Spatial reasoning tasks in multi-agent environments such as event prediction, agent type identification, or missing data imputation are important for multiple applications (e.g., autonomous surveillance over sensor networks and subtasks for reinforcement learning (RL)). StarCraft II game replays encode intelligent (and adversarial) multi-agent behavior and could provide a testbed for these tasks; however, extracting simple and standardized representations for prototyping these tasks is laborious and hinders reproducibility. In contrast, MNIST and CIFAR10, despite their extreme simplicity, have enabled rapid prototyping and reproducibility of ML methods. Following the simplicity of these datasets, we construct a benchmark spatial reasoning dataset based on StarCraft II replays that exhibit complex multi-agent behaviors, while still being as easy to use as MNIST and CIFAR10. Specifically, we carefully summarize a window of 255 consecutive game states to create 3.6 million summary images from 60,000 replays, including all relevant metadata such as game outcome and player races. We develop three formats of decreasing complexity: Hyperspectral images that include one channel for every unit type (similar to multispectral geospatial images), RGB images that mimic CIFAR10, and grayscale images that mimic MNIST. We show how this dataset can be used for prototyping spatial reasoning methods. All datasets, code for extraction, and code for dataset loading can be found at https://starcraftdata.davidinouye.com

In this manuscript, we present various proposed methods estimate the prevalence of disease, a critical prerequisite for the adequate interpretation of screening tests. To address the limitations of these approaches, which revolve primarily around their a posteriori nature, we introduce a novel method to estimate the pretest probability of disease, a priori, utilizing the Logit function from the logistic regression model. This approach is a modification of McGee's heuristic, originally designed for estimating the posttest probability of disease. In a patient presenting with $n_\theta$ signs or symptoms, the minimal bound of the pretest probability, $\phi$, can be approximated by: $\phi \approx \frac{1}{5}{ln\left[\displaystyle\prod_{\theta=1}^{i}\kappa_\theta\right]}$ where $ln$ is the natural logarithm, and $\kappa_\theta$ is the likelihood ratio associated with the sign or symptom in question.

When planning with an inaccurate dynamics model, a practical strategy is to restrict planning to regions of state-action space where the model is accurate: also known as a model precondition. Empirical real-world trajectory data is valuable for defining data-driven model preconditions regardless of the model form (analytical, simulator, learned, etc...). However, real-world data is often expensive and dangerous to collect. In order to achieve data efficiency, this paper presents an algorithm for actively selecting trajectories to learn a model precondition for an inaccurate pre-specified dynamics model. Our proposed techniques address challenges arising from the sequential nature of trajectories, and potential benefit of prioritizing task-relevant data. The experimental analysis shows how algorithmic properties affect performance in three planning scenarios: icy gridworld, simulated plant watering, and real-world plant watering. Results demonstrate an improvement of approximately 80% after only four real-world trajectories when using our proposed techniques.

Single-cell RNA sequencing (scRNA-seq) data are important for studying the biology of development or diseases at single-cell level. To better understand the properties of the data, to build controlled benchmark data for testing downstream methods, and to augment data when collecting sufficient real data is challenging, generative models have been proposed to computationally generate synthetic scRNA-seq data. However, the data generated with current models are not very realistic yet, especially when we need to generate data with controlled conditions. In the meantime, the Diffusion models have shown their power in generating data in computer vision at high fidelity, providing a new opportunity for scRNA-seq generation. In this study, we developed scDiffusion, a diffusion-based model to generate high-quality scRNA-seq data with controlled conditions. We designed multiple classifiers to guide the diffusion process simultaneously, enabling scDiffusion to generate data under multiple condition combinations. We also proposed a new control strategy called Gradient Interpolation. This strategy allows the model to generate continuous trajectories of cell development from a given cell state. Experiments showed that scDiffusion can generate single-cell gene expression data closely resembling real scRNA-seq data, surpassing state-of-the-art models in multiple metrics. Also, scDiffusion can conditionally produce data on specific cell types including rare cell types. Furthermore, we could use the multiple-condition generation of scDiffusion to generate cell type that was out of the training data. Leveraging the Gradient Interpolation strategy, we generated a continuous developmental trajectory of mouse embryonic cells. These experiments demonstrate that scDiffusion is a powerful tool for augmenting the real scRNA-seq data and can provide insights into cell fate research.

In Natural Language Processing (NLP) classification tasks such as topic categorisation and sentiment analysis, model generalizability is generally measured with standard metrics such as Accuracy, F-Measure, or AUC-ROC. The diversity of metrics, and the arbitrariness of their application suggest that there is no agreement within NLP on a single best metric to use. This lack suggests there has not been sufficient examination of the underlying heuristics which each metric encodes. To address this we compare several standard classification metrics with more 'exotic' metrics and demonstrate that a random-guess normalised Informedness metric is a parsimonious baseline for task performance. To show how important the choice of metric is, we perform extensive experiments on a wide range of NLP tasks including a synthetic scenario, natural language understanding, question answering and machine translation. Across these tasks we use a superset of metrics to rank models and find that Informedness best captures the ideal model characteristics. Finally, we release a Python implementation of Informedness following the SciKitLearn classifier format.

