Engineering Commons^™

Multi-View Human Action Recognition Based On Deep Neural Network, Zhao Ying, Lu Yao, Zhang Jian, Qidi Liang, Long Wei

Journal of System Simulation

Abstract: A novel deep neural network named CNN+CA(Convolutional Neural Network plus Context Attention) model is constructed and a new recognition algorithm based on sequence matching is presented to improve the recognition accuracy of MVHAR (Multi-view Human Action Recognition). A CNN(Convolutional Neural Network) is designed to automatically learn multi-view fusion features; the CA (Context Attention) module is introduced to selectively focus on the parts of the features that are relevant for the recognition task; the proposed recognition algorithm based on sequence matching is used to realize MVHAR. The experimental results on the IXMAS dataset and the i3DPost dataset …

Design And Simulation For Compensatory Controller Of Aircraft Rudder Electro-Hydraulic Loading System, Xiaolin Liu, Jingyi Wu

Journal of System Simulation

Abstract: The electro-hydraulic loading system of aircraft rudder is a torque servo system which is a special equipment for testing the performance of rudder. In order to reduce the influence of surplus force in loading system, a control method for PID controller tuned in real time by radial basis function neural network based on particle swarm optimization is proposed. The characteristics of global and hyper parameter optimization of particle swarm optimization are used to improve the control effect of the controller. The learning coefficient based on annealing is used to accelerate the network convergence speed. Simulation results show that, compared …

An Artificial Emotion Model For The Mutual Mapping Between Discrete State And Dimensional Space, Zhihang Tian, Xiaming Chen, Dazhi Jiang

Journal of System Simulation

Abstract: Emotional intelligence is an important component and development direction of machine intelligence. The purpose of artificial emotion model is to construct emotion models for machines to develope systematic ability of emotion understanding and expression. However, the existing methods are still insufficient in artificial emotion modeling ability. Aiming at the key factor of personalization in the construction of artificial emotion model, this paper proposes a method of mutual mapping between discrete emotion state and dimension space state, and constructs a machine personalized artificial emotion model based on Big Five personality model and emotion state transfer model. The relevant experimental results …

System Reliability Modeling In Competitive Failure Considering Zoned Shock Effect, Qiguo Hu, Gao Zhan

Journal of System Simulation

Abstract: Shocks have certain effects on system reliability, and how to quantify the degree of shock loads becomes the key of system reliability analysis. The reliability modeling problem of system suffered from different shock strength is researched based on degradation process competing with sudden failure. Shock process is descripted by extreme shock and two types of degradation processes are descripted by Wiener process under the condition of shifting failure threshold. Aiming at different intensity shocks on the system, the different shock load suffered by zoned shock effect is partitioned, the distribution function of the two types of failure processes is …

Time-Varying Ocean Channel Modeling Method, Yuehua Pei, Su Wei, Jincheng Tao, Xialin Jiang

Journal of System Simulation

Abstract: For the ocean channel with extremely complicated situation, an underwater acoustic channel modeling algorithm which can reflect the sparsity, time-varying and space-varying characteristics is proposed. Based on the prior information obtained from the sea trials in a specific sea area, the statistical characteristics of the channel impulses response structure with time and space are obtained. According to the obtained channel sparsities and non-zero position vectors’ statistics, a time-varying underwater acoustic channel model match the real environment is generated. Based on the measured data of marine communication in specific sea area, the simulation results show that the proposed …

Bilingual Harmony Micro-Simulation Model And Computational Experiment, Shouming Zhang, Zhiping Wang, Guihong Bi, Zhenghua Zeng

Journal of System Simulation

Abstract: Under the background of urbanization, the weak connection of social networks has increased, which has challenged the protection of vulnerable languages. A new social network with remote weak connection is constructed based on the improved modeling method of agent social circle network; in addition to considering the influence of language status and the language population ratio on the language evolution mechanism of different populations, a new mechanism is introduced for the influence of bilinguals on the transition from monolingual to bilingual, and the influence of language attitudes and network connections on language choice behaviors; an improved agent language level …

Explicit Model Predictive Control For Intelligent Vehicle Lateral Trajectory Tracking, Leng Yao, Shuen Zhao

Journal of System Simulation

Abstract: To ensure the accuracy, driving stability and online real-time of intelligent vehicle tracking control, an explicit model predictive tracking control method is designed. The cost functions and constraints for tracking accuracy and driving stability in the prediction time domain are proposed. The tracking control problem is transformed into the optimization of the active steering angle with dynamic disturbances. To improve the real-time performance, the traditional model predictive control system is transformed into an equivalent explicit polyhedral piece-wise affine (PPWA) system, and the active steering angle of front wheel is gained by the explicit law on parameter partition. Carsim and …

