教学课程资源库 更多>>

关键词： Computer science   Transportation   Robots   Confidence   Engineers   Innovations   Braking systems   Trust   Passengers  

摘要： The numbers of autonomous vehicles are increasingly growing across America. From self-driving cars to driverless busses and shuttles, autonomous vehicles are here to stay. However, human willingness to use or accept autonomous vehicles is not keeping pace with the innovation. Human bias (trust) in the safety of autonomous vehicles can have negative impacts on whether people will accept them. This study examines whether demographics such as gender, age, education, or racial identity has an impact on the level of trust in five safety-critical systems of autonomous vehicles using the SC-TAM model as a framework. The study shows that both gender and age have an impact on the safety expectancy, perceived usefulness, and perceived ease of use of autonomous vehicles. Follow-on studies should examine whether other demographics also impact these areas.

关键词： Oncology   Biomedical engineering   Computer science  

关键词： Internet of Things   Software   Marine biology   Biological oceanography   Biology   Computer science   Web studies  

摘要： Although recent years portray an increase demand for Internet of Things (IoT) applications in aquatic setting, there is a lack of standardization in collecting and displaying these data to a wider set of audiences ranging from marine biologists, whale-watching companies and environmentalists. More flexible APIs and long-range data access are necessary, providing the facilitated remote access to the data, while reducing significantly the cost of fuel and time when obtaining the data from oceanic settings. The main goal of this thesis is to produce the robust back-end and an API for: (i) managing the IoT devices to be applied in aquatic setting; (ii) obtaining the status and the telemetry in real-time; and (iii) visualizing the collected data from IoT devices such as temperature, pressure, humidity, luminosity, GPS position, etc. The final product advances the state of the art in back-end development for collecting, storing and displaying larger datasets (e.g. collected telemetries, radio transmission data) in Single-page applications (SPAs). It will, moreover, use the latest back-end and front-end development techniques (e.g. ***, Laravel) while optimizing database querying, and providing the real-time access to the data on any device, and without the need of refreshing the page.

关键词： Computer science   Operations research  

摘要： Blockchain technology is defined as a decentralized, distributed ledger recording the origin of a digital asset and all of its updates without the need of any governing authority. In Supply-Chain Management, Blockchain can be used very effectively, leading to a more open and reliable supply chain. In recent years, different companies have begun to use blockchain to build blockchain-based supply chain solutions. Blockchain has been shown to help provide improved transparency across the supply chain. This research focuses on the supply chain management of medical devices and supplies using blockchain technology. These devices are manufactured by the authorized device manufacturers and are supplied to the different healthcare institutions on their demand. This entire process becomes vulnerable as there is no track of individual product once it gets shipped till it gets used. Traceability of medical devices in this scenario is hardly efficient and not trustworthy. To address this issue, the paper presents a blockchain-based solution to maintain the supply chain of medical devices. The solution provides a distributed environment that can track various medical treatments from production to use. The finished product is stored in the blockchain through its digital thread. Required details are added from time to time which records the entire virtual life-cycle of the medical device forming the digital thread. This digital thread adds traceability to the existing supply chain. Keeping track of devices also helps in returning the expired devices to the manufacturer for its recycling. This blockchain-based solution is mainly composed of two phases. Blockchain-based solution design, this involves the design of the blockchain network architecture, which constitutes the required smart contract. This phase is implemented using the secure network of Hyperledger Fabric (HLF). The next phase includes the deployment of the generated network over the Kubernetes to make the system scalab

关键词： Design   Decision making   Computer science   Web studies  

摘要： In this thesis, we address some of the challenges that the Intelligent Networking Automation (INA) paradigm poses. Our goal is to design schemes leveraging Machine Learning (ML) techniques to cope with situations that involve hard decision-making actions. The proposed solutions are data-driven and consist of an agent that operates at network elements such as routers, switches, or network servers. The data are gathered from realistic scenarios, either actual network deployments or emulated environments. To evaluate the enhancements that the designed schemes provide, we compare our solutions to non-intelligent ones. Additionally, we assess the trade-off between the obtained improvements and the computational costs of implementing the proposed mechanisms. Accordingly, this thesis tackles the challenges that four specific research problems present. The first topic addresses the problem of balancing traffic in dense Internet of Things (IoT) network scenarios where the end devices and the Base Stations (BSs) form complex networks. By applying ML techniques to discover patterns in the association between the end devices and the BSs, the proposed scheme can balance the traffic load in a IoT network to increase the packet delivery ratio and reduce the energy cost of data delivery. The second research topic proposes an intelligent congestion control for internet connections at edge network elements. The design includes a congestion predictor based on an Artificial Neural Network (ANN) and an Active Queue Management (AQM) parameter tuner. Similarly, the third research topic includes an intelligent solution to the inter-domain congestion. Different from second topic, this problem considers the preservation of the private network data by means of Federated Learning (FL), since network elements of several organizations participate in the intelligent process. Finally, the fourth research topic refers to a framework to efficiently gathering network telemetry (NT) data. The proposed

关键词： Medicine   Biology   Acoustics   Analytical chemistry   Artificial intelligence   Chemistry   Computer science   Medical imaging   Medical personnel   Optics  

摘要： Machine learning models are being deployed to biological and clinical settings, including here at Stanford, e.g. to analyze ultrasounds automatically or map ancestries from genomics data. However, machine learning models suffer from issues of reliability: even models with good test performance often fail in unpredictable ways when deployed to real-world settings. In this thesis, I present two frameworks for more reliable machine learning: one for supervised learning and one for unsupervised learning. In the case of supervised learning, I present Gradio (***), an open-source Python framework for interactively testing models on real-world data. Gradio is being used to run the first real-time clinical trial of a machine learning model in the Stanford Department of Dermatology, and has been used to validate models at Google, Siemens, Amazon, Mercy Hospital, and Harvard. In the thesis, I describe the core questions that led to the development of Gradio, and showcase applications that demonstrate the usefulness of the framework. I further describe a novel explanation method that we have developed that allows debugging of faulty models with Gradio. On the unsupervised side, I introduce the framework of contrastive datasets, which provides a more reliable way to find patterns in unlabeled data. Our framework is quite general and has been adopted for purposes such as denoising images and mapping ancestries of admixed populations. Together, these frameworks provide a way to do more reliable unsupervised and supervised machine learning.