Thyroid cancer, the most prevalent endocrine cancer, has gained significant global attention due to its impact on public health. Extensive research efforts have been dedicated to leveraging artificial intelligence (AI) methods for the early detection of this disease, aiming to reduce its morbidity rates. However, a comprehensive understanding of the structured organization of research applications in this particular field remains elusive. To address this knowledge gap, we conducted a systematic review and developed a comprehensive taxonomy of machine learning-based applications in thyroid cancer pathogenesis, diagnosis, and prognosis. Our primary objective was to facilitate the research community's ability to stay abreast of technological advancements and potentially lead the emerging trends in this field. This survey presents a coherent literature review framework for interpreting the advanced techniques used in thyroid cancer research. A total of 758 related studies were identified and scrutinized. To the best of our knowledge, this is the first review that provides an in-depth analysis of the various aspects of AI applications employed in the context of thyroid cancer. Furthermore, we highlight key challenges encountered in this domain and propose future research opportunities for those interested in studying the latest trends or exploring less-investigated aspects of thyroid cancer research. By presenting this comprehensive review and taxonomy, we contribute to the existing knowledge in the field, while providing valuable insights for researchers, clinicians, and stakeholders in advancing the understanding and management of this disease.

Optimizing service schedules is pivotal to the reliable, efficient, and inclusive on-demand mobility. This pressing challenge is further exacerbated by the increasing needs of an aging population, the over-subscription of existing services, and the lack of effective solution methods. This study addresses the intricacies of service scheduling, by jointly optimizing rider trip planning and crew scheduling for a complex dynamic mobility service. The resulting optimization problems are extremely challenging computationally for state-of-the-art methods. To address this fundamental gap, this paper introduces the Joint Rider Trip Planning and Crew Shift Scheduling Problem (JRTPCSSP) and a novel solution method, called AGGNNI-CG (Attention and Gated GNN- Informed Column Generation), that hybridizes column generation and machine learning to obtain near-optimal solutions to the JRTPCSSP with the real-time constraints of the application. The key idea of the machine-learning component is to dramatically reduce the number of paths to explore in the pricing component, accelerating the most time-consuming component of the column generation. The machine learning component is a graph neural network with an attention mechanism and a gated architecture, that is particularly suited to cater for the different input sizes coming from daily operations. AGGNNI-CG has been applied to a challenging, real-world dataset from the Paratransit system of Chatham County in Georgia. It produces dramatic improvements compared to the baseline column generation approach, which typically cannot produce feasible solutions in reasonable time on both medium-sized and large-scale complex instances. AGGNNI-CG also produces significant improvements in service compared to the existing system.

Educators are increasingly concerned about the usage of Large Language Models (LLMs) such as ChatGPT in programming education, particularly regarding the potential exploitation of imperfections in Artificial Intelligence Generated Content (AIGC) Detectors for academic misconduct. In this paper, we present an empirical study where the LLM is examined for its attempts to bypass detection by AIGC Detectors. This is achieved by generating code in response to a given question using different variants. We collected a dataset comprising 5,069 samples, with each sample consisting of a textual description of a coding problem and its corresponding human-written Python solution codes. These samples were obtained from various sources, including 80 from Quescol, 3,264 from Kaggle, and 1,725 from LeetCode. From the dataset, we created 13 sets of code problem variant prompts, which were used to instruct ChatGPT to generate the outputs. Subsequently, we assessed the performance of five AIGC detectors. Our results demonstrate that existing AIGC Detectors perform poorly in distinguishing between human-written code and AI-generated code.

While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solution, Machine Learning as a Service (MLaaS) has emerged, lowering the barriers for users to release or productize their deep learning models. However, previous studies have highlighted potential privacy and security concerns associated with MLaaS, and one primary threat is model extraction attacks. To address this, there are many defense solutions but they suffer from unrealistic assumptions and generalization issues, making them less practical for reliable protection. Driven by these limitations, we introduce a novel defense mechanism, SAME, based on the concept of sample reconstruction. This strategy imposes minimal prerequisites on the defender's capabilities, eliminating the need for auxiliary Out-of-Distribution (OOD) datasets, user query history, white-box model access, and additional intervention during model training. It is compatible with existing active defense methods. Our extensive experiments corroborate the superior efficacy of SAME over state-of-the-art solutions. Our code is available at https://github.com/xythink/SAME.

Generative Artificial Intelligence (AI) can be used to automatically generate medical reports based on transcripts of medical consultations. The aim is to reduce the administrative burden that healthcare professionals face. The accuracy of the generated reports needs to be established to ensure their correctness and usefulness. There are several metrics for measuring the accuracy of AI generated reports, but little work has been done towards the application of these metrics in medical reporting. A comparative experimentation of 10 accuracy metrics has been performed on AI generated medical reports against their corresponding General Practitioner's (GP) medical reports concerning Otitis consultations. The number of missing, incorrect, and additional statements of the generated reports have been correlated with the metric scores. In addition, we introduce and define a Composite Accuracy Score which produces a single score for comparing the metrics within the field of automated medical reporting. Findings show that based on the correlation study and the Composite Accuracy Score, the ROUGE-L and Word Mover's Distance metrics are the preferred metrics, which is not in line with previous work. These findings help determine the accuracy of an AI generated medical report, which aids the development of systems that generate medical reports for GPs to reduce the administrative burden.