Simulation And Experimental Verification Of Precision Grinding Of Micro-Groove Structure, Haoyang Cao

Journal of System Simulation

Abstract: In order to study the influence of micro-groove structure precision grinding, based on grinding wheel dressing and grinding kinematics, a grinding simulation model for the micro-groove structural surface is established. The influence of dressing, grinding parameters and pitch length on the profile of micro-groove structure was analyzed systematically, the grinding conditions for forming complete or interfering micro-groove profile are described, the profile and size of micro-groove are predicted, and the grinding test is carried out on carbon steel. The test results are consistent with the trend of the simulation model. The profile and size of the micro-groove …

Multi-Objective Optimization Of Multi-Task Parallel Motorcycle Suspension System Parameters, Xiansheng Ran, Yang Jing, Luo Ling, Chen Kai

Journal of System Simulation

Abstract: Aiming at the comprehensive problem of wobble of front suspension system and weave of rear suspension system of large displacement motorcycle at medium and high speed, a multi-objective optimization scheme based on sensitivity analysis and approximate modeling is proposed. The motorcycle model is established and the dynamics simulation is carried out. The lateral acceleration of front wheel's centroid position, the yaw rate and roll rate of whole vehicle's centroid position, which characterize the wobble and weave are the targets. The sensitivity analysis of suspension system parameters and the approximate modeling are carried out. Based on the analysis results, …

Research On Variable Swept Wing Mode Of Missile Based On Flutter Characteristics, Gao Yang, Yanbin Li, Wang Ying, Zhang Ze, Lü Rui

Journal of System Simulation

Abstract: The variable sweep angle of missile wing is an important variant missile design scheme. In the process of variant design, the aerodynamic and flutter characteristics of missile will be significantly different by using different variable sweep methods. Referring to the shape characteristics of Tomahawk missile, the geometric model of variable sweep wing missile is established. The flutter characteristics of variable sweep wing missile under different variable sweep angle modes are calculated and analyzed by fluid structure coupling method, and the selection scheme of variable sweep wing mode based on flutter characteristics is explored. The results show that the …

Multi-Class Multi-Intersection Iot-Based Vehicle Counting, Jay Ladhad, Colin Rioux, Maggie Dong, Chris Tian, Donovan Allen

Computer Science and Engineering Senior Theses

Traffic management is an important public infrastructure component that can greatly benefit from an intelligent reactive system. Vehicle counting is a vital aspect of an intelligent traffic system that could mitigate traffic congestion and increase the efficiency of traffic lights. While previous research has made progress in developing machine learning algorithms for vehicle counting and tracking, they did not have any hardware constraints and were not designed to run on IoT devices in real time. Our team proposes a decentralized method of vehicle counting and tracking through a system of IoT devices, namely Jetson Xavier NX’s, that communicate vehicle identification …

Crossroad - Avoid Crowd Intelligence, Xukun Zhang, Yuzheng Wu, Haochen Zhang

Interdisciplinary Design Senior Theses

Nowadays, waiting takes big chunks of daily-life activity. People may always find themselves facing long queues, waiting in a crowded facility, even when they have tried to avoid peak hours. Heading to a highly populated public area may have felt like heading to a battlefield. Without access to the real-time information of the facility, people start to discover that waiting starts to become an unpredictable event that can sometimes delay their schedule or even worse. This project serves as a solution to tackle this lack of transparency. Crossroad aims to combine facilities’ cameras with micro-controller to see the engagement of …

A Method For Comparative Analysis Of Trusted Execution Environments, Stephano Cetola

Dissertations and Theses

The problem of secure remote computation has become a serious concern of hardware manufacturers and software developers alike. Trusted Execution Environments (TEEs) are a solution to the problem of secure remote computation in applications ranging from "chip and pin" financial transactions to intellectual property protection in modern gaming systems. While extensive literature has been published about many of these technologies, there exists no current model for comparing TEEs. This thesis provides hardware architects and designers with a set of tools for comparing TEEs. I do so by examining several properties of a TEE and comparing their implementations in several technologies. …

Real-Time Multi-Camera Traffic Intersection Analysis On Iot Devices, Ethan Paek, Tyler Niiyama, Justin Liu, Spencer Tsang, Kent Ngo, Jackson Tseng

Computer Science and Engineering Senior Theses

The continuous growth of urban and suburban areas has increased the number of commuters and general transportation along central roadways, which has resulted in a trend of more traffic congestion in essential areas every year. This creates a challenge for civil engineers to improve the efficiency of the traffic intersection systems. Our team worked on this issue by building a system to improve traffic intersection analysis by video camera to count cars using multiple camera angles at a single intersection. By providing better real-time traffic network analysis, civil engineers can more accurately monitor the efficiency of traffic intersections and then …

Smart Grid Security Simulator, Christopher Woo

Computer Science and Engineering Senior Theses

No abstract provided.