关键词： Computer science   Robotics   Engineering   Artificial intelligence  

摘要： Autonomous mobile robots are finding increasing use in areas such as agriculture, environmental monitoring, and search. Most field robots are currently powered by batteries and therefore have limited energy budgets. As a result, these robots have to finish tasks or visit recharging stations before the batteries run out of power. Addressing these limitations by designing energy-aware robot navigation algorithms is gaining importance in order to improve the operation time, save the robot energy, and ensure task success. The research in this dissertation focuses on energy mapping and energy-aware path planning for field robots. Specifically, we identify and address two new challenges associated with energy-constrained robot planning: (1) With the energy constraint, robots may not be able to finish the mission with onboard power. The need to visit a recharging station to get recharged and then continue the mission adds to the complexity of designing planning algorithms. New algorithms with optimality or near-optimality guarantees are needed. (2) Path planning algorithms often require environment maps. However, there is a disconnect between theoretical results and real applications because of the difficulty of obtaining energy-cost maps for planning energy-optimal paths. Modeling ground robot energy consumption on rough terrains can be rather complex. Obtaining energy-cost maps in a practical setting has not been sufficiently addressed in the prior literature. Based on these challenges, we study two research problems: energy-aware coverage path planning, and energy mapping for navigation path planning to goal locations. In the energy-aware coverage planning problem, the goal is to plan paths for robots to visit every location of given environments. Prior work tends to plan a single path for the robot, assuming an unlimited energy budget. However, the energy constraint inhibits the robots to complete coverage in one iteration especially for large environments, whichcalls

关键词： Computer science   Mechanics  

摘要： Many real-world systems can be represented as networks and studied using graph theory. Brain graphs are widely used to analyze brain connectomes using graph theory. Electrophysiological data, tract-tracing, and MRI data have been used to extract functional brain graphs. This study analyzes the properties of brain graphs generated using a neural network simulator. Using a simulator solves the problems related to pre-processing, data acquisition, and length of time series which exist in extracting brain graphs using other data collection methods. Synaptic plasticity is an important part of the functioning and growth of a neural network, and spike-time-dependent plasticity (STDP) has emerged as one of the most widely used plasticity mechanisms due to its physiological realistic induction and evidence of its presence in vivo. This thesis presents the graphical analysis for a spatiotemporal neural dataset and compares the properties of the connectome with a random graph model of similar size. We implement different STDP algorithms and use STDP to refine a simulation equivalent to neuronal growth for 28 days in vitro. We analyze the effect of STDP on the network's connections and structural properties.

关键词： Artificial intelligence   Computer science   Literature  

摘要： Intelligent Narrative Technologies have changed storytelling by facilitating new types of story experiences, such as interactive stories. However, Intelligent Narrative Technologies also introduce a prohibitively high cost of authorship, which goes beyond the effort it takes to learn how to use new technology and tools. New technology replaces aspects of traditional human authoring with instructions and procedures. Evaluating the power of expressiveness in different storytelling approaches is similar to understanding the difference in utility between a hammer and a nail gun, or between Python and Assembly. This dissertation asks why such authorship is so difficult, and proposes a technique for making it easier. The three main contributions of this work are: (1) it provides an author-centric design model for intelligent narrative, positioning storytelling as the management of variations; (2) it introduces the Authorial Leverage (AL) framework, a means for evaluating the costs and benefits of interactive story authorship; and (3) it introduces a system designed to demonstrate the aforementioned concepts. The author-centric design model sees interactive stories as composed of constituent and supplementary events, as opposed to the traditional story-and- discourse model. This allows us to build interactive storytelling tools with greater authorial leverage. We describe one such system, called RoleModel.

关键词： Robotics   Engineering   Computer science  

摘要： There has been an increasing interest in visual sensors and vision-based solutions for single and multi-robot systems. Vision-based sensors, e.g., traditional RGB cameras, grant rich semantic information and accurate directional measurements at a relatively low cost; however, such sensors have two major drawbacks. They do not generally provide reliable depth estimates, and typically have a limited field of view. These limitations considerably increase the complexity of controlling multiagent systems. This thesis studies some of the underlying problems in vision-based multiagent control and mapping. The first contribution of this thesis is a method for restoring bearing rigidity in non-rigid networks of robots. We introduce means to determine which bearing measurements can improve bearing rigidity in non-rigid graphs and provide a greedy algorithm that restores rigidity in 2D with a minimum number of added edges. The focus of the second part is on the formation control problem using only bearing measurements. We address the control problem for consensus and formation control through non-smooth Lyapunov functions and differential inclusion. We provide a stability analysis for undirected graphs and investigate the derived controllers for directed graphs. We also introduce a newer notion of bearing persistence for pure bearing-based control in directed graphs. The third part is concerned with the bearing-only visual homing problem with a limited field of view sensor. In essence, this problem is a special case of the formation control problem where there is a single moving agent with fixed neighbors. We introduce a navigational vector field composed of two orthogonal vector fields that converges to the goal position and does not violate the field of view constraints. Our method does not require the landmarks' locations and is robust to the landmarks' tracking loss. The last part of this dissertation considers outlier detection in pose graphs for Structure from Motion (Sf