2021 IEEE MIT Undergraduate Research Technology Conference (URTC)最新文献

AdversarialDroid: A Deep Learning based Malware Detection Approach for Android System Against Adversarial Example Attacks AdversarialDroid:基于深度学习的Android系统恶意软件检测方法对抗对抗性示例攻击

2021 IEEE MIT Undergraduate Research Technology Conference (URTC) Pub Date : 2021-10-08 DOI: 10.1109/URTC54388.2021.9701615

Giuseppe D’Ambrosio, Wenjia Li

引用次数: 1

SALT: Spacecraft Air Leak Technology SALT:航天器空气泄漏技术

2021 IEEE MIT Undergraduate Research Technology Conference (URTC) Pub Date : 2021-10-08 DOI: 10.1109/URTC54388.2021.9701654

Alyssa Wan, Hannah Robinson, S. Wan, Steve Robinson, Soon Wan

{"title":"SALT: Spacecraft Air Leak Technology","authors":"Alyssa Wan, Hannah Robinson, S. Wan, Steve Robinson, Soon Wan","doi":"10.1109/URTC54388.2021.9701654","DOIUrl":"https://doi.org/10.1109/URTC54388.2021.9701654","url":null,"abstract":"According to NASA, there are millions of micrometeoroids and orbital debris in the space [1] [2]. They are the number one threat to satellites, spacecraft and astronauts. They travel at high speed and direct collide with spacecraft will result hole and air leak. Detecting the air leaks in spacecraft is challenging, and not finding the leaks in time can cause destruction of scientific instruments, and the life of astronauts. The current tools or methods are either complicated or needed significant time to locate the hole, and they are not reliable. As a result, valuable resources, such as astronaut's time, are lost. SALT (Spacecraft Air Leak Technology) is an innovative solution to address the above problem. Each SALT is laid on a one foot by one foot flexible PCB (Printed Circuit Board), and each PCB can be placed on the walls of a spacecraft to create a wallpaper grid covering the entire interior of the spacecraft. A SALT is made up of two parts: the Hole Trap and the Electronic Circuit with RFID (Radio Frequency Identification). The Hole Trap is a thin trace that is 6 mils, or 0.1524mm, in width, that coils around on a one foot by one-foot area. The trace closes a SALT circuit. When a micrometeorite punctures the wall of a spacecraft, it will break the trace on the Hole Trap. When the Hole Trap is broken, the circuit is opened, and it will trigger the RFID to send a unique identification code to a host computer. The host computer will immediately alert the astronauts with the specific location of the hole.","PeriodicalId":240930,"journal":{"name":"2021 IEEE MIT Undergraduate Research Technology Conference (URTC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133917583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Assessing Paper Texture Similarity in Matisse Lithographs Using a Triplet Neural Network 用三重神经网络评价马蒂斯平版版画的纸张纹理相似性

2021 IEEE MIT Undergraduate Research Technology Conference (URTC) Pub Date : 2021-10-08 DOI: 10.1109/URTC54388.2021.9740159

Karen M. Aguilar, Shelby Powers, Leah Lackey, Arick Grootveld, A. G. Klein

引用次数: 0

Global Landslide Forecasting and Dynamic Susceptibility Mapping Using a New Dataset of Geophysical and Meteorological Features 基于地球物理和气象特征新数据集的全球滑坡预测和动态敏感性制图

2021 IEEE MIT Undergraduate Research Technology Conference (URTC) Pub Date : 2021-10-08 DOI: 10.1109/URTC54388.2021.9701628

Ishaan Javali, Shrey Joshi

引用次数: 1

A Study of Illumination Filtering and Movement Detection in Video Streaming Processing 视频流处理中光照滤波与运动检测的研究

2021 IEEE MIT Undergraduate Research Technology Conference (URTC) Pub Date : 2021-10-08 DOI: 10.1109/URTC54388.2021.9701635

Mai Phuong Nguyen, Xingjie Li

引用次数: 0

Modeling Li-ion Battery Behavior to Identify Safety Limits 模拟锂离子电池的行为，以确定安全限制

2021 IEEE MIT Undergraduate Research Technology Conference (URTC) Pub Date : 2021-10-08 DOI: 10.1109/URTC54388.2021.9701631

Alice Gaehring, R. Kripalani, Dakota Neuls, Owen Rondeau, Naomi Schlag

引用次数: 1

An Efficient and Reliable Multi-Robot Navigation Platform with Collision Avoidance 一种高效可靠的多机器人避碰导航平台