Smart Pantry, Audrey Hou, Sukruth Krishnakumar, Jacob Lucke

Computer Science and Engineering Senior Theses

Two-thirds of food waste at home is due to food going bad before it is used. Mitigating this food waste would mean keeping track of groceries’ shelf lives, which is a time sink. Our solution is a grocery monitoring system that tracks grocery items, saves time, and makes meal planning more convenient and efficient through recipe recommendation. Tracking groceries is accomplished through using a camera in tandem with weight sensors. Grocery items are identified using computer vision to avoid the tedium of manually inputting grocery information. With the data collected, a dashboard is generated with groceries currently on the scale …

Urban Planning Optimization Via “Cities: Skylines”, Carter Duncan, Jack Cunningham, Andrew Wang, Alexander Kennedy

Computer Science and Engineering Senior Theses

Artificial intelligence and machine learning have recently become a hot topic in terms of software solutions to complex problems. Every year, new prototypes and projects are created to solve specific problems, ranging from self-driving vehicles to facial recognition. One project which interested our team was OpenAI Five, which created an artificial intelligence agent to play the complex online competitive game DotA 2. We wanted to create our own agent to design optimized city layouts in the game Cities: Skylines. By doing so, we hope to illustrate the viability of using artificial intelligence as a tool in urban planning for real …

Stickars: Effortlessly Apply A Fun Overlay To The Real World, Théo Arrouye, Jackson Centeno, Morgan Fleshren, Vasilis Odysseos

Computer Science and Engineering Senior Theses

Augmented Reality (AR) technology has slowly seeped into the mainstream as many mobile phone manufacturers increasingly develop hardware and software that enable AR applications. While the technology has been available for the past few years, there are not many compelling AR applications available on mobile phones. Additionally, shared AR experiences are difficult to produce and share. In order to create a compelling AR application, we created StickARs, an iOS application that makes it easy to create and share AR experiences , by placing virtual stickers anywhere in the world.

StickARs allows users to choose from a predefined set of sticker …

Nicaragua Weather Application, Alexa Grau, Justin Ling, Greta Seitz

Computer Science and Engineering Senior Theses

ASDENIC is an organization that partners with local farmers and citizens in northern Nicaragua to provide resources and information to ensure the safety of residents and optimize agricultural techniques. Currently, a singular, localized weather station collects useful information on patterns that can be used for indicators, yet the data requires manual processing and there is not a system in place to report the findings. The current method of information transfer is in person during weekly meetings which can be ineffective and inconsistent.

In continuation of a previous project focused on sharing water quality information, our mobile application acts as a …

Understanding Covid-19 Public Sentiment Towards Public Health Policies Using Social Media Data, Olivia Figueira, Yuka Hatori, Liying Liang, Christine Chye

Computer Science and Engineering Senior Theses

With the outbreak of the COVID-19 pandemic, an overabundance of information related to the virus was released through social media. While more information can ultimately help people learn about the virus and how to protect themselves from it, there has been a lack of uniformity amongst individual states and the federal government in regards to policies and health guidelines (69), which may lead to the public being confused on the best guidelines to follow. There has also been an ideological divide driven by political polarization in the US on how to respond to this pandemic, causing greater contention (17; 86; …

Jamming Attack Workaround Study, Soren Madsen, Jack Schoen

Interdisciplinary Design Senior Theses

The Internet of Things (IoT) is a fast growing industry with strong footholds in the smart home market featuring devices such as the Amazon Echo, Ring security cameras, smart TVs, and much more. However, it doesn’t stop there; the industrial sector has begun using smart devices for measurement, automated tasks, and time sensitive communication. Many of these devices have become reliant on WiFi technology and are vulnerable to attacks on the security of the protocols involved.

In this paper, we discuss the details of the deauthentication attack on WPA and WPA2 systems and propose a solution for detection and recovery …

Siheyuan, Andrea Horvath, Isabel Wu

Computer Science and Engineering Senior Theses

Learning Chinese as a second language often poses a challenge to students, and the extensive non-alphabetic script that accompanies it adds to the complexity of the language. It can take years for a student to feel comfortable writing with Chinese characters, and practice is a key component of this learning process. Most practice includes repetitive writing of the characters until the student memorizes the look and stroke order of a character, but this method could be improved with the addition of visuals and audio to enhance the learning experience. The stakeholders of this problem are students seeking to learn the …

Lightweight Speed Protocol, Zachary James Hardy

Computer Science and Engineering Senior Theses

In this project, we aimed to design and implement a network protocol, using existing C networking libraries as a foundational basis for expansion and elaboration. Our design, Lightweight Speed Protocol (LSP), aims to offer increased flexibility and adaptability for programmers utilizing our protocol compared to existing alternatives (such as TCP). LSP aims to offer these benefits by utilizing variable levels of encryption (specifiable by the programmer using our protocol) and customizable amounts of cache space to store these varying levels of encryption algorithms. In order to give developers as much flexibility as possible, we want to pass on to them …

