荣誉论文

作者: 杰里米·陈

标题: 警务人员投诉的传播模式

文摘: 最近的电子游戏正规平台表明，警察的行为, 包括过度使用武力和不当行为, 能否通过传染过程在警察社会互动网络上传播. 然而, 关于这个话题的文献是混杂的, where null findings have followed positive findings of contagion in some cities in others. Robust and easy-toimplement statistical tests are needed to help police agencies detect the contagion of unwanted police behavior in policing networks. 在本论文中, we contribute to this literature on whether excessive police use of force is socially contagious in officer networks and present several models of excessive use of force complaints. Our proposed algorithms do not require as many parametric modeling assumptions as existing models. We propose a set-based Resampling Test variation as a baseline model to test the hypothesis that the use of force arises through a random, 独立事件过程. We then compare this baseline to two other algorithms we adapt for modeling police use of force: the Pólya Urn Model and Spillover Pólya Urn Model. 最后，我们使用芝加哥警方使用武力的数据来实现这三种算法. Our results indicate that contagion plays a role in the excessive use of force in Chicago police networks.

作者: 杰瑞侯

标题: 无源声窃听

文摘: The goal of this project is to demonstrate a potential eavesdropping hazard associated with 60GHz wireless communications, where acoustic signals can be detected by an eavesdropper by observing the wireless communications signals. 不像最近的工作，使用雷达波形进行窃听测距, our system uses binary-shift-keying (BPSK) signals by exploiting variations in the multipath environment between a transmitter and receiver caused by vibrations due to an acoustic excitation. 因此，该系统显示出被动窃听的危险, where an eavesdropper can passively observe the wireless communications signal transmitted by a legitimate source to listen in on acoustic signals, 不需要窃听者传送自己的任何信号. 使用pytorch使用自定义深度学习框架工作, we have proved that we could obtain an accuracy of 30% classifications of accuracy for words.

作者: 快乐近藤

标题: 数据花园:在VR数据可视化中探索我们的社区

文摘: 随着人们对提高数据素养的需求不断增加, 正在开发有效表示和分析数据的方法和途径. Traditional representations of data such as charts and abstract visuals detract from the humanity represented by datasets.

本文介绍了DataGarden, a system that supports embodied interactions with humane representations of data in an immersive VR environment for users to think about the people behind the data. 在这个互动系统中, 用户可以在我们的虚拟花园中与他们的个人可视化交互, as well as with the visualizations created using the data of the 电子游戏软件 community.

作者: 约翰Marangola

标题: 具有时差正则化的完美系统发育模型的高效求解器

文摘: Many inference tools use the Perfect Phylogeny Model (PPM) to learn trees from noisy variant allele frequency (VAF) data. PPM常常导致推理歧义, 因为许多不同的树木为观测到的VAF数据提供了同样充分的解释. 此外，PPM不捕获任何时间概念. 而与空间采样无关, this is problematic when samples are taken in time; randomly reordering time samples does not change the best tree found under the PPM, 一个反直觉的结果. 为了消除这种歧义, 我们增加PPM，这样它就可以理解突变体随时间的增长. 特别是, 我们的增广PPM假设取样的突变体生长路径, 哪些在时间上是粗采样的, 快速进行, 并且可以很好地通过具有小l1范数导数的路径来建模. 对于树比较小的场景, we advocate for an inference algorithm that conducts a (semi) exhaustive search over the entire space of trees. 这项任务需要一个新的、速度极快的推理引擎. We develop a homotopy algorithm that extends the solution of the original PPM to the solution of the novel augmented model. Key to its efficiency are several computational insights that make our implementation significantly outperform competitor solvers.

作者: 詹姆斯·努南

标题: 未修改led的可见光定位

文摘: 随着工业和学术界变得越来越自动化, 需要具有成本效益, 可扩展的室内定位算法增加. 当前的方法, 在可见光定位(VLP)这一新的电子游戏正规平台领域, 利用调制发光二极管(led)进行定位. 在这些作品中, led的发光强度变化很快, 接收到的光线水平被用来找到接收器的位置. 在本文中, 我们提出了一种利用可见光的替代定位技术, 而是使用未经修改的led. 我们的建议包括一个基本的方法, 同时也证明了这一概念的性价比, 易于复制和可靠的室内定位技术. 我们利用LED灯泡固有的制造变化, 从而产生独特的可识别的光发射, to localize two-dimensional position directly through a simple multiple output regression neural network trained on light samples taken in the target environment, 消除了对组件分解的需要, 硬件修改, 或三角.

作者: 泰勒奥斯本

标题: 认知状态:基于深度学习的信念状态推断

文摘: The Cognitive States project is an ongoing investigation of how well a pre-trained deep learning model, 微调与各种语料库的注释文本, 可以推断信念状态. 整体, the goal of this project is to make incremental progress towards more advanced belief state and 情绪 detection capabilities. Previous research has focused on achieving state-of-the-art F1 results on classification tasks as well as end-to-end generative tasks defined on two corpora annotated for belief, 情绪, 或两个, 事实银行和MPQA, 使用两个模型, BERT和Flan-T5 (Murzaku et al). 我们使用相同的模型在语言理解(LU)语料库上定义类似的任务, 为了证实从以前的工作中获得的见解. 此外, 我们提出了一种新的数据库表示用于微调数据, 允许Factbank的统一, MPQA, LU, and additional annotation-based belief/情绪 corpora into a single dataset for seamless use in multi-task learning contexts, requiring unifying data transformations such as converting unigram head words to n-gram spans. 我们的结果与Murzaku等人的结果一致. 在所有任务中，我们的方法在少数族裔中表现不佳. Plans to improve minority performance include leveraging a few-shot approach or generating synthetic data by swapping out words in existing examples with close synonyms.

作者: 广州机床厂周

标题: Exploratory Analysis and Predictive Modeling for Electrocardiogram (ECG) and Photoplethysmogram (PPG) Human Heart Activity Data

文摘: Electrocardiography (ECG) and Photoplethysmography (PPG) are two widely used techniques for monitoring cardiovascular activity. 心电图是一种公认的检测心脏电活动的方法, while PPG utilizes optical technology to measure variations in blood volume in peripheral tissues. 本文探讨了PPG和心电信号的两种应用, utilizing a PPG dataset with Human Activity Recognition labels and an ECG dataset labeled with various cardiac conditions. 对原始时间序列数据进行预处理, 通过消除趋势, 带通滤波, 排除异常值. 还考虑了数据的两个简化版本, 一种是使用心率变异性(HRV)汇总测量, 另一种是基于快速傅里叶变换(FFT)的频谱表示。. Exploratory Data Analysis and predictive data modeling using machine learning techniques were then performed on the preprocessed datasets. 我们对模型的预测性能进行了评价, 试着从生理学的角度来理解结果, 并建议未来工作的可能方向.