2021 IEEE MIT Undergraduate Research Technology Conference (URTC) Pub Date : 2021-10-08 DOI: 10.1109/URTC54388.2021.9701650

David Crafts, Jake Sousa, W. Mclellan, N. Robson, Cuong H. Pham

{"title":"An Efficient and Reliable Multi-Robot Navigation Platform with Collision Avoidance","authors":"David Crafts, Jake Sousa, W. Mclellan, N. Robson, Cuong H. Pham","doi":"10.1109/URTC54388.2021.9701650","DOIUrl":"https://doi.org/10.1109/URTC54388.2021.9701650","url":null,"abstract":"With the ever-increasing demand for consumer goods, companies are pivoting towards semi or fully autonomous robotic warehouses to efficiently fulfill orders. Large companies have become increasingly reliant on autonomous robotic warehouse solutions, however, the demand from small to medium-sized companies has increased dramatically [8]. These companies often rely on manual solutions, such as forklifts, to traverse their warehouses. In 2019, forklifts accounted for 79 work related deaths and 8,140 nonfatal injuries [9]. Warehouse accidents are the direct result of their fast paced, ever-changing nature. With warehouses containing a multitude of static and dynamic variables, an open-source robotics platform is needed that can safely traverse a warehouse, preventing unnecessary death and injury. The proposed solution allows for the safe and effective navigation of these environments utilizing a path-planning algorithm in tandem with a dynamic obstacle avoidance algorithm. The dynamic obstacle avoidance algorithm uses LiDAR sensor data to detect and avoid obstacles along a path. The path-planning algorithm uses a map of a warehouse environment that accounts for static objects, such as shelves, and generates an efficient path from a starting point to a goal point. These algorithms are simulated in Gazebo allowing for a detailed visual of the platform's performance. These algorithms, together, create a platform that allows for robots to autonomously navigate to desired destinations while safely avoiding a myriad of obstacles.","PeriodicalId":240930,"journal":{"name":"2021 IEEE MIT Undergraduate Research Technology Conference (URTC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122551395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ECG Data Analysis with MSE and Machine Learning 基于MSE和机器学习的心电图数据分析

2021 IEEE MIT Undergraduate Research Technology Conference (URTC) Pub Date : 2021-10-08 DOI: 10.1109/URTC54388.2021.9701641

Abhigya Pote Shrestha, Chen-Hsiang Yu

{"title":"ECG Data Analysis with MSE and Machine Learning","authors":"Abhigya Pote Shrestha, Chen-Hsiang Yu","doi":"10.1109/URTC54388.2021.9701641","DOIUrl":"https://doi.org/10.1109/URTC54388.2021.9701641","url":null,"abstract":"Time series data such as electrocardiogram (ECG) recordings display patterns that indicate regularity in heartbeat rhythms. Medical researchers normally analyze data statistically after collecting all data, but this kind of post-processing approach is difficult to be applied to real-time issue, such as identifying abnormal heartbeats. To address this issue, we investigated applying supervised machine learning approaches to RR intervals of ECG data for classifying three different types of heartbeat patterns: Healthy Heartbeat, Heart Failure and Atrial Fibrillation. In our study, we also applied the same methods to Multiscale Entropy (MSE) of RR intervals to verify if we can have a better prediction result. The evaluation results show that simply using RR Intervals of ECG data can build machine learning models to predict unseen ECG data with an 80%+ accuracy. However, there is no significant improvement when using MSE of RR intervals. The findings of this study demonstrated that supervised machine learning approaches are relatively successful in predicting heartbeat types with RR interval data than using MSE technique of coarse graining data with higher time scales. Based on this finding, we believe there is a chance to build a mobile or Web-based system that can use a trained model to distinguish three heartbeat patterns for real-time service.","PeriodicalId":240930,"journal":{"name":"2021 IEEE MIT Undergraduate Research Technology Conference (URTC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131517412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Enhancing the Bionic Eye: A Real-time Image Optimization Framework to Encode Color and Spatial Information Into Retinal Prostheses 增强仿生眼:一种将颜色和空间信息编码到视网膜假体中的实时图像优化框架

2021 IEEE MIT Undergraduate Research Technology Conference (URTC) Pub Date : 2021-10-08 DOI: 10.1109/URTC54388.2021.9701618

William Huang

引用次数: 0

A Distributed Decision Tree on Hadoop Hadoop上的分布式决策树

2021 IEEE MIT Undergraduate Research Technology Conference (URTC) Pub Date : 2021-10-08 DOI: 10.1109/URTC54388.2021.9701636

William Jones, Min Chen

引用次数: 0