Martha: Offline Streaming Media For Cameroonian Refugees, Sarah Ahmed, Marco Marenzi, Leila Scola

Computer Science and Engineering Senior Theses

MARTHA is a mobile application intended to deliver educational content to refugees from Cameroon currently residing in Nigeria. Refugees were forced to flee after advocating for educational freedom, so education is of utmost importance to those residing in these refugee camps. Parents want their children to benefit from learning general educational content, as well as vocational content which is important for social mobility. Our application will display files that can be followed at the users’ pace. While the project entails two phases, the final goal is to have a Raspberry Pi act as a server and local database, allowing local …

A Method For Monitoring Operating Equipment Effectiveness With The Internet Of Things And Big Data, Carl D. Hays Iii

Master's Theses

The purpose of this paper was to use the Overall Equipment Effectiveness productivity formula in plant manufacturing and convert it to measuring productivity for forklifts. Productivity for a forklift was defined as being available and picking up and moving containers at port locations in Seattle and Alaska. This research uses performance measures in plant manufacturing and applies them to mobile equipment in order to establish the most effective means of analyzing reliability and productivity. Using the Internet of Things to collect data on fifteen forklift trucks in three different locations, this data was then analyzed over a six-month period to …

Music For Me, Zachary Graber, William Henrion

Computer Science and Engineering Senior Theses

Music For Me is an online web application that enables users to compose improvised music alongside an AI. Users have an array of understandable, easy to use yet powerful options available to them. While previous AI-collaborative music improvisation tools exist, they are either limited in scope, with minimal structure and user customization or completely overwhelming with a large amount of provided options so as to be inaccessible except to those dedicated to learning the program. This web application provides an intersection between these two extremes, providing a pick-up and play model that allows for a rich improvisational experience while still …

Physically Based Rendering Techniques To Visualize Thin-Film Smoothed Particle Hydrodynamics Fluid Simulations, Aditya H. Prasad

Dartmouth College Undergraduate Theses

This thesis introduces a methodology and workflow I developed to visualize smoothed hydrodynamic particle based simulations for the research paper ’Thin-Film Smoothed Particle Hydrodynamics Fluid’ (2021), that I co-authored. I introduce a physically based rendering model which allows point cloud simulation data representing thin film fluids and bubbles to be rendered in a photorealistic manner. This includes simulating the optic phenomenon of thin-film interference and rendering the resulting iridescent patterns. The key to the model lies in the implementation of a physically based surface shader that accounts for the interference of infinitely many internally reflected rays in its bidirectional surface …

Object Manipulation With Modular Planar Tensegrity Robots, Maxine Perroni-Scharf

Dartmouth College Undergraduate Theses

This thesis explores the creation of a novel two-dimensional tensegrity-based mod- ular system. When individual planar modules are linked together, they form a larger tensegrity robot that can be used to achieve non-prehensile manipulation. The first half of this dissertation focuses on the study of preexisting types of tensegrity mod- ules and proposes different possible structures and arrangements of modules. The second half describes the construction and actuation of a modular 2D robot com- posed of planar three-bar tensegrity structures. We conclude that tensegrity modules are suitably adapted to object manipulation and propose a future extension of the modular 2D …

Learning Medical Materials From Radiography Images, Carson Molder, Benjamin Lowe, Justin Zhan

Computer Science and Computer Engineering Faculty Publications and Presentations

Deep learning models have been shown to be effective for material analysis, a subfield of computer vision, on natural images. In medicine, deep learning systems have been shown to more accurately analyze radiography images than algorithmic approaches and even experts. However, one major roadblock to applying deep learning-based material analysis on radiography images is a lack of material annotations accompanying image sets. To solve this, we first introduce an automated procedure to augment annotated radiography images into a set of material samples. Next, using a novel Siamese neural network that compares material sample pairs, called D-CNN, we demonstrate how to …

The Effects Of Artificial Intelligence On Competitive Sports, Qiyu Pu

School of Professional Studies

This Research thesis is to explore the application and impact of artificial intelligence in the field of competitive sports, discover the risks and problems in it, and discuss solutions. Nowadays, artificial intelligence has been applied to all walks of life, and the field of competitive sports is no exception, such as VR video technology, artificial intelligence for competition and player data analysis, artificial intelligence equipment to help players train, artificial intelligence to develop tactics, etc. But artificial intelligence has also brought about problems such as disrupting game viewing, making intellectual competitive sports meaningless, and threatening the status of industry practitioners. …