then fix the IA to remove the inclusivity bugs they had found. Our results showed that using Why/Where/Fix reduced the number of inclusivity bugs that OSS newcomer participants experienced by 90%. Diverse teams have been shown to be more productive as well as more innovative. One form of diversity, cognitive diversity - differences in cognitive styles - helps generate diversity of thoughts. However, cognitive diversity is often not supported in software tools. This means that these tools are not inclusive of individuals with different cognitive styles (e.g., those who like to learn through process vs. those who learn by tinkering), which burdens these individuals with a cognitive “tax” each time they use the tool. In this work, we present an approach that enables software developers to: (1) evaluate their tools, especially those that are information-heavy, to find “inclusivity bugs”- cases where diverse cognitive styles are unsupported, (2) find where in the tool these bugs lurk, and (3) fix these bugs. Our evaluation in an open source project shows that by following this approach developers were able to reduce inclusivity bugs in their projects by 90%.
14.
Anurag Koul; Mariano Phielipp; Alan Fern
Offline Policy Comparison with Confidence: Benchmarks and Baselines Miscellaneous
2022, (arXiv:2205.10739 [cs]).
Abstract | Links | BibTeX | Tags: AI
@misc{koul_offline_2022,
title = {Offline Policy Comparison with Confidence: Benchmarks and Baselines},
author = { Anurag Koul and Mariano Phielipp and Alan Fern},
url = {http://arxiv.org/abs/2205.10739},
doi = {10.48550/arXiv.2205.10739},
year = {2022},
date = {2022-05-01},
urldate = {2022-05-01},
publisher = {arXiv},
abstract = {Decision makers often wish to use offline historical data to compare sequential-action policies at various world states. Importantly, computational tools should produce confidence values for such offline policy comparison (OPC) to account for statistical variance and limited data coverage. Nevertheless, there is little work that directly evaluates the quality of confidence values for OPC. In this work, we address this issue by creating benchmarks for OPC with Confidence (OPCC), derived by adding sets of policy comparison queries to datasets from offline reinforcement learning. In addition, we present an empirical evaluation of the risk versus coverage trade-off for a class of model-based baselines. In particular, the baselines learn ensembles of dynamics models, which are used in various ways to produce simulations for answering queries with confidence values. While our results suggest advantages for certain baseline variations, there appears to be significant room for improvement in future work.},
note = {arXiv:2205.10739 [cs]},
keywords = {AI},
pubstate = {published},
tppubtype = {misc}
}
Decision makers often wish to use offline historical data to compare sequential-action policies at various world states. Importantly, computational tools should produce confidence values for such offline policy comparison (OPC) to account for statistical variance and limited data coverage. Nevertheless, there is little work that directly evaluates the quality of confidence values for OPC. In this work, we address this issue by creating benchmarks for OPC with Confidence (OPCC), derived by adding sets of policy comparison queries to datasets from offline reinforcement learning. In addition, we present an empirical evaluation of the risk versus coverage trade-off for a class of model-based baselines. In particular, the baselines learn ensembles of dynamics models, which are used in various ways to produce simulations for answering queries with confidence values. While our results suggest advantages for certain baseline variations, there appears to be significant room for improvement in future work.
15.
Taymaz Homayouni; Akram Gholami; Arash Toudeshki; Leili Afsah-Hejri; Reza Ehsani
Estimation of proper shaking parameters for pistachio trees based on their trunk size Journal Article
In: Biosystems Engineering, vol. 216, pp. 121–131, 2022, ISSN: 1537-5110.
Abstract | Links | BibTeX | Tags: Labor
@article{homayouni_estimation_2022,
title = {Estimation of proper shaking parameters for pistachio trees based on their trunk size},
author = { Taymaz Homayouni and Akram Gholami and Arash Toudeshki and Leili Afsah-Hejri and Reza Ehsani},
url = {https://www.sciencedirect.com/science/article/pii/S1537511022000411},
doi = {10.1016/j.biosystemseng.2022.02.008},
issn = {1537-5110},
year = {2022},
date = {2022-04-01},
urldate = {2022-04-01},
journal = {Biosystems Engineering},
volume = {216},
pages = {121--131},
abstract = {Trunk shaking is the most common mechanical harvesting system for harvesting pistachio. Harvesting machine operators often subjectively decide how to set the shaking parameters such as frequency and duration and this requires experience. The main objectives of this study were to evaluate the effect of tree morphology and shaking parameters such as trunk size and shaking pattern on the energy distribution through the branches and to optimise the shaking intensity of individual pistachio trees based on a tree-specific feedback loop. Wireless 3D accelerometer sensors were built and used to measure vibration transmission through the tree canopy at different locations and to monitor the energy transmission between the machine shaker head and the tree trunk. Thirty trees were selected for this study and were divided into three groups based on the trunk circumference size. To study the effect of a shaking pattern on the vibration transmission through the tree, four shaking patterns were selected and tested. Shaking duration was measured and it showed an average of 30% longer time compared to the shaking pattern duration. The effect of all four shaking patterns was analysed using continuous wavelet transform. The responses of trees were analysed and the optimum shaking intensity for each tree was determined. A model was developed to estimate the optimum shaking intensity for pistachio trees based on their trunk size. The model showed that 37, 57, and 65% are the optimum shaking intensity percentages for small, medium, and large trees, respectively.},
keywords = {Labor},
pubstate = {published},
tppubtype = {article}
}
Trunk shaking is the most common mechanical harvesting system for harvesting pistachio. Harvesting machine operators often subjectively decide how to set the shaking parameters such as frequency and duration and this requires experience. The main objectives of this study were to evaluate the effect of tree morphology and shaking parameters such as trunk size and shaking pattern on the energy distribution through the branches and to optimise the shaking intensity of individual pistachio trees based on a tree-specific feedback loop. Wireless 3D accelerometer sensors were built and used to measure vibration transmission through the tree canopy at different locations and to monitor the energy transmission between the machine shaker head and the tree trunk. Thirty trees were selected for this study and were divided into three groups based on the trunk circumference size. To study the effect of a shaking pattern on the vibration transmission through the tree, four shaking patterns were selected and tested. Shaking duration was measured and it showed an average of 30% longer time compared to the shaking pattern duration. The effect of all four shaking patterns was analysed using continuous wavelet transform. The responses of trees were analysed and the optimum shaking intensity for each tree was determined. A model was developed to estimate the optimum shaking intensity for pistachio trees based on their trunk size. The model showed that 37, 57, and 65% are the optimum shaking intensity percentages for small, medium, and large trees, respectively.
16.
Taha Belkhouja; Janardhan Rao Doppa
Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features Journal Article
In: Journal of Artificial Intelligence Research, vol. 73, pp. 1435–1471, 2022, ISSN: 1076-9757.
Abstract | Links | BibTeX | Tags: AI
@article{belkhouja_adversarial_2022,
title = {Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features},
author = { Taha Belkhouja and Janardhan Rao Doppa},
url = {https://www.jair.org/index.php/jair/article/view/13543},
doi = {10.1613/jair.1.13543},
issn = {1076-9757},
year = {2022},
date = {2022-04-01},
urldate = {2022-04-01},
journal = {Journal of Artificial Intelligence Research},
volume = {73},
pages = {1435--1471},
abstract = {Time-series data arises in many real-world applications (e.g., mobile health) and deep neural networks (DNNs) have shown great success in solving them. Despite their success, little is known about their robustness to adversarial attacks. In this paper, we propose a novel adversarial framework referred to as Time-Series Attacks via STATistical Features (TSA-STAT). To address the unique challenges of time-series domain, TSA-STAT employs constraints on statistical features of the time-series data to construct adversarial examples. Optimized polynomial transformations are used to create attacks that are more effective (in terms of successfully fooling DNNs) than those based on additive perturbations. We also provide certified bounds on the norm of the statistical features for constructing adversarial examples. Our experiments on diverse real-world benchmark datasets show the effectiveness of TSA-STAT in fooling DNNs for time-series domain and in improving their robustness.},
keywords = {AI},
pubstate = {published},
tppubtype = {article}
}
Time-series data arises in many real-world applications (e.g., mobile health) and deep neural networks (DNNs) have shown great success in solving them. Despite their success, little is known about their robustness to adversarial attacks. In this paper, we propose a novel adversarial framework referred to as Time-Series Attacks via STATistical Features (TSA-STAT). To address the unique challenges of time-series domain, TSA-STAT employs constraints on statistical features of the time-series data to construct adversarial examples. Optimized polynomial transformations are used to create attacks that are more effective (in terms of successfully fooling DNNs) than those based on additive perturbations. We also provide certified bounds on the norm of the statistical features for constructing adversarial examples. Our experiments on diverse real-world benchmark datasets show the effectiveness of TSA-STAT in fooling DNNs for time-series domain and in improving their robustness.
17.
Jonathan Dodge; Andrew A. Anderson; Matthew Olson; Rupika Dikkala; Margaret Burnett
How Do People Rank Multiple Mutant Agents? Inproceedings
In: 27th International Conference on Intelligent User Interfaces, pp. 191–211, Association for Computing Machinery, New York, NY, USA, 2022, ISBN: 978-1-4503-9144-3.
Abstract | Links | BibTeX | Tags: AI, Human-Computer Interaction
@inproceedings{dodge_how_2022,
title = {How Do People Rank Multiple Mutant Agents?},
author = { Jonathan Dodge and Andrew A. Anderson and Matthew Olson and Rupika Dikkala and Margaret Burnett},
url = {https://doi.org/10.1145/3490099.3511115},
doi = {10.1145/3490099.3511115},
isbn = {978-1-4503-9144-3},
year = {2022},
date = {2022-03-01},
urldate = {2022-03-01},
booktitle = {27th International Conference on Intelligent User Interfaces},
pages = {191--211},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
series = {IUI '22},
abstract = {Faced with several AI-powered sequential decision-making systems, how might someone choose on which to rely? For example, imagine car buyer Blair shopping for a self-driving car, or developer Dillon trying to choose an appropriate ML model to use in their application. Their first choice might be infeasible (i.e., too expensive in money or execution time), so they may need to select their second or third choice. To address this question, this paper presents: 1) Explanation Resolution, a quantifiable direct measurement concept; 2) a new XAI empirical task to measure explanations: “the Ranking Task”; and 3) a new strategy for inducing controllable agent variations\textemdashMutant Agent Generation. In support of those main contributions, it also presents 4) novel explanations for sequential decision-making agents; 5) an adaptation to the AAR/AI assessment process; and 6) a qualitative study around these devices with 10 participants to investigate how they performed the Ranking Task on our mutant agents, using our explanations, and structured by AAR/AI. From an XAI researcher perspective, just as mutation testing can be applied to any code, mutant agent generation can be applied to essentially any neural network for which one wants to evaluate an assessment process or explanation type. As to an XAI user’s perspective, the participants ranked the agents well overall, but showed the importance of high explanation resolution for close differences between agents. The participants also revealed the importance of supporting a wide diversity of explanation diets and agent “test selection” strategies.},
keywords = {AI, Human-Computer Interaction},
pubstate = {published},
tppubtype = {inproceedings}
}
Faced with several AI-powered sequential decision-making systems, how might someone choose on which to rely? For example, imagine car buyer Blair shopping for a self-driving car, or developer Dillon trying to choose an appropriate ML model to use in their application. Their first choice might be infeasible (i.e., too expensive in money or execution time), so they may need to select their second or third choice. To address this question, this paper presents: 1) Explanation Resolution, a quantifiable direct measurement concept; 2) a new XAI empirical task to measure explanations: “the Ranking Task”; and 3) a new strategy for inducing controllable agent variations—Mutant Agent Generation. In support of those main contributions, it also presents 4) novel explanations for sequential decision-making agents; 5) an adaptation to the AAR/AI assessment process; and 6) a qualitative study around these devices with 10 participants to investigate how they performed the Ranking Task on our mutant agents, using our explanations, and structured by AAR/AI. From an XAI researcher perspective, just as mutation testing can be applied to any code, mutant agent generation can be applied to essentially any neural network for which one wants to evaluate an assessment process or explanation type. As to an XAI user’s perspective, the participants ranked the agents well overall, but showed the importance of high explanation resolution for close differences between agents. The participants also revealed the importance of supporting a wide diversity of explanation diets and agent “test selection” strategies.
18.
Roli Khanna; Jonathan Dodge; Andrew Anderson; Rupika Dikkala; Jed Irvine; Zeyad Shureih; Kin-Ho Lam; Caleb R. Matthews; Zhengxian Lin; Minsuk Kahng; Alan Fern; Margaret Burnett
Finding AI’s Faults with AAR/AI: An Empirical Study Journal Article
In: ACM Transactions on Interactive Intelligent Systems, vol. 12, no. 1, pp. 1:1–1:33, 2022, ISSN: 2160-6455.
Abstract | Links | BibTeX | Tags: AI, Human-Computer Interaction
@article{khanna_finding_2022,
title = {Finding AI’s Faults with AAR/AI: An Empirical Study},
author = { Roli Khanna and Jonathan Dodge and Andrew Anderson and Rupika Dikkala and Jed Irvine and Zeyad Shureih and Kin-Ho Lam and Caleb R. Matthews and Zhengxian Lin and Minsuk Kahng and Alan Fern and Margaret Burnett},
url = {https://doi.org/10.1145/3487065},
doi = {10.1145/3487065},
issn = {2160-6455},
year = {2022},
date = {2022-03-01},
urldate = {2022-03-01},
journal = {ACM Transactions on Interactive Intelligent Systems},
volume = {12},
number = {1},
pages = {1:1--1:33},
abstract = {Would you allow an AI agent to make decisions on your behalf? If the answer is “not always,” the next question becomes “in what circumstances”? Answering this question requires human users to be able to assess an AI agent\textemdashand not just with overall pass/fail assessments or statistics. Here users need to be able to localize an agent’s bugs so that they can determine when they are willing to rely on the agent and when they are not. After-Action Review for AI (AAR/AI), a new AI assessment process for integration with Explainable AI systems, aims to support human users in this endeavor, and in this article we empirically investigate AAR/AI’s effectiveness with domain-knowledgeable users. Our results show that AAR/AI participants not only located significantly more bugs than non-AAR/AI participants did (i.e., showed greater recall) but also located them more precisely (i.e., with greater precision). In fact, AAR/AI participants outperformed non-AAR/AI participants on every bug and were, on average, almost six times as likely as non-AAR/AI participants to find any particular bug. Finally, evidence suggests that incorporating labeling into the AAR/AI process may encourage domain-knowledgeable users to abstract above individual instances of bugs; we hypothesize that doing so may have contributed further to AAR/AI participants’ effectiveness.},
keywords = {AI, Human-Computer Interaction},
pubstate = {published},
tppubtype = {article}
}
Would you allow an AI agent to make decisions on your behalf? If the answer is “not always,” the next question becomes “in what circumstances”? Answering this question requires human users to be able to assess an AI agent—and not just with overall pass/fail assessments or statistics. Here users need to be able to localize an agent’s bugs so that they can determine when they are willing to rely on the agent and when they are not. After-Action Review for AI (AAR/AI), a new AI assessment process for integration with Explainable AI systems, aims to support human users in this endeavor, and in this article we empirically investigate AAR/AI’s effectiveness with domain-knowledgeable users. Our results show that AAR/AI participants not only located significantly more bugs than non-AAR/AI participants did (i.e., showed greater recall) but also located them more precisely (i.e., with greater precision). In fact, AAR/AI participants outperformed non-AAR/AI participants on every bug and were, on average, almost six times as likely as non-AAR/AI participants to find any particular bug. Finally, evidence suggests that incorporating labeling into the AAR/AI process may encourage domain-knowledgeable users to abstract above individual instances of bugs; we hypothesize that doing so may have contributed further to AAR/AI participants’ effectiveness.
19.
Alexander You; Cindy Grimm; Joseph R. Davidson
Optical flow-based branch segmentation for complex orchard environments Miscellaneous
2022, (arXiv:2202.13050 [cs]).
Abstract | Links | BibTeX | Tags: Labor
@misc{you_optical_2022,
title = {Optical flow-based branch segmentation for complex orchard environments},
author = { Alexander You and Cindy Grimm and Joseph R. Davidson},
url = {http://arxiv.org/abs/2202.13050},
doi = {10.48550/arXiv.2202.13050},
year = {2022},
date = {2022-02-01},
urldate = {2022-02-01},
publisher = {arXiv},
abstract = {Machine vision is a critical subsystem for enabling robots to be able to perform a variety of tasks in orchard environments. However, orchards are highly visually complex environments, and computer vision algorithms operating in them must be able to contend with variable lighting conditions and background noise. Past work on enabling deep learning algorithms to operate in these environments has typically required large amounts of hand-labeled data to train a deep neural network or physically controlling the conditions under which the environment is perceived. In this paper, we train a neural network system in simulation only using simulated RGB data and optical flow. This resulting neural network is able to perform foreground segmentation of branches in a busy orchard environment without additional real-world training or using any special setup or equipment beyond a standard camera. Our results show that our system is highly accurate and, when compared to a network using manually labeled RGBD data, achieves significantly more consistent and robust performance across environments that differ from the training set.},
note = {arXiv:2202.13050 [cs]},
keywords = {Labor},
pubstate = {published},
tppubtype = {misc}
}
Machine vision is a critical subsystem for enabling robots to be able to perform a variety of tasks in orchard environments. However, orchards are highly visually complex environments, and computer vision algorithms operating in them must be able to contend with variable lighting conditions and background noise. Past work on enabling deep learning algorithms to operate in these environments has typically required large amounts of hand-labeled data to train a deep neural network or physically controlling the conditions under which the environment is perceived. In this paper, we train a neural network system in simulation only using simulated RGB data and optical flow. This resulting neural network is able to perform foreground segmentation of branches in a busy orchard environment without additional real-world training or using any special setup or equipment beyond a standard camera. Our results show that our system is highly accurate and, when compared to a network using manually labeled RGBD data, achieves significantly more consistent and robust performance across environments that differ from the training set.
20.
Amreeta Chatterjee; Lara Letaw; Rosalinda Garcia; Doshna Umma Reddy; Rudrajit Choudhuri; Sabyatha Sathish Kumar; Patricia Morreale; Anita Sarma; Margaret Burnett
Inclusivity Bugs in Online Courseware: A Field Study Inproceedings
In: Proceedings of the 2022 ACM Conference on International Computing Education Research - Volume 1, pp. 356–372, Association for Computing Machinery, New York, NY, USA, 2022, ISBN: 978-1-4503-9194-8.
Abstract | Links | BibTeX | Tags: Education, Human-Computer Interaction
@inproceedings{chatterjee_inclusivity_2022,
title = {Inclusivity Bugs in Online Courseware: A Field Study},
author = { Amreeta Chatterjee and Lara Letaw and Rosalinda Garcia and Doshna Umma Reddy and Rudrajit Choudhuri and Sabyatha Sathish Kumar and Patricia Morreale and Anita Sarma and Margaret Burnett},
url = {https://doi.org/10.1145/3501385.3543973},
doi = {10.1145/3501385.3543973},
isbn = {978-1-4503-9194-8},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Proceedings of the 2022 ACM Conference on International Computing Education Research - Volume 1},
pages = {356--372},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
series = {ICER '22},
abstract = {Motivation: Although asynchronous online CS courses have enabled more diverse populations to access CS higher education, research shows that online CS-ed is far from inclusive, with women and other underrepresented groups continuing to face inclusion gaps. Worse, diversity/inclusion research in CS-ed has largely overlooked the online courseware\textemdashthe web pages and course materials that populate the online learning platforms\textemdashthat constitute asynchronous online CS-ed’s only mechanism of course delivery. Objective: To investigate this aspect of CS-ed’s inclusivity, we conducted a three-phase field study with online CS faculty, with three research questions: (1) whether, how, and where online CS-ed’s courseware has inclusivity bugs; (2) whether an automated tool can detect them; and (3) how online CS faculty would make use of such a tool. Method: In the study’s first phase, we facilitated online CS faculty members’ use of GenderMag (an inclusive design method) on two online CS courses to find their own courseware’s inclusivity bugs. In the second phase, we used a variant of the GenderMag Automated Inclusivity Detector (AID) tool to automatically locate a “vertical slice” of such courseware inclusivity bugs, and evaluated the tool’s accuracy. In the third phase, we investigated how online CS faculty used the tool to find inclusivity bugs in their own courseware. Results: The results revealed 29 inclusivity bugs spanning 6 categories in the online courseware of 9 online CS courses; showed that the tool achieved an accuracy of 75% at finding such bugs; and revealed new insights into how a tool could help online CS faculty uncover assumptions about their own courseware to make it more inclusive. Implications: As the first study to investigate the presence and types of cognitive- and gender-inclusivity bugs in online CS courseware and whether an automated tool can find them, our results reveal new possibilities for how to make online CS education a more inclusive virtual environment for gender-diverse students.},
keywords = {Education, Human-Computer Interaction},
pubstate = {published},
tppubtype = {inproceedings}
}
Motivation: Although asynchronous online CS courses have enabled more diverse populations to access CS higher education, research shows that online CS-ed is far from inclusive, with women and other underrepresented groups continuing to face inclusion gaps. Worse, diversity/inclusion research in CS-ed has largely overlooked the online courseware—the web pages and course materials that populate the online learning platforms—that constitute asynchronous online CS-ed’s only mechanism of course delivery. Objective: To investigate this aspect of CS-ed’s inclusivity, we conducted a three-phase field study with online CS faculty, with three research questions: (1) whether, how, and where online CS-ed’s courseware has inclusivity bugs; (2) whether an automated tool can detect them; and (3) how online CS faculty would make use of such a tool. Method: In the study’s first phase, we facilitated online CS faculty members’ use of GenderMag (an inclusive design method) on two online CS courses to find their own courseware’s inclusivity bugs. In the second phase, we used a variant of the GenderMag Automated Inclusivity Detector (AID) tool to automatically locate a “vertical slice” of such courseware inclusivity bugs, and evaluated the tool’s accuracy. In the third phase, we investigated how online CS faculty used the tool to find inclusivity bugs in their own courseware. Results: The results revealed 29 inclusivity bugs spanning 6 categories in the online courseware of 9 online CS courses; showed that the tool achieved an accuracy of 75% at finding such bugs; and revealed new insights into how a tool could help online CS faculty uncover assumptions about their own courseware to make it more inclusive. Implications: As the first study to investigate the presence and types of cognitive- and gender-inclusivity bugs in online CS courseware and whether an automated tool can find them, our results reveal new possibilities for how to make online CS education a more inclusive virtual environment for gender-diverse